{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "7ba05a39",
   "metadata": {},
   "source": [
    "# Simulationsstudie: Diebstahlerkennung eines Autos in Echtzeit\n",
    "\n",
    "**Name:** Yann Ahlgrim  \n",
    "\n",
    "In dieser Simulationsstudie wird ein Modell entwickelt, das anhand von Fahrverhaltensdaten erkennt, ob ein anderer Fahrer als üblich am Steuer sitzt. Ziel ist es, eine Wahrscheinlichkeit für einen Fahrerwechsel zu schätzen und bei hoher Wahrscheinlichkeit eine Diebstahlwarnung auszugeben. Die Studie umfasst die Generierung einer synthetischen Grundgesamtheit, die Simulation der Data Scientist Perspektive und die Analyse der Modellgüte."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f04292ef",
   "metadata": {},
   "source": [
    "## Erzeugung der Grundgesamtheit"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a5fe9381",
   "metadata": {},
   "source": [
    "### Datengrundlage\n",
    "\n",
    "#### Erklärende Variablen:\n",
    "\n",
    "1. **Durchschnittsgeschwindigkeit (metrisch):**  \n",
    "   Die Werte verteilen sich natürlicherweise ungefähr normal um ca. 47 km/h (29 mph) mit großer Streuung. Aggressive Fahrer tendieren zu höheren Durchschnittsgeschwindigkeiten. Diese Variable ist erklärend, da ein anderer Fahrer oft abweichende Geschwindigkeitsprofile aufweist.  \n",
    "   → Die Verteilung basiert auf: [NHTSA 100-Car Naturalistic Driving Study](https://www.nhtsa.gov/sites/nhtsa.gov/files/100carmain.pdf)\n",
    "\n",
    "2. **Schaltverhalten (ordinal):**  \n",
    "   Charakteristisches Schaltmuster bei Handschaltgetrieben, insbesondere der Drehzahlbereich beim Hochschalten. Fahrer unterscheiden sich deutlich:  \n",
    "   - *frueh* (ökonomisches Fahren),  \n",
    "   - *normal*,  \n",
    "   - *spaet* (sportliches/aggressives Fahren).  \n",
    "   Diese Variable dürfte prädiktiv sein, da Schaltgewohnheiten fahrerspezifisch sind. Studien zeigen, dass sie zur Fahreridentifikation genutzt werden können.  \n",
    "   → Quelle: [Driver Identification Based on Gear Shift Events and Attention-Based Bidirectional Long Short-Term Memory for Manual Transmission System)](https://ieeexplore.ieee.org/document/10034086)\n",
    "\n",
    "3. **Harte Bremsmanöver (metrisch):**  \n",
    "   Anzahl starker Bremsvorgänge mit hoher Verzögerung (>0,3 g). Modellierung z.B. als Poisson-verteilte Zufallsvariable mit geringem Mittelwert (wenige Ereignisse pro 100 km). Harte Bremsmanöver korrelieren mit aggressiver Fahrweise und sind prädiktiv für Fahrerwechsel.  \n",
    "   → Quelle: [Tesla Safety Score Definition](https://www.findmyelectric.com/blog/tesla-safety-score-beta-explained)\n",
    "\n",
    "4. **Geschwindigkeitsüberschreitungen (ordinal, 3 Kategorien):**  \n",
    "   haeufigkeit bzw. Ausmaß, mit dem Tempolimits überschritten werden. Kategorisierung z.B. in:  \n",
    "   - *selten*,  \n",
    "   - *manchmal*,  \n",
    "   - *haeufig* zu schnell.  \n",
    "   Diese Variable ist prädiktiv, da ein fremder Fahrer oft ein anderes Risikoverhalten beim Speeding zeigt.\n",
    "   Laut einer AAA-Verkehrssicherheitsstudie geben nahezu 50 % der Fahrer an, auf Autobahnen im letzten Monat ~15 mph (~24 km/h) über dem Tempolimit gefahren zu sein.\n",
    "   → Quelle: [87 Percent of Drivers Engage in Unsafe Behaviors While Behind the Wheel](https://newsroom.aaa.com/2016/02/87-percent-of-drivers-engage-in-unsafe-behaviors-while-behind-the-wheel/)\n",
    "\n",
    "---\n",
    "\n",
    "#### Nicht erklärende Variablen:\n",
    "\n",
    "\n",
    "5. **Wetterbedingungen (nominal, 3 Kategorien):**  \n",
    "   - *trocken* (~70–75 %)  \n",
    "   - *nass* (~20–25 %)  \n",
    "   - *winterlich* (<5 %)  \n",
    "   → Modelliert als Multinomial. Kontextvariable.  \n",
    "\n",
    "6. **Fahrstrecke (metrisch):**  \n",
    "   Länge der Fahrt (z.B. lognormalverteilt um 16 km). Kontextvariable, nicht direkt erklärend.  \n",
    "   → Quelle: [Mobilität in Deutschland 2017 – Ergebnisbericht](https://www.bmv.de/SharedDocs/DE/Anlage/G/mid-ergebnisbericht.pdf)\n",
    "\n",
    "   \n",
    "7. **Straßentyp (nominal, 3 Kategorien):**  \n",
    "   - *Autobahn* (~30–33 %)  \n",
    "   - *Außerorts* (~43 %)  \n",
    "   - *Innerorts* (~24–27 %)  \n",
    "   → Modelliert als Multinomialverteilung. Kontextvariable ohne direkte Prädiktionswirkung.  \n",
    "   → Quelle: [Klimaschutzinstrumente im Verkehr](https://openumwelt.de/server/api/core/bitstreams/07bd23f9-ff0a-41e5-b89b-8d7baf0a5c36/content)\n",
    "\n",
    "8. **Wochentag (nominal, 2–3 Kategorien):**  \n",
    "   Z.B. *Werktag* vs *Wochenende* oder *Mo–Fr*, *Sa*, *So*. Modellierung als kategorische Variable. Kontextvariable.  \n",
    "   → Quelle: [Mobilität in Deutschland 2017 – Ergebnisbericht](https://www.bmv.de/SharedDocs/DE/Anlage/G/mid-ergebnisbericht.pdf)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1468207b",
   "metadata": {},
   "source": [
    "### Bibliotheken Imports"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "97ba29a9",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Import der benötigten Bibliotheken\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "from scipy.stats import norm, multinomial, poisson, lognorm, bernoulli\n",
    "import statsmodels.api as sm\n",
    "from statsmodels.stats.outliers_influence import variance_inflation_factor\n",
    "\n",
    "np.random.seed(11)\n",
    "N = 1_000_000"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "27947656",
   "metadata": {},
   "source": [
    "### Verteilungen der Variablen"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "61247da5",
   "metadata": {},
   "outputs": [],
   "source": [
    "# 1. Durchschnittsgeschwindigkeit (metrisch, normalverteilt)\n",
    "avg_speed = np.clip(np.random.normal(loc=47, scale=10, size=N), 10, 130)\n",
    "\n",
    "# 2. Schaltverhalten (ordinal, 3 Kategorien)\n",
    "shift_behavior = np.random.choice(['frueh', 'normal', 'spaet'], size=N, p=[0.4, 0.4, 0.2])\n",
    "\n",
    "# 3. Harte Bremsmanöver (metrisch, Poisson)\n",
    "hard_brakes = np.random.poisson(lam=2, size=N)\n",
    "\n",
    "# 4. Geschwindigkeitsüberschreitungen (ordinal, 3 Kategorien) – Abhängigkeit von avg_speed\n",
    "def softmax(x):\n",
    "    e_x = np.exp(x - np.max(x, axis=1, keepdims=True))\n",
    "    return e_x / e_x.sum(axis=1, keepdims=True)\n",
    "\n",
    "speed_scaled = (avg_speed - avg_speed.min()) / (avg_speed.max() - avg_speed.min())\n",
    "strength = 0.18\n",
    "logits = np.zeros((N, 3))\n",
    "logits[:, 0] = 1 - strength * speed_scaled   # selten\n",
    "logits[:, 1] = 1                            # manchmal\n",
    "logits[:, 2] = 1 + strength * speed_scaled   # haeufig\n",
    "probs = softmax(logits)\n",
    "speeding = [np.random.choice(['selten', 'manchmal', 'haeufig'], p=p) for p in probs]\n",
    "\n",
    "# 5. Wetterbedingungen (nominal, Kontext)\n",
    "weather = np.random.choice(['trocken', 'nass', 'winterlich'], size=N, p=[0.75, 0.2, 0.05])\n",
    "\n",
    "# 6. Fahrstrecke (metrisch, lognormal)\n",
    "mu, sigma = np.log(16), 0.7\n",
    "trip_distance = np.random.lognormal(mean=mu, sigma=sigma, size=N)\n",
    "\n",
    "# 7. Straßentyp (nominal, Kontext) – Abhängigkeit von trip_distance mit Softmax-Funktion\n",
    "# Skaliere trip_distance auf [0, 1]\n",
    "dist_scaled = (trip_distance - trip_distance.min()) / (trip_distance.max() - trip_distance.min())\n",
    "road_strength = 0.18\n",
    "road_logits = np.zeros((N, 3))\n",
    "road_logits[:, 0] = 1 - road_strength * dist_scaled   # Innerorts\n",
    "road_logits[:, 1] = 1                                # Außerorts\n",
    "road_logits[:, 2] = 1 + road_strength * dist_scaled   # Autobahn\n",
    "road_probs = softmax(road_logits)\n",
    "road_type = [np.random.choice(['Innerorts', 'Außerorts', 'Autobahn'], p=p) for p in road_probs]\n",
    "\n",
    "# 8. Wochentag (nominal, Kontext)\n",
    "weekday = np.random.choice(['Mo-Fr', 'Sa', 'So'], size=N, p=[0.7, 0.15, 0.15])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "defebcc1",
   "metadata": {},
   "source": [
    "### Zusammenführen der Daten in ein DataFrame"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "f8e0efb0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>avg_speed</th>\n",
       "      <th>shift_behavior</th>\n",
       "      <th>hard_brakes</th>\n",
       "      <th>speeding</th>\n",
       "      <th>weather</th>\n",
       "      <th>trip_distance</th>\n",
       "      <th>road_type</th>\n",
       "      <th>weekday</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>64.494547</td>\n",
       "      <td>frueh</td>\n",
       "      <td>2</td>\n",
       "      <td>manchmal</td>\n",
       "      <td>trocken</td>\n",
       "      <td>40.599949</td>\n",
       "      <td>Innerorts</td>\n",
       "      <td>Mo-Fr</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>44.139270</td>\n",
       "      <td>frueh</td>\n",
       "      <td>3</td>\n",
       "      <td>haeufig</td>\n",
       "      <td>trocken</td>\n",
       "      <td>15.881471</td>\n",
       "      <td>Autobahn</td>\n",
       "      <td>Mo-Fr</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>42.154349</td>\n",
       "      <td>spaet</td>\n",
       "      <td>2</td>\n",
       "      <td>selten</td>\n",
       "      <td>trocken</td>\n",
       "      <td>8.114740</td>\n",
       "      <td>Autobahn</td>\n",
       "      <td>Mo-Fr</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>20.466814</td>\n",
       "      <td>normal</td>\n",
       "      <td>5</td>\n",
       "      <td>haeufig</td>\n",
       "      <td>trocken</td>\n",
       "      <td>7.643579</td>\n",
       "      <td>Innerorts</td>\n",
       "      <td>Mo-Fr</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>46.917154</td>\n",
       "      <td>spaet</td>\n",
       "      <td>2</td>\n",
       "      <td>selten</td>\n",
       "      <td>trocken</td>\n",
       "      <td>9.675677</td>\n",
       "      <td>Außerorts</td>\n",
       "      <td>Mo-Fr</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   avg_speed shift_behavior  hard_brakes  speeding  weather  trip_distance  \\\n",
       "0  64.494547          frueh            2  manchmal  trocken      40.599949   \n",
       "1  44.139270          frueh            3   haeufig  trocken      15.881471   \n",
       "2  42.154349          spaet            2    selten  trocken       8.114740   \n",
       "3  20.466814         normal            5   haeufig  trocken       7.643579   \n",
       "4  46.917154          spaet            2    selten  trocken       9.675677   \n",
       "\n",
       "   road_type weekday  \n",
       "0  Innerorts   Mo-Fr  \n",
       "1   Autobahn   Mo-Fr  \n",
       "2   Autobahn   Mo-Fr  \n",
       "3  Innerorts   Mo-Fr  \n",
       "4  Außerorts   Mo-Fr  "
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.DataFrame({\n",
    "    'avg_speed': avg_speed,\n",
    "    'shift_behavior': shift_behavior,\n",
    "    'hard_brakes': hard_brakes,\n",
    "    'speeding': speeding,\n",
    "    'weather': weather,\n",
    "    'trip_distance': trip_distance,\n",
    "    'road_type': road_type,\n",
    "    'weekday': weekday\n",
    "})\n",
    "\n",
    "df.head()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f06e7c4d",
   "metadata": {},
   "source": [
    "### VIF der Abhängigkeiten prüfen (<5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "6bfb199a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Variance Inflation Factor (VIF) für ausgewählte Variabeln:\n",
      "            features  VIF Factor\n",
      "0          avg_speed    2.570716\n",
      "1  speeding_manchmal    1.819868\n",
      "2    speeding_selten    1.750848\n"
     ]
    }
   ],
   "source": [
    "vif = pd.DataFrame()\n",
    "columns = ['avg_speed', 'speeding']\n",
    "vif_df = pd.get_dummies(df[columns], drop_first=True)\n",
    "vif_df = vif_df.astype(float)\n",
    "vif['features'] = vif_df.columns\n",
    "vif['VIF Factor'] = [variance_inflation_factor(vif_df.values, i) for i in range(vif_df.shape[1])]\n",
    "vif = vif.sort_values('VIF Factor', ascending=False).reset_index(drop=True)\n",
    "print(\"\\nVariance Inflation Factor (VIF) für ausgewählte Variabeln:\")\n",
    "print(vif)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "1d3df64a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Variance Inflation Factor (VIF) für ausgewählte Variabeln:\n",
      "              features  VIF Factor\n",
      "0        trip_distance    1.677148\n",
      "1  road_type_Außerorts    1.342378\n",
      "2  road_type_Innerorts    1.334770\n"
     ]
    }
   ],
   "source": [
    "vif = pd.DataFrame()\n",
    "columns = ['road_type', 'trip_distance']\n",
    "vif_df = pd.get_dummies(df[columns], drop_first=True)\n",
    "vif_df = vif_df.astype(float)\n",
    "vif['features'] = vif_df.columns\n",
    "vif['VIF Factor'] = [variance_inflation_factor(vif_df.values, i) for i in range(vif_df.shape[1])]\n",
    "vif = vif.sort_values('VIF Factor', ascending=False).reset_index(drop=True)\n",
    "print(\"\\nVariance Inflation Factor (VIF) für ausgewählte Variabeln:\")\n",
    "print(vif)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "49045ee5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>avg_speed</th>\n",
       "      <th>shift_behavior</th>\n",
       "      <th>hard_brakes</th>\n",
       "      <th>speeding</th>\n",
       "      <th>weather</th>\n",
       "      <th>trip_distance</th>\n",
       "      <th>road_type</th>\n",
       "      <th>weekday</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>64.494547</td>\n",
       "      <td>frueh</td>\n",
       "      <td>2</td>\n",
       "      <td>manchmal</td>\n",
       "      <td>trocken</td>\n",
       "      <td>40.599949</td>\n",
       "      <td>Innerorts</td>\n",
       "      <td>Mo-Fr</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>44.139270</td>\n",
       "      <td>frueh</td>\n",
       "      <td>3</td>\n",
       "      <td>haeufig</td>\n",
       "      <td>trocken</td>\n",
       "      <td>15.881471</td>\n",
       "      <td>Autobahn</td>\n",
       "      <td>Mo-Fr</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>42.154349</td>\n",
       "      <td>spaet</td>\n",
       "      <td>2</td>\n",
       "      <td>selten</td>\n",
       "      <td>trocken</td>\n",
       "      <td>8.114740</td>\n",
       "      <td>Autobahn</td>\n",
       "      <td>Mo-Fr</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>20.466814</td>\n",
       "      <td>normal</td>\n",
       "      <td>5</td>\n",
       "      <td>haeufig</td>\n",
       "      <td>trocken</td>\n",
       "      <td>7.643579</td>\n",
       "      <td>Innerorts</td>\n",
       "      <td>Mo-Fr</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>46.917154</td>\n",
       "      <td>spaet</td>\n",
       "      <td>2</td>\n",
       "      <td>selten</td>\n",
       "      <td>trocken</td>\n",
       "      <td>9.675677</td>\n",
       "      <td>Außerorts</td>\n",
       "      <td>Mo-Fr</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   avg_speed shift_behavior  hard_brakes  speeding  weather  trip_distance  \\\n",
       "0  64.494547          frueh            2  manchmal  trocken      40.599949   \n",
       "1  44.139270          frueh            3   haeufig  trocken      15.881471   \n",
       "2  42.154349          spaet            2    selten  trocken       8.114740   \n",
       "3  20.466814         normal            5   haeufig  trocken       7.643579   \n",
       "4  46.917154          spaet            2    selten  trocken       9.675677   \n",
       "\n",
       "   road_type weekday  \n",
       "0  Innerorts   Mo-Fr  \n",
       "1   Autobahn   Mo-Fr  \n",
       "2   Autobahn   Mo-Fr  \n",
       "3  Innerorts   Mo-Fr  \n",
       "4  Außerorts   Mo-Fr  "
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d27de9c5",
   "metadata": {},
   "source": [
    "### Dummies erzeugen"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "4ad287b1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>const</th>\n",
       "      <th>avg_speed</th>\n",
       "      <th>hard_brakes</th>\n",
       "      <th>trip_distance</th>\n",
       "      <th>shift_frueh</th>\n",
       "      <th>shift_normal</th>\n",
       "      <th>shift_spaet</th>\n",
       "      <th>speeding_haeufig</th>\n",
       "      <th>speeding_manchmal</th>\n",
       "      <th>speeding_selten</th>\n",
       "      <th>weather_nass</th>\n",
       "      <th>weather_trocken</th>\n",
       "      <th>weather_winterlich</th>\n",
       "      <th>road_Autobahn</th>\n",
       "      <th>road_Außerorts</th>\n",
       "      <th>road_Innerorts</th>\n",
       "      <th>weekday_Mo-Fr</th>\n",
       "      <th>weekday_Sa</th>\n",
       "      <th>weekday_So</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.0</td>\n",
       "      <td>64.494547</td>\n",
       "      <td>2.0</td>\n",
       "      <td>40.599949</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1.0</td>\n",
       "      <td>44.139270</td>\n",
       "      <td>3.0</td>\n",
       "      <td>15.881471</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.0</td>\n",
       "      <td>42.154349</td>\n",
       "      <td>2.0</td>\n",
       "      <td>8.114740</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1.0</td>\n",
       "      <td>20.466814</td>\n",
       "      <td>5.0</td>\n",
       "      <td>7.643579</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1.0</td>\n",
       "      <td>46.917154</td>\n",
       "      <td>2.0</td>\n",
       "      <td>9.675677</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   const  avg_speed  hard_brakes  trip_distance  shift_frueh  shift_normal  \\\n",
       "0    1.0  64.494547          2.0      40.599949          1.0           0.0   \n",
       "1    1.0  44.139270          3.0      15.881471          1.0           0.0   \n",
       "2    1.0  42.154349          2.0       8.114740          0.0           0.0   \n",
       "3    1.0  20.466814          5.0       7.643579          0.0           1.0   \n",
       "4    1.0  46.917154          2.0       9.675677          0.0           0.0   \n",
       "\n",
       "   shift_spaet  speeding_haeufig  speeding_manchmal  speeding_selten  \\\n",
       "0          0.0               0.0                1.0              0.0   \n",
       "1          0.0               1.0                0.0              0.0   \n",
       "2          1.0               0.0                0.0              1.0   \n",
       "3          0.0               1.0                0.0              0.0   \n",
       "4          1.0               0.0                0.0              1.0   \n",
       "\n",
       "   weather_nass  weather_trocken  weather_winterlich  road_Autobahn  \\\n",
       "0           0.0              1.0                 0.0            0.0   \n",
       "1           0.0              1.0                 0.0            1.0   \n",
       "2           0.0              1.0                 0.0            1.0   \n",
       "3           0.0              1.0                 0.0            0.0   \n",
       "4           0.0              1.0                 0.0            0.0   \n",
       "\n",
       "   road_Außerorts  road_Innerorts  weekday_Mo-Fr  weekday_Sa  weekday_So  \n",
       "0             0.0             1.0            1.0         0.0         0.0  \n",
       "1             0.0             0.0            1.0         0.0         0.0  \n",
       "2             0.0             0.0            1.0         0.0         0.0  \n",
       "3             0.0             1.0            1.0         0.0         0.0  \n",
       "4             1.0             0.0            1.0         0.0         0.0  "
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "shift_dummies = pd.get_dummies(shift_behavior, prefix='shift')\n",
    "speeding_dummies = pd.get_dummies(speeding, prefix='speeding')\n",
    "weather_dummies = pd.get_dummies(weather, prefix='weather')\n",
    "road_dummies = pd.get_dummies(road_type, prefix='road')\n",
    "weekday_dummies = pd.get_dummies(weekday, prefix='weekday')\n",
    "\n",
    "X = pd.DataFrame({\n",
    "    'const': np.ones(N),  # fuer konstante\n",
    "    'avg_speed': avg_speed,\n",
    "    'hard_brakes': hard_brakes,\n",
    "    'trip_distance': trip_distance\n",
    "})\n",
    "X = pd.concat([X, shift_dummies, speeding_dummies, weather_dummies, road_dummies, weekday_dummies], axis=1)\n",
    "\n",
    "X = X.astype(float)\n",
    "\n",
    "X.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1f6ee727",
   "metadata": {},
   "source": [
    "### Zielvariable erzeugen"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "75318d77",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Anzahl Diebstähle: 301381\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "betas = np.array([\n",
    "    -2,        # konstante\n",
    "    0.015,     # avg_speed (erklärend)\n",
    "    0.1,       # hard_brakes (erklärend)\n",
    "    0.,        # trip_distance\n",
    "    -0.3,      # shift_normal (erklärend) - frueh dropped\n",
    "    0.5,       # shift_spaet (erklärend)\n",
    "    -0.3,      # speeding_manchmal (erklärend) - selten dropped\n",
    "    0.5,       # speeding_haeufig (erklärend)\n",
    "    0.,        # weather_trocken - nass dropped\n",
    "    0.,        # weather_winterlich\n",
    "    0.,        # road_Außerorts - Autobahn dropped\n",
    "    0.,        # road_Innerorts\n",
    "    0.,        # weekday_Sa - Mo-Fr dropped\n",
    "    0.         # weekday_So\n",
    "])\n",
    "\n",
    "# Sicherstellen, dass die Dimension passt\n",
    "X_model = X.iloc[:, :len(betas)]\n",
    "\n",
    "X_model = X_model.astype(float)\n",
    "rauschen = np.random.normal(0, 0.2, size=N)\n",
    "\n",
    "# Linearkombination + Rauschen\n",
    "lin_comb = X_model.values @ betas + rauschen\n",
    "\n",
    "# Logistische Funktion\n",
    "pi = 1 / (1 + np.exp(-lin_comb))\n",
    "\n",
    "# Zielvariable simulieren\n",
    "target = np.random.binomial(1, pi)\n",
    "\n",
    "print(\"Anzahl Diebstähle:\", np.sum(target))\n",
    "\n",
    "plt.figure(figsize=(10, 6))\n",
    "sns.countplot(x=target, palette='viridis')\n",
    "plt.title('Verteilung der Zielvariable (Diebstahl: ja/nein)')\n",
    "plt.xlabel('Diebstahl')\n",
    "plt.ylabel('Anzahl')\n",
    "plt.xticks([0, 1], ['Nein', 'Ja'])\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "76948d4a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Mittelwert der pi-Werte: 0.3013\n",
      "Standardabweichung der pi-Werte: 0.1115\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Verteilung der pi-Werte\n",
    "mean_pi = np.mean(pi)\n",
    "std_pi = np.std(pi)\n",
    "print(f\"Mittelwert der pi-Werte: {mean_pi:.4f}\")\n",
    "print(f\"Standardabweichung der pi-Werte: {std_pi:.4f}\")\n",
    "\n",
    "plt.figure(figsize=(10, 6))\n",
    "sns.histplot(pi, bins=50, kde=True, color='blue')\n",
    "plt.title('Verteilung der pi-Werte')\n",
    "plt.xlabel('pi-Werte')\n",
    "plt.ylabel('Häufigkeit')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "825cc812",
   "metadata": {},
   "source": [
    "### Verteilungen der Variablen\n",
    "\n",
    "- **Durchschnittsgeschwindigkeit (`avg_speed`)**: normalverteilt mit Mittelwert 47 km/h und Standardabweichung 10, begrenzt auf den Bereich [10, 130].\n",
    "- **Schaltverhalten (`shift_behavior`)**: ordinal skaliert mit 3 Kategorien, gezogen aus einer Multinomialverteilung (Wahrscheinlichkeiten: 40% früh, 40% normal, 20% spät).\n",
    "- **Harte Bremsmanöver (`hard_brakes`)**: metrisch, modelliert mit einer Poisson-Verteilung (λ = 2).\n",
    "- **Geschwindigkeitsüberschreitungen (`speeding`)**: ordinal skaliert mit 3 Stufen, abhängig von `avg_speed` über eine Softmax-basierte Wahrscheinlichkeitsverteilung.\n",
    "- **Wetterbedingungen (`weather`)**: nominal skaliert, zufällig verteilt mit 75% trocken, 20% nass und 5% winterlich.\n",
    "- **Fahrstrecke (`trip_distance`)**: lognormal verteilt mit μ = ln(12) und σ = 0.7.\n",
    "- **Straßentyp (`road_type`)**: abhängig von `trip_distance`, mit kategorialer Softmax-Verteilung (Innerorts, Außerorts, Autobahn).\n",
    "- **Wochentag (`weekday`)**: nominal mit festgelegter Verteilung (70% Werktage, je 15% Samstag und Sonntag).\n",
    "\n",
    "### Modellierte Abhängigkeiten\n",
    "\n",
    "Die Variablen `speeding` und `road_type` wurden nicht rein zufällig erzeugt, sondern basieren auf skalierter Eingangsvariablen - `avg_speed` bzw. `trip_distance` - und einem gewichteten Softmax-Verfahren für realistischere Zusammenhänge.\n",
    "\n",
    "### Zielvariable und 𝑝ᵢ-Werte\n",
    "\n",
    "Die Zielvariable, die eine Diebstahlwahrscheinlichkeit beschreibt, wurde aus diesen Features modelliert. Die 𝑝ᵢ-Werte repräsentieren dabei individuelle Wahrscheinlichkeiten für Fahrerwechsel und wurden anhand von Beta-Verteilungen erzeugt.\n",
    "\n",
    "### Wahl und Begründung der Beta-Werte\n",
    "\n",
    "Die Beta-Gewichte wurden bewusst so gewählt, dass sie realistische Zusammenhänge zwischen den Merkmalen und dem Auftreten eines möglichen Diebstahls modellieren, ohne die Zielvariable künstlich zu verzerren. Das Ziel war ein realistischer, aber nicht übermäßig häufiger positiver Klassenanteil.\n",
    "\n",
    "- **Konstante (-2):** Sorgt für eine niedrige Grundwahrscheinlichkeit für Diebstahl, wenn keine auffälligen Merkmale vorliegen. Dadurch bleibt die Zielvariable realistisch balanciert.\n",
    "- **avg_speed (0.015):** Ein leicht positiver Zusammenhang, da eine ungewöhnlich hohe Durchschnittsgeschwindigkeit auf einen anderen Fahrstil und damit auf einen möglichen Fahrerwechsel hindeuten kann.\n",
    "- **hard_brakes (0.1):** Ein deutlicher positiver Effekt, da häufige harte Bremsmanöver ein Indiz für einen ungewohnten oder riskanten Fahrstil sind, der auf einen Fahrerwechsel hindeuten kann.\n",
    "- **trip_distance (0):** Kein Einfluss, da die reine Fahrstrecke keine Aussage über den Fahrerwechsel zulässt.\n",
    "- **shift_frueh (-0.3), shift_normal (-0.3), shift_spaet (0.5):** Das Schaltverhalten ist ein starker Prädiktor für den Fahrer. Besonders „spät“ schalten wird mit einem hohen positiven Beta gewichtet, da es einen aggressiveren Fahrstil beschreibt. „Früh“ und „normal“ schalten erhalten einen negativen Einfluss, da sie auf einen defensiveren oder gewohnten Fahrstil hindeuten.\n",
    "- **speeding_selten (-0.3), speeding_manchmal (-0.3), speeding_haeufig (0.5):** Die Häufigkeit von Geschwindigkeitsüberschreitungen ist ein wichtiger Indikator für den Fahrstil. Besonders „häufig“ zu schnell fahren (0.5) ist ein starkes Signal für einen Fahrerwechsel, da dies ein sehr auffälliges Verhalten ist. „Selten“ und „manchmal“ werden negativ gewichtet, da sie auf einen defensiveren Fahrstil hindeuten.\n",
    "- **weather_nass, weather_trocken, weather_winterlich (je 0):** Wetterbedingungen haben keinen Einfluss auf die Wahrscheinlichkeit eines Fahrerwechsels, da sie unabhängig vom Fahrer sind.\n",
    "- **road_Außerorts, road_Autobahn, road_Innerorts (je 0):** Der Straßentyp ist nicht prädiktiv für einen Fahrerwechsel, da er nicht vom Fahrverhalten abhängt.\n",
