{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Archive:  ./archive (67).zip\n",
      "  inflating: names-by-nationality.csv  \n"
     ]
    }
   ],
   "source": [
    "!unzip ./archive\\ \\(67\\).zip"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "data = pd.read_csv('./names-by-nationality.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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>name</th>\n",
       "      <th>sex</th>\n",
       "      <th>nationality</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Aarav</td>\n",
       "      <td>Male</td>\n",
       "      <td>Indian</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Aaryan</td>\n",
       "      <td>Male</td>\n",
       "      <td>Indian</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Abha</td>\n",
       "      <td>Female</td>\n",
       "      <td>Indian</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Abhay</td>\n",
       "      <td>Male</td>\n",
       "      <td>Indian</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Abhilash</td>\n",
       "      <td>Male</td>\n",
       "      <td>Indian</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       name     sex nationality\n",
       "0     Aarav    Male      Indian\n",
       "1    Aaryan    Male      Indian\n",
       "2      Abha  Female      Indian\n",
       "3     Abhay    Male      Indian\n",
       "4  Abhilash    Male      Indian"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "4695"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "name           0\n",
       "sex            0\n",
       "nationality    0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "import json\n",
    "def object_to_int(data,coloum):\n",
    "    info_dict = {}\n",
    "    all_info = []\n",
    "    index = -1\n",
    "    for info in data[coloum]:\n",
    "        if info not in info_dict:\n",
    "            index = index + 1\n",
    "            info_dict[info] = index\n",
    "    for info in data[coloum]:\n",
    "        all_info.append(info_dict[info])\n",
    "    with open(f'{coloum}.json','w') as json_file:\n",
    "        json.dump(info_dict,json_file)\n",
    "    return all_info,info_dict"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "nationality_info = object_to_int(data,'nationality')\n",
    "data['nationality'] = nationality_info[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "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>name</th>\n",
       "      <th>sex</th>\n",
       "      <th>nationality</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Aarav</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Aaryan</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Abha</td>\n",
       "      <td>Female</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Abhay</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Abhilash</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       name     sex  nationality\n",
       "0     Aarav    Male            0\n",
       "1    Aaryan    Male            0\n",
       "2      Abha  Female            0\n",
       "3     Abhay    Male            0\n",
       "4  Abhilash    Male            0"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "'archive (67).zip'   names-by-nationality.csv   Untitled.ipynb\r\n",
      " main.ipynb\t     nationality.json\r\n"
     ]
    }
   ],
   "source": [
    "!ls"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "sex_info = object_to_int(data,'sex')\n",
    "data['sex'] = sex_info[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "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>name</th>\n",
       "      <th>sex</th>\n",
       "      <th>nationality</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Aarav</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Aaryan</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Abha</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Abhay</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Abhilash</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       name  sex  nationality\n",
       "0     Aarav    0            0\n",
       "1    Aaryan    0            0\n",
       "2      Abha    1            0\n",
       "3     Abhay    0            0\n",
       "4  Abhilash    0            0"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1    2573\n",
       "0    1356\n",
       "2     766\n",
       "Name: sex, dtype: int64"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data['sex'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "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>name</th>\n",
       "      <th>sex</th>\n",
       "      <th>nationality</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Aarav</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Aaryan</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Abha</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Abhay</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Abhilash</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       name  sex  nationality\n",
       "0     Aarav    0            0\n",
       "1    Aaryan    0            0\n",
       "2      Abha    1            0\n",
       "3     Abhay    0            0\n",
       "4  Abhilash    0            0"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='sex'>"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "pd.crosstab(data['sex'],data['nationality']).plot()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "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>name</th>\n",
       "      <th>sex</th>\n",
       "      <th>nationality</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Aarav</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Aaryan</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Abha</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Abhay</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Abhilash</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       name  sex  nationality\n",
       "0     Aarav    0            0\n",
       "1    Aaryan    0            0\n",
       "2      Abha    1            0\n",
       "3     Abhay    0            0\n",
       "4  Abhilash    0            0"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.tree import DecisionTreeClassifier,ExtraTreeClassifier\n",
    "from sklearn.model_selection import *\n",
    "from sklearn.metrics import *\n",
    "from sklearn.ensemble import RandomForestClassifier,AdaBoostClassifier,BaggingClassifier,ExtraTreesClassifier,GradientBoostingClassifier,StackingClassifier,VotingClassifier\n",
    "from sklearn.linear_model import RidgeClassifier,SGDClassifier,Ridge,RidgeClassifierCV,RidgeCV\n",
    "from sklearn.naive_bayes import GaussianNB\n",
    "import pickle\n",
    "import os"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "def fit_and_calcuate_metrixs(models:dict,X_train,X_test,y_train,y_test):\n",
    "    models_info = {}\n",
    "    for name,model in models.items():\n",
    "        print(name)\n",
    "        model = model.fit(X_train,y_train)\n",
    "        y_preds = model.predict(X_test)\n",
    "        try:\n",
    "            info = {\n",
    "                'Accuracy':model.score(X_test,y_test),\n",
    "                'F1 Score':f1_score(y_test,y_preds,average='macro'),\n",
    "                'Precision':precision_score(y_test,y_preds,average='macro'),\n",
    "                'Recall':recall_score(y_test,y_preds,average='macro')\n",
    "            }\n",
    "            plot_confusion_matrix(model,X_test,y_test)\n",
    "        except:\n",
    "            info = {'Accuracy':model.score(X_test,y_test)}\n",
    "        models_info[name] = info\n",
    "        print('\\n\\n')\n",
    "    return models_info\n",
    "def calcuate_metrixs(models:dict,X_train,X_test,y_train,y_test):\n",
    "    models_info = {}\n",
    "    for name,model in models.items():\n",
    "        print(name)\n",
    "        y_preds = model.predict(X_test)\n",
    "        info = {\n",
    "            'Accuracy':model.score(X_test,y_test),\n",
    "            'F1 Score':f1_score(y_test,y_preds,average='macro'),\n",
    "            'Precision':precision_score(y_test,y_preds,average='macro'),\n",
    "            'Recall':recall_score(y_test,y_preds,average='macro')\n",
    "        }\n",
    "        plot_confusion_matrix(model,X_test,y_test)\n",
    "        plot_roc_curve(model,X_test,y_test)\n",
    "        models_info[name] = info\n",
    "        print('\\n\\n')\n",
    "    return models_info"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "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>name</th>\n",
       "      <th>sex</th>\n",
       "      <th>nationality</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Aarav</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Aaryan</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Abha</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Abhay</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Abhilash</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4690</th>\n",
       "      <td>Worth</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4691</th>\n",
       "      <td>Wrigley</td>\n",
       "      <td>2</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4692</th>\n",
       "      <td>X-iomania</td>\n",
       "      <td>1</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4693</th>\n",
       "      <td>Xadrian</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4694</th>\n",
       "      <td>Xakery</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4695 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "           name  sex  nationality\n",
       "0         Aarav    0            0\n",
       "1        Aaryan    0            0\n",
       "2          Abha    1            0\n",
       "3         Abhay    0            0\n",
       "4      Abhilash    0            0\n",
       "...         ...  ...          ...\n",
       "4690      Worth    0            6\n",
       "4691    Wrigley    2            6\n",
       "4692  X-iomania    1            6\n",
       "4693    Xadrian    0            6\n",
       "4694     Xakery    0            6\n",
       "\n",
       "[4695 rows x 3 columns]"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "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>name</th>\n",
       "      <th>sex</th>\n",
       "      <th>nationality</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Aarav</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Aaryan</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Abha</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Abhay</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Abhilash</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4690</th>\n",
