DataScienceAnalisisModel.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 104,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[nltk_data] Downloading package wordnet to\n",
      "[nltk_data]     C:\\Users\\simon\\AppData\\Roaming\\nltk_data...\n",
      "[nltk_data]   Package wordnet is already up-to-date!\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 104,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import re\n",
    "import string\n",
    "import collections\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "import nltk\n",
    "from nltk.corpus import stopwords\n",
    "from nltk.stem import WordNetLemmatizer, SnowballStemmer\n",
    "\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.feature_extraction.text import TfidfTransformer\n",
    "\n",
    "from sklearn.model_selection import RandomizedSearchCV\n",
    "from sklearn import svm\n",
    "from xgboost import XGBClassifier\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.pipeline import Pipeline\n",
    "\n",
    "from sklearn.metrics import f1_score\n",
    "from sklearn.feature_extraction.text import CountVectorizer\n",
    "from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay\n",
    "from sklearn.metrics import recall_score\n",
    "from sklearn.metrics import precision_score\n",
    "import pickle\n",
    "from sklearn.compose import ColumnTransformer\n",
    "nltk.download('wordnet')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv('./FakeData.csv')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "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>Unnamed: 0</th>\n",
       "      <th>title</th>\n",
       "      <th>text</th>\n",
       "      <th>label</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>LAW ENFORCEMENT ON HIGH ALERT Following Threat...</td>\n",
       "      <td>No comment is expected from Barack Obama Membe...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Did they post their votes for Hillary already?</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>UNBELIEVABLE! OBAMA’S ATTORNEY GENERAL SAYS MO...</td>\n",
       "      <td>Now, most of the demonstrators gathered last ...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>Bobby Jindal, raised Hindu, uses story of Chri...</td>\n",
       "      <td>A dozen politically active pastors came here f...</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4</td>\n",
       "      <td>SATAN 2: Russia unvelis an image of its terrif...</td>\n",
       "      <td>The RS-28 Sarmat missile, dubbed Satan 2, will...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Unnamed: 0                                              title  \\\n",