    "- **weekday_Mo-Fr, weekday_Sa, weekday_So (je 0):** Der Wochentag hat keinen Einfluss auf die Wahrscheinlichkeit eines Fahrerwechsels.\n",
    "\n",
    "\n",
    "Alle Beta-Werte wurden bewusst reduziert (unterhalb von 0.1), um eine Übergewichtung einzelner Faktoren zu vermeiden und die Zielvariable `Diebstahl` in einem nahe zu realistischen Bereich zu halten. Eine stärkere Gewichtung hätte zu einer zu häufigen Klassifikation als Diebstahl geführt.\n",
    "\n",
    "```visualisierung\n",
    "Die grafische Darstellung zeigt, dass rund 20 % der Fahrten als potenzielle Diebstähle klassifiziert wurden - ein geeignetes Trainingsverhältnis für ein Klassifikationsmodell.\n",
    "```\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "adbc166b",
   "metadata": {},
   "source": [
    "## Simulation der Perspektive des Data Scientist"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f8abd5f5",
   "metadata": {},
   "source": [
    "### Stichprobe entnehmen"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "706ff5c6",
   "metadata": {},
   "outputs": [],
   "source": [
    "sample_size = 20_000\n",
    "sample_indices = np.random.choice(X.index, size=sample_size, replace=False)\n",
    "X_sample = X.loc[sample_indices]\n",
    "target_sample = target[sample_indices]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9b67610e",
   "metadata": {},
   "source": [
    "### Datenexploration und -vorverarbeitung\n",
    "\n",
    "Zunächst verschafft sich der Data Scientist einen Überblick über die Stichprobe, prüft die Verteilung der Zielvariable und der erklärenden Variablen, erkennt potenzielle Ausreißer und prüft auf fehlende Werte. Außerdem werden die Variablentypen für die Modellierung vorbereitet (z.B. One-Hot-Encoding für kategoriale Variablen)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "9f12d325",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Form der Stichprobe: (20000, 19)\n",
      "Anteil Zielvariable (Diebstahl):\n",
      "0    0.6959\n",
      "1    0.3041\n",
      "dtype: float64\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>const</th>\n",
       "      <th>avg_speed</th>\n",
       "      <th>hard_brakes</th>\n",
       "      <th>trip_distance</th>\n",
       "      <th>shift_frueh</th>\n",
       "      <th>shift_normal</th>\n",
       "      <th>shift_spaet</th>\n",
       "      <th>speeding_haeufig</th>\n",
       "      <th>speeding_manchmal</th>\n",
       "      <th>speeding_selten</th>\n",
       "      <th>weather_nass</th>\n",
       "      <th>weather_trocken</th>\n",
       "      <th>weather_winterlich</th>\n",
       "      <th>road_Autobahn</th>\n",
       "      <th>road_Außerorts</th>\n",
       "      <th>road_Innerorts</th>\n",
       "      <th>weekday_Mo-Fr</th>\n",
       "      <th>weekday_Sa</th>\n",
       "      <th>weekday_So</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>20000.0</td>\n",
       "      <td>20000.000000</td>\n",
       "      <td>20000.000000</td>\n",
       "      <td>20000.000000</td>\n",
       "      <td>20000.000000</td>\n",
       "      <td>20000.000000</td>\n",
       "      <td>20000.000000</td>\n",
       "      <td>20000.000000</td>\n",
       "      <td>20000.000000</td>\n",
       "      <td>20000.000000</td>\n",
       "      <td>20000.000000</td>\n",
       "      <td>20000.000000</td>\n",
       "      <td>20000.000000</td>\n",
       "      <td>20000.000000</td>\n",
       "      <td>20000.000000</td>\n",
       "      <td>20000.000000</td>\n",
       "      <td>20000.000000</td>\n",
       "      <td>20000.000000</td>\n",
       "      <td>20000.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>1.0</td>\n",
       "      <td>46.955431</td>\n",
       "      <td>1.987300</td>\n",
       "      <td>20.400866</td>\n",
       "      <td>0.396750</td>\n",
       "      <td>0.405100</td>\n",
       "      <td>0.198150</td>\n",
       "      <td>0.365450</td>\n",
       "      <td>0.328300</td>\n",
       "      <td>0.306250</td>\n",
       "      <td>0.198100</td>\n",
       "      <td>0.753000</td>\n",
       "      <td>0.048900</td>\n",
       "      <td>0.339150</td>\n",
       "      <td>0.334750</td>\n",
       "      <td>0.326100</td>\n",
       "      <td>0.699600</td>\n",
       "      <td>0.147950</td>\n",
       "      <td>0.152450</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>0.0</td>\n",
       "      <td>9.983939</td>\n",
       "      <td>1.406321</td>\n",
       "      <td>16.370594</td>\n",
       "      <td>0.489236</td>\n",
       "      <td>0.490924</td>\n",
       "      <td>0.398616</td>\n",
       "      <td>0.481568</td>\n",
       "      <td>0.469606</td>\n",
       "      <td>0.460946</td>\n",
       "      <td>0.398578</td>\n",
       "      <td>0.431278</td>\n",
       "      <td>0.215664</td>\n",
       "      <td>0.473433</td>\n",
       "      <td>0.471915</td>\n",
       "      <td>0.468796</td>\n",
       "      <td>0.458443</td>\n",
       "      <td>0.355059</td>\n",
       "      <td>0.359466</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.0</td>\n",
       "      <td>10.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.019350</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>1.0</td>\n",
       "      <td>40.210704</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>9.923435</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>1.0</td>\n",
       "      <td>46.933676</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>15.896143</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>1.0</td>\n",
       "      <td>53.726714</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>25.538578</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>1.0</td>\n",
       "      <td>81.665638</td>\n",
       "      <td>10.000000</td>\n",
       "      <td>228.850160</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         const     avg_speed   hard_brakes  trip_distance   shift_frueh  \\\n",
       "count  20000.0  20000.000000  20000.000000   20000.000000  20000.000000   \n",
       "mean       1.0     46.955431      1.987300      20.400866      0.396750   \n",
       "std        0.0      9.983939      1.406321      16.370594      0.489236   \n",
       "min        1.0     10.000000      0.000000       1.019350      0.000000   \n",
       "25%        1.0     40.210704      1.000000       9.923435      0.000000   \n",
       "50%        1.0     46.933676      2.000000      15.896143      0.000000   \n",
       "75%        1.0     53.726714      3.000000      25.538578      1.000000   \n",
       "max        1.0     81.665638     10.000000     228.850160      1.000000   \n",
       "\n",
       "       shift_normal   shift_spaet  speeding_haeufig  speeding_manchmal  \\\n",
       "count  20000.000000  20000.000000      20000.000000       20000.000000   \n",
       "mean       0.405100      0.198150          0.365450           0.328300   \n",
       "std        0.490924      0.398616          0.481568           0.469606   \n",
       "min        0.000000      0.000000          0.000000           0.000000   \n",
       "25%        0.000000      0.000000          0.000000           0.000000   \n",
       "50%        0.000000      0.000000          0.000000           0.000000   \n",
       "75%        1.000000      0.000000          1.000000           1.000000   \n",
       "max        1.000000      1.000000          1.000000           1.000000   \n",
       "\n",
       "       speeding_selten  weather_nass  weather_trocken  weather_winterlich  \\\n",
       "count     20000.000000  20000.000000     20000.000000        20000.000000   \n",
       "mean          0.306250      0.198100         0.753000            0.048900   \n",
       "std           0.460946      0.398578         0.431278            0.215664   \n",
       "min           0.000000      0.000000         0.000000            0.000000   \n",
       "25%           0.000000      0.000000         1.000000            0.000000   \n",
       "50%           0.000000      0.000000         1.000000            0.000000   \n",
       "75%           1.000000      0.000000         1.000000            0.000000   \n",
       "max           1.000000      1.000000         1.000000            1.000000   \n",
       "\n",
       "       road_Autobahn  road_Außerorts  road_Innerorts  weekday_Mo-Fr  \\\n",
       "count   20000.000000    20000.000000    20000.000000   20000.000000   \n",
       "mean        0.339150        0.334750        0.326100       0.699600   \n",
       "std         0.473433        0.471915        0.468796       0.458443   \n",
       "min         0.000000        0.000000        0.000000       0.000000   \n",
       "25%         0.000000        0.000000        0.000000       0.000000   \n",
       "50%         0.000000        0.000000        0.000000       1.000000   \n",
       "75%         1.000000        1.000000        1.000000       1.000000   \n",
       "max         1.000000        1.000000        1.000000       1.000000   \n",
       "\n",
       "         weekday_Sa    weekday_So  \n",
       "count  20000.000000  20000.000000  \n",
       "mean       0.147950      0.152450  \n",
       "std        0.355059      0.359466  \n",
       "min        0.000000      0.000000  \n",
       "25%        0.000000      0.000000  \n",
       "50%        0.000000      0.000000  \n",
       "75%        0.000000      0.000000  \n",
       "max        1.000000      1.000000  "
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Überblick über die Stichprobe\n",
    "print(\"Form der Stichprobe:\", X_sample.shape)\n",
    "print(\"Anteil Zielvariable (Diebstahl):\")\n",
    "print(pd.Series(target_sample).value_counts(normalize=True))\n",
    "\n",
    "# Merkmale\n",
    "X_sample.describe(include='all')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "30bfcdde",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Fehlende Werte pro Spalte:\n",
      "const                 0\n",
      "avg_speed             0\n",
      "hard_brakes           0\n",
      "trip_distance         0\n",
      "shift_frueh           0\n",
      "shift_normal          0\n",
      "shift_spaet           0\n",
      "speeding_haeufig      0\n",
      "speeding_manchmal     0\n",
      "speeding_selten       0\n",
      "weather_nass          0\n",
      "weather_trocken       0\n",
      "weather_winterlich    0\n",
      "road_Autobahn         0\n",
      "road_Außerorts        0\n",
      "road_Innerorts        0\n",
      "weekday_Mo-Fr         0\n",
      "weekday_Sa            0\n",
      "weekday_So            0\n",
      "dtype: int64\n"
     ]
    }
   ],
   "source": [
    "# Prüfung auf fehlende Werte\n",
    "print(\"Fehlende Werte pro Spalte:\")\n",
    "print(X_sample.isnull().sum())"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "201bca58",
   "metadata": {},
   "source": [
    "### Feature Engineering\n",
    "\n",
    "Für die Modellierung werden kategoriale Variablen in numerische Dummy-Variablen umgewandelt. Dies ist notwendig, damit die Regressionsmodelle die Informationen nutzen können. In unserem Fall sind die kategorischen Variablen schon aus dem vorherigen Schritt One-Hot Encoded, weil wir aus den Variablen das logistische Regressionsproblem erstellt haben. Außerdem werden die Daten normalerweise in Trainings- und Testdaten aufgeteilt, jedoch habe ich mich hier nicht dazu entschieden weil 20.000 Instanzen wenig ist zum Trainieren und es die Aufgabe nicht vorgibt. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "b71ab517",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Trainingsdaten: (20000, 19)\n"
     ]
    }
   ],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "# Zielvariable\n",
    "y = target_sample\n",
    "\n",
    "# One-Hot-Encoding für kategoriale Variablen\n",
    "# X_encoded = pd.get_dummies(X_sample)\n",
    "\n",
    "# Aufteilung in Trainings- und Testdaten\n",
    "# X_train, X_test, y_train, y_test = train_test_split(X_encoded, y, test_size=0.3, random_state=42)\n",
    "X_train = X_sample\n",
    "y_train = y\n",
    "print(\"Trainingsdaten:\", X_train.shape)\n",
    "# print(\"Testdaten:\", X_test.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "103a8399",
   "metadata": {},
   "source": [
    "### Visualisierung der Variablen"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d423f20f",
   "metadata": {},
   "source": [
    "Um weiteres Verständnis über den Datensatz zu bekommen, visualisieren wir nun die Variablen. Kategorische Variablen werden als Balkendiagramme dargestellt, weil wir eine Anzahl diskreter Werte haben und Metrische Variablen werden in Histogrammen veranschaulicht, um die Verteilung dieser zu erkennen."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "b748cb80",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABdEAAAPdCAYAAABlRyFLAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy88F64QAAAACXBIWXMAAA9hAAAPYQGoP6dpAAEAAElEQVR4nOzdf1hUdd7/8dfEjxEIR8FgJDGpiDQwvbUQbVddETWRXO9yi5p0c9VuTSM1y2wLK6Gs1IIyI1ITjfbestRqEtpi11WUKCrNtfpm/igQb8PBXwHi+f7hxcnhh6GCYD4f1zXX5ZzznnM+nzMzvpn3fObzsRiGYQgAAAAAAAAAANRxUUs3AAAAAAAAAACA1ooiOgAAAAAAAAAADaCIDgAAAAAAAABAAyiiAwAAAAAAAADQAIroAAAAAAAAAAA0gCI6AAAAAAAAAAANoIgOAAAAAAAAAEADKKIDAAAAAAAAANAAiugAAAAAAAAAADSAIvp56Pnnn5fFYlFkZGRLN8VNcnKyLBaL/u///u9XY7t06aKxY8ee8bksFouSk5PP+PGN8c4778hiseill15qMCYnJ0cWi0Xz589vknNaLBbdc889TXKsC8lnn32m/v37y2azyWKxaOHChZKk77//XhaLRc8884wk6eKLLz6r193paOxzuXTpUlksFn3//fdu2x9++GF17txZnp6eateunY4cOaLk5GR9/PHHjTp/Td9rbl5eXgoMDNR1112n++67T1u3bj2DXrUeH3/8sSwWS6OvB3A2yLvkXbhrjXm3Nar9vmvJ3FVz7pqbt7e3LrnkEvXr10+zZ8/Wzp07z3mbmlJDf08B9SGvk9fh7kLN6++9916D74PW8Fo6OW97eHioffv2uvbaazVx4kTl5+e3aNvOVs1ra+nSpS3dlNPi2dINwOl79dVXJUlbt27Vpk2bFB0d3cIt+m0aPny47Ha7Xn31Vd199931xixZskReXl5yOBznuHU42V133aXDhw8rOztb7du3V5cuXSRJHTt21MaNG3XZZZdJkj766CMFBAS0YEvrGj58uDZu3KiOHTua29555x3NnTtXs2fP1rBhw2S1WnXkyBHNmTNHkjRgwIBGH3/KlClKTEzU8ePHdeDAAX322Wd69dVXlZaWptTUVN1///1N3aVz4r/+67+0ceNGdevWraWbggsAeffcIO+eP87nvNuSWkPuSklJ0cCBA1VdXa39+/dr06ZNevXVV7VgwQJlZGTo9ttvb7G2nY36/p4CGkJePzfI6+ePCzWvv/fee3rhhRea/Quls3HzzTdr+vTpMgxD5eXl2rJli1577TW9/PLLmjp1qp577rmWbuIZqXltXXHFFS3dlNPCSPTzzCeffKLPP/9cw4cPlyRlZma2cIvOf1VVVTp27Fid7Z6enrrzzjtVUFCgLVu21Nl/4MABrVq1SgkJCbrkkkvOqg1Hjx49q8df6LZs2aLY2FgNGzZMffr0kd1ulyRZrVb16dPH/EB13XXXNfo/6XP1nFxyySXq06ePrFarua3m9TZ16lT169dPvXv3PuPjd+7cWX369FHfvn114403avbs2dqyZYsGDx6smTNn6v333z/rPrSEtm3bqk+fPmrbtm1LNwW/ceTdpkfePf+dz3m3JbWG3BUeHq4+ffqoX79+SkhI0Ny5c7V161ZdffXVGjt2rL788ssWa9vZqO/vKaA+5PWmR14//5HXW0ZD752TBQcHq0+fPoqJidGQIUM0ffp0ffrpp7rrrrv0/PPPa9GiReeotU2r5rV1tu/9c40i+nmmJsk/+eST6tu3r7Kzs3XkyBG3mJN/cjN//nyFhYXp4osvVkxMjNtPPmpP91D7ViMnJ0c33XSTOnXqpDZt2ujKK6/UxIkTG/yZ2d69e3XbbbfJZrMpODhYd911l1wu1xn1t7y8XOPHj1dgYKAuvvhiDR06VF9//XW9sd98840SExMVFBQkq9Wqrl276oUXXnCLqfkp6/LlyzV9+nRdeumlslqt+vbbb+s95rhx4ySd+Ia8ttdff10///yz7rrrLknSzz//rFmzZiksLEze3t669NJLNXnyZB04cMDtcV26dFF8fLzeeust9ezZU23atDFHGNdmGIYeeugheXl5KSMjQ5J0/PhxzZs3T1dffbWsVquCgoJ05513as+ePW6PHTBggCIjI7Vx40b17dtXPj4+6tKli9mXd999V//1X/8lX19fRUVFyel0uj2+5ueEX3zxhW655RbZbDYFBARo2rRpOnbsmLZv366hQ4fK399fXbp00bx58+q0v7y8XDNmzHC7JklJSTp8+LBbXM1PpZYvX66uXbvK19dX1157rdauXVvvdalR89PdY8eOadGiRW6v3Zr2N/SYk3/uezrPiXTi527x8fHmay0kJETDhw+v8xxI+tU+1W5Ply5d9PDDD0s6kTAtFovGjh1rJpc5c+aY/TzTn9L5+PgoMzNTXl5eevrpp83tZ3LN1q5dq549e8rHx0ddu3Y1+7d06VJ17dpVfn5+uv766/XJJ5+4HXPs2LG6+OKL9Z///EdDhgyRn5+fOnbsqCeffFKSlJ+frxtuuEF+fn666qqrtGzZMrfHN/ST+E8++UQJCQkKCAhQmzZt1LNnT/3tb39zizly5Ij5umzTpo0CAgLUu3dvvf7666d9LfHbR94l75J3f9Ga825NnxYvXqyrrrpKVqtV3bp1U3Z2dp3jlZSUaOLEierUqZO8vb0VFhamOXPm1PkgW1lZqSeeeMJ87i+55BL9+c9/1r59+9ziqqqqNHPmTNntdvn6+uqGG27Q5s2b65y3vtxVkw+//fZb3Xjjjbr44osVGhqq6dOnq6Kiwu3xe/bs0c033yx/f3+1a9dOt99+uwoKCs7659ABAQFavHixjh07pgULFri1rWY04snqe65rrv+SJUsUEREhHx8f9e7dW/n5+TIMQ08//bT5f+Mf/vCHOv8HnO37p6HpXHJzczVo0CC1bdtWvr6+6tevnz788EO3mH379mnChAkKDQ01n+d+/fopNzf3dC8lzgPkdfI6ef0XLZHXX3jhBV100UUqLS01tz377LOyWCyaPHmyue348eNq3769pk+fbm5rbF5+4403FBcXp44dO5qfUx988EG36zZ27Fjz9X3y+7Z2HmnMNW2O986peHh4KD09XR06dHD7PN9QLqzv74+Wfn03NJ1LY67l8ePH9cQTT5h/b7Rr107du3c/N6PyDZw3jhw5YthsNuO6664zDMMwXnnlFUOSsXTpUre4HTt2GJKMLl26GEOHDjXefvtt4+233zaioqKM9u3bGwcOHDAMwzB+/vlnY+PGjW631atXG23btjW6du1qHm/RokVGamqqsXr1aiMvL89YtmyZce211xoRERFGZWWlGffoo48akoyIiAjjkUceMXJycoz58+cbVqvV+POf/+zWxssuu8wYM2bMKft7/PhxY+DAgYbVajXmzp1rrFu3znj00UeNyy+/3JBkPProo2bs1q1bDZvNZkRFRRmvvfaasW7dOmP69OnGRRddZCQnJ5txH330kSHJuPTSS42bb77ZWL16tbF27Vpj//79DbbjhhtuMIKCgtz6ahiGcd111xmXXnqpcezYMeP48ePGkCFDDE9PT+Ovf/2rsW7dOuOZZ54x/Pz8jJ49exo///yzW987duxoXH755carr75qfPTRR8bmzZsNwzAMScbkyZPN5+fWW281/P39jffff998/IQJEwxJxj333GM4nU7jpZdeMi655BIjNDTU2LdvnxnXv39/IzAw0IiIiDAyMzONDz74wIiPjzckGXPmzDGioqKM119/3XjvvfeMPn36GFar1fjhhx/qfT4ff/xxIycnx5g5c6Z57quvvtp4/vnnjZycHOPPf/6zIcl48803zccfPnzY6NGjh9GhQwdj/vz5Rm5urvHcc88ZNpvN+MMf/mAcP37cjK15vV5//fXG3/72N+O9994zBgwYYHh6ehr/7//9vwafm9LSUmPjxo2GJOPmm282X8cnt7+2JUuWGJKMHTt2NOo5qe3QoUNGYGCg0bt3b+Nvf/ubkZeXZ7zxxhvG3XffbXz11Ven3afa7fn000+NcePGGZIMp9NpbNy40fj+++8Np9NpSDLGjRtn9vPbb79t8NrU/D/w9NNPNxhT87xXVVWd0TXr1KmTERkZab6OoqOjDS8vL+ORRx4x+vXrZ7z11lvGqlWrjKuuusoIDg42jhw5Yj5+zJgxhre3t9G1a1fjueeec3sdzZo1y7jqqqvqvG4/+eQT8/E17+WPPvrI3PaPf/zD8Pb2Nn73u98Zb7zxhuF0Oo2xY8cakowlS5aYcRMnTjR8fX2N+fPnGx999JGxdu1a48knnzTS0tIavFa4MJF3ybuGQd49WWvPu6GhoUa3bt2M119/3Vi9erUxdOhQQ5Lxv//7v2ZccXGxERoaalx22WXG4sWLjdzcXOPxxx83rFarMXbsWDOuurraGDp0qOHn52fMmTPHyMnJMV555RXj0ksvNbp161Ynp1ksFuP+++831q1bZ8yfP9+49NJLjbZt27q97+rLXSfnw2eeecbIzc01HnnkEcNisRhz5sxxuw5XXnmlERAQYLzwwgvGBx98YNx3331GWFhYnTxXn5pzn3wtauvYsaNxxRVXuLXtsssuqxNX33MtybjsssuMvn37uuX/gIAA47777jNuuukmY+3atcaKFSuM4OBgo3v37m6vybN9/9T3Olu+fLlhsViMkSNHGm+99ZaxZs0aIz4+3vDw8DByc3PNuCFDhhiXXHKJ8fLLLxsff/yx8fbbbxuPPPKIkZ2dfcprivMPeZ28bhjk9ZO1RF7/z3/+Y0gyVq5caW4bOnSo4ePjY4SHh5vbNm3aZEgy3nvvPcMwTi8vP/7448aCBQuMd9991/j444+Nl156yQgLCzMGDhxoxnz77bfGzTffbEhyew/XvNYae02b871z8uu5Prfeeqshydi9e3eDz83J5z7574+Wfn3X/D978t8vjb2WqamphoeHh/Hoo48aH374oeF0Oo2FCxe6xTQXiujnkddee82QZLz00kuGYRjGwYMHjYsvvtj43e9+5xZX82KMiooyjh07Zm7fvHmzIcl4/fXX6z3+4cOHjeuvv97o2LGj8f3339cbc/z4caOqqsrYuXOnIcl45513zH01b6J58+a5PWbSpElGmzZt3P6Tb0zSf//99w1JxnPPPee2fe7cuXWS/pAhQ4xOnToZLpfLLfaee+4x2rRpY/z000+GYfzyn8fvf//7U577ZDX/Eb311lvmti1bthiSjNmzZxuGYZgFztp9f+ONNwxJxssvv+zWdw8PD2P79u11zlXzn+T+/fuNG264wbj00kuNoqIic/+2bdsMScakSZPcHleTYB566CFzW//+/esUHvfv3294eHgYPj4+bv8BFhUVGZKM559/3txW83w+++yzbufq0aNHnetRVVVlXHLJJcaoUaPMbampqcZFF11kFBQUuD3+73//u1syrOl3cHCwUV5ebm4rKSkxLrroIiM1NbXOdWroup3sdJN+Q89JbZ988okhyXj77bd/tU2N6VN97alp+8l/xO3bt6/O6/5UGlNE/9Of/mRIMvbu3et23toaumY+Pj7Gnj17zG01r6OOHTsahw8fNre//fbbhiRj9erV5rYxY8bUSaQ1ryNJxqeffmpur3ndTps2zdxW3x8CV199tdGzZ0/zS4Ea8fHxRseOHY3q6mrDMAwjMjLSGDlyZIPXBahB3j2BvEvebei6naw15F0fHx+jpKTE3Hbs2DHj6quvNq688kpz28SJE42LL77Y2Llzp9vjn3nmGUOSsXXrVsMwDOP111+vk6cMwzAKCgoMScaLL75oGMYvr5H77rvPLW7FihWGpEYV0SUZf/vb39wef+ONNxoRERHm/RdeeMGQ5FYIqulPUxXRo6OjDR8fH7e2nU4R3W63G4cOHTK31eT/Hj16uP1/tHDhQkOS8cUXX5jbzvb9U/t1dvjwYSMgIMAYMWKEWzurq6uNa6+91rj++uvNbRdffLGRlJTU4HXBbwd5/QTyOnm9oet2subK64ZhGJ06dTLuuusuwzAMo6KiwvDz8zMeeOABQ5KZn+fOnWt4eXmZeaWxebm2mvdcXl6eIcn4/PPPzX2TJ0+ut4+G0fhr2pzvnV8rotdcs02bNhmGcfpF9JZ8fddXRG/stYyPjzd69OjR4HVpTkznch7JzMyUj4+Pbr31VkknVka+5ZZb9K9//UvffPNNnfjhw4fLw8PDvN+9e3dJ0s6dO+vEVldX609/+pO2bdum9957z1w4QpJKS0t19913KzQ0VJ6envLy8jL3b9u2rc6xEhIS3O53795dP//8s9vPdRrjo48+kqQ6CxwlJia63f/555/14Ycf6o9//KN8fX117Ngx83bjjTfq559/rrNy8X//9383uh2jR4+Wv7+/uQCNdGIxGovFoj//+c+SpH/84x+SVGd6jVtuuUV+fn51fjbavXt3XXXVVfWeb8eOHYqJiVF5ebny8/N17bXXmvtqrknt81x//fXq2rVrnfN07NhRvXr1Mu8HBAQoKChIPXr0UEhIiLm9a9eukup/bcTHx7vd79q1qywWi4YNG2Zu8/T01JVXXun2+LVr1yoyMlI9evRwe06GDBlS7zQcAwcOlL+/v3k/ODhYQUFB9bapOZzqOTnZlVdeqfbt2+uBBx7QSy+9pK+++qrB2Jbu068xDOOsHt+jRw9deuml5v2a19GAAQPk6+tbZ3vtflssFt14443m/ZrXUceOHdWzZ09ze83r9lTX7dtvv9V//vMf8/+L2v8PFBcXa/v27ZJOvF/ef/99Pfjgg/r444+Zrw8NIu+eQN4l7zaH5si7gwYNUnBwsHnfw8NDf/rTn/Ttt9+aP9Nfu3atBg4cqJCQELfrVHN98/LyzLh27dppxIgRbnE9evSQ3W43r2dD75vRo0fL09OzUdfCYrFoxIgRbtu6d+/u9lzk5eXJ399fQ4cOdYu77bbbGnWOxjjbvwsGDhwoPz8/837N63zYsGFuUwI09PpvivdPjQ0bNuinn37SmDFj3J6/48ePa+jQoSooKDB/1n/99ddr6dKleuKJJ5Sfn6+qqqozvQRo5cjrJ5DXyevNobF5XTqRr2umzNqwYYOOHDmiadOmqUOHDsrJyZF0YjqumJgYM680Ni9L0nfffafExETZ7XZ5eHjIy8tL/fv3l1T/e64hv3ZNm/u982vONm+35Ou7ttO5ltdff70+//xzTZo0SR988IHKy8vP7AKcAYro54lvv/1W//znPzV8+HAZhqEDBw7owIEDuvnmmyXJLSHVCAwMdLtfs9BOfQWju+++W06nU3//+9/Vo0cPc/vx48cVFxent956SzNnztSHH36ozZs3my/e+o51Ouc9lf3798vT07PO8WoWuTg57tixY0pLS5OXl5fbraZAV3u+uZqFMRrD19dXt956q5xOp0pKSnTs2DFlZWWpf//+5qIaNW2tvSiCxWKR3W7X/v37G33+zZs36+uvv9af/vQnderUqU5fG3p8SEhInfPUt3K2t7d3ne3e3t6STvzHVVt9sb6+vmrTpk2d7Sc/fu/evfriiy/qPCf+/v4yDKPOc1L7eZZOvHbOVYGzsa8Jm82mvLw89ejRQw899JCuueYahYSE6NFHH63zoaul+/Rrdu7cKavVesYrrDf0Omrs66uh11FDr9v6Xp819u7dK0maMWNGndfcpEmTJP3y/8Dzzz+vBx54QG+//bYGDhyogIAAjRw5st4PT7hwkXd/Qd4l7zaH5si7tV+rJ2+rea727t2rNWvW1LlO11xzjaRfXrt79+7VgQMH5O3tXSe2pKTEjKs5bu1z1/deakh9z6/VanV7fvfv3+/2BUGN+radqV27drl9aD5dZ/t3QVO8f2rU/F1w880313n+nnrqKRmGoZ9++knSiblzx4wZo1deeUUxMTEKCAjQnXfeqZKSkl/tM84f5PVfkNfJ683hdF4TsbGx2rVrl7755hvl5uaqZ8+eCgoK0h/+8Afl5ubq6NGj2rBhg2JjY83HNDYvHzp0SL/73e+0adMmPfHEE/r4449VUFCgt956S9LpvY9+7Zo293vn19QUpc80d7fk67u207mWs2bN0jPPPKP8/HwNGzZMgYGBGjRoUJ112JpD44ZHoMW9+uqrMgxDf//73/X3v/+9zv5ly5bpiSeecPumvLGSk5P1yiuvaMmSJYqLi3Pbt2XLFn3++edaunSpxowZY24/k8UPTldgYKCOHTum/fv3u/3nVfsP2vbt28vDw0MOh8NtIYqThYWFud2vb4GMUxk3bpwyMjL02muv6aqrrlJpaameffbZOm3dt2+fW+I3DEMlJSW67rrrGn3+P/3pT7Lb7Zo9e7aOHz9uLjJZcx5JKi4urvMHwY8//qgOHTqcVr+aU4cOHeTj41PvH6Q1+5tTzX/aFRUV5h+eUt0kVuN0XhNRUVHKzs6WYRj64osvtHTpUj322GPy8fHRgw8+eHYNP0d++OEHFRYWqn///uZIudO9Zq1Jzetp1qxZGjVqVL0xERERkiQ/Pz/NmTNHc+bM0d69e81R6SNGjNB//vOfc9ZmtG7kXfJuzXkk8m5jtIa8W1/Rs2ZbzXPZoUMHde/eXXPnzq33XDUfRDt06KDAwMA6C2nVqBmZVnPckpISt19n1byXmkpgYGC9i5U2VaF38+bNKikpMRcBlE48p7UXN5XOr78L0tLS1KdPn3pjar6A6NChgxYuXKiFCxdq165dWr16tR588EGVlpY2+Pzj/ENeJ6/XnEcirzdGc+b1QYMGSTox2jwnJ0eDBw82tz/88MP65z//qYqKCrciemPz8j/+8Q/9+OOP+vjjj83R55LqLFDbFM7Fe6chR48eVW5urq644grztXzyc3ay8yFvn8619PT01LRp0zRt2jQdOHBAubm5euihhzRkyBDt3r3b7VfxTY0i+nmgurpay5Yt0xVXXKFXXnmlzv61a9fq2Wef1fvvv1/npxS/JjMzU3PmzNFjjz1W5ydN0i9v8JP/05SkxYsXn9Z5zsTAgQM1b948rVixQlOnTjW3r1y50i3O19dXAwcO1Geffabu3bub35I1pejoaEVGRmrJkiW66qqrZLPZ3H6GM2jQIM2bN09ZWVm67777zO1vvvmmDh8+bCaJxnr44Yfl7++v++67T4cPH1Zqaqok6Q9/+IMkKSsry+0PiYKCAm3btk2zZ88+m242qfj4eKWkpCgwMLBO4jgXunTpIkn64osv3K7VmjVrmuwcFotF1157rRYsWKClS5fq008/bbJj13amI1Dqc/ToUf3lL3/RsWPHNHPmTHP7ubhmzSUiIkLh4eH6/PPPlZKS0ujHBQcHa+zYsfr888+1cOFCHTlypFmTLs4P5F3yLnn39LWGvPvhhx9q7969ZnG0urpab7zxhtsHzPj4eL333nu64oor1L59+wbPFR8fr+zsbFVXVys6OrrBuAEDBkiSVqxY4faT6L/97W86duzYmXa1jv79++tvf/ub3n//fbefSGdnZ5/1sX/66Sfdfffd8vLycns/denSRaWlpW7XtLKyUh988MFZn7O59evXT+3atdNXX32le+65p9GP69y5s+655x59+OGH+ve//92MLcS5RF4nr5PXT19z5vWOHTuqW7duevPNN1VYWGh+fhs8eLAmTpyo+fPnq23btm7nbWxePp333MmfsX18fE67H+fivVOf6upq3XPPPdq/f7/52pbcn7OaAWSStHr16nPSrrNxpteyXbt2uvnmm/XDDz8oKSlJ33//vbp169Zs7aSIfh54//339eOPP+qpp54y/1A/WWRkpNLT05WZmXlaSX/jxo26++671a9fPw0ePLjOXE19+vTR1VdfrSuuuEIPPvigDMNQQECA1qxZY85T1Zzi4uL0+9//XjNnztThw4fVu3dv/fvf/9by5cvrxD733HO64YYb9Lvf/U7/8z//oy5duujgwYP69ttvtWbNGnOOtbNx1113adq0adq+fbsmTpzo9p/s4MGDNWTIED3wwAMqLy9Xv3799MUXX+jRRx9Vz5495XA4Tvt89957ry6++GJNmDBBhw4d0vPPP6+IiAhNmDBBaWlpuuiiizRs2DB9//33+utf/6rQ0FC3PzhaWlJSkt588039/ve/13333afu3bvr+PHj2rVrl9atW6fp06efMvmdrRtvvFEBAQEaN26cHnvsMXl6emrp0qXavXv3WR137dq1evHFFzVy5EhdfvnlMgxDb731lg4cOGB+g94c/P39ddlll+mdd97RoEGDFBAQoA4dOpiJsiG7du1Sfn6+jh8/LpfLpc8++0yvvvqqdu7cqWeffdZttExzXbNzZfHixRo2bJiGDBmisWPH6tJLL9VPP/2kbdu26dNPP9X//u//SjrxR3x8fLy6d++u9u3ba9u2bVq+fLliYmIooEMSeZe8S949E60h73bo0EF/+MMf9Ne//lV+fn568cUX9Z///Met0PzYY48pJydHffv21dSpUxUREaGff/5Z33//vd577z299NJL6tSpk2699VatWLFCN954o+69915df/318vLy0p49e/TRRx/ppptu0h//+Ed17dpVd9xxhxYuXCgvLy/FxsZqy5YteuaZZ9S2bduz6vvJxowZowULFuiOO+7QE088oSuvvFLvv/++WdC+6KLGzdL5zTffmH8X7N+/X5s2bVJmZqbKy8v12muvmdPaSCdGcz7yyCO69dZbdf/99+vnn3/W888/r+rq6ibrV3O5+OKLlZaWpjFjxuinn37SzTffrKCgIO3bt0+ff/659u3bp0WLFsnlcmngwIFKTEzU1VdfLX9/fxUUFMjpdDb4yzacf8jr5HXy+ulr7s+GgwYNUlpamnx8fNSvXz9JJ0Yah4WFad26dUpISHBbW6Sxeblv375q37697r77bj366KPy8vLSihUr9Pnnn9dpQ1RUlCTpqaee0rBhw+Th4XHaxfDmfu/s3btX+fn5MgxDBw8e1JYtW/Taa6/p888/13333afx48ebsdddd50iIiI0Y8YMHTt2TO3bt9eqVau0fv36s2rDudLYazlixAhFRkaqd+/euuSSS7Rz504tXLhQl112mcLDw5u1jRTRzwOZmZny9vY2F92orUOHDvrjH/+ov//97+b8f42xfft2HTt2TP/+978VExNTZ79hGPLy8tKaNWt07733auLEifL09FRsbKxyc3PVuXPnM+5TY1x00UVavXq1pk2bpnnz5qmyslL9+vXTe++9p6uvvtottlu3bvr000/1+OOP6+GHH1ZpaanatWun8PBwt4ULz4bD4dCDDz6oyspK3XXXXW77LBaL3n77bSUnJ2vJkiWaO3euOnToIIfDoZSUlDrfgjbWuHHj5OfnJ4fDocOHD+uVV17RokWLdMUVVygzM1MvvPCCbDabhg4dqtTU1EbPvXku+Pn56V//+peefPJJvfzyy9qxY4d8fHzUuXNnxcbG/mrx92y1bdtWTqdTSUlJuuOOO9SuXTv95S9/0bBhw/SXv/zljI8bHh6udu3aad68efrxxx/l7e2tiIiIOj/RbA6ZmZm6//77lZCQoIqKCo0ZM0ZLly495WPS0tKUlpYmDw8PtW3bVpdffrlGjBih8ePH1/mGtrmu2bkycOBAbd68WXPnzlVSUpLKysoUGBiobt26afTo0WbcH/7wB61evVoLFizQkSNHdOmll+rOO+9sVSNP0LLIu+Rd8u7paw15NyEhQddcc40efvhh7dq1S1dccYVWrFihP/3pT2ZMx44d9cknn+jxxx/X008/rT179sjf319hYWEaOnSoOTrdw8NDq1ev1nPPPafly5crNTVVnp6e6tSpk/r3729+8JZO/J8RHByspUuX6vnnn1ePHj305ptvmosXNgU/Pz/94x//UFJSkmbOnCmLxaK4uDi9+OKLuvHGG9WuXbtGHeehhx6SdOKn0DabTVdddZXuuusuTZgwwW0hROlEMeOdd97RQw89pJtvvlkdO3bUtGnTtG/fPs2ZM6fJ+tZc7rjjDnXu3Fnz5s3TxIkTdfDgQXPBtJoRw23atFF0dLSWL1+u77//XlVVVercubMeeOABt1/r4fxGXievk9dPX3N/NoyNjVVaWppuuOEGt/mzY2NjlZGR4TaVi9T4vBwYGKh3331X06dP1x133CE/Pz/ddNNNeuONN/Rf//VfbsdMTEzUv//9b7344ot67LHHZBiGduzYcVrXtrnfOzVTUF100UW6+OKLddlllykmJkYvvfRSnenKPDw8tGbNGt1zzz26++67ZbVadeuttyo9PV3Dhw8/67Y0t8Zey4EDB+rNN9/UK6+8ovLyctntdg0ePFh//etf5eXl1axttBhnu5wrAAAAALQgi8WiyZMnKz09vaWbck6lpKSYXxrUnt8XAAAATYeR6AAAAADQytV8QXD11VerqqpK//jHP/T888/rjjvuoIAOAADQzCiiAwAAAEAr5+vrqwULFuj7779XRUWFOe3Iww8/3NJNAwAA+M1jOhcAAAAAAAAAABrQuGXcAQAAAAAAAAC4AFFEBwAAAAAAAACgAcyJ3kjHjx/Xjz/+KH9/f1kslpZuDgDgN8QwDB08eFAhISG66CK+324O5HEAQHMhjzc/8jgAoLk0No9TRG+kH3/8UaGhoS3dDADAb9ju3bvVqVOnlm7GbxJ5HADQ3MjjzYc8DgBobr+WxymiN5K/v7+kExe0bdu2LdwaAMBvSXl5uUJDQ81cg6ZHHgcANBfyePMjjwMAmktj8zhF9Eaq+clY27ZtSdoAgGbBz5ObD3kcANDcyOPNhzwOAGhuv5bHmbANAAAAAAAAAIAGUEQHAAAAAAAAAKABFNEBAAAAAAAAAGgARXQAAAAAAAAAABpAER0AAAAAAAAAgAZQRAcAAAAAAAAAoAEU0QEAAAAAAAAAaABFdAAAAAAAAAAAGkARHQAAAAAAAACABlBEBwAAAAAAAACgARTRAQAAAAAAAABoAEV0AAAAAAAAAAAaQBEdAAAAAAAAAIAGeLbkyY8dO6bk5GStWLFCJSUl6tixo8aOHauHH35YF110or5vGIbmzJmjl19+WWVlZYqOjtYLL7yga665xjxORUWFZsyYoddff11Hjx7VoEGD9OKLL6pTp05mTFlZmaZOnarVq1dLkhISEpSWlqZ27do1ax/j/vRYsx4fzWPdG4+0dBMAAK0Aefz8RB4HAEjk8fMRORxAa9WiI9GfeuopvfTSS0pPT9e2bds0b948Pf3000pLSzNj5s2bp/nz5ys9PV0FBQWy2+0aPHiwDh48aMYkJSVp1apVys7O1vr163Xo0CHFx8erurrajElMTFRRUZGcTqecTqeKiorkcDjOaX8BAAAAAAAAAOeXFh2JvnHjRt10000aPny4JKlLly56/fXX9cknn0g6MQp94cKFmj17tkaNGiVJWrZsmYKDg7Vy5UpNnDhRLpdLmZmZWr58uWJjYyVJWVlZCg0NVW5uroYMGaJt27bJ6XQqPz9f0dHRkqSMjAzFxMRo+/btioiIaIHeAwAAAAAAAABauxYdiX7DDTfoww8/1Ndffy1J+vzzz7V+/XrdeOONkqQdO3aopKREcXFx5mOsVqv69++vDRs2SJIKCwtVVVXlFhMSEqLIyEgzZuPGjbLZbGYBXZL69Okjm81mxtRWUVGh8vJytxsAAAAAAAAA4MLSoiPRH3jgAblcLl199dXy8PBQdXW15s6dq9tuu02SVFJSIkkKDg52e1xwcLB27txpxnh7e6t9+/Z1YmoeX1JSoqCgoDrnDwoKMmNqS01N1Zw5c86ugwAAAAAAAACA81qLjkR/4403lJWVpZUrV+rTTz/VsmXL9Mwzz2jZsmVucRaLxe2+YRh1ttVWO6a++FMdZ9asWXK5XOZt9+7dje0WAAAAAAAAAOA3okVHot9///168MEHdeutt0qSoqKitHPnTqWmpmrMmDGy2+2STowk79ixo/m40tJSc3S63W5XZWWlysrK3Eajl5aWqm/fvmbM3r1765x/3759dUa517BarbJarU3TUeAUejyR3NJNwGkqeji5pZsAAAAAAACAc6RFR6IfOXJEF13k3gQPDw8dP35ckhQWFia73a6cnBxzf2VlpfLy8swCea9eveTl5eUWU1xcrC1btpgxMTExcrlc2rx5sxmzadMmuVwuMwYAAAAAAAAAgNpadCT6iBEjNHfuXHXu3FnXXHONPvvsM82fP1933XWXpBNTsCQlJSklJUXh4eEKDw9XSkqKfH19lZiYKEmy2WwaN26cpk+frsDAQAUEBGjGjBmKiopSbGysJKlr164aOnSoxo8fr8WLF0uSJkyYoPj4eEVERLRM5wEAAAAAAAAArV6LFtHT0tL017/+VZMmTVJpaalCQkI0ceJEPfLII2bMzJkzdfToUU2aNEllZWWKjo7WunXr5