       "      <td>Worth</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4691</th>\n",
       "      <td>Wrigley</td>\n",
       "      <td>2</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4692</th>\n",
       "      <td>X-iomania</td>\n",
       "      <td>1</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4693</th>\n",
       "      <td>Xadrian</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4694</th>\n",
       "      <td>Xakery</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4695 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "           name  sex  nationality\n",
       "0         Aarav    0            0\n",
       "1        Aaryan    0            0\n",
       "2          Abha    1            0\n",
       "3         Abhay    0            0\n",
       "4      Abhilash    0            0\n",
       "...         ...  ...          ...\n",
       "4690      Worth    0            6\n",
       "4691    Wrigley    2            6\n",
       "4692  X-iomania    1            6\n",
       "4693    Xadrian    0            6\n",
       "4694     Xakery    0            6\n",
       "\n",
       "[4695 rows x 3 columns]"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "X = data['name']\n",
    "y = data['sex']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "GradientBoostingClassifier\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/ranuga/.local/lib/python3.8/site-packages/sklearn/metrics/_classification.py:1221: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
      "  _warn_prf(average, modifier, msg_start, len(result))\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\n",
      "ExtraTreesClassifier\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/ranuga/.local/lib/python3.8/site-packages/sklearn/metrics/_classification.py:1221: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
      "  _warn_prf(average, modifier, msg_start, len(result))\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\n",
      "BaggingClassifier\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/ranuga/.local/lib/python3.8/site-packages/sklearn/metrics/_classification.py:1221: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
      "  _warn_prf(average, modifier, msg_start, len(result))\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\n",
      "AdaBoostClassifier\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/ranuga/.local/lib/python3.8/site-packages/sklearn/metrics/_classification.py:1221: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
      "  _warn_prf(average, modifier, msg_start, len(result))\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\n",
      "RandomForestClassifier\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/ranuga/.local/lib/python3.8/site-packages/sklearn/metrics/_classification.py:1221: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
      "  _warn_prf(average, modifier, msg_start, len(result))\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\n",
      "SGDClassifier\n",
      "\n",
      "\n",
      "\n",
      "RidgeClassifier\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/ranuga/.local/lib/python3.8/site-packages/sklearn/metrics/_classification.py:1221: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
      "  _warn_prf(average, modifier, msg_start, len(result))\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\n",
      "ExtraTreeClassifier\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/ranuga/.local/lib/python3.8/site-packages/sklearn/metrics/_classification.py:1221: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
      "  _warn_prf(average, modifier, msg_start, len(result))\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\n",
      "DecisionTreeClassifier\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/ranuga/.local/lib/python3.8/site-packages/sklearn/metrics/_classification.py:1221: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
      "  _warn_prf(average, modifier, msg_start, len(result))\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAATgAAAEGCAYAAADxD4m3AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8vihELAAAACXBIWXMAAAsTAAALEwEAmpwYAAAejklEQVR4nO3deZQdZZ3/8fenO52V7DtJI0EiMTADxMiqnAjOsDgH0HFB/Sk/xBNRQAGRAZ1xQQdh/A0IgjgIjEE2g6iEEQgYQGAkQMCIkACJAbITGrIATdLb9/dHVcOFdLrvJfem7q3+vM6p01VP1a363nuqv+d56qmnShGBmVke1WUdgJlZpTjBmVluOcGZWW45wZlZbjnBmVlu9ck6gEJ91S/6MyjrMKrWll0HZh1C1ev3XHPWIVS1zbxGS2zR9uzj8A8Nipdebi9q20cf3zI3Io7YnuNtj6pKcP0ZxP46LOswqtYz35medQhV7z1fWJB1CFXtoZi33ft46eV2Hp67S1Hb1o9fMmq7D7gdqirBmVn1C6CDjqzDKIoTnJmVJAhao7gmatac4MysZK7BmVkuBUF7jQzxdIIzs5J14ARnZjkUQHuNJDjf6GtmJesgipp6ImmYpF9LekrSYkkHShoh6S5JS9K/w9NtJekSSUslPS5pWk/7d4Izs5IE0BpR1FSEi4E7ImIKsDewGDgbmBcRk4F56TLAkcDkdJoJXN7Tzp3gzKwkQdBe5NQdSUOBQ4CrACKiJSI2AMcAs9LNZgHHpvPHANdEYj4wTNL47o7hBGdmpQloL3ICRklaUDDNLNjTJOBF4L8l/VnSlZIGAWMjYk26zVpgbDo/AVhR8PmVadk2uZPBzEqSjGQoWlNEbGuMYR9gGnBqRDwk6WLebI4mx4oISe+4R8M1ODMrkWgvcurBSmBlRDyULv+aJOG90Nn0TP+uS9evAhoLPj8xLdsmJzgzK0nSyaCipm73E7EWWCFpj7ToMGARMAc4Pi07HrglnZ8DfD7tTT0A2FjQlO2Sm6hmVpLkPrjteuJSoVOB6yT1BZYBJ5BUvGZLOhF4Hvhkuu1twFHAUqA53bZbTnBmVrKOHmpnxYqIhUBX1+i2em5aJK8APLmU/TvBmVlJylyDqygnODMrSSDaa+TyvROcmZWsXE3USnOCM7OSBKIl6rMOoyhOcGZWkuRGXzdRzSyn3MlgZrkUIdrDNTgzy6kO1+DMLI+STobaSB21EaWZVQ13MphZrrX7PjgzyyOPZDCzXOtwL6qZ5VEy2N4JzsxyKBCtHqpVu6bP2MRJ319NfV1w+w0jmH3p2J4/lENq7aDx/KdQa0BH8Or04bx07ATGXvUsA59+hfYByUn+womT2LLLQAAGPLWJ0TesQO1B+059WHn2lCy/QmbyfA5F4Bt9ASQdQfLew3rgyog4v5LHK4e6uuDk81ZxznG70bSmgZ/ctoT5c4eyfEn/rEPb4aKPWPGNPYj+9dDWQeMPn+a1vxsKwIufnMir00e8Zfu65jbG/HI5q86YTNvIftRvas0i7Mzl/xxSzdzoW7E0LKkeuIzkZa1TgU9Lmlqp45XLHvs2s/q5vqxd3o+21jruvWUYBx6+MeuwsiElyQ1Qe6D27l9uNHj+y7z6vuG0jewHQPuQhoqHWI3yfg4FSQ2umClrlazB7QcsjYhlAJJuJHlx66IKHnO7jRzXyour+76x3LSmgSnTmjOMKGMdwS7fW0TfdVvYcOgYNr97J4be+yKjbl7FyDlraH7vYJo+PpFoqKPv2s2oPZh4wVPUbe5g/YfH8MrBo7L+BjtcbziH3MnQ9Uta96/g8awS6sTy7+1JXXMbO1/6N/qufJ2mf55A+9AG1BaMmfU8w29fy8tH74w6gn7PN7PyG+9BLR3s8u9PsfndO9E6Li9NM4Okk6FWHniZeRqWNLPzrdetbMk6HF5a28DonVveWB41vpWmNb2zqVWoY2AfmqcMZtATG2kf1jdpvjbUsekDI+m/7DUAWof3pXmvIUS/ejoGN/D6ewbTb0W+ai7FyPs5lLw2sE9RU9YqmeCKeklrRFwREdMjYnoD/SoYTnGeXjiQCZNaGNu4hT4NHcw4ZgPz7xyadViZqN/USl1zGwBq6WDgk5toGdef+g3pP28EOz22gZYJAwB4bd9hDFjyKrQH2tJO/2dfpWX8gKzCz0z+z6Gyvfi54iqZYh8BJkuaRJLYjgM+U8HjlUVHu7jsWxM47/pl1NXDnTeO4PlnemcTq35jK+OuehZ1ABG88v4RvLbPMCb+x9PUv9IGBFsaB/LC598FQMvOA3htr6G869tPQh1s/OBoWib2vgSX93Mo8EgGIqJN0inAXJLbRK6OiCcrdbxyeuTuITxy95Csw8hcS+NAln93z63KV561RxdbJ9YfOY71R46rZFg1Ie/nUDXUzopR0UZyRNxG8jZqM8uJCLkGZ2b5lHQy1MZQrdpIw2ZWRVS2G30lPSfpr5IWSlqQlo2QdJekJenf4Wm5JF0iaamkxyVN62n/TnBmVpKkk0FFTUX6UETsExHT0+WzgXkRMRmYly5DMipqcjrNBC7vacdOcGZWsnbqipreoWOAWen8LODYgvJrIjEfGCZpfHc7coIzs5J0jmQosgY3qvNG/nSaudXu4E5JjxasGxsRa9L5tUDno1i6Gh01obtY3clgZiUr4aUzTQVNz658ICJWSRoD3CXpqcKVERGSun/KQzec4MysJBHQ2lGexl9ErEr/rpP0W5KHdLwgaXxErEmboOvSzYsaHVXITVQzK0nSRK0rauqOpEGSBnfOA/8IPAHMAY5PNzseuCWdnwN8Pu1NPQDYWNCU7ZJrcGZWsjKNZBgL/FYSJLno+oi4Q9IjwGxJJwLPA59Mt78NOApYCjQDJ/R0ACc4MytJ520i272f5FmRe3dR/hJwWBflAZxcyjGc4MysRB6qZWY5VivvZHCCM7OSJL2otTEW1QnOzEpSS48sd4Izs5K5iWpmuVSuXtQdwQnOzErmXlQzy6UI0eYEZ2Z55SaqmeWSr8GZWa45wZlZLvk+ODPLNd8HZ2a5FAFtZXrgZaU5wZlZydxENbNc8jU4M8u1cIIzs7xyJ4OZ5VKEr8GZWW6Jdveimlle+Rqcld2zR1yZdQhV73D2yTqE3PNYVDPLr0iuw9UCJzgzK5l7Uc0sl6KGOhlqI0ozqyoRxU3FkFQv6c+S/iddniTpIUlLJf1KUt+0vF+6vDRdv2tP+3aCM7OSRaioqUhfAxYXLF8AXBQRuwPrgRPT8hOB9Wn5Rel23XKCM7OSJLWz8iQ4SROBjwBXpssCDgV+nW4yCzg2nT8mXSZdf1i6/Tb5GpyZlayE20RGSVpQsHxFRFxRsPxj4CxgcLo8EtgQEW3p8kpgQjo/AVgBEBFtkjam2zdt6+BOcGZWshJuE2mKiOldrZD0T8C6iHhU0ozyRPZWTnBmVpJAdJSnF/Vg4GhJRwH9gSHAxcAwSX3SWtxEYFW6/SqgEVgpqQ8wFHipuwP4GpyZlSyKnLrdR8Q5ETExInYFjgPujojPAvcAH083Ox64JZ2fky6Trr87ovu6pBOcmZWmjJ0M2/AvwBmSlpJcY7sqLb8KGJmWnwGc3dOO3EQ1s9KVeahWRNwL3JvOLwP262KbzcAnStmvE5yZlazmnyYi6Sd0k6cj4qsVicjMqloAHR01nuCABd2sM7PeKoBar8FFxKzCZUkDI6K58iGZWbWrlccl9diLKulASYuAp9LlvSX9tOKRmVn1Ksd9IjtAMbeJ/Bg4nPSGuoj4C3BIBWMys6pW3C0i1dARUVQvakSseNuY1vbKhGNmNaEKamfFKCbBrZB0EBCSGtj60SZm1psERI30ohbTRD0JOJlkJP9qYJ902cx6LRU5ZavHGlxENAGf3QGxmFmtqJEmajG9qLtJulXSi5LWSbpF0m47Ijgzq1I56kW9HpgNjAd2Bm4CbqhkUGZWxTpv9C1mylgxCW5gRPwyItrS6VqSZzeZWS9VzpfOVFJ3Y1FHpLO3SzobuJEkd38KuG0HxGZm1apGelG762R4lCShdX6TLxWsC+CcSgVlZtVNVVA7K0Z3Y1En7chAzKxGVEkHQjGKGskgaS9gKgXX3iLimkoFZWbVrDo6EIrRY4KT9B1gBkmCuw04EngAcIIz661qpAZXTC/qx4HDgLURcQKwN8nbbMyst+oocspYMU3U1yOiQ1KbpCHAOpJXd+XW9BmbOOn7q6mvC26/YQSzLx2bdUiZeXVjPRed2chzT/VHgjMuXM4jdw/hwblDkWDYqFbO/PFyRo5r4+7fDGf2ZWOIgAGDOjj1/BW8e8/NWX+FTOT6HMrDAy8LLJA0DPg5Sc/qq8CDPX1I0tVA54td99qeIHekurrg5PNWcc5xu9G0poGf3LaE+XOHsnxJ77z17/JvT2D6jE3828+fo7VFbHm9jnftsY7jz1oLwO+uHMW1F43jaxesZGzjFn5081IGD2vnkbsHc/FZjVzy+yUZf4MdrzecQ7XSi9pjEzUivhIRGyLiZ8A/AMenTdWe/AI4Yjvj2+H22LeZ1c/1Ze3yfrS11nHvLcM48PCNWYeVidc21fHX+YM44jMvA9DQN9hpaDuDBr/Z9tj8eh2dT9La8/3NDB6WPElryrRmmtY07PCYq0GvOIdqZKhWdzf6TutuXUQ81t2OI+I+SbtuR2yZGDmulRdX931juWlNA1Om9c4nta9d3o+hI9v4z9N3YdmT/Zn896/z5e+vov/ADv77/HH84aYRDBrSzn/8eulWn73jhhG8/0OvZBB19nwOVY/umqj/2c26AA4tRwCSZgIzAfozsBy7tDJpb4elfx3IyT9YxZRpzVz+bxP41aVjOP6stZxwdjLd+JMxzLl6NJ//xto3Prfwf3di7g0jufB3va952lvUShO1uxt9P7QjAoiIK4ArAIZoROY/20trGxi9c8sby6PGt/baptao8a2MHt/6Ru3jA/+0gdmXjnnLNod+dD3/+rnd3khwyxb158dnNvKDa5cxZETvfPBz7s+hoGaGahVzm0iv8vTCgUyY1MLYxi30aehgxjEbmH9n77wrZsSYNkbt3MKKpf0AWHj/YHaZvIVVy95sfj04dyiNu28BYN3KBs794iS+ccnzTHz3lkxirga94hwqwzU4Sf0lPSzpL5KelPS9tHySpIckLZX0K0l90/J+6fLSdP2uPYXpN9u/TUe7uOxbEzjv+mXU1cOdN47g+Wfy0/tVqpN/sIoLTnkXba1i3C4tfP2i5Vx0ZiMr/9aPujoYM6GFr16wEoDrLhrHK+vrufSc5C6i+j7BpXc8k2X4megN51CZmqhbgEMj4tX0dQgPSLodOAO4KCJulPQz4ETg8vTv+ojYXdJxwAUkD//oJs4KPdNE0g0kIyBGAS8A34mIq7r7zBCNiP11WEXiyYO5qxdmHULVO3znfbIOoao9FPPYFC9vV/uyX2NjTDzt9KK2XXbm1x+NiOk9bSdpIMkIqS8DvwfGRUSbpAOB70bE4ZLmpvMPSuoDrAVGRzdJrJihWiJ5ZPluEXGupF3Sgz/c3eci4tM97dvMalSZ6kWS6knur90duAz4G7AhItrSTVaSvA+G9O8KgDT5bQRGAk3b2n8x1+B+ChwIdCasV9JAzKwXUhQ/AaMkLSiYZhbuKyLaI2IfYCKwHzClnLEWcw1u/4iYJunPaUDrOy/6mVkvVXwvalMxTdSI2CDpHpLK1DBJfdJa3ERgVbrZKpJhoivTJupQ0hfSb0sxNbjWtBoZAJJGUxXDaM0sKyXU4La9D2l0OgwUSQNIRkotBu4hecgHwPHALen8nHSZdP3d3V1/g+JqcJcAvwXGSPr3dMf/WsTnzCyvynMNbjwwK61A1QGzI+J/JC0CbpT0A+DPQGfn5FXALyUtBV4GjuvpAMW8F/U6SY+SPDJJwLER4Tfbm/VWRdTOitpNxOPAvl2ULyO5Hvf28s3AJ0o5RjG9qLsAzcCthWURsbyUA5lZjmQ+5qg4xTRRf8+bL5/pD0wCngb2rGBcZlbFVCNX4Ytpov5d4XL6lJGvVCwiM7MyKXmoVkQ8Jmn/SgRjZjUiL01USWcULNYB04DVFYvIzKpbmToZdoRianCDC+bbSK7J3VyZcMysJuQhwaX3pwyOiDN3UDxmVgtqPcF1DpWQdPCODMjMqpvIRy/qwyTX2xZKmgPcBLzWuTIiflPh2MysGuXsGlx/kgGth/Lm/XABOMGZ9VY5SHBj0h7UJ3gzsXWqka9nZhVRIxmguwRXD+zEWxNbpxr5emZWCXlooq6JiHN3WCRmVjtykOBq471gZrZjRT56Uf32FzPrWq3X4CLi5R0ZiJnVjjxcgzMz65oTnJnlUhFvra8WTnBmVhLhJqqZ5ZgTnJnllxOcmeWWE5yZ5VLOniZiZvZWTnBmlld5GKplVeaAs07KOoSqN5T5WYfQK9RKE7Uu6wDMrMZECVM3JDVKukfSIklPSvpaWj5C0l2SlqR/h6flknSJpKWSHk/f0dwtJzgzK10ZEhzJW/q+HhFTgQOAkyVNBc4G5kXEZGBeugxwJDA5nWYCl/d0ACc4MytJ50iGYqbuRMSaiHgsnX8FWAxMAI4BZqWbzQKOTeePAa6JxHxgmKTx3R3D1+DMrGTqKPoi3ChJCwqWr4iIK7ban7QrsC/wEDA2Itakq9YCY9P5CcCKgo+tTMvWsA1OcGZWmtIG2zdFxPTuNpC0E8nL5E+LiE3Sm8/ajYiQ3nmXhpuoZlaycjRRASQ1kCS36wpeRfpCZ9Mz/bsuLV8FNBZ8fGJatk1OcGZWuvL0ogq4ClgcERcWrJoDHJ/OHw/cUlD++bQ39QBgY0FTtktuoppZycp0H9zBwOeAv0pamJZ9EzgfmC3pROB54JPputuAo4ClQDNwQk8HcIIzs9KVIcFFxANs++VWW70TJiICOLmUYzjBmVlpcvJWLTOzrfiJvmaWb1EbGc4JzsxK5hqcmeWT36plZnnmTgYzyy0nODPLp8CdDGaWX+5kMLP8coIzszzyjb5mll8RpTzwMlNOcGZWutrIb05wZlY6N1HNLJ8CcBPVzHKrNvKbE5yZlc5NVDPLLfeimlk++WkiZpZXyY2+tZHhnODMrHR+moiZ5ZVrcDVs+oxNnPT91dTXBbffMILZl47NOqRMfOsT93Lwe59n/asD+OyFyaspJ49v4l8+dj99G9pp7xA/+u0HWbRiDADTdlvNaUf/iT51HWxo7s9XfnZ0luFnKtfnkK/BgaRG4BpgLMnPcUVEXFyp45VLXV1w8nmrOOe43Wha08BPblvC/LlDWb6kf9ah7XC/X/Aefv2nPfn2p+55o+yUjzzEVX94Hw8+vQsHTlnOKUfN5yv/dTQ79d/CNz56P6dddRQvbBjM8EGvZxh5tvJ/DtXOWNS6Cu67Dfh6REwFDgBOljS1gscriz32bWb1c31Zu7wfba113HvLMA48fGPWYWVi4bM7s6n5rf+UETCofwsAO/Vv4cVNgwA4fN+l3PvEJF7YMBiA9a8N2LHBVpFecQ5FFDdlrGIJLiLWRMRj6fwrwGJgQqWOVy4jx7Xy4uq+byw3rWlg1PjWDCOqLj++9SBOOeohbvnmtZz6kQe5/Pb9AGgctYHBA7bw0y/N4RdfvZkjpz2TcaTZyf05lL74uZipJ5KulrRO0hMFZSMk3SVpSfp3eFouSZdIWirpcUnTetp/JWtwb5C0K7Av8NCOOJ5VzscOWMTFtx7IMef9Hy6+9SC+9Yk/AlBfF0yZ0MQZVx/J1648ii98+FEaR23INlirnPLV4H4BHPG2srOBeRExGZiXLgMcCUxOp5nA5T3tvOIJTtJOwM3AaRGxqYv1MyUtkLSglS2VDqdHL61tYPTOLW8sjxrfStOahgwjqi5Hve8Z7nliEgDzHt+NqY3rAFi3cRDzn5nI5tYGNjYP4M/LxjN5/EtZhpqZXnEORZFTT7uJuA94+W3FxwCz0vlZwLEF5ddEYj4wTNL47vZf0QQnqYEkuV0XEb/papuIuCIipkfE9Ab6VTKcojy9cCATJrUwtnELfRo6mHHMBubfOTTrsKpG06aBTNttDQDTd1/Fiqbkt7l/0a7sveta6us66NfQyp67rOO5dcOzDDUzveEcUkdHURMwqrMCk04zi9j92IhYk86vJemohOQS14qC7VbSw2WvSvaiCrgKWBwRF1bqOOXW0S4u+9YEzrt+GXX1cOeNI3j+mbz0fpXm3M/8gWm7rWHYoM3M+ea1/Pyu6fzw5kM4/eg/UV/XQUtbH3548yEAPLduOPOfaeTa02+iI8Sch6ew7IURGX+DbOT+HApKudG3KSKmv+NDRYT0zof2V/I+uIOBzwF/lbQwLftmRNxWwWOWxSN3D+GRu4dkHUbmvn39h7ss/7+X/HOX5df9cR+u++M+FYyoduT5HBJR6Rt9X5A0PiLWpE3QdWn5KqCxYLuJadk2VSzBRcQDJMPWzCxvKpvg5gDHA+enf28pKD9F0o3A/sDGgqZslzySwcxKV6YEJ+kGYAbJtbqVwHdIEttsSScCzwOfTDe/DTgKWAo0Ayf0tH8nODMrTWnX4LrfVcSnt7HqsC62DeDkUvbvBGdmJUt7SKueE5yZlag6hmEVwwnOzEoTOMGZWY7VRgvVCc7MSucHXppZfjnBmVkuRUB7bbRRneDMrHSuwZlZbjnBmVkuBVAj72RwgjOzEgWEr8GZWR4F7mQwsxzzNTgzyy0nODPLJw+2N7O8CsCPSzKz3HINzszyyUO1zCyvAsL3wZlZbnkkg5nllq/BmVkuRbgX1cxyzDU4M8unINrbsw6iKE5wZlYaPy7JzHKtRm4Tqcs6ADOrLQFERxQ19UTSEZKelrRU0tnljtUJzsxKE+kDL4uZuiGpHrgMOBKYCnxa0tRyhuomqpmVrEydDPsBSyNiGYCkG4FjgEXl2DmAooq6eyW9CDyfdRwFRgFNWQdRxfz79KzafqN3RcTo7dmBpDtIvlcx+gObC5aviIgr0v18HDgiIr6YLn8O2D8iTtme+ApVVQ1ue3/4cpO0ICKmZx1HtfLv07M8/kYRcUTWMRTL1+DMLCurgMaC5YlpWdk4wZlZVh4BJkuaJKkvcBwwp5wHqKomahW6IusAqpx/n575N9qGiGiTdAowF6gHro6IJ8t5jKrqZDAzKyc3Uc0st5zgzCy3nOC6UOnhI7VO0tWS1kl6IutYqpGkRkn3SFok6UlJX8s6pt7K1+DeJh0+8gzwD8BKkp6eT0dE2e6urnWSDgFeBa6JiL2yjqfaSBoPjI+IxyQNBh4FjvU5tOO5Bre1N4aPREQL0Dl8xFIRcR/wctZxVKuIWBMRj6XzrwCLgQnZRtU7OcFtbQKwomB5JT457R2StCuwL/BQxqH0Sk5wZhUiaSfgZuC0iNiUdTy9kRPc1io+fMTyT1IDSXK7LiJ+k3U8vZUT3NYqPnzE8k2SgKuAxRFxYdbx9GZOcG8TEW1A5/CRxcDscg8fqXWSbgAeBPaQtFLSiVnHVGUOBj4HHCppYTodlXVQvZFvEzGz3HINzsxyywnOzHLLCc7McssJzsxyywnOzHLLCa6GSGpPbzl4QtJNkgZux75+kb7VCElXdvc+SkkzJB30Do7xnKSt3r60rfK3bfNqicf6rqQzS43R8s0Jrra8HhH7pE/waAFOKlwp6R09gj4ivtjDky5mACUnOLOsOcHVrvuB3dPa1f2S5gCLJNVL+pGkRyQ9LulLkNxdL+nS9Dl3fwDGdO5I0r2SpqfzR0h6TNJfJM1LB4ufBJye1h4/KGm0pJvTYzwi6eD0syMl3Zk+A+1KQD19CUm/k/Ro+pmZb1t3UVo+T9LotOzdku5IP3O/pCll+TUtl/zSmRqU1tSOBO5Ii6YBe0XEs2mS2BgR75fUD/hfSXeSPNFiD2AqMJbk7eFXv22/o4GfA4ek+xoRES9L+hnwakT8v3S764GLIuIBSbuQjPp4L/Ad4IGIOFfSR4BiRjh8IT3GAOARSTdHxEvAIGBBRJwu6dvpvk8heYnLSRGxRNL+wE+BQ9/Bz2i9gBNcbRkgaWE6fz/JeMeDgIcj4tm0/B+Bv++8vgYMBSYDhwA3REQ7sFrS3V3s/wDgvs59RcS2nvn2YWBqMuQSgCHpkzMOAT6Wfvb3ktYX8Z2+Kumj6XxjGutLQAfwq7T8WuA36TEOAm4qOHa/Io5hvZQTXG15PSL2KSxI/9FfKywCTo2IuW/brpxjIeuAAyJicxexFE3SDJJkeWBENEu6F+i/jc0jPe6Gt/8GZtvia3D5Mxf4cvq4HiS9R9Ig4D7gU+k1uvHAh7r47HzgEEmT0s+OSMtfAQYXbHcncGrngqR90tn7gM+kZUcCw3uIdSiwPk1uU0hqkJ3qgM5a6GdImr6bgGclfSI9hiTt3cMxrBdzgsufK0murz2m5KUw/0VSU/8tsCRddw3J00DeIiJeBGaSNAf/wptNxFuBj3Z2MgBfBaannRiLeLM393skCfJJkqbq8h5ivQPoI2kxcD5Jgu30GrBf+h0OBc5Nyz8LnJjG9yR+nLx1w08TMbPccg3OzHLLCc7McssJzsxyywnOzHLLCc7McssJzsxyywnOzHLr/wP9l+UEcftTOgAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAATgAAAEGCAYAAADxD4m3AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8vihELAAAACXBIWXMAAAsTAAALEwEAmpwYAAAejklEQVR4nO3deZQdZZ3/8fenO52V7DtJI0EiMTADxMiqnAjOsDgH0HFB/Sk/xBNRQAGRAZ1xQQdh/A0IgjgIjEE2g6iEEQgYQGAkQMCIkACJAbITGrIATdLb9/dHVcOFdLrvJfem7q3+vM6p01VP1a363nuqv+d56qmnShGBmVke1WUdgJlZpTjBmVluOcGZWW45wZlZbjnBmVlu9ck6gEJ91S/6MyjrMKrWll0HZh1C1ev3XHPWIVS1zbxGS2zR9uzj8A8Nipdebi9q20cf3zI3Io7YnuNtj6pKcP0ZxP46LOswqtYz35medQhV7z1fWJB1CFXtoZi33ft46eV2Hp67S1Hb1o9fMmq7D7gdqirBmVn1C6CDjqzDKIoTnJmVJAhao7gmatac4MysZK7BmVkuBUF7jQzxdIIzs5J14ARnZjkUQHuNJDjf6GtmJesgipp6ImmYpF9LekrSYkkHShoh6S5JS9K/w9NtJekSSUslPS5pWk/7d4Izs5IE0BpR1FSEi4E7ImIKsDewGDgbmBcRk4F56TLAkcDkdJoJXN7Tzp3gzKwkQdBe5NQdSUOBQ4CrACKiJSI2AMcAs9LNZgHHpvPHANdEYj4wTNL47o7hBGdmpQloL3ICRklaUDDNLNjTJOBF4L8l/VnSlZIGAWMjYk26zVpgbDo/AVhR8PmVadk2uZPBzEqSjGQoWlNEbGuMYR9gGnBqRDwk6WLebI4mx4oISe+4R8M1ODMrkWgvcurBSmBlRDyULv+aJOG90Nn0TP+uS9evAhoLPj8xLdsmJzgzK0nSyaCipm73E7EWWCFpj7ToMGARMAc4Pi07HrglnZ8DfD7tTT0A2FjQlO2Sm6hmVpLkPrjteuJSoVOB6yT1BZYBJ5BUvGZLOhF4Hvhkuu1twFHAUqA53bZbTnBmVrKOHmpnxYqIhUBX1+i2em5aJK8APLmU/TvBmVlJylyDqygnODMrSSDaa+TyvROcmZWsXE3USnOCM7OSBKIl6rMOoyhOcGZWkuRGXzdRzSyn3MlgZrkUIdrDNTgzy6kO1+DMLI+STobaSB21EaWZVQ13MphZrrX7PjgzyyOPZDCzXOtwL6qZ5VEy2N4JzsxyKBCtHqpVu6bP2MRJ319NfV1w+w0jmH3p2J4/lENq7aDx/KdQa0BH8Or04bx07ATGXvUsA59+hfYByUn+womT2LLLQAAGPLWJ0TesQO1B+059WHn2lCy/QmbyfA5F4Bt9ASQdQfLew3rgyog4v5LHK4e6uuDk81ZxznG70bSmgZ/ctoT5c4eyfEn/rEPb4aKPWPGNPYj+9dDWQeMPn+a1vxsKwIufnMir00e8Zfu65jbG/HI5q86YTNvIftRvas0i7Mzl/xxSzdzoW7E0LKkeuIzkZa1TgU9Lmlqp45XLHvs2s/q5vqxd3o+21jruvWUYBx6+MeuwsiElyQ1Qe6D27l9uNHj+y7z6vuG0jewHQPuQhoqHWI3yfg4FSQ2umClrlazB7QcsjYhlAJJuJHlx66IKHnO7jRzXyour+76x3LSmgSnTmjOMKGMdwS7fW0TfdVvYcOgYNr97J4be+yKjbl7FyDlraH7vYJo+PpFoqKPv2s2oPZh4wVPUbe5g/YfH8MrBo7L+BjtcbziH3MnQ9Uta96/g8awS6sTy7+1JXXMbO1/6N/qufJ2mf55A+9AG1BaMmfU8w29fy8tH74w6gn7PN7PyG+9BLR3s8u9PsfndO9E6Li9NM4Okk6FWHniZeRqWNLPzrdetbMk6HF5a28DonVveWB41vpWmNb2zqVWoY2AfmqcMZtATG2kf1jdpvjbUsekDI+m/7DUAWof3pXmvIUS/ejoGN/D6ewbTb0W+ai7FyPs5lLw2sE9RU9YqmeCKeklrRFwREdMjYnoD/SoYTnGeXjiQCZNaGNu4hT4NHcw4ZgPz7xyadViZqN/USl1zGwBq6WDgk5toGdef+g3pP28EOz22gZYJAwB4bd9hDFjyKrQH2tJO/2dfpWX8gKzCz0z+z6Gyvfi54iqZYh8BJkuaRJLYjgM+U8HjlUVHu7jsWxM47/pl1NXDnTeO4PlnemcTq35jK+OuehZ1ABG88v4RvLbPMCb+x9PUv9IGBFsaB/LC598FQMvOA3htr6G869tPQh1s/OBoWib2vgSX93Mo8EgGIqJN0inAXJLbRK6OiCcrdbxyeuTuITxy95Csw8hcS+NAln93z63KV561RxdbJ9YfOY71R46rZFg1Ie/nUDXUzopR0UZyRNxG8jZqM8uJCLkGZ2b5lHQy1MZQrdpIw2ZWRVS2G30lPSfpr5IWSlqQlo2QdJekJenf4Wm5JF0iaamkxyVN62n/TnBmVpKkk0FFTUX6UETsExHT0+WzgXkRMRmYly5DMipqcjrNBC7vacdOcGZWsnbqipreoWOAWen8LODYgvJrIjEfGCZpfHc7coIzs5J0jmQosgY3qvNG/nSaudXu4E5JjxasGxsRa9L5tUDno1i6Gh01obtY3clgZiUr4aUzTQVNz658ICJWSRoD3CXpqcKVERGSun/KQzec4MysJBHQ2lGexl9ErEr/rpP0W5KHdLwgaXxErEmboOvSzYsaHVXITVQzK0nSRK0rauqOpEGSBnfOA/8IPAHMAY5PNzseuCWdnwN8Pu1NPQDYWNCU7ZJrcGZWsjKNZBgL/FYSJLno+oi4Q9IjwGxJJwLPA59Mt78NOApYCjQDJ/R0ACc4MytJ520i272f5FmRe3dR/hJwWBflAZxcyjGc4MysRB6qZWY5VivvZHCCM7OSJL2otTEW1QnOzEpSS48sd4Izs5K5iWpmuVSuXtQdwQnOzErmXlQzy6UI0eYEZ2Z55SaqmeWSr8GZWa45wZlZLvk+ODPLNd8HZ2a5FAFtZXrgZaU5wZlZydxENbNc8jU4M8u1cIIzs7xyJ4OZ5VKEr8GZWW6Jdveimlle+Rqcld2zR1yZdQhV73D2yTqE3PNYVDPLr0iuw9UCJzgzK5l7Uc0sl6KGOhlqI0ozqyoRxU3FkFQv6c+S/iddniTpIUlLJf1KUt+0vF+6vDRdv2tP+3aCM7OSRaioqUhfAxYXLF8AXBQRuwPrgRPT8hOB9Wn5Rel23XKCM7OSJLWz8iQ4SROBjwBXpssCDgV+nW4yCzg2nT8mXSZdf1i6/Tb5GpyZlayE20RGSVpQsHxFRFxRsPxj4CxgcLo8EtgQEW3p8kpgQjo/AVgBEBFtkjam2zdt6+BOcGZWshJuE2mKiOldrZD0T8C6iHhU0ozyRPZWTnBmVpJAdJSnF/Vg4GhJRwH9gSHAxcAwSX3SWtxEYFW6/SqgEVgpqQ8wFHipuwP4GpyZlSyKnLrdR8Q5ETExInYFjgPujojPAvcAH083Ox64JZ2fky6Trr87ovu6pBOcmZWmjJ0M2/AvwBmSlpJcY7sqLb8KGJmWnwGc3dOO3EQ1s9KVeahWRNwL3JvOLwP262KbzcAnStmvE5yZlazmnyYi6Sd0k6cj4qsVicjMqloAHR01nuCABd2sM7PeKoBar8FFxKzCZUkDI6K58iGZWbWrlccl9diLKulASYuAp9LlvSX9tOKRmVn1Ksd9IjtAMbeJ/Bg4nPSGuoj4C3BIBWMys6pW3C0i1dARUVQvakSseNuY1vbKhGNmNaEKamfFKCbBrZB0EBCSGtj60SZm1psERI30ohbTRD0JOJlkJP9qYJ902cx6LRU5ZavHGlxENAGf3QGxmFmtqJEmajG9qLtJulXSi5LWSbpF0m47Ijgzq1I56kW9HpgNjAd2Bm4CbqhkUGZWxTpv9C1mylgxCW5gRPwyItrS6VqSZzeZWS9VzpfOVFJ3Y1FHpLO3SzobuJEkd38KuG0HxGZm1apGelG762R4lCShdX6TLxWsC+CcSgVlZtVNVVA7K0Z3Y1En7chAzKxGVEkHQjGKGskgaS9gKgXX3iLimkoFZWbVrDo6EIrRY4KT9B1gBkmCuw04EngAcIIz661qpAZXTC/qx4HDgLURcQKwN8nbbMyst+oocspYMU3U1yOiQ1KbpCHAOpJXd+XW9BmbOOn7q6mvC26/YQSzLx2bdUiZeXVjPRed2chzT/VHgjMuXM4jdw/hwblDkWDYqFbO/PFyRo5r4+7fDGf2ZWOIgAGDOjj1/BW8e8/NWX+FTOT6HMrDAy8LLJA0DPg5Sc/qq8CDPX1I0tVA54td99qeIHekurrg5PNWcc5xu9G0poGf3LaE+XOHsnxJ77z17/JvT2D6jE3828+fo7VFbHm9jnftsY7jz1oLwO+uHMW1F43jaxesZGzjFn5081IGD2vnkbsHc/FZjVzy+yUZf4MdrzecQ7XSi9pjEzUivhIRGyLiZ8A/AMenTdWe/AI4Yjvj2+H22LeZ1c/1Ze3yfrS11nHvLcM48PCNWYeVidc21fHX+YM44jMvA9DQN9hpaDuDBr/Z9tj8eh2dT9La8/3NDB6WPElryrRmmtY07PCYq0GvOIdqZKhWdzf6TutuXUQ81t2OI+I+SbtuR2yZGDmulRdX931juWlNA1Om9c4nta9d3o+hI9v4z9N3YdmT/Zn896/z5e+vov/ADv77/HH84aYRDBrSzn/8eulWn73jhhG8/0OvZBB19nwOVY/umqj/2c26AA4tRwCSZgIzAfozsBy7tDJpb4elfx3IyT9YxZRpzVz+bxP41aVjOP6stZxwdjLd+JMxzLl6NJ//xto3Prfwf3di7g0jufB3va952lvUShO1uxt9P7QjAoiIK4ArAIZoROY/20trGxi9c8sby6PGt/baptao8a2MHt/6Ru3jA/+0gdmXjnnLNod+dD3/+rnd3khwyxb158dnNvKDa5cxZETvfPBz7s+hoGaGahVzm0iv8vTCgUyY1MLYxi30aehgxjEbmH9n77wrZsSYNkbt3MKKpf0AWHj/YHaZvIVVy95sfj04dyiNu28BYN3KBs794iS+ccnzTHz3lkxirga94hwqwzU4Sf0lPSzpL5KelPS9tHySpIckLZX0K0l90/J+6fLSdP2uPYXpN9u/TUe7uOxbEzjv+mXU1cOdN47g+Wfy0/tVqpN/sIoLTnkXba1i3C4tfP2i5Vx0ZiMr/9aPujoYM6GFr16wEoDrLhrHK+vrufSc5C6i+j7BpXc8k2X4megN51CZmqhbgEMj4tX0dQgPSLodOAO4KCJulPQz4ETg8vTv+ojYXdJxwAUkD//oJs4KPdNE0g0kIyBGAS8A34mIq7r7zBCNiP11WEXiyYO5qxdmHULVO3znfbIOoao9FPPYFC9vV/uyX2NjTDzt9KK2XXbm1x+NiOk9bSdpIMkIqS8DvwfGRUSbpAOB70bE4ZLmpvMPSuoDrAVGRzdJrJihWiJ5ZPluEXGupF3Sgz/c3eci4tM97dvMalSZ6kWS6knur90duAz4G7AhItrSTVaSvA+G9O8KgDT5bQRGAk3b2n8x1+B+ChwIdCasV9JAzKwXUhQ/AaMkLSiYZhbuKyLaI2IfYCKwHzClnLEWcw1u/4iYJunPaUDrOy/6mVkvVXwvalMxTdSI2CDpHpLK1DBJfdJa3ERgVbrZKpJhoivTJupQ0hfSb0sxNbjWtBoZAJJGUxXDaM0sKyXU4La9D2l0OgwUSQNIRkotBu4hecgHwPHALen8nHSZdP3d3V1/g+JqcJcAvwXGSPr3dMf/WsTnzCyvynMNbjwwK61A1QGzI+J/JC0CbpT0A+DPQGfn5FXALyUtBV4GjuvpAMW8F/U6SY+SPDJJwLER4Tfbm/VWRdTOitpNxOPAvl2ULyO5Hvf28s3AJ0o5RjG9qLsAzcCthWURsbyUA5lZjmQ+5qg4xTRRf8+bL5/pD0wCngb2rGBcZlbFVCNX4Ytpov5d4XL6lJGvVCwiM7MyKXmoVkQ8Jmn/SgRjZjUiL01USWcULNYB04DVFYvIzKpbmToZdoRianCDC+bbSK7J3VyZcMysJuQhwaX3pwyOiDN3UDxmVgtqPcF1DpWQdPCODMjMqpvIRy/qwyTX2xZKmgPcBLzWuTIiflPh2MysGuXsGlx/kgGth/Lm/XABOMGZ9VY5SHBj0h7UJ3gzsXWqka9nZhVRIxmguwRXD+zEWxNbpxr5emZWCXlooq6JiHN3WCRmVjtykOBq471gZrZjRT56Uf32FzPrWq3X4CLi5R0ZiJnVjjxcgzMz65oTnJnlUhFvra8WTnBmVhLhJqqZ5ZgTnJnllxOcmeWWE5yZ5VLOniZiZvZWTnBmlld5GKplVeaAs07KOoSqN5T5WYfQK9RKE7Uu6wDMrMZECVM3JDVKukfSIklPSvpaWj5C0l2SlqR/h6flknSJpKWSHk/f0dwtJzgzK10ZEhzJW/q+HhFTgQOAkyVNBc4G5kXEZGBeugxwJDA5nWYCl/d