       "0           0  LAW ENFORCEMENT ON HIGH ALERT Following Threat...   \n",
       "1           1                                                NaN   \n",
       "2           2  UNBELIEVABLE! OBAMA’S ATTORNEY GENERAL SAYS MO...   \n",
       "3           3  Bobby Jindal, raised Hindu, uses story of Chri...   \n",
       "4           4  SATAN 2: Russia unvelis an image of its terrif...   \n",
       "\n",
       "                                                text  label  \n",
       "0  No comment is expected from Barack Obama Membe...      1  \n",
       "1     Did they post their votes for Hillary already?      1  \n",
       "2   Now, most of the demonstrators gathered last ...      1  \n",
       "3  A dozen politically active pastors came here f...      0  \n",
       "4  The RS-28 Sarmat missile, dubbed Satan 2, will...      1  "
      ]
     },
     "execution_count": 83,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 72134 entries, 0 to 72133\n",
      "Data columns (total 4 columns):\n",
      " #   Column      Non-Null Count  Dtype \n",
      "---  ------      --------------  ----- \n",
      " 0   Unnamed: 0  72134 non-null  int64 \n",
      " 1   title       71576 non-null  object\n",
      " 2   text        72095 non-null  object\n",
      " 3   label       72134 non-null  int64 \n",
      "dtypes: int64(2), object(2)\n",
      "memory usage: 2.2+ MB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.FacetGrid at 0x1a402ecc650>"
      ]
     },
     "execution_count": 85,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAeoAAAHpCAYAAABN+X+UAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAAPYQAAD2EBqD+naQAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjAsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy8GearUAAAgAElEQVR4nO3df1RU953/8dcEZEQCU5Dwq6IxjRIJaltMEG3rb9CKxJpd02V3ju5aNGuUWKX5xtg2pK2ajT8bTK312JiKFk9rTN2YTtAk2lB/09CIGmsbU7UFf0QYhJKB4P3+keZuRhAFET6Jz8c59xzmft5z7/t+TjIvPzMXxmFZliUAAGCk2zq7AQAAcHUENQAABiOoAQAwGEENAIDBCGoAAAxGUAMAYDCCGgAAgxHU7ciyLFVXV4tfTQcAtBeCuh1dunRJLpdLly5d6uxWAACfEQQ1AAAGI6gBADAYQQ0AgMEIagAADEZQAwBgMIIaAACDEdQAABiMoAYAwGAENQAABiOoAQAwGEENAIDBCGoAAAxGUAMAYDCCGgAAgxHUAAAYjKAGAMBgBDUAAAYjqAEAMFhgZzcAAEBHOXXqlC5cuHBDx4iMjFTPnj3bqaNrI6gBALeEU6dO6Z57+qmu7h83dJzg4G56551jHRbWBDUA4JZw4cIF1dX9Qyn/9aTCYu9s0zGqy9/T/p8/pQsXLhDUAADcDGGxdyqiZ0Jnt3HduJkMAACDEdQAABiMoAYAwGAENQAABiOoAQAwGEENAIDBCGoAAAxGUAMAYDCCGgAAgxHUAAAYjKAGAMBgBDUAAAYjqAEAMBhBDQCAwQhqAAAMRlADAGAwghoAAIN1alCvXr1aAwYMUFhYmMLCwpSamqrf/va39vjUqVPlcDj8tsGDB/sdw+fzafbs2YqMjFRISIgyMzN15swZv5rKykq53W65XC65XC653W5VVVX51Zw6dUoTJkxQSEiIIiMjlZOTo/r6+pt38QAAXIdODeoePXro6aef1qFDh3To0CGNHDlSDzzwgI4cOWLXjB