O/vb8YsWLBAnp6eGj16tI4ePapBgwZp6dKl8vDwMGNWrFihqVOnKi4uTpKUkJCg9PT0c9dZAAAAAAAAAMB5p0Wnc/H399fChQu1c+dOHT16VP/v//0/PfHEE/L29jZjLBaLkpOTVVxcrJ9//ll5eXmKjIx0O06bNm2Ulpam/fv368iRI1qzZo1CQ0PdYgICApSVlaXy8nKVl5crKytL7dq1OxfdBADgN6lLly6yWCx1bpMnT5Z0YgHv5ORkhYSEyMfHRwMGDNDWrVvdjlFRUaEpU6aoQ4cO8vPzU0JCgvbs2eMWU1ZWJofDIZvNJpvNJofDoQMHDpyrbgIAAAAALnAtWkQHAADnr4KCAhUXF5u3mvVJbrnlFknSvHnzNH/+fKWnp6ugoEB2u12DBw/WwYMHzWMkJSVp1apVys7O1vr163Xo0CHFx8erurrajElMTFRRUZGcTqecTqeKiorkcDjObWcBAAAAABesFp3OBQAAnL8uueQSt/tPPvmkrrjiCvXv31+GYWjhwoWaPXu2Ro0aJUlatmyZgoODtXLlSk2cOFEul0uZmZlavny5uY5JVlaWQkNDlZubqyFDhmjbtm1yOp3Kz89XdHS0JCkjI0MxMTHavn17g2ubVFRUqKKiwrxfXl7eHJcAAAAAAHABYCQ6AAA4a5WVlcrKytJdd90li8WiHTt2qKSkxFyLRJKsVqv69++vDRs2SJIKCwtVVVXlFhMSEqLIyEgzZuPGjbLZbGYBXZL69Okjm81mxtQnNTXVnP7FZrPVmeYNAAAAAIDGoogOAADO2ttvv60DBw5o7NixkqSSkhJJUnBwsFtccHCwua+kpETe3t5q3779KWOCgoLqnC8oKMiMqc+sWbPkcrnM2+7du8+4bwAAAACACxvTuQAAgLOWmZmpYcOGKSQkxG27xWJxu28YRp1ttdWOqS/+145jtVpltVob03QAAAAAAE6JkegAAOCs7Ny5U7m5ufrLX/5ibrPb7ZJUZ7R4aWmpOTrdbrersrJSZWVlp4zZu3dvnXPu27evzih3AAAAAACaA0V0AABwVpYsWaKgoCANHz7c3BYWFia73a6cnBxzW2VlpfLy8tS3b19JUq9eveTl5eUWU1xcrC1btpgxMTExcrlc2rx5sxmzadMmuVwuMwYAAAAAgObEdC4AAOCMHT9+XEuWLNGYMWPk6fnLnxUWi0VJSUlKSUlReHi4wsPDlZKSIl9fXyUmJkqSbDabxo0bp+nTpyswMFABAQGaMWOGoqKiFBsbK0nq2rWrhg4dqvHjx2vx4sWSpAkTJig+Pl4RERHnvsMAAAAAgAsOI9EBAMAZy83N1a5du3TXXXfV2Tdz5kwlJSVp0qRJ6t27t3744QetW7dO/v7+ZsyCBQs0cuRIjR49Wv369ZOvr6/WrFkjDw8PM2bFihWKiopSXFyc4uLi1L17dy1fvvyc9A8AgPPRP//5T40YMUIhISGyWCx6++23G4ydOHGiLBaLFi5c6La9oqJCU6ZMUYcOHeTn56eEhATt2bPHLaasrEwOh0M2m002m00Oh0MHDhxwi9m1a5dGjBghPz8/dejQQVOnTlVlZWUT9RQAgHODkegAAOCMxcXFyTCMevdZLBYlJycrOTm5wce3adNGaWlpSktLazAmICBAWVlZZ9tUAAAuGIcPH9a1116rP//5z/rv//7vBuPefvttbdq0qc7C4JKUlJSkNWvWKDs7W4GBgZo+fbri4+NVWFhoftmdmJioPXv2yOl0SjrxazGHw6E1a9ZIkqqrqzV8+HBdcsklWr9+vfbv368xY8bIMIxT5n4AAFobiugAAAAAAPyGDBs2TMOGDTtlzA8//KB77rlHH3zwgdu6JpLkcrmUmZmp5cuXm1OsZWVlKTQ0VLm5uRoyZIi2bdsmp9Op/Px8RUdHS5IyMjIUExOj7du3KyIiQuvWrdNXX32l3bt3m4X6Z599VmPHjtXcuXPVtm3bettWUVGhiooK8355efkZXwsAAJoC07kAAAAAAHABOX78uBwOh+6//35dc801dfYXFhaqqqpKcXFx5raQkBBFRkZqw4YNkqSNGzfKZrOZBXRJ6tOnj2w2m1tMZGSk20j3IUOGqKKiQoWFhQ22LzU11ZwixmazKTQ09Kz7DADA2aCIDgAAAADABeSpp56Sp6enpk6dWu/+kpISeXt7q3379m7bg4ODVVJSYsYEBQXVeWxQUJBbTHBwsNv+9u3by9vb24ypz6xZs+Ryuczb7t27T6t/AAA0NaZzAQAAAADgAlFYWKjnnntOn376qSwWy2k91jAMt8fU9/gzianNarXKarWeVtsAAGhOjEQHAAAAAOAC8a9//UulpaXq3LmzPD095enpqZ07d2r69Onq0qWLJMlut6uyslJlZWVujy0tLTVHltvtdu3du7fO8fft2+cWU3vEeVlZmaqqquqMUAcAoDWjiA4AAAAAwAXC4XDoiy++UFFRkXkLCQnR/fffrw8++ECS1KtXL3l5eSknJ8d8XHFxsbZs2aK+fftKkmJiYuRyubR582YzZtOmTXK5XG4xW7ZsUXFxsRmzbt06Wa1W9erV61x0FwCAJsF0LgAAAAAA/IYcOnRI3377rXl/x44dKioqUkBAgDp37qzAwEC3eC8vL9ntdkVEREiSbDabxo0bp+nTpyswMFABAQGaMWOGoqKiFBsbK0nq2rWrhg4dqvHjx2vx4sWSpAkTJig+Pt48TlxcnLp16yaHw6Gnn35aP/30k2bMmKHx48erbdu25+JSAADQJBiJDgAAAADAb8gnn3yinj17qmfPnpKkadOmqWfPnnrkkUcafYwFCxZo5MiRGj16tPr16ydfX1+tWbNGHh4eZsyKFSsUFRWluLg4xcXFqXv37lq+fLm538PDQ++++67atGmjfv36afTo0Ro5cqSeeeaZpussAADnACPRAQAAAAD4DRkwYIAMw2h0/Pfff19nW5s2bZSWlqa0tLQGHxcQEKCsrKxTHrtz585au3Zto9sCAEBrxEh0AAAAAAAAAAAaQBEdAAAAAAAAAIAGMJ0LAAAAcIZ6PJHc0k3AaSp6OLmlmwAAAIDzDCPRAQAAAAAAAABoAEV0AAAAAAAAAAAaQBEdAAAAAAAAAIAGUEQHAAAAAAAAAKABFNEBAAAAAAAAAGgARXQAAAAAAAAAABrQokX0Ll26yGKx1LlNnjxZkmQYhpKTkxUSEiIfHx8NGDBAW7dudTtGRUWFpkyZog4dOsjPz08JCQnas2ePW0xZWZkcDodsNptsNpscDocOHDhwrroJAAAAAAAAADhPtWgRvaCgQMXFxeYtJydHknTLLbdIkubNm6f58+crPT1dBQUFstvtGjx4sA4ePGgeIykpSatWrVJ2drbWr1+vQ4cOKT4+XtXV1WZMYmKiioqK5HQ65XQ6VVRUJIfDcW47CwAAAAAAAAA473i25MkvueQSt/tPPvmkrrjiCvXv31+GYWjhwoWaPXu2Ro0aJUlatmyZgoODtXLlSk2cOFEul0uZmZlavny5YmNjJUlZWVkKDQ1Vbm6uhgwZom3btsnpdCo/P1/R0dGSpIyMDMXExGj79u2KiIg4t50GAAAAAAAAAJw3Ws2c6JWVlcrKytJdd90li8WiHTt2qKSkRHFxcWaM1WpV//79tWHDBklSYWGhqqqq3GJCQkIUGRlpxmzcuFE2m80soEtSnz59ZLPZzJj6VFRUqLy83O0GAAAAAAAAALiwtJoi+ttvv60DBw5o7NixkqSSkhJJUnBwsFtccHCwua+kpETe3t5q3779KWOCgoLqnC8oKMiMqU9qaqo5h7rNZlNoaOgZ9w0AAAAAAAAAcH5qNUX0zMxMDRs2TCEhIW7bLRaL233DMOpsq612TH3xv3acWbNmyeVymbfdu3c3phsAAAAAAAAAgN+QVlFE37lzp3Jzc/WXv/zF3Ga32yWpzmjx0tJSc3S63W5XZWWlysrKThmzd+/eOufct29fnVHuJ7NarWrbtq3bDQAAAAAAAABwYWkVRfQlS5YoKChIw4cPN7eFhYXJbrcrJyfH3FZZWam8vDz17dtXktSrVy95eXm5xRQXF2vLli1mTExMjFwulzZv3mzGbNq0SS6Xy4wBAAAAAAAAAKA+ni3dgOPHj2vJkiUaM2aMPD1/aY7FYlFSUpJSUlIUHh6u8PBwpaSkyNfXV4mJiZIkm82mcePGafr06QoMDFRAQIBmzJihqKgoxcbGSpK6du2qoUOHavz48Vq8eLEkacKECYqPj1dERMS57zAAAAAAAAAA4LzR4kX03Nxc7dq1S3fddVedfTNnztTRo0c1adIklZWVKTo6WuvWrZO/v78Zs2DBAnl6emr06NE6evSoBg0apKVLl8rDw8OMWbFihaZOnaq4uDhJUkJCgtLT05u/cwAAAAAAAACA81qLF9Hj4uJkGEa9+ywWi5KTk5WcnNzg49u0aaO0tDSlpaU1GBMQEKCsrKyzbSoAAAAAAAAA4ALTKuZEBwAAAAAAAACgNWrxkegAAAAA8Fs05cN7W7oJOE1pg55r6SYAAIBWiJHoAAAAAAAAAAA0gCI6AAA4Yz/88IPuuOMOBQYGytfXVz169FBhYaG53zAMJScnKyQkRD4+PhowYIC2bt3qdoyKigpNmTJFHTp0kJ+fnxISErRnzx63mLKyMjkcDtlsNtlsNjkcDh04cOBcdBEAAAAAcIGjiA4AAM5IWVmZ+vXrJy8vL73//vv66quv9Oyzz6pdu3ZmzLx58zR//nylp6eroKBAdrtdgwcP1sGDB82YpKQkrVq1StnZ2Vq/fr0OHTqk+Ph4VVdXmzGJiYkqKiqS0+mU0+lUUVGRHA7HuewuAAAAAOACxZzoAADgjDz11FMKDQ3VkiVLzG1dunQx/20YhhYuXKjZs2dr1KhRkqRly5YpODhYK1eu1MSJE+VyuZSZmanly5crNjZWkpSVlaXQ0FDl5uZqyJAh2rZtm5xOp/Lz8xUdHS1JysjIUExMjLZv366IiIg6bauoqFBFRYV5v7y8vDkuAQAAAADgAsBIdAAAcEZWr16t3r1765ZbblFQUJB69uypjIwMc/+OHTtUUlKiuLg4c5vValX//v21YcMGSVJhYaGqqqrcYkJCQhQZGWnGbNy4UTabzSygS1KfPn1ks9nMmNpSU1PNqV9sNptCQ0ObtO8AAAAAgAsHRXQAAHBGvvvuOy1atEjh4eH64IMPdPfdd2vq1Kl67bXXJEklJSWSpODgYLfHBQcHm/tKSkrk7e2t9u3bnzImKCiozvmDgoLMmNpmzZoll8tl3nbv3n12nQUAAAAAXLCYzgUAAJyR48ePq3fv3kpJSZEk9ezZU1u3btWiRYt05513mnEWi8XtcYZh1NlWW+2Y+uJPdRyr1Sqr1drovgAAAAAA0BBGogMAgDPSsWNHdevWzW1b165dtWvXLkmS3W6XpDqjxUtLS83R6Xa7XZWVlSorKztlzN69e+ucf9++fXVGuQMAAAAA0NQoogMAgDPSr18/bd++3W3b119/rcsuu0ySFBYWJrvdrpycHHN/ZWWl8vLy1LdvX0lSr1695OXl5RZTXFysLVu2mDExMTFyuVzavHmzGbNp0ya5XC4zBgAA/OKf//ynRowYoZCQEFksFr399tvmvqqqKj3wwAOKioqSn5+fQkJCdOedd+rHH390O0ZFRYWmTJmiDh06yM/PTwkJCdqzZ49bTFlZmRwOh7kGicPh0IEDB9xidu3apREjRsjPz08dOnTQ1KlTVVlZ2VxdBwCgWVBEBwAAZ+S+++5Tfn6+UlJS9O2332rlypV6+eWXNXnyZEknpmBJSkpSSkqKVq1apS1btmjs2LHy9fVVYmKiJMlms2ncuHGaPn26PvzwQ3322We64447FBUVpdjYWEknRrcPHTpU48ePV35+vvLz8zV+/HjFx8crIiKixfoPAEBrdfjwYV177bVKT0+vs+/IkSP69NNP9de//lWffvqp3nrrLX399ddKSEhwi0tKStKqVauUnZ2t9evX69ChQ4qPj1d1dbUZk5iYqKKiIjmdTjmdThUVFcnhcJj7q6urNXz4cB0+fFjr169Xdna23nzzTU2fPr35Og8AQDNgTnQAAHBGrrvuOq1atUqzZs3SY489prCwMC1cuFC33367GTNz5kwdPXpUkyZNUllZmaKjo7Vu3Tr5+/ubMQsWLJCnp6dGjx6to0ePatCgQVq6dKk8PDzMmBUrVmjq1KmKi4uTJCUkJNRbGAAAANKwYcM0bNiwevfZbDa3X4BJUlpamq6//nrt2rVLnTt3lsvlUmZmppYvX25+qZ2VlaXQ0FDl5uZqyJAh2rZtm5xOp/Lz8xUdHS1JysjIUExMjLZv366IiAitW7dOX331lXbv3q2QkBBJ0rPPPquxY8dq7ty5atu2bTNeBQAAmg5FdAAAcMbi4+MVHx/f4H6LxaLk5GQlJyc3GNOmTRulpaUpLS2twZiAgABlZWWdTVMBAEADXC6XLBaL2rVrJ0kqLCxUVVWV+eW1JIWEhCgyMlIbNmzQkCFDtHHjRtlsNrOALkl9+vSRzWbThg0bFBERoY0bNyoyMtIsoEvSkCFDVFFRocLCQg0cOLDe9lRUVKiiosK8X15e3sQ9BgDg9DCdCwAAAAAAF6iff/5ZDz74oBITE82R4SUlJfL29lb79u3dYoODg80Fw0tKShQUFFTneEFBQW4xtRcBb9++vby9vessPH6y1NRUc551m82m0NDQs+ojAABniyI6AAAAAAAXoKqqKt166606fvy4XnzxxV+NNwxDFovFvH/yv88mprZZs2bJ5XKZt927d/9q2wAAaE4U0QEAAAAAuMBUVVVp9OjR2rFjh3JyctzmJ7fb7aqsrFRZWZnbY0pLS82R5Xa7XXv37q1z3H379rnF1B5xXlZWpqqqqjoj1E9mtVrVtm1btxsAAC2JIjoAAAAAABeQmgL6N998o9zcXAUGBrrt79Wrl7y8vNwWIC0uLtaWLVvUt29fSVJMTIxcLpc2b95sxmzatEkul8stZsuWLSouLjZj1q1bJ6vVql69ejVnFwEAaFIsLAoAAAAAwG/IoUOH9O2335r3d+zYoaKiIgUEBCgkJEQ333yzPv30U61du1bV1dXmaPGAgAB5e3vLZrNp3Lhxmj59ugIDAxUQEKAZM2YoKipKsbGxkqSuXbtq6NChGj9+vBYvXixJmjBhguLj4xURESFJiouLU7du3eRwOPT000/rp59+0owZMzR+/HhGlwMAzisU0QEAAAAA+A355JNPNHDgQPP+tGnTJEljxoxRcnKyVq9eLUnq0aOH2+M++ugjDRgwQJK0YMECeXp6avTo0Tp69KgGDRqkpUuXysPDw4xfsWKFpk6dqri4OElSQkKC0tPTzf0eHh569913NWnSJPXr108+Pj5KTEzUM8880xzdBgCg2VBEBwAAAADgN2TAgAEyDKPB/afaV6NNmzZKS0tTWlpagzEBAQHKyso65XE6d+6stWvX/ur5AABozZgTHQAAAAAAAACABlBEBwAAAAAAAACgARTRAQAAAAAAAABoAEV0AAAAAAAAAAAaQBEdAAAAAAAAAIAGUEQHAAAAAAAAAKABFNEBAAAAAAAAAGhAixfRf/jhB91xxx0KDAyUr6+vevToocLCQnO/YRhKTk5WSEiIfHx8NGDAAG3dutXtGBUVFZoyZYo6dOggPz8/JSQkaM+ePW4xZWVlcjgcstlsstlscjgcOnDgwLnoIgAAAAAAAADgPNWiRfSysjL169dPXl5eev/99/XVV1/p2WefVbt27cyYefPmaf78+UpPT1dBQYHsdrsGDx6sgwcPmjFJSUlatWqVsrOztX79eh06dEjx8fGqrq42YxITE1VUVCSn0ymn06mioiI5HI5z2V0AAAAAAAAAwHnGsyVP/tRTTyk0NFRLliwxt3Xp0sX8t2EYWrhwoWbPnq1Ro0ZJkpYtW6bg4GCtXLlSEydOlMvlUmZmppYvX67Y2FhJUlZWlkJDQ5Wbm6shQ4Zo27Ztcjqdys/PV3R0tCQpIyNDMTEx2r59uyIiIuq0raKiQhUVFeb98vLy5rgEAAAAAAAAAIBWrEVHoq9evVq9e/fWLbfcoqCgIPXs2VMZGRnm/h07dqikpERxcXHmNqvVqv79+2vDhg2SpMLCQlVVVbnFhISEKDIy0ozZuHGjbDabWUCXpD59+shms5kxtaWmpppTv9hsNoWGhjZp3wEAAAAAAAAArV+LFtG/++47LVq0SOHh4frggw909913a+rUqXrttdckSSUlJZKk4OBgt8cFBweb+0pKSuTt7a327dufMiYoKKjO+YOCgsyY2mbNmiWXy2Xedu/efXadBQAAAAAAAACcd1p0Opfjx4+rd+/eSklJkST17NlTW7du1aJFi3TnnXeacRaLxe1xhmHU2VZb7Zj64k91HKvVKqvV2ui+AAAAAAAAAAB+e1p0JHrHjh3VrVs3t21du3bVrl27JEl2u12S6owWLy0tNUen2+12VVZWqqys7JQxe/furXP+ffv21RnlDgAAAAAAAABAjRYtovfr10/bt2932/b111/rsssukySFhYXJbrcrJyfH3F9ZWam8vDz17dtXktSrVy95eXm5xRQXF2vLli1mTExMjFwulzZv3mzGbNq0SS6Xy4wBAAAAAAAAAKC2Fp3O5b777lPfvn2VkpKi0aNHa/PmzXr55Zf18ssvSzoxBUtSUpJSUlIUHh6u8PBwpaSkyNfXV4mJiZIkm82mcePGafr06QoMDFRAQIBmzJihqKgoxcbGSjoxun3o0KEaP368Fi9eLEmaMGGC4uPjFRER0TKdBwAAAAAAAAC0ei1aRL/uuuu0atUqzZo1S4899pjCwsK0cOFC3X777WbMzJkzdfToUU2aNEllZWWKjo7WunXr5O/vb8YsWLBAnp6eGj16tI4ePapBgwZp6dKl8vDwMGNWrFihqVOnKi4uTpKUkJCg9PT0c9dZAAAAAAAAAMB5p0WL6JIUHx+v+Pj4BvdbLBYlJycrOTm5wZg2bdooLS1NaWlpDcYEBAQoKyvrbJoKAAAAAAAAALjAtOic6AAAAAAAAAAAtGYU0QEAAAAAAAAAaABFdAAAAAAAAAAAGkARHQAAAAAAAACABlBEBwAAAAAAAACgARTRAQAAAAAAAABoAEV0AAAAAAAAAAAaQBEdAACckeTkZFksFreb3W439xuGoeTkZIWEhMjHx0cDBgzQ1q1b3Y5RUVGhKVOmqEOHDvLz81NCQoL27NnjFlNWViaHwyGbzSabzSaHw6EDBw6ciy4CAAAAAEARHQAAnLlrrrlGxcXF5u3LL780982bN0/z589Xenq6CgoKZLfbNXjwYB08eNCMSUpK0qpVq5Sdna3169fr0KFDio+PV3V1tRmTmJiooqIiOZ1OOZ1OFRUVyeFwnNN+AgAAAAAuXJ4t3QAAAHD+8vT0dBt9XsMwDC1cuFCzZ8/WqFGjJEnLli1TcHCwVq5cqYkTJ8rlcikzM1PLly9XbGysJCkrK0uhoaHKzc3VkCFDtG3bNjmdTuXn5ys6OlqSlJGRoZiYGG3fvl0RERH1tquiokIVFRXm/fLy8qbuOgAAAADgAsFIdAAAcMa++eYbhYSEKCwsTLfeequ+++47SdKOHTtUUlKiuLg4M9Zqtap///7asGGDJKmwsFBVVVVuMSEhIYqMjDRjNm7cKJvNZhbQJalPnz6y2WxmTH1SU1PN6V9sNptCQ0ObtN8AAAAAgAsHRXQAAHBGoqOj9dprr+mDDz5QRkaGSkpK1LdvX+3fv18lJSWSpODgYLfHBAcHm/tKSkrk7e2t9u3bnzImKCiozrmDgoLMmPrMmjVLLpfLvO3evfus+goAAAAAuHAxnQsAADgjw4YNM/8dFRWlmJgYXXHFFVq2bJn69OkjSbJYLG6PMQyjzrbaasfUF/9rx7FarbJarY3qBwAAAAAAp8JIdAAA0CT8/PwUFRWlb775xpwnvfZo8dLSUnN0ut1uV2VlpcrKyk4Zs3fv3jrn2rdvX51R7gAA4IR//vOfGjFihEJCQmSxWPT222+77TcMQ8nJyQoJCZGPj48GDBigrVu3usVUVFRoypQp6tChg/z8/JSQkKA9e/a4xZSVlcnhcJjTpzkcDh04cMAtZteuXRoxYoT8/PzUoUMHTZ06VZWVlc3RbQAAmg1FdAAA0CQqKiq0bds2dezYUWFhYbLb7crJyTH3V1ZWKi8vT3379pUk9erVS15eXm4xxcXF2rJlixkTExMjl8ulzZs3mzGbNm2Sy+UyYwAAgLvDhw/r2muvVXp6er37582bp/nz5ys9PV0FBQWy2+0aPHiwDh48aMYkJSVp1apVys7O1vr163Xo0CHFx8erurrajElMTFRRUZGcTqecTqeKiorkcDjM/dXV1Ro+fLgOHz6s9evXKzs7W2+++aamT5/efJ0HAKAZMJ0LAAA4IzNmzNCIESPUuXNnlZaW6oknnlB5ebnGjBkji8WipKQkpaSkKDw8XOHh4UpJSZGvr68SExMlSTabTePGjdP06dMVGBiogIAAzZgxQ1FRUYqNjZUkde3aVUOHDtX48eO1ePFiSdKECRMUHx+viIiIFus7AACt2bBhw9ymXTuZYRhauHChZs+erVGjRkmSli1bpuDgYK1cuVITJ06Uy+VSZmamli9fbubkrKwshYaGKjc3V0OGDNG2bdvkdDqVn59vLgCekZGhmJgYbd++XREREVq3bp2++uor7d69WyEhIZKkZ599VmPHjtXcuXPVtm3bettYUVGhiooK8355eXmTXRsAAM4EI9EBAMAZ2bNnj2677TZFRERo1KhR8vb2Vn5+vi677DJJ0syZM5WUlKRJkyapd+/e+uGHH7Ru3Tr5+/ubx1iwYIFGjhyp0aNHq1+/fvL19dWaNWvk4eFhxqxYsUJRUVGKi4tTXFycunfvruXLl5/z/gIA8FuwY8cOlZSUKC4uztxmtVrVv39/bdiwQZJUWFioqqoqt5iQkBBFRkaaMRs3bpTNZjML6JLUp08f2Ww2t5jIyEizgC5JQ4YMUUVFhQoLCxtsY2pqqjlFjM1mU2hoaNN0HgCAM8RIdAAAcEays7NPud9isSg5OVnJyckNxrRp00ZpaWlKS0trMCYgIEBZWVln2kwAAHCSmvVKaq8tEhwcrJ07d5ox3t7eat++fZ2YmseXlJQoKCiozvGDgoLcYmqfp3379vL29q6zbsrJZs2apWnTppn3y8vLKaQDAFoURXQAAAAAAC4wFovF7b5hGHW21VY7pr74M4mpzWq1ymq1nrItAACcS0znAgAAAADABcJut0tSnZHgpaWl5qhxu92uyspKlZWVnTJm7969dY6/b98+t5ja5ykrK1NVVVWdEeoAALRmFNEBAAAAALhAhIWFyW63Kycnx9xWWVmpvLw89e3bV5LUq1cveXl5ucUUFxdry5YtZkxMTIxcLpc2b95sxmzatEkul8stZsuWLSouLjZj1q1bJ6vVql69ejVrPwEAaEpM5wIAAAAAwG/IoUOH9O2335r3d+zYoaKiIgUEBKhz585KSkpSSkqKwsPDFR4erpSUFPn6+ioxMVGSZLPZNG7cOE2fPl2BgYEKCAjQjBkzFBUVpdjYWElS165dNXToUI0fP16LFy+WJE2YMEHx8fGKiIiQJMXFxalbt25yOBx6+umn9dNPP2nGjBkaP3682rZte46vCgAAZ44iOgAAAAAAvyGffPKJBg4caN6vWaRzzJgxWrp0qWbOnKmjR49q0qRJKisrU3R0tNatWyd/f3/zMQsWLJCnp6dGjx6to0ePatCgQVq6dKk8PDzMmBUrVmjq1KmKi4uTJCUkJCg9Pd3c7+HhoXfffVeTJk1Sv3795OPjo8TERD3zzDPNfQkAAGhSFNEBAAAAAPgNGTBggAzDaHC/xWJRcnKykpOTG4xp06aN0tLSlJaW1mBMQECAsrKyTtmWzp07a+3atb/aZgAAWjPmRAcAAAAAAAAAoAEU0QEAAAAAAAAAaABFdAAAAAAAAAAAGtCiRfTk5GRZLBa3m91uN/cbhqHk5GSFhITIx8dHAwYM0NatW92OUVFRoSlTpqhDhw7y8/NTQkKC9uzZ4xZTVlYmh8Mhm80mm80mh8OhAwcOnIsuAgAAAAAAAADOYy0+Ev2aa65RcXGxefvyyy/NffPmzdP8+fOVnp6ugoIC2e12DR48WAcPHjRjkpKStGrVKmVnZ2v9+vU6dOiQ4uPjVV1dbcYkJiaqqKhITqdTTqdTRUVFcjgc57SfAAAAAAAAAIDzj2eLN8DT0230eQ3DMLRw4ULNnj1bo0aNkiQtW7ZMwcHBWrlypSZOnCiXy6XMzEwtX75csbGxkqSsrCyFhoYqNzdXQ4YM0bZt2+R0OpWfn6/o6GhJUkZGhmJiYrR9+3ZFREScu84CAAAAAAAAAM4rLT4S/ZtvvlFISIjCwsJ066236rvvvpMk7dixQyUlJYqLizNjrVar+vfvrw0bNkiSCgsLVVVV5RYTEhKiyMhIM2bjxo2y2WxmAV2S+vTpI5vNZsbUp6KiQuXl5W43AAAAAAAAAMCFpUWL6NHR0Xrttdf0wQcfKCMjQyUlJerbt6/279+vkpISSVJwcLDbY4KDg819JSUl8vb2Vvv27U8ZExQUVOfcQUFBZkx9UlNTzTnUbTabQkNDz6qvAAAAAAAAAIDzT4sW0YcNG6b//u//VlRUlGJjY/Xuu+9KOjFtSw2LxeL2GMMw6myrrXZMffG/dpxZs2bJ5XKZt927dzeqTwAAAAAAAACA344Wn87lZH5+foqKitI333xjzpNee7R4aWmpOTrdbrersrJSZWVlp4zZu3dvnXPt27evzij3k1mtVrVt29btBgAAAAAAAAC4sLSqInpFRYW2bdumjh07KiwsTHa7XTk5Oeb+yspK5eXlqW/fvpKkXr16ycvLyy2muLhYW7ZsMWNiYmLkcrm0efNmM2bTpk1yuVxmDAAAAAAAAAAA9fFsyZPPmDFDI0aMUOfOnVVaWqonnnhC5eXlGjNmjCwWi5KSkpSSkqLw8HCFh4crJSVFvr6+SkxMlCTZbDaNGzdO06dPV2BgoAICAjRjxgxzehhJ6tq1q4YOHarx48dr8eLFkqQJEyYoPj5eERERLdZ3AAAAAAAAAEDr16JF9D179ui2227T//3f/+mSSy5Rnz59lJ+fr8suu0ySNHPmTB09elSTJk1SWVmZoqOjtW7dOvn7+5vHWLBggTw9PTV69GgdPXpUgwYN0tKlS+Xh4WHGrFixQlOnTlVcXJwkKSEhQenp6ee2swAAAAAAAACA806LFtGzs7NPud9isSg5OVnJyckNxrRp00ZpaWlKS0trMCYgIEBZWVln2kwAAAAAAAAAwAWqVc2JDgAAAAAAAABAa0IRHQAAAAAAAACABjRqOpdp06Y1+oDz588/48YAAICmRx4HAKB1IkcDAHB+aFQR/bPPPmvUwSwWy1k1BgAAND3yOAAArRM5GgCA80OjiugfffRRc7cDAAA0E/I4AACtEzkaAIDzA3OiAwAAAAAAAADQgEaNRD/Z4cOH9eSTT+rDDz9UaWmpjh8/7rb/u+++a7LGAQCApkUeBwCgdSJHAwDQep12Ef0vf/mL8vLy5HA41LFjR+ZmAwDgPEIeBwCgdSJHAwDQep12Ef3999/Xu+++q379+jVHewAAQDMijwMA0DqRowEAaL1Oe0709u3bKyAgoDnaAgAAmhl5HACA1okcDQBA63XaRfTHH39cjzzyiI4cOdIc7QEAAM2IPA4AQOtEjgYAoPVq1HQuPXv2dJuP7dtvv1VwcLC6dOkiLy8vt9hPP/20aVsIAADOyrnI46mpqXrooYd07733auHChZIkwzA0Z84cvfzyyyorK1N0dLReeOEFXXPNNebjKioqNGPGDL3++us6evSoBg0apBdffFGdOnUyY8rKyjR16lStXr1akpSQkKC0tDS1a9fujNoKAEBrwWdtAADOD40qoo8cObKZmwEAAJpLc+fxgoICvfzyy+revbvb9nnz5mn+/PlaunSprrrqKj3xxBMaPHiwtm/fLn9/f0lSUlKS1qxZo+zsbAUGBmr69OmKj49XYWGhPDw8JEmJiYnas2ePnE6nJGnChAlyOBxas2ZNs/YLAIDmxmdtAADOD40qoj/66KPN3Q4AANBMmjOPHzp0SLfffrsyMjL0xBNPmNsNw9DChQs1e/ZsjRo1SpK0bNkyBQcHa+XKlZo4caJcLpcyMzO1fPlyxcbGSpKysrIUGhqq3NxcDRkyRNu2bZPT6VR+fr6io6MlSRkZGYqJidH27dsVERHRbH0DAKC58VkbAIDzw2nPiQ4AAFBj8uTJGj58uFkEr7Fjxw6VlJQoLi7O3Ga1WtW/f39t2LBBklRYWKiqqiq3mJCQEEVGRpoxGzdulM1mMwvoktSnTx/ZbDYzpj4VFRUqLy93uwEAAAAAcCYaNRL9ZNXV1VqwYIH+9re/adeuXaqsrHTb/9NPPzVZ4wAAQNNqyjyenZ2tTz/9VAUFBXX2lZSUSJKCg4PdtgcHB2vnzp1mjLe3t9q3b18npubxJSUlCgoKqnP8oKAgM6Y+qampmjNnTqP7AgBAS+OzNgAArddpj0SfM2eO5s+fr9GjR8vlcmnatGkaNWqULrroIiUnJzdDEwEAQFNpqjy+e/du3XvvvcrKylKbNm0ajDt5sTTpxDQvtbfVVjumvvhfO86sWbPkcrnM2+7du095TgAAWtq5/Kx97NgxPfzwwwoLC5OPj48uv/xyPfbYYzp+/LgZYxiGkpOTFRISIh8fHw0YMEBbt251O05FRYWmTJmiDh06yM/PTwkJCdqzZ49bTFlZmRwOh2w2m2w2mxwOhw4cONCk/QEAoLmddhF9xYoVysjI0IwZM+Tp6anbbrtNr7zyih555BHl5+c3RxsBAEATaao8XlhYqNLSUvXq1Uuenp7y9PRUXl6enn/+eXl6epoj0GuPFi8tLTX32e12VVZWqqys7JQxe/furXP+ffv21RnlfjKr1aq2bdu63QAAaM3O5Wftp556Si+99JLS09O1bds2zZs3T08//bTS0tLMmJoFwtPT01VQUCC73a7Bgwfr4MGDZkxSUpJWrVql7OxsrV+/XocOHVJ8fLyqq6vNmMTERBUVFcnpdMrpdKqoqEgOh6NJ+wMAQHM77SJ6SUmJoqKiJEkXX3yxXC6XJCk+Pl7vvvtu07YOAAA0qabK44MGDdKXX36poqIi89a7d2/dfvvtKioq0uWXXy673a6cnBzzMZWVlcrLy1Pfvn0lSb169ZKXl5dbTHFxsbZs2WLGxMTEyOVyafPmzWbMpk2b5HK5zBgAAH4LzuVn7Y0bN+qmm27S8OHD1aVLF918882Ki4vTJ598IqnuAuGRkZFatmyZjhw5opUrV0qSuUD4s88+q9jYWPXs2VNZWVn68ssvlZubK0nmAuGvvPKKYmJiFBMTo4yMDK1du1bbt29v0j4BANCcTruI3qlTJxUXF0uSrrzySq1bt06SVFBQIKvV2rStAwAATaqp8ri/v78iIyPdbn5+fgoMDFRkZKQsFouSkpKUkpKiVatWacuWLRo7dqx8fX2VmJgoSbLZbBo3bpymT5+uDz/8UJ999pnuuOMORUVFmQuVdu3aVUOHDtX48eOVn5+v/Px8jR8/XvHx8YqIiGjiqwMAQMs5l5+1b7jhBn344Yf6+uuvJUmff/651q9frxtvvFESC4QDAFDbaS8s+sc//lEffvihoqOjde+99+q2225TZmamdu3apfvuu6852ggAAJrIuczjM2fO1NGjRzVp0iSVlZUpOjpa69atk7+/vxmzYMECeXp6avTo0Tp69KgGDRqkpUuXysPDw4xZsWKFpk6dan5IT0hIUHp6epO2FQCAlnYuc/QDDzwgl8ulq6++Wh4eHqqurtbcuXN12223SWKBcAAAajvtIvqTTz5p/vvmm29WaGio/v3vf+vKK69UQkJCkzYOAAA0rebM4x9//LHbfYvFouTk5FMuhtamTRulpaW5zcFaW0BAgLKyss6qbQAAtHbn8rP2G2+8oaysLK1cuVLXXHONioqKlJSUpJCQEI0ZM8aMa8kFwqdNm2beLy8vV2ho6K/2CwCA5nLaRfTaoqOj3X6aBQAAzh/kcQAAWqfmzNH333+/HnzwQd16662SpKioKO3cuVOpqakaM2aM7Ha7pBMjyTt27Gg+rqEFwk8ejV5aWmquW3I2C4QzXSwAoDU57TnRPTw8NHDgQP30009u2/fu3ev202sAAND6kMcBAGidzmWOPnLkiC66yL0c4OHhoePHj0uSwsLCWCAcAICTnHYR3TAMVVRUqHfv3tqyZUudfQAAoPUijwMA0Dqdyxw9YsQIzZ07V++++66+//57rVq1SvPnz9cf//hHSWKBcAAAajntIrrFYtGbb76pESNGqG/fvnrnnXfc9gEAgNaLPA4AQOt0LnN0Wlqabr75Zk2aNEldu3bVjBkzNHHiRD3++ONmzMyZM5WUlKRJkyapd+/e+uGHH+pdIHzkyJEaPXq0+vXrJ19fX61Zs6bOAuFRUVGKi4tTXFycunfvruXLlzdpfwAAaG6nPSe6YRjy8PDQc889p2uuuUZ/+tOf9PDDD+svf/lLc7QPAAA0IfI4AACt07nM0f7+/lq4cKEWLlzYYAwLhAMA8IuzWlh0woQJuuqqq3TzzTcrLy+vqdoEAADOAfI4AACtEzkaAIDW5bSnc7nsssvcfpo1YMAA5efna8+ePWfVkNTUVHPetRqGYSg5OVkhISHy8fHRgAEDtHXrVrfHVVRUaMqUKerQoYP8/PyUkJBQpy1lZWVyOByy2Wyy2WxyOBw6cODAWbUXAIDzUXPlcQAAcHbI0QAAtF6nXUTfsWOHAgMD3bZdeeWV+uyzz/Tdd9+dUSMKCgr08ssvq3v37m7b582bp/nz5ys9PV0FBQWy2+0aPHiwDh48aMYkJSVp1apVys7O1vr163Xo0CHFx8erurrajElMTFRRUZGcTqecTqeKiorkcDjOqK0AAJzPmiOPAwCAs0eOBgCg9Trj6VwqKytVWlqq48ePm9vOZLGTQ4cO6fbbb1dGRoaeeOIJc7thGFq4cKFmz56tUaNGSZKWLVum4OBgrVy5UhMnTpTL5VJmZqaWL19urv6dlZWl0NBQ5ebmasiQIdq2bZucTqfy8/MVHR0tScrIyFBMTIy2b9/OiuAAgAtSU+VxAADQtMjRAAC0Pqc9Ev3rr7/W7373O/n4+Oiyyy5TWFiYwsLC1KVLF4WFhZ12AyZPnqzhw4ebRfAaO3bsUElJieLi4sxtVqtV/fv314YNGyRJhYWFqqqqcosJCQlRZGSkGbNx40bZbDazgC5Jffr0kc1mM2PqU1FRofLycrcbAADnu6bO4wAAoGmQowEAaL1OeyT6n//8Z3l6emrt2rXq2LHjWX0jnp2drU8//VQFBQV19pWUlEiSgoOD3bYHBwdr586dZoy3t7fat29fJ6bm8SUlJQoKCqpz/KCgIDOmPqmpqZozZ87pdQgAgFauKfM4AABoOuRoAABar9MuohcVFamwsFBXX331WZ149+7duvfee7Vu3Tq1adOmwbjafzgYhvGrf0zUjqkv/teOM2vWLE2bNs28X15ertDQ0FOeFwCa2pQP723pJuA0pQ16rqWbcEpNlccBAEDTIkcDANB6nfZ0Lt26ddP//d//nfWJCwsLVVpaql69esnT01Oenp7Ky8vT888/L09PT3MEeu3R4qWlpeY+u92uyspKlZWVnTJm7969dc6/b9++OqPcT2a1WtW2bVu3GwAA57umyuMAAKBpkaMBAGi9TruI/tRTT2nmzJn6+OOPtX///jOeN3zQoEH68ssvVVRUZN569+6t22+/XUVFRbr88stlt9uVk5NjPqayslJ5eXnq27evJKlXr17y8vJyiykuLtaWLVvMmJiYGLlcLm3evNmM2bRpk1wulxkDAMCFoqnyOAAAaFrkaAAAWq/Tns6lZgHQQYMGuW2vmR6lurq6Ucfx9/dXZGSk2zY/Pz8FBgaa25OSkpSSkqLw8HCFh4crJSVFvr6+SkxMlCTZbDaNGzdO06dPV2BgoAICAjRjxgxFRUWZ7ezatauGDh2q8ePHa/HixZKkCRMmKD4+XhEREafbfQAAzmtNlccBAEDTIkcDANB6nXYR/aOPPmpw32effXZWjalt5syZOnr0qCZNmqSysjJFR0dr3bp18vf3N2MWLFggT09PjR49WkePHtWgQYO0dOlSeXh4mDErVqzQ1KlTFRcXJ0lKSEhQenp6k7YVAIDzwbnM4wAAoPHI0QAAtF6nXUTv37+/232Xy6UVK1bolVde0eeff66kpKQzbszHH3/sdt9isSg5OVnJyckNPqZNmzZKS0tTWlpagzEBAQHKyso643YBAPBb0Zx5HAAAnDlyNAAArddpz4le4x//+IfuuOMOdezYUWlpabrxxhv1ySefNGXbAABAMyGPAwDQOpGjAQBofU5rJPqePXu0dOlSvfrqqzp8+LBGjx6tqqoqvfnmm+rWrVtztREAADQB8jgAAK0TORoAgNat0SPRb7zxRnXr1k1fffWV0tLS9OOPP55yChUAANB6kMcBAGidyNEAALR+jR6Jvm7dOk2dOlX/8z//o/Dw8OZsEwAAaGLkcQAAWidyNAAArV+jR6L/61//0sGDB9W7d29FR0crPT1d+/bta862AQCAJkIeBwCgdSJHAwDQ+jW6iB4TE6OMjAwVFxdr4sSJys7O1qWXXqrjx48rJydHBw8ebM52AgCAs0AeBwCgdSJHAwDQ+jW6iF7D19dXd911l9avX68vv/xS06dP15NPPqmgoCAlJCQ0RxsBAEATIY8DANA6kaMBAGi9TruIfrKIiAjNmzdPe/bs0euvv95UbQIAAOcAeRwAgNaJHA0AQOtyVkX0Gh4eHho5cqRWr17dFIcDAADnEHkcAIDWiRwNAEDr0CRFdAAAAAAAAAAAfosoogMAAAAAAAAA0ACK6AAAAAAAAAAANIAiOgAAAAAAAAAADaCIDgAAAAAAAABAAyiiAwAAAAAAAADQAIroAADgjCxatEjdu3dX27Zt1bZtW8XExOj999839xuGoeTkZIWEhMjHx0cDBgzQ1q1b3Y5RUVGhKVOmqEOHDvLz81NCQoL27NnjFlNWViaHwyGbzSabzSaHw6EDBw6ciy4CAAAAAEARHQAAnJlOnTrpySef1CeffKJPPvlEf/jDH3TTTTeZhfJ58+Zp/vz5Sk9PV0FBgex2uwYPHqyDBw+ax0hKStKqVauUnZ2t9evX69ChQ4qPj1d1dbUZk5iYqKKiIjmdTjmdThUVFcnhcJzz/gIAAAAALkyeLd0AAABwfhoxYoTb/blz52rRokXKz89Xt27dtHDhQs2ePVujRo2SJC1btkzBwcFauXKlJk6cKJfLpczMTC1fvlyxsbGSpKysLIWGhio3N1dDhgzRtm3b5HQ6lZ+fr+joaElSRkaGYmJitH37dkVERJzbTgMAAAAALjiMRAcAAGeturpa2dnZOnz4sGJiYrRjxw6VlJQoLi7OjLFarerfv782bNggSSosLFRVVZVbTEhIiCIjI82YjRs3ymazmQV0SerTp49sNpsZU5+KigqVl5e73QAAAAAAOBMU0QEAwBn78ssvdfHFF8tqteruu+/WqlWr1K1bN5WUlEiSgoOD3eKDg4PNfSUlJfL29lb79u1PGRMUFFTnvEFBQWZMfVJTU8051G02m0JDQ8+qnwAA/Nb88MMPuuOOOxQYGChfX1/16NFDhYWF5n7WNgEA4BcU0QEAwBmLiIhQUVGR8vPz9T//8z8aM2aMvvrqK3O/xWJxizcMo8622mrH1Bf/a8eZNWuWXC6Xedu9e3djuwQAwG9eWVmZ+vXrJy8vL73//vv66quv9Oyzz6pdu3ZmDGubAADwC+ZEBwAAZ8zb21tXXnmlJKl3794qKCjQc889pwceeEDSiZHkHTt2NONLS0vN0el2u12VlZUqKytzG41eWlqqvn37mjF79+6tc959+/bVGeV+MqvVKqvVevYdBADgN+ipp55SaGiolixZYm7r0qWL+W/DMFjbBACAkzASHQAANBnDMFRRUaGwsDDZ7Xbl5OSY+yorK5WXl2cWyHv16iUvLy+3mOLiYm3ZssWMiYmJkcvl0ubNm82YTZs2yeVymTEAAOD0rF69Wr1799Ytt9yioKAg9ezZUxkZGeZ+1jYBAMAdI9EBAMAZeeihhzRs2DCFhobq4MGDys7O1scffyyn0ymLxaKkpCSlpKQoPDxc4eHhSklJka+vrxITEyVJNptN48aN0/Tp0xUYGKiAgADNmDFDUVFR5oi2rl27aujQoRo/frwWL14sSZowYYLi4+MZvQYAwBn67rvvtGjRIk2bNk0PPfSQNm/erKlTp8pqterOO+885domO3fulNT8a5vMmTPnrPoIAEBToogOAADOyN69e+VwOFRcXCybzabu3bvL6XRq8ODBkqSZM2fq6NGjmjRpksrKyhQdHa1169bJ39/fPMaCBQvk6emp0aNH6+jRoxo0aJCWLl0qDw8PM2bFihWaOnWqOdItISFB6enp57azAAD8hhw/fly9e/dWSkqKJKlnz57aunWrFi1apDvvvNOMa8m1TaZNm2beLy8vZ5FwAECLoogOAADOSGZm5in3WywWJScnKzk5ucGYNm3aKC0tTWlpaQ3GBAQEKCsr60ybCQAAaunYsaO6devmtq1r16568803JZ1Yk0RibRMAAGowJzoAAAAAABeQfv36afv27W7bvv76a1122WWSxNomAADUwkh0AAAAAAAuIPfdd5/69u2rlJQUjR49Wps3b9bLL7+sl19+WZJY2wQAgFpadCT6okWL1L17d7Vt21Zt27ZVTEyM3n//fXO/YRhKTk5WSEiIfHx8NGDAAG3dutXtGBUVFZoyZYo6dOggPz8/JSQkaM+ePW4xZWVlcjgcstlsstlscjgcOnDgwLnoIgAAAAAArcp1112nVatW6fXXX1dkZKQef/xxLVy4ULfffrsZM3PmTCUlJWnSpEnq3bu3fvjhh3rXNhk5cqRGjx6tfv36ydfXV2vWrKmztklUVJTi4uIUFxen7t27a/ny5ee0vwAAnK0WHYneqVMnPfnkk7ryyislScuWLdNNN92kzz77TNdcc43mzZun+fPna+nSpbrqqqv0xBNPaPDgwdq+fbuZuJOSkrRmzRplZ2crMDBQ06dPV3x8vAoLC83EnZiYqD179sjpdEo68c23w+HQmjVrWqbjAAAAAAC0oPj4eMXHxze4n7VNAAD4RYsW0UeMGOF2f+7cuVq0aJHy8/PVrVs3LVy4ULNnz9aoUaMknSiyBwcHa+XKlZo4caJcLpcyMzO1fPly8+diWVlZCg0NVW5uroYMGaJt27bJ6XQqPz9f0dHRkqSMjAzFxMRo+/btDf6ErKKiQhUVFeb98vLy5rgEAAAAAAAAAIBWrNUsLFpdXa3s7GwdPnxYMTEx2rFjh0pKShQXF2fGWK1W9e/fXxs2bJAkFRYWqqqqyi0mJCREkZGRZszGjRtls9nMArok9enTRzabzYypT2pqqjn9i81mU2hoaFN3GQAAAAAAAADQyrV4Ef3LL7/UxRdfLKvVqrvvvlurVq1St27dVFJSIkkKDg52iw8ODjb3lZSUyNvbW+3btz9lTFBQUJ3zBgUFmTH1mTVrllwul3nbvXv3WfUTAAAAAAAAAHD+adHpXCQpIiJCRUVFOnDggN58802NGTNGeXl55n6LxeIWbxhGnW211Y6pL/7XjmO1WmW1WhvbDQAAAAAAAADAb1CLj0T39vbWlVdeqd69eys1NVXXXnutnnvuOdntdkmqM1q8tLTUHJ1ut9tVWVmpsrKyU8bs3bu3znn37dtXZ5Q7AAAAAAAAAAAna/Eiem2GYaiiokJhYWGy2+3Kyckx91VWViovL099+/aVJPXq1UteXl5uMcXFxdqyZYsZExMTI5fLpc2bN5sxmzZtksvlMmMAAAAAAAAAAKhPi07n8tBDD2nYsGEKDQ3VwYMHlZ2drY8//lhOp1MWi0VJSUlKSUlReHi4wsPDlZKSIl9fXyUmJkqSbDabxo0bp+nTpyswMFABAQGaMWOGoqKiFBsbK0nq2rWrhg4dqvHjx2vx4sWSpAkTJig+Pl4REREt1ncAAAAAAAAAQOvXokX0vXv3yuFwqLi4WDabTd27d5fT6dTgwYMlSTNnztTRo0c1adIklZWVKTo6WuvWrZO/v795jAULFsjT01OjR4/W0aNHNWjQIC1dulQeHh5mzIoVKzR16lTFxcVJkhISEpSenn5uOwsAAAAAAAAAOO+0aBE9MzPzlPstFouSk5OVnJzcYEybNm2UlpamtLS0BmMCAgKUlZV1ps0EAAAAAAAAAFygWt2c6AAAAAAAAAAAtBYU0QEAAAAAAAAAaABFdAAAAAAAAAAAGkARHQAAAAAAAACABlBEBwAAAAAAAACgARTRAQAAAAAAAABoAEV0AAAAAAAAAAAaQBEdAAAAAAAAAIAGUEQHAAAAAAAAAKABFNEBAAAAAAAAAGgARXQAAAAAAAAAABpAER0AAAAAAAAAgAZQRAcAAAAAAAAAoAEU0QEAAAAAAAAAaABFdAAAAAAAAAAAGkARHQAAAAAAAACABlBEBwAAAAAAAACgARTRAQAAAAAAAABoAEV0AAAAAAAAAAAaQBEdAACckdTUVF133XXy9/dXUFCQRo4cqe3bt7vFGIah5ORkhYSEyMfHRwMGDNDWrVvdYioqKjRlyhR16NBBfn5+SkhI0J49e9xiysrK5HA4ZLPZZLPZ5HA4dODAgebuIgAAAAAAFNEBAMCZycvL0+TJk5Wfn6+cnBwdO3ZMcXFxOnz4sBkzb948zZ8/X+np6SooKJDdbtfgwYN18OBBMyYpKUmrVq1Sdna21q9fr0OHDik+Pl7V1dVmTGJiooqKiuR0OuV0OlVUVCSHw3FO+wsAAAAAuDB5tnQDAADA+cnpdLrdX7JkiYKCglRYWKjf//73MgxDCxcu1OzZszVq1ChJ0rJlyxQcHKyVK1dq4sSJcrlcyszM1PLlyxUbGytJysrKUmhoqHJzczVkyBBt27ZNTqdT+fn5io6OliRlZGQoJiZG27dvV0RExLntOAAAAADggsJIdAAA0CRcLpckKSAgQJK0Y8cOlZSUKC4uzoyxWq3q37+/NmzYIEkqLCxUVVWVW0xISIgiIyPNmI0bN8pms5kFdEnq06ePbDabGVNbRUWFysvL3W4AAKB+qampslgsSkpKMrcxJRsAAL+giA4AAM6aYRiaNm2abrjhBkVGRkqSSkpKJEnBwcFuscHBwea+kpISeXt7q3379qeMCQoKqnPOoKAgM6a21NRU88O6zWZTaGjo2XUQAIDfqIKCAr388svq3r2723amZAMA4BcU0QEAwFm755579MUXX+j111+vs89isbjdNwyjzrbaasfUF3+q48yaNUsul8u87d69uzHdAADggnLo0CHdfvvtysjIcPtCu/aUbJGRkVq2bJmOHDmilStXSpI5Jduzzz6r2NhY9ezZU1lZWfryyy+Vm5srSeaUbK+88opiYmIUExOjjIwMrV27ts5i5CfjF2UAgNaGIjoAADgrU6ZM0erVq/XRRx+pU6dO5na73S5JdUaLl5aWmqPT7Xa7KisrVVZWdsqYvXv31jnvvn376oxyr2G1WtW2bVu3GwAAcDd58mQNHz7cXJekRktOySbxizIAQOvDwqIAAOCMGIahKVOmaNWqVfr4448VFhbmtj8sLEx2u105OTnq2bOnJKmyslJ5eXl66qmnJEm9evWSl5eXcnJyNHr0aElScXGxtmzZonnz5kmSYmJi5HK5tHnzZl1//fWSpE2bNsnlcqlv377nqrsAAPymZGdn69NPP1VBQUGdfaeakm3nzp1mTHNMySad+EXZtGnTzPvl5eUU0tEsejyR3NJNwGkqeji5pZuACxRFdAAAcEYmT56slStX6p133pG/v7/5Ydhms8nHx8dcoCwlJUXh4eEKDw9XSkqKfH19lZiYaMaOGzdO06dPV2BgoAICAjRjxgxFRUWZo+K6du2qoUOHavz48Vq8eLEkacKECYqPj1dERETLdB4AgPPY7t27de+992rdunVq06ZNg3EtMSWbdGLUu9VqPeV5AAA4l1p0OpfU1FRdd9118vf3V1BQkEaOHFlnXjRWBAcAoHVatGiRXC6XBgwYoI4dO5q3N954w4yZOXOmkpKSNGnSJPXu3Vs//PCD1q1bJ39/fzNmwYIFGjlypEaPHq1+/frJ19dXa9askYeHhxmzYsUKRUVFKS4uTnFxcerevbuWL19+TvsLAMBvRWFhoUpLS9WrVy95enrK09NTeXl5ev755+Xp6WmOQG+JKdkAAGiNWrSInpeXp8mTJys/P185OTk6duyY4uLidPjwYTOGFcEBAGidDMOo9zZ27FgzxmKxKDk5WcXFxfr555+Vl5enyMhIt+O0adNGaWlp2r9/v44cOaI1a9bU+cl2QECAsrKyzMXFsrKy1K5du3PQSwAAfnsGDRqkL7/8UkVFReatd+/euv3221VUVKTLL7/cnJKtRs2UbDVTqZ08JVuNminZamJOnpKtBlOyAQDORy06nYvT6XS7v2TJEgUFBamwsFC///3v66wILknLli1TcHCwVq5cqYkTJ5orgi9fvtz82XdWVpZCQ0OVm5urIUOGmCuC5+fnmwuaZGRkKCYmRtu3b6/3p+AVFRWqqKgw77MaOAAAAADgt8Df37/Ol9p+fn4KDAw0tzMlGwAAv2jRkei1uVwuSSdGm0ktuyI4q4EDAAAAAC5UTMkGAMAvWs3CooZhaNq0abrhhhvMb75bckVwVgMHAAAAAFwoPv74Y7f7NVOyJScnN/iYminZ0tLSGoypmZINAIDzWaspot9zzz364osvtH79+jr7WmJFcFYDBwAAAAAAAAC0iulcpkyZotWrV+ujjz5Sp06dzO12u10SK4IDAAAAAAAAAFpGixbRDcPQPffco7feekv/+Mc/FBYW5rY/LCyMFcEBAAAAAAAAAC2mRadzmTx5slauXKl33nlH/v7+5ohzm80mHx8fWSwWVgQHAAAAAAAAALSYFi2iL1q0SJI0YMAAt+1LlizR2LFjJZ1YEfzo0aOaNGmSysrKFB0dXe+K4J6enho9erSOHj2qQYMGaenSpXVWBJ86dari4uIkSQkJCUpPT2/eDgIAAAAAAAAAzmstWkQ3DONXY1gRHAAAAAAAAADQUlrFwqIAAAAAAAAAALRGFNEBAAAAAAAAAGgARXQAAAAAAAAAABpAER0AAAAAAAAAgAZQRAcAAAAAAAAAoAEU0QEAAAAAAAAAaABFdAAAAAAAAAAAGkARHQAAAAAAAACABlBEBwAAAAAAAACgARTRAQAAAAAAAABoAEV0AAAAAAAAAAAaQBEdAAAAAAAAAIAGUEQHAAAAAAAAAKABFNEBAAAAAAAAAGgARXQAAAAAAAAAABpAER0AAAAAAAAAgAZQRAcAAAAAAAAAoAEU0QEAAAAAAAAAaABFdAAAAAAAAAAAGkARHQAAAAAAAACABlBEBwAAAAAAAACgARTRAQAAAAAAAABoAEV0AAAAAAAAAAAaQBEdAACckX/+858aMWKEQkJCZLFY9Pbbb7vtNwxDycnJCgkJkY+PjwYMGKCtW7e6xVRUVGjKlCnq0KGD/Pz8lJCQoD179rjFlJWVyeFwyGazyWazyeFw6MCBA83cOwAAAAAATqCIDgAAzsjhw4d17bXXKj09vd798+bN0/z585Wenq6CggLZ7XYNHjxYBw8eNGOSkpK0atUqZWdna/369Tp06JDi4+NVXV1txiQmJqqoqEhOp1NOp1NFRUVyOBzN3j8AAH6rUlNTdd1118nf319BQUEaOXKktm/f7hbDl+EAAPyCIjoAADgjw4YN0xNPPKFRo0bV2WcYhhYuXKjZs2dr1KhRioyM1LJly3TkyBGtXLlSkuRyuZSZmalnn31WsbGx6tmzp7KysvTll18qNzdXkrRt2zY5nU698soriomJUUxMjDIyMrR27do6H/YBAEDj5OXlafLkycrPz1dOTo6OHTumuLg4HT582Izhy3AAAH5BER0AADS5HTt2qKSkRHFxceY2q9Wq/v37a8OGDZKkwsJCVVVVucWEhIQoMjLSjNm4caNsNpuio6PNmD59+shms5kx9amoqFB5ebnbDQAAnOB0OjV27Fhdc801uvbaa7VkyRLt2rVLhYWFkvgyHACA2lq0iM5cqgAA/DaVlJRIkoKDg922BwcHm/tKSkrk7e2t9u3bnzImKCiozvGDgoLMmPqkpqaaed9msyk0NPSs+gMAwG+Zy+WSJAUEBEjiy3AAAGpr0SI6c6kCAPDbZrFY3O4bhlFnW221Y+qL/7XjzJo1Sy6Xy7zt3r37NFsOAMCFwTAMTZs2TTfccIMiIyMl8WU4AAC1ebbkyYcNG6Zhw4bVu6/2z8ckadmyZQoODtbKlSs1ceJE8+djy5cvV2xsrCQpKytLoaGhys3N1ZAhQ8yfj+Xn55vffmdkZCgmJkbbt29XRETEueksAAAXELvdLunEh+eOHTua20tLS80P5Ha7XZWVlSorK3P7AF5aWqq+ffuaMXv37q1z/H379tX5YH8yq9Uqq9XaJH0BAOC37J577tEXX3yh9evX19nXkl+GT5s2zbxfXl5OIR0A0KJa7Zzo/HwMAIDzV1hYmOx2u3JycsxtlZWVysvLMwvkvXr1kpeXl1tMcXGxtmzZYsbExMTI5XJp8+bNZsymTZvkcrnMGAAAcGamTJmi1atX66OPPlKnTp3M7Sd/GX6yhr4MP1XMmX4Z3rZtW7cbAAAtqdUW0fn5GAAArduhQ4dUVFSkoqIiSSe+AC8q+v/s3XVYVNvXB/DvMICEICbGNVCxFQOxERW7sMAuDAwQCxAbFQNFUekysAEDu8VCRELsxsJWume9f/ByfjMiN9Uh1ud5eC6cunucc3assyMaL1++hEgkgrW1NRwdHXHw4EHcuXMH48ePh5qaGkaOHAkAKFOmDMzNzTF37lycO3cOUVFRGD16NJo2bSqMMGvYsCF69eqFyZMnIywsDGFhYZg8eTL69evHo8kYY4yxf4mIMHPmTAQHB+P8+fPQ0dGR2c8vwxljjDFZcp3O5e/g4WOMMcZY4RQREYEuXboIf+eVm+PGjcO2bdtgY2ODtLQ0TJ8+HV+/fkWbNm1w+vRpaGhoCOds3LgRioqKMDU1RVpaGrp164Zt27ZBLBYLx+zatQtWVlbCyLMBAwYUuJ4KY4wxxv7ajBkzsHv3bhw+fBgaGhpCB7MyZcpAVVVV5mW4rq4udHV14ejoWODL8PLly6NcuXKYN29egS/DPT09AQBTpkzhl+GMMcaKnEIbROe5VBljjLHCzcjICERU4H6RSIRly5Zh2bJlBR6joqKCLVu2YMuWLQUeU65cOQQEBPyXpDLGGGNMiru7O4Dcslyav78/xo8fDwD8MpwxxhiTUminc+HhY4wxxhhjjDHG2M9HRD/8yQugA/97GR4fH4/09HRcunQJTZo0kblO3svwz58/IzU1FSEhIflGcOe9DM9baywgIABaWlq/4VMyxhhjP49ce6InJyfjyZMnwt95c6mWK1cONWrU4OFjjDHGGGOMMcYYY4wxxuRKrkF0nkuVMcYYY4wxxhhjjDHGWGEm1yA6z6XKGGOMMcYYY4wxxhhjrDArtHOiM8YYY4wxxhhjjDHGGGPyxkF0xhhjjDHGGGOMMcYYY6wAHERnjDHGGGOMMcYYY4wxxgrAQXTGGGOMMcYYY4wxxhhjrAAcRGeMMcYYY4wxxhhjjDHGCsBBdMYYY4wxxhhjjDHGGGOsABxEZ4wxxhhjjDHGGGOMMcYKwEF0xhhjjDHGGGOMMcYYY6wAHERnjDHGGGOMMcYYY4wxxgrAQXTGGGOMMcYYY4wxxhhjrAAcRGeMMcYYY4wxxhhjjDHGCqAo7wQwxhhjjDHGGGOMMcZYYWJ5bpa8k8D+oS3dXH7ZtbknOmOMMcYYY4wxxhhjjDFWAA6iM8YYY4wxxhhjjDHGGGMF4CA6Y4wxxhhjjDHGGGOMMVYADqIzxhhjjDHGGGOMMcYYYwXgIDpjjDHGGGOMMcYYY4wxVgAOojPGGGOMMcYYY4wxxhhjBeAgOmOMMcYYY4wxxhhjjDFWAA6iM8YYY4wxxhhjjDHGGGMF4CA6Y4wxxhhjjDHGGGOMMVYADqIzxhhjjDHGGGOMMcYYYwXgIDpjjDHGGGOMMcYYY4wxVgAOojPGGGOMMcYYY4wxxhhjBeAgOmOMMcYYY4wxxhhjjDFWAA6iM8YYY4wxxhhjjDHGGGMF4CA6Y4wxxhhjjDHGGGOMMVYADqIzxhhjjDHGGGOMMcYYYwUoUUF0Nzc36OjoQEVFBa1atcLly5flnSTGGGOM/U1cjjPGGGNFF5fjjDHGirISE0Tft28frK2tsXDhQkRFRaFTp07o3bs3Xr58Ke+kMcYYY+wvcDnOGGOMFV1cjjPGGCvqFOWdgN/F2dkZ5ubmmDRpEgBg06ZNOHXqFNzd3bF69ep8x2dkZCAjI0P4OyEhAQCQmJj4j/6/2Vnp/yHVTF7+6ff8X+SkZ/z1QaxQ+Z33R2YK3x9Fzb+5P/LOIaKfnZxig8tx9k9wOc7+DJfj7M9wOf5rcDnO/q7fmUcDXI4XRVyOsz/zS8txKgEyMjJILBZTcHCwzHYrKysyNDT84TlLly4lAPzDP/zDP/zDP7/t59WrV7+jWCxyuBznH/7hH/7hn6Lww+X4j3E5zj/8wz/8wz9F4eevyvES0RP906dPyMnJgba2tsx2bW1tvHv37ofnLFiwAHPmzBH+lkgk+PLlC8qXLw+RSPRL01sUJCYmonr16nj16hU0NTXlnRxWyPD9wf4K3yOyiAhJSUmoWrWqvJNSKHE5/vPxM8j+DN8f7K/wPSKLy/E/x+X4z8fPIPszfH+wv8L3iKy/W46XiCB6nu8LWyIqsAAuVaoUSpUqJbNNS0vrVyWtyNLU1OQHjhWI7w/2V/ge+Z8yZcrIOwmFHpfjPx8/g+zP8P3B/grfI//D5fhf43L85+NnkP0Zvj/YX+F75H/+TjleIhYWrVChAsRicb633B8+fMj3NpwxxhhjhQuX44wxxljRxeU4Y4yx4qBEBNGVlZXRqlUrnDlzRmb7mTNn0L59ezmlijHGGGN/B5fjjDHGWNHF5ThjjLHioMRM5zJnzhyMGTMG+vr6aNeuHby8vPDy5UtYWFjIO2lFUqlSpbB06dJ8Q+wYA/j+YH+N7xH2T3E5/nPxM8j+DN8f7K/wPcL+KS7Hfy5+Btmf4fuD/RW+R/4dERGRvBPxu7i5uWHdunWIj49HkyZNsHHjRhgaGso7WYwxxhj7G7gcZ4wxxoouLscZY4wVZSUqiM4YY4wxxhhjjDHGGGOM/RMlYk50xhhjjDHGGGOMMcYYY+zf4CA6Y4wxxhhjjDHGGGOMMVYADqIzxhhjjDHGGGOMMcYYYwXgIDpjjDHGGGOMMcYYY4wxVgAOojPGGGOMMcYYY4wxxhhjBeAgOiuUgoOD8fbtW3kngzFWxBCRvJPAGGNMDi5evIjU1FR5J4MxxhhjjBVTHERnhc7+/fsxfPhw7NixA+/fv5d3clgh8H1glAOlrCAikQgAkJGRIeeUMMb+KYlEIu8ksCLK19cXXbt2RWBgINLT0+WdHMYYKzHy2mXS7TNuq5U8XIdjP1thvacU5Z0Axr5namqKBw8ewMPDA0SEiRMnQltbW97JYnKSnZ0NRcXcrCouLg5aWlooXbo0xGKxnFPGCpNLly5BSUkJ7du3x9y5c6Grq4upU6cKQXXGWOGnoJDbtyMkJASVKlVCmzZt5JwiVlSYm5sjNjYW06ZNAxHB1NQUqqqq8k4W+8UkEomQbzDGfj/pZzAxMVFoo4lEIn4+SxDp7/ratWvQ1tZGnTp15JwqVpRJx4Du3r2LMmXKQF1dHWXLlpVzyjiIzgqZnJwciMViLFmyBEQEd3d3AOBAegnk4+ODjh07okGDBgCARYsWISQkBJ8/f8bkyZMxZMgQNGnSRM6pZIXB27dv4eDgACUlJZQvXx4HDhxAREQEB9AZKyKkG1/37t3DiBEjMHToUKiqqqJZs2ZyTh0r7PLqjps2bQIRYerUqQDAgfRijoiEfCMwMBDPnj2Dnp4e2rRpAy0tLfkmjrESIu8ZdHR0xOHDh1G+fHl07twZtra2UFBQ4EB6CSD9HS9YsACnT5/GnDlzUKlSJWhoaMg5dayocXR0ROfOndGhQwcAgJ2dHQ4cOICkpCT06tULEyZMQJcuXeSaRhHxWBtWyOQ1hgBg+fLl8PX1xbRp0ziQXoIcP34cU6ZMweDBg2Fra4sbN25gxowZcHFxQXh4OEJDQ1GnTh3Mnz8fLVu2lHdyWSFw4cIFjB8/Hm/fvoWvry/Gjh3LFXfGigAiEl54LVmyBOnp6dizZw/ev3+PAQMGYPHixdDT05NzKllhJ113tLKygpeXFzw9PTmQXkxJ5xv29vbYsmUL6tevj+joaEydOhVTpkzhfIOxX0i6ju3u7o5FixbB1tYWUVFRuHv3LvT19eHn55fvWFZ8LV26FB4eHti9ezfatm0LdXV1mf3S+TZjP3Ljxg1MmzYN1apVw8qVK5GQkIAxY8bAx8cH9+/fx/nz5/HhwwcsXboUPXv2lFs6OYjOCoU/K1yXLl0Kf39/DqSXMFu2bMG2bdtgbGyMrKwstGjRAmPGjAEA7Nu3D66urqhSpQpsbW05kF6C5eUdUVFRmDFjBgCgfPnysLW1RceOHQFwpY2xwkr62XR2dsaKFStw9OhRaGho4NmzZzA3N0f37t1hb2/PPdJZPn9Wd7S0tIS3tzcH0ou5yMhI2NvbY9myZWjbti2Cg4OxcOFCtG/fHpaWlmjevLm8k8hYsXb+/HlERESgYcOG6N+/P5KSkrBv3z44OTmhffv28Pf3B8CB9OLu8ePHGDRoENavX49evXrh06dPePnyJc6cOYPatWtj2LBh8k4iKyIOHToEd3d3lC5dGjVr1kT16tUxe/ZsAMDly5exZcsWvHr1CsuWLZNbIJ2nc2FyJ12oHj16FG/evIGWlhbat2+P6tWrY/ny5cLULiKRCBMmTOBAejGWdz9YWloiJycHAQEBePHiBRo2bCgcY2ZmBgBwc3PD+vXrYWVlhbZt28oryUwO8u6TvLyjefPmuHbtGs6ePYt169Zh5cqVWLRoETp27CgE6VJTU6GmpibPZDPGAAQFBcHExERmbYvr169j2LBhwvDNZs2aQUNDA/3794dEIsGCBQvQokULeSWZFTLSdcezZ8/i27dv0NTUhKGhIVRUVLBlyxZhaheRSARTU1OoqKjIOdXsZ3Jzc8Ply5ehqamJVq1aAQAGDx4MIsLixYshEolgaWnJPdIZ+0WuXr2K8ePHIzU1FcHBwQAADQ0NoZ22fv16mJubw9fXlwPoxcz3L0U0NTWhpKSEFy9e4PLly/Dz80NkZCREIhEePHiAxMREmJubyzHFrLDLmwPdxMQEOTk58PHxwY4dO2BlZSUc06lTJ4hEImzZsgUODg5IT0/HwIEDf3taOTdjciU9n6GdnR0mTZqE3bt3Y9asWZgzZw6OHz8OAHBwcMCECRPg6ekJFxcXfPnyRZ7JZr9I3v2QnZ0NALC2tsakSZOgqqqKkJAQPHnyRDjWzMwMM2fORFRUlHCfsJJBuuIWGBgIV1dXODg44OPHjzA2NoaNjQ0AYM2aNQgNDQUAmJiYIDAwUG5pZozlWrFiBQ4fPiwzOiQzMxPp6enIyMgAkFuRzs7ORrdu3YT1MFxdXfHo0SN5JZsVItJ1xwULFmDs2LFYvXo1+vfvDysrK4SHhwMAtm7dismTJ2P69OnYtm0bMjMz5Zls9pOlp6fj0KFDiIyMxLNnz4TtQ4YMwcqVK3Hjxg0sX74cjx8/lmMqGSu+atWqJQRG9+3bJ2zX0NDA8OHDYWNjg6CgIKxatUpeSWS/gHQ7LCIiAq9fv4aGhgbq1asHf39/GBkZQVNTE2vXrsXly5fRtWtXxMfHyznVrDCTSCTCIqLZ2dkYMmQILC0tUbduXezbtw83btwQju3YsSOsrKygqqqKY8eOySfBxFgh4OzsTH/88QeFhYUREZGLiwuJxWLq2bMnHT58WDjO2tqaBg0aRBKJRF5JZb9ITk6O8HtaWholJCQIf7u7u1OzZs3I0tKSnjx5InPeuXPnKDs7+7elkxUe8+fPp+rVq9PAgQOpZcuWVK1aNdq/fz8RER09epT69etHNWvWpBYtWlDNmjUpMzNTzilmrGRzcHCgR48eUVZWFhER3bx5U3gu3d3dSUFBga5cuUJE/ysTXFxcqG/fvlShQgWytbUlIuI6ACMionXr1lG1atXo+vXrRETk5OREIpGIhg8fTjdu3BCOGz16NBkZGfF9U4RJ1xGl+fr6UsWKFWnu3Ln0/PlzmX0BAQE0cuTIAs9ljP193z9HGRkZRET05csXWrlyJdWtW5fs7e1ljklISKCQkBBupxUj0veBvb09tWzZkoKCgoiI6OPHj3Tjxg26efOmzDnt2rUjJyen35pOVnRI31Pr1q0jGxsbev36NRERHTlyhIyNjalfv34UHh4uc15MTIzcyncOojO5+/r1K1lYWJCHhwcREQUHB5OWlhbZ2NhQ48aNqUOHDhQSEiIcn9cI4sZQ8SGdAa5fv5569uxJ+vr6NGLECHr79i0REW3evJlatGhBlpaW9PTp03zX4ApaybJr1y6qWrUq3b59m4hyX6aIRCKZl27h4eHk7e1Ny5YtE4J2ef9ljP1eAwYMoOrVqwtB82PHjlHdunVp06ZNwrbRo0eThoYGnTlzhhISEig5OZn69+9Phw4dIl9fXxKLxRQXFyfPj8EKiXfv3tHYsWNpx44dREQUFBREWlpaNGfOHCpbtiwNHDhQCK4T/a+ewXXHoke6jnj27FkKDg6mnTt3Ctvc3NyoatWqZGtrSy9evPjLazDG/hnp58fFxYUmT55MBgYGtGPHDnr16hUlJyfTihUrqGHDhrRw4cIfXoPbacXL4sWLSVtbm06ePCnT8S1PQkICPXr0iHr16kXNmzfn9hf7SzY2NlS5cmVyc3MTguhEubHB7t27U79+/fK9oCGST/nOQXQmd9nZ2RQREUEfPnyg2NhYql27Nm3atImIiHbu3EkaGhrUrl07unDhgnAON4KKJ3t7e6pcuTJt3ryZLl68SCoqKtSjRw+hcN68eTPp6+vTmDFj6M2bN3JOLZMnJycnmjRpEhHlBtQ1NTXJzc2NiHIrbj+q0HEFnjH5uHv3LtWuXZtiY2OJiOjkyZOUlZVFo0aNoo4dO5KrqytlZ2fT+/fvafLkyaSoqEgNGzakWrVqUYMGDSgzM5NOnjxJurq69PnzZzl/GlYYpKam0qlTp+jLly8UGRlJtWrVIhcXFyLKrSuoqqpSnz59hBetRBxILepsbGxIV1eXmjdvTs2aNSNdXV169uwZEeUG0v/44w9asGBBvhGLjLGfw9bWlrS1tWnFihW0ZMkSKlOmDE2cOJEyMzPp3bt3tHLlSmrcuDHNnDlT3kllv9CDBw+oQYMGdPz4cSIi+vz5M8XGxtLWrVvp0KFDRETk5eVFPXr0ICMjI6GjBLfDWEGOHz9OVatWlRlFKF1nO3jwIPXs2ZPatm1L9+/fl0cSZfDCouy3+tHK3GKxGI0aNYKqqioOHDiA6tWrY8KECQCArKwsdOzYEQ0bNoShoaFwjvRcqqx4ePToEUJCQrBz504YGxvjwoULEIvFGDJkCDQ1NQEAlpaWSEhIwNOnT1G5cmU5p5jJ0/3795GdnY0bN27AwsICa9euxbRp0wAA/v7+SEpKgr29vUx+I72IIWPs96lVqxbKli0Le3t71K1bF15eXvjw4QPc3NwwY8YM7NixAyKRCFOmTIGXlxeGDh2Kly9fQiwWY8yYMVBUVMTJkydRoUIFXpysBPpR3VFVVRUdOnSAuro6vL290aBBA6HuKJFIYGRkBA0NDTRu3Fg4h++dosvDwwN+fn44efIkWrVqhW3btmHixIl48OABdHR0MG3aNBARrKysUKNGDdSpU0feSWasWLly5QqCgoJw9OhR6OvrIyIiAitWrEDXrl2hpKQEbW1tWFhYIDExEa9fvwYRcXu9mFJUVESpUqWQkpKCS5cuYdeuXQgLC0NGRgYyMjKQk5MDU1NTVKxYEf3794dYLBYWjWTMzc0NU6dOlWmXx8fHo0aNGtDT0xPuFen8w8TEBOnp6QgLC0O9evXkkWwZfCez34akFoJydXXF8+fPoaKiggULFkBdXR0AkJqaiuTkZDx69Ah6eno4dOgQevfuDUtLSwA/bkix4iEhIQGZmZkwNjZGSEgIRo4ciQ0bNmDKlClITEzEkSNHMHr0aCxatEiomPH9UPwV9B2PHTsW48ePx86dO+Hj44OJEycCyM1Dzpw5g7p16/K9wVghoaamhg0bNmDo0KE4c+YMrl+/DjU1NQC59YEZM2Zg+/btkEgkmDJlCnr06CGc++zZM6xduxYHDhzAxYsXoaWlJadPweRBuu7o6+uLN2/eoGLFihg9ejQ0NDQgkUjw/v17pKen49u3b1BTU8OFCxcwZswYjBgxAgDXHYui7wNwT548wfz589GqVSsEBQVh1qxZ8PDwQO/evZGYmAhNTU1Mnz4d2traMDExkV/CGSsmvs8309LSUKlSJejr62Pv3r2YPHkyXF1dMWrUKCQlJeH27dvo0KED7OzsoKWlBZFIxIH0YuBH32GlSpVQpkwZrFmzBlFRUZg5cybWrFmDli1bYtiwYXjx4gXKlCkj5MXSi0ayku3cuXPw8fHB1KlTZbZ//vwZT548gaKiIsRiMXJycoT/Xrx4EY0aNcLw4cMxfPhwAPKv13GNkv02eRnw8uXLsXTpUty9exf79+9H06ZN8erVKwBA27ZtkZKSglGjRqF+/fp4+vQpLCwsAMg2pFjRRkT5tlWuXBmqqqqws7PDqFGjsGHDBiGDffr0KTw8PBAWFgYAQsWM74fiTbqAfPz4MR48eIDk5GQAQMOGDdGzZ0/o6uri69evSEpKwq1btzB06FC8ffsW69evB/Dje40x9ntIP3+xsbHIyspC9erVsXLlSuTk5AAANDU14erqinr16mHPnj1wdnYW9iUmJuLWrVv4+PEjLl68iGbNmsnlczD5yas7Ll68GHZ2djh27Bi2bt2KXr164cuXL1BQUECPHj0QHh6OAQMGoEGDBnj8+DGGDRsGgOuORdGPgjYxMTFISUnBuXPnMGHCBKxZswZTpkwBEcHd3R0uLi4AgCFDhggNb8bYP5dXbuflm6GhocJLynfv3uHgwYP5RoBevHgR7u7uePnyJcqWLcsB9GJCIpEI3+GjR48QFxeHuLg4aGho4NChQ3B0dMTVq1fh4uKCPn36oHLlykLwE8h/L7GSTSKRoFu3brh58ybEYjHOnTuHzMxMAECXLl1QqVIlLFu2DAkJCcI9lJqailWrViEkJETmWvK+p0TEEQb2i33/pmjGjBkYO3Ys2rRpg0ePHsHCwgKPHj3C5cuXoaOjg2vXruHBgwdITU2FhYUFFBUVeQhQMeXs7Iw6deqgb9++SEtLw/Tp0xEcHIyJEydiy5YtAICMjAwMGzYMCgoKCA4OlnumyX4P6cr3smXLsGfPHmRmZiItLQ3e3t7o378/nj9/Djc3NwQEBCAtLQ01a9ZExYoVceLECSgpKclU5Bhj8pOUlISPHz8iLS0Njx8/xpIlS6Cjo4NDhw4Jz3liYiJGjhyJatWqwcPDQ9iempoKIhJGrLGSQbrumJWVBXNzc8yZMweNGzdGaGgolixZgoSEBFy8eBEVKlTAmTNncOvWLYhEIsydOxeKiopcBhRBYWFhUFVVhZ6eHqZOnYpmzZphxowZ2LJlCwICAnDnzh1s2LBB6GDz9etXjBkzBm3btsWiRYvknHrGirakpCRhhI+CggJ2796NFStW4O7du8jJyUGPHj1w6dIlbNiwAbNnzwYApKenY9iwYShdujR2797NgfNiQrodtnz5cgQFBSE1NRUqKipYtWoVBg4cKByTkpKCT58+wcLCAu/evcPNmzc5bsNkTJ8+HUOGDEGXLl2goKCAu3fvomnTppg9ezY2bNiAnJwczJ8/H2FhYWjatCmsrKzw4cMHrF+/Hu/fv0dYWFjhuqd+2+zrrESSXhDg1q1bdPnyZerVqxdFR0cL258/f05dunShatWq0fPnz/NdgxehKL4GDBhA6urqdOLECSIiunnzJnXs2JHatGlDNjY2tHbtWurSpQs1adJEWJSEFwYrWZYtW0aVK1emI0eOUHJyMvXu3ZuqVKlC3t7eRESUkZFB79+/p5MnT9K9e/eE+4NXgWescNi1axcZGBjQnTt3iIgoKSmJdu/eTc2aNaMBAwbILBSekpIiPMOc15dc0t/9vXv3KDo6mrp27UqPHj0iotzF5S9fvkzt2rWjJk2a0MePH4XtebgMKHpev35N2traNHbsWBo3bhypqalRVFQUEeUuZNeyZUtq1qwZHT9+nLKzs+nx48fUp08fat26NX/fjP1HCxYsoKFDhwr5KRFRYGAg9e3bl4hy89QDBw6QgYEB6evr08mTJ8nPz4969uxJjRs3Fp5BLruLlyVLllDFihXp2LFjFBMTQyYmJiQSiWjv3r1ElPt9b9y4kTp27EidO3fmRUTZD9WpU4fq1q1LV65cEe6N3bt3k4qKCs2ZM4eIiDIzM8nR0ZHatm1LIpGImjZtSl27di2U9xQH0dlvYWNjQ5qamtS4cWNSUlKiI0eOyOx//vw5GRsbk6KiIsXHx8splexXKqhSNXbsWNLU1KRjx44RUe7LlsWLF1P9+vWpf//+NG3aNKFixo2kkiU6OpoMDQ2F1d9DQkJIS0uLOnfuTEpKSuTj40Pfvn3Ldx5X4BkrPHbv3k1du3alXr160e3bt4koN1i+e/du0tPTo0GDBskEP4n4GWa5bG1tqVy5ctSsWTMqV64cxcTECPvyAukdO3akSpUqUUJCghxTyv6LI0eOUEpKChERhYWFUfny5UlJSYn2799PRP97ORIVFUXt27en+vXrU8WKFal169bUrl27QtnAZqyoWb58OXXo0IEmT55M79+/JyIib29vGjRokHBMVlYWnT59mvr370+VKlWidu3a0ahRo/gZLKZu3LhBHTt2pPPnzxPR/9phXbt2JQUFBdq3bx8REX379o12794tfP/cXmd5pOvz7dq1o1q1atHly5eFe2Xv3r2kqKgoBNIlEgnl5ORQeHg4PX/+vNB2juMgOvslpBvEZ8+epaZNm9LJkyfp1KlT1KdPH6pSpQrdvHlT5pzHjx+TpaUlF8DFXF7FTPoeGTVqlEwgnYgoPT1d5jy+L0qeZ8+ekbe3N+Xk5NDFixepcuXK5ObmRkRExsbGVK1aNdq8eTOlpaXJOaWMMaKCg98HDx6k7t27U/fu3WUC6Xv27KHKlSuTra3t70wmK6Sk6wUnTpygOnXqUEhICPn6+lLbtm1JR0dHpqOFRCKhc+fO0dSpU7mOUES5ublRrVq1aP369ZSUlET379+n2rVrU9WqVWnChAl069YtmeNfv35NN27cIC8vLwoNDeWgDWP/kXS+u3HjRmrXrh2Zm5vTly9fyMXFhfr06fPD8z5+/EhpaWnC+fwMFj/Pnj2jVatWUU5ODp09e1Zoh339+pXat29PioqKwsjgPFwWM2nftwuMjY1JR0fnh4H0efPmCS/k/uwahQHPic5+OpKaQ2vr1q14//49AGDFihUAcuc3HTZsGKKjo3H48GHo6+vnuwbPY1l8SM9revDgQYwcORJhYWHQ09OTOc7U1BSXL1/G9u3bYWRkBGVlZWEf8eI0xV5Bq2x/+PABlSpVwtixY6Guro6tW7cCACZOnIjLly+jevXquHjxIt8fjBUiR44cgZ6eHmrWrClsCw4OhqenJ4gImzdvRoMGDZCSkoJr166ha9euXOYzgZeXFxITEyGRSGBjYwMiwpMnTzB+/Hi8e/cOV69eReXKlfOdx3XHoic9PR2zZs3C7du3MXz4cMyaNQsAcOXKFYwePRqdOnXCnDlz0KJFiwKvwd87Y/9e3uKRefXojRs3Yt++fdDX14empibi4uLQr18/qKurC+uUffz4ET179sQff/wBgNtpxUFB7bBv375BS0sLY8eOhZaWFjZu3AixWIxx48YhIiIC5cqVQ2hoKADwPcAKNHfuXFSuXBnz589Hu3bt8OHDB2zfvh3t2rWDWCzG/v37MW7cOIwbNw6urq6FvkznFfrYTyVdiEokEly5cgWrVq3CnTt3kJGRAQBQU1NDYGAgWrRogcGDB+PatWv5rlPYHxz29xCRUCDv2bMHrVu3RseOHTFkyBDExMQIxwCApaUl3r9/j969eyMyMlLmOlwoF2/SFbfQ0FBcvnwZN27cAABUqlQJ6enpePbsGSpUqACxWAyxWIy0tDScPHlSCKDz+2DGCofIyEjY29tjwYIFeP36tbB98ODBGDNmDKKjozFnzhxER0dDXV0d3bt3h1gsRk5OjhxTzQqLrKws+Pr6wsbGBo8fPwaQWwfQ1dXF9u3bUaVKFXTu3Blv3rzJdy7XHYuWnJwcqKioYPPmzWjSpAl27twJZ2dnJCcno2PHjvD29saVK1ewefNmREREAAC6dOmCbdu2yVyHv3fG/p28+rdIJEJUVBQkEglmz54NU1NTxMTEwN3dHYGBgfDz84OVlRWmT58OOzs77NmzB1WqVBGuw+20ok26HXbp0iUcO3YML1++RE5ODrS0tJCQkICoqChoa2tDLBYjNTUVycnJ2LRpE0JDQ/n7Z/lIt8tPnDiBo0ePok2bNgCA69evo1KlShg3bhyuX7+OnJwcmJqawt3dHffv3//hy5zChnuis59GOoA+ceJEPHv2DBcvXsS4ceMQGBiI3bt3o3fv3kIP47S0NHTp0gXa2to4fPiwPJPOfgHp+2HdunVwdnbG2bNnUatWLZiYmODJkyc4fPiw0CP9xo0bOHLkCFRVVWFnZ1e4VmBmv4z0fTJnzhzs3r0b2dnZUFFRgYGBAXbu3Al1dXVMmzYNu3fvxujRoxEREYGUlBTExMRALBYX2HuCMfbr/agH2pYtWxAYGIgaNWpg9erVQm81iUSCNm3a4P379xg8eDA2bdrEPdhKuB99/4mJiRg/fjyuXbuG48ePo2XLlsK+p0+fonfv3mjevDn279//u5PLfrLs7GwoKioiPT0dM2fORGxsLIYNG4Zp06ZBXV0dZ8+exYwZM1CuXDmkpqYiNTUVd+/elRmtyBj756Tz3kWLFiEkJATLly+HiYkJAGDTpk04cuQIypUrB39/f2hoaCA5ORmlS5cWzuX6d9EnfR/MmzcPe/bsQUJCAho1aoQRI0Zg+vTpKFWqFGbPng13d3dYWVnh8uXLyMrKwo0bNyAWi7kexwp04sQJHD58GJUrV8ayZcuQnp4OFRUVAEC7du3w8eNHbN++HW3atJGJ/RT2e4qD6Oyne/r0KWbMmIF58+bB2NgYQG4PtMuXL2Pbtm3o0aMHlJSUAACZmZlQVFTkArgYcXJywpQpU1CmTBkAwK1bt7B161aYmZmhV69eAIDk5GQMGjQI9+/fh7OzM2rWrAlHR0dUrVoV7u7uAP7XsGLFl3QBefnyZUydOhV+fn5QU1PD27dvYWFhgVq1auHixYsAgJkzZ+LVq1fQ0tKCj48PlJSUeBg3Y3Ik3YBOSkpCYmIiqlWrBgDw9/eHt7c36tSpAycnJ1SuXBkfPnyAjY0NevXqBVNTUy77SzjpMuDVq1dQVFQUejempqaib9++ePHiBQ4fPoxmzZoJ57158waVK1fmvL+I+j7wlpGRgVKlSiE9PR1WVlaIioqCmZmZEEgPCwvDlStXkJqaCnt7e2FKCa4jMvbfOTg4wNXVFTt37kTz5s1RqVIlYd+GDRsQGBgIPT09LFmyBFWrVhX2cQC96JMug0NDQzF//nxs2rQJFSpUgJOTE2JjY9G7d2/Y2dkhJSUFq1atwq1bt1C9enX4+vpyO4z9qdevX6NPnz548uQJRo0aBW9vbwD/K/MBoGPHjoiOjsa1a9dk6nmFHQfR2U/l7+8Pf39/lC1bFvv27QMA4W3T4MGDceXKFWzbtg3GxsYyvUi4IC4eevTogWfPnuH+/ftQUlLC/v374ejoiPT0dBw6dAgNGjQQCluJRIIRI0bg7NmzUFdXR5UqVXDlyhXhBQsrOQIDA3HgwAGULVsWHh4ewvb79++jS5cuGDRokPByJTMzU8g7uBHNmPxIN75WrlyJc+fO4d69e+jSpQtGjx6Nfv36wdvbGwEBAUhPT4eZmRmOHj0KsViMU6dOQUFBgcv+EsrX1xft2rVDo0aNAAALFizAiRMn8PLlS0ybNg2mpqbQ09MTAulxcXE4fPgwmjZtKnMdbrwXPdLPvIeHB27evIl3796hd+/emDlzJjIzMzFz5kzExMTA1NQU06ZNg5qamkx+w987Yz/Hu3fv0LdvX1hbW2PMmDHCdun69ebNm7FlyxaYm5vDzs5OXkllv1BwcDCOHz+OsmXLwsnJCQCQkpKChQsX4vr16xg4cCDmzZsHZWVlJCUlQUNDAwC3w5isvHJaury+fv067OzsEB8fjw0bNqB///4AZNvzU6dOhZubW5Eq17nlwn6atLQ0vHjxAm/fvsXTp0+hoqICFRUVpKenA8jNoA0NDdGvXz/cunVL5lxuRBd9YWFhePLkCUJDQ6GkpISIiAh07doVVatWxYsXL3D06FEAuXNXZmdnQ0FBAfv27cOZM2dw+PBhXLt2DUpKSsjOzpbzJ2G/Wt67WyLCu3fvsGPHDpw7dw5v374VjsnOzkbDhg0xa9YsREdH49u3bwAgFLhExBU3xuQor4K8bNkybN26FZMmTcL58+dx8+ZNLF++HG/evMHkyZMxf/581KlTBzt27EC5cuVw/PhxDqCXYKGhoZg6dSo8PT3x8uVL7NmzBwEBAZg3bx5sbGywa9cuODk5ISwsDGpqajh+/Dh0dHRgYGCAp0+fylyrKDW4WK68Z97W1hYrV65EuXLlYGxsDCsrK8yZMwfKysrYsmUL9PT0EBQUBCcnJ2RkZMgM6+bvnbGfIzExEc+ePUODBg0A5L7kAiBMsZQ3OmTlypWYP3++PJPKfpHU1FR4eXlhz549uHv3rrBdXV0djo6OaN++PY4ePYqFCxciMzNTCKBzO4xJy1ugGADi4+Px9u1bpKWloV27dtiwYQO0tbXh7e2N06dPA8htz+etl+jp6Vnk1kbi1gv71/IK2jyqqqqYPn06LCws8Pr1a0yfPh0AZALpgYGBsLOzg4GBwW9PL/u16tSpg+zsbKxduxa2trbo1asXypYtC3d3dxgbG+PgwYPYu3cvgNzKWVZWFgCgZcuWaNGihZB5coFcvEkXshkZGahcuTJWrVqFnj174sqVK8JQr7z7oGLFikhISMi3cGhhnieNsZKAiPDy5UscPXoU/v7+GDVqFL59+4b4+HhYWFgI07r069cPu3fvxoULF3DgwAHhZSkH0EsmQ0ND7NixAwcPHoSnpydiYmKwevVqjB49GnZ2dvDy8sLt27exefNmhIWFQVVVFUeOHMGkSZNQq1YteSef/QRXr14VRqA5OTmhTZs2EIlEwlDuUqVKYfPmzahatSpev37N858z9hP8aPKBatWqoWzZsjh27BiA3JdceZ2Zrly5gh07dgAAzMzMilyQi/09ampq2LVrF4YOHYonT57A3d1diPGoqalh1apVqF+/PhISEmRGi3M7jOUhIqFOv2LFCgwYMADGxsZo3rw5jh07Bn19fTg5OeHbt29wdXXFmTNnAECY0iVPkXpBToz9Czk5OcLvjx8/pidPntDHjx+JiCghIYHWrl1LDRs2pDlz5gjHpaamylwjKyvr9ySW/XISiYRycnLowIEDpKWlRWpqavTo0SNh/5MnT6h3797UtWtX2rt3r8x5rOSQzjdWr15N48ePp0+fPhER0b1792jEiBHUunVr2rJlC2VlZdGrV6/I2NiYevfuzfcKY4XQixcvqFGjRkREdPDgQSpdujS5u7sTEVFycjLt3buX3r17J3MOP8slV3Z2tvD7tm3bqFq1aqSqqkobN26UOe7UqVPUtGlTGj16NF26dKnAa7CiKSQkhIyMjIiI6MCBA1S6dGny8PAgIqKvX7/S9evXiYgoIyNDqDdwvsHYvydd/5ZIJJSRkUFEufmppaUltW3blrZt2yYck5WVRT179qThw4fzs1fM5d0bnz59IlNTU+rYsSN5eXnJfO9paWmcF7O/tGzZMqpYsSIdPHiQ4uPjqV27dlSjRg16+vQpERFdvXqVjIyMqEOHDnTjxg05p/a/4W5A7B8jqbdNixYtQp8+fWBkZIRGjRphy5YtUFBQwPTp0zF+/HicOnVKGP6lqqoqcx3ucVx8iEQiKCgo4OnTp8jKyhJ6oOepU6cOtmzZAhUVFfj6+sLf3184j5UcefmGjY0Ntm7dCn19fSQnJwMAGjZsCFtbW9SpUwezZs1Cw4YNMW/ePIhEIgQHB0MkEuUb/cIYky9VVVV8/foVM2fOxIQJE+Dk5AQLCwsAuYuMe3t74+HDhzLncL5fMkkkEpleRuPGjcOmTZugpqaGy5cv48GDB8K+Hj16YMOGDTh9+jTOnz8vc50i1VOJFVhuf/78GZ6enjA3N8e6deswdepUALm91JctW4YXL15AWVlZmPqJ8w3G/h3pqdOcnZ0xcuRItGnTBhs2bMCzZ8+wZMkS1KhRAxs2bMCQIUNgY2MDQ0NDvHnzBjt27BDmOGbFU14eW758eWzduhVVq1bFjh074OfnJ3zvKioqnBezP/X161dcuHAB7u7uMDExQUREBO7fv48FCxagdu3akEgkaN++PRYtWoRmzZpBX19f3kn+b+QcxGdF2Nq1a6lChQp09OhRCg0NpRUrVpCmpibZ29tTdnY2ffr0idatW0cVK1akzZs3yzu57DcICQmhW7dukY+PD+no6NCMGTNk9j958oQMDAzIyspKTilk8hYUFETa2tp08+ZNYVtKSgq9ffuWiIji4uJo+PDh1KJFC1q9erVwTHp6+m9PK2Msl3Qvtu+tWLGCSpcuTePHjyei3F5KaWlp1LdvX+rVq9efnstKBul7YNOmTWRjYyP8vWfPHqpatSpZWVnJjGAjIgoPD+ee50WY9Pd++PBhunz5MmVkZNCLFy/I2NiYSpUqRUuXLhWOSUtLowEDBtDIkSO5tyNjP5mdnR2VL1+eFixYQFOmTKG6detSnz59KCIigr59+0ZeXl5kbGxMJiYmZGlpKYwY55HjRZ90flpQ3pqXX3/48IGGDx9O9evXpyNHjvyW9LGi7/nz51S5cmX69OkTnTlzRmaEWXJyMq1cuZK+ffsmc05Rbh+IiPjVIvvnMjMz0b9/f3Ts2BGLFy8Wtnt7e2PGjBnYs2cPhgwZgvfv3+Ps2bMYPnw49x4qQb58+YI9e/bA2dkZvXv3xtatW4V9b968QZUqVXg+3BJq06ZNOH36NI4fP46YmBicPn0aPj4+SEpKwqRJk+Dg4IDbt29j3bp1iIuLw4wZMzB8+HB5J5uxEku6F5u/vz+eP3+Ojx8/Yvbs2ahbty7i4uLg6OiI/fv3Y9SoUVBUVMTdu3fx4cMHREZGQklJiRcRZQByRyHt3r0b06dPx/Dhw1G7dm0AwK5du2Bra4shQ4bA0tISdevWlTkvJyeH65BFDBEJPRbt7Oywa9curF69Gn379kXZsmXh6+uLjRs3om7duhgzZgwyMzOxbds2xMfHIzIyEoqKipxvMPaTxMTEYMiQIfD19UXnzp0BABcuXICzszMUFRXh5eWFihUr5jsvOzubR44Xcf8kH8079sOHD9i6dSuWLl3KZS/L5/nz59DR0QEA7NixA0OGDIG6ujr69OkDdXV1nDhxAi4uLjA3NwcAvHz5EiNHjsScOXMwePBgmfpBUcVBdPaPSSQSpKWloW3bthg7dizmz5+PzMxMYeGfcePGIS4uDmfOnJFZgIIbQSXL169fsXv3bmzcuBF9+vTB5s2bZfZz46hkOnToEAYPHoxJkybh3LlzaNOmDTp16oQvX75gzZo1iI6ORp06dXD79m2sX78ekZGRWLJkCUxNTeWddMZKNDs7O/j7+6N79+548uQJvnz5gkWLFmHkyJH4+vUrjhw5Aj8/P9SoUQO1atXCihUroKioyI1wBiA37582bRoOHTqENm3aAJANtO7atQv29vYwMjLCqlWr8Mcff8gzuewnWbNmDVxcXBAUFITWrVvLtAsOHjyIgIAAnDx5Evr6+qhcuTICAgKgpKTEbQbG/oPv21j3799Hly5dEBgYiI4dOwrbz549i2HDhiEoKAhdu3aVR1LZLyRdxk6YMAESiQTbt2//03O+z3s5L2bSrly5gvnz52P+/Pm4fPkyXFxc8OTJE9SqVQsODg5wdXVF165dsW/fPgBASkoKTE1NkZmZiZMnTxabe4lbNewvfV8QKygoQF1dHW3btoW7uzvGjx+PihUrIisrC0pKSqhUqRK+ffsmU1EGeB7LkqZs2bIYNWoURCIRbGxsUKtWLcyZM0fYzwH0ksnExATe3t44ePAg7O3tYWxsjJo1a+Lt27c4fPgwUlNTAQDNmjWDtbU1PDw8YGBgIOdUM1ayeXp6Ys+ePTh58iRatGiB0NBQGBkZYcWKFcjOzsbw4cNhbm6OsWPH5nt5zgF0BgCPHj1C8+bN0aZNG6FeKd3AHzVqFBITE3Hq1ClUrVpVzqllP0NSUhLOnj0LW1tbtG/fHq9evcLDhw+xfft26OjoYO7cuRg0aBBevXqFSpUqQVlZGSKRiF+8MfYf5bWxbG1tUaNGDWH+4bdv3wKA0GY3NjbGH3/8gRs3bnAQvZiRLl/v3r2L6OhorF+//i/Pk26fc17MvqejowNtbW1YW1sjMTERMTExwqjC2bNn48WLF4iOjkbXrl1Rt25d3L17F8nJyYiIiIBYLC42L2U4isX+lHQAPSIiAuHh4fj06RMAYM6cOahatSpMTU3x8eNHoedIZGQkKlWqJM9ks18kJyfnHx2vpaWF4cOHY8eOHZg1a9YvShUraszNzXHo0CGYm5ujevXqSE9Ph7m5OUqXLo3GjRsLx7Vs2RJbt25FrVq15JdYxkq49PR0JCcnw9bWFi1atEBwcDAGDBgAb29vtGzZEra2ttizZw++fPnCL89ZgVJSUvDy5UukpKQIAXQFBQVkZWUhODgYRIRp06bh4MGDwgJmrOiTSCR4+fIltm/fDmtrazg6OuLly5c4duwYZs+ejaysLFSrVg2lSpUSFjDkoA1j/470BAOXL1+Gt7c39PX10aZNG5iammLKlCmIiIgQyuqvX78CAL+4LIbyAui+vr5Yvnw5DAwM0K1btz9dJFY68L5p0yZMnz6dy2ImyMnJQbVq1dChQwd8/vwZderUkVkUvkyZMnBxccH8+fNRpUoV5OTkoFevXrh16xaUlJSQnZ1dbNoFPJ0L+1vmzZuHwMBAxMfHo1u3bhg3bhzMzMxw9uxZLFu2DHfu3EGLFi3w7ds3ZGZmIjo6GkpKSsViziOW6+HDh6hfvz4AwNXVFQ0bNvzHvRb4jTaTlp6ejoCAAAQEBCApKQlhYWE8fzJjcvajcvv27duoVKkSUlJSYGJiAnNzc1hbW+P+/fto1aoVypQpAy8vL/Tv319OqWaFRUH59+7du2FjY4P169ejf//+UFdXB5DbW7l3796YOHEiJk6cKDTwue5YPDg5OeHAgQO4f/8+rK2t0bNnT3Ts2BEzZsxARkYGfHx85J1ExoodV1dX5OTkIDk5Gfb29gByX2ROmjQJBw8exOzZs1G6dGmEhobi3bt3uHXrFrfPiqHPnz/DxsYGR44cQZs2bXD06FEAPy6npet+Xl5emDdvHjw8PDBy5Mjfnm5WuHw/evDKlSsQiURwdnbGp0+fhJGof6a49EDPw7kl+yHpjPTMmTM4efIktm/fjpycHGzevBlbtmxBeno6xo0bh9atW8Pf3x9fv35FmTJlYGVlxfOgFiOHDx+GgYEBGjZsiICAAERHR8PPzw83btz4y3O/L6T5fije/mkBmZycDBUVFbRs2RLr1q3jfIMxOcsb4p33OwAoKSmhWbNmAIBTp05BLBajT58+AICPHz9i3Lhx0NbWFraxkku6zA8MDERqaipUVFRgamqKkSNHIjg4GPPnz8enT5/QsWNHiEQi2NnZITMzU2iAcfC8eMhrR8yfPx/Dhg0DAJlRZY8fP0bDhg3llDrGiq/k5GTs3LkT4eHhmDhxorBdXV0de/bsgaOjI86dO4fMzEzUqlULR48ehaKiYrELcpVE37e7y5cvjzlz5kBVVRXe3t5wd3fHtGnThNFeecdKx308PT1hY2ODbdu2YfDgwXL5HKzwkL5PHjx4gAoVKqBJkybQ0tJC1apVYW1tDV9fX4jFYowaNQoAsHbtWsycOVPoLAEUv5Gp3BOd/aljx47h6NGj+OOPP7Bw4UIAQFxcHOzt7REXF4fx48dj0qRJ+c7jgrh4MDQ0RFJSEi5dugRvb2/Y29ujVKlSiI2NRc2aNf+0x7B0gbxlyxYkJydjwYIFvzP57Df6tyMVpBcl5gA6Y/IRGhoKQ0ND4e9169bh/Pnz0NTUhImJidATaceOHbC3t4ePjw/q1asHa2tr6OjowMXFBQCX/SWZdJk/f/58eHl5oUaNGnj06BFGjBiBbdu2AQCmTJmCmzdvIiYmBnp6eihdujTOnz/Pi0kWQ9/XERMTE3Hv3j04ODjg1atXiIqK4jKfsf/oyZMnqFu3LgDAz88PgwYNwpcvX2BnZ4eLFy/i0qVLaNSokUz+mpqaCmVlZeH54/p30Sed3z59+hRJSUnQ1dWFuro63r17hxUrVuDs2bOwsbGBubl5vnMAwNvbG/PmzYOfnx+GDBkil8/BCqeFCxdi165dUFRURPPmzbFkyRI0a9YML168wOzZs/Hp0ycYGBjg0aNHuH79Ot6/f1+s63M8Xp4V6P3791i6dCm2bduGp0+fCttr1qwJR0dH1KpVCwEBAdiwYUO+c4vzQ1NS7Nu3D8+fP0d4eDg0NTWRmZmJrKwsJCcnIzQ0FEDBi4N+PyTMxsYGOjo6vy3t7Pc5fPgw4uPj0bBhQ2G4/tKlS1GzZs2/PJeIhAA6z4PKmHxs374dRkZG2LVrFwBg9erVcHJyQsOGDZGdnY2pU6cKi1GNHTsWtWvXxujRo9G5c2e8fv1aZqEqLvtLrrwy/8OHDwgLC8OVK1dw+vRpHD58GIcPH4aZmRmA3DrBoUOHcPHiRWzbtg2XLl0qdnNlslzf1xFv3LgBe3t7KCoqIjIyUuj9yhj7d65du4aRI0di9+7dsLa2xqRJk5CQkIA6derAyckJenp66NmzJ+Li4iAWi5GdnQ0AUFVVFercXP8u+vLWGAGAxYsXY8CAARgwYABat24NBwcHqKioYO7cuejZsyfWr18PPz8/ALJ5tKurK6ZPn45t27ZxAL2EIyKZufNPnjwJf39/uLu7Y+rUqcjKysLw4cMRGRmJWrVqwcXFBXp6erh79y4UFBQQHx8PsVhcvOfTJ8b+xN27d6lnz57UpEkTCgwMlNkXFxdHvXv3pmnTppFEIpFTCtmvcuHCBapXrx6FhISQvb09TZ48maKiomj9+vUkEonI09OTiIhycnIKvIaHhwdpampScHDw70o2+406depEzZs3p4SEBFq/fj0pKyuThoYGvXjxgoj+/N6QzjM2b95Mjo6Ovzy9jLH8Xrx4QfPmzaMyZcrQtm3byNnZmc6dO0dERJ8/f6Z169aRSCSSeUaPHDlCJ0+epOzsbCIiysrKkkvaWeGyevVq6tmzJ40ePZpSUlKE7RcuXKCyZcuSmZnZD8/7s7KCFU7ff2d/9zuMjIwUjuV8g7H/5tOnT2RqakrVqlUjTU1NioqKIqL/1bGfP39OXbp0oerVqwt1c26zF19r164lbW1tOnXqFBERDRgwgKpUqUIRERFERPTw4UOysrIiLS0tCgkJkTnX3d2d9u3b99vTzAq33bt305IlS2jLli3CtqtXr9LAgQOpfv36dOvWLSIiSklJoZSUFCF/Ke7lOwfRWYHyHoI7d+5Qt27dqFevXnTw4EGZY969eydUhrlQLh7ygiKvXr2iMWPGUN26dUkkEtGTJ0+IiCghIYFWrlxJIpGIfH19hfPs7e0pNDRU+NvT05M0NTXzvXxhxcPevXvpjz/+oMzMTCIicnR0JJFIRCKRiHbs2PGn50rnFZ6enqSiokJ79uz5pelljBXs1atXQiC9SpUqFBYWJuxLSEggJycnUlBQoDVr1uQ7N6/MYCWbRCIhHx8f0tLSosaNGwv3RV5+f+HCBapQoQL16tWLg+ZFnHQZ7u3tTUlJSUT091+cM8b+u7w8dtOmTVS6dGlq3rw57dy5M1+Z/Pz5czI2NiZFRUWKj4+XR1LZLyaRSCgtLY169epF3t7eRER0/Phx0tTUJA8PDyIiob127949cnZ25roby8fY2FimPX7//n1q27Ytqaurk7Ozs8yxV69eJRMTE2rUqBGFh4fL7CsJ5T0H0dmfynsIYmJihED64cOH8x3HDaLiYeLEiXT27Fnhex85ciQpKyuTgYEBHTp0SDguKSmJVq1aRSKRiCZPnkydOnWiBg0ayFTo1NTUKCgoSC6fg/16PFKBseIlLi6OFi5cSIqKikKjK09iYiJt2LCBRCIR7dq1S04pZIXJjxpJycnJtHfvXlJRUaHZs2fn23/y5EkOohdx0t/dq1evSFNTk4yMjCg5OTnffmnS98uFCxcoJibm1yaUsRLixo0bdOvWLRo5ciR16NCBvLy88j2Hz58/p5kzZ3LgtJiSSCSUmJhITZs2pRcvXtC5c+eodOnS5O7uTkREaWlp5Obmli/f5fuB5fn8+TO5ublRRkaGzPYDBw5Qu3btSFdXl54/fy6z79q1a9SxY0caMWLEb0xp4cBBdPaXpAPp3bt3J319fZkex6x4yMjIoKlTpwpvqomI1q9fT/v27aOhQ4dSly5daPfu3TLH79ixg4yNjWnixInCeZmZmWRraytzLCs+eKQCY8XXy5cvafbs2aSiokI7d+6U2fft2zfavXt3sR+iyf6adIDm48eP9PnzZ+Hv9PR02rFjBykrK9O8efP+1jVY0SAdCF+6dCkNGzaMmjRpQiKRiNq2bStM4fP9dyt93tatW6lChQrC9AKMsZ/j/fv3NGzYMOrQoYNM/XvVqlX07ds34W8OnBZ9BZWfRkZG1KpVK9LQ0CA/Pz9h+5s3b6hz5860ffv235VEVoStXbtWZuTpoUOHyMjIiIyMjIRpofLExsaWyPocB9FLsH9SiOZVgCMiIsjKyqpEPizF2fffp5eXFwUHBwvBksjISDIxMaGuXbvmC45Lz3vKwZXijUcqMFb8vXr1iubOnUsaGhr5Aul5OK8vuaTrC6tXryYDAwNq2rQpde3aVQimZ2dn044dO6hUqVJkY2Mjr6SyX2TDhg2kqalJly5dotjYWDpw4ADp6upSq1at8vVIlw6ge3h4kJaWFs+7y9hPlve8ffjwgczMzKhdu3Y0ffp06tOnD5UtW5YD58WIdBn84MEDevXqlZDvnjx5kurVq0ft2rUTjklISKDevXuToaEh3wfsh6TvqZycHKEzjfQ86IGBgdS1a1cyMjKiuLi4P71GSaDw10uPsuLo4cOHEIvFAHJXYz5//vyfHi8SiUBEaNWqFVxcXKCgoICcnJzfkVT2G0ivzp2TkwNvb28sX74cR44cQWZmJlq0aIGlS5dCU1MTvr6+2Ldvn3C8mpoaAF7dvbjLzMyEkpISDA0NIRKJAAAtW7bEzp07UaNGDbi4uGDPnj0AgNKlS2PevHnYvn07nj9/Dl1dXdy+fRtisRhZWVmIj4+Hj48PBg8eLM+PxBj7gT/++APW1taYOnUqLC0t4eXlle8YzutLrrz6wqJFi+Di4oLJkydj69atePr0Kfr27YvY2FiIxWKMHDkSPj4+cHJygqurq5xTzX6WnJwcREdHY/z48TA0NESTJk0wePBg7Ny5Ex8/fkSvXr2QkpICBQUFZGZmCvUFT09P2NjYwMfHB6ampnL+FIwVLUT0w9/zKCgoQCKRoGLFinB1dUX79u3x6tUrlCpVCu/fv4dYLIZEIvmdSWY/mYuLC65duyaUwba2thg4cCAaN24MGxsbXL9+HT179sTMmTPx+vVrNG3aFH369EGvXr0QHx+Ps2fPQiwWc/yG5ZN3Tx08eBDx8fFYtmwZ7OzsYG9vj82bNwMAhgwZghkzZkBJSQl9+vTB+/fvf3iNkkJEP8qJWbF1+PBhGBgYoFq1aggICEB0dDT8/Pxw48YN1KlT50/PlUgkJe4BKQl+9L2mpaVh0KBB+PTpExYsWIB+/fqhVKlSiImJgYODA548eQJnZ2d069ZNTqlmv9P394i3tzcqVKiA/v37Q1FREVFRUXBwcEBiYiImTZqEESNGCMempqYKL1qys7M5+MZYEfH69Ws4ODjgxYsXOH36tLyTwwqRCxcuYM6cOdi0aRM6d+6M48ePY8SIEdDS0oKioiIOHz6MJk2aIDs7G+fOnUO3bt047y9G+vfvj6SkJFy8eFFm+7Jly+Dg4ID27dvj8uXLQgDdw8MDNjY22LZtG788Z+wf+ift77xjs7OzIZFIoKSkBJFIxPXvIu769esYMWIEDA0NMW/ePLx+/RrTpk2Dm5sbnj59iv3790NTUxP29vbo2LEj7t69C09PT5QuXRpVq1aFhYUFFBUV+T5gBXrw4AFGjx6NiRMnYvr06Xj79i28vLzg7OyMlStXwsrKCgCwa9cuhIeHw9nZWeiQWxJxEL0EMTQ0RFJSEi5dugRvb2/Y29ujVKlSiI2NRc2aNf+0kCYioTK8ZcsWJCcnY8GCBb8z+ewXkC5MHzx4IDSAK1SogNTUVAwYMADfvn2TCaRHREQgKCgIK1euLNGZZ0mVk5ODdu3aITMzE0uWLEG/fv2grKyM6OhoLF++HElJSZg8eTLMzMxkzpPOQxhjv9f35fvfbZR/+PABFStWFEaj8TPMAODq1asIDw/H7Nmzcfr0aYwaNQorVqzAoEGD0KpVK9SoUQOurq5o0aKFcA433ouegvKJAwcOwMHBAXPmzMGECROE7QEBATh//jwiIiJQv359HDhwADdv3sTQoUPh7OyMIUOG/M7kM1bkSZe7EyZMgEQiwfbt2//RedwJrngICgrCunXr0LJlS6iqqkJXVxfTpk0DAFy8eBGOjo4Qi8WYO3cujI2N852fk5PD7XYm+FG+MHPmTJw9exbh4eHQ1NTE69ev4ePjg40bN2LVqlWYOXOmzPEl+Z7iHLWE2LdvH54/fy48FJmZmcjKykJycjJCQ0MBFDwMQ7og9vLygo2NDXR0dH5b2tnPt2bNGkRERAgN2gULFqB///5o2bIlbG1tERoaCjU1NRw5cgRaWlpYu3Ytjh07hoyMDOjr62P16tU8JKyE+H74p1gsxqVLl1C5cmU4OjoiJCQEGRkZaN68OZYtW4YyZcrA0dER586dkzmPg2+MyQcRCeW7j48PkpOThaHff6VSpUrCs8vPcMn0o/ukQ4cOMDU1RXZ2NpydnTFlyhRYWFhATU0NOjo6CAsLw8qVK2XO4QB60SLdwD516hR27dqF27dvA4AwjcuuXbvg5uYGIsLHjx+xf/9+1KpVC5aWloiOjsbz58+hr6+Po0ePcgCdsX9Iuv199+5dREdHY+zYsf/ovOzsbA6gF3GZmZkAcqfTWLhwIW7evAlfX198+vRJOMbIyAj29vaQSCRwcXHBoUOH8l2npAY72Y/l5QuHDh0SRpVt3boVqqqqGD9+PIDc6R2nTJmCOXPmwMrKCgcOHJC5Rkm+pzhXLSG0tbWhpqaGU6dOYeHChXj+/DkiIyPh5OSEcePGCXOe/qixJD2f4fz587F7924MHz78t6af/TxXr17Fnj17sGrVKjx48AAXLlxAQEAAtmzZAmtra7x//x4LFy7E2bNnhUB62bJlMXv2bFy/fl3mWiU58ywJpCvfDx48wLt37/Dp0yeoqqoiODgYWlpaWL16NY4ePYqMjAzo6elhwYIF6NOnD4yMjOSbeMYYJBKJUIa/fv0ac+fORf/+/YU5iwsKpEsPUrx48aIQPGMli3QgNTo6Gk+fPsWXL18AANWqVcOnT5/w/PlztGrVCkBunaBWrVq4d+9evsYWK1qk590dOnQoli9fjubNm8PR0RHlypXDunXrUKNGDWzYsAEVK1ZEx44d8fTpUyxZsgR16tRBTk6OkP80bdpUzp+GsaInr+z29fXF8uXLYWBggG7duv1wTvQ80gH0TZs2Yfr06TwXehGWmJgIZWVlALkjgLp37w4HBwf88ccfOHPmDMLDw4VjjYyMsHDhQrx9+xZXrlyRV5JZEXL58mUMHjwY48aNw/LlywEAy5cvx7dv37Bz504AQNWqVTFp0iR4e3tj0KBB8kxu4fJblzFlv13eKsyvXr2iMWPGUN26dUkkEtGTJ0+IKHfF5pUrV5JIJCJfX1/hPHt7ewoNDRX+9vT0JE1NTQoMDPy9H4D9Env37qVu3bqRqakpzZ07lzZv3izsO3v2LA0aNIjat29PZ86cISKi5ORksrKy4lW9S4jVq1fTzZs3hb/t7Oyobt26VKVKFZo4cSJdunSJiIhSUlKoW7du1Lp1awoKCqL09HSZ6/D9wpj8SCQS4felS5fSsGHDqEmTJiQSiaht27aUkpJCREQ5OTkFnrd161aqUKECRURE/J5Es0LJxsaGqlevTpqamjR27Fg6efKksK9Vq1akr69PPj4+1LlzZ2rdurVwT3EZUPRI5wcRERHUtm1bunbtGqWkpNDWrVupdOnSZG9vT+np6ZScnEyPHz+mzZs3U1BQEGVlZRERkZWVFRkaGtLXr1/l9CkYKx4+ffpEEydOpAoVKlDfvn2F7d+X20SyZbenpydpaGjQrl27fks62c934cIFKlu2LCUlJdHcuXOpevXq9ObNGyIiOnjwILVq1YrGjBkj014jIoqMjPzh/cFY3n2Rl1d8+vSJzMzMaPDgwVS1alWaOHEiubi4UN++fWn69OmUkJCQ7xp55XxJx0H0YmzixIl09uxZ4UEZOXIkKSsrk4GBAR06dEg4LikpiVatWkUikYgmT55MnTp1ogYNGgiNn02bNpGamhoFBQXJ5XOwnyczM1P4/cCBA2RsbEwVKlSgtWvXyhx37tw5Gjx4MHXq1IlCQkJk9nGjuHi7cuUKNWvWjExMTOj+/ft0/vx5+uOPP+jEiRO0du1a6tu3L3Xs2FF4wZKSkkI9evSgGjVq0IULF+SbeMZYPhs2bCBNTU26dOkSxcbG0oEDB0hXV5datWpFycnJRJS/Yk1E5OHhQVpaWrRv3z65pJvJj/R9cOnSJWrYsCFdvnyZfH19qW/fvtSlSxehU8WjR4+oTZs2pK+vT7179xbqGdyIL1pu374t8/e6detoxowZNH36dJntbm5uVLp0aVq0aBHFx8fL7Lt16xZZW1uTpqYmRUdH//I0M1bc/CjfvHPnDs2YMYOUlZXJzc3th8d+X3Zrampyu72Ie/nyJXXv3p3Kly9PZcqUoadPn8rsP3DgAOnr69OYMWN+2NGBy2BWEOkXL97e3jRy5Ei6e/cuOTg4kIWFBVWvXp1EIhF5eXnJMZWFGwfRi6mMjAyaOnWqTNB0/fr1tG/fPho6dCh16dKFdu/eLXP8jh07yNjYmCZOnCicl5mZSba2tjLHsqJJujANCQmhjx8/0uHDh6lVq1bUrFkzioqKkjn+/PnzZGhoSBYWFkQkW0FjxRuPVGCseMjOzqYxY8aQlZWVsC0nJ4fCwsKoRo0a1LFjRyGQnpGRIRyT1wjn0Wclz/cN70uXLsncP9euXaPBgwdT586d6fDhw8L2d+/eCfUE7qlUtIwYMULmOyYimj17NolEIjIwMKDPnz/L7HN3dyctLS2aNWsWffr0Sdju7+9PJiYm+QLyjLG/Jp33PnnyhKKiooTyOT4+nqZPn0716tUjHx+fH55DROTl5cVldzFiZ2dHIpGIKlWqRB8+fCCi/B3i2rRpQ3379qUHDx7IK5msCLl+/TqJRCIaPXo03b17l4iIBgwYQKampkRE9PDhQ7K1tSWRSEQ9evQgIo4B/QgH0YuhHxWowcHBQqMmMjKSTExMqGvXrvmC43nDu4m4EVScSGd+CxYsoMqVK5OrqysR5RbARkZGZGJikq/n0K1bt/hNdgnCIxUYK3769etHnTt3zrd96dKlJBKJqEOHDjJlhLu7O2loaHAvthJu/fr1NHToUBo4cCBNnTpVZt+1a9doyJAh1KVLl3zTBXBjq+h58OCB8BItLi5O2L5mzRoSiUTk4uIiBPPyODk5Uffu3fN934mJib8+wYwVM9LP0aJFi6hRo0ZUvXp1atiwIS1fvpy+fv1KT58+JUtLS2rQoIHMFKx5tm7dSoqKihQcHPw7k85+orz7IO+/d+7coXPnzlHv3r2patWqQm906ekzg4KCaMKECdxeZ39LamoqhYWFUYsWLahLly60cuVKevPmDfXo0UMmXzlx4gS36f8EB9GLuezsbGrdujXp6elRUFCQUEmOiooiExMT6tatG+3duzffedwIKp4cHByoQoUKFB4eTt++fRO2Hzx4kHr06EEmJiYUExOT7zwumIs/HqnAWNFWUD69f/9+atKkCfn5+cls37lzJ02YMIGaNm1KQ4cOJSKi8PBwqlGjBvdiK4Gk759Vq1ZRmTJlaPTo0dS4cWNSUVHJFyy/fv06GRkZ0YwZM353UtlPsnfvXnr37p3wt5ubGxkaGtLFixeFbQsXLiSxWEyurq75AunSAR+uAzD2361du5a0tbXp1KlTRJTbQ7RKlSrCdB0PHz4kKysr0tLSyteJxd3dnadfK8K+r8NJd2Z89uwZGRsbU9WqVenFixfC9q1bt8p0gOT2OvsreWX1x48fad26ddS6dWuqUaMGDRw4kEaPHk3v37+XOZ471f4YB9GLmR9lnqmpqdSzZ09q1aoVBQYGCm8vo6OjafDgwdSsWTM6e/bs704q+80+f/5MxsbGFBAQQEREr1+/pvPnz9OkSZNo7969tHr1aurTpw916tRJWHiWlQw8UoGxok36OTx58iQFBAQIL0TfvXtHw4cPp27dupGrqytJJBL68OED9e/fn5YvX05eXl5Ut25devbsGUkkEp6KoYSLioqiDRs2CIHU2NhYmjRpEjVs2JD27Nkjc+ydO3e4DCiitm/fTtWrV6fly5fTly9fiCh3IdG6deuSiYmJsIA4EZG9vT0pKSmRu7s7JSUlyVyHg+eM/XcSiYTS0tKoV69e5O3tTUREx48fJ01NTfLw8CCi/40WvXfvHjk7O3Mv0WJEuhz18PCgCRMm0NChQ2VeisTFxVH37t2pYsWKFBAQQF26dKGWLVtyGcz+sbx7Jisri969e0dTpkwhNTU1EolE3Inmb+IgejEi/abo/v37FB8fTx8/fiSi3GlaunXrli+QfvPmTbKzs+OCuAT48uULVa1alRYuXEiXLl0iMzMzMjAwIH19fapcuTJ5eXnR9u3bacaMGVwgl1A8UoGxos3GxoZKly5Nurq6JBKJaNWqVZSZmUkvX76kCRMmUO3atal8+fJUr149atSoERHlTs+ko6PDL08ZnTt3jkQiEWlra9ONGzeE7bdv36bJkydTw4YNfzh6kcuAosnGxoZatWpFS5cuFXqfRUdHU4MGDah///4ygfRFixaRSCTiqSIY+wUkEgklJiZS06ZN6cWLF3Tu3DkqXbo0ubu7ExFRWloaubm55auDc/u9eLG1taVq1arR5MmTae7cuSQSiWjjxo3C9/z+/XsaMWIENW3alPr06cMLebMfkn65/XdfdB84cIBmz57NPc//Jg6iFwOrV6+WWWXXzs6O6tatS1WqVKGJEycKleC8QHrr1q0pKChIZj4tIi6ISwIfHx8qW7YsaWpqko2NjbAw5MiRI8nc3FzmWC6QSxYeqcBY0SOdT0dERFDbtm3p2rVrlJKSQlu3bqXSpUuTvb09paenU3JyMj1+/Jg2b95MQUFBQkXZysqKDA0N6evXr3L6FKywePbsGdnZ2ZGKiorQ+zFPbGwsWVhYULly5YS6AyuapOv/s2fPpvbt29OyZcuERUILCqR7enpyA5uxn6CgNpaRkRG1atWKNDQ0ZKZge/PmDXXu3Jm2b9/+u5LIfrOAgACqVauW8AL71KlTJBKJSCQS0eLFi2XiNHFxcbyQN/uhfxq/+dHxfE/9NREREViRdfXqVUyfPh21a9fG6tWrER8fj7Fjx8Lb2xu3b99GaGgoEhISsHTpUhgbGyM1NRWDBg3CgwcPsH37dhgZGcn7I7Df7OXLl8jIyICuri4AQCKRoEePHjAwMICjo6OcU8fk5evXr2jSpAkmTJiAHj16wM3NDc+fP4dEIsHr16/h4OCAUqVKITw8HJs3b4aCgoK8k8xYiRUbG4umTZsKfzs5OSEuLg5EBFdXV2G7u7s7bGxsYG1tjRkzZqBy5crCvsjISOzcuRN+fn4IDQ2Fnp7eb/0MrHB6/fo1nJ2d4e7uDm9vb4wePVrYFxUVhTNnzmDu3LkQi8VyTCX7t4gIIpEIAODv74979+7Bz88PEokEc+bMgYWFBSpWrIiYmBiMGDEC9evXx/Tp09G9e3fhGtnZ2VBUVJTXR2CsSJNIJEId+uHDh1BXV0fZsmWhrq6OU6dOwcrKCuXLl8e1a9cAAImJiRg+fDhSUlJw/vx5znuLoczMTPj5+QEALCwscOzYMYwaNQobNmxAdnY2pk2bBicnJ8yYMQMqKirCedL3EmPS5fuECRMgkUiwffv2vzyP76N/Qa4hfPZT7N27l7p160ampqY0d+5c2rx5s7Dv7NmzNGjQIGrfvr3Qcyg5OZmsrKy453kJl5SURJcvX6Z+/fpR06ZN+a0j45EKjBUBI0aMICsrK5lts2fPJpFIRAYGBvT582eZfe7u7qSlpUWzZs0SepoSEfn7+5OJiQnPgc7yefXqFc2dO5c0NDRo586dPzyG65BF2/Lly6lMmTK0e/duOnToEA0dOpQaNGhAy5YtE6aCjI6OprJly5KNjY2cU8tY0bdp0ya6evWq8LeNjQ3Vr1+fNDU1afr06XTt2jUiItq8eTNVr16dmjRpQr1796Z27dpR8+bNhak7OO8t+qQXZc4TFxdHz549ozdv3pCenh45OzsTUe50aurq6iQSicjLy0su6WWFn/S9dOfOHWrevPnfWvNQ+jyOBf193I2gCMvKyoKSkhLMzMwgFovh6emJ8+fPY/78+cIx3bp1g0gkgqurKxwcHJCeno5+/frBxcUFAJCTk8NvtEsgIkJERAQ2bNiArKws3Lp1C4qKinw/lHDm5ubo3r17vpEK79+/h4GBgcyx/MaaMflYunQpdHR0AOSOLKpRowacnZ2hra2NBQsWICAgAObm5lBXVweQ26spOTkZp0+fRrly5YTrjB8/HkOGDIGGhoZcPgcrvP744w9YW1tDJBLB0tISqampmDJliswxXFcomogIX79+xaFDh+Dg4IARI0YAAAYOHAgrKyt4e3tDLBbDwsICenp6CA8PF/Ibxti/c/36dWzcuBGGhoYoXbo0Xr9+jb1798LNzQ1Pnz7F/v378fz5c9jb28PS0hJdu3aFp6cnSpcujapVq8LCwgKKioo8CqQYkO71++nTJygrK0NJSQk1atQAAERERCAnJwe9evUCAKiqqsLc3By9evWSGRHEmLS8Hui+vr44deoUDAwM0K1bN5ne6d+T3rdp0ybcu3cPHh4e3Mb/G3g6lyJKOgM+evQo2rZti2vXrsHBwQFZWVnYvn07mjdvLhx/4cIFLFu2DI0aNYK7u/ufPlCsZMjIyMC9e/egp6cHBQUFrpgxGcnJyYiOjsbatWsRFxeHyMhIvj8Yk6N9+/bByMgI2traAHKnatm7dy8cHBzQuXNnAMCiRYuwZs0abN68GePGjRMC6cD/Kst51T6uA7C/kjeV14sXL3D69Gl5J4f9JBkZGejUqRNMTExgb28vU//r0KED3r59i0GDBmHx4sUoW7YsAO50w9h/FRQUhHXr1qFly5ZQVVWFrq4upk2bBgC4ePEiHB0dIRaLMXfuXBgbG+c7n5/Bok86/rJmzRocO3YMKSkpUFZWhre3N5o2bYqIiAgYGBjAy8sLrVu3xsKFCyESiRASEgKAp9NiBfv8+TNsbGxw5MgRtGnTBkePHgXw4+lapO9FLy8vzJs3Dx4eHhg5cuRvT3dRxK8ZiiAiEh4Ee3t7TJ48Gfv378eAAQNgZ2eHcuXKYfny5YiJiRHO6dKlCzZu3CjMlcqNZ1aqVCm0aNECCgoKkEgkXCAzQd5IhbVr1+YbqcAY+/127NiB+fPnw9PTE1+/fgUAGBgY4O3bt9i0aRNCQ0MBACtXroStrS2sra2xc+dOJCcnC9fIC6CLRCKuA5RAEonkT//+kT/++AMrV67EqVOnAADc76bo+dH3rKysjCpVqiAkJASZmZlQVFQUjmvQoAGUlJSQmZkJLS0t4RwO3jH272RmZgIAhgwZgoULF+LmzZvw9fXFp0+fhGOMjIxgb28PiUQCFxcXHDp0KN91+Bks+vLqXosXL8aGDRtgaWkJT09PJCcnY+DAgYiPj4e+vj6WL1+OKVOmYOjQoXj37h2Cg4MB5JbB3F5neb4v38uXL485c+bAzMwMZ86cgbu7OwAIsZ480gF0T09PzJ8/H9u2beMA+j/x2yeQYT+Ng4MDVahQgcLDw+nbt2/C9oMHD1KPHj3IxMSEYmJi8p3Hcxkzxv5Keno6RUZGCvkFz5PGmHzZ2NhQq1ataOnSpfT+/Xsiyp2zuEGDBtS/f3+6dOmScOyiRYtIJBJRcHCwvJLLChHpOS+9vb0pKSmJiLg+WNxJf783btygsLAwunLlChERvX79mqpVq0YmJib09etXysjIIIlEQmZmZnTw4MEfztnLGPtnEhIShN/3799PqampdOzYMWrUqBF16tSJbty4IXP8pUuXqGXLljR37tzfnVT2C0nnp2/fvqV27drR8ePHiYjoyJEjpKWlRW5ubjLnREVFUXh4OLfD2A9Jl+9PnjyhqKgoSk5OJiKi+Ph4mj59OtWrV498fHx+eA4RkZeXF2lqalJgYODvSXQxwtO5FFFfvnyBmZkZxo8fj1GjRuHNmzd49OgRdu/eDWNjYzx//hyXL19GUlIS/P39UadOHXknmTFWRPGq3YzJT0ZGBkqVKgUAmDNnDm7cuIEePXpg5syZKF++PGJiYjB8+HDo6upi3rx5MDQ0BJA7PHPixInca6mEk86/X79+jcaNG6Nly5Y4evQo1NXVC8zfSaqn0sWLF1GuXDk0a9bst6ad/XvS35+9vT0CAwNRqlQpvHnzBoMHD8by5csRFxcHU1NTaGhoQFtbG0lJSUhKSsL9+/chFou57GfsP7h48SIGDx6Mly9fYtmyZdi/fz/CwsJQtWpVHDp0CCtXrkSjRo1gZWUFfX194byoqChhqk1WvKSmpiIxMRGNGzfGy5cvceXKFQwdOhROTk7C+jWenp6YMmWKzHo1PJUPkyZdvi9evBjBwcFISkpC6dKlMXz4cFhZWeHLly/YtGkTzpw5g/nz52PixIky13B1dYW1tTX279+PQYMGyeNjFGmcOxdRIpEI9+7dw/379xEaGoq5c+fCzs4O0dHRsLa2Rvny5WFmZoZmzZrxgkCMsf+EK/KMyQcRCQF0f39/iMViPHjwAJs2bYKbmxs+fvwIPT097N27F0+ePMHGjRtx5swZAMCUKVOEhchYyURS0/8tW7YMc+bMQY0aNXDp0iUYGxsjNTU13zDfvPPyGmiurq4YNmwYsrKyfnv62b+X9/05OzvD29sbO3fuRGxsLGbPng0/Pz/Ex8ejffv2ePDgAUaMGIHWrVujZ8+euHfvHsRiMXJycrjsZ+w/qFOnDvT19VGrVi34+Pjg4sWLqFq1KgDAxMQEdnZ2uH//PjZv3oxbt24J50lPtcmKj7179woLdrdr1w62trYYOnQoNm7cCAsLCwDA27dvcfr0aYSFhcmcywF0Ji2vfF+3bh28vb2xceNGvHz5Erq6uvDw8MDTp09Ru3ZtzJw5Ez169MDcuXOF+dHziMVi7Nq1iwPo/5b8OsGz/8rHx4fKli1LmpqaZGNjQ2fOnCEiopEjR5K5ubnMsTxklzHGGCuali9fTmXKlKHdu3fToUOHaOjQodSgQQNatmwZffz4kYhyp3YpW7Ys2djYyDm1rLDZsGEDaWpq0qVLlyg2NpYOHDhAurq61KpVK2H4b149UXr6Dg8PD9LS0qJ9+/bJJd3svxs3bhxt2bKFiIgOHDggM21ASkrKD8/haQMY+zns7OxIJBJRpUqV6MOHD0RElJmZKew/cOAAtWnThvr27UsPHjyQVzLZL/D9VFgrV66kFi1aUFRUFE2bNo1EIhFNnTpV2J+SkkJ9+vShnj17ctyG/SmJREJpaWnUq1cv8vb2JiKi48ePk6amJnl4eBDR//KZe/fukbOzM2VnZ8stvcURT+dSxL18+RIZGRnQ1dUFkDtst0ePHjAwMICjo6OcU8cYY4yxf4uI8PXrVxgbG2P8+PGwsrIS9llZWSE4OBgWFhawsLBAhQoV8OTJE+jo6HCvJSbIycnBhAkTULZsWbi4uADIrSvevHkTpqamqFGjBk6ePAl1dXVkZmZCWVkZQO5iUzY2NvDz88OQIUPk+RHYv0BESEtLg56eHhwdHVGtWjX07NlTmDYgKysLCxcuRM+ePdGtWzd5J5exYoH+fxRP3n/v3r2L9+/fY/369YiJicHly5dRu3ZtmWnagoODcfToUfj4+PDoj2KCpEZzffnyBeXKlQOQuyB8jRo1EBgYiP79++PVq1eoX78+dHR0cPXqVSQkJODWrVtQUlLi6bRYgYgIycnJ6NChA0JCQvD06VMMHDhQKN/T09Ph7++PDh06yEzDx9MC/Tz8ZBZxNWrUgK6uLpKTk3HlyhUMHDgQHz58gIODg7yTxhhjjLH/QCQSQV1dHYqKikhOTgYAYXqWzZs3o2bNmvD19YWjoyO+fv2KunXrClMxMAbkDtn9+vUrYmJihG0KCgpo06YNJkyYgKtXr6Jnz54gIiGA7uHhgfnz58Pf358D6EXE91M/iEQiqKmpYdiwYXByckK3bt2wefNmYdqA5ORkREVFydwXjLF/TyKRCIFTkUiE7OxsNG7cGF27doWrqysaNWqETp06IS4uTgigu7q6olevXvDz8+MpXIqRvPtg1apVGDlyJEJCQgAAAQEBiIyMhK+vL/bv34/Ro0cjJSUFz549Q4cOHRAZGQklJSVkZ2dzAJ0JflS+a2hooHz58hgyZAhMTExkyvcvX75g3759iI6OljmPA+g/Dz+dxQARISIiAmvXrkVWVhZu3boFRUVFbkQzxhhjRciPGtDKysqoUqUKQkJCkJmZCUVFReG4Bg0aQElJCZmZmdDS0hLO4YpyyVRQAGbs2LH4/Pkz/P39ZbbXrVsX48ePR2JiIkxNTQEAN2/exOrVq+Hv74/Bgwf/8jSz/066x+KdO3dw6dIlPH/+HJmZmejXrx8SEhLQunVrdOrUCQDw7t07jB49GqmpqZg1a5Y8k85YsSD9DHp6emLixIkYMWIE9u/fDwDQ0dGBr68vGjdujNatW2PXrl3o2rUr/Pz8oKKiIlyHA6fFR05ODm7fvo3Tp09jxIgRsLe3R0pKCkaMGIFTp07h3bt3mDdvHo4ePYr9+/djzZo1QvyGF4RneaTzlocPH+L169dISUkBANjZ2SEpKQlNmjTBhAkTAACJiYmYNGkSiAijRo2SW7qLO57OpZjIyMjAvXv3hNW8s7OzOQNmjDHGigjpinJ4eDiICNnZ2ejQoQPevHmDNm3aoHXr1vD394eamhqUlJQwYsQIDB8+HAMHDpQZQs5KHun759SpU/j06ROaNm2KZs2a4f3797C2tsbHjx8xePBgTJs2DZ8+fYK5uTn09fVRpUoVrFu3DqdPn0atWrVw584dNG3aVM6fiP0d0s/8ggULEBISgs+fP6NevXqoVKkStm/fjqCgIHh4eCAuLg6VK1cWFpy9du0alJSUeIg3Yz+JnZ0dAgIC0KdPH2hqasLZ2RnOzs6wtLSEWCzGhw8fYG1tjTt37qB69eo4dOgQT91RjF24cAHbtm1D27ZtERQUBF1dXXz58gXh4eGYO3cuZs6cKe8kskLKxcUFrVu3Rvv27QEAtra2OHz4MOLj4zF69GiMHj0a7dq1w5YtW+Dk5IQyZcqgevXq+PbtG9LS0hAeHs7l+y/EQfRiiAtixhhjrOiQDoTZ29sjMDAQpUqVwps3bzB48GAsX74ccXFxMDU1hYaGBrS1tZGUlISkpCTcv38fYrGYy34GILeh5ebmhipVquDJkydYuXIl5s+fj3fv3mHp0qW4dOkSEhISUL58eSgqKuLu3bs4f/48Jk2ahDNnzqBOnTry/gjsX9i0aRMcHR0RGBgIQ0NDzJgxA76+vjhz5gw6deqEmJgYxMbG4vXr16hduzaGDBkCsVjMnW4Y+0l27dqFRYsWYd++fTAwMMDp06fRq1cvAMCiRYuwdOlSIZj18uVLVK9eXZj2hZ/B4mPjxo0AgNmzZ0MikQi9gj08PLB//36EhobC19cXABATE8MvrFk+169fx4gRI2BoaIh58+bh9evXmDZtGtzc3PD06VPs378fmpqasLe3R8eOHXH37l14enqidOnSqFq1KiwsLKCoqMh5yy/EQXTGGGOMsULA2dkZq1evxtGjR9GmTRusWLECS5cuRXh4OPT19ZGcnAxnZ2ckJSVBSUkJDg4OwvBf7mlSMkm/PLl16xZmzpwJZ2dn6Onpwd/fH3Z2drCyssKSJUuQnZ2N+Ph4nDhxAtWqVcOAAQOgqKiIWbNmITo6GocPH5aZFogVfkSErKwsjBkzRgieHz9+HGZmZnB2dsbkyZORmZmJnJwcqKqqypzL+QZjP0dmZib8/PwAABYWFjh27BhGjRqFDRs2IDs7G9OmTYOTkxNmzJghM30Lv/wuXjIzM7Fu3TosW7YMw4YNw6RJk2BkZAR9fX2YmZnBzs4OOTk5sLGxQWxsLE6cOMF5MPuhoKAgrFu3Di1btoSqqip0dXUxbdo0AMDFixfh6OgIsViMuXPnwtjYON/5XL7/WhxEZ4wxxhgrBMaPHw99fX3MnDkTgYGBmDx5MhwdHTFt2jSkpqZCTU0t3znc06Rkio2NlenB5uTkhLi4OBARXF1dhe3u7u6wsbGBtbU1ZsyYgcqVKwv7IiMjsXPnTvj5+SE0NBR6enq/9TOwn0MikaBnz56wsbFBVlYWzMzM4OTkBAsLC2RlZWHnzp2oVKkS+vbty9M9MfYT5I0ekx5F9vLlS+Tk5KBUqVLo06cPxo0bh9mzZyM2Nhbt2rVDamoqPD09MXnyZDmnnv1qd+/exeLFixEfH49GjRqha9euCA4OxoIFC6Cvrw/gf/cQBzuZtMzMTGGR9yNHjsDBwQGPHz/GvHnzsHjxYuG4ixcvYvXq1VBWVoa5uTlMTEzklOKSiV99MsYYY4zJEREhNTUVV69ehba2Nq5du4YJEyZg9erVmDZtGrKysrBs2TKcO3cu37kcQC95Ro4cCR8fH5lt8fHxcHNzQ0REBL58+SJsz+sBuXXrVqxZswafP38W9t2+fRsvXrzAlStXOIBeRPxo8VgigrKyMubMmSP0frWwsAAAfPz4EXv37sXbt285gM7YTyCRSIRn6dOnT0hISEBqaipq1KgBHR0dvH37Fjk5OcJULqqqqjA3N8exY8eExf9Y8da4cWN4eXnB1tYWsbGxMDc3x6VLl3Ds2DHhmLyXMBxAZ3kSExOFAPqBAwfQvXt3ODg44I8//sCZM2cQHh4uHGtkZISFCxfi7du3uHLlirySXGJxT3TGGGOMsd+ooCHc9vb2OHv2LGJjY+Hm5iY0uL9+/QpTU1P07t0bc+bM+d3JZYXMw4cPoaOjA2VlZbx8+RI1atQAAKxduxYLFizApk2bYG5uDnV1deGc9evX4/Tp0zh16pRMMDUpKQkaGhq//TOwf04637h//z40NDRARKhevTqePn2KPn36QEVFBeHh4cjOzkZ6ejrGjBmDxMREXLp0iYM1jP1H0j3P16xZg2PHjiElJQXKysrw9vZG06ZNERERAQMDA3h5eaF169ZYuHAhRCIRQkJCAPDosZJo8eLF2LRpE/T19XHhwgV5J4cVQhcvXsTgwYPx8uVLLFu2DPv370dYWBiqVq2KQ4cOYeXKlWjUqBGsrKyE0QwAEBUVBT09PZ4W6jfjIDpjjDHG2G8iHQi7c+cOPn/+jBo1aqBatWqIiIjAhAkToK2tDT8/P9StWxfv3r2Dubk5vn37htDQUA6ElWD79u2DkZERtLW1AeRO1bJ37144ODigc+fOAHIXsFuzZg02b96McePGyQTSpacgAMA9k4soW1tb7Nu3D5mZmdDU1ISVlRWmT5+OU6dOYeTIkahcuTLEYjE0NTWRmpqKGzduQElJiacNYOwnWbx4MTw8PODq6godHR1MmDBBGE1WpUoVYT2TOnXqoEyZMrh+/TqUlJRkgvCs+JP+viMiItCiRQuIxWK+D1g+r169grm5OSIjI5GdnY3IyEjUrl1b2B8YGIi1a9eiYcOGmDVrFlq1aiVzPq+v8Hvxa1DGGGOMsd+AiIRK7oIFCxASEoLPnz+jXr16qFSpErZv345FixbBw8MDRkZGqFy5snDOtWvXIBaLORBWQu3YsQOLFi3CpEmTYGlpibJly8LAwADOzs7YtGkTRCIRDA0NsXLlShARrK2toaCggNGjR6N06dIAkG8OX1Y0SH9nR44cwc6dO+Hr64vU1FTcuXMHlpaW+PbtG+zt7fHw4UPs2LEDEokE1apVg6mpKcRiMfd+Zew/kH4B+e7dO5w7dw47duxA7969ERISgjdv3sDR0RFVqlQBkBtk79+/P7KystCqVSsoKCjwM1gCSZe5eb2HuQ7HfqR69epo1aoVzp49i4oVKwojBLOysqCkpIShQ4cCyB1VuHTpUmzYsAH169cXzucA+u/FPdEZY0VGrVq1YG1tDWtr6791/LZt22BtbY1v374VeMyyZctw6NAhREdH/5Q0MsbYX9m0aRMcHR0RGBgIQ0NDzJgxA76+vjhz5gw6deqEmJgYxMbG4vXr16hduzaGDBnCgTAGW1tbnDt3Dv369cP06dNRqVIlxMTEYPjw4dDV1cW8efNgaGgIIDeIs2rVKgQFBWHQoEFyTjn7GUJCQnDkyBHo6OjA3t5e2O7v7w9zc3Ps2bMHZmZm+c7joA1jP0dqaioSExPRuHFjvHz5EleuXMHQoUOFhXyTk5Ph6emJKVOmyEyTxc8gY+x73y9QfPfuXbx//x7r169HTEwMLl++jNq1ayMjIwOlSpUCAAQHB+Po0aPw8fHhwLkc8b88Y7/B+PHjIRKJIBKJoKSkBG1tbXTv3h1+fn4/XCSqqLK0tISuru4P97158wZisRjBwcH/+vo3b97ElClT/vX5jDEmT0SEzMxMXL9+HUuXLoWhoSGOHz+OHTt2YMuWLejUqRMyMzNRr149jB49GnZ2dkJP0pycHA6gl1AZGRkAcuc8NzQ0xJkzZ+Du7o7Pnz9DT08Pe/fuxePHj7F+/XqEhoYCAFasWAEPDw/0799fnkln/4F0/fDRo0dYsWIFDhw4gPT0dAC5+YlEIsHYsWMxYsQIHDlyBFlZWcjJyZG5DgfvGPvv9u7dC2tra4hEIrRr1w62trYYOnQoNm7cKCzk+/btW5w+fRphYWEy5/IzyBiTJr1AsUgkQnZ2Nho3boyuXbvC1dUVjRo1QqdOnRAXFycE0F1dXdGrVy/4+flBQUGhWMWQihoOojP2m/Tq1Qvx8fF48eIFTpw4gS5dumDWrFno168fsrOz5Z28n8Lc3BxPnjzB5cuX8+3btm0bypcv/68a9JmZmQCAihUrQk1N7T+nkzHG5EEkEkFRURFfvnxBvXr1cPz4cZiZmcHJyQmTJ09GVlYWAgICcO7cOXw/UJAb4SUTEQkNKH9/f4jFYjx48ACbNm2Cm5sbPn78KATSnzx5go0bN+LMmTMAgClTpkBRUbHY1DFKEun5TY8cOYLy5ctj4cKF0NXVRUBAAG7dugWRSAQFBQWIxWKUK1cOHz9+hJKSEucVjP0E35fBT58+RUREBOLj41GjRg24ublh1KhRmDRpEoDcXuqzZ8+GSCRCt27d5JFkxlgRIF2+e3p6YuLEiRgxYgT2798PANDR0YGvry8aN26M1q1bY9euXejatSv8/PygoqIiXId7ossP/8sz9puUKlUKlStXRrVq1dCyZUvY29vj8OHDOHHiBLZt2wYAePHiBUQikczUIt++fYNIJMLFixcB5K7eLBKJcOrUKbRo0QKqqqro2rUrPnz4gBMnTqBhw4bQ1NTEiBEjkJqaKlzHyMgIlpaWsLa2RtmyZaGtrQ0vLy+kpKRgwoQJ0NDQQJ06dXDixAkAuZXHunXrYv369TKf486dO1BQUMDTp0/zfcbmzZujZcuW8PPzy7dv27ZtGDt2LBQUFGBubg4dHR2oqqqifv36cHFxkTl2/PjxMDExwerVq1G1alXUq1cPQO50Lps2bRKOc3Z2RtOmTaGuro7q1atj+vTpSE5Ozvf/PnToEOrVqwcVFRV0794dr169KviLQm6gomHDhlBRUUGDBg3g5uYm7Mv7joKDg9GlSxeoqalBT08P169f/9NrMsZKnh/1EiEiKCsrY86cORg1ahQ2bNgg9GL7+PEj9u7di7dv3/K81QzA/xb/dHBwwOzZs4Uy1tjYGLt374abmxs+ffoEPT097NmzB5cuXcLZs2dlrsEjGIoW6bUT7O3tMXXqVOzbtw8DBw7EggULUL16dSxatAhRUVEAgJSUFNy+fRuVK1eWZ7IZKzak1yH48uULAGDhwoVQVFTEypUr4ebmhr59+yIsLAxmZmaws7NDz5498erVK4SEhHAvUcZYgfLKdzs7O6xYsQKKioqoWbMmhg8fjk2bNiEnJwc1atRAQEAAjI2NsXbtWqiqqiIsLIzzlsKCGGO/3Lhx42jgwIE/3Kenp0e9e/cmIqLnz58TAIqKihL2f/36lQDQhQsXiIjowoULBIDatm1LV65cocjISKpbty517tyZevToQZGRkRQaGkrly5enNWvWCNfp3LkzaWho0IoVK+jRo0e0YsUKUlBQoN69e5OXlxc9evSIpk2bRuXLl6eUlBQiIlq1ahU1atRIJr2zZ88mQ0PDAj+rq6srqaurU1JSkrDt4sWLBIDu3r1LmZmZtGTJEgoPD6dnz55RQEAAqamp0b59+2T+vUqXLk1jxoyhO3fuUGxsLBER1axZkzZu3Cgct3HjRjp//jw9e/aMzp07R/Xr16dp06YJ+/39/UlJSYn09fXp2rVrFBERQQYGBtS+fXvhmKVLl5Kenp7wt5eXF1WpUoWCgoLo2bNnFBQUROXKlaNt27bJfEcNGjSgo0eP0sOHD2no0KFUs2ZNysrKKvDfhTFWsuTk5Ai/37t3j169ekUvX74kIqInT55QvXr1qFmzZpSenk7Jycn06dMn6t27N3Xo0IGys7PllWxWyEgkEvr8+TO1aNGCXFxcZPZZWlpStWrVaMWKFfTx40ciInr8+DHfP8WEg4MDVahQgcLDw+nbt2/C9kOHDlGHDh1IQ0ODDA0NyczMjJo3b04ZGRlElHvPMMb+u5UrV1LPnj3pyJEjRET08OFD0tHRIR8fH0pNTSUnJyfq27cvDRs2jGxtbYV2ALcHGGN/JiAggGrVqkU3btwgIqJTp06RSCQikUhEixcvlqnHxcXFCeU65y2FAwfRGfsN/iyIbmZmRg0bNiSifxZEP3v2rHDM6tWrCQA9ffpU2DZ16lTq2bOn8Hfnzp2pY8eOwt/Z2dmkrq5OY8aMEbbFx8cTALp+/ToREb19+5bEYrGQwWdmZlLFihWFgPKPfP36lVRUVMjPz0/YNnbsWGrXrl2B50yfPp2GDBki/D1u3DjS1tYWGoR5vg+if2///v1Uvnx54W9/f38CQGFhYcK2+/fvEwDhM30fRK9evTrt3r1b5rorVqwQ0p/3Hfn4+Aj77969SwDo/v37BaaNMVYy2djYUM2aNalKlSpUv359cnV1JSKikydPUrly5ahRo0bUtGlT6tChA7Vo0YIyMzOJiDgQygTp6enUunVrWrVqFRHJNqLat29PtWrVotmzZ9OXL1+E7Xz/FG2fP38mY2NjCggIICKi169f0/nz52nSpEm0d+9ecnZ2pg4dOlCrVq3I29tbOC8v/2CM/TfZ2dlkampKIpGI1NXVacGCBRQZGUn29vY0bNgwevbsWYHnMcZYQTIyMsjd3Z3c3d2JiOjo0aNUpkwZ8vHxIQ8PDxKJRLR+/XpKS0uTOU+6cw6TLx7fyZickdSQwX+iWbNmwu/a2tpQU1ND7dq1ZbaFh4cXeI5YLEb58uXRtGlTmXMA4MOHDwCAKlWqoG/fvvDz84OBgQGOHj2K9PR0DBs2rMB0aWlpYfDgwfDz88OECROQlJSEoKAgmWlYPDw84OPjg7i4OKSlpSEzMxPNmzeXuU7Tpk2hrKz8p/8GFy5cgKOjI+7du4fExERkZ2cjPT0dKSkpUFdXB5A7jF1fX184p0GDBtDS0sL9+/dhYGAgc72PHz/i1atXMDc3x+TJk4Xt2dnZKFOmjMyx0v+WVapUEf7dGjRo8KdpZowVb9J5+pEjR7Bz5074+voiNTUVd+7cgaWlJb59+wZ7e3s8fPgQO3bsgEQiQbVq1YRFRLOzs3kKjhJKeq7MPMrKyqhSpQpCQkIwb948KCsrC8c1aNAAHz9+RGZmJrS0tIRzeF7sok0kEuHevXu4f/8+QkND4ebmhufPn0MikeDo0aNYvnw5rK2t4e3tjaNHj6Jjx45o0KABlJSU5J10xooFsVgMCwsLqKiooG3btggKCsLXr1/x5csX3Lx5E8eOHcPMmTN/eB5jjOXJaxfk/VdZWRl9+vRBTk4O3r59i4ULF2Lp0qUwNzdHbGws1NTUMH/+fGhqasrEI3gO9MKDvwnG5Oz+/fvQ0dEB8L/MkaQWs8nKyvrhedINJZFIlK/hJBKJ8s2Z9aNjvr8OIDuP76RJk7B3716kpaXB398fZmZmf7m4p7m5Oa5cuYLHjx9j3759AAAzMzMAwP79+zF79mxMnDgRp0+fRnR0NCZMmCAsHponLwhekLi4OPTp0wdNmjRBUFAQbt26BVdXVwD5/81+9JLiR9vyPre3tzeio6OFnzt37iAsLEzm2L/6d2OMlUx5+UFISAhCQkIwc+ZM9O7dG0OGDMHSpUvh4+ODRYsWYd++fahQoQLmzJmDefPmYcSIERCLxcjJyeEAegklHUAPDw/HjRs3cPXqVYhEIri5ueHVq1cwMzPDt2/fkJ2dDSJCSkoK1q1bhy1btgiNNFb0lS1bFg4ODnBzc0P//v1Rs2ZNrFq1Cjdv3kTXrl0RHh6OoUOHYuLEiUhLS8P06dNx9+5deSebsSJv48aN2LhxIwCgc+fOEIvFCA8Px7Fjx9C+fXtoamoiLi4OVlZWiI2NlXNqGWOFmUQiEdoFnz59QkJCAlJTU1GjRg3o6Ojg7du3yMnJQa9evQAAqqqqMDc3x7FjxzBhwgR5Jp39CW6lMSZH58+fR2xsLGbPng0AqFixIgAgPj4eLVq0AACZRUbloU+fPlBXV4e7uztOnDiB0NDQvzynS5cuqF27NrZt24YLFy7A1NQUGhoaAIDLly+jffv2mD59unD8jxYp/SsRERHIzs7Ghg0bhKBD3qrW0rKzsxERESH0On/48CG+ffv2wx7j2traqFatGp49e4ZRo0b94zQxxkou6QDoo0ePsGLFCjx69AhWVlYAcl+OEhHGjh2Ls2fP4siRIxg8eDAUFBRkeq5xL7aSib5bTDIwMBClSpXCmzdvMHjwYCxfvhz79++Hqakp2rVrB21tbSQlJSEpKQm7du0SXpxzT6Xiw9zcHN27d0dGRgZ0dXUB5OYz79+/R+vWrQHkdlDIyMhAUFBQvhFzjLF/JjMzEykpKVi2bBnCw8MxadIkeHt7Q19fHxs3boSdnR1GjhwJTU1NxMbGolGjRvJOMmOskJKu161ZswbHjh1DSkoKlJWV4e3tLcwGcPfuXVy9ehWZmZlYuHAhRCIRevfuDQA8MrWQ4po2Y79JRkYG3r17hzdv3iAyMhKOjo4YOHAg+vXrh7FjxwLIffvYtm1brFmzBvfu3UNoaCgWLVok13SLxWKMHz8eCxYsQN26ddGuXbu/PEckEmHChAlwd3fH9evXYW5uLuyrW7cuIiIicOrUKTx69AiLFy/GzZs3/3G66tSpg+zsbGzZsgXPnj3Dzp074eHhke84JSUlWFpa4saNG4iMjMSECRPQtm3bfFO55Fm2bBlWr14NFxcXPHr0CLGxsfD394ezs/M/TiNjrGSQDl4eOXIE5cuXx8KFC6Grq4uAgADcunULIpFICJiXK1cOHz9+hJKSEgfNGYD/jWBwdnaGt7c3du7cKbxk9/PzQ3x8PNq3b48HDx5gxIgRaN26NXr27Il79+4JIxg4gF781KhRA7q6ukhOTsaVK1cwcOBAfPjwAStWrBCOGTt2LAICAvDHH3/IMaWMFX3KyspYtGgRYmJikJGRgUWLFmHKlCmYN28ebt68iYiICIjFYmzYsAGnTp0S8l7GGPteXr1u8eLF2LBhAywtLeHp6Ynk5GQMHDgQ8fHx0NfXx/LlyzFlyhQMHToU7969Q3BwMIDcIDwH0Asnrm0z9pucPHkSVapUQa1atdCrVy9cuHABmzdvxuHDh2WCKH5+fsjKyoK+vj5mzZqFlStXyjHVuczNzZGZmYmJEyf+7XPGjx+PhIQE1K9fHx06dBC2W1hYYPDgwTAzM0ObNm3w+fNnmV7pf1fz5s3h7OyMtWvXokmTJti1axdWr16d7zg1NTXY2tpi5MiRaNeuHVRVVbF3794Crztp0iT4+Phg27ZtaNq0KTp37oxt27YJU+4wxpi073sQT506Ffv27cPAgQOxYMECVK9eHYsWLUJUVBQAICUlBbdv30blypXlmWxWSN2+fRtLly5FmzZtEBgYCGdnZ7i6ukJfXx+pqakoXbo0lixZAicnJzg6OkJRURHZ2dn8MqYYIyJERERg7dq1yMrKwq1bt6CoqIicnBxh+p680X6Msf+ucePG8PLygq2tLWJjY2Fubo5L/8fencdFXe1/HH+PbALiKCibmloqLriQmqJ11UTRROtaYVGYSi5ZKqnXMrMwF9JyKSwtN8yNupmlpiSauaS4U1Jey5uZlqg/Q3AFhO/vDx98ryOMgaG4vJ6PxzwezPl+zvd7vt+Z4cx85sw5Gzboyy+/NGPyp8/ify+Ay+X3y4Zh6OjRo1q3bp0++ugjhYeHmwMq//Wvf5lrqo0ePVq7d+/W4sWLtX37djk5OenixYvXtGYebgyLweSJAP7Ct99+q7Zt2+rIkSPm4qMAgP8ZO3as3n33Xa1atUp16tQxp1b44osv9NZbb+n7779XUFCQ/Pz8tH//fm3btk3Ozs7XvLg0bi+GYej8+fNq3LixJkyYoCpVqig0NFRvvfWWBgwYoJycHI0aNUqhoaFq3759aTcXN1hWVpZ+/PFHNW7cWGXKlOEn3sANNHr0aE2bNk3NmjXT+vXrS7s5AG4B586dU2Zmpho0aKDffvtNmzdv1mOPPWa+rztz5ow++OAD9evXz+aL8NzcXL6cu8kxEh2AXVlZWTpw4IBGjx6t8PBwEugAUIg///xTGzdu1LRp09S8eXOdOXNG69evV9++fXXhwgU9+uijatSokc6ePauQkBDt2bNHzs7OysnJIYF+h7pyIWqLxSI3Nzc9/vjjeuutt9S+fXu9++67GjBggCTpzJkz2rNnj7777rvSaC5KmYuLi4KCglSmTBnl5eWRQAdugPyxhmPHjtX69eu1du1am3IAKExCQoKio6NlsVgUHBysl156SY899pimTp1qvq/7448/tGbNGiUnJ9vUJYF+8yOJDsCuJUuWKCAgQBkZGZo0aVJpNwcAbkoWi0U//vij9u3bp40bN2rYsGF6+eWXlZKSoujoaLm7uys6OlpeXl5auXKl/vOf/0i6tGYD7jyXz6GfmpqqDRs26ODBg8rOzlZYWJgyMjLUvHlzPfDAA5KktLQ0Pf300zp37pyGDBlSmk3HTYC574EbI3/KFklq1qyZOQc6X34DuNyVX6z997//1c6dO3X06FHdddddev/99/XUU0/p2WeflXRplPqLL74oi8XCrwtvQUznAgAA8DfNmTNH//rXv5Sbm6sBAwaoQ4cOCgkJ0VNPPSVXV1fNnj1bH3/8sbnuRVxcnBo0aFDazcYNdvn0PSNHjtSKFSt08uRJ1alTR97e3po/f76WLl2qmTNn6tChQ/L19TXn3d+yZYucnJz4qS8AAMBN4PL3dX/++ac8PT0lSffdd5/uuusuffrpp+ratasOHz6sgIAA1axZU99++60yMjK0a9cuOTk52QyuwM2P3wICAAD8TVFRUerQoYOysrJUu3ZtSZdGHB87dkzNmzeXJPXo0UNZWVlaunSpOWc67iz5H7SmTZumOXPm6NNPP9U//vEPPf/885ozZ4527dqlyMhINWrUSHv37tWRI0d0991369FHamhqOwAAy3RJREFUH5WDgwNzYQMAANwk8t/XjR8/Xps2bdLzzz+vrl27auHCherUqZPmzJmjTz75RO+9956++eYb/fLLL2rdurXGjRtnLg7P+7pbCyPRAQAAStCZM2eUkpKiiRMn6tChQ9q9e7fNG+TTp0/bLCKEO4dhGMrJyVFkZKSZPF+1apV69OihKVOmqG/fvsrOzlZubq5cXV1t6jICHQAA4OaSm5uriIgI/fvf/5abm5sGDx6sxx9/XJ9++ql+/vlnTZw4UTVr1iy0Hu/rbj185QEAAFBCDMPQzp07NXnyZOXk5GjXrl1ydHRUbm6uypQpI4vFQgL9DmaxWOTo6Kg///xTderUMRPob731lvr27aucnBwtXLhQ3t7e6tKli83cu3zQAgAAuLk4ODhowIABKlu2rFq2bKmlS5cqPT1df/75p3bs2KEvv/xSL7zwQqH1cOth4h0AAIASYrFYFBwcrDfeeEOrVq2Sk5OTLl68KAcHBxYjuwPl5eUVKDMMQ87Ozho6dKieeuopTZ48WQMGDJAknThxQgkJCfrjjz94vgAAANykpk6dqqlTp0qS2rRpIwcHB23fvl1ffvmlWrVqpfLly+vQoUMaPHiw9u7dW8qtRUlhOhcAAIDrhMWC7lyXP/b79u2Th4eHDMNQtWrV9N///lcPPfSQypYtq+3bt+vixYu6cOGCIiMjlZmZqQ0bNjBCCQAA4CaUnZ2tSZMmKSYmRo8//rieffZZtW3bVs2aNVOPHj308ssvKzc3VyNGjNDevXu1evVq3tfdJkiiAwAAANfJSy+9pI8//ljZ2dkqX768Bg8erIEDB+qrr75SRESEfH195eDgoPLly+vcuXPatm2bnJycmCsTAADgJvbDDz9o9OjROnr0qOrXr68HH3xQn332mUaOHKlmzZpJuvQLRIvFwvu62wRzogMAAAAlJP/DkiQtX75cCxYs0Jw5c3Tu3DmlpqZq0KBBOnXqlF555RXt379fH330kfLy8lSlShWFh4fLwcFBFy9etFmMFgAAADeXBg0a6MMPP9TmzZs1YcIELVq0SOXKlVOjRo3MJLrFYpFhGCTQbxOMRAcAAABK2IoVK7R8+XLVrFlTr7zyilk+b948RUVFacmSJerRo0eBeoxUAgAAuPWMHj1a06ZNU7NmzbR+/frSbg6uA5LoAAAAwN90+RzoP/30k55++mn99NNPGjx4sN544w0ZhmHeevbsKUmKj49XmTJlSJoDAADcoi7/FeLOnTsVFBQkBwcHm3LcHljpCgAAAPgbLk+gL1++XF5eXho1apRq166thQsXateuXbJYLGbC3NPTUydOnJCTkxMJdAAAgFtY/pQtktSsWTM5ODgoNzeXBPptiCQ6AAAAcI0MwzAT6K+88or69++vjz/+WA8//LBGjhypatWq6dVXX9WePXskSWfPntX3338vX1/f0mw2AAAASsiVCXMGSdyemM4FAAAA+JvGjh2rd999V6tWrVKdOnVktVolSV988YXeeustff/99woKCpKfn5/279+vbdu2ydnZmZ/6AgAAALcARqIDAAAAf8Off/6pjRs3atq0aWrevLnOnDmj9evXq2/fvrpw4YIeffRRNWrUSGfPnlVISIj27NkjZ2dn5eTkkEAHAAAAbgEk0QEAAIC/wWKx6Mcff9S+ffu0ceNGDRs2TC+//LJSUlIUHR0td3d3RUdHy8vLSytXrtR//vMfSZKTk1MptxwAAABAUZBEBwAAAP6GihUr6o033tD777+vrl27qnr16ho/frx27NihBx98UNu3b9djjz2mPn366Pz58xo4cKB++OGH0m42AAAAgCJyLO0GAAAAALe6qKgodejQQVlZWapdu7YkKS8vT8eOHVPz5s0lST169FBWVpaWLl1qzpkOAAAA4ObHwqIAAABACTpz5oxSUlI0ceJEHTp0SLt375aj4//Grpw+fVoeHh6l2EIAAAAAxcFIdAAAAKCEGIahnTt3avLkycrJydGuXbvk6Oio3NxclSlTRhaLhQQ6AAAAcIthTnQAAACghFgsFgUHB+uNN97QqlWr5OTkpIsXL8rBwUEWi6W0mwcAAHBNatSooWnTphU5Pj4+XhUqVLhqTExMjJo0afK32gXcKCTRAQAAgBLk4uKioKAglSlTRnl5eTZTuQAAgBurV69eslgsslgscnJyko+Pjzp06KC5c+cqLy+vtJtXYgYNGmSuy3Kl33//XQ4ODvrss8+uef87duxQv379rrk+cKsjiQ4AAABcJ2XK8HYbAIDS1qlTJx09elS//vqrVq9erXbt2mnIkCEKCwvTxYsXS7t5JSIqKkoHDhzQpk2bCmyLj4+Xl5eXunbtWuz9ZmdnS5IqV64sNze3v91O4FbFu3oAAAAAAADctlxcXOTr66sqVaro3nvv1SuvvKIvvvhCq1evVnx8vCTp119/lcViUUpKilnv1KlTslgs+uabbyRJ33zzjSwWi7766isFBQXJ1dVVDz74oI4fP67Vq1erXr16Kl++vJ588kmdO3fO3E/btm01aNAgRUdHq2LFivLx8dGHH36os2fPqnfv3vLw8NA999yj1atXS7q0xkqtWrX09ttv25xHamqqypQpo//+978FzrFJkya69957NXfu3ALb4uPj1bNnT5UpU0ZRUVGqWbOmXF1dFRAQoHfeeccmtlevXnrkkUcUGxsrf39/1alTR1LB6VymTJmihg0byt3dXdWqVdPAgQN15syZAsf+/PPPVadOHZUtW1YdOnTQ4cOH7T9QkubNm6d69eqpbNmyqlu3rt5//31zW/5j9Nlnn6ldu3Zyc3NT48aNtXXr1qvuEygJJNEBAAAAAABwR3nwwQfVuHHja5riJCYmRtOnT9eWLVt0+PBhhYeHa9q0aVq8eLG+/PJLJSUlKS4uzqbO/PnzValSJW3fvl2DBg3Sc889p8cff1ytWrXS7t27FRoaqsjISJ07d04Wi0V9+vTRvHnzbPYxd+5cPfDAA7rnnnsKbVdUVJT+/e9/2ySzN2zYoAMHDqhPnz7Ky8tT1apV9cknn+jHH3/Ua6+9pldeeUWffPKJzX7WrVunffv2KSkpSStXriz0WGXKlNG7776r1NRUzZ8/X19//bVGjBhhE3Pu3DmNHz9e8+fP17fffqvMzEw98cQTdq/rrFmzNGrUKI0fP1779u3ThAkTNHr0aM2fP98mbtSoURo+fLhSUlJUp04dPfnkk7fNLwpw8yKJDgAAAAAAgDtO3bp19euvvxa73rhx49S6dWsFBQUpKipKGzZs0IwZMxQUFKQHHnhAjz32mNavX29Tp3Hjxnr11VdVu3ZtjRw5Uq6urqpUqZL69u2r2rVr67XXXtPJkyf1/fffS5J69+6t/fv3a/v27ZKknJwcLVy4UH369LHbroiICOXm5urf//63WTZ37lwFBwerfv36cnJy0pgxY9S8eXPVrFlTTz31lHr16lUgie7u7q7Zs2erQYMGCgwMLPRY0dHRateunWrWrKkHH3xQY8eOLbCfnJwcTZ8+XcHBwWratKnmz5+vLVu2mOd0pbFjx2ry5Mnq3r27atasqe7du+vFF1/UBx98YBM3fPhwdenSRXXq1NGYMWN06NAhHThwwO51AUoCSXQAAAAAAADccQzDkMViKXa9Ro0amX/7+PjIzc1Nd999t03Z8ePH7dZxcHCQl5eXGjZsaFNHklnPz89PXbp0MadnWblypS5cuKDHH3/cbrsqVKig7t27m3VOnz6tpUuX2iTeZ86cqWbNmqly5coqV66cZs2apd9++81mPw0bNpSzs/NVr8H69evVoUMHValSRR4eHurZs6dOnjyps2fPmjGOjo5q1qyZeb9u3bqqUKGC9u3bV2B/J06c0OHDhxUVFaVy5cqZt3HjxhWYvubya+nn52dz3YDrhSQ6AAAAAAAA7jj79u1TzZo1Jf1vMXDDMMztOTk5hdZzcnIy/7ZYLDb388vy8vLs1imsXn4y//J6zz77rBISEnT+/HnNmzdPPXr0+MvFPaOiorR582b9/PPP+vjjjyVJPXr0kCR98sknevHFF9WnTx+tWbNGKSkp6t27t7l4aD53d/erHuPQoUN66KGHFBgYqKVLl2rXrl167733JBW8ZoV9SVFYWf55z5o1SykpKeYtNTVVycnJNrF/dd2A64EkOgAAAIDr7soFyf5KfHy8KlSocNWYmJgYNWnS5G+1CwBwZ/r666+1d+9ePfroo5KkypUrS5KOHj1qxly+yGhpeOihh+Tu7q4ZM2Zo9erVV53KJV+7du109913Kz4+XnPnzlV4eLg8PDwkSZs2bVKrVq00cOBABQUFqVatWoUuUvpXdu7cqYsXL2ry5Mlq2bKl6tSpoz/++KNA3MWLF7Vz507z/v79+3Xq1CnVrVu3QKyPj4+qVKmiX375RbVq1bK55X/RAZQmkugAAADAVfTq1UsWi8UcMebj46MOHTpo7ty5t9Wop0GDBql27dqFbvv999/l4OBwTYuv5duxY4f69et3zfUBALhWWVlZSktL0++//67du3drwoQJevjhhxUWFqaePXtKklxdXdWyZUu9+eab+vHHH7Vx40a9+uqrpdpuBwcH9erVSyNHjlStWrUUHBz8l3UsFot69+6tGTNmaOvWrYqKijK31apVSzt37tRXX32ln376SaNHj9aOHTuK3a577rlHFy9eVFxcnH755RctWLBAM2fOLBDn5OSkQYMGadu2bdq9e7d69+6tli1b6r777it0vzExMYqNjdU777yjn376SXv37tW8efM0ZcqUYrcRKGkk0QEAAIC/0KlTJx09elS//vqrVq9erXbt2mnIkCEKCwvTxYsXS7t5JSIqKkoHDhzQpk2bCmyLj4+Xl5eXunbtWuz95v9EvHLlyn/5E3QAAK6HxMRE+fn5qUaNGurUqZPWr1+vd999V1988YUcHBzMuLlz5yonJ0fNmjXTkCFDNG7cuFJs9SVRUVHKzs4u0ij0fL169VJGRoYCAgLUunVrs3zAgAHq3r27evTooRYtWujkyZMaOHBgsdvUpEkTTZkyRRMnTlRgYKAWLVqk2NjYAnFubm566aWXFBERoeDgYLm6uiohIcHufp999lnNnj1b8fHxatiwodq0aaP4+HhGouPmYAAAAACw65lnnjEefvjhAuXr1q0zJBmzZs0yDMMwDh48aEgy9uzZY8akp6cbkoz169cbhmEY69evNyQZiYmJRpMmTYyyZcsa7dq1M44dO2asWrXKqFu3ruHh4WE88cQTxtmzZ839tGnTxnjhhReMIUOGGBUqVDC8vb2NDz74wDhz5ozRq1cvo1y5csbdd99trFq1yjAMw8jLyzPuuece46233rJp8969ew2LxWIcOHCg0HO99957jV69ehUor1WrljFs2DDj4sWLRp8+fYwaNWoYZcuWNerUqWNMmzat0Os1YcIEw8/Pz6hevbphGIZRvXp1Y+rUqWbc5MmTjcDAQMPNzc2oWrWq8dxzzxmnT582t8+bN8+wWq3GsmXLjNq1axsuLi5GSEiI8dtvv5kxr7/+utG4cWOb48+dO9eoW7eu4eLiYgQEBBjvvfeeuS3/MVq6dKnRtm1bw9XV1WjUqJGxZcuWQq8HAAClbfPmzYajo6ORlpZW2k0B7miMRAcAAACuwYMPPqjGjRtf0xQnMTExmj59urZs2aLDhw8rPDxc06ZN0+LFi/Xll18qKSlJcXFxNnXmz5+vSpUqafv27Ro0aJCee+45Pf7442rVqpV2796t0NBQRUZG6ty5c7JYLOrTp4/mzZtns4+5c+fqgQce0D333FNou6KiovTvf/9bZ86cMcs2bNigAwcOqE+fPsrLy1PVqlX1ySef6Mcff9Rrr72mV155RZ988onNftatW6d9+/YpKSlJK1euLPRYZcqU0bvvvqvU1FTNnz9fX3/9tUaMGGETc+7cOY0fP17z58/Xt99+q8zMTD3xxBN2r+usWbM0atQojR8/Xvv27dOECRM0evRozZ8/3yZu1KhRGj58uFJSUlSnTh09+eSTt80vCgAAt4esrCwdOHBAo0ePVnh4uHx8fEq7ScAdjSQ6AAAAcI3q1q2rX3/9tdj1xo0bp9atWysoKEhRUVHasGGDZsyYoaCgID3wwAN67LHHtH79eps6jRs31quvvqratWtr5MiRcnV1VaVKldS3b1/Vrl1br732mk6ePKnvv/9ektS7d2/t379f27dvlyTl5ORo4cKFV/05eEREhHJzc/Xvf//bLJs7d66Cg4NVv359OTk5acyYMWrevLlq1qypp556Sr169SqQRHd3d9fs2bPVoEEDBQYGFnqs6OhotWvXTjVr1tSDDz6osWPHFthPTk6Opk+fruDgYDVt2lTz58/Xli1bzHO60tixYzV58mR1795dNWvWVPfu3fXiiy/qgw8+sIkbPny4unTpojp16mjMmDE6dOiQDhw4YPe6AABwoy1ZskQBAQHKyMjQpEmTSrs5wB2PJDoAAABwjQzDkMViKXa9Ro0amX/7+PjIzc1Nd999t03Z8ePH7dZxcHCQl5eXGjZsaFNHklnPz89PXbp00dy5cyVJK1eu1IULF/T444/bbVeFChXUvXt3s87p06e1dOlSm8T7zJkz1axZM1WuXFnlypXTrFmz9Ntvv9nsp2HDhnJ2dr7qNVi/fr06dOigKlWqyMPDQz179tTJkyd19uxZM8bR0VHNmjUz79etW1cVKlTQvn37CuzvxIkTOnz4sKKiolSuXDnzNm7cOP33v/+1ib38Wvr5+dlcNwAAbga9evVSbm6udu3apSpVqpR2c4A7Hkl0AAAA4Brt27fPXOyqTJlLb60NwzC35+TkFFrPycnJ/Ntisdjczy/Ly8uzW6ewevnJ/MvrPfvss0pISND58+c1b9489ejR4y8X94yKitLmzZv1888/6+OPP5Yk9ejRQ5L0ySef6MUXX1SfPn20Zs0apaSkqHfv3ubiofnc3d2veoxDhw7poYceUmBgoJYuXapdu3bpvffek1TwmhX2JUVhZfnnPWvWLKWkpJi31NRUJScn28T+1XUDAAAALudY2g0AAAAAbkVff/219u7dqxdffFGSVLlyZUnS0aNHFRQUJElKSUkpreZJkh566CG5u7trxowZWr16tTZu3PiXddq1a6e7775b8fHxWr9+vcLDw+Xh4SFJ2rRpk1q1aqWBAwea8VeO8i6KnTt36uLFi5o8ebL55cOVU7lI0sWLF7Vz507dd999kqT9+/fr1KlTqlu3boFYHx8fValSRb/88oueeuqpYrcJAAAAsIckOgAAAPAXsrKylJaWptzcXB07dkyJiYmKjY1VWFiYevbsKUlydXVVy5Yt9eabb6pGjRr6v//7P7366qul2m4HBwf16tVLI0eOVK1atRQcHPyXdSwWi3r37q0pU6YoPT1db731lrmtVq1a+uijj/TVV1+pZs2aWrBggXbs2GGOxi+qe+65RxcvXlRcXJy6du2qb7/9VjNnziwQ5+TkpEGDBundd9+Vk5OTXnjhBbVs2dJMql8pJiZGgwcPVvny5dW5c2dlZWVp586dSk9P19ChQ4vVRgAAACAf07kAAAAAfyExMVF+fn6qUaOGOnXqpPXr1+vdd9/VF198IQcHBzNu7ty5ysnJUbNmzTRkyBCNGzeuFFt9SVRUlLKzs6+6oOiVevXqpYyMDAUEBKh169Zm+YABA9S9e3f16NFDLVq00MmTJ21GpRdVkyZNNGXKFE2cOFGBgYFatGiRYmNjC8S5ubnppZdeUkREhIKDg+Xq6qqEhAS7+3322Wc1e/ZsxcfHq2HDhmrTpo3i4+OLneQHAAAALmcxLp+0EQAAAMBt5dtvv1Xbtm115MgRc/FRAAAAAEVHEh0AAAC4DWVlZenw4cPq16+f/Pz8tGjRotJuEgAAAHBLYjoXAAAA4Da0ZMkSBQQEKCMjQ5MmTSrt5gAAAAC3LEaiAwAAAAAAAABgByPRAQAAAAAAAACwgyQ6AAAAAAAAAAB2kEQHAAAAAAAAAMAOkugAAAAAAAAAANhBEh0AAAAAAAAAADtIogMAAAAAAAAAYAdJdAAAAAAAAAAA7CCJDgAAAAAAAACAHSTRAQAAAAAAAACwgyQ6AAAAAAAAAAB2kEQHAAAAAAAAAMAOkugAAAAAAAAAANhBEh0AAAAAAAAAADtIogMAAAAAAAAAYAdJ9FvMu+++K4vFosDAwNJuio2YmBhZLBb93//931/G1qhRQ7169brmY1ksFsXExFxz/aL44osvZLFYNHPmTLsxSUlJslgsmjJlSokc02Kx6IUXXiiRfd1J9uzZozZt2shqtcpisWjatGmSpF9//VUWi0Vvv/22JKlcuXJ/63l3Mynqa8hisZg3BwcHVaxYUY0bN1b//v2VnJx8/Rt6HeU/vvHx8aXdFNwh6H/pf2HrTux/JalXr14qV67cNdf/u6/Dv3Pc/PcEZcqUkdVqVb169dSzZ0+tWbPmhrenpN2I/08AAODO5ljaDUDxzJ07V5L0ww8/aNu2bWrRokUpt+j21KVLF/n6+mru3LkaMGBAoTHz5s2Tk5OTIiMjb3DrcLk+ffro7NmzSkhIUMWKFVWjRg1Jkp+fn7Zu3arq1atLktavXy9PT89SbGnpeOyxxzRs2DAZhqHMzEylpqbqo48+0ocffqjBgwfrnXfeKe0mXpP8x/eee+4p7abgDkH/e2PQ/9466H9vPa1btza/3Dhz5oz279+vhIQEhYaG6tFHH9WSJUvk5ORUyq28Nlu3blXVqlVLuxkAAOA2xkj0W8jOnTv13XffqUuXLpKkOXPmlHKLbn05OTm6ePFigXJHR0f17NlTO3bsUGpqaoHtp06d0rJly9StWzdVrlz5b7Xh/Pnzf6v+nS41NVUhISHq3LmzWrZsKV9fX0mSi4uLWrZsKT8/P0lS8+bNi5xwLe5jcu7cueI1+gby8fFRy5YtFRwcrNDQUA0bNky7d+9Wnz599O6772rGjBml3cRrkv/4/t3