0ACc4MytJ50iGYqbuRMSaiHgsnX8FWAxMAI4BZqWbzQKOTeePAa6JxHxgmKTx3R3D1+DMrGTqKPoi3ChJCwqWr4iIK7ban7QrsC/wEDA2Itakq9YCY9P5CcCKgo+tTMvWsA1OcGZWmtIG2zdFxPTuNpC0E8nL5E+LiE3Sm8/ajYiQ3nmXhpuoZlaycjRRASQ1kCS36wpeRfpCZ9Mz/bsuLV8FNBZ8fGJatk1OcGZWuvL0ogq4ClgcERcWrJoDHJ/OHw/cUlD++bQ39QBgY0FTtktuoppZycp0H9zBwOeAv0pamJZ9EzgfmC3pROB54JPputuAo4ClQDNwQk8HcIIzs9KVIcFFxANs++VWW70TJiICOLmUYzjBmVlpcvJWLTOzrfiJvmaWb1EbGc4JzsxK5hqcmeWT36plZnnmTgYzyy0nODPLp8CdDGaWX+5kMLP8coIzszzyjb5mll8RpTzwMlNOcGZWutrIb05wZlY6N1HNLJ8CcBPVzHKrNvKbE5yZlc5NVDPLLfeimlk++WkiZpZXyY2+tZHhnODMrHR+moiZ5ZVrcDVs+oxNnPT91dTXBbffMILZl47NOqRMfOsT93Lwe59n/asD+OyFyaspJ49v4l8+dj99G9pp7xA/+u0HWbRiDADTdlvNaUf/iT51HWxo7s9XfnZ0luFnKtfnkK/BgaRG4BpgLMnPcUVEXFyp45VLXV1w8nmrOOe43Wha08BPblvC/LlDWb6kf9ah7XC/X/Aefv2nPfn2p+55o+yUjzzEVX94Hw8+vQsHTlnOKUfN5yv/dTQ79d/CNz56P6dddRQvbBjM8EGvZxh5tvJ/DtXOWNS6Cu67Dfh6REwFDgBOljS1gscriz32bWb1c31Zu7wfba113HvLMA48fGPWYWVi4bM7s6n5rf+UETCofwsAO/Vv4cVNgwA4fN+l3PvEJF7YMBiA9a8N2LHBVpFecQ5FFDdlrGIJLiLWRMRj6fwrwGJgQqWOVy4jx7Xy4uq+byw3rWlg1PjWDCOqLj++9SBOOeohbvnmtZz6kQe5/Pb9AGgctYHBA7bw0y/N4RdfvZkjpz2TcaTZyf05lL74uZipJ5KulrRO0hMFZSMk3SVpSfp3eFouSZdIWirpcUnTetp/JWtwb5C0K7Av8NCOOJ5VzscOWMTFtx7IMef9Hy6+9SC+9Yk/AlBfF0yZ0MQZVx/J1648ii98+FEaR23INlirnPLV4H4BHPG2srOBeRExGZiXLgMcCUxOp5nA5T3tvOIJTtJOwM3AaRGxqYv1MyUtkLSglS2VDqdHL61tYPTOLW8sjxrfStOahgwjqi5Hve8Z7nliEgDzHt+NqY3rAFi3cRDzn5nI5tYGNjYP4M/LxjN5/EtZhpqZXnEORZFTT7uJuA94+W3FxwCz0vlZwLEF5ddEYj4wTNL47vZf0QQnqYEkuV0XEb/papuIuCIipkfE9Ab6VTKcojy9cCATJrUwtnELfRo6mHHMBubfOTTrsKpG06aBTNttDQDTd1/Fiqbkt7l/0a7sveta6us66NfQyp67rOO5dcOzDDUzveEcUkdHURMwqrMCk04zi9j92IhYk86vJemohOQS14qC7VbSw2WvSvaiCrgKWBwRF1bqOOXW0S4u+9YEzrt+GXX1cOeNI3j+mbz0fpXm3M/8gWm7rWHYoM3M+ea1/Pyu6fzw5kM4/eg/UV/XQUtbH3548yEAPLduOPOfaeTa02+iI8Sch6ew7IURGX+DbOT+HApKudG3KSKmv+NDRYT0zof2V/I+uIOBzwF/lbQwLftmRNxWwWOWxSN3D+GRu4dkHUbmvn39h7ss/7+X/HOX5df9cR+u++M+FYyoduT5HBJR6Rt9X5A0PiLWpE3QdWn5KqCxYLuJadk2VSzBRcQDJMPWzCxvKpvg5gDHA+enf28pKD9F0o3A/sDGgqZslzySwcxKV6YEJ+kGYAbJtbqVwHdIEttsSScCzwOfTDe/DTgKWAo0Ayf0tH8nODMrTWnX4LrfVcSnt7HqsC62DeDkUvbvBGdmJUt7SKueE5yZlag6hmEVwwnOzEoTOMGZWY7VRgvVCc7MSucHXppZfjnBmVkuRUB7bbRRneDMrHSuwZlZbjnBmVkuBVAj72RwgjOzEgWEr8GZWR4F7mQwsxzzNTgzyy0nODPLJw+2N7O8CsCPSzKz3HINzszyyUO1zCyvAsL3wZlZbnkkg5nllq/BmVkuRbgX1cxyzDU4M8unINrbsw6iKE5wZlYaPy7JzHKtRm4Tqcs6ADOrLQFERxQ19UTSEZKelrRU0tnljtUJzsxKE+kDL4uZuiGpHrgMOBKYCnxa0tRyhuomqpmVrEydDPsBSyNiGYCkG4FjgEXl2DmAooq6eyW9CDyfdRwFRgFNWQdRxfz79KzafqN3RcTo7dmBpDtIvlcx+gObC5aviIgr0v18HDgiIr6YLn8O2D8iTtme+ApVVQ1ue3/4cpO0ICKmZx1HtfLv07M8/kYRcUTWMRTL1+DMLCurgMaC5YlpWdk4wZlZVh4BJkuaJKkvcBwwp5wHqKomahW6IusAqpx/n575N9qGiGiTdAowF6gHro6IJ8t5jKrqZDAzKyc3Uc0st5zgzCy3nOC6UOnhI7VO0tWS1kl6IutYqpGkRkn3SFok6UlJX8s6pt7K1+DeJh0+8gzwD8BKkp6eT0dE2e6urnWSDgFeBa6JiL2yjqfaSBoPjI+IxyQNBh4FjvU5tOO5Bre1N4aPREQL0Dl8xFIRcR/wctZxVKuIWBMRj6XzrwCLgQnZRtU7OcFtbQKwomB5JT457R2StCuwL/BQxqH0Sk5wZhUiaSfgZuC0iNiUdTy9kRPc1io+fMTyT1IDSXK7LiJ+k3U8vZUT3NYqPnzE8k2SgKuAxRFxYdbx9GZOcG8TEW1A5/CRxcDscg8fqXWSbgAeBPaQtFLSiVnHVGUOBj4HHCppYTodlXVQvZFvEzGz3HINzsxyywnOzHLLCc7McssJzsxyywnOzHLLCa6GSGpPbzl4QtJNkgZux75+kb7VCElXdvc+SkkzJB30Do7xnKSt3r60rfK3bfNqicf6rqQzS43R8s0Jrra8HhH7pE/waAFOKlwp6R09gj4ivtjDky5mACUnOLOsOcHVrvuB3dPa1f2S5gCLJNVL+pGkRyQ9LulLkNxdL+nS9Dl3fwDGdO5I0r2SpqfzR0h6TNJfJM1LB4ufBJye1h4/KGm0pJvTYzwi6eD0syMl3Zk+A+1KQD19CUm/k/Ro+pmZb1t3UVo+T9LotOzdku5IP3O/pCll+TUtl/zSmRqU1tSOBO5Ii6YBe0XEs2mS2BgR75fUD/hfSXeSPNFiD2AqMJbk7eFXv22/o4GfA4ek+xoRES9L+hnwakT8v3S764GLIuIBSbuQjPp4L/Ad4IGIOFfSR4BiRjh8IT3GAOARSTdHxEvAIGBBRJwu6dvpvk8heYnLSRGxRNL+wE+BQ9/Bz2i9gBNcbRkgaWE6fz/JeMeDgIcj4tm0/B+Bv++8vgYMBSYDhwA3REQ7sFrS3V3s/wDgvs59RcS2nvn2YWBqMuQSgCHpkzMOAT6Wfvb3ktYX8Z2+Kumj6XxjGutLQAfwq7T8WuA36TEOAm4qOHa/Io5hvZQTXG15PSL2KSxI/9FfKywCTo2IuW/brpxjIeuAAyJicxexFE3SDJJkeWBENEu6F+i/jc0jPe6Gt/8GZtvia3D5Mxf4cvq4HiS9R9Ig4D7gU+k1uvHAh7r47HzgEEmT0s+OSMtfAQYXbHcncGrngqR90tn7gM+kZUcCw3uIdSiwPk1uU0hqkJ3qgM5a6GdImr6bgGclfSI9hiTt3cMxrBdzgsufK0murz2m5KUw/0VSU/8tsCRddw3J00DeIiJeBGaSNAf/wptNxFuBj3Z2MgBfBaannRiLeLM393skCfJJkqbq8h5ivQPoI2kxcD5Jgu30GrBf+h0OBc5Nyz8LnJjG9yR+nLx1w08TMbPccg3OzHLLCc7McssJzsxyywnOzHLLCc7McssJzsxyywnOzHLr/wP9l+UEcftTOgAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAATgAAAEGCAYAAADxD4m3AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8vihELAAAACXBIWXMAAAsTAAALEwEAmpwYAAAejklEQVR4nO3deZQdZZ3/8fenO52V7DtJI0EiMTADxMiqnAjOsDgH0HFB/Sk/xBNRQAGRAZ1xQQdh/A0IgjgIjEE2g6iEEQgYQGAkQMCIkACJAbITGrIATdLb9/dHVcOFdLrvJfem7q3+vM6p01VP1a363nuqv+d56qmnShGBmVke1WUdgJlZpTjBmVluOcGZWW45wZlZbjnBmVlu9ck6gEJ91S/6MyjrMKrWll0HZh1C1ev3XHPWIVS1zbxGS2zR9uzj8A8Nipdebi9q20cf3zI3Io7YnuNtj6pKcP0ZxP46LOswqtYz35medQhV7z1fWJB1CFXtoZi33ft46eV2Hp67S1Hb1o9fMmq7D7gdqirBmVn1C6CDjqzDKIoTnJmVJAhao7gmatac4MysZK7BmVkuBUF7jQzxdIIzs5J14ARnZjkUQHuNJDjf6GtmJesgipp6ImmYpF9LekrSYkkHShoh6S5JS9K/w9NtJekSSUslPS5pWk/7d4Izs5IE0BpR1FSEi4E7ImIKsDewGDgbmBcRk4F56TLAkcDkdJoJXN7Tzp3gzKwkQdBe5NQdSUOBQ4CrACKiJSI2AMcAs9LNZgHHpvPHANdEYj4wTNL47o7hBGdmpQloL3ICRklaUDDNLNjTJOBF4L8l/VnSlZIGAWMjYk26zVpgbDo/AVhR8PmVadk2uZPBzEqSjGQoWlNEbGuMYR9gGnBqRDwk6WLebI4mx4oISe+4R8M1ODMrkWgvcurBSmBlRDyULv+aJOG90Nn0TP+uS9evAhoLPj8xLdsmJzgzK0nSyaCipm73E7EWWCFpj7ToMGARMAc4Pi07HrglnZ8DfD7tTT0A2FjQlO2Sm6hmVpLkPrjteuJSoVOB6yT1BZYBJ5BUvGZLOhF4Hvhkuu1twFHAUqA53bZbTnBmVrKOHmpnxYqIhUBX1+i2em5aJK8APLmU/TvBmVlJylyDqygnODMrSSDaa+TyvROcmZWsXE3USnOCM7OSBKIl6rMOoyhOcGZWkuRGXzdRzSyn3MlgZrkUIdrDNTgzy6kO1+DMLI+STobaSB21EaWZVQ13MphZrrX7PjgzyyOPZDCzXOtwL6qZ5VEy2N4JzsxyKBCtHqpVu6bP2MRJ319NfV1w+w0jmH3p2J4/lENq7aDx/KdQa0BH8Or04bx07ATGXvUsA59+hfYByUn+womT2LLLQAAGPLWJ0TesQO1B+059WHn2lCy/QmbyfA5F4Bt9ASQdQfLew3rgyog4v5LHK4e6uuDk81ZxznG70bSmgZ/ctoT5c4eyfEn/rEPb4aKPWPGNPYj+9dDWQeMPn+a1vxsKwIufnMir00e8Zfu65jbG/HI5q86YTNvIftRvas0i7Mzl/xxSzdzoW7E0LKkeuIzkZa1TgU9Lmlqp45XLHvs2s/q5vqxd3o+21jruvWUYBx6+MeuwsiElyQ1Qe6D27l9uNHj+y7z6vuG0jewHQPuQhoqHWI3yfg4FSQ2umClrlazB7QcsjYhlAJJuJHlx66IKHnO7jRzXyour+76x3LSmgSnTmjOMKGMdwS7fW0TfdVvYcOgYNr97J4be+yKjbl7FyDlraH7vYJo+PpFoqKPv2s2oPZh4wVPUbe5g/YfH8MrBo7L+BjtcbziH3MnQ9Uta96/g8awS6sTy7+1JXXMbO1/6N/qufJ2mf55A+9AG1BaMmfU8w29fy8tH74w6gn7PN7PyG+9BLR3s8u9PsfndO9E6Li9NM4Okk6FWHniZeRqWNLPzrdetbMk6HF5a28DonVveWB41vpWmNb2zqVWoY2AfmqcMZtATG2kf1jdpvjbUsekDI+m/7DUAWof3pXmvIUS/ejoGN/D6ewbTb0W+ai7FyPs5lLw2sE9RU9YqmeCKeklrRFwREdMjYnoD/SoYTnGeXjiQCZNaGNu4hT4NHcw4ZgPz7xyadViZqN/USl1zGwBq6WDgk5toGdef+g3pP28EOz22gZYJAwB4bd9hDFjyKrQH2tJO/2dfpWX8gKzCz0z+z6Gyvfi54iqZYh8BJkuaRJLYjgM+U8HjlUVHu7jsWxM47/pl1NXDnTeO4PlnemcTq35jK+OuehZ1ABG88v4RvLbPMCb+x9PUv9IGBFsaB/LC598FQMvOA3htr6G869tPQh1s/OBoWib2vgSX93Mo8EgGIqJN0inAXJLbRK6OiCcrdbxyeuTuITxy95Csw8hcS+NAln93z63KV561RxdbJ9YfOY71R46rZFg1Ie/nUDXUzopR0UZyRNxG8jZqM8uJCLkGZ2b5lHQy1MZQrdpIw2ZWRVS2G30lPSfpr5IWSlqQlo2QdJekJenf4Wm5JF0iaamkxyVN62n/TnBmVpKkk0FFTUX6UETsExHT0+WzgXkRMRmYly5DMipqcjrNBC7vacdOcGZWsnbqipreoWOAWen8LODYgvJrIjEfGCZpfHc7coIzs5J0jmQosgY3qvNG/nSaudXu4E5JjxasGxsRa9L5tUDno1i6Gh01obtY3clgZiUr4aUzTQVNz658ICJWSRoD3CXpqcKVERGSun/KQzec4MysJBHQ2lGexl9ErEr/rpP0W5KHdLwgaXxErEmboOvSzYsaHVXITVQzK0nSRK0rauqOpEGSBnfOA/8IPAHMAY5PNzseuCWdnwN8Pu1NPQDYWNCU7ZJrcGZWsjKNZBgL/FYSJLno+oi4Q9IjwGxJJwLPA59Mt78NOApYCjQDJ/R0ACc4MytJ520i272f5FmRe3dR/hJwWBflAZxcyjGc4MysRB6qZWY5VivvZHCCM7OSJL2otTEW1QnOzEpSS48sd4Izs5K5iWpmuVSuXtQdwQnOzErmXlQzy6UI0eYEZ2Z55SaqmeWSr8GZWa45wZlZLvk+ODPLNd8HZ2a5FAFtZXrgZaU5wZlZydxENbNc8jU4M8u1cIIzs7xyJ4OZ5VKEr8GZWW6Jdveimlle+Rqcld2zR1yZdQhV73D2yTqE3PNYVDPLr0iuw9UCJzgzK5l7Uc0sl6KGOhlqI0ozqyoRxU3FkFQv6c+S/iddniTpIUlLJf1KUt+0vF+6vDRdv2tP+3aCM7OSRaioqUhfAxYXLF8AXBQRuwPrgRPT8hOB9Wn5Rel23XKCM7OSJLWz8iQ4SROBjwBXpssCDgV+nW4yCzg2nT8mXSZdf1i6/Tb5GpyZlayE20RGSVpQsHxFRFxRsPxj4CxgcLo8EtgQEW3p8kpgQjo/AVgBEBFtkjam2zdt6+BOcGZWshJuE2mKiOldrZD0T8C6iHhU0ozyRPZWTnBmVpJAdJSnF/Vg4GhJRwH9gSHAxcAwSX3SWtxEYFW6/SqgEVgpqQ8wFHipuwP4GpyZlSyKnLrdR8Q5ETExInYFjgPujojPAvcAH083Ox64JZ2fky6Trr87ovu6pBOcmZWmjJ0M2/AvwBmSlpJcY7sqLb8KGJmWnwGc3dOO3EQ1s9KVeahWRNwL3JvOLwP262KbzcAnStmvE5yZlazmnyYi6Sd0k6cj4qsVicjMqloAHR01nuCABd2sM7PeKoBar8FFxKzCZUkDI6K58iGZWbWrlccl9diLKulASYuAp9LlvSX9tOKRmVn1Ksd9IjtAMbeJ/Bg4nPSGuoj4C3BIBWMys6pW3C0i1dARUVQvakSseNuY1vbKhGNmNaEKamfFKCbBrZB0EBCSGtj60SZm1psERI30ohbTRD0JOJlkJP9qYJ902cx6LRU5ZavHGlxENAGf3QGxmFmtqJEmajG9qLtJulXSi5LWSbpF0m47Ijgzq1I56kW9HpgNjAd2Bm4CbqhkUGZWxTpv9C1mylgxCW5gRPwyItrS6VqSZzeZWS9VzpfOVFJ3Y1FHpLO3SzobuJEkd38KuG0HxGZm1apGelG762R4lCShdX6TLxWsC+CcSgVlZtVNVVA7K0Z3Y1En7chAzKxGVEkHQjGKGskgaS9gKgXX3iLimkoFZWbVrDo6EIrRY4KT9B1gBkmCuw04EngAcIIz661qpAZXTC/qx4HDgLURcQKwN8nbbMyst+oocspYMU3U1yOiQ1KbpCHAOpJXd+XW9BmbOOn7q6mvC26/YQSzLx2bdUiZeXVjPRed2chzT/VHgjMuXM4jdw/hwblDkWDYqFbO/PFyRo5r4+7fDGf2ZWOIgAGDOjj1/BW8e8/NWX+FTOT6HMrDAy8LLJA0DPg5Sc/qq8CDPX1I0tVA54td99qeIHekurrg5PNWcc5xu9G0poGf3LaE+XOHsnxJ77z17/JvT2D6jE3828+fo7VFbHm9jnftsY7jz1oLwO+uHMW1F43jaxesZGzjFn5081IGD2vnkbsHc/FZjVzy+yUZf4MdrzecQ7XSi9pjEzUivhIRGyLiZ8A/AMenTdWe/AI4Yjvj2+H22LeZ1c/1Ze3yfrS11nHvLcM48PCNWYeVidc21fHX+YM44jMvA9DQN9hpaDuDBr/Z9tj8eh2dT9La8/3NDB6WPElryrRmmtY07PCYq0GvOIdqZKhWdzf6TutuXUQ81t2OI+I+SbtuR2yZGDmulRdX931juWlNA1Om9c4nta9d3o+hI9v4z9N3YdmT/Zn896/z5e+vov/ADv77/HH84aYRDBrSzn/8eulWn73jhhG8/0OvZBB19nwOVY/umqj/2c26AA4tRwCSZgIzAfozsBy7tDJpb4elfx3IyT9YxZRpzVz+bxP41aVjOP6stZxwdjLd+JMxzLl6NJ//xto3Prfwf3di7g0jufB3va952lvUShO1uxt9P7QjAoiIK4ArAIZoROY/20trGxi9c8sby6PGt/baptao8a2MHt/6Ru3jA/+0gdmXjnnLNod+dD3/+rnd3khwyxb158dnNvKDa5cxZETvfPBz7s+hoGaGahVzm0iv8vTCgUyY1MLYxi30aehgxjEbmH9n77wrZsSYNkbt3MKKpf0AWHj/YHaZvIVVy95sfj04dyiNu28BYN3KBs794iS+ccnzTHz3lkxirga94hwqwzU4Sf0lPSzpL5KelPS9tHySpIckLZX0K0l90/J+6fLSdP2uPYXpN9u/TUe7uOxbEzjv+mXU1cOdN47g+Wfy0/tVqpN/sIoLTnkXba1i3C4tfP2i5Vx0ZiMr/9aPujoYM6GFr16wEoDrLhrHK+vrufSc5C6i+j7BpXc8k2X4megN51CZmqhbgEMj4tX0dQgPSLodOAO4KCJulPQz4ETg8vTv+ojYXdJxwAUkD//oJs4KPdNE0g0kIyBGAS8A34mIq7r7zBCNiP11WEXiyYO5qxdmHULVO3znfbIOoao9FPPYFC9vV/uyX2NjTDzt9KK2XXbm1x+NiOk9bSdpIMkIqS8DvwfGRUSbpAOB70bE4ZLmpvMPSuoDrAVGRzdJrJihWiJ5ZPluEXGupF3Sgz/c3eci4tM97dvMalSZ6kWS6knur90duAz4G7AhItrSTVaSvA+G9O8KgDT5bQRGAk3b2n8x1+B+ChwIdCasV9JAzKwXUhQ/AaMkLSiYZhbuKyLaI2IfYCKwHzClnLEWcw1u/4iYJunPaUDrOy/6mVkvVXwvalMxTdSI2CDpHpLK1DBJfdJa3ERgVbrZKpJhoivTJupQ0hfSb0sxNbjWtBoZAJJGUxXDaM0sKyXU4La9D2l0OgwUSQNIRkotBu4hecgHwPHALen8nHSZdP3d3V1/g+JqcJcAvwXGSPr3dMf/WsTnzCyvynMNbjwwK61A1QGzI+J/JC0CbpT0A+DPQGfn5FXALyUtBV4GjuvpAMW8F/U6SY+SPDJJwLER4Tfbm/VWRdTOitpNxOPAvl2ULyO5Hvf28s3AJ0o5RjG9qLsAzcCthWURsbyUA5lZjmQ+5qg4xTRRf8+bL5/pD0wCngb2rGBcZlbFVCNX4Ytpov5d4XL6lJGvVCwiM7MyKXmoVkQ8Jmn/SgRjZjUiL01USWcULNYB04DVFYvIzKpbmToZdoRianCDC+bbSK7J3VyZcMysJuQhwaX3pwyOiDN3UDxmVgtqPcF1DpWQdPCODMjMqpvIRy/qwyTX2xZKmgPcBLzWuTIiflPh2MysGuXsGlx/kgGth/Lm/XABOMGZ9VY5SHBj0h7UJ3gzsXWqka9nZhVRIxmguwRXD+zEWxNbpxr5emZWCXlooq6JiHN3WCRmVjtykOBq471gZrZjRT56Uf32FzPrWq3X4CLi5R0ZiJnVjjxcgzMz65oTnJnlUhFvra8WTnBmVhLhJqqZ5ZgTnJnllxOcmeWWE5yZ5VLOniZiZvZWTnBmlld5GKplVeaAs07KOoSqN5T5WYfQK9RKE7Uu6wDMrMZECVM3JDVKukfSIklPSvpaWj5C0l2SlqR/h6flknSJpKWSHk/f0dwtJzgzK10ZEhzJW/q+HhFTgQOAkyVNBc4G5kXEZGBeugxwJDA5nWYCl/d0ACc4MytJ50iGYqbuRMSaiHgsnX8FWAxMAI4BZqWbzQKOTeePAa6JxHxgmKTx3R3D1+DMrGTqKPoi3ChJCwqWr4iIK7ban7QrsC/wEDA2Itakq9YCY9P5CcCKgo+tTMvWsA1OcGZWmtIG2zdFxPTuNpC0E8nL5E+LiE3Sm8/ajYiQ3nmXhpuoZlaycjRRASQ1kCS36wpeRfpCZ9Mz/bsuLV8FNBZ8fGJatk1OcGZWuvL0ogq4ClgcERcWrJoDHJ/OHw/cUlD++bQ39QBgY0FTtktuoppZycp0H9zBwOeAv0pamJZ9EzgfmC3pROB54JPputuAo4ClQDNwQk8HcIIzs9KVIcFFxANs++VWW70TJiICOLmUYzjBmVlpcvJWLTOzrfiJvmaWb1EbGc4JzsxK5hqcmeWT36plZnnmTgYzyy0nODPLp8CdDGaWX+5kMLP8coIzszzyjb5mll8RpTzwMlNOcGZWutrIb05wZlY6N1HNLJ8CcBPVzHKrNvKbE5yZlc5NVDPLLfeimlk++WkiZpZXyY2+tZHhnODMrHR+moiZ5ZVrcDVs+oxNnPT91dTXBbffMILZl47NOqRMfOsT93Lwe59n/asD+OyFyaspJ49v4l8+dj99G9pp7xA/+u0HWbRiDADTdlvNaUf/iT51HWxo7s9XfnZ0luFnKtfnkK/BgaRG4BpgLMnPcUVEXFyp45VLXV1w8nmrOOe43Wha08BPblvC/LlDWb6kf9ah7XC/X/Aefv2nPfn2p+55o+yUjzzEVX94Hw8+vQsHTlnOKUfN5yv/dTQ79d/CNz56P6dddRQvbBjM8EGvZxh5tvJ/DtXOWNS6Cu67Dfh6REwFDgBOljS1gscriz32bWb1c31Zu7wfba113HvLMA48fGPWYWVi4bM7s6n5rf+UETCofwsAO/Vv4cVNgwA4fN+l3PvEJF7YMBiA9a8N2LHBVpFecQ5FFDdlrGIJLiLWRMRj6fwrwGJgQqWOVy4jx7Xy4uq+byw3rWlg1PjWDCOqLj++9SBOOeohbvnmtZz6kQe5/Pb9AGgctYHBA7bw0y/N4RdfvZkjpz2TcaTZyf05lL74uZipJ5KulrRO0hMFZSMk3SVpSfp3eFouSZdIWirpcUnTetp/JWtwb5C0K7Av8NCOOJ5VzscOWMTFtx7IMef9Hy6+9SC+9Yk/AlBfF0yZ0MQZVx/J1648ii98+FEaR23INlirnPLV4H4BHPG2srOBeRExGZiXLgMcCUxOp5nA5T3tvOIJTtJOwM3AaRGxqYv1MyUtkLSglS2VDqdHL61tYPTOLW8sjxrfStOahgwjqi5Hve8Z7nliEgDzHt+NqY3rAFi3cRDzn5nI5tYGNjYP4M/LxjN5/EtZhpqZXnEORZFTT7uJuA94+W3FxwCz0vlZwLEF5ddEYj4wTNL47vZf0QQnqYEkuV0XEb/papuIuCIipkfE9Ab6VTKcojy9cCATJrUwtnELfRo6mHHMBubfOTTrsKpG06aBTNttDQDTd1/Fiqbkt7l/0a7sveta6us66NfQyp67rOO5dcOzDDUzveEcUkdHURMwqrMCk04zi9j92IhYk86vJemohOQS14qC7VbSw2WvSvaiCrgKWBwRF1bqOOXW0S4u+9YEzrt+GXX1cOeNI3j+mbz0fpXm3M/8gWm7rWHYoM3M+ea1/Pyu6fzw5kM4/eg/UV/XQUtbH3548yEAPLduOPOfaeTa02+iI8Sch6ew7IURGX+DbOT+HApKudG3KSKmv+NDRYT0zof2V/I+uIOBzwF/lbQwLftmRNxWwWOWxSN3D+GRu4dkHUbmvn39h7ss/7+X/HOX5df9cR+u++M+FYyoduT5HBJR6Rt9X5A0PiLWpE3QdWn5KqCxYLuJadk2VSzBRcQDJMPWzCxvKpvg5gDHA+enf28pKD9F0o3A/sDGgqZslzySwcxKV6YEJ+kGYAbJtbqVwHdIEttsSScCzwOfTDe/DTgKWAo0Ayf0tH8nODMrTWnX4LrfVcSnt7HqsC62DeDkUvbvBGdmJUt7SKueE5yZlag6hmEVwwnOzEoTOMGZWY7VRgvVCc7MSucHXppZfjnBmVkuRUB7bbRRneDMrHSuwZlZbjnBmVkuBVAj72RwgjOzEgWEr8GZWR4F7mQwsxzzNTgzyy0nODPLJw+2N7O8CsCPSzKz3HINzszyyUO1zCyvAsL3wZlZbnkkg5nllq/BmVkuRbgX1cxyzDU4M8unINrbsw6iKE5wZlYaPy7JzHKtRm4Tqcs6ADOrLQFERxQ19UTSEZKelrRU0tnljtUJzsxKE+kDL4uZuiGpHrgMOBKYCnxa0tRyhuomqpmVrEydDPsBSyNiGYCkG4FjgEXl2DmAooq6eyW9CDyfdRwFRgFNWQdRxfz79KzafqN3RcTo7dmBpDtIvlcx+gObC5aviIgr0v18HDgiIr6YLn8O2D8iTtme+ApVVQ1ue3/4cpO0ICKmZx1HtfLv07M8/kYRcUTWMRTL1+DMLCurgMaC5YlpWdk4wZlZVh4BJkuaJKkvcBwwp5wHqKomahW6IusAqpx/n575N9qGiGiTdAowF6gHro6IJ8t5jKrqZDAzKyc3Uc0st5zgzCy3nOC6UOnhI7VO0tWS1kl6IutYqpGkRkn3SFok6UlJX8s6pt7K1+DeJh0+8gzwD8BKkp6eT0dE2e6urnWSDgFeBa6JiL2yjqfaSBoPjI+IxyQNBh4FjvU5tOO5Bre1N4aPREQL0Dl8xFIRcR/wctZxVKuIWBMRj6XzrwCLgQnZRtU7OcFtbQKwomB5JT457R2StCuwL/BQxqH0Sk5wZhUiaSfgZuC0iNiUdTy9kRPc1io+fMTyT1IDSXK7LiJ+k3U8vZUT3NYqPnzE8k2SgKuAxRFxYdbx9GZOcG8TEW1A5/CRxcDscg8fqXWSbgAeBPaQtFLSiVnHVGUOBj4HHCppYTodlXVQvZFvEzGz3HINzsxyywnOzHLLCc7McssJzsxyywnOzHLLCa6GSGpPbzl4QtJNkgZux75+kb7VCElXdvc+SkkzJB30Do7xnKSt3r60rfK3bfNqicf6rqQzS43R8s0Jrra8HhH7pE/waAFOKlwp6R09gj4ivtjDky5mACUnOLOsOcHVrvuB3dPa1f2S5gCLJNVL+pGkRyQ9LulLkNxdL+nS9Dl3fwDGdO5I0r2SpqfzR0h6TNJfJM1LB4ufBJye1h4/KGm0pJvTYzwi6eD0syMl3Zk+A+1KQD19CUm/k/Ro+pmZb1t3UVo+T9LotOzdku5IP3O/pCll+TUtl/zSmRqU1tSOBO5Ii6YBe0XEs2mS2BgR75fUD/hfSXeSPNFiD2AqMJbk7eFXv22/o4GfA4ek+xoRES9L+hnwakT8v3S764GLIuIBSbuQjPp4L/Ad4IGIOFfSR4BiRjh8IT3GAOARSTdHxEvAIGBBRJwu6dvpvk8heYnLSRGxRNL+wE+BQ9/Bz2i9gBNcbRkgaWE6fz/JeMeDgIcj4tm0/B+Bv++8vgYMBSYDhwA3REQ7sFrS3V3s/wDgvs59RcS2nvn2YWBqMuQSgCHpkzMOAT6Wfvb3ktYX8Z2+Kumj6XxjGutLQAfwq7T8WuA36TEOAm4qOHa/Io5hvZQTXG15PSL2KSxI/9FfKywCTo2IuW/brpxjIeuAAyJicxexFE3SDJJkeWBENEu6F+i/jc0jPe6Gt/8GZtvia3D5Mxf4cvq4HiS9R9Ig4D7gU+k1uvHAh7r47HzgEEmT0s+OSMtfAQYXbHcncGrngqR90tn7gM+kZUcCw3uIdSiwPk1uU0hqkJ3qgM5a6GdImr6bgGclfSI9hiTt3cMxrBdzgsufK0murz2m5KUw/0VSU/8tsCRddw3J00DeIiJeBGaSNAf/wptNxFuBj3Z2MgBfBaannRiLeLM393skCfJJkqbq8h5ivQPoI2kxcD5Jgu30GrBf+h0OBc5Nyz8LnJjG9yR+nLx1w08TMbPccg3OzHLLCc7McssJzsxyywnOzHLLCc7McssJzsxyywnOzHLr/wP9l+UEcftTOgAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAATgAAAEGCAYAAADxD4m3AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8vihELAAAACXBIWXMAAAsTAAALEwEAmpwYAAAejklEQVR4nO3deZQdZZ3/8fenO52V7DtJI0EiMTADxMiqnAjOsDgH0HFB/Sk/xBNRQAGRAZ1xQQdh/A0IgjgIjEE2g6iEEQgYQGAkQMCIkACJAbITGrIATdLb9/dHVcOFdLrvJfem7q3+vM6p01VP1a363nuqv+d56qmnShGBmVke1WUdgJlZpTjBmVluOcGZWW45wZlZbjnBmVlu9ck6gEJ91S/6MyjrMKrWll0HZh1C1ev3XHPWIVS1zbxGS2zR9uzj8A8Nipdebi9q20cf3zI3Io7YnuNtj6pKcP0ZxP46LOswqtYz35medQhV7z1fWJB1CFXtoZi33ft46eV2Hp67S1Hb1o9fMmq7D7gdqirBmVn1C6CDjqzDKIoTnJmVJAhao7gmatac4MysZK7BmVkuBUF7jQzxdIIzs5J14ARnZjkUQHuNJDjf6GtmJesgipp6ImmYpF9LekrSYkkHShoh6S5JS9K/w9NtJekSSUslPS5pWk/7d4Izs5IE0BpR1FSEi4E7ImIKsDewGDgbmBcRk4F56TLAkcDkdJoJXN7Tzp3gzKwkQdBe5NQdSUOBQ4CrACKiJSI2AMcAs9LNZgHHpvPHANdEYj4wTNL47o7hBGdmpQloL3ICRklaUDDNLNjTJOBF4L8l/VnSlZIGAWMjYk26zVpgbDo/AVhR8PmVadk2uZPBzEqSjGQoWlNEbGuMYR9gGnBqRDwk6WLebI4mx4oISe+4R8M1ODMrkWgvcurBSmBlRDyULv+aJOG90Nn0TP+uS9evAhoLPj8xLdsmJzgzK0nSyaCipm73E7EWWCFpj7ToMGARMAc4Pi07HrglnZ8DfD7tTT0A2FjQlO2Sm6hmVpLkPrjteuJSoVOB6yT1BZYBJ5BUvGZLOhF4Hvhkuu1twFHAUqA53bZbTnBmVrKOHmpnxYqIhUBX1+i2em5aJK8APLmU/TvBmVlJylyDqygnODMrSSDaa+TyvROcmZWsXE3USnOCM7OSBKIl6rMOoyhOcGZWkuRGXzdRzSyn3MlgZrkUIdrDNTgzy6kO1+DMLI+STobaSB21EaWZVQ13MphZrrX7PjgzyyOPZDCzXOtwL6qZ5VEy2N4JzsxyKBCtHqpVu6bP2MRJ319NfV1w+w0jmH3p2J4/lENq7aDx/KdQa0BH8Or04bx07ATGXvUsA59+hfYByUn+womT2LLLQAAGPLWJ0TesQO1B+059WHn2lCy/QmbyfA5F4Bt9ASQdQfLew3rgyog4v5LHK4e6uuDk81ZxznG70bSmgZ/ctoT5c4eyfEn/rEPb4aKPWPGNPYj+9dDWQeMPn+a1vxsKwIufnMir00e8Zfu65jbG/HI5q86YTNvIftRvas0i7Mzl/xxSzdzoW7E0LKkeuIzkZa1TgU9Lmlqp45XLHvs2s/q5vqxd3o+21jruvWUYBx6+MeuwsiElyQ1Qe6D27l9uNHj+y7z6vuG0jewHQPuQhoqHWI3yfg4FSQ2umClrlazB7QcsjYhlAJJuJHlx66IKHnO7jRzXyour+76x3LSmgSnTmjOMKGMdwS7fW0TfdVvYcOgYNr97J4be+yKjbl7FyDlraH7vYJo+PpFoqKPv2s2oPZh4wVPUbe5g/YfH8MrBo7L+BjtcbziH3MnQ9Uta96/g8awS6sTy7+1JXXMbO1/6N/qufJ2mf55A+9AG1BaMmfU8w29fy8tH74w6gn7PN7PyG+9BLR3s8u9PsfndO9E6Li9NM4Okk6FWHniZeRqWNLPzrdetbMk6HF5a28DonVveWB41vpWmNb2zqVWoY2AfmqcMZtATG2kf1jdpvjbUsekDI+m/7DUAWof3pXmvIUS/ejoGN/D6ewbTb0W+ai7FyPs5lLw2sE9RU9YqmeCKeklrRFwREdMjYnoD/SoYTnGeXjiQCZNaGNu4hT4NHcw4ZgPz7xyadViZqN/USl1zGwBq6WDgk5toGdef+g3pP28EOz22gZYJAwB4bd9hDFjyKrQH2tJO/2dfpWX8gKzCz0z+z6Gyvfi54iqZYh8BJkuaRJLYjgM+U8HjlUVHu7jsWxM47/pl1NXDnTeO4PlnemcTq35jK+OuehZ1ABG88v4RvLbPMCb+x9PUv9IGBFsaB/LC598FQMvOA3htr6G869tPQh1s/OBoWib2vgSX93Mo8EgGIqJN0inAXJLbRK6OiCcrdbxyeuTuITxy95Csw8hcS+NAln93z63KV561RxdbJ9YfOY71R46rZFg1Ie/nUDXUzopR0UZyRNxG8jZqM8uJCLkGZ2b5lHQy1MZQrdpIw2ZWRVS2G30lPSfpr5IWSlqQlo2QdJekJenf4Wm5JF0iaamkxyVN62n/TnBmVpKkk0FFTUX6UETsExHT0+WzgXkRMRmYly5DMipqcjrNBC7vacdOcGZWsnbqipreoWOAWen8LODYgvJrIjEfGCZpfHc7coIzs5J0jmQosgY3qvNG/nSaudXu4E5JjxasGxsRa9L5tUDno1i6Gh01obtY3clgZiUr4aUzTQVNz658ICJWSRoD3CXpqcKVERGSun/KQzec4MysJBHQ2lGexl9ErEr/rpP0W5KHdLwgaXxErEmboOvSzYsaHVXITVQzK0nSRK0rauqOpEGSBnfOA/8IPAHMAY5PNzseuCWdnwN8Pu1NPQDYWNCU7ZJrcGZWsjKNZBgL/FYSJLno+oi4Q9IjwGxJJwLPA59Mt78NOApYCjQDJ/R0ACc4MytJ520i272f5FmRe3dR/hJwWBflAZxcyjGc4MysRB6qZWY5VivvZHCCM7OSJL2otTEW1QnOzEpSS48sd4Izs5K5iWpmuVSuXtQdwQnOzErmXlQzy6UI0eYEZ2Z55SaqmeWSr8GZWa45wZlZLvk+ODPLNd8HZ2a5FAFtZXrgZaU5wZlZydxENbNc8jU4M8u1cIIzs7xyJ4OZ5VKEr8GZWW6Jdveimlle+Rqcld2zR1yZdQhV73D2yTqE3PNYVDPLr0iuw9UCJzgzK5l7Uc0sl6KGOhlqI0ozqyoRxU3FkFQv6c+S/iddniTpIUlLJf1KUt+0vF+6vDRdv2tP+3aCM7OSRaioqUhfAxYXLF8AXBQRuwPrgRPT8hOB9Wn5Rel23XKCM7OSJLWz8iQ4SROBjwBXpssCDgV+nW4yCzg2nT8mXSZdf1i6/Tb5GpyZlayE20RGSVpQsHxFRFxRsPxj4CxgcLo8EtgQEW3p8kpgQjo/AVgBEBFtkjam2zdt6+BOcGZWshJuE2mKiOldrZD0T8C6iHhU0ozyRPZWTnBmVpJAdJSnF/Vg4GhJRwH9gSHAxcAwSX3SWtxEYFW6/SqgEVgpqQ8wFHipuwP4GpyZlSyKnLrdR8Q5ETExInYFjgPujojPAvcAH083Ox64JZ2fky6Trr87ovu6pBOcmZWmjJ0M2/AvwBmSlpJcY7sqLb8KGJmWnwGc3dOO3EQ1s9KVeahWRNwL3JvOLwP262KbzcAnStmvE5yZlazmnyYi6Sd0k6cj4qsVicjMqloAHR01nuCABd2sM7PeKoBar8FFxKzCZUkDI6K58iGZWbWrlccl9diLKulASYuAp9LlvSX9tOKRmVn1Ksd9IjtAMbeJ/Bg4nPSGuoj4C3BIBWMys6pW3C0i1dARUVQvakSseNuY1vbKhGNmNaEKamfFKCbBrZB0EBCSGtj60SZm1psERI30ohbTRD0JOJlkJP9qYJ902cx6LRU5ZavHGlxENAGf3QGxmFmtqJEmajG9qLtJulXSi5LWSbpF0m47Ijgzq1I56kW9HpgNjAd2Bm4CbqhkUGZWxTpv9C1mylgxCW5gRPwyItrS6VqSZzeZWS9VzpfOVFJ3Y1FHpLO3SzobuJEkd38KuG0HxGZm1apGelG762R4lCShdX6TLxWsC+CcSgVlZtVNVVA7K0Z3Y1En7chAzKxGVEkHQjGKGskgaS9gKgXX3iLimkoFZWbVrDo6EIrRY4KT9B1gBkmCuw04EngAcIIz661qpAZXTC/qx4HDgLURcQKwN8nbbMyst+oocspYMU3U1yOiQ1KbpCHAOpJXd+XW9BmbOOn7q6mvC26/YQSzLx2bdUiZeXVjPRed2chzT/VHgjMuXM4jdw/hwblDkWDYqFbO/PFyRo5r4+7fDGf2ZWOIgAGDOjj1/BW8e8/NWX+FTOT6HMrDAy8LLJA0DPg5Sc/qq8CDPX1I0tVA54td99qeIHekurrg5PNWcc5xu9G0poGf3LaE+XOHsnxJ77z17/JvT2D6jE3828+fo7VFbHm9jnftsY7jz1oLwO+uHMW1F43jaxesZGzjFn5081IGD2vnkbsHc/FZjVzy+yUZf4MdrzecQ7XSi9pjEzUivhIRGyLiZ8A/AMenTdWe/AI4Yjvj2+H22LeZ1c/1Ze3yfrS11nHvLcM48PCNWYeVidc21fHX+YM44jMvA9DQN9hpaDuDBr/Z9tj8eh2dT9La8/3NDB6WPElryrRmmtY07PCYq0GvOIdqZKhWdzf6TutuXUQ81t2OI+I+SbtuR2yZGDmulRdX931juWlNA1Om9c4nta9d3o+hI9v4z9N3YdmT/Zn896/z5e+vov/ADv77/HH84aYRDBrSzn/8eulWn73jhhG8/0OvZBB19nwOVY/umqj/2c26AA4tRwCSZgIzAfozsBy7tDJpb4elfx3IyT9YxZRpzVz+bxP41aVjOP6stZxwdjLd+JMxzLl6NJ//xto3Prfwf3di7g0jufB3va952lvUShO1uxt9P7QjAoiIK4ArAIZoROY/20trGxi9c8sby6PGt/baptao8a2MHt/6Ru3jA/+0gdmXjnnLNod+dD3/+rnd3khwyxb158dnNvKDa5cxZETvfPBz7s+hoGaGahVzm0iv8vTCgUyY1MLYxi30aehgxjEbmH9n77wrZsSYNkbt3MKKpf0AWHj/YHaZvIVVy95sfj04dyiNu28BYN3KBs794iS+ccnzTHz3lkxirga94hwqwzU4Sf0lPSzpL5KelPS9tHySpIckLZX0K0l90/J+6fLSdP2uPYXpN9u/TUe7uOxbEzjv+mXU1cOdN47g+Wfy0/tVqpN/sIoLTnkXba1i3C4tfP2i5Vx0ZiMr/9aPujoYM6GFr16wEoDrLhrHK+vrufSc5C6i+j7BpXc8k2X4megN51CZmqhbgEMj4tX0dQgPSLodOAO4KCJulPQz4ETg8vTv+ojYXdJxwAUkD//oJs4KPdNE0g0kIyBGAS8A34mIq7r7zBCNiP11WEXiyYO5qxdmHULVO3znfbIOoao9FPPYFC9vV/uyX2NjTDzt9KK2XXbm1x+NiOk9bSdpIMkIqS8DvwfGRUSbpAOB70bE4ZLmpvMPSuoDrAVGRzdJrJihWiJ5ZPluEXGupF3Sgz/c3eci4tM97dvMalSZ6kWS6knur90duAz4G7AhItrSTVaSvA+G9O8KgDT5bQRGAk3b2n8x1+B+ChwIdCasV9JAzKwXUhQ/AaMkLSiYZhbuKyLaI2IfYCKwHzClnLEWcw1u/4iYJunPaUDrOy/6mVkvVXwvalMxTdSI2CDpHpLK1DBJfdJa3ERgVbrZKpJhoivTJupQ0hfSb0sxNbjWtBoZAJJGUxXDaM0sKyXU4La9D2l0OgwUSQNIRkotBu4hecgHwPHALen8nHSZdP3d3V1/g+JqcJcAvwXGSPr3dMf/WsTnzCyvynMNbjwwK61A1QGzI+J/JC0CbpT0A+DPQGfn5FXALyUtBV4GjuvpAMW8F/U6SY+SPDJJwLER4Tfbm/VWRdTOitpNxOPAvl2ULyO5Hvf28s3AJ0o5RjG9qLsAzcCthWURsbyUA5lZjmQ+5qg4xTRRf8+bL5/pD0wCngb2rGBcZlbFVCNX4Ytpov5d4XL6lJGvVCwiM7MyKXmoVkQ8Jmn/SgRjZjUiL01USWcULNYB04DVFYvIzKpbmToZdoRianCDC+bbSK7J3VyZcMysJuQhwaX3pwyOiDN3UDxmVgtqPcF1DpWQdPCODMjMqpvIRy/qwyTX2xZKmgPcBLzWuTIiflPh2MysGuXsGlx/kgGth/Lm/XABOMGZ9VY5SHBj0h7UJ3gzsXWqka9nZhVRIxmguwRXD+zEWxNbpxr5emZWCXlooq6JiHN3WCRmVjtykOBq471gZrZjRT56Uf32FzPrWq3X4CLi5R0ZiJnVjjxcgzMz65oTnJnlUhFvra8WTnBmVhLhJqqZ5ZgTnJnllxOcmeWWE5yZ5VLOniZiZvZWTnBmlld5GKplVeaAs07KOoSqN5T5WYfQK9RKE7Uu6wDMrMZECVM3JDVKukfSIklPSvpaWj5C0l2SlqR/h6flknSJpKWSHk/f0dwtJzgzK10ZEhzJW/q+HhFTgQOAkyVNBc4G5kXEZGBeugxwJDA5nWYCl/d0ACc4MytJ50iGYqbuRMSaiHgsnX8FWAxMAI4BZqWbzQKOTeePAa6JxHxgmKTx3R3D1+DMrGTqKPoi3ChJCwqWr4iIK7ban7QrsC/wEDA2Itakq9YCY9P5CcCKgo+tTMvWsA