07VuXl5fb2yiuv+B1jzpw52rp1qwoLC1VcXKyamhplZGSosbHRrsnKylJpaak8Ho88Ho9KS0vldrvt8cbGRo0fP161tbUqLi5WYWGhtmzZonnz5t38SQAAoAWBnXnyCRMm+D1euHChVq9erX379unee++VJDmdTsXExDT7fK/Xq3Xr1mnDhg0aPXq0JKmgoEDx8fHauXOn0tPTdezYMXk8Hu3bt08pKSmSpLVr1yo1NVXHjx9XQkKCioqKdPToUZ0+fVpxcXGSpGXLlmnq1KlauHChwsLCmj2/z+eTz+ezH1dXV9/YhHzCqVOndOHChRs6RmRkpHr27NlOHQEAOkOnBvUnNTY26le/+pVqa2uVmppq79+1a5eioqL0uc99TsOGDdPChQsVFRUlSSopKVFDQ4PS0tLs+ri4OCUlJWnPnj1KT0/X3r175XK57JCWpMGDB8vlcmnPnj1KSEjQ3r17lZSUZIe0JKWnp8vn86mkpEQjRoxotufFixfrqaeeau+p0KlTp3TPPf1UV/ePGzpOcHA3vfPOMcIaAD7FOj2oDx8+rNTUVH3wwQe6/fbbtXXrViUmJkqSxo0bp3/9139Vr169dPLkSX3ve9/TyJEjVVJSIqfTqYqKCgUFBSk8PNzvmNHR0aqoqJAkVVRU2MH+SVFRUX410dHRfuPh4eEKCgqya5ozf/58zZ07135cXV2t+Pj4tk3EJ1y4cEF1df9Qyn89qbDYO9t0jOry97T/50/pwoULBDUAfIp1elAnJCSotLRUVVVV2rJli6ZMmaLdu3crMTFRDz30kF2XlJSkQYMGqVevXtq+fbsmTZp01WNaliWHw2E//uTPN1JzJafTKafTec1rbKuw2DsV0TPhph0fAGC+Tv/1rKCgIN19990aNGiQFi9erIEDB+rHP/5xs7WxsbHq1auXTpw4IUmKiYlRfX29Kisr/erOnTtnr5BjYmJ09uzZJsc6f/68X82VK+fKyko1NDQ0WWkDANCROj2or2RZlt8NWp/0/vvv6/Tp04qNjZUkJScnq0uXLtqxY4ddU15errKyMg0ZMkSSlJqaKq/XqwMHDtg1+/fvl9fr9aspKytTeXm5XVNUVCSn06nk5OR2v0YAAK5Xp771/cQTT2jcuHGKj4/XpUuXVFhYqF27dsnj8aimpkZ5eXl68MEHFRsbq/fee09PPPGEIiMj9Y1vfEOS5HK5NG3aNM2bN0/du3dXRESEcnNz1b9/f/su8H79+mns2LHKzs7WmjVrJEnTp09XRkaGEhI+els5LS1NiYmJcrvdWrJkiS5evKjc3FxlZ2df9Y5vAAA6QqcG9dmzZ+V2u1VeXi6Xy6UBAwbI4/FozJgxqqur0+HDh/WLX/xCVVVVio2N1YgRI7R582aFhobax1ixYoUCAwM1efJk1dXVadSoUVq/fr0CAgLsmo0bNyonJ8e+OzwzM1OrVq2yxwMCArR9+3bNnDlTQ4cOVXBwsLKysrR06dKOmwwAAJrRqUG9bt26q44FBwfr1VdfveYxunbtqvz8fOXn51+1JiIiQgUFBS0ep2fPnnr55ZeveT4AADqScZ9RAwCA/0NQAwBgMIIaAACDEdQAABiMoAYAwGAENQAABiOoAQAwGEENAIDBCGoAAAxGUAMAYDCCGgAAgxHUAAAYjKAGAMBgBDUAAAYjqAEAMBhBDQCAwQhqAAAMRlADAGAwghoAAIMR1AAAGIygBgDAYAQ1AAAGI6gBADAYQQ0AgMEIagAADEZQAwBgMIIaAACDEdQAABiMoAYAwGAENQAABiOoAQAwGEENAIDBCGoAAAxGUAMAYDCCGgAAgxHUAAAYjKAGAMBgBDUAAAYjqAEAMBhBDQCAwQhqAAAMRlADAGAwghoAAIMR1AAAGKxTg3r16tUaMGCAwsLCFBYWptTUVP32t7+1xy3LUl5enuLi4hQcHKzhw4fryJEjfsfw+XyaPXu2IiMjFRISoszMTJ05c8avprKyUm63Wy6XSy6XS263W1VVVX41p06d0oQJExQSEqLIyEjl5OSovr7+5l08AADXoVODukePHnr66ad16NAhHTp0SCNHjtQDDzxgh/Ezzzyj5cuXa9WqVTp48KBiYmI0ZswYXbp0yT7GnDlztHXrVhUWFqq4uFg1NTXKyMhQY2OjXZOVlaXS0lJ5PB55PB6VlpbK7Xbb442NjRo/frxqa2tVXFyswsJCbdmyRfPmzeu4yQAAoBmBnXnyCRMm+D1euHChVq9erX379ikxMVErV67UggULNGnSJEnSCy+8oOjoaG3atEkzZsyQ1+vVunXrtGHDBo0ePVqSVFBQoPj4eO3cuVPp6ek6duyYPB6P9u3bp5SUFEnS2rVrlZqaquPHjyshIUFFRUU6evSoTp8+rbi4OEnSsmXLNHXqVC1cuFBhYWHN9u/z+eTz+ezH1dXV7T5HAIBbmzGfUTc2NqqwsFC1tbVKTU3VyZMnVVFRobS0NLvG6XRq2LBh2rNnjySppKREDQ0NfjVxcXFKSkqya/bu3SuXy2WHtCQNHjxYLpfLryYpKckOaUlKT0+Xz+dTSUnJVXtevHix/Xa6y+VSfHx8+0wGAAD/1OlBffjwYd1+++1yOp16+OGHtXXrViUmJqqiokKSFB0d7VcfHR1tj1VUVCgoKEjh4eEt1kRFRTU