XH1AU9L8lj/731ncz9L8ongoVKqhly5Zq2bKlQkJC9Pzzz2vTpk16/fXXtXTpUr366qul3cRr1rJlS5LoAADguiKJfgvJ/9D+5ptvqlWrVkpISCiQvLv8J7RTpkxRzZo1Va5cOQUHB9tM35AfZ++WLykpSQ8//LCqVq2qsmXLqlatWurfv7/dn40fO3ZMTz75pKxWq3x8fNSnTx9lZGRc0/lmZmaqb9++8vLyUrly5dSpUyf99NNPhcb+/PPPioiIkLe3t1xcXFSvXj299957NjHffPONLBaLFixYoGHDhqlKlSpycXHRgQMHCt1nVFSUpEsj3q60ZMkSXbhwQX369JEkXbhwQSNHjlTNmjXl7OysKlWq6Pnnn9epU6ds6tWoUUNhYWH67LPPFBQUpLJly2rMmDGFHt8wDL3yyitycnLSrFmzJEl5eXmaNGmS6tatKxcXF3l7e6tnz546cuSITd22bdsqMDBQW7duVatWreTq6qoaNWqY5/Lll1/q3nvvlZubmxo2bKjExESb+vnTA3z//fd6/PHHZbVa5enpqaFDh+rixYvav3+/OnXqJA8PD9WoUUOTJk0q0P7MzEwNHz7c5ppER0fr7NmzNnH5P6NfsGCB6tWrJzc3NzVu3FgrV64s9Lrki4+Pl8Vi0cWLFzVjxgyb525+++3V+fXXX6/pMbn82m7cuFGtWrWSm5ub+Tz47bff9PTTT9s8DydPnqy8vDybfYwZM0YtWrSQp6enypcvr3vvvVdz5syRYRg2cTk5ORoxYoR8fX3l5uam+++/X9u3b7/qdSkKBwcHTZ8+XZUqVdJbb7111esj/e+188033xS4DqX1HLM3nUtR/hfk5eVp3LhxCggIkKurqypUqKBGjRrdsqPycf3R/9L/0v/+T2n0v++9957KlCmj48ePm2WTJ0+WxWLR888/b5bl5eWpYsWKGjZsmFmWnZ2tcePGmY9d5cqV1bt3b504caLAcT7++GMFBwfL3d1d5cqVU2hoqPbs2XPV6yFJ3377rSpVqqSwsDDzOhe1Dz9x4oQGDhyo+vXrq1y5cvL29taDDz6oTZs2mTGGYah27doKDQ0tUP/MmTOyWq0216G4YmJi1KBBA02fPl0XLlyQVHjfLxXe/+ZPcfOf//xHoaGhcnd3l5+fn958801JUnJysu6//365u7urTp06mj9/vs0+858fX3/9tfm/p3z58urZs6fOnj2rtLQ0hYeHq0KFCvLz89Pw4cOVk5Njs4/CpnNJS0tT//79VbVqVTk7O6tmzZoaM2ZMgS/wZsyYocaNG6tcuXLy8PBQ3bp19corr1zz9QQAALcpA7eEc+fOGVar1WjevLlhGIYxe/ZsQ5IRHx9vE3fw4EFDklGjRg2jU6dOxueff258/vnnRsOGDY2KFSsap06dMgzDMC5cuGBs3brV5rZ8+XKjfPnyRr169cz9zZgxw4iNjTWWL19ubNiwwZg/f77RuHFjIyAgwMjOzjbjXn/9dUOSERAQYLz22mtGUlKSMWXKFMPFxcXo3bu3TRurV69uPPPMM1c937y8PKNdu3aGi4uLMX78eGPNmjXG66+/btx9992GJOP11183Y3/44QfDarUaDRs2ND766CNjzZo1xrBhw4wyZcoYMTExZtz69esNSUaVKlWMxx57zFi+fLmxcuVK4+TJk3bbcf/99xve3t4252oYhtG8eXOjSpUqxsWLF428vDwjNDTUcHR0NEaPHm2sWbPGePvttw13d3cjKCjIuHDhgs25+/n5GXfffbcxd+5cY/369cb27dsNwzAMScbzzz9vPj5PPPGE4eHhYaxevdqs369fP0OS8cILLxiJiYnGzJkzjcqVKxvVqlUzTpw4Yca1adPG8PLyMgICAow5c+YYX331lREWFmZIMsaMGWM0bNjQWLJkibFq1SqjZcuWhouLi/H7778X+niOHTvWSEpKMkaMGGEeu27dusa7775rJCUlGb179zYkGUuXLjXrnz171mjSpIlRqVIlY8qUKcbatWuNd955x7BarcaDDz5o5OXlmbH5z9f77rvP+OSTT4xVq1YZbdu2NRwdHY3//ve/dh+b48ePG1u3bjUkGY899pj5PL68/VeaN2+eIck4ePBgkR6TwrRp08bw9PQ0qlWrZsTFxRnr1683NmzYYBw/ftyoUqWKUblyZWPmzJlGYmKi8cILLxiSjOeee85mH7169TLmzJljJCUlGUlJScbYsWMNV1dXY8yYMTZxzzzzjGGxWIx//etfxpo1a4wpU6YYVapUMcqXL/+Xr6H8a5v/nCrME088YUgyDh8+bPf6GMb/Xjvr16+3uQ6l+RzL/183b948s6yo/wtiY2MNBwcH4/XXXzfWrVtnJCYmGtOmTbOJAfLR/9L/Ggb97+VKo//9z3/+Y0gyFi9ebJZ16tTJcHV1NWrXrm2Wbdu2zZBkrFq1yjAMw8jNzTU6depkuLu7G2PGjDGSkpKM2bNnG1WqVDHq169vnDt3zqw7fvx4w2KxGH369DFWrlxpfPbZZ0ZwcLDh7u5u/PDDD2bcM888Y7i7u5v3P/74Y8PFxcV47rnnjIsXL9rEFaUP/89//mM899xzRkJCgvHNN98YK1euNKKioowyZcrY9LvvvPOOYbFYjJ9++snm2rz33nuGJJs2FqZ69epGly5d7G5/+eWXDUnGpk2bDMMovO83jML732eeecZwdnY26tWrZ7zzzjs2z8+RI0caderUKfB62Llzp1k///lRs2ZNY9iwYcaaNWuMiRMnGg4ODsaTTz5p3Hvvvca4ceOMpKQk46WXXjIkGZMnT7Zp15X/n44ePWpUq1bNqF69uvHBBx8Ya9euNcaOHWu4uLgYvXr1MuOWLFliSDIGDRpkrFmzxli7dq0xc+ZMY/DgwVe9ngAA4M5DEv0W8dFHHxmSjJkzZxqGYRinT582ypUrZzzwwAM2cflvbBs2bGjzRn779u2GJGPJkiWF7v/s2bPGfffdZ/j5+Rm//vproTF5eXlGTk6OcejQIUOS8cUXX5jb8j80TZo0yabOwIEDjbJly9p8aCvKh/jVq1cbkox33nnHpnz8+PEF3iSHhoYaVatWNTIyMmxiX3jhBaNs2bLGn3/+aRjG/z4M/OMf/7jqsS+X/6b+s88+M8tSU1MNScaoUaMMwzCMxMTEQs/9448/NiQZH374oc25Ozg4GPv37y9wrPwP8SdPnjTuv/9+o0qVKkZKSoq5fd++fYYkY+DAgTb18j8wvvLKK2ZZmzZtCnxAOXnypOHg4GC4urrafGBPSUkxJBnvvvuuWZb/eF75AaVJkyYFrkdOTo5RuXJlo3v37mZZbGysUaZMGWPHjh029T/99FObD7f55+3j42NkZmaaZWlpaUaZMmWM2NjYAtfJ3nW7XHE/xNt7TAqTf23XrVtnU57/4XPbtm025c8995xhsVjs7j83N9fIyckx3njjDcPLy8t8reQ/3i+++KJN/KJFiwxJJZJEz/8gmt/m4ibRS/M5VtiH+KL+LwgLCzOaNGli97oAl6P/vYT+l/7X3nW73PXsf6tWrWr06dPHMAzDyMrKMtzd3c1+7NChQ4ZhXHqeOjk5GWfOnDEM438J0su/aDAMw9ixY4chyXj//fcNwzCM3377zXB0dDQGDRpkE3f69GnD19fXCA8PN8suT6K/+eabhoODgzFx4kSben+nD7948aKRk5NjtG/f3vjnP/9plmdmZhoeHh7GkCFDbOLr169vtGvXzu7+8v1VEn3GjBmGJOPjjz82DKP4SfQrr3P+81OSsXv3brM8//UwdOhQsyz/+XHl9X/kkUcMScaUKVNsyps0aWLce++9NmVX/n/q37+/Ua5cOfO5ke/tt9+2+dLhhRdeMCpUqGD3ugAAAORjOpdbxJw5c+Tq6qonnnhCklSuXDk9/vjj2rRpk37++ecC8V26dJGDg4N5v1GjRpKkQ4cOFYjNzc1Vjx49tG/fPq1atcpcCEqSjh8/rgEDBqhatWpydHSUk5OTuX3fvn0F9tWtWzeb+40aNdKFCxdsfn5bFOvXr5ckPfXUUzblERERNvcvXLigdevW6Z///Kfc3Nx08eJF8/bQQw/pwoULNj+jl6RHH320yO0IDw+Xh4eHuaCcdGlxOYvFot69e0uSvv76a0mXfsp6uccff1zu7u5at26dTXmjRo1Up06dQo938OBBBQcHKzMzU8nJyWrcuLG5Lf+aXHmc++67T/Xq1StwHD8/PzVt2tS87+npKW9vbzVp0kT+/v5meb169SQV/twICwuzuV+vXj1ZLBZ17tzZLHN0dFStWrVs6q9cuVKBgYFq0qSJzWMSGhpa6E+D27VrJw8PD/O+j4+PvL29C23T9XC1x6QwFStW1IMPPmhT9vXXX6t+/fq67777bMp79eolwzDM50l+bEhIiKxWqxwcHOTk5KTXXntNJ0+eNF8r9l4D4eHhcnQsmTWhjSumjymu0nyOXak4/wvuu+8+fffddxo4cKC++uorZWZmXtsFwB2B/vcS+l/63+uhOP1v+/bttXbtWknSli1bdO7cOQ0dOlSVKlVSUlKSJGnt2rXmdCzSpetRoUIFde3a1eZ6NGnSRL6+vub1+Oqrr3Tx4kX17NnTJq5s2bJq06ZNgetmGIb69++v119/XYsXL9aIESNsthe3D585c6buvfdelS1b1ny9r1u3zua17uHhod69eys+Pt6cMubrr7/Wjz/+qBdeeKFI1/Bq/u57AovFooceesi8n//89PPzU1BQkFme/3oo6vNekrkexeXlf/UcXblypdq1ayd/f3+bxzT/NbRhwwZJl17Hp06d0pNPPqkvvvjC7pRZAAAAJNFvAQcOHNDGjRvVpUsXGYahU6dO6dSpU3rsscckyeYDZj4vLy+b+y4uLpIKX7BpwIABSkxM1KeffqomTZqY5Xl5eerYsaM+++wzjRgxQuvWrdP27dvND8WF7as4x72akydPytHRscD+8hetujzu4sWLiouLk5OTk80t/438lW+G8xe6Kgo3Nzc98cQTSkxMVFpami5evKiFCxeqTZs25iJZ+W29coEzi8UiX19fnTx5ssjH3759u3766Sf16NGjwOJI+fsprL6/v3+B43h6ehaIc3Z2LlDu7OwsSeYcmFfbh7Ozs9zc3FS2bNkC5ZfXP3bsmL7//vsCj4mHh4cMwyjwmFz5OEuXnjs3aoGx4jwn7MWfPHnS7mOTv1269Bh37NhRkjRr1ix9++232rFjh0aNGiXpf6+V/Pgrn/OFvS6uVf4H0MuTOsVRms+xKxXnf8HIkSP19ttvKzk5WZ07d5aXl5fat2+vnTt3FuGscSeh//0f+l/63+uhOM+JkJAQ/fbbb/r555+1du1aBQUFmfOHr127VufPn9eWLVsUEhJi1jl27JhOnTolZ2fnAtckLS3NvB7Hjh2TdGkR1CvjPv744wLXLTs7Wx9//LEaNGhg88VGvuL04VOmTNFzzz2nFi1aaOnSpUpOTtaOHTvUqVOnAo/DoEGDdPr0aS1atEiSNH36dFWtWlUPP/xwka+jPX/3PYG956e910NRn/f2yq/2nkC69JiuWLGiwOPZoEEDSf/7/xQZGam5c+fq0KFDevTRR+Xt7a0WLVqYX8wAAADkK5nhjLiu5s6dK8Mw9Omnn+rTTz8tsH3+/PkaN26czci3ooqJidHs2bM1b948M7GXLzU1Vd99953i4+P1zDPPmOX2FgIrSV5eXrp48aJOnjxp82EjLS3NJq5ixYpycHBQZGSk3QWVatasaXO/sAWvriYqKkqzZs3SRx99pDp16uj48eOaPHlygbaeOHHC5oO8YRhKS0tT8+bNi3z8Hj16yNfXV6NGjVJeXp5effVVm+NI0tGjRwt8wP/jjz9UqVKlYp3X9VSpUiW5uroWmmDK33495X+Iy8rKMhNJUsGETr7iPicKi/fy8tLRo0cLlP/xxx+S/nfOCQkJcnJy0sqVK20+bH7++ecF9iddes5XqVLFLM9/Xfxd58+f19q1a3XPPfeYz6fLr9vlboVRWcX5X+Do6KihQ4dq6NChOnXqlNauXatXXnlFoaGhOnz4sNzc3G5k03ETo/+l/80/jkT/WxTXs/9t3769pEujzZOSktShQwez/NVXX9XGjRuVlZVlk0SvVKmSvLy8Cizgmi9/FH7+dfn0009tfhFij4uLi9avX6/Q0FCFhIQoMTFRFStWNLcXpw9fuHCh2rZtqxkzZtiUnz59usBxa9Wqpc6dO+u9995T586dtXz5co0ZM+aa/gddzjAMrVixQu7u7mrWrJmkW/s9gXTpMW3UqJHGjx9f6PbLvyzo3bu3evfurbNnz2rjxo16/fXXFRYWpp9++qlIzwcAAHBnIIl+k8vNzdX8+fN1zz33aPbs2QW2r1y5UpMnT9bq1asL/ATyr8yZM0djxozRG2+8UeAnytL/Pthc/iFIkj744INiHedatGvXTpMmTdKiRYs0ePBgs3zx4sU2cW5ubmrXrp327NmjRo0amSNWSlKLFi0UGBioefPmqU6dOrJarTY/SW/fvr0mTZqkhQsX6sUXXzTLly5dqrNnz5of+orq1VdflYeHh1588UWdPXtWsbGxkmROH7Jw4UKbxMCOHTu0b98+cyTzzSAsLEwTJkyQl5dXgSTKjVCjRg1J0vfff29zrVasWHHdjtm+fXvFxsZq9+7duvfee83yjz76SBaLRe3atZN06XXl6Oho84H3/PnzWrBggc3+2rZtK0latGiRzbQAn3zyiS5evPi32pqbm6sXXnhBJ0+eNJ9fku11CwgIMMuXL1/+t453I1zr/4IKFSroscce0++//67o6Gj9+uuvql+//nVuLW4F9L/0v/S/xXc9+18/Pz/Vr19fS5cu1a5duzRhwgRJUocOHdS/f39NmTJF5cuXtzluWFiYEhISlJubqxYtWtjdd2hoqBwdHfXf//63yNMOBQUFacOGDQoJCVHbtm2VlJQkb29vScXrwy0WS4HX+vfff6+tW7eqWrVqBY47ZMgQdezYUc8884wcHBzUt2/fIrX3asaMGaMff/xRr7zyipk8v/yxDA0NNWNvhfcE0qXHftWqVbrnnntsvuC4Gnd3d3Xu3FnZ2dl65JFH9MMPP5BEBwAAJpLoN7nVq1frjz/+0MSJE8035JcLDAzU9OnTNWfOnGJ9iN+6dasGDBig1q1bq0OHDgXmLW3ZsqXq1q2re+65Ry+//LIMw5Cnp6dWrFhxQ37e2LFjR/3jH//QiBEjdPbsWTVr1kzffvttgUSjJL3zzju6//779cADD+i5555TjRo1dPr0aR04cEArVqywmYv6WvXp00dDhw7V/v371b9/f7m6uprbOnTooNDQUL300kvKzMxU69at9f333+v1119XUFCQIiMji328IUOGqFy5curXr5/OnDmjd999VwEBAerXr5/i4uJUpkwZde7cWb/++qtGjx6tatWq2SQQSlt0dLSWLl2qf/zjH3rxxRfVqFEj5eXl6bffftOaNWs0bNiwq36Y/bseeugheXp6KioqSm+88YYcHR0VHx+vw4cPX7djvvjii/roo4/UpUsXvfHGG6pevbq+/PJLvf/++3ruuefMOV+7dOmiKVOmKCIiQv369dPJkyf19ttvF/gAXa9ePT399NOaNm2anJycFBISotTUVL399tsqX758kdt17NgxJScnyzAMnT59Wqmpqfroo4/03Xff6cUXX7T58N28eXMFBARo+PDhunjxoipWrKhly5Zp8+bNJXORrrOi/i/o2rWrAgMD1axZM1WuXFmHDh3StGnTVL16ddWuXbuUzwI3C/pf+l/63+K73v1v+/btFRcXJ1dXV7Vu3VrSpV881KxZU2vWrFG3bt1s5hx/4okntGjRIj300EMaMmSI7rvvPjk5OenIkSNav369Hn74Yf3zn/9UjRo19MYbb2jUqFH65Zdf1KlTJ1WsWFHHjh3T9u3b5e7urjFjxhRoT7169bRp0yaFhIToH//4h9auXauqVasWqw8PCwvT2LFj9frrr6tNmzbav3+/3njjDdWsWbPQL807dOig+vXra/369Xr66afNxH1RnDp1yvyfc/bsWe3fv18JCQnatGmTwsPDbc7R19dXISEhio2NVcWKFVW9enWtW7dOn332WZGPV5reeOMNJSUlqVWrVho8eLACAgJ04cIF/frrr1q1apVmzpypqlWrqm/fvubzyc/PT2lpaYqNjZXVai3waxYAAHBnI4l+k5szZ46cnZ3NRbSuVKlSJf3zn//Up59+as7nWBT79+/XxYsX9e233yo4OLjAdsMw5OTkpBUrVmjIkCHq37+/HB0dFRISorVr1+quu+665nMqijJlymj58uUaOnSoJk2apOzsbLVu3VqrVq1S3bp1bWLr16+v3bt3a+zYsXr11Vd1/PhxVahQQbVr17ZZ4OjviIyM1Msvv6zs7Gz16dPHZpvFYtHnn3+umJgYzZs3T+PHj1elSpUUGRmpCRMmFEiOFlVUVJTc3d0VGRmps2fPavbs2ZoxY4buuecezZkzR++9956sVqs6deqk2NjYEpsnuyS4u7tr06ZNevPNN/Xhhx/q4MGDcnV11V133aWQkBBzdNP1Ur58eSUmJio6OlpPP/20KlSooGeffVadO3fWs88+e12OWblyZW3ZskUjR47UyJEjlZmZqbvvvluTJk3S0KFDzbgHH3xQc+fO1cSJE9W1a1dVqVJFffv2lbe3t6Kiomz2OWfOHPn4+Cg+Pl7vvvuumjRpoqVLl5oLHBZF/jQUZcqUUbly5VS9enUFBwdr5syZatmypU2sg4ODVqxYoRdeeEEDBgyQi4uLnnjiCU2fPr3Aol43o6L+L2jXrp2WLl2q2bNnKzMzU76+vurQoYNGjx4tJyenUjwD3Ezof+l/6X+L73r3vyEhIYqLi9P9999vMyVaSEiIZs2aZTOVi3SpX1u+fLneeecdLViwQLGxsXJ0dFTVqlXVpk0bNWzY0IwdOXKk6tevr3feeUdLlixRVlaWfH191bx5cw0YMMBum+6++24zkf7AAw9o3bp1uvvuu4vch48aNUrnzp3TnDlzNGnSJNWvX18zZ87UsmXLCixomi88PFwxMTHFXlA0//+OxWKRu7u7qlSpovvuu0+vvvpqgWmlJGnBggUaNGiQXnrpJeXm5qpr165asmSJOeXLzczPz087d+7U2LFj9dZbb+nIkSPy8PBQzZo1zS9JJOmBBx5QfHy8PvnkE6Wnp6tSpUq6//779dFHHxVYbwEAANzZLMbfXYodAAAAAHBDNGvWTBaLRTt27CjtpgAAANwxGIkOAAAAADexzMxMpaamauXKldq1a5eWLVtW2k0CAAC4o5BEBwAAAICb2O7du9WuXTt5eXnp9ddf1yOPPFLaTQIAALijMJ0LAAAAAAAAAAB2lCntBgAAAAAAAAAAcLMiiQ4AAAAAAAAAgB0k0QEAAAAAAAAAsIOFRYsoLy9Pf/zxhzw8PGSxWEq7OQCA24hhGDp9+rT8/f1Vpgzfb18P9OMAgOuFfhwAgNsfSfQi+uOPP1StWrXSbgYA4DZ2+PBhVa1atbSbcVuiHwcAXG/04wAA3L5IoheRh4eHpEtvjMqXL1/KrQEA3E4yMzNVrVo1s69ByaMfBwBcL/TjAADc/ko1iV6jRg0dOnSoQPnAgQP13nvvyTAMjRkzRh9++KHS09PVokULvffee2rQoIEZm5WVpeHDh2vJkiU6f/682rdvr/fff99mBEB6eroGDx6s5cuXS5K6deumuLg4VahQochtzf/pd/ny5fnwDQC4Lphm5PqhHwcAXG/04wAA3L5KdcK2HTt26OjRo+YtKSlJkvT4449LkiZNmqQpU6Zo+vTp2rFjh3x9fdWhQwedPn3a3Ed0dLSWLVumhIQEbd68WWfOnFFYWJhyc3PNmIiICKWkpCgxMVGJiYlKSUlRZGTkjT1ZAAAAAAAAAMAtx2IYhlHajcgXHR2tlStX6ueff5Yk+fv7Kzo6Wi+99JKkS6POfXx8NHHiRPXv318ZGRmqXLmyFixYoB49ekj635ynq1atUmhoqPbt26f69esrOTlZLVq0kCQlJycrODhY//nPfxQQEFBoW7KyspSVlWXez/+JXkZGBiPYAAAlKjMzU1arlT7mOuIaAwCuF/oYAABufzfN0uHZ2dlauHCh+vTpI4vFooMHDyotLU0dO3Y0Y1xcXNSmTRtt2bJFkrRr1y7l5OTYxPj7+yswMNCM2bp1q6xWq5lAl6SWLVvKarWaMYWJjY2V1Wo1byxGBgAAAAAAAAB3npsmif7555/r1KlT6tWrlyQpLS1NkuTj42MT5+PjY25LS0uTs7OzKlaseNUYb2/vAsfz9vY2YwozcuRIZWRkmLfDhw9f87kBAAAAAAAAAG5Npbqw6OXmzJmjzp07y9/f36b8ysVZDMP4ywVbrowpLP6v9uPi4iIXF5eiNB0AAAAAAAAAcJu6KUaiHzp0SGvXrtWzzz5rlvn6+kpSgdHix48fN0en+/r6Kjs7W+np6VeNOXbsWIFjnjhxosAodwAAAAAAAAAALndTJNHnzZsnb29vdenSxSyrWbOmfH19lZSUZJZlZ2drw4YNatWqlSSpadOmcnJysok5evSoUlNTzZjg4GBlZGRo+/btZsy2bduUkZFhxgAAAAAAAAAAUJhSn84lLy9P8+bN0zPPPCNHx/81x2KxKDo6WhMmTFDt2rVVu3ZtTZgwQW5uboqIiJAkWa1WRUVFadiwYfLy8pKnp6eGDx+uhg0bKiQkRJJUr149derUSX379tUHH3wgSerXr5/CwsIUEBBw408YAAAAAAAAAHDLKPUk+tq1a/Xbb7+pT58+BbaNGDFC58+f18CBA5Wenq4WLVpozZo18vDwMGOmTp0qR0dHhYeH6/z582rfvr3i4+Pl4OBgxixatEiDBw9Wx44dJUndunXT9OnTr//JAQAAAAAAAABuaaU+nUvHjh1lGIbq1KlTYJvFYlFMTIyOHj2qCxcuaMOGDQoMDLSJKVu2rOLi4nTy5EmdO3dOK1asULVq1WxiPD09tXDhQmVmZiozM1MLFy5UhQoVrudpAQBwS9u4caO6du0qf39/WSwWff7553Zj+/fvL4vFomnTptmUZ2VladCgQapUqZLc3d3VrVs3HTlyxCYmPT1dkZGRslqtslqtioyM1KlTp2xifvvtN3Xt2lXu7u6qVKmSBg8erOzs7BI6UwAAAAAArq7Uk+gAAODmc/bsWTVu3Pgvf7n1+eefa9u2bfL39y+wLTo6WsuWLVNCQoI2b96sM2fOKCwsTLm5uWZMRESEUlJSlJiYqMTERKWkpCgyMtLcnpubqy5duujs2bPavHmzEhIStHTpUg0bNqzkThYAAAAAgKso9elcAADAzadz587q3LnzVWN+//13vfDCC/rqq69sFgeXpIyMDM2ZM0cLFiww1ylZuHChqlWrprVr1yo0NFT79u1TYmKikpOT1aJFC0nSrFmzFBwcrP379ysgIEBr1qzRjz/+qMOHD5uJ+smTJ6tXr14aP368ypcvX2jbsrKylJWVZd7PzMy85msBAAAAALizkUS/zjr2eKO0m4BrsObj10q7CQBwU8vLy1NkZKT+9a9/qUGDBgW279q1Szk5OeZ6JJLk7++vwMBAbdmyRaGhodq6dausVquZQJekli1bymq1asuWLQoICNDWrVsVGBhoM9I9NDRUWVlZ2rVrl9q1a1do+2JjYzVmzJi/fZ7047cm+nEAAAAAJYnpXAAAQLFNnDhRjo6OGjx4cKHb09LS5OzsrIoVK9qU+/j4KC0tzYzx9vYuUNfb29smxsfHx2Z7xYoV5ezsbMYUZuTIkcrIyDBvhw8fLtb5AQAAAACQj5HoAACgWHbt2qV33nlHu3fvlsViKVZdwzBs6hRW/1piruTi4iIXF5ditQ0AAAAAgMIwEh0AABTLpk2bdPz4cd11111ydHSUo6OjDh06pGHDhqlGjRqSJF9fX2VnZys9Pd2m7vHjx82R5b6+vjp27FiB/Z84ccIm5soR5+np6crJySkwQh0AAAAAgOuBkehAKWsyLqa0m4BiSnk1prSbAJSqyMhIc7HQfKGhoYqMjFTv3r0lSU2bNpWTk5OSkpIUHh4uSTp69KhSU1M1adIkSVJwcLAyMjK0fft23XfffZKkbdu2KSMjQ61atTJjxo8fr6NHj8rPz0+StGbNGrm4uKhp06Y35HwBAAAAAHc2kugAAKCAM2fO6MCBA+b9gwcPKiUlRZ6enrrrrrvk5eVlE+/k5CRfX18FBARIkqxWq6KiojRs2DB5eXnJ09NTw4cPV8OGDc0EfL169dSpUyf17dtXH3zwgSSpX79+CgsLM/fTsWNH1a9fX5GRkXrrrbf0559/avjw4erbt6/Kly9/Iy4FAAAAAOAOx3QuAACggJ07dyooKEhBQUGSpKFDhyooKEivvfZakfcxdepUPfLIIwoPD1fr1q3l5uamFStWyMHBwYxZtGiRGjZsqI4dO6pjx45q1KiRFixYYG53cHDQl19+qbJly6p169YKDw/XI488orfffrvkThYAAAAAgKtgJDoAACigbdu2MgyjyPG//vprgbKyZcsqLi5OcXFxdut5enpq4cKFV933XXfdpZUrVxa5LQAAAAAAlCRGogMAAAAAAAAAYAdJdAAAAAAAAAAA7CCJDgAAAAAAAACAHSTRAQAAAAAAAACwg4VFAeAmNmjdkNJuAooprv07pd0EAAAAAABQghiJDgAAAAAAAACAHSTRAQAAAAAAAACwgyQ6AAAAAAAAAAB2kEQHAAAAAAAAAMAOkugAAAAAAAAAANhBEh0AAAAAAAAAADtIogMAAAAAAAAAYAdJdAAAAAAAAAAA7CCJDgAAAAAAAACAHSTRAQAAAAAAAACwgyQ6AAAAAAAAAAB2kEQHAAAAAAAAAMAOkugAAAAAAAAAANhBEh0AAAAAAAAAADtIogMAAAAAAAAAYAdJdAAAAAAAAAAA7CCJDgAAAAAAAACAHSTRAQAAAAAAAACwgyQ6AAAAAAAAAAB2kEQHAAAAAAAAAMCOUk+i//7773r66afl5eUlNzc3NWnSRLt27TK3G4ahmJgY+fv7y9XVVW3bttUPP/xgs4+srCwNGjRIlSpVkru7u7p166YjR47YxKSnpysyMlJWq1VWq1WRkZE6derUjThFAAAAAAAAAMAtqlST6Onp6WrdurWcnJy0evVq/fjjj5o8ebIqVKhgxkyaNElTpkzR9OnTtWPHDvn6+qpDhw46ffq0GRMdHa1ly5YpISFBmzdv1pkzZxQWFqbc3FwzJiIiQikpKUpMTFRiYqJSUlIUGRl5I08XAAAAAAAAAHCLcSzNg0+cOFHVqlXTvHnzzLIaNWqYfxuGoWnTpmnUqFHq3r27JGn+/Pny8fHR4sWL1b9/f2VkZGjOnDlasGCBQkJCJEkLFy5UtWrVtHbtWoWGhmrfvn1KTExUcnKyWrRoIUmaNWuWgoODtX//fgUEBBRoW1ZWlrKyssz7mZmZ1+MSAAAAAAAAAABuYqU6En358uVq1qyZHn/8cXl7eysoKEizZs0ytx88eFBpaWnq2LGjWebi4qI2bdpoy5YtkqRdu3YpJyfHJsbf31+BgYFmzNatW2W1Ws0EuiS1bNlSVqvVjLlSbGysOfWL1WpVtWrVSvTcAQAAAAAAAAA3v1JNov/yyy+aMWOGateura+++koDBgzQ4MGD9dFHH0mS0tLSJEk+Pj429Xx8fMxtaWlpcnZ2VsWKFa8a4+3tXeD43t7eZsyVRo4cqYyMDPN2+PDhv3eyAAAAAAAAAIBbTqlO55KXl6dmzZppwoQJkqSgoCD98MMPmjFjhnr27GnGWSwWm3qGYRQou9KVMYXFX20/Li4ucnFxKfK5AAAAAAAAAABuP6U6Et3Pz0/169e3KatXr55+++03SZKvr68kFRgtfvz4cXN0uq+vr7Kzs5Wenn7VmGPHjhU4/okTJwqMcgcAAAAAAAAAIF+pJtFbt26t/fv325T99NNPql69uiSpZs2a8vX1VVJSkrk9OztbGzZsUKtWrSRJTZs2lZOTk03M0aNHlZqaasYEBwcrIyND27dvN2O2bdumjIwMMwYAAAAAAAAAgCuVahL9xRdfVHJysiZMmKADBw5o8eLF+vDDD/X8889LujQFS3R0tCZMmKBly5YpNTVVvXr1kpubmyIiIiRJVqtVUVFRGjZsmNatW6c9e/bo6aefVsOGDRUSEiLp0uj2Tp06qW/fvkpOTlZycrL69u2rsLAwBQQElNr5AwBws9q4caO6du0qf39/WSwWff755+a2nJwcvfTSS2rYsKHc3d3l7++vnj176o8//rDZR1ZWlgYNGqRKlSrJ3d1d3bp105EjR2xi0tPTFRkZaS7kHRkZqVOnTtnE/Pbbb+ratavc3d1VqVIlDR48WNnZ2dfr1AEAAAAAsFGqSfTmzZtr2bJlWrJkiQIDAzV27FhNmzZNTz31lBkzYsQIRUdHa+DAgWrWrJl+//13rVmzRh4eHmbM1KlT9cgjjyg8PFytW7eWm5ubVqxYIQcHBzNm0aJFatiwoTp27KiOHTuqUaNGWrBgwQ09XwAAbhVnz55V48aNNX369ALbzp07p927d2v06NHavXu3PvvsM/3000/q1q2bTVx0dLSWLVumhIQEbd68WWfOnFFYWJhyc3PNmIiICKWkpCgxMVGJiYlKSUlRZGSkuT03N1ddunTR2bNntXnzZiUkJGjp0qUaNmzY9Tt5AAAAAAAuYzEMwyjtRtwKMjMzZbValZGRofLlyxe5Xsceb1zHVuF6WfPxazfsWE3GxdywY6FkpLwac8OONWjdkBt2LJSMuPbvFLvOtfYxN4rFYtGyZcv0yCOP2I3ZsWOH7rvvPh06dEh33XWXMjIyVLlyZS1YsEA9evSQJP3xxx+qVq2aVq1apdDQUO3bt0/169dXcnKyWrRoIUlKTk5WcHCw/vOf/yggIECrV69WWFiYDh8+LH9/f0lSQkKCevXqpePHjxf5etGP31luZD8OADd7Pw4AAP6+Uh2JDgAAbg8ZGRmyWCyqUKGCJGnXrl3KyclRx44dzRh/f38FBgZqy5YtkqStW7fKarWaCXRJatmypaxWq01MYGCgmUCXpNDQUGVlZWnXrl1225OVlaXMzEybGwAAAAAA14IkOgAA+FsuXLigl19+WREREeYIvLS0NDk7O6tixYo2sT4+PkpLSzNjvL29C+zP29vbJsbHx8dme8WKFeXs7GzGFCY2NtacZ91qtapatWp/6xwBAAAAAHcukugAAOCa5eTk6IknnlBeXp7ef//9v4w3DEMWi8W8f/nffyfmSiNHjlRGRoZ5O3z48F+2DQAAAACAwpBEBwAA1yQnJ0fh4eE6ePCgkpKSbOaB9fX1VXZ2ttLT023qHD9+3BxZ7uvrq2PHjhXY74kTJ2xirhxxnp6erpycnAIj1C/n4uKi8uXL29wAAAAAALgWJNEBAECx5SfQf/75Z61du1ZeXl4225s2bSonJyclJSWZZUePHlVqaqpatWolSQoODlZGRoa2b99uxmzbtk0ZGRk2MampqTp69KgZs2bNGrm4uKhp06bX8xQBAAAAAJAkOZZ2AwAAwM3nzJkzOnDggHn/4MGDSklJkaenp/z9/fXYY49p9+7dWrlypXJzc83R4p6ennJ2dpbValVUVJSGDRsmLy8veXp6avjw4WrYsKFCQkIkSfXq1VOnTp3Ut29fffDBB5Kkfv36KSwsTAEBAZKkjh07qn79+oqMjNRbb72lP//8U8OHD1ffvn0ZXQ4AAAAAuCFIogMAgAJ27typdu3amfeHDh0qSXrmmWcUExOj5cuXS5KaNGliU2/9+vVq27atJGnq1KlydHRUeHi4zp8/r/bt2ys+Pl4ODg5m/KJFizR48GB17NhRktStWzdNnz7d3O7g4KAvv/xSAwcOVOvWreXq6qqIiAi9/fbb1+O0AQAAAAAogCQ6AAAooG3btjIMw+72q23LV7ZsWcXFxSkuLs5ujKenpxYuXHjV/dx1111auXLlXx4PAAAAAIDrgTnRAQAAAAAAAACwgyQ6AAAAAAAAAAB2kEQHAAAAAAAAAMAOkugAAAAAAAAAANhBEh0AAAAAAAAAADtIogMAAAAAAAAAYAdJdAAAAAAAAAAA7CCJDgAAAAAAAACAHSTRAQAAAAAAAACwgyQ6AAAAAAAAAAB2kEQHAAAAAAAAAMAOkugAAAAAAAAAANhBEh0AAAAAAAAAADtIogMAAAAAAAAAYAdJdAAAAAAAAAAA7CCJDgAAAAAAAACAHSTRAQAAAAAAAACwgyQ6AAAAAAAAAAB2kEQHAAAAAAAAAMAOkugAAAAAAAAAANhBEh0AAAAAAAAAADtIogMAAAAAAAAAYAdJdAAAAAAAAAAA7CCJDgAAAAAAAACAHSTRAQAAAAAAAACwgyQ6AAAAAAAAAAB2kEQHAAAAAAAAAMCOUk2ix8TEyGKx2Nx8fX3N7YZhKCYmRv7+/nJ1dVXbtm31ww8/2OwjKytLgwYNUqVKleTu7q5u3brpyJEjNjHp6emKjIyU1WqV1WpVZGSkTp06dSNOEQAAAAAAAABwCyv1kegNGjTQ0aNHzdvevXvNbZMmTdKUKVM0ffp07dixQ76+vurQoYNOnz5txkRHR2vZsmVKSEjQ5s2bdebMGYWFhSk3N9eMiYiIUEpKihITE5WYmKiUlBRFRkbe0PMEAAAAAAAAANx6HEu9AY6ONqPP8xmGoWnTpmnUqFHq3r27JGn+/Pny8fHR4sWL1b9/f2VkZGjOnDlasGCBQkJCJEkLFy5UtWrVtHbtWoWGhmrfvn1KTExUcnKyWrRoIUmaNWuWgoODtX//fgUEBNy4kwUAAAAAAAAA3FJKfST6zz//LH9/f9WsWVNPPPGEfvnlF0nSwYMHlZaWpo4dO5qxLi4uatOmjbZs2SJJ2rVrl3Jycmxi/P39FRgYaMZs3bpVVqvVTKBLUsuWLWW1Ws2YwmRlZSkzM9PmBgAAAAAAAAC4s5RqEr1Fixb66KOP9NVXX2nWrFlKS0tTq1atdPLkSaWlpUmSfHx8bOr4+PiY29LS0uTs7KyKFSteNcbb27vAsb29vc2YwsTGxppzqFutVlWrVu1vnSsAAAAAAAAA4NZTqkn0zp0769FHH1XDhg0VEhKiL7/8UtKlaVvyWSwWmzqGYRQou9KVMYXF/9V+Ro4cqYyMDPN2+PDhIp0TAAAAAAAAAOD2UerTuVzO3d1dDRs21M8//2zOk37laPHjx4+bo9N9fX2VnZ2t9PT0q8YcO3aswLFOnDhRYJT75VxcXFS+fHmbGwAAAAAAAADgznJTJdGzsrK0b98++fn5qWbNmvL19VVSUpK5PTs7Wxs2bFCrVq0kSU2bNpWTk5NNzNGjR5WammrGBAcHKyMjQ9u3bzdjtm3bpoyMDDMGAADY2rhxo7p27Sp/f39ZLBZ9/vnnNtsNw1BMTIz8/f3l6uqqtm3b6ocffrCJycrK0qBBg1SpUiW5u7urW7duOnLkiE1Menq6IiMjzenTIiMjderUKZuY3377TV27dpW7u7sqVaqkwYMHKzs7+3qcNgAAAAAABZRqEn348OHasGGDDh48qG3btumxxx5TZmamnnnmGVksFkVHR2vChAlatmyZUlNT1atXL7m5uSkiIkKSZLVaFRUVpWHDhmndunXas2ePnn76aXN6GEmqV6+eOnXqpL59+yo5OVnJycnq27evwsLCFBAQUJqnDwDATevs2bNq3Lixpk+fXuj2SZMmacqUKZo+fbp27NghX19fdejQQadPnzZjoqOjtWzZMiUkJGjz5s06c+aMwsLClJuba8ZEREQoJSVFiYmJSkxMVEpKiiIjI83tubm56tKli86ePavNmzcrISFBS5cu1bBhw67fyQMAAAAAcBnH0jz4kSNH9OSTT+r//u//VLlyZbVs2VLJycmqXr26JGnEiBE6f/68Bg4cqPT0dLVo0UJr1qyRh4eHuY+pU6fK0dFR4eHhOn/+vNq3b6/4+Hg5ODiYMYsWLdLgwYPVsWNHSVK3bt3sJgUAAMCldUs6d+5c6DbDMDRt2jSNGjVK3bt3l3RpPRMfHx8tXrxY/fv3V0ZGhubMmaMFCxaYX2wvXLhQ1apV09q1axUaGqp9+/YpMTFRycnJatGihSRp1qxZCg4O1v79+xUQEKA1a9boxx9/1OHDh+Xv7y9Jmjx5snr16qXx48cz3RoAAAAA4Lor1SR6QkLCVbdbLBbFxMQoJibGbkzZsmUVFxenuLg4uzGenp5auHDhtTYTAABc5uDBg0pLSzO/nJYurSXSpk0bbdmyRf3799euXbuUk5NjE+Pv76/AwEBt2bJFoaGh2rp1q6xWq5lAl6SWLVvKarVqy5YtCggI0NatWxUYGGgm0CUpNDRUWVlZ2rVrl9q1a1doG7OyspSVlWXez8zMLMlLAAAAAAC4g9xUc6IDAICbX/6i31cu0O3j42NuS0tLk7OzsypWrHjVGG9v7wL79/b2tom58jgVK1aUs7NzgcXHLxcbG2vOs261WlWtWrViniUAAAAAAJeQRAcAANfEYrHY3DcMo0DZla6MKSz+WmKuNHLkSGVkZJi3w4cPX7VdAAAAAADYQxIdAAAUi6+vryQVGAl+/Phxc9S4r6+vsrOzlZ6eftWYY8eOFdj/iRMnbGKuPE56erpycnIKjFC/nIuLi8qXL29zAwAAAADgWpBEBwAAxVKzZk35+voqKSnJLMvOztaGDRvUqlUrSVLTpk3l5ORkE3P06FGlpqaaMcHBwcrIyND27dvNmG3btikjI8MmJjU1VUePHjVj1qxZIxcXFzVt2vS6nicAAAAAAFIpLywKAABuTmfOnNGBAwfM+wcPHlRKSoo8PT111113KTo6WhMmTFDt2rVVu3ZtTZgwQW5uboqIiJAkWa1WRUVFadiwYfLy8pKnp6eGDx+uhg0bKiQkRJJUr149derUSX379tUHH3wgSerXr5/CwsIUEBAgSerYsaPq16+vyMhIvfXWW/rzzz81fPhw9e3bl9HlAAAAAIAbgiQ6AAAoYOfOnWrXrp15f+jQoZKkZ555RvHx8RoxYoTOnz+vgQMHKj09XS1atNCaNWvk4eFh1pk6daocHR0VHh6u8+fPq3379oqPj5eDg4MZs2jRIg0ePFgdO3aUJHXr1k3Tp083tzs4OOjLL7/UwIED1bp1a7m6uioiIkJvv/329b4EAAAAAABIIokOAAAK0bZtWxmGYXe7xWJRTEyMYmJi7MaULVtWcXFxiouLsxvj6emphQsXXrUtd911l1auXPmXbQYAAAAA4HpgTnQAAAAAAAAAAOwgiQ4AAAAAAAAAgB0k0QEAAAAAAAAAsIMkOgAAAAAAAAAAdpBEBwAAAAAAAADADpLoAAAAAAAAAADYQRIdAAAAAAAAAAA7SKIDAAAAAAAAAGAHSXQAAAAAAAAAAOwgiQ4AAAAAAAAAgB0k0QEAAAAAAAAAsIMkOgAAAAAAAAAAdpBEBwAAAAAAAADADpLoAAAAAAAAAADYQRIdAAAAAAAAAAA7SKIDAAAAAAAAAGAHSXQAAAAAAAAAAOwgiQ4AAAAAAAAAgB0k0QEAAAAAAAAAsIMkOgAAAAAAAAAAdpBEBwAAAAAAAADADpLoAAAAAAAAAADYQRIdAAAAAAAAAAA7SKIDAAAAAAAAAGAHSXQAAAAAAAAAAOwgiQ4AAAAAAAAAgB0k0QEAAAAAAAAAsIMkOgAAAAAAAAAAdtw0SfTY2FhZLBZFR0ebZYZhKCYmRv7+/nJ1dVXbtm31ww8/2NTLysrSoEGDVKlSJbm7u6tbt246cuSITUx6eroiIyNltVpltVoVGRmpU6dO3YCzAgAAAAAAAADcym6KJPqOHTv04YcfqlGjRjblkyZN0pQpUzR9+nTt2LFDvr6+6tChg06fPm3GREdHa9myZUpISNDmzZt15swZhYWFKTc314yJiIhQSkqKEhMTlZiYqJSUFEVGRt6w8wMAAAAAAAAA3JpKPYl+5swZPfXUU5o1a5YqVqxolhuGoWnTpmnUqFHq3r27AgMDNX/+fJ07d06LFy+WJGVkZGjOnDmaPHmyQkJCFBQUpIULF2rv3r1au3atJGnfvn1KTEzU7NmzFRwcrODgYM2aNUsrV67U/v37S+WcAQAAAAAAAAC3hlJPoj///PPq0qWLQkJCbMoPHjyotLQ0dezY0SxzcXFRmzZttGXLFknSrl27lJOTYxPj7++vwMBAM2br1q2yWq1q0aKFGdOyZUtZrVYzpjBZWVnKzMy0uQEAAAAAAAAA7iyOpXnwhIQE7d69Wzt27CiwLS0tTZLk4+NjU+7j46NDhw6ZMc7OzjYj2PNj8uunpaXJ29u7wP69vb3NmMLExsZqzJgxxTshAAAAAAAAAMBtpUhJ9KFDhxZ5h1OmTClS3OHDhzVkyBCtWbNGZcuWtRtnsVhs7huGUaDsSlfGFBb/V/sZOXKkzXlnZmaqWrVqVz0uAAA32vXoowEAAAAAwP8UKYm+Z8+eIu3sr5Lbl9u1a5eOHz+upk2bmmW5ubnauHGjpk+fbs5XnpaWJj8/PzPm+PHj5uh0X19fZWdnKz093WY0+vHjx9WqVSsz5tixYwWOf+LEiQKj3C/n4uIiFxeXIp8PAACl4Xr00UV18eJFxcTEaNGiRWZ/3atXL7366qsqU+bSjHGGYWjMmDH68MMPlZ6erhYtWui9995TgwYNzP1kZWVp+PDhWrJkic6fP6/27dvr/fffV9WqVc2Y9PR0DR48WMuXL5ckdevWTXFxcapQoUKJnxcAAAAAAJcrUhJ9/fr1JX7g9u3ba+/evTZlvXv3Vt26dfXSSy/p7rvvlq+vr5KSkhQUFCRJys7O1oYNGzRx4kRJUtOmTeXk5KSkpCSFh4dLko4eParU1FRNmjRJkhQcHKyMjAxt375d9913nyRp27ZtysjIMBPtAADcqq5HH11UEydO1MyZMzV//nw1aNBAO3fuVO/evWW1WjVkyBBJ0qRJkzRlyhTFx8erTp06GjdunDp06KD9+/fLw8NDkhQdHa0VK1YoISFBXl5eGjZsmMLCwrRr1y45ODhIkiIiInTkyBElJiZKkvr166fIyEitWLGidE4eAAAAAHDHKLU50T08PBQYGGhT5u7uLi8vL7M8OjpaEyZMUO3atVW7dm1NmDBBbm5uioiIkCRZrVZFRUVp2LBh8vLykqenp4YPH66GDRuaC5XWq1dPnTp1Ut++ffXBBx9IuvTBOywsTAEBATfwjAEAuL1s3bpVDz/8sLp06SJJqlGjhpYsWaKdO3dKujQKfdq0aRo1apS6d+8uSZo/f758fHy0ePFi9e/fXxkZGZozZ44WLFhg9t0LFy5UtWrVtHbtWoWGhmrfvn1KTExUcnKyuVD4rFmzFBwcrP379xfan2dlZSkrK8u8zwLhAAAAAIBrVaa4Fc6ePavRo0erVatWqlWrlu6++26bW0kaMWKEoqOjNXDgQDVr1ky///671qxZY45ck6SpU6fqkUceUXh4uFq3bi03NzetWLHCHLkmSYsWLVLDhg3VsWNHdezYUY0aNdKCBQtKtK0AAJS2G9lHS9L999+vdevW6aeffpIkfffdd9q8ebMeeughSdLBgweVlpamjh07mnVcXFzUpk0bbdmyRdKl6d1ycnJsYvz9/RUYGGjGbN26VVar1UygS1LLli1ltVrNmCvFxsbKarWaN9Y1AQAAAABcq2KPRH/22We1YcMGRUZGys/Pr0TnWP3mm29s7lssFsXExCgmJsZunbJlyyouLk5xcXF2Yzw9PbVw4cISaiUAADen69lHF+all15SRkaG6tatKwcHB+Xm5mr8+PF68sknJV1a10RSgTVIfHx8dOjQITPG2dnZZm2T/Jj8+mlpafL29i5wfG9vbzPmSiwQDgAAAAAoKcVOoq9evVpffvmlWrdufT3aAwAArtGN7qM//vhjLVy4UIsXL1aDBg2UkpKi6Oho+fv765lnnjHjrkzmG4bxlwn+K2MKi7/aflggHAAAAABQUoqdRK9YsaI8PT2vR1sAAMDfcKP76H/96196+eWX9cQTT0iSGjZsqEOHDik2NlbPPPOMfH19JV0aSe7n52fWO378uDk63dfXV9nZ2UpPT7cZjX78+HFzAXBfX18dO3aswPFPnDhRYJQ7AAAAAAAlrdhzoo8dO1avvfaazp07dz3aAwAArtGN7qPPnTunMmVs30o4ODgoLy9PklSzZk35+voqKSnJ3J6dna0NGzaYCfKmTZvKycnJJubo0aNKTU01Y4KDg5WRkaHt27ebMdu2bVNGRoYZAwAAAADA9VKkkehBQUE2P5c+cOCAfHx8VKNGDTk5OdnE7t69u2RbCAAA7CrNPrpr164aP3687rrrLjVo0EB79uzRlClT1KdPH0mXpmCJjo7WhAkTVLt2bdWuXVsTJkyQm5ubIiIiJElWq1VRUVEaNmyYvLy85OnpqeHDh6thw4YKCQmRJNWrV0+dOnVS37599cEHH0iS+vXrp7CwMAUEBJToOQEAAAAAcKUiJdEfeeSR69wMAABwLUqzj46Li9Po0aM1cOBAHT9+XP7+/urfv79ee+01M2bEiBE6f/68Bg4cqPT0dLVo0UJr1qyRh4eHGTN16lQ5OjoqPDxc58+fV/v27RUfHy8HBwczZtGiRRo8eLA6duwoSerWrZumT59+404WAAAAAHDHshiGYZR2I24FmZmZslqtysjIUPny5Ytcr2OPN65jq3C9rPn4tb8OKiFNxsXcsGOhZKS8GnPDjjVo3ZAbdiyUjLj27xS7zrX2MSg6+vE7y43sxwGAfhwAgNtfsedEBwAAAAAAAADgTlGk6Vwul5ubq6lTp+qTTz7Rb7/9puzsbJvtf/75Z4k1DgAAFB19NAAAAAAAJa/YI9HHjBmjKVOmKDw8XBkZGRo6dKi6d++uMmXKKCYm5jo0EQAAFAV9NAAAAAAAJa/YSfRFixZp1qxZGj58uBwdHfXkk09q9uzZeu2115ScnHw92ggAAIqAPhoAAAAAgJJX7CR6WlqaGjZsKEkqV66cMjIyJElhYWH68ssvS7Z1AACgyOijAQAAAAAoecVOoletWlVHjx6VJNWqVUtr1qyRJO3YsUMuLi4l2zoAAFBk9NEAAAAAAJS8YifR//nPf2rdunWSpCFDhmj06NGqXbu2evbsqT59+pR4AwEAQNHQRwMAAAAAUPIci1vhzTffNP9+7LHHVK1aNX377beqVauWunXrVqKNAwAARUcfDQAAAABAySt2Ev1KLVq0UIsWLUqiLQAAoATRRwMAAAAA8PcVezoXBwcHtWvXTn/++adN+bFjx+Tg4FBiDQMAAMVDHw0AAAAAQMkrdhLdMAxlZWWpWbNmSk1NLbANAACUDvpoAAAAAABKXrGT6BaLRUuXLlXXrl3VqlUrffHFFzbbAABA6aCPBgAAAACg5F3TSHQHBwe98847evvtt9WjRw+NGzeOEW4AAJQy+mgAAAAAAEre31pYtF+/fqpTp44ee+wxbdiwoaTaBAAA/ib6aAAAAAAASkaxR6JXr17dZnGytm3bKjk5WUeOHCnRhgEAgOKhjwYAAAAAoOQVeyT6wYMHC5TVqlVLe/bs0bFjx0qkUQAAoPjoowEAAAAAKHnXPJ1Ldna2jh8/rry8PLOMRcsAACh99NEAAAAAAJScYifRf/rpJ0VFRWnLli025YZhyGKxKDc3t8QaBwAAio4+GgAAAACAklfsJHrv3r3l6OiolStXys/Pj5FtAADcJOijAQAAAAAoecVOoqekpGjXrl2qW7fu9WgPAAC4RvTRAAAAAACUvDLFrVC/fn393//93/VoCwAA+BvoowEAAAAAKHnFTqJPnDhRI0aM0DfffKOTJ08qMzPT5gYAAEoHfTQAAAAAACWv2NO5hISESJLat29vU86iZQAAlC76aAAAAAAASl6xk+jr16+3u23Pnj1/qzEAAODa0UcDAAAAAFDyip1Eb9Omjc39jIwMLVq0SLNnz9Z3332n6OjokmobAAAoBvpoAAAAAABKXrHnRM/39ddf6+mnn5afn5/i4uL00EMPaefOnSXZNgAAcA3oowEAAAAAKDnFGol+5MgRxcfHa+7cuTp79qzCw8OVk5OjpUuXqn79+terjQAA4C/QRwMAAAAAcH0UeST6Qw89pPr16+vHH39UXFyc/vjjD8XFxV3PtgEAgCKgjwYAAAAA4Pop8kj0NWvWaPDgwXruuedUu3bt69kmAABQDPTRAAAAAABcP0Ueib5p0yadPn1azZo1U4sWLTR9+nSdOHHierYNAAAUAX00AAAAAADXT5GT6MHBwZo1a5aOHj2q/v37KyEhQVWqVFFeXp6SkpJ0+vTpYh98xowZatSokcqXL6/y5csrODhYq1evNrcbhqGYmBj5+/vL1dVVbdu21Q8//GCzj6ysLA0aNEiVKlWSu7u7unXrpiNHjtjEpKenKzIyUlarVVarVZGRkTp16lSx2wsAwM3oevTRAAAAAADgkiIn0fO5ubmpT58+2rx5s/bu3athw4bpzTfflLe3t7p161asfVWtWlVvvvmmdu7cqZ07d+rBBx/Uww8/bCbKJ02apClTpmj69OnasWOHfH191aFDB5tkQHR0tJYtW6aEhARt3rxZZ86cUVhYmHJzc82YiIgIpaSkKDExUYmJiUpJSVFkZGRxTx0AgJtaSfbRAAAAAADgkmIn0S8XEBCgSZMm6ciRI1qyZEmx63ft2lUPPfSQ6tSpozp16mj8+PEqV66ckpOTZRiGpk2bplGjRql79+4KDAzU/Pnzde7cOS1evFiSlJGRoTlz5mjy5MkKCQlRUFCQFi5cqL1792rt2rWSpH379ikxMVGzZ89WcHCwOVpv5cqV2r9/v922ZWVlKTMz0+YGAMCt4u/20QAAAAAA4JK/lUTP5+DgoEceeUTLly+/5n3k5uYqISFBZ8+eVXBwsA4ePKi0tDR17NjRjHFxcVGbNm20ZcsWSdKuXbuUk5NjE+Pv76/AwEAzZuvWrbJarWrRooUZ07JlS1mtVjOmMLGxseb0L1arVdWqVbvmcwMAoLSURB8NAAAAAMCdrESS6H/H3r17Va5cObm4uGjAgAFatmyZ6tevr7S0NEmSj4+PTbyPj4+5LS0tTc7OzqpYseJVY7y9vQsc19vb24wpzMiRI5WRkWHeDh8+/LfOEwCA29Hvv/+up59+Wl5eXnJzc1OTJk20a9cuczvrmwAAAAAAbnWlnkQPCAhQSkqKkpOT9dxzz+mZZ57Rjz/+aG63WCw28YZhFCi70pUxhcX/1X5cXFzMBU/zbwAA4H/S09PVunVrOTk5afXq1frxxx81efJkVahQwYxhfRMAAAAAwK3OsbQb4OzsrFq1akmSmjVrph07duidd97RSy+9JOnSSHI/Pz8z/vjx4+bodF9fX2VnZys9Pd1mNPrx48fVqlUrM+bYsWMFjnvixIkCo9wBAEDRTZw4UdWqVdO8efPMsho1aph/X7m+iSTNnz9fPj4+Wrx4sfr372+ub7JgwQKFhIRIkhYuXKhq1app7dq1Cg0NNdc3SU5ONqdnmzVrloKDg7V//34FBAQUaFtWVpaysrLM+6xtAgAAAAC4VqU+Ev1KhmEoKytLNWvWlK+vr5KSksxt2dnZ2rBhg5kgb9q0qZycnGxijh49qtTUVDMmODhYGRkZ2r59uxmzbds2ZWRkmDEAAKD4li9frmbNmunxxx+Xt7e3goKCNGvWLHN7aa5vwtomAAAAAICSUqpJ9FdeeUWbNm3Sr7/+qr1792rUqFH65ptv9NRTT8lisSg6OloTJkzQsmXLlJqaql69esnNzU0RERGSJKvVqqioKA0bNkzr1q3Tnj179PTTT6thw4bmaLZ69eqpU6dO6tu3r5KTk5WcnKy+ffsqLCys0JFrAACgaH755RfNmDFDtWvX1ldffaUBAwZo8ODB+uijjySpVNc3YW0TAAAAAEBJKdXpXI4dO6bIyEgdPXpUVqtVjRo1UmJiojp06CBJGjFihM6fP6+BAwcqPT1dLVq00Jo1a+Th4WHuY+rUqXJ0dFR4eLjOnz+v9u3bKz4+Xg4ODmbMokWLNHjwYHOUW7du3TR9+vQbe7IAANxm8vLy1KxZM02YMEGSFBQUpB9++EEzZsxQz549zbjSWN/ExcVFLi4uRT4XAAAAAADsKdUk+pw5c6663WKxKCYmRjExMXZjypYtq7i4OMXFxdmN8fT01MKFC6+1mQAAoBB+fn6qX7++TVm9evW0dOlSSZfWJZFY3wQAAAAAcGu76eZEBwAAt4bWrVtr//79NmU//fSTqlevLkmsbwIAAAAAuC2U6kh0AABw63rxxRfVqlUrTZgwQeHh4dq+fbs+/PBDffjhh5Jks75J7dq1Vbt2bU2YMMHu+iZeXl7y9PTU8OHD7a5v8sEHH0iS+vXrx/omAAAAAIAbgiQ6AAC4Js2bN9eyZcs0cuRIvfHGG6pZs6amTZump556yoxhfRMAAAAAwK2OJDoAALhmYWFhCgsLs7ud9U0AAAAAALc65kQHAAAAAAAAAMAOkugAAAAAAAAAANhBEh0AAAAAAAAAADtIogMAAAAAAAAAYAdJdAAAAAAAAAAA7CCJDgAAAAAAAACAHSTRAQAAAAAAAACwgyQ6AAAAAAAAAAB2kEQHAAAAAAAAAMAOkugAAAAAAAAAANhBEh0AAAAAAAAAADtIogMAAAAAAAAAYAdJdAAAAAAAAAAA7CCJDgAAAAAAAACAHSTRAQAAAAAAAACwgyQ6AAAAAAAAAAB2kEQHAAAAAAAAAMAOkugAAAAAAAAAANhBEh0AAAAAAAAAADtIogMAAAAAAAAAYAdJdAAAAAAAAAAA7CCJDgAAAAAAAACAHSTRAQAAAAAAAACwgyQ6AAAAAAAAAAB2kEQHAAAAAAAAAMAOkugAAAAAAAAAANhBEh0AAAAAAAAAADtIogMAAAAAAAAAYAdJdAAAAAAAAAAA7CCJDgAAAAAAAACAHSTRAQAAAAAAAACwo1ST6LGxsWrevLk8PDzk7e2tRx55RPv377eJMQxDMTEx8vf3l6urq9q2basffvjBJiYrK0uDBg1SpUqV5O7urm7duunIkSM2Menp6YqMjJTVapXValVkZKROnTp1vU8RAAAAAAAAAHALK9Uk+oYNG/T8888rOTlZSUlJunjxojp27KizZ8+aMZMmTdKUKVM0ffp07dixQ76+vurQoYNOnz5txkRHR2vZsmVKSEjQ5s2bdebMGYWFhSk3N9eMiYiIUEpKihITE5WYmKiUlBRFRkbe0PMFAAAAAAAAANxaHEvz4ImJiTb3582bJ29vb+3atUv/+Mc/ZBiGpk2bplGjRql79+6SpPnz58vHx0eLFy9W//79lZGRoTlz5mjBggUKCQmRJC1cuFDVqlXT2rVrFRoaqn379ikxMVHJyclq0aKFJGnWrFkKDg7W/v37FRAQUKBtWVlZysrKMu9nZmZer8sAAAAAAAAAALhJ3VRzomdkZEiSPD09JUkHDx5UWlqaOnbsaMa4uLioTZs22rJliyRp165dysnJsYnx9/dXYGCgGbN161ZZrVYzgS5JLVu2lNVqNWOuFBsba079YrVaVa1atZI9WQAAbiOxsbGyWCyKjo42y5iSDQAAAABwO7hpkuiGYWjo0KG6//77FRgYKElKS0uTJPn4+NjE+vj4mNvS0tLk7OysihUrXjXG29u7wDG9vb3NmCuNHDlSGRkZ5u3w4cN/7wQBALhN7dixQx9++KEaNWpkU86UbAAAAACA20GpTudyuRdeeEHff/+9Nm/eXGCbxWKxuW8YRoGyK10ZU1j81fbj4uIiFxeXojQdAIA71pkzZ/TUU09p1qxZGjdunFlemlOySUzLBgAAAAAoOTfFSPRBgwZp+fLlWr9+vapWrWqW+/r6SlKB0eLHjx83R6f7+voqOztb6enpV405duxYgeOeOHGiwCh3AABQdM8//7y6dOliJsHzleaUbBLTsgEAAAAASk6pJtENw9ALL7ygzz77TF9//bVq1qxps71mzZry9fVVUlKSWZadna0NGzaoVatWkqSmTZvKycnJJubo0aNKTU01Y4KDg5WRkaHt27ebMdu2bVNGRoYZAwAAiichIUG7d+9WbGxsgW2lOSWbxLRsAAAAAICSU6rTuTz//PNavHixvvjiC3l4eJgfhq1Wq1xdXc0FyiZMmKDatWurdu3amjBhgtzc3BQREWHGRkVFadiwYfLy8pKnp6eGDx+uhg0bmqPi6tWrp06dOqlv37764IMPJEn9+vVTWFiY3Z+BAwAA+w4fPqwhQ4ZozZo1Klu2rN240piSTWJaNgAAAABAySnVJPqMGTMkSW3btrUpnzdvnnr16iVJGjFihM6fP6+BAwcqPT1dLVq00Jo1a+Th4WHGT506VY6OjgoPD9f58+fVvn17xcfHy8HBwYxZtGiRBg8ebP5kvFu3bpo+ffr1PUEAAG5Tu3bt0vHjx9W0aVOzLDc3Vxs3btT06dO1f/9+SZdGkvv5+Zkx9qZku3w0+vHjx81fijElGwAAAACgtJVqEt0wjL+MsVgsiomJUUxMjN2YsmXLKi4uTnFxcXZjPD09tXDhwmtpJgAAuEL79u21d+9em7LevXurbt26eumll3T33XebU7IFBQVJ+t+UbBMnTpRkOyVbeHi4pP9NyTZp0iRJtlOy3XfffZKYkg0AAAAAcGOVahIdAADcmjw8PBQYGGhT5u7uLi8vL7OcKdkAAAAAALcDkugAAOC6YEo2AAAAAMDtgCQ6AAAoEd98843NfaZkAwAAAADcDsqUdgMAAAAAAAAAALhZkUQHAAAAAAAAAMAOkugAAAAAAAAAANhBEh0AAAAAAAAAADtIogMAAAAAAAAAYAdJdAAAAAAAAAAA7CCJDgAAAAAAAACAHSTRAQAAAAAAAACwgyQ6AAAAAAAAAAB2kEQHAAAAAAAAAMAOkugAAAAAAAAAANhBEh0AAAAAAAAAADtIogMAAAAAAAAAYIdjaTcAAAAAuFU1GRdT2k1AMaW8GlPaTQAAAMAthpHoAAAAAAAAAADYwUh0AAAAALgOBq0bUtpNQDHFtX+ntJsAAABuQoxEBwAAAAAAAADADpLoAAAAAAAAAADYQRIdAAAAAAAAAAA7SKIDAAAAAAAAAGAHSXQAAAAAAAAAAOwgiQ4AAAAAAAAAgB0k0QEAAAAAAAAAsIMkOgAAAAAAAAAAdpBEBwAAAAAAAADADpLoAAAAAAAAAADYQRIdAAAAAAAAAAA7SKIDAAAAAAAAAGAHSXQAAAAAAAAAAOwgiQ4AAAAAAAAAgB0k0QEAAAAAAAAAsIMkOgAAAAAAAAAAdpRqEn3jxo3q2rWr/P39ZbFY9Pnnn9tsNwxDMTEx8vf3l6urq9q2basffvjBJiYrK0uDBg1SpUqV5O7urm7duunIkSM2Menp6YqMjJTVapXValVkZKROnTp1nc8OAAAAAAAAAHCrK9Uk+tmzZ9W4cWNNnz690O2TJk3SlClTNH36dO3YsUO+vr7q0KGDTp8+bcZER0dr2bJlSkhI0ObNm3XmzBmFhYUpNzfXjImIiFBKSooSExOVmJiolJQURUZGXvfzAwDgdhYbG6vmzZvLw8ND3t7eeuSRR7R//36bGL4QBwAAAADc6ko1id65c2eNGzdO3bt3L7DNMAxNmzZNo0aNUvfu3RUYGKj58+fr3LlzWrx4sSQpIyNDc+bM0eTJkxUSEqKgoCAtXLhQe/fu1dq1ayVJ+/bt+//27ju+xvP/4/jrZBEjMWuPqFWlZhGjKVp7VO3YElusasSI2KNKlFhB7BKbGrW3BrGpvVt7E2Tevz88cr4J0vXD4eT9fDw8yH2u+/Y5OZ9zj8913dfNr7/+yvTp03F1dcXV1ZVp06axevXqVy704woPD+fRo0fx/oiIiMj/bN++nc6dOxMSEsLGjRuJioqicuXKhIWFmduoQ1xEREREREQ+dO/tnOgXL17kxo0bVK5c2bwsSZIkuLm5sWfPHgAOHDhAZGRkvDaZM2emYMGC5ja//fYbzs7OlCpVytymdOnSODs7m9u8zogRI8yj3ZydncmWLdubfosiIiIftF9//ZVWrVrx6aefUrhwYWbOnMmVK1c4cOAAYPkOcREREREREZE34b0tot+4cQOADBkyxFueIUMG82s3btzAwcGB1KlT/2Wbjz766JXtf/TRR+Y2r9OnTx8ePnxo/nP16tX/1/sRERGxdg8fPgQgTZo0gGU7xHVHmYiIiIiIiLwp720RPZbJZIr3s2EYryx72cttXtf+77aTJEkSnJyc4v0RERGR1zMMg549e1KuXDkKFiwIWLZDXHeUiYiIiIiIyJvy3hbRM2bMCPDKxfGtW7fMF+MZM2YkIiKC+/fv/2WbmzdvvrL927dvv3JRLyIiIv9Nly5dOHr0KAsWLHjlNUt0iOuOMhEREREREXlT3tsiuouLCxkzZmTjxo3mZREREWzfvp0yZcoAULx4cezt7eO1uX79OsePHze3cXV15eHDh+zbt8/cZu/evTx8+NDcRkRERP47Ly8vVq1axdatW8maNat5uSU7xHVHmYiIiIiIiLwpFi2iP3nyhMOHD3P48GHgxdyphw8f5sqVK5hMJrp3787w4cNZvnw5x48fp1WrViRLlgx3d3cAnJ2d8fDw4LvvvmPz5s0cOnSIZs2aUahQIb766isAPvnkE6pWrUrbtm0JCQkhJCSEtm3bUrNmTfLly2epty4iIvLBMwyDLl26sGzZMrZs2YKLi0u819UhLiIiIiIiItbAzpL/eWhoKBUqVDD/3LNnTwBatmzJrFmz8Pb25tmzZ3Tq1In79+9TqlQpNmzYQMqUKc3r+Pv7Y2dnR8OGDXn27BmVKlVi1qxZ2NramtvMnz+frl27mh9aVrt2bQICAt7RuxQREbFOnTt35ueff2blypWkTJnSPOLc2dkZR0fHeB3iefLkIU+ePAwfPjzBDvG0adOSJk0aevXqlWCH+NSpUwFo166dOsRFRERERETknbBoEf3LL7/EMIwEXzeZTAwcOJCBAwcm2CZp0qRMmDCBCRMmJNgmTZo0zJs37/8TqoiIiLxk8uTJwIvjeVwzZ86kVatWAOoQFxERERERkQ+eRYvoIiIi8uH6q47wWOoQFxERERERkQ/de/tgURERERERERERERERS1MRXUREREREREREREQkASqii4iIiIiIiIiIiIgkQEV0EREREREREREREZEEqIguIiIiIiIiIiIiIpIAFdFFRERERERERERERBKgIrqIiIiIiIiIiIiISAJURBcRERERERERERERSYCK6CIiIiIiIiIiIiIiCVARXUREREREREREREQkASqii4iIiIiIiIiIiIgkQEV0EREREREREREREZEEqIguIiIiIiIiIiIiIpIAFdFFRERERERERERERBKgIrqIiIiIiIiIiIiISAJURBcRERERERERERERSYCK6CIiIiIiIiIiIiIiCVARXUREREREREREREQkASqii4iIiIiIiIiIiIgkQEV0EREREREREREREZEEqIguIiIiIiIiIiIiIpIAFdFFRERERERERERERBKgIrqIiIiIiIiIiIiISAJURBcRERERERERERERSYCK6CIiIiIiIiIiIiIiCVARXUREREREREREREQkASqii4iIiIiIiIiIiIgkQEV0EREREREREREREZEEqIguIiIiIiIiIiIiIpIAFdFFRERERERERERERBKgIrqIiIiIiIiIiIiISAJURBcRERERERERERERSYCK6CIiIiIiIiIiIiIiCVARXUREREREREREREQkAYmqiD5p0iRcXFxImjQpxYsXZ+fOnZYOSURERP4hHcdFRERERETEEhJNET04OJju3bvTr18/Dh06RPny5alWrRpXrlyxdGgiIiLyN3QcFxEREREREUtJNEX0sWPH4uHhgaenJ5988gnjxo0jW7ZsTJ482dKhiYiIyN/QcVxEREREREQsxc7SAbwLERERHDhwAB8fn3jLK1euzJ49e167Tnh4OOHh4eafHz58CMCjR4/+1f8dFfn8X0Yr74N/+zn/f0Q/D//7RvJeeZf5ERGm/PjQ/Jf8iF3HMIw3HY5V0HFc/i0dx+Wv6Dguf0XHcREREXmdRFFEv3PnDtHR0WTIkCHe8gwZMnDjxo3XrjNixAgGDRr0yvJs2bK9lRjl/eK8fISlQ5D3mPOwkZYOQd5jgUz9z+s+fvwYZ2fnNxiNddBxXP4tHcflr+g4Ln9Fx3ERERF5nURRRI9lMpni/WwYxivLYvXp04eePXuaf46JieHevXukTZs2wXUSk0ePHpEtWzauXr2Kk5OTpcOR94zyQ/6OciQ+wzB4/PgxmTNntnQo7zUdx98cfQflryg/5O8oR+LTcVxERMT6JYoierp06bC1tX1ltNqtW7deGdUWK0mSJCRJkiTeslSpUr2tED9YTk5OOnGWBCk/5O8oR/5HI9cSpuP426PvoPwV5Yf8HeXI/+g4LiIiYt0SxYNFHRwcKF68OBs3boy3fOPGjZQpU8ZCUYmIiMg/oeO4iIiIiIiIWFKiGIkO0LNnT5o3b06JEiVwdXUlMDCQK1eu0KFDB0uHJiIiIn9Dx3ERERERERGxlERTRG/UqBF3795l8ODBXL9+nYIFC7J27Vpy5Mhh6dA+SEmSJMHPz++VW+VFQPkhf085Iv+WjuNvlr6D8leUH/J3lCMiIiKS2JgMwzAsHYSIiIiIiIiIiIiIyPsoUcyJLiIiIiIiIiIiIiLyX6iILiIiIiIiIiIiIiKSABXRRUREREREREREREQSoCK6iIiIiIiIiIiIiEgCVEQXEREREREREREREUmAiugiIiIi8k7FxMRYOgQREREREZF/TEV0EREREXmnbGxenIIOGzaMiRMnWjgaERERERGRv6YiunxwDMP4y59FNMJRXuflvNC+Q+TdMgwj3vdw4cKFTJ06lZIlS+r7mMjo85a/EzdHlC8iIiLyPlARXT4oMTExmEwmAG7evElUVJT5Z51gC7zIkdgRjidOnODBgweWDUjeC3HzYtu2bdy6dcu87xCRd+PcuXPm7+H27ds5cOAAvXr14vPPP9cxPBGJey737Nkz7t+/H+915YLEzZGYmBjCw8MtHJGIiIiIiujygYm9+B48eDB16tShRIkSTJw4kT///BOTyaQLr0QubqHU19eX1q1bExoayvPnzy0cmViSYRjmvOjbty/dunVjyZIlREREaJ8h8o5MnDiRfPnycfnyZc6ePUuNGjUYM2YMN2/eBF4c3/V9tH5x98fDhw+nVq1afPrpp7Rt25aVK1cC6HwukYt7Ljdu3Djq16+Pm5sbY8aMISwszMLRiYiISGKmIrp8EOLe/h0UFMT48ePx9PQkf/78zJw5kyFDhnDp0iVdeCVysRdd/fr1Y/r06QwYMICiRYuSNGnSeO2UI4lL7Gg2X19fAgMDCQgIoGnTpjg4OGg0usg7MHXqVHr16sXixYvJkSMHefLkYdWqVWTLlo3t27cTGhoKoO9jIhD7GQ8YMICxY8dSs2ZN+vTpw7Fjx/D39ycwMDBeO0l84nZ6//DDDxQoUICWLVvy/fff4+fnx5UrVywcoYiIiCRWKqLLByH2hDokJIQjR44wdepUPD09WbhwIc2bN+fIkSOMGDGCy5cvq5CeCMX9vA8fPkxwcDBz5syhZs2aODg4cP78eebPn8+uXbsAXZwnFnE7386fP8/q1asJDg6mfPnyREREcPDgQfr168emTZssGKWIdQsKCqJLly4sXryYevXqmZeXL1+eBQsWcOXKFSZOnMixY8fMr+kYbp1iP9eLFy+yYsUKgoKC6N69O15eXixYsAAXFxd+/vlnDh06ZOFIxdKWLVvGokWLWLZsGUOHDqVIkSKYTCbGjRtH//79VUgXERERi1ARXT4Ymzdvpnnz5gQHB2Nvb29e3q1bN5o0acKxY8cYOXIk58+fV5E0EYmOjo73eSdJkgQ7OzucnZ3ZtWsXffv2pXbt2nh7e9OtWzfWrFljwWjlXYrtfHv06BHOzs7cvXuXc+fOcejQIby9vWnZsiVr1qyhcuXKrFu3zsLRilifHTt24OnpSdeuXalZs6Z5ubu7O35+fpQpU4bAwEC2bNmCv78/x48fB9TRaW1u3bpFRESE+XNNliwZDx8+NE+1FhMTg4uLC0OGDOH06dPs3LnTkuGKBcTmCGB+3lHPnj0pXbo0a9eupUaNGsyfP5/169ezYMECxo4dy4ULFywctYiIiCQ2KqLLe+vlkWiVKlWiSZMmGIbBsmXLuH37tvm1rl274u7uzsaNG1m6dOm7DlUsZNu2beaLqB49ejBo0CBy5sxJVFQUnp6eVKpUiZiYGEaMGMGOHTt4+vRpvLwR67Ru3TqWLFkCvMiLoUOHAlC/fn1GjBiBq6srTk5ODB8+nMOHD1OxYkW2bt1qyZBFrNJHH31E2bJlOXPmjLkDs1GjRoSGhtK+fXsAqlatytSpU9m2bRu+vr4qjFmZFStW8N133zF9+nQiIyPNyx0cHDh69Cjw4nwvJiaGrFmzUrx4cc6dO2epcMUCXs4ROzs7ypcvT61atbh79y6DBw+mT58+NG7cmAIFCpApUybGjx/P/PnzLR26iIiIJDJ2lg5A5HUiIyPNo81jp2SwsbFh8ODBREdHs3btWgICAvDy8iJdunQAdOnShYwZM1K3bl2LxS3vhmEYhIWFUbt2bT7//HOyZ8/OihUr2Lp1K46Ojhw6dIhffvmFrFmzUrZsWWxtbQFIlSoV0dHRFo5e3qb79++zcOFCdu/ezfz58/n111/Zu3cv6dKlo3fv3rRs2ZKoqCiKFy8OvBjx9vTpU7JkyWLhyEWsi2EY5M+fn6lTp9K9e3cmTpzI4MGDef78Odu2bSNz5szmzvKqVasyduxY5s6dS86cOS0buLwxM2bMoHfv3nTt2pXixYubz+syZMhA//79adOmDTlz5sTT0xOA8PBwrl+/Trly5SwZtrxDCeVI7Ln9uXPnePz4MZ9//jnw4i6Vxo0bU7duXfMyERERkXfFZGjiSXmPhISEULp0afPP48aNY/v27WTJkoVKlSqZC+S9e/dm06ZN1KxZM14hPVZ0dLS5cCrWJ/bzff78OZkzZ+bx48csWbKEOnXqEBMTY57GA+Dp06c8fPiQNm3acPPmTfbv36/csFKxn/3Jkyf55ptvOHv2LD/++CM9e/bEMAwMwzDnxrNnzzh37hw+Pj5cu3aN/fv3Y2enfmWRN8kwDEwmE7///js9evQgNDSUYcOG0aFDB+DFdzZ2io+4U7i8vB+XD8+qVato0aIF06dPp27duq897g4fPpz+/ftTr149nJycuHTpEjdv3uTw4cPaHycC/yRHzpw5Q5EiRejWrRtubm6MHz+ep0+fsm3bNuBFR7hyRURERN4VXaHIe2PSpEnUqFGDZcuWATB06FCGDBlC2rRpOXbsGD4+PkyYMAGAUaNG8fXXX7Nu3TqGDh3Kw4cP421LRVLrZRiG+fOdN28e6dOnx9nZmcmTJ3Py5Elz4SU6OhrDMAgMDKR69eo8efKEvXv3Ymtrq9HoVihugfzevXtUqlSJ2rVrM3PmTBYvXozJZMLGxobo6GhiYmJYvnw5vr6+PHnyhH379mFnZ6e8EHkLYmJiKFCgAAEBAZQoUYIVK1aYp12zsbExF9rjUgH9w2UYBpGRkaxatYqOHTtSv3598zH79OnTzJ07Fz8/P44ePUrfvn1Zs2YNSZMm5eHDh3z66afmArr2x9brn+bIoUOHyJs3L9OmTWPcuHF0796dhw8fsnHjRvN2VEAXERGRd0lnHvLeKFmyJN9++y2+vr6EhYURHh7O8uXL+eKLL7hw4QKBgYGMGjUKwzDo2rUrI0eOpEOHDjx69AgnJydLhy/vQNxii6+vL1u2bGHTpk2kSJGC/Pnz4+XlRUBAAPny5TNfkHl6epIuXTqaNGmCra2tRi1ZobijVr///nt+/vlnQkJCuH//PuPGjcPPzw+TyRTvQj1r1qx4eXnx5ZdfKi9E3iIbGxsuX75Mnjx5GDduHN26dSMwMBAbGxvq1q2rgrmVMZlM2Nvb8+eff8b7bIcPH87OnTvZvXs3GTNmZMSIEaxZs4Zq1apRqVIlHBwczG21P7Zu/yRHMmXKxPDhw1m7di1NmzalbNmyxMTEkDNnTmxsbJQjIiIiYhGazkXeK0eOHCEgIIDdu3cTGRnJmjVryJs3LwCXL19mypQpzJs3D29vb7y8vID/FVZfN5pNrNOBAwcYPHgw3t7euLq6YmNjw9WrVylRogRFihThxx9/pECBAtSpU4evvvqK7t27A5rmx9rdvXuXQYMGUbt2bb766ivgxT5l/Pjx7Nu3j/79+9OoUSNq1apF2bJl8fHxATR1hMjbEHtMXrx4MT179mTTpk3ky5ePkydP0rNnT27dusXYsWNxc3OzdKjyhkVHR9OjRw/27t1L6dKlOXz4MNeuXaN58+Z8++23FCxYkLp163L58mVCQkKwtbU1H5t1Lpc4/NMcuXTpEiEhISRJksS8ro7ZIiIiYikqost7Ie5F06FDh5g0aRKzZ89m1qxZuLu7m9tdvnzZPCJ9wYIFNGjQ4JX1xbrNmTOHBQsW8OzZM3755RdSpkxpfhDt1atXKVOmDKlTpyYmJgbDMDh8+LD5QVVivebMmUPr1q3Jnz8/CxcupFChQubXjhw5wpQpU5g7dy4uLi48f/6c33//XXkh8gb8VUFr+fLluLu78+OPP9K5c2fzsfro0aPMnDmTMWPGqBhmZWI/40ePHtG9e3du376NyWRixIgR5MiRgxQpUhATE8N3333HxYsXWbFihaVDlndMOSIiIiIfKt0HJxYVe/EdtwBetGhROnfuTHh4OH5+fjg4OFC/fn0AcuTIgYeHB9myZePbb781r6MCeuIRERHBuXPnuH37NsePH8fV1RV7e3siIyPJli0b+/fvZ86cOdjY2NC9e3fs7Ox0228iUKpUKWrWrMm6det49OgR8L8pAQoXLky/fv2oU6cOZ8+epWPHjsoLkTcgbgH9+PHjPHjwgJw5c5IuXTqSJk3K1q1bGTduHO3btwdeHKtjYmL47LPP8Pf3f2Ub8uEzmUxER0fj5OTE9OnTMZlMr5yjRUZGcvLkyXidnZJ4KEdERETkQ6WR6GIxcS+c9+3bx7Nnz3B0dKRkyZIAhIaGMmXKFPbs2cOQIUOoV6/eK9vQ9BzWLaHiyuLFixk4cCAFCxakT58+FClSBMA8Ij0uFUqtz+vywjAMLl68SOvWrbl48SJ79uwha9asCX7+2neI/P/EvQPMx8eHZcuWcePGDXLkyEHevHkJCgrC2dnZwlGKpcTNj9h9dmRkJFevXqVLly5cu3aN0NBQ7OzsdDdhIqUcERERkQ+NiuhiEXFPhvv168fy5cu5f/8+Li4ufPbZZ0yZMgX4XyF979699O7dm2bNmlkybHmH4hZKf/vtN8LDw7G1taV8+fIAzJ8/n7Fjx/LZZ5/RvXt3ChcuDGhqH2sXNy82b97M3bt3cXJyonjx4qRPn56rV6/SuHFjrl27xq5du8iSJYsK5iJv0fjx4xk0aBCLFi0iS5Ys7Ny5k9mzZwPwyy+/kDp1agtHKO+DBw8eMHjwYE6cOMHz58/ZtGkT9vb22j+LmXJERERE3ne6f1YsIrbIOXz4cKZPn05gYCCnT5/G1dWVwMBAmjRpAkCJEiXo2LEjefPmZd26dZYMWd6x2EKpt7c3TZs2pVGjRri7u/PFF1/w4MEDmjZtSrdu3Th+/DgTJkwgNDQU0NQ+1i42L77//nvc3d0ZOnQotWrVomnTpixcuJBs2bKxcOFCsmbNipubG1euXNHFt8gbZhgGMTExRERE8Ntvv9GxY0cqVapE/vz58fDwwM/Pj6ioKEaNGoXGalinmJiYv/z5ZQ4ODjg5OVG9enW2bNmCvb09UVFR2j9bMeWIiIiIWBuNRBeLOXnyJF26dMHb25sqVaqwfv166tevT5MmTVi1ahVfffUV8+bNA+DUqVPkzZtX86YmMpMmTcLX15c1a9bg5OTEnTt36NSpEw4ODuzfvx9bW1vmzp1Lv3796NChA3379rV0yPIOzJkzB29vb1auXEmRIkU4e/YsAwcO5P79+3Tv3p1atWpx4cIFatasSYECBViyZImlQxaxCmvWrCFNmjS4urqal9WqVQsHBweWLl0ar22nTp04fvw427dvV+emFdu9ezdly5b9yzaxdxDFHVGs0cWJh3JERERErIUqkmIxn3zyCQ0bNqRYsWLs2rWLNm3aMGbMGAIDA6latSo///wzlStXBiB//vzY2Nj87SgW+bC9/PkePnyYJk2aULp0aQoUKMAXX3zBmjVrePjwIS1atACgefPmTJ8+nd69e1siZHkHXs6LEydOUKxYMUqVKoWDgwMFCxZk0KBBREVFsWjRIgBy5crFpk2bCA4OtkTIIlZn586d1KpVizp16rBz507gRZHr888/5+rVq4SEhBAdHW1uX7RoUaKjo3n8+LGlQpa3bPPmzXTq1IlLly4BJHjXwcvFUY0uTjyUIyIiImJNVESXdyLuhXVc7du3J3369KxevZpq1aqZC6O5c+emZs2aZMiQIV4BTSPRrZdhGObPd9WqVQDcvHmTU6dOmdtER0eTI0cOOnXqxNmzZ7l//z4AlStXxtbWNsE8kw9bbF6sWLGC27dvY2Njw7Nnz8z7hpiYGD799FO6du1KcHCw+WI9c+bMyguRN+Tp06dkz56dQoUK0aJFCzZu3IitrS0dO3bkyZMn9OvXjy1btvDkyRMePnxonl7JycnJ0qHLW5I7d27++OMPli9fDiQ8nZphGOaC6LJly1i/fr2m+UkklCMiIiJiTVSRlLcqMjISwHxivH79embPnk1ISAh//PGHud2JEyc4f/48SZMmJTIyksOHD1OtWjXmzp2rEeiJQNyHgQ4dOpSOHTty4cIFmjRpwvXr1/n555+B/+VR2rRpzbkVl0YtWZe43/uBAwfSrFkzoqKiKFu2LNu3b2fBggWYTCZzkT1lypQUKlSIZMmSxduO8kLk/69UqVI4OzuTKlUq6tSpQ7t27diwYQPp06dn8+bNPHr0iO+++468efPy1Vdfcfv2bebOnQskPPpUPhxxOy3hxUjhHDlyMHDgQH7++WcuXLjw2vXiHt+nTp1K/fr1cXR01BQ/Vkg5IiIiItZORXR5axo1asS0adMIDw8HXjwgskGDBgwdOpTq1avTpk0bVqxYAUCLFi24ePEi5cqVo1y5cpw6dYq2bdsC8Ucoi3WKvVA6ePAgJ0+eZN68eeTKlYvSpUvzySefMG/ePGbMmAHAjRs3CA4O5uOPPyZVqlQWjFrettjv/ZUrV7Czs2Px4sVkypSJmjVr0r9/f9q0acOUKVM4ceIE165dw9/fnzRp0pA+fXoLRy5iXWJiYkiVKhUjRozg0aNHlClThnLlytG+fXs2bNhApkyZ2LhxIz/++CM+Pj50796dQ4cOmR8MqGLYhy92fxxbCLWzswOgSJEiPHr0iHPnzgHxOz9fLo76+PiwePFiKlas+C5Dl3dEOSIiIiLWTg8WlbemVatWLFq0iMmTJ5MjRw66du3KpEmTKFWqFDt27GDmzJmcOXOGUaNGUaZMGVasWMGGDRtIlSoVo0aNws7OTg8VSkTmzZvH1KlTCQsL45dffiFLliwAHD9+nFGjRrF9+3aeP39OhgwZsLOzY9++fdjb25sfRiXWafXq1dSuXZsMGTKwcOFC3NzcAAgPD2fcuHEMGzaMFClSkDJlSpycnNizZ4/yQuQNWLduHQBff/21uRh27NgxunTpQv/+/SlQoAC9evUiJCSEadOm8dVXX72yDR3DrcuaNWuoVasWbdu25auvvqJBgwYAdOzYkV27dhESEkLy5MmBV4uj3t7eBAUFUa9ePYvFL2+fckRERESsmYro8sbFPSnu2bMngYGBdOrUiXv37jF9+nRzu/379zNw4EAyZMhAUFDQK9uJiooyX7iL9duyZQt9+vTh6NGjzJgxA3d3d/Nrd+7c4f79+2zdupVMmTJRvXp1bG1tlSOJwI0bNxg+fDgTJ05k1qxZNG/ePF6B/Pjx49y9e5fIyEgqVKigvBB5A7Zv306FChWAF8fxFClSMHDgQABGjRrFvHnz2L9/P+fOnWPUqFH89ttvBAQEULVqVQtGLW/btWvXOHToEBMnTuSPP/7A0dERX19fIiIimDdvHm3btqVatWrx9tGTJ0+mT58+zJgxQ8XRREA5IiIiItZMRXR5K+KOPuvZsyfjxo2jQIECbN26Nd5UC5MmTcLb25vz58+TIUMGS4Ur71hCo4T37dtHjx49SJYsGd9//z2VK1cG4nfMxNIIR+uTUF48evTI/NDQX3/9FTc3twQ/f+WFyP/f5s2bGTVqFCEhIfTo0YPQ0FAuX75Mq1at+OSTT1iwYAHt2rXjiy++4PDhw/Tr1w9HR0eWLFli6dDlDYm7P46MjMTe3t782t27d7l37x79+/fn9u3bnDlzhmvXruHp6UlgYKB5/Vu3blGpUiUGDRpE/fr1LfI+5O1RjoiIiEhioyK6vFGvK3YC9OvXjxEjRvDTTz/RsmVLnJycgBej3Tp27MiaNWtwcXF51+GKBcS96AoODuaPP/7g5s2bdOjQgVy5crF371569epFmjRp6NKlC19//TWQcG6JdYibFzNnzuTkyZM8fvyYr776irp16xIVFUW7du1YtGgRv/76K1988YWmbBF5S6Kjo9mxYwdDhgzhwYMHbNu2jWXLlrFt2zaWLl1KWFgY7du3Z/LkyQCcPXuWjz/+WN9HKxF33xoQEMCBAwe4ffs27u7uVKlShbRp05rbHj9+nJCQECZMmMDNmzeZO3eu+bgNcO/ePdKkSfPO34O8XcoRERERSYxURJc3Ju4J9R9//EF4eDjp06c3F8y9vLyYOnUqAwYMoGrVqqRKlYpOnTrx+PFjdu/erYvvROb7779n0aJFFC1alKioKH799Vd+/vlnGjZsyO7du+nTpw/p0qWjTZs21KxZ09Lhyjvi7e3N7NmzadGiBVevXmX//v3UrFmTn376iTt37uDt7c3ixYtZtmxZvItwEXkzYjssY2Ji2LlzJ9999x1JkiRh48aNJEuWjLVr17Jq1Srat29P0aJF462rji3r4uPjw4wZM+jcuTPnzp3j5MmTuLq64ufn98oDnE+dOkWnTp2oXr06vXr1Ui4kEsoRERERSUx05iJvhGEY5hPh/v37U6dOHT777DPq1atH3759AZgwYQIdO3ZkwIABVKhQgUGDBpEkSRJ27NiBjY0NMTExlnwL8g4tWrSI+fPns3LlSlasWGG+mIqdhqNs2bIMGzaMkydPsmvXLgtHK+/Kxo0bWbp0Kb/88gujR4+mQYMGXLt2jRIlSgCQLl06fvrpJypWrMiIESMsHK2IdYq948fGxoby5cszduxYIiIiKFu2LA8ePKB69er4+/tTtGhRXh6HoYKY9Zg7dy5Lly5l/fr1DBw4kGbNmnH48GG2bt1K3759uXv3LvDi+TWGYZA/f37Kly/P3LlzCQsLUy4kAsoRERERSWx09iJvROxF9/Dhw5k8eTK+vr7Mnz+f4sWLs3jxYtq2bQvATz/9hJ+fH2FhYbi7u7Nq1Srs7e2JiorSybSVi1tsuXHjBrVq1aJIkSIEBwdTu3ZtJk2aRL169Xjw4AFPnjyhfPnyLFiwgGHDhlkwanmXrl+/TtasWSlZsiRLliyhdevW+Pv707x5c548ecLOnTtJmTIl8+bNY9OmTZYOV8Tq2djYUK5cOcaMGYODgwMVK1bk0aNHODo6Eh0drSm2rES9evVeOdba2Njg7u5OsWLFWLFiBU2bNmXChAk0btyYJUuW0L9/f27cuBHvIc63bt0ibdq0ygsrpBwRERERAbu/byLyz9y/f5+tW7cybNgwvvnmGwC+/PJL8uTJww8//EBgYCDt2rXDz88PJycnKleujMlkwjCMeCfYYj02bNiAs7MzadOmJXfu3OZpAi5dusTNmzfZsGEDbdu2ZdSoUXTo0AGAOXPmcObMGfz9/SlSpAigh0Vau9jPNzw8nAwZMrB27Vpat27N6NGjzXmxZcsWdu7cSf78+c23iOtWcJG3L7aQPnr0aHx8fChQoABnzpwhWbJklg5N3oDIyEgKFSqEn58fKVOmpGvXrgDUqVOHsLAwbt26xbBhw+jTpw+dOnXi3r17TJ8+nTVr1pA1a1b69euHYRjcu3ePPXv2EBQUpNywMsoRERERkRdUuZT/7OUHPSZNmpQrV65w5coV87JUqVLRoEEDli5dypEjR8zLe/ToAby4xVMFdOtUtWpVrl27RpIkSbh69So7d+4kT548ANSuXZuePXtSs2ZNxo4dS8eOHQEICwtj8+bNZM+ePV5eqIBuXV4ufsd+vuXKlcPLy4slS5YQFBREq1atAHj+/DmTJ08mU6ZMpEuXzryeCugi/93L38O/6pSKLaQPGjSIRYsWkSRJkncVprxl9vb29O3bl5QpU9KjRw9MJhNeXl6kSJGCFClSEBoayu3bt6lQoQLw4o4hV1dXKleubN5Hm0wm0qZNy969e0maNKkF3428DcoRERERkRdUvZT/5NixY+TIkQMnJyf69etH6dKlqVmzJmXLluXMmTNcvHgRFxcXAJycnMibNy/nzp17pWiuArp16t69O0+ePGHHjh2cPHmSsWPHEhkZaS7SFC1alOLFi/P06VPu3bvH9evXuXTpEkOGDOH69essXbrUfJeCbvm1LnGfnxAUFMTZs2fJkiUL1apV45NPPmH69Om0a9eOI0eOsHnzZgzD4IcffuDmzZv88ssvyguRNyT2e7h7927Kli37t51SNjY2VKpUyfxAX3WCf/hi7wJycHDAzc2Ntm3b0q1bNxwdHfH09DS3c3Z2ZuXKlQDmuwlbt25tfgBtbO6oc8X6KEdERERE/kfD+ORfiYmJ4fz58xQuXJiAgAA6derE+PHjyZUrFyaTiWbNmrFlyxbGjRvHqVOngBejiw8dOsTHH3+sC+5EwDAMzp07h5ubG6lSpeLKlStcvXqVAgUKmC+inJ2dGTt2LDVr1mTBggXkzJkTLy8voqKi2LdvH3Z2dppv1wrFxMSYP1MfHx98fHzYsWMHgYGBuLu7c+LECZo1a8asWbNYunQprVq1ok+fPjg6OhIaGqq8EHnDNm/eTKdOnbh06RLAKw8KjSs6Otq8D1cB3TrE3gXk4+ND27ZtefToEdmyZaNdu3aMHz8egCJFilCxYkUWLVpErVq1uHfvHrNnzzZ3aMbtfNG+2fooR0RERET+x2T81RWTSAIWL15Ms2bNsLOz49dff6V8+fLmkSarV6+mffv2ZMuWzXzy/fDhQw4dOoS9vb1GkVoxwzB49uwZ3377LR999BFBQUEcPHiQKlWq0LNnT1KkSMH58+eJjIzEzc0Nd3d3njx5wv79+8mZMyc5cuTAxsZGBRord/78eUaOHEnnzp0pUqQIW7duxd/fn7Nnz7Jo0SIKFSrEzZs3efz4MY6OjmTOnBmTyaS8EHnDLl++TLFixejfv795mrXXiXvcXrZsGUmSJKF69eo6lluBFStW0KxZMzZu3Mjnn3/OtWvXCAoKYvDgwYwdO5bu3bsTFRXF2bNnefLkCcWLF9dxOpFRjoiIiIi8oDMb+cdii+SGYZAmTRpiYmJ49uwZO3bsoECBAqRNmxbDMKhZsya//PILBw4c4MiRI+TMmZPu3btjZ2enE2orZzKZSJYsGe3ataNRo0Zky5YNT09PfHx8mDVrFuHh4bi6unLr1i3Wr1/P06dP8fT0NM+jCS/yTDlivRYuXEj//v3JkCED2bJlA6BChQo4ODgwatQoGjVqxIIFCyhcuDAZMmQwr6e8EPn/iT2Gx/4dFRVFjhw5GDhwIHPmzKFOnTrkypXrlfXiFtCnTp1Kx44d2bRpkwroH6iXBzLcuHGDPHny4OrqCkD27Nnp0aMHjx49omfPnqRMmRIPDw8++eQT8zrR0dHaH1sx5YiIiIjI62k6F/nHYm/HPHfuHJUqVSIyMpK5c+fi6+vLTz/9xL1798wn3cWKFaNt27YEBATQq1cv8zQMOqG2XjExMeZ/f/vtt0yaNIkRI0YwZ84c2rVrx6FDhzh48CDz589n7ty55MqVi9u3b7+yHT0s0rrFxMSQNWtWTp48SXh4uHl52bJl8fHxIV++fFSsWJELFy7EW095IfL/E/sdiv1uxR6PixQpwqNHjzh37hwQf1/+cgHdx8eHxYsXU7FixXcZurwhcT/PR48eAZA5c2bOnDnDiRMnzG2cnZ2pUaMGAG3btiU4ODjedvSwb+ulHBERERFJmKoS8q8EBwdTq1Ytfv75Z6KiomjatCmBgYEMHTqUCRMmcOfOHQDc3d3ZsGFDvHV1Qm3dYgs0x48fJyoqirZt2zJ16lQGDRrEjz/+yPPnz0mVKhUAGTNmJCIigujoaAtGLG9b3GJcLHd3d3r06IGLiwuNGjXiypUr5tfKlClD165d8fT0JEeOHO8yVJFEYc2aNeTNm5f27duzePFiAMqXL0/FihX57rvvCAsLM+/LXy6ge3t7M336dOrVq2ex+OW/i4qKMn+eo0aNYvDgwQAULFiQUqVKMWbMGE6dOmVukzFjRlq3bk1wcLA+80RCOSIiIiLy11REl3+lYsWKZM+encDAQIKDg4mOjsbT09NcSG/fvj0lS5Zk//798abokMQhODiYxo0bs2DBAqKjo2nbti2BgYGMGDGCMWPGcOfOHX777TeqVavGw4cP8fHxsXTI8pbEThkBsHr1apYvX27uWKtTpw79+/fH3t6eli1bcvXqVfN6FSpUYNSoUdja2qqTReQNK1q0KL/88gtXr15lyJAhlCpVitWrV/P111+TJ08eduzYAcR/CPDkyZPp3bs3QUFBKpR9gHr27Mm9e/ews7MjIiICgC1btpAnTx4AcuXKRdOmTTl9+jTe3t6sWrWKkJAQvv/+e+7evUv9+vXN0/GJdVKOiIiIiPwzmltDEhS3CBYrffr0LFiwgObNmzN58mQAGjdujKenJ87OzmzevJnMmTPj7++vOdAToYoVKzJjxgymT5+OjY2NOTcA2rVrh6OjIx999BEpU6bk4MGD5ml+dJeCdTEMw7zv+P777wkMDCRjxoxcvHiR3r17M2TIEOrWrQtAQEAArVu3Zvr06eTMmTPedpQXIv9d3GN4ZGQk9vb2ZM6cmcyZM1O6dGnu3btH//79GTt2LGfOnOHatWukS5eOatWqmedOv3XrFgEBARqB/oE6efIkq1atYuvWrWzdupVUqVIRFRXF3bt3SZo0qbmdh4cHjo6OrFy5km+++YY8efLg7OzM7t27MZlMGIahczkrpRwRERER+edMhmEYlg5C3m8LFiwgTZo0VKlSxbzs7t27NGvWjOvXr9OnTx/q16+Pra0t4eHhJEmSBEAFdCv3uk4WeJEbzZs359GjR3Ts2JHGjRtja2vL9OnTadeuHQsWLKBhw4aYTCbliBWKOwXE1atX+eabbwgKCiJlypTs2rWLtm3b0qlTJ/z9/QFYsWIFAwYMwM3NjQkTJlgydBGrEXf/HBAQwIEDB7h9+zbu7u5UqVKFtGnTmtseP36ckJAQJkyYwM2bN5k7dy5ff/21+fV79+6RJk2ad/4e5P8vJiaGPXv20Lt3b548ecK2bdtInTo1xYsX5/vvv6dx48Y8e/YMR0dH8zqnT5/GZDKRO3du8wNodZy2XsoRERERkX9ORXRJkGEYPHr0iM8++4yPP/6YAQMG8OWXX5pfDwsLo0CBAmTNmpVWrVrh4eGhh/8lQv+mk2XlypXUqFEDOzu7eMVWsT7Dhw/n1KlTJEuWjIkTJ5pHlS9atIjmzZvTuXNnxo4dC8D27dspV66cRp6LvGE+Pj7MmDGDzp07c+7cOU6ePImrqyt+fn6kT58+XttTp07RqVMnqlevTq9evRLsKJUPQ+wx1jAMdu3ahbe3N2FhYYSEhNC6dWvq1KmDu7s7YWFh2Nvb4+DgwNWrV8mWLZt5G8oB66YcEREREfl3VESXBMVOs3Hx4kUaNGhAmjRp6NOnT7y5zuvUqcOePXto0qQJ48ePt2C08q79m06Wli1b4unpab7Q0qgl67Np0yby5MlDjhw5iImJYcSIEQwcOJCSJUuye/fueG0XLVpE69atady4MTNmzDAv19Q+Im/O3LlzGTx4MMHBwRQrVoxff/2VGjVqkD9/fsqUKcPIkSNJmzYtUVFR2NraYjKZ8PPzY8WKFezZs4fkyZNb+i3IfxS3OGoymYiJiWH37t307NmTu3fvcu/ePTJmzIjJZDIXSAFKly7N/PnzLRy9vAvKEREREZF/T1UsMVu5ciUODg64uLiQP39+czHLxcWFxYsXU7duXUaMGEFMTAyVKlUCIEOGDCxZsoTy5ctbMnSxgJiYGJydndm2bRsNGjRg+PDhGIZh7mRJnjw5RYoUYc+ePRw/fjzeSCUV0K3L8+fPad++PY6Ojqxbt45s2bLRvXt3nJ2d6datG2PGjOG7774zt2/YsCHPnj1j5syZ8UaxqYAu8t/Uq1ePYsWK0a9fP/MyGxsb3N3dKVasGCtWrMDDw4MJEyZw9+5dxo4di52dHX5+fmTMmJHY8RS3bt0ibdq0ukvoAxZ3n/rkyRMeP35M5syZKV++PAEBAQwcOJBt27YxYMAAcufOzc2bN7Gzs+Pp06fUqVPHwtHLu6AcEREREflvNBJdADhx4gSFChWifv36nDt3jiZNmlCrVi3y589vbnPhwgWaNGmCyWQiXbp0PHnyhLt373LkyBFsbGw0itTKvdzJEtfFixepW7cuH330Eb179zZ3srRr146mTZtSvnx5bGxsNIWLFfvjjz+oWbMmdnZ2LF++nGzZsvH8+XMCAgLw9vZm7NixdO/e/bXr6nZwkf8uMjKSYcOGMXToUMaOHUvXrl2BF8WxsLAwTCYTNWrUoFGjRvTq1Yt79+5RtGhRDMOgffv29OvXj5iYGO7fv0/FihUJCgqiePHiFn5X8l/EPcYOHjyYHTt2EBoaSoMGDahQoQLu7u7s2LEDX19fnj9/zqZNm0iZMmW8behczropR0RERET+OxXRBXhxsV2yZEmqVatGzZo1+f7770mdOjUZMmRg2LBhODk5kTp1aq5evcqMGTM4ffo0Tk5OTJw4ETs7OxXBrJw6WeSf+PPPP6lcuTKOjo7mQnp4eDgTJkygd+/e+Pv7mwt8IvLmREREMGHCBLy9vRk3bhxeXl7m10JDQ6lfvz5Lly6lePHinDhxgiFDhlC5cmVatWoVr4Pz+fPnJE2a1ILvRN4EPz8/Jk+ezMSJE8mSJQteXl5ERESwevVqsmXLxp49e/D29ubChQucO3eOFClSWDpkeceUIyIiIiL/nqqeQnR0NClSpMDPz4/r169ToUIFli5dyujRo7l48SJlypShdevWbN68mWzZsjFw4EAWLFjA1KlTsbOzIyoqSgV0K5cjRw7y589PtmzZGDNmDMHBwXh5edGsWTMuX77M/fv3yZUrF0uWLKFq1aqkTJmSfPnycejQIWxsbIiJiVEBPRHIkiULGzZs4NmzZ9StW5erV6+SJEkSvLy8GD16NN27d2fRokWWDlPEakRHRwPg4OCAm5sbbdu2pVu3bkyfPj1eO2dnZ1auXMmBAwfo3bs3NjY2tG7d2rx/jh2ZmiRJknf+HuTNMQyDS5cusXbtWubNm0eDBg2Ijo7m999/p2fPnuTIkQMbGxvKlSvHsGHDqF27No6OjpYOW94h5YiIiIjIf6eR6GJ24MABGjdujL+/PzVr1gSgSJEipEiRgo8//pgFCxZQrFgx+vbtS+3atQE0PUciEDuCPDg4mJUrV/Lzzz+bC+edO3fm0qVLfP7553h5eZmncYlLDxFNfF43Iv358+csX76cBg0aKB9E3jAfHx/Wr1/PJ598wu7du7l69Srjxo2ja9euREVF8f3337Nu3ToePXpEzpw52b59O/b29jqGW6E///yTqlWrEhoaytq1a2nRogWjR4+mQ4cOPHv2jBUrVuDm5kbmzJnN6+hOscRFOSIiIiLy32j4sJgVL16c+vXrM2HCBG7evEmRIkVIlSoVK1euZPbs2axcuZKKFStSo0YN8zq6+LZ+sRdNuXPnZv/+/axevZocOXJQpEgRwsLCcHFxwdnZmWrVqlG6dGlWrVplXtcwDBVME6HYEenPnz+nfv36XLp0iaRJk9KkSRPz3Ssi8masWLGCgIAAJk2axJw5c9i5cycDBgyge/fujBs3Djs7O0aPHs3y5ctZuXIlu3btwt7enqioKB3DP3Cx42Dijod5/vw5t2/fpn///nh4eDBq1Cg6dOgAwOnTp5k3bx5nz56Ntx0VR62XckRERETkzdFIdAH+N6J83759+Pj4cPToUYoWLcqcOXPIlCnTK+01IiVx6tOnDwcPHmTOnDlUqVKFVKlSsXTpUtKmTcu6devYuXMnQ4YMUW5Yoa1bt1KhQoV/tc6ff/5JkSJFqF27NjNmzHhLkYkkLi+PHp8yZQpTp07l0KFD5mUPHz5k0KBBjBs3jmnTpuHh4RFvGzqGf/jiPovm9u3bODg4YG9vT7JkyRg0aBCDBg2iU6dOBAQEAPDs2TMaNGhAVFQUa9eu1TR8iYByREREROTN0hBRAf43orxkyZJ89NFHREZGsmLFCpInTw68etGui+/EJfbzr1u3Lnv37uXTTz81d7KkTZsWgGrVqlGtWjVABRprExwcTJMmTQgKCqJVq1b/eL0sWbLw+++/kyZNmrcXnEgiEvdY/OjRI5ycnMicOTNnzpzhxIkTfPrppxiGgbOzMzVq1GDcuHG0bduWFClS0KhRI/N2tH/+sBmGYS5wjhw5kjVr1hAWFoaDgwPTpk2jVatWXLt2jUmTJmFjY0NkZCRnzpzh1q1bHDx40DwXvoqk1ks5IiIiIvLm6cxIzGJiYgDo27cv2bNn59dffzW/plu+E7eEOlli71J4+YYWFWisS6NGjfDz86N9+/bMnDnzH68XExND+vTpzfkQu48RkX8v7vQro0aNYvDgwQAULFiQUqVKMWbMGE6dOmVukzFjRlq3bk1wcDD16tWzWNzy5sV+xr6+vowZMwYvLy+mTp3K48ePqVu3LilSpGDUqFFMnTqVU6dO8eDBA0qXLs2hQ4fMU/moOGrdlCMiIiIib57OjhKBrVu3/qN2sSfLWbJkIUOGDPHmthZRJ0viFB0dDYCfnx8DBgygQ4cOLFy48G/XizsK7vjx4wC6IBf5D3r27Mm9e/ews7MjIiICgC1btpAnTx4AcuXKRdOmTTl9+jTe3t6sWrWKkJAQvv/+e+7evUv9+vX1LAIrEXd+6+vXr7N582bmzJlDw4YNuXHjBteuXaNnz56kTZsWZ2dn2rZty8qVK1mwYAHDhg3Dzs6O6OhoPavEiilHRERERN4eVTSsXHBwMJUqVWLWrFn/eJ20adPSsGFDzp49+8oIY7E+6mSRhBiGYR5F/tNPP5EkSRIiIyPx8PBgzpw5f7lebMfK5MmTadWqFefPn38nMYtYk5MnT7Jq1SoqVarEgwcPcHBwICoqirt375I0aVJzOw8PDzp37oyjoyPffPMNLVu25M6dOyxevBiTyaSHPFuJ2P3qs2fPMJlMnD59mi+++IL169fj7u7OiBEj6NSpE2FhYYwZM4bHjx/j6OgYbxu6U8y6KUdERERE3h4V0a3cf52GoWXLluzatct8Mq5pGKyTOlnkr8R+/wcMGMCwYcPImjUrAQEBNGjQAA8Pj9fmTdwCemBgIN7e3vj4+PDxxx+/y9BFrEK+fPmYNWsWyZIlw83Njfv372NnZ4dhGCRJkgR4USwDcHd3Jzg4mJMnT/LLL78QEhJinpZBdwtZj4ULF9K9e3dMJhOurq707t2b+vXr4+/vT4cOHYAXD3XeuHEje/futXC0YgnKEREREZG3Q8OSrFjswx39/Pyws7OjQ4cOODo60rhx479cL+7F+ZEjRyhcuLCmYbBSjRo14tSpU7Rv3x7DMGjduvU/Wq9ly5Z4enrG62RRjlinBw8esHr1agYMGGDed7Rt25ZMmTLRrl077O3tcXd3N492jc2JqVOn4u3tzezZs/n2228t+RZEPkixUyKVLVuWkSNH4u3tjZubGyEhIeTOndvcuR0TE0NERAQODg5cvXqVfPnymbcRExOjEegfuJcf7H7+/HlCQ0O5fv062bNnZ9KkSbRr1w5PT08Anj59So8ePTCZTFSsWNFSYcs7pBwREREReTdMhoaSWqW4J9Q//fQTkZGReHt74+joyOTJk2nRosXfrjd58mRmzJhBcHCwRpFaodhOFoBhw4YxePBgZs+e/Y86WWJzJLaTRazX7du3KViwICNGjKBNmzbExMRgMpl48uQJ1apV48SJE4waNYp27dqZ15k8eTJ9+/Zl+vTpeqChyH8Qu5+N/TsmJobdu3fTs2dP7t69y71798iYMSMmk4mwsDDs7e0BKF26NPPnz7dw9PKmxD3e3rt3jzRp0gAvHvKdPXt2lixZQq1atcydJy4uLuzevZuHDx9y4MAB7O3t1clt5ZQjIiIiIu+OzpislKZhkL/ypua69vDw0FzXViRun2rsv9OnT0/lypWZOnUqN27cMF9op0yZkty5c5MhQwbmzZtnbr969Wr69etHYGCgCugi/0FsRxXAkydPuHbtGjY2NpQvX56AgADy5ctHeHg4AwYMYPbs2UycOJGAgAB++OEHZs+ebeHo5U2KzYNhw4bh7u7OL7/8AsC8efM4ePAgM2bMYNGiRTRr1oywsDAuXLhA2bJlOXjwoHkqHxVHrZtyREREROTd0Uh0K/bgwQMqVqxImzZt6NKlCwCRkZEMGDCAMWPGMHPmzL+chmHmzJmahsHKDRgwgClTpjB+/Hju3bvHvn37mD9/PtOmTaNVq1bx2r7cyfLdd98xc+ZM6tevb4HI5U2LOxItMjKSiIgIkidPDsDatWsZOXIk2bNnZ/z48aRJk4bw8HAaNmzId999R/ny5c25sW3bNuzs7ChXrpzF3ovIhyrufnbw4MHs2LGD0NBQGjRoQIUKFXB3d2fHjh34+vry/PlzNm3aRMqUKeNtI+5dRvLhi46Oxt3dncWLF5MsWTK6du1KgwYNWLJkCWfPnmXUqFG4uLi8dj3lQeKgHBERERF5NzRRphWLjIzkzz//JFmyZMD/5kbt27cvO3fupEuXLoSFhdGuXbt4o4v79u1LUFCQCuhWTnNdS6y4BfQxY8awZcsWrl27Ro0aNejXrx/Vq1fn+vXrBAUF8emnn1KuXDlOnz5NTEwMZcqUwWQymS/Gv/zyS8u+GZEPWOx+1s/Pj8mTJzNx4kQGDx6Ml5cXISEhlC1blnLlyjFs2DC8vb3JkycP586dI0WKFOZtqChmXWxtbenQoQNJkyaldOnSLF26lPv373Pv3j3279/PmjVrzAMlXl5PEgfliIiIiMi7ofv3rISmYZB/6686WUqWLEmXLl2YNm0aQLxOFh8fH3WyWJnYfUPfvn0ZM2YMpUuX5rvvvuOHH36ga9eu/Pnnn3h4eBAYGEjnzp1xdnamSpUqHD58GDs7O41mE3lDDMPg0qVLrF27lnnz5tGgQQOio6P5/fff6dmzJzly5MDGxsZcSK9duzaOjo6WDlveAn9/f/z9/QFwc3PD1taWffv2sWbNGsqUKYOTkxOXL1+ma9euHDt2zMLRiiUoR0RERETeLY1EtwJ/NQ1DkyZNGDlyJL169Yo3DcP9+/cJDAyMNw1DihQpWLVqlaZhsEJxR5LH/jtuJ0v16tXJmDEjhmGYO1nu3LnDvHnzaNu2LSaTSZ0sVm7VqlUsWbKEJUuWUKZMGXbv3g3A7NmzuXHjBgEBAXz66ad8+umn8daLiorCzk6HEpE3wWQyYW9vz/Pnz3Fzc2P58uW0aNECf39/WrduzbNnz1ixYgVubm5UqFCBChUqAJqWwdpEREQQFhbGwIED2bdvH56enkybNo0SJUrg7++Pj48P7u7uODk5cezYMQoUKGDpkOUdU46IiIiIvHuaE/0D93fTMDg6OjJjxgyCgoK4cOFCvGkYNIo0cdBc1/J3DMNg3bp1XLp0iU6dOrFu3Trc3d2ZOHEi+fLlo2zZsjRr1oyePXvqQlzkDYrt1Izb0Xn+/HnKli1L8+bNmTFjBkOHDqVTp04AHD58mH79+uHt7Y2bm5slQ5d34MSJE/j6+nL9+nUKFChAxYoVWbZsGX369KFEiRLA/3JI53KJk3JERERE5N1REd1K9O3bl1mzZtGxY0dcXFxo06YNLVu2ZODAgWTJkoUTJ06wfPlyLl26ROrUqRkxYoQK6ImAOlnkdV5XuLt//z6PHz/GycmJGjVqUKtWLXx8fLh9+zaurq5cuHABb29vRo4caeHoRaxD3P3z7du3cXBwwN7enmTJkjFo0CAGDRpEp06dCAgIAODZs2c0aNCAqKgo1q5da15XrNudO3fYtWsXw4cP5+jRo6RIkQIvLy/8/PzMbeLuyyXxUY6IiIiIvBsqoluBVatW0atXL2bNmmWehiH2Fu8qVaoQEBBAjhw5XllP0zAkHupkkVhxC3d37twhefLkxMTEmO9OuHz5MtWqVcPf358qVapw9+5dhg8fTrNmzShUqJD2GSJvQNyC1siRI1mzZg1hYWE4ODgwbdo0nJycGD58ONOmTaNLly5ERkZy5swZbt26xcGDB7G3t4/3XZbEwdfXl3HjxlGiRAm2bt1q6XDkPaQcEREREXl7VET/wGkaBvk76mSRWHELd8OGDWPt2rU8fvyYtGnTMnr0aEqUKMEff/xBwYIFcXd3N8+Z/+jRI3bt2oXJZFJeiLxBvr6+TJkyhYkTJ+Li4kKrVq0IDw9n79692NrasnjxYhYvXkzatGnJlSsXgwYNws7OTt/DRCbuvjs0NJSiRYtia2ur0cViphwREREReftURP/AaBoG+TfUySKv4+vry6RJk/jxxx+5c+cOe/fuZc2aNQQHB1O7dm1WrlxJixYtyJo1K2nSpGHLli3Y29vrYlzk/ynuMfzGjRvUq1cPX19fqlWrxi+//EKLFi0YNmwYnTp1Mrd99uwZjo6O5m3oDqHE6eX9r/JAXqYcEREREXm7NIzpAxL31u27d++ap2FInTo1qVOn5vLly9y/f5+iRYsCYGNjQ506dczTMIj1e7mTxWQy4erqSsGCBXnw4AFDhw6ld+/euLu7c/v2bbJmzUpQUBDp0qVTJ4sVi7vvePz4MZs2bWLcuHE0b94cgIiICLy9vWnYsCFHjhyhTp06nDlzhoiICLJkyYKNjY1Gvoq8AbEFrmfPnmEymTh9+jRffPEF69evx93dndGjR9OhQwfCwsKYPHky7du3J2XKlPG2oaJY4vRyB6byQF6mHBERERF5uzSZ5gfCMAxzEWzYsGHUqVOHUqVKUbNmTUJDQ4EXJ8vXrl1j5cqVrFixgmbNmhESEkKRIkXMt3+L9YqJiTFfQN29e5dnz54RFhZG6tSpyZ49Ow8fPnxtJ8uBAwcYOnSoJUOXtyx23+Hn58eYMWM4deoUadKkAV7sW+zt7Rk4cCDFihVj3rx5REdHkyFDBrJly4aNjQ0xMTEqoIu8IQsXLqR79+7mTs7evXtTv359/P396dChAwB//vknGzduZO/evRaOVkREREREREBF9A9GbHHU19eXsWPH4unpSfPmzUmbNi3ly5dn1apVZM2aldmzZzN//nz69evHkydP2LZtm3lksopg1kudLPI6MTEx5n8vWrSImTNnUq9ePUqVKsX8+fN59OiRed/i7OxM8uTJefDgwSuj1/TwQpH/7uVZ886fP09oaCjXr18ne/bsTJo0iaZNm+Lp6QnA06dP6dGjByaTiYoVK1oiZBEREREREXmJ5kR/z708DUPlypXp1KnTK9MwTJkyhSNHjpAvXz5u3rypaRgSKc11La+zbds2Fi9eTN68eenWrRtjx45lyZIlVK1alT59+mBvb09ERARfffUVlSpVws/Pz9Ihi1iFuPvWe/fume8AKVmyJNmzZ2fJkiXUqlWLq1evki9fPlxcXNi9ezcPHz7kwIED2NvbxzsPEBEREREREctQEf0D4efnh8lk4qeffmLevHnUqFHDPLrt4cOHVK9enUqVKjFw4MB4o0h18W3d1Mkif+fGjRuUK1eOW7du0bdvX3x8fIiKiqJPnz5s3bqVmJgYypQpw4EDB3j06BFHjhxRPoi8YcOGDWPnzp107tyZWrVqcebMGapWrUq/fv3MD3vetm0byZIlI1euXAwdOtR8h5C+jyIiIiIiIpan6up7StMwyD+hua7l72TMmJFly5aRIUMGVq1axYEDB7Czs2PkyJH4+vri6urK7du3KVOmjLmAHh0dbemwRaxGdHQ0R48eZcOGDTRp0oS+ffsSFhZGkyZNWL9+PTdu3KBXr16sXr2aRYsWMXLkSPP3UPtnERERERGR94MqrO+p2OLotm3b2L59O9999x2FChWicuXKXLp0iXHjxhEZGYnJZCIyMpLw8HDSpUtn4ajlXVEni/wbn332GUuXLuXZs2dMmTKFo0ePYmtrS506dZg4cSILFy5kzJgx5pGvL+eJiPx3tra2dOjQgebNmzN69Gj27dtHYGAg586dY//+/axZsybB9UREREREROT9oArae+zGjRt4enoyd+5cnj17BkDXrl0pW7Ysq1atolSpUnTp0gU3Nzfu3r1Lv379LByxvCvqZJF/67PPPiMoKIiDBw8SEBDAiRMnzK/FnQ9fI19F3gx/f3/8/f0BcHNzw9bWln379rFmzRrKlCmDk5MTly9fpmvXrhw7dszC0YqIiIiIiMhf0Zzo77mjR49Sr1490qdPz4QJEyhevDjR0dGsXr2aDRs2cOfOHbJmzcqoUaPMt39r9FrioLmu5b84dOgQ7du3J0eOHPzwww+4uLhYOiQRqxMREcEPP/zAwIEDadCgAZ6ennz55ZeUKFGCRo0a4ePjQ3R0NN7e3hw7dox169bp2C0iIiIiIvIeUxH9A3D06FFatmxJiRIl8PLy4rPPPjO/ZhiGeRSpHkCW+KiTRf6Lffv2MWXKFKZPn64pfUTeohMnTuDr68v169cpUKAAFStWZNmyZfTp04cSJUoA/zuOa/8sIiIiIiLy/lIR/QNx6NAhPD09KV68ON26dePTTz+1dEjynlAni/wXsbkRExOjQrrIW3Tnzh127drF8OHDOXr0KClSpMDLyws/Pz9zm7j7ahEREREREXn/qIj+AdE0DJIQdbLIf6HCnci75evry7hx4yhRogRbt261dDgiIiIiIiLyD6mI/oHRNAySEHWyiIi8n+J2WIWGhlK0aFFsbW3VkSUiIiIiIvKBUBH9A6RpGCQh6mQREXk/vVww1xzoIiIiIiIiHw4V0T9QGr0mCVEni4iIiIiIiIiIyJujIrqIFVIni4iIiIiIiIiIyJuhYaoiVkgFdBERERERERERkTdDRXQRERERERERERERkQSoiC4iIiIiIiIiIiIikgAV0UVEREREREREREREEqAiuoiIiIiIiIiIiIhIAlREF5EPRs6cORk3btw/bj9r1ixSpUr1l20GDhxIkSJF/l9xiYiIiIiIiIiI9VIRXeQdaNWqFSaTCZPJhL29PRkyZODrr78mKCiImJgYS4f3xnh5eZEnT57Xvvbnn39ia2vLsmXL/vP29+/fT7t27f7z+iIiImI56gwXERERkQ+Viugi70jVqlW5fv06ly5dYt26dVSoUIFu3bpRs2ZNoqKiLB3eG+Hh4cG5c+fYuXPnK6/NmjWLtGnTUqtWrX+93YiICADSp09PsmTJ/t9xioiI/BvqDFdnuIiIiIgkbiqii7wjSZIkIWPGjGTJkoVixYrRt29fVq5cybp165g1axYAly5dwmQycfjwYfN6Dx48wGQysW3bNgC2bduGyWRi/fr1FC1aFEdHRypWrMitW7dYt24dn3zyCU5OTjRp0oSnT5+at/Pll1/i5eVF9+7dSZ06NRkyZCAwMJCwsDBat25NypQp+fjjj1m3bh0AhmGQO3dufvzxx3jv4/jx49jY2HD+/PlX3mORIkUoVqwYQUFBr7w2a9YsWrRogY2NDR4eHri4uODo6Ei+fPn46aef4rVt1aoV33zzDSNGjCBz5szkzZsXeHUE29ixYylUqBDJkycnW7ZsdOrUiSdPnrzyf69YsYK8efOSNGlSvv76a65evZrwBwXMnDmTTz75hKRJk5I/f34mTZpkfi32M1q2bBkVKlQgWbJkFC5cmN9+++0vtykiIh82dYarM1xEREREEi8V0UUsqGLFihQuXPg/jeoaOHAgAQEB7Nmzh6tXr9KwYUPGjRvHzz//zJo1a9i4cSMTJkyIt87s2bNJly4d+/btw8vLi44dO9KgQQPKlCnDwYMHqVKlCs2bN+fp06eYTCbatGnDzJkz420jKCiI8uXL8/HHH782Lg8PDxYvXhyvmL19+3bOnTtHmzZtiImJIWvWrCxatIjff/+dAQMG0LdvXxYtWhRvO5s3b+bkyZNs3LiR1atXv/b/srGxYfz48Rw/fpzZs2ezZcsWvL2947V5+vQpw4YNY/bs2ezevZtHjx7RuHHjBH+v06ZNo1+/fgwbNoyTJ08yfPhwfH19mT17drx2/fr1o1evXhw+fJi8efPSpEkTqymiiIjIq9QZrs5wEREREUnEDBF561q2bGnUqVPnta81atTI+OSTTwzDMIyLFy8agHHo0CHz6/fv3zcAY+vWrYZhGMbWrVsNwNi0aZO5zYgRIwzAOH/+vHlZ+/btjSpVqph/dnNzM8qVK2f+OSoqykiePLnRvHlz87Lr168bgPHbb78ZhmEY165dM2xtbY29e/cahmEYERERRvr06Y1Zs2Yl+F7v379vJE2a1AgKCjIva9GiheHq6prgOp06dTLq1atn/rlly5ZGhgwZjPDw8HjtcuTIYfj7+ye4nUWLFhlp06Y1/zxz5kwDMEJCQszLTp48aQDm9+Tn52cULlzY/Hq2bNmMn3/+Od52hwwZYo4/9jOaPn26+fUTJ04YgHHy5MkEYxMRkQ/XXx3HCxcubFSrVs0wjH93HC9durSxa9cu4+DBg0bu3LkNNzc3o3LlysbBgweNHTt2GGnTpjVGjhxp3o6bm5uRMmVKY8iQIcaZM2eMIUOGGDY2Nka1atWMwMBA48yZM0bHjh2NtGnTGmFhYYZhGMawYcOMAgUKxIu3R48exhdffJHge504caKRPHly4/Hjx+Zl27ZtMwDjxIkTRkREhDFgwABj3759xoULF4x58+YZyZIlM4KDg+P9vlKkSGE0b97cOH78uHHs2DHDMF49jvv7+xtbtmwxLly4YGzevNnIly+f0bFjR/PrM2fONOzt7Y0SJUoYe/bsMUJDQ42SJUsaZcqUMbd5+TgeGBhoZMqUyVi6dKlx4cIFY+nSpUaaNGnM5y6xn1H+/PmN1atXG6dPnzbq169v5MiRw4iMjEzw9yIiIiIiiZtGootYmGEYmEymf73eZ599Zv53hgwZSJYsGbly5Yq37NatWwmuY2trS9q0aSlUqFC8dQDzepkyZaJGjRrmEWmrV6/m+fPnNGjQIMG4UqVKxbfffmte5/HjxyxdupQ2bdqY20yZMoUSJUqQPn16UqRIwbRp07hy5Uq87RQqVAgHB4e//B1s3bqVr7/+mixZspAyZUpatGjB3bt3CQsLM7exs7OjRIkS5p/z589PqlSpOHny5Cvbu337NlevXsXDw4MUKVKY/wwdOvSVEXtxf5eZMmWK93sTEZHEI3/+/Fy6dOlfrzd06FDKli1L0aJF8fDwYPv27UyePJmiRYtSvnx56tevz9atW+OtU7hwYfr370+ePHno06cPjo6OpEuXjrZt25InTx4GDBjA3bt3OXr0KACtW7fm9OnT7Nu3D4DIyEjmzZsX75j8Mnd3d6Kjo1m8eLF5WVBQEK6urhQoUAB7e3sGDRrE559/jouLC02bNqVVq1av3FGWPHlypk+fzqeffkrBggVf+391796dChUq4OLiQsWKFRkyZMgr24mMjCQgIABXV1eKFy/O7Nmz2bNnj/k9vWzIkCGMGTOGb7/9FhcXF7799lt69OjB1KlT47Xr1asXNWrUIG/evAwaNIjLly9z7ty5BH8vIiIiIpK4qYguYmEnT57ExcUFeDE9CbworMeKjIx87Xr29vbmf8c+6Cwuk8n0ysPOXtfm5e0A8dbz9PRk4cKFPHv2jJkzZ9KoUaO/nc/Uw8ODXbt2cfbsWYKDgwFo1KgRAIsWLaJHjx60adOGDRs2cPjwYVq3bm2eLzVW8uTJ//L/uHz5MtWrV6dgwYIsXbqUAwcOMHHiRODV39nrOiletyz2fU+bNo3Dhw+b/xw/fpyQkJB4bf/u9yYiIomDOsPVGS4iIiIi1s/O0gGIJGZbtmzh2LFj9OjRA3jxwC2A69evU7RoUYB486paQvXq1UmePDmTJ09m3bp17Nix42/XqVChArly5WLWrFls3bqVhg0bkjJlSgB27txJmTJl6NSpk7n96+Zl/TuhoaFERUUxZswYc+fDy6PXAKKioggNDaVkyZIAnD59mgcPHpA/f/5X2mbIkIEsWbJw4cIFmjZt+q9jEhGRxOdD6Axv3rw5/v7+/6ozvFKlSpw9e5bt27cDr3aGjxkzBldXV1KmTMno0aPZu3dvvG38087wDh06MGTIENKkScOuXbvw8PB4I53hpUqViveara1tvJ/VGS4iIiIi/4aK6CLvSHh4ODdu3CA6OpqbN2/y66+/MmLECGrWrEmLFi0AcHR0pHTp0owcOZKcOXNy584d+vfvb9G4bW1tadWqFX369CF37ty4urr+7Tomk4nWrVszduxY7t+/z+jRo82v5c6dmzlz5rB+/XpcXFyYO3cu+/fvNxcg/qmPP/6YqKgoJkyYQK1atdi9ezdTpkx5pZ29vT1eXl6MHz8ee3t7unTpQunSpc1F9ZcNHDiQrl274uTkRLVq1QgPDyc0NJT79+/Ts2fPfxWjiIhYN3WGv6DOcBERERGxdprOReQd+fXXX8mUKRM5c+akatWqbN26lfHjx7Ny5cp4o6OCgoKIjIykRIkSdOvWjaFDh1ow6hc8PDyIiIj4yzlUX9aqVSsePnxIvnz5KFu2rHl5hw4d+Pbbb2nUqBGlSpXi7t278S7E/6kiRYowduxYRo0aRcGCBZk/fz4jRox4pV2yZMno3bs37u7uuLq64ujoyMKFCxPcrqenJ9OnT2fWrFkUKlQINzc3Zs2a9a+L/CIiYl1iO8P//PNPDh48yPDhw6lTp06CneG///47O3bs+KA7wydPnsxvv/2Gh4eH+bXcuXMTGhrK+vXrOXPmDL6+vuzfv/9fxxW3M/zChQvMnTv3LzvD9+7dy8GDB2nduvXfdoaPGDGCn376iTNnznDs2DFmzpzJ2LFj/3WMIiIiIiJmln2uqYh8CHbt2mXY2dkZN27csHQoIiIi71zLli0NwAAMOzs7I3369MZXX31lBAUFGdHR0fHa/v7770bp0qUNR0dHo0iRIsaGDRsMwNi6dathGIaxdetWAzDu379vXmfmzJmGs7NzvO34+fkZhQsXNv/s5uZmdOvWLV6bHDlyGP7+/vGWAcby5cvjLTt//rwBGD/88MM/fs9Xr141bGxsjHz58sVb/vz5c6NVq1aGs7OzkSpVKqNjx46Gj49PvFhbtmxp1KlT55Vtvhzv2LFjjUyZMhmOjo5GlSpVjDlz5sT73cT+XpYuXWrkypXLcHBwMCpWrGhcunTJvI2Xf0+GYRjz5883ihQpYjg4OBipU6c2vvjiC2PZsmWGYRjGxYsXDcA4dOiQuf39+/fjfUYiIiIiIi8zGUacSRtFROIIDw/n6tWrtGvXjkyZMjF//nxLhyQiIiL/0u7du/nyyy/5448/zA8fFRERERGRf07TuYhIghYsWEC+fPl4+PAhP/zwg6XDERERkX8hPDycc+fO4evrS8OGDVVAFxERERH5jzQSXURERETECs2aNQsPDw+KFCnCqlWryJIli6VDEhERERH5IKmILiIiIiIiIiIiIiKSAE3nIiIiIiIiIiIiIiKSABXRRUREREREREREREQSoCK6iIiIiIiIiIiIiEgCVEQXEREREREREREREUmAiugiIiIiIiIiIiIiIglQEV1EREREREREREREJAEqoouIiIiIiIiIiIiIJEBFdBERERERERERERGRBPwfV3dNNdiG6bsAAAAASUVORK5CYII=",
      "text/plain": [
       "<Figure size 1500x1000 with 6 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "def plot_dummy_counts_grid(df, prefixes):\n",
    "    n_prefixes = len(prefixes)\n",
    "    n_rows = (n_prefixes + 2) // 3\n",
    "\n",
    "    fig, axes = plt.subplots(n_rows, 3, figsize=(15, 5 * n_rows))\n",
    "\n",
    "    if n_rows == 1:\n",
    "        axes = axes.reshape(1, -1)\n",
    "    axes = axes.flatten()\n",
    "\n",
    "    for i, prefix in enumerate(prefixes):\n",
    "        dummy_cols = [col for col in df.columns if col.startswith(prefix)]\n",
    "        counts = df[dummy_cols].sum().sort_values(ascending=False)\n",
    "\n",
    "        sns.barplot(x=counts.index, y=counts.values, palette='viridis', ax=axes[i])\n",
    "        axes[i].set_title(f'Anzahl der Vorkommen für {prefix} Dummies')\n",
    "        axes[i].set_xlabel('Dummy Variablen')\n",
    "        axes[i].set_ylabel('Anzahl')\n",
    "        axes[i].tick_params(axis='x', rotation=45)\n",
    "\n",
    "    for i in range(n_prefixes, len(axes)):\n",
    "        axes[i].set_visible(False)\n",
    "\n",
    "    plt.tight_layout()\n",
    "    plt.show()\n",
    "\n",
    "prefixes = ['shift', 'speeding', 'weather', 'road', 'weekday']\n",
    "plot_dummy_counts_grid(X_train, prefixes)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "3ffbfe79",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deskriptive Statistiken für metrische Variablen:\n",
      "          avg_speed   hard_brakes  trip_distance\n",
      "count  20000.000000  20000.000000   20000.000000\n",
      "mean      46.955431      1.987300      20.400866\n",
      "std        9.983939      1.406321      16.370594\n",
      "min       10.000000      0.000000       1.019350\n",
      "25%       40.210704      1.000000       9.923435\n",
      "50%       46.933676      2.000000      15.896143\n",
      "75%       53.726714      3.000000      25.538578\n",
      "max       81.665638     10.000000     228.850160\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1800x1200 with 6 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "def plot_metric_variables(df):\n",
    "    metric_vars = ['avg_speed', 'hard_brakes', 'trip_distance']\n",
    "\n",
    "    fig, axes = plt.subplots(2, 3, figsize=(18, 12))\n",
    "\n",
    "    for i, var in enumerate(metric_vars):\n",
    "        sns.histplot(df[var], kde=True, ax=axes[0, i], bins=30, alpha=0.7)\n",
    "        axes[0, i].set_title(f'Verteilung von {var}')\n",
    "        axes[0, i].set_xlabel(var)\n",
    "        axes[0, i].set_ylabel('Häufigkeit')\n",
    "\n",
    "    for i, var in enumerate(metric_vars):\n",
    "        sns.boxplot(y=df[var], ax=axes[1, i])\n",
    "        axes[1, i].set_title(f'Boxplot von {var}')\n",
    "        axes[1, i].set_ylabel(var)\n",
    "\n",
    "    plt.tight_layout()\n",
    "    plt.show()\n",
    "\n",
    "metric_vars = ['avg_speed', 'hard_brakes', 'trip_distance']\n",
    "print(\"Deskriptive Statistiken für metrische Variablen:\")\n",
    "print(X_train[metric_vars].describe())\n",
    "\n",
    "plot_metric_variables(X_train)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ab122f01",
   "metadata": {},
   "source": [
    "Man kann die Verteilungen deutlich erkennen:\n",
    "\n",
    "- **avg_speed**: Normalverteilung mit einem Mittelwert um 47 km/h und einer Standardabweichung von etwa 10. Die Histogramm zeigt die charakteristische Glockenform einer Normalverteilung. Der Boxplot bestätigt eine symmetrische Verteilung mit wenigen Ausreißern.\n",
    "\n",
    "- **hard_brakes**: Poisson-Verteilung mit λ ≈ 2, erkennbar an der rechtschiefen Verteilung mit einem Peak bei niedrigen Werten (0-2 harte Bremsmanöver). Die meisten Fahrten haben wenige bis gar keine harten Bremsmanöver, was realistisch ist.\n",
    "\n",
    "- **trip_distance**: Lognormalverteilung mit deutlicher Rechtsschiefe. Die meisten Fahrten sind kurz (um 16 km), aber es gibt einen langen Schwanz mit wenigen sehr langen Fahrten. Dies entspricht typischen Fahrtmustern, bei denen viele kurze Fahrten und wenige lange Strecken gefahren werden.\n",
    "\n",
    "Die Boxplots zeigen zusätzlich die Quartile und identifizieren Ausreißer, die bei allen drei Variablen vorhanden sind, aber besonders bei trip_distance aufgrund der Lognormalverteilung."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "761c0673",
   "metadata": {},
   "source": [
    "### Modellierung der Korrelationen"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "14d31bfe",
   "metadata": {},
   "source": [
    "Wir prüfen nun, wie hoch die lineare Korrelation zwischen den einzelnen Variablen sind, denn wir wollen aus unabhängigen Variablen eine abhängige Zielvariable vorhersagen. Besteht eine zu große Korrelation zwischen den erklärenden Variablen, treffen wir auf ein Multikolinearitätsproblem."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "8a320b4c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x1000 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Korrelationsmatrix\n",
    "plt.figure(figsize=(12, 10))\n",
    "sns.heatmap(X_train.corr(), annot=True, fmt=\".2f\", cmap='coolwarm', square=True, cbar_kws={\"shrink\": .8})\n",
    "plt.title('Korrelationsmatrix der Merkmale')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "684d6fee",
   "metadata": {},
   "source": [
    "Man kann erkennen das die kategorischen Variablen natürlich eine stärkere Korrelation haben, weil sie schon in Dummies umgewandelt wurden. Ansonsten gibt es keine stärkeren Korrelationen, sodass wir sehr wahrscheinlich kein Multikolinearitätsproblem haben."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2127272a",
   "metadata": {},
   "source": [
    "### Schrittweise Variablenselektion: Backward Selection\n",
    "\n",
    "Um herauszufinden, welche Variablen tatsächlich erklärend für die Zielvariable sind, wird eine schrittweise Backward Selection durchgeführt. Dabei startet man mit allen potenziellen erklärenden Varriablen und entfernt schrittweise die am wenigsten signifikanten Variablen, bis nur noch signifikante Prädiktoren übrig bleiben. Dies hilft, ein einfaches und interpretierbares Modell zu erhalten. Da die Zielvariable binär ist, wird eine logistische Regression verwendet. Das Modell wird auf den Trainingsdaten trainiert und die Modellgüte auf den Testdaten evaluiert."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "19c7e28c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Entfernte Variablen und zugehörige p-Werte:\n",
      "road_Außerorts: p=1.0000\n",
      "weather_winterlich: p=1.0000\n",
      "road_Autobahn: p=0.8703\n",
      "trip_distance: p=0.6828\n",
      "speeding_haeufig: p=1.0000\n",
      "road_Innerorts: p=0.3855\n",
      "weekday_Mo-Fr: p=1.0000\n",
      "weekday_So: p=0.6575\n",
      "shift_normal: p=1.0000\n",
      "weekday_Sa: p=0.5344\n",
      "weather_trocken: p=0.3417\n",
      "weather_nass: p=0.0516\n",
      "\n",
      "Verbleibende Variablen im Modell:\n",
      "['const', 'avg_speed', 'hard_brakes', 'shift_frueh', 'shift_spaet', 'speeding_manchmal', 'speeding_selten']\n",
      "\n",
      "Zusammenfassung des finalen Modells:\n",
      "                           Logit Regression Results                           \n",
      "==============================================================================\n",
      "Dep. Variable:                      y   No. Observations:                20000\n",
      "Model:                          Logit   Df Residuals:                    19993\n",
      "Method:                           MLE   Df Model:                            6\n",
      "Date:                Sat, 05 Jul 2025   Pseudo R-squ.:                 0.04322\n",
      "Time:                        10:31:36   Log-Likelihood:                -11755.\n",
      "converged:                       True   LL-Null:                       -12286.\n",
      "Covariance Type:            nonrobust   LLR p-value:                3.464e-226\n",
      "=====================================================================================\n",
      "                        coef    std err          z      P>|z|      [0.025      0.975]\n",
      "-------------------------------------------------------------------------------------\n",
      "const                -1.0751      0.085    -12.714      0.000      -1.241      -0.909\n",
      "avg_speed             0.0177      0.002     11.111      0.000       0.015       0.021\n",
      "hard_brakes           0.0822      0.011      7.401      0.000       0.060       0.104\n",
      "shift_frueh          -0.8050      0.035    -22.841      0.000      -0.874      -0.736\n",
      "shift_spaet          -0.7985      0.044    -18.075      0.000      -0.885      -0.712\n",
      "speeding_manchmal    -0.5367      0.038    -14.142      0.000      -0.611      -0.462\n",
      "speeding_selten      -0.4607      0.038    -11.994      0.000      -0.536      -0.385\n",
      "=====================================================================================\n"
     ]
    }
   ],
   "source": [
    "import statsmodels.api as sm\n",
    "\n",
    "def backward_selection(X, y, significance_level=0.05):\n",
    "    X_ = X.copy().astype(float)\n",
    "    removed_features = []\n",
    "    while True:\n",
    "        X_with_const = sm.add_constant(X_)\n",
    "        model = sm.Logit(y, X_with_const).fit(disp=0)\n",
    "        pvalues = model.pvalues.drop('const')\n",
    "        max_pval = pvalues.max()\n",
    "        if max_pval > significance_level:\n",
    "            excluded_feature = pvalues.idxmax()\n",
    "            removed_features.append((excluded_feature, max_pval))\n",
    "            X_ = X_.drop(columns=[excluded_feature])\n",
    "        else:\n",
    "            break\n",
    "    return X_, removed_features, model\n",
    "\n",
    "X_selected, removed_features, final_model = backward_selection(X_train, y_train)\n",
    "\n",
    "print(\"Entfernte Variablen und zugehörige p-Werte:\")\n",
    "for feat, pval in removed_features:\n",
    "    print(f\"{feat}: p={pval:.4f}\")\n",
    "\n",
    "print(\"\\nVerbleibende Variablen im Modell:\")\n",
    "print(list(X_selected.columns))\n",
    "\n",
    "print(\"\\nZusammenfassung des finalen Modells:\")\n",
    "print(final_model.summary())"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e9fd3cbc",
   "metadata": {},
   "source": [
    "Die Backward Selection funktioniert wie erwartet: Alle erklärenden Variablen werden im Modell beibehalten, während die nicht-erklärenden Variablen (Wetter, Straßentyp, Wochentag, Fahrstrecke) aufgrund ihrer statistischen Insignifikanz entfernt werden.\n",
    "\n",
    "Ein wichtiges Detail ist die Behandlung der kategorialen Variablen: Bei den ordinalen Features (Schaltverhalten und Geschwindigkeitsüberschreitungen) wird jeweils eine Dummy-Variable entfernt. Dies ist methodisch korrekt, da bei k Kategorien nur k-1 Dummy-Variablen benötigt werden, um alle Informationen zu kodieren."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "257e622b",
   "metadata": {},
   "source": [
    "### Interpretation der Modellkoeffizienten\n",
    "\n",
    "Die geschätzten Koeffizienten der logistischen Regression geben Aufschluss darüber, welche Variablen einen Einfluss auf die Wahrscheinlichkeit eines Diebstahls haben. Diese werden mit den tatsächlichen, zur Generierung verwendeten Koeffizienten verglichen."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6641f80c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Modellkoeffizienten:\n",
      "const               -0.788152\n",
      "avg_speed            0.017391\n",
      "hard_brakes          0.081678\n",
      "shift_frueh         -0.814953\n",
      "shift_normal        -0.808104\n",
      "speeding_haeufig    -0.838057\n",
      "speeding_manchmal   -0.834292\n",
      "road_Autobahn       -0.257555\n",
      "road_Außerorts      -0.273524\n",
      "road_Innerorts      -0.257073\n",
      "dtype: float64\n"
     ]
    }
   ],
   "source": [
    "# Modellkoeffizienten anzeigen\n",
    "coefficients = final_model.params\n",
    "print(\"\\nModellkoeffizienten:\")\n",
    "print(coefficients)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4194adef",
   "metadata": {},
   "source": [
    "### Vergleich mit dem Generierungsmodell (Verlassen der Anwenderperspektive)\n",
    "\n",
    "Abschließend wird das trainierte Modell mit dem tatsächlich zur Generierung der Zielvariable verwendeten Modell verglichen. Die geschätzten Koeffizienten sollten – abgesehen von Zufallsschwankungen – mit den wahren Koeffizienten übereinstimmen. Dies zeigt, dass das systematische Vorgehen des Data Scientist erfolgreich war und das zugrundeliegende Modell korrekt rekonstruiert wurde."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0541fa09",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Vergleich der geschätzten und wahren Koeffizienten:\n",
      "                    Geschätzte Koeffizienten  Wahre Koeffizienten\n",
      "avg_speed                           0.017391                0.015\n",
      "const                              -0.788152               -2.000\n",
      "hard_brakes                         0.081678                0.100\n",
      "road_Autobahn                      -0.257555                0.000\n",
      "road_Außerorts                     -0.273524                0.000\n",
      "road_Innerorts                     -0.257073                0.000\n",
      "shift_frueh                        -0.814953                0.500\n",
      "shift_normal                       -0.808104               -0.300\n",
      "shift_spaet                              NaN               -0.300\n",
      "speeding_haeufig                   -0.838057               -0.300\n",
      "speeding_manchmal                  -0.834292               -0.300\n",
      "speeding_selten                          NaN                0.500\n",
      "trip_distance                            NaN                0.000\n",
      "weather_nass                             NaN                0.000\n",
      "weather_trocken                          NaN                0.000\n",
      "weather_winterlich                       NaN                0.000\n",
      "weekday_Mo-Fr                            NaN                0.000\n",
      "weekday_Sa                               NaN                0.000\n",
      "weekday_So                               NaN                0.000\n"
     ]
    }
   ],
   "source": [
    "# Tatsächliche Betas aus der Generierung (angepasst an drop_first=True)\n",
    "true_betas_dict = {\n",
    "    'const': -2,\n",
    "    'avg_speed': 0.015,\n",
    "    'hard_brakes': 0.1,\n",
    "    'trip_distance': 0.,\n",
    "    'shift_normal': -0.3,     # frueh wurde gedroppt\n",
    "    'shift_spaet': 0.5,\n",
    "    'speeding_manchmal': -0.3, # selten wurde gedroppt\n",
    "    'speeding_haeufig': 0.5,\n",
    "    'weather_trocken': 0.,    # nass wurde gedroppt\n",
    "    'weather_winterlich': 0.,\n",
    "    'road_Außerorts': 0.,     # Autobahn wurde gedroppt\n",
    "    'road_Innerorts': 0.,\n",
    "    'weekday_Sa': 0.,         # Mo-Fr wurde gedroppt\n",
    "    'weekday_So': 0.\n",
    "}\n",
    "\n",
    "# Erstelle Series nur für Variablen, die im finalen Modell sind\n",
    "true_betas = pd.Series({var: true_betas_dict.get(var, 0) for var in coefficients.index})\n",
    "\n",
    "print(\"Vergleich der geschätzten und wahren Koeffizienten:\")\n",
    "comparison = pd.DataFrame({\n",
    "    'Geschätzte Koeffizienten': coefficients,\n",
    "    'Wahre Koeffizienten': true_betas\n",
    "})\n",
    "print(comparison)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c16e59df",
   "metadata": {},
   "source": [
    "Die Koeffizienten sind nicht deckend gleich aber das erlernte Modell kommt dem idealen sehr nahe."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7516554c",
   "metadata": {},
   "source": [
    "## Güte der Modellparameter"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c1bb79ce",
   "metadata": {},
   "source": [
    "### Einfluss des Stichprobenumfangs\n",
    "\n",
    "In diesem Abschnitt wird untersucht, wie sich der Stichprobenumfang auf die Schätzgüte der Modellparameter auswirkt. Dazu werden jeweils k = 1.000 zufällige Stichproben aus der Grundgesamtheit gezogen, mit Stichprobenumfängen n von 1.000 bis 50.000 (Schrittweite 5.000). Für jede Stichprobe wird das optimale Modell aus Abschnitt 3 trainiert und der geschätzte Beta-Wert einer erklärenden Variable (z.B. `avg_speed`) gespeichert. Die Verteilungen der geschätzten Beta-Werte werden für drei ausgewählte Stichprobenumfänge verglichen und der funktionale Zusammenhang zwischen n und der Standardabweichung der Schätzungen analysiert."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "616ae484",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Stichprobenumfang:   0%|          | 0/10 [00:00<?, ?it/s]c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "Stichprobenumfang:  10%|█         | 1/10 [01:21<12:12, 81.40s/it]c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "Stichprobenumfang:  20%|██        | 2/10 [02:54<11:45, 88.21s/it]c:\\Users\\yann.MSI\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "Stichprobenumfang: 100%|██████████| 10/10 [32:08<00:00, 192.82s/it]\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "from tqdm import tqdm\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "\n",
    "k = 1000\n",
    "n_values = np.arange(1000, 50001, 5000)\n",
    "beta_name = 'avg_speed'\n",
    "\n",
    "betas_by_n = {}\n",
    "\n",
    "for n in tqdm(n_values, desc=\"Stichprobenumfang\"):\n",
    "    betas = []\n",
    "    for _ in range(k):\n",
    "        idx = np.random.choice(X.index, size=n, replace=False)\n",
    "        X_sub = X.iloc[idx]\n",
    "        y_sub = target[idx]\n",
    "        X_sub_enc = pd.get_dummies(X_sub, drop_first=True)\n",
    "        # Modell mit denselben Features wie das finale Modell aus Abschnitt 3\n",
    "        model = LogisticRegression(max_iter=200, solver='lbfgs')\n",
    "        model.fit(X_sub_enc, y_sub)\n",
    "        # Finde Index der gewünschten Variable\n",
    "        try:\n",
    "            beta_idx = list(X_sub_enc.columns).index(beta_name)\n",
    "            betas.append(model.coef_[0][beta_idx])\n",
    "        except ValueError:\n",
    "            betas.append(np.nan)  # Falls Feature in kleiner Stichprobe fehlt\n",
    "    betas_by_n[n] = np.array(betas)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "28e0cb42",
   "metadata": {},
   "source": [
    "### Vergleich der Verteilungen des geschätzten Beta-Werts für drei Stichprobenumfänge\n",
    "\n",
    "Im Folgenden werden die Verteilungen des geschätzten Beta-Werts für die erklärende Variable `avg_speed` für drei verschiedene Stichprobenumfänge (n = 1.000, 10.000, 50.000) graphisch verglichen."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b0bb7329",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(12, 6))\n",
    "# Use only available keys from betas_by_n\n",
    "for n in [1000, 11000, 46000]:\n",
    "    sns.kdeplot(betas_by_n[n][~np.isnan(betas_by_n[n])], label=f\"n={n}\")\n",
    "plt.title(\"Verteilung des geschätzten Beta-Werts für avg_speed bei verschiedenen Stichprobenumfängen\")\n",
    "plt.xlabel(\"Geschätzter Beta-Wert für avg_speed\")\n",
    "plt.ylabel(\"Dichte\")\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "990bb2a0",
   "metadata": {},
   "source": [
    "**Interpretation:**\n",
    "\n",
    "Mit wachsendem Stichprobenumfang werden die Verteilungen der geschätzten Beta-Werte schmaler und konzentrieren sich stärker um den wahren Wert. Kleine Stichproben führen zu einer größeren Streuung und damit zu unsichereren Schätzungen."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "50ea2928",
   "metadata": {},
   "source": [
    "### Funktionaler Zusammenhang zwischen n und der Standardabweichung des geschätzten Beta-Werts\n",
    "\n",
    "Für jeden Stichprobenumfang wird die Standardabweichung der geschätzten Beta-Werte berechnet und gegen n aufgetragen. Zusätzlich wird die theoretische Entwicklung der Standardabweichung nach der Formel $\\sigma(\\hat{\\beta}) \\propto 1/\\sqrt{n}$ eingezeichnet."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cf7a7e61",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "stds = np.array([np.nanstd(betas_by_n[n]) for n in n_values])\n",
    "\n",
    "plt.figure(figsize=(10, 6))\n",
    "plt.plot(n_values, stds, marker='o', label='Empirische Standardabweichung')\n",
    "plt.plot(n_values, stds[0]*np.sqrt(n_values[0]/n_values), '--', label=r'$\\propto 1/\\sqrt{n}$')\n",
    "plt.xlabel('Stichprobenumfang n')\n",
    "plt.ylabel('Standardabweichung des geschätzten Beta-Werts')\n",
    "plt.title('Zusammenhang zwischen Stichprobenumfang und Schätzgenauigkeit')\n",
    "plt.legend()\n",
    "plt.grid(True)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "10afcd69",
   "metadata": {},
   "source": [
    "Die Standardabweichung der Schätzung eines Modellparameters nimmt mit wachsendem Stichprobenumfang näherungsweise proportional zu $1/\\sqrt{n}$ ab. Das bedeutet: Je mehr Daten zur Verfügung stehen, desto präziser und stabiler werden die Parameterschätzungen. Die Lernqualität eines Modells steigt also mit der Datenmenge, wobei der Zugewinn mit zunehmender Datenmenge abnimmt (abnehmender Grenznutzen)."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}