1OcGZWmtIG2zdFxPTuNpC0E8nL5E+LiE3Sm8/ajYiQ3nmXhpuoZlaycjRRASQ1kCS36wpeRfpCZ9Mz/bsuLV8FNBZ8fGJatk1OcGZWuvL0ogq4ClgcERcWrJoDHJ/OHw/cUlD++bQ39QBgY0FTtktuoppZycp0H9zBwOeAv0pamJZ9EzgfmC3pROB54JPputuAo4ClQDNwQk8HcIIzs9KVIcFFxANs++VWW70TJiICOLmUYzjBmVlpcvJWLTOzrfiJvmaWb1EbGc4JzsxK5hqcmeWT36plZnnmTgYzyy0nODPLp8CdDGaWX+5kMLP8coIzszzyjb5mll8RpTzwMlNOcGZWutrIb05wZlY6N1HNLJ8CcBPVzHKrNvKbE5yZlc5NVDPLLfeimlk++WkiZpZXyY2+tZHhnODMrHR+moiZ5ZVrcDVs+oxNnPT91dTXBbffMILZl47NOqRMfOsT93Lwe59n/asD+OyFyaspJ49v4l8+dj99G9pp7xA/+u0HWbRiDADTdlvNaUf/iT51HWxo7s9XfnZ0luFnKtfnkK/BgaRG4BpgLMnPcUVEXFyp45VLXV1w8nmrOOe43Wha08BPblvC/LlDWb6kf9ah7XC/X/Aefv2nPfn2p+55o+yUjzzEVX94Hw8+vQsHTlnOKUfN5yv/dTQ79d/CNz56P6dddRQvbBjM8EGvZxh5tvJ/DtXOWNS6Cu67Dfh6REwFDgBOljS1gscriz32bWb1c31Zu7wfba113HvLMA48fGPWYWVi4bM7s6n5rf+UETCofwsAO/Vv4cVNgwA4fN+l3PvEJF7YMBiA9a8N2LHBVpFecQ5FFDdlrGIJLiLWRMRj6fwrwGJgQqWOVy4jx7Xy4uq+byw3rWlg1PjWDCOqLj++9SBOOeohbvnmtZz6kQe5/Pb9AGgctYHBA7bw0y/N4RdfvZkjpz2TcaTZyf05lL74uZipJ5KulrRO0hMFZSMk3SVpSfp3eFouSZdIWirpcUnTetp/JWtwb5C0K7Av8NCOOJ5VzscOWMTFtx7IMef9Hy6+9SC+9Yk/AlBfF0yZ0MQZVx/J1648ii98+FEaR23INlirnPLV4H4BHPG2srOBeRExGZiXLgMcCUxOp5nA5T3tvOIJTtJOwM3AaRGxqYv1MyUtkLSglS2VDqdHL61tYPTOLW8sjxrfStOahgwjqi5Hve8Z7nliEgDzHt+NqY3rAFi3cRDzn5nI5tYGNjYP4M/LxjN5/EtZhpqZXnEORZFTT7uJuA94+W3FxwCz0vlZwLEF5ddEYj4wTNL47vZf0QQnqYEkuV0XEb/papuIuCIipkfE9Ab6VTKcojy9cCATJrUwtnELfRo6mHHMBubfOTTrsKpG06aBTNttDQDTd1/Fiqbkt7l/0a7sveta6us66NfQyp67rOO5dcOzDDUzveEcUkdHURMwqrMCk04zi9j92IhYk86vJemohOQS14qC7VbSw2WvSvaiCrgKWBwRF1bqOOXW0S4u+9YEzrt+GXX1cOeNI3j+mbz0fpXm3M/8gWm7rWHYoM3M+ea1/Pyu6fzw5kM4/eg/UV/XQUtbH3548yEAPLduOPOfaeTa02+iI8Sch6ew7IURGX+DbOT+HApKudG3KSKmv+NDRYT0zof2V/I+uIOBzwF/lbQwLftmRNxWwWOWxSN3D+GRu4dkHUbmvn39h7ss/7+X/HOX5df9cR+u++M+FYyoduT5HBJR6Rt9X5A0PiLWpE3QdWn5KqCxYLuJadk2VSzBRcQDJMPWzCxvKpvg5gDHA+enf28pKD9F0o3A/sDGgqZslzySwcxKV6YEJ+kGYAbJtbqVwHdIEttsSScCzwOfTDe/DTgKWAo0Ayf0tH8nODMrTWnX4LrfVcSnt7HqsC62DeDkUvbvBGdmJUt7SKueE5yZlag6hmEVwwnOzEoTOMGZWY7VRgvVCc7MSucHXppZfjnBmVkuRUB7bbRRneDMrHSuwZlZbjnBmVkuBVAj72RwgjOzEgWEr8GZWR4F7mQwsxzzNTgzyy0nODPLJw+2N7O8CsCPSzKz3HINzszyyUO1zCyvAsL3wZlZbnkkg5nllq/BmVkuRbgX1cxyzDU4M8unINrbsw6iKE5wZlYaPy7JzHKtRm4Tqcs6ADOrLQFERxQ19UTSEZKelrRU0tnljtUJzsxKE+kDL4uZuiGpHrgMOBKYCnxa0tRyhuomqpmVrEydDPsBSyNiGYCkG4FjgEXl2DmAooq6eyW9CDyfdRwFRgFNWQdRxfz79KzafqN3RcTo7dmBpDtIvlcx+gObC5aviIgr0v18HDgiIr6YLn8O2D8iTtme+ApVVQ1ue3/4cpO0ICKmZx1HtfLv07M8/kYRcUTWMRTL1+DMLCurgMaC5YlpWdk4wZlZVh4BJkuaJKkvcBwwp5wHqKomahW6IusAqpx/n575N9qGiGiTdAowF6gHro6IJ8t5jKrqZDAzKyc3Uc0st5zgzCy3nOC6UOnhI7VO0tWS1kl6IutYqpGkRkn3SFok6UlJX8s6pt7K1+DeJh0+8gzwD8BKkp6eT0dE2e6urnWSDgFeBa6JiL2yjqfaSBoPjI+IxyQNBh4FjvU5tOO5Bre1N4aPREQL0Dl8xFIRcR/wctZxVKuIWBMRj6XzrwCLgQnZRtU7OcFtbQKwomB5JT457R2StCuwL/BQxqH0Sk5wZhUiaSfgZuC0iNiUdTy9kRPc1io+fMTyT1IDSXK7LiJ+k3U8vZUT3NYqPnzE8k2SgKuAxRFxYdbx9GZOcG8TEW1A5/CRxcDscg8fqXWSbgAeBPaQtFLSiVnHVGUOBj4HHCppYTodlXVQvZFvEzGz3HINzsxyywnOzHLLCc7McssJzsxyywnOzHLLCa6GSGpPbzl4QtJNkgZux75+kb7VCElXdvc+SkkzJB30Do7xnKSt3r60rfK3bfNqicf6rqQzS43R8s0Jrra8HhH7pE/waAFOKlwp6R09gj4ivtjDky5mACUnOLOsOcHVrvuB3dPa1f2S5gCLJNVL+pGkRyQ9LulLkNxdL+nS9Dl3fwDGdO5I0r2SpqfzR0h6TNJfJM1LB4ufBJye1h4/KGm0pJvTYzwi6eD0syMl3Zk+A+1KQD19CUm/k/Ro+pmZb1t3UVo+T9LotOzdku5IP3O/pCll+TUtl/zSmRqU1tSOBO5Ii6YBe0XEs2mS2BgR75fUD/hfSXeSPNFiD2AqMJbk7eFXv22/o4GfA4ek+xoRES9L+hnwakT8v3S764GLIuIBSbuQjPp4L/Ad4IGIOFfSR4BiRjh8IT3GAOARSTdHxEvAIGBBRJwu6dvpvk8heYnLSRGxRNL+wE+BQ9/Bz2i9gBNcbRkgaWE6fz/JeMeDgIcj4tm0/B+Bv++8vgYMBSYDhwA3REQ7sFrS3V3s/wDgvs59RcS2nvn2YWBqMuQSgCHpkzMOAT6Wfvb3ktYX8Z2+Kumj6XxjGutLQAfwq7T8WuA36TEOAm4qOHa/Io5hvZQTXG15PSL2KSxI/9FfKywCTo2IuW/brpxjIeuAAyJicxexFE3SDJJkeWBENEu6F+i/jc0jPe6Gt/8GZtvia3D5Mxf4cvq4HiS9R9Ig4D7gU+k1uvHAh7r47HzgEEmT0s+OSMtfAQYXbHcncGrngqR90tn7gM+kZUcCw3uIdSiwPk1uU0hqkJ3qgM5a6GdImr6bgGclfSI9hiTt3cMxrBdzgsufK0murz2m5KUw/0VSU/8tsCRddw3J00DeIiJeBGaSNAf/wptNxFuBj3Z2MgBfBaannRiLeLM393skCfJJkqbq8h5ivQPoI2kxcD5Jgu30GrBf+h0OBc5Nyz8LnJjG9yR+nLx1w08TMbPccg3OzHLLCc7McssJzsxyywnOzHLLCc7McssJzsxyywnOzHLr/wP9l+UEcftTOgAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "X = data['name']\n",
    "y = data['sex']\n",
    "from sklearn.feature_extraction.text import CountVectorizer,TfidfVectorizer\n",
    "cv = CountVectorizer()\n",
    "cv.fit(X)\n",
    "X = cv.transform(X)\n",
    "X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.25)\n",
    "models = {\n",
    "    'GradientBoostingClassifier':GradientBoostingClassifier(),\n",
    "    'ExtraTreesClassifier':ExtraTreesClassifier(),\n",
    "    'BaggingClassifier':BaggingClassifier(),\n",
    "    'AdaBoostClassifier':AdaBoostClassifier(),\n",
    "    'RandomForestClassifier':RandomForestClassifier(),\n",
    "    'SGDClassifier':SGDClassifier(),\n",
    "    'RidgeClassifier':RidgeClassifier(),\n",
    "    'ExtraTreeClassifier':ExtraTreeClassifier(),\n",
    "    'DecisionTreeClassifier':DecisionTreeClassifier(),\n",
    "}\n",
    "models_clf_results = fit_and_calcuate_metrixs(models,X_train,X_test,y_train,y_test)\n",
    "models_clf_results = pd.DataFrame(models_clf_results.values(),models_clf_results.keys())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.25)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "GradientBoostingClassifier\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/ranuga/.local/lib/python3.8/site-packages/sklearn/metrics/_classification.py:1221: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
      "  _warn_prf(average, modifier, msg_start, len(result))\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\n",
      "ExtraTreesClassifier\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/ranuga/.local/lib/python3.8/site-packages/sklearn/metrics/_classification.py:1221: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
      "  _warn_prf(average, modifier, msg_start, len(result))\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\n",
      "BaggingClassifier\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/ranuga/.local/lib/python3.8/site-packages/sklearn/metrics/_classification.py:1221: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
      "  _warn_prf(average, modifier, msg_start, len(result))\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\n",
      "AdaBoostClassifier\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/ranuga/.local/lib/python3.8/site-packages/sklearn/metrics/_classification.py:1221: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
      "  _warn_prf(average, modifier, msg_start, len(result))\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\n",
      "RandomForestClassifier\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/ranuga/.local/lib/python3.8/site-packages/sklearn/metrics/_classification.py:1221: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
      "  _warn_prf(average, modifier, msg_start, len(result))\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\n",
      "SGDClassifier\n",
      "\n",
      "\n",
      "\n",
      "RidgeClassifier\n",
      "\n",
      "\n",
      "\n",
      "ExtraTreeClassifier\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/ranuga/.local/lib/python3.8/site-packages/sklearn/metrics/_classification.py:1221: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
      "  _warn_prf(average, modifier, msg_start, len(result))\n",
      "/home/ranuga/.local/lib/python3.8/site-packages/sklearn/metrics/_classification.py:1221: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
      "  _warn_prf(average, modifier, msg_start, len(result))\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\n",
      "DecisionTreeClassifier\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/ranuga/.local/lib/python3.8/site-packages/sklearn/metrics/_classification.py:1221: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
      "  _warn_prf(average, modifier, msg_start, len(result))\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "models = {\n",
    "    'GradientBoostingClassifier':GradientBoostingClassifier(),\n",
    "    'ExtraTreesClassifier':ExtraTreesClassifier(),\n",
    "    'BaggingClassifier':BaggingClassifier(),\n",
    "    'AdaBoostClassifier':AdaBoostClassifier(),\n",
    "    'RandomForestClassifier':RandomForestClassifier(),\n",
    "    'SGDClassifier':SGDClassifier(),\n",
    "    'RidgeClassifier':RidgeClassifier(),\n",
    "    'ExtraTreeClassifier':ExtraTreeClassifier(),\n",
    "    'DecisionTreeClassifier':DecisionTreeClassifier(),\n",
    "}\n",
    "models_clf_results = fit_and_calcuate_metrixs(models,X_train,X_test,y_train,y_test)\n",
    "models_clf_results = pd.DataFrame(models_clf_results.values(),models_clf_results.keys())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "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>Accuracy</th>\n",
       "      <th>F1 Score</th>\n",
       "      <th>Precision</th>\n",
       "      <th>Recall</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>GradientBoostingClassifier</th>\n",
       "      <td>0.545145</td>\n",
       "      <td>0.235208</td>\n",
       "      <td>0.181715</td>\n",
       "      <td>0.333333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ExtraTreesClassifier</th>\n",
       "      <td>0.545145</td>\n",
       "      <td>0.235208</td>\n",
       "      <td>0.181715</td>\n",
       "      <td>0.333333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>BaggingClassifier</th>\n",
       "      <td>0.545145</td>\n",
       "      <td>0.235208</td>\n",
       "      <td>0.181715</td>\n",
       "      <td>0.333333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>AdaBoostClassifier</th>\n",
       "      <td>0.545145</td>\n",
       "      <td>0.235208</td>\n",
       "      <td>0.181715</td>\n",
       "      <td>0.333333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>RandomForestClassifier</th>\n",
       "      <td>0.545145</td>\n",
       "      <td>0.235208</td>\n",
       "      <td>0.181715</td>\n",
       "      <td>0.333333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>SGDClassifier</th>\n",
       "      <td>0.545997</td>\n",
       "      <td>0.237316</td>\n",
       "      <td>0.515203</td>\n",
       "      <td>0.334325</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>RidgeClassifier</th>\n",
       "      <td>0.545997</td>\n",
       "      <td>0.237316</td>\n",
       "      <td>0.515203</td>\n",
       "      <td>0.334325</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ExtraTreeClassifier</th>\n",
       "      <td>0.545997</td>\n",
       "      <td>0.237316</td>\n",
       "      <td>0.515203</td>\n",
       "      <td>0.334325</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>DecisionTreeClassifier</th>\n",
       "      <td>0.545997</td>\n",
       "      <td>0.237316</td>\n",
       "      <td>0.515203</td>\n",
       "      <td>0.334325</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                            Accuracy  F1 Score  Precision    Recall\n",
       "GradientBoostingClassifier  0.545145  0.235208   0.181715  0.333333\n",
       "ExtraTreesClassifier        0.545145  0.235208   0.181715  0.333333\n",
       "BaggingClassifier           0.545145  0.235208   0.181715  0.333333\n",
       "AdaBoostClassifier          0.545145  0.235208   0.181715  0.333333\n",
       "RandomForestClassifier      0.545145  0.235208   0.181715  0.333333\n",
       "SGDClassifier               0.545997  0.237316   0.515203  0.334325\n",
       "RidgeClassifier             0.545997  0.237316   0.515203  0.334325\n",
       "ExtraTreeClassifier         0.545997  0.237316   0.515203  0.334325\n",
       "DecisionTreeClassifier      0.545997  0.237316   0.515203  0.334325"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "models_clf_results"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1440x720 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "models_clf_results.plot.bar(figsize=(20,10))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### SGDClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Fitting 2 folds for each of 72 candidates, totalling 144 fits\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l2, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l2, power_t=0.25, shuffle=True, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l2, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l2, power_t=0.25, shuffle=True, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l2, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l2, power_t=0.25, shuffle=True, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l2, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l2, power_t=0.25, shuffle=True, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l2, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l2, power_t=0.25, shuffle=False, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l2, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l2, power_t=0.25, shuffle=False, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l2, power_t=0.25, shuffle=False, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l2, power_t=0.25, shuffle=False, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l2, power_t=0.25, shuffle=False, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l2, power_t=0.25, shuffle=False, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l1, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l1, power_t=0.25, shuffle=True, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l1, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l1, power_t=0.25, shuffle=True, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l1, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l1, power_t=0.25, shuffle=True, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l1, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l1, power_t=0.25, shuffle=True, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l1, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l1, power_t=0.25, shuffle=False, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l1, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l1, power_t=0.25, shuffle=False, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l1, power_t=0.25, shuffle=False, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l1, power_t=0.25, shuffle=False, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l1, power_t=0.25, shuffle=False, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l1, power_t=0.25, shuffle=False, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=False \n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=1)]: Using backend SequentialBackend with 1 concurrent workers.\n",
      "[Parallel(n_jobs=1)]: Done   1 out of   1 | elapsed:    0.0s remaining:    0.0s\n",
      "[Parallel(n_jobs=1)]: Done   2 out of   2 | elapsed:    0.0s remaining:    0.0s\n",
      "[Parallel(n_jobs=1)]: Done   3 out of   3 | elapsed:    0.0s remaining:    0.0s\n",
      "[Parallel(n_jobs=1)]: Done   4 out of   4 | elapsed:    0.0s remaining:    0.0s\n",
      "[Parallel(n_jobs=1)]: Done   5 out of   5 | elapsed:    0.1s remaining:    0.0s\n",
      "[Parallel(n_jobs=1)]: Done   6 out of   6 | elapsed:    0.1s remaining:    0.0s\n",
      "[Parallel(n_jobs=1)]: Done   7 out of   7 | elapsed:    0.1s remaining:    0.0s\n",
      "[Parallel(n_jobs=1)]: Done   8 out of   8 | elapsed:    0.1s remaining:    0.0s\n",
      "[Parallel(n_jobs=1)]: Done   9 out of   9 | elapsed:    0.1s remaining:    0.0s\n",
      "[Parallel(n_jobs=1)]: Done  10 out of  10 | elapsed:    0.1s remaining:    0.0s\n",
      "[Parallel(n_jobs=1)]: Done  11 out of  11 | elapsed:    0.1s remaining:    0.0s\n",
      "[Parallel(n_jobs=1)]: Done  12 out of  12 | elapsed:    0.1s remaining:    0.0s\n",
      "[Parallel(n_jobs=1)]: Done  13 out of  13 | elapsed:    0.1s remaining:    0.0s\n",
      "[Parallel(n_jobs=1)]: Done  14 out of  14 | elapsed:    0.1s remaining:    0.0s\n",
      "[Parallel(n_jobs=1)]: Done  15 out of  15 | elapsed:    0.1s remaining:    0.0s\n",
      "[Parallel(n_jobs=1)]: Done  16 out of  16 | elapsed:    0.1s remaining:    0.0s\n",
      "[Parallel(n_jobs=1)]: Done  17 out of  17 | elapsed:    0.2s remaining:    0.0s\n",
      "[Parallel(n_jobs=1)]: Done  18 out of  18 | elapsed:    0.2s remaining:    0.0s\n",
      "[Parallel(n_jobs=1)]: Done  19 out of  19 | elapsed:    0.2s remaining:    0.0s\n",
      "[Parallel(n_jobs=1)]: Done  20 out of  20 | elapsed:    0.2s remaining:    0.0s\n",
      "[Parallel(n_jobs=1)]: Done  21 out of  21 | elapsed:    0.2s remaining:    0.0s\n",
      "[Parallel(n_jobs=1)]: Done  22 out of  22 | elapsed:    0.2s remaining:    0.0s\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l2, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l2, power_t=0.25, shuffle=True, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l2, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l2, power_t=0.25, shuffle=True, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l2, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l2, power_t=0.25, shuffle=True, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l2, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l2, power_t=0.25, shuffle=True, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l2, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l2, power_t=0.25, shuffle=False, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l2, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l2, power_t=0.25, shuffle=False, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l2, power_t=0.25, shuffle=False, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l2, power_t=0.25, shuffle=False, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l2, power_t=0.25, shuffle=False, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l2, power_t=0.25, shuffle=False, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l1, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l1, power_t=0.25, shuffle=True, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l1, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l1, power_t=0.25, shuffle=True, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l1, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l1, power_t=0.25, shuffle=True, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l1, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l1, power_t=0.25, shuffle=True, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l1, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l1, power_t=0.25, shuffle=False, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l1, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l1, power_t=0.25, shuffle=False, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l1, power_t=0.25, shuffle=False, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l1, power_t=0.25, shuffle=False, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l1, power_t=0.25, shuffle=False, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l1, power_t=0.25, shuffle=False, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=True \n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=1)]: Done  23 out of  23 | elapsed:    0.2s remaining:    0.0s\n",
      "[Parallel(n_jobs=1)]: Done  24 out of  24 | elapsed:    0.2s remaining:    0.0s\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l2, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l2, power_t=0.25, shuffle=True, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l2, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l2, power_t=0.25, shuffle=True, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l2, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l2, power_t=0.25, shuffle=True, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l2, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l2, power_t=0.25, shuffle=True, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l2, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l2, power_t=0.25, shuffle=False, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l2, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l2, power_t=0.25, shuffle=False, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l2, power_t=0.25, shuffle=False, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l2, power_t=0.25, shuffle=False, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l2, power_t=0.25, shuffle=False, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l2, power_t=0.25, shuffle=False, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l1, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l1, power_t=0.25, shuffle=True, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l1, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l1, power_t=0.25, shuffle=True, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l1, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l1, power_t=0.25, shuffle=True, warm_start=False, score=0.161, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l1, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l1, power_t=0.25, shuffle=True, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l1, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l1, power_t=0.25, shuffle=False, warm_start=True, score=0.290, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l1, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l1, power_t=0.25, shuffle=False, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l1, power_t=0.25, shuffle=False, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l1, power_t=0.25, shuffle=False, warm_start=False, score=0.290, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l1, power_t=0.25, shuffle=False, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l1, power_t=0.25, shuffle=False, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=True, score=0.290, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=True, score=0.161, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=False, score=0.290, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=True, score=0.290, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=False, score=0.290, total=   0.0s\n",
      "[CV] alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=False \n",
      "[CV]  alpha=0.25, average=False, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l2, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l2, power_t=0.25, shuffle=True, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l2, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l2, power_t=0.25, shuffle=True, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l2, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l2, power_t=0.25, shuffle=True, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l2, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l2, power_t=0.25, shuffle=True, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l2, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l2, power_t=0.25, shuffle=False, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l2, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l2, power_t=0.25, shuffle=False, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l2, power_t=0.25, shuffle=False, warm_start=False \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l2, power_t=0.25, shuffle=False, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l2, power_t=0.25, shuffle=False, warm_start=False \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l2, power_t=0.25, shuffle=False, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l1, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l1, power_t=0.25, shuffle=True, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l1, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l1, power_t=0.25, shuffle=True, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l1, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l1, power_t=0.25, shuffle=True, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l1, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l1, power_t=0.25, shuffle=True, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l1, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l1, power_t=0.25, shuffle=False, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l1, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l1, power_t=0.25, shuffle=False, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l1, power_t=0.25, shuffle=False, warm_start=False \n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l1, power_t=0.25, shuffle=False, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l1, power_t=0.25, shuffle=False, warm_start=False \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=l1, power_t=0.25, shuffle=False, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=False \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=False \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=log, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l2, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l2, power_t=0.25, shuffle=True, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l2, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l2, power_t=0.25, shuffle=True, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l2, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l2, power_t=0.25, shuffle=True, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l2, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l2, power_t=0.25, shuffle=True, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l2, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l2, power_t=0.25, shuffle=False, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l2, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l2, power_t=0.25, shuffle=False, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l2, power_t=0.25, shuffle=False, warm_start=False \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l2, power_t=0.25, shuffle=False, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l2, power_t=0.25, shuffle=False, warm_start=False \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l2, power_t=0.25, shuffle=False, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l1, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l1, power_t=0.25, shuffle=True, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l1, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l1, power_t=0.25, shuffle=True, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l1, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l1, power_t=0.25, shuffle=True, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l1, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l1, power_t=0.25, shuffle=True, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l1, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l1, power_t=0.25, shuffle=False, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l1, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l1, power_t=0.25, shuffle=False, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l1, power_t=0.25, shuffle=False, warm_start=False \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l1, power_t=0.25, shuffle=False, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l1, power_t=0.25, shuffle=False, warm_start=False \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=l1, power_t=0.25, shuffle=False, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=False \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=False \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=hinge, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l2, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l2, power_t=0.25, shuffle=True, warm_start=True, score=0.290, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l2, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l2, power_t=0.25, shuffle=True, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l2, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l2, power_t=0.25, shuffle=True, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l2, power_t=0.25, shuffle=True, warm_start=False \n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l2, power_t=0.25, shuffle=True, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l2, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l2, power_t=0.25, shuffle=False, warm_start=True, score=0.161, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l2, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l2, power_t=0.25, shuffle=False, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l2, power_t=0.25, shuffle=False, warm_start=False \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l2, power_t=0.25, shuffle=False, warm_start=False, score=0.161, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l2, power_t=0.25, shuffle=False, warm_start=False \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l2, power_t=0.25, shuffle=False, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l1, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l1, power_t=0.25, shuffle=True, warm_start=True, score=0.290, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l1, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l1, power_t=0.25, shuffle=True, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l1, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l1, power_t=0.25, shuffle=True, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l1, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l1, power_t=0.25, shuffle=True, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l1, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l1, power_t=0.25, shuffle=False, warm_start=True, score=0.161, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l1, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l1, power_t=0.25, shuffle=False, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l1, power_t=0.25, shuffle=False, warm_start=False \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l1, power_t=0.25, shuffle=False, warm_start=False, score=0.161, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l1, power_t=0.25, shuffle=False, warm_start=False \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=l1, power_t=0.25, shuffle=False, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=True, score=0.290, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=False \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=elasticnet, power_t=0.25, shuffle=True, warm_start=False, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=True, score=0.161, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=True \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=True, score=0.549, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=False \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=False, score=0.161, total=   0.0s\n",
      "[CV] alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=False \n",
      "[CV]  alpha=0.25, average=True, epsilon=0.25, l1_ratio=0.25, loss=perceptron, penalty=elasticnet, power_t=0.25, shuffle=False, warm_start=False, score=0.549, total=   0.0s\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=1)]: Done 144 out of 144 | elapsed:    1.4s finished\n"
     ]
    }
   ],
   "source": [
    "grid = {\n",
    "    'loss':['log','hinge','perceptron'],\n",
    "    'penalty':['l2','l1','elasticnet'],\n",
    "    'alpha':[0.25],\n",
    "    'shuffle':[True,False],\n",
    "    'warm_start':[True,False],\n",
    "    'l1_ratio':[0.25],\n",
    "    'epsilon':[0.25],\n",
    "    'power_t':[0.25],\n",
    "    'average':[False,True]\n",
    "}\n",
    "gs = GridSearchCV(SGDClassifier(),cv=2,verbose=25,param_grid=grid).fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.545144804088586"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gs.score(X_test,y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "pickle.dump(gs,open('model.pkl','wb'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<4695x4698 sparse matrix of type '<class 'numpy.int64'>'\n",
       "\twith 4699 stored elements in Compressed Sparse Row format>"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "pickle.dump(cv,open('transformer.pkl','wb'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}