5b1RUlF/NlecJDw9XUFCQXdOc+fPny+v12tvp06dbefUAALSsU9/6lqSEhASVlpaqqqpKW7Zs0ZQpU7R792573OFw+NVbltVk35WurGmuvi01V3I6nXI6nS32AgDAjej0FXVQUJDuvvtuDRo0SIsXL9bAgQP14x//WDExMZLUZEV77tw5e/UbExOj+vp6VVZWtlhz9uzZJuc9f/68X82V56msrFRDQ0OTlTYAAB2p04P6SpZlyefzqXfv3oqJidGOHTvssfr6eu3evVtDhgyRJCUnJ6tLly5+NeXl5SorK7NrUlNT5fV6deDAAbtm//798nq9fjVlZWUqLy+3a4qKiuR0OpWcnHxTrxcAgJZ06lvfTzzxhMaNG6f4+HhdunRJhYWF2rVrlzwejxwOh+bMmaNFixapT58+6tOnjxYtWqRu3bopKytLkuRyuTRt2jTNmzdP3bt3V0REhHJzc9W/f3/7LvB+/fpp7Nixys7O1po1ayRJ06dPV0ZGhhISEiRJaWlpSkxMlNvt1pIlS3Tx4kXl5uYqOzv7qnd8AwDQETo1qM+ePSu3263y8nK5XC4NGDBAHo9HY8aMkSQ99thjqqur08yZM1VZWamUlBQVFRUpNDTUPsaKFSsUGBioyZMnq66uTqNGjdL69esVEBBg12zcuFE5OTn23eGZmZlatWqVPR4QEKDt27dr5syZGjp0qIKDg5WVlaWlS5d20EwAANC8Tg3qdevWtTjucDiUl5envLy8q9Z07dpV+fn5ys/Pv2pNRESECgoKWjxXz5499fLLL7dYAwBARzPuM2oAAPB/CGoAAAxGUAMAYDCCGgAAgxHUAAAYjKAGAMBgBDUAAAYjqAEAMBhBDQCAwQhqAAAMRlADAGAwghoAAIMR1AAAGIygBgDAYAQ1AAAGI6gBADAYQQ0AgMEIagAADEZQAwBgMIIaAACDEdQAABiMoAYAwGAENQAABiOoAQAwGEENAIDBCGoAAAxGUAMAYDCCGgAAgxHUAAAYjKAGAMBgBDUAAAYjqAEAMBhBDQCAwQhqAAAMRlADAGAwghoAAIMR1AAAGIygBgDAYAQ1AAAGI6gBADAYQQ0AgMEIagAADEZQAwBgsE4N6sWLF+u+++5TaGiooqKiNHHiRB0/ftyvZurUqXI4HH7b4MGD/Wp8Pp9mz56tyMhIhYSEKDMzU2fOnPGrqayslNvtlsvlksvlktvtVlVVlV/NqVOnNGHCBIWEhCgyMlI5OTmqr6+/ORcPAMB16NSg3r17tx555BHt27dPO3bs0Icffqi0tDTV1tb61Y0dO1bl5eX29sorr/iNz5kzR1u3blVhYaGKi4tVU1OjjIwMNTY22jVZWVkqLS2Vx+ORx+NRaWmp3G63Pd7Y2Kjx48ertrZWxcXFKiws1JYtWzRv3rybOwkAALQgsDNP7vF4/B4///zzioqKUklJib72ta/Z+51Op2JiYpo9htfr1bp167RhwwaNHj1aklRQUKD4+Hjt3LlT6enpOnbsmDwej/bt26eUlBRJ0tq1a5Wamqrjx48rISFBRUVFOnr0qE6fPq24uDhJ0rJlyzR16lQtXLhQYWFhN2MKAABokVGfUXu9XklSRESE3/5du3YpKipKffv2VXZ2ts6dO2ePlZSUqKGhQWlpafa+uLg4JSUlac+ePZKkvXv3yuVy2SEtSYMHD5bL5fKrSUpKskNaktLT0+Xz+VRSUtJsvz6fT9XV1X4bAADtyZigtixLc+fO1Ve+8hUlJSXZ+8eNG6eNGzfq9ddf17Jly3Tw4EGNHDlSPp9PklRRUaGgoCCFh4f7HS86OloVFRV2TVRUVJNzRkVF+dVER0f7jYeHhysoKMiuudLixYvtz7xdLpfi4+PbPgEAADSjU9/6/qRZs2bp7bffVnFxsd/+hx56yP45KSlJgwYNUq9evbR9+3ZNmjTpqsezLEsOh8N+/Mmfb6Tmk+bPn6+5c+faj6urqwlrAEC7MmJFPXv2bG3btk1vvPGGevTo0WJtbGysevXqpRMnTkiSYmJiVF9fr8rKSr+6c+fO2SvkmJgYnT17tsmxzp8/71dz5cq5srJSDQ0NTVbaH3M6nQoLC/PbAABoT50a1JZladasWXrxxRf1+uuvq3fv3td8zvvvv6/Tp08rNjZWkpScnKwuXbpox44ddk15ebnKyso0ZMgQSVJqaqq8Xq8OHDhg1+zfv19er9evpqysTOXl5XZNUVGRnE6nkpOT2+V6AQBorU596/uRRx7Rpk2b9Jvf/EahoaH2itblcik4OFg1NTXKy8vTgw8+qNjYWL333nt64oknFBkZqW984xt27bRp0zRv3jx1795dERERys3NVf/+/e27wPv166exY8cqOztba9askSRNnz5dGRkZSkhIkCSlpaUpMTFRbrdbS5Ys0cWLF5Wbm6vs7GxWygCATtOpK+rVq1fL6/Vq+PDhio2NtbfNmzdLkgICAnT48GE98MAD6tu3r6ZMmaK+fftq7969Cg0NtY+zYsUKTZw4UZMnT9bQoUPVrVs3/e///q8CAgLsmo0bN6p///5KS0tTWlqaBgwYoA0bNtjjAQEB2r59u7p27aqhQ4dq8uTJmjhxopYuXdpxEwIAwBU6dUVtWVaL48HBwXr11VeveZyuXbsqPz9f+fn5V62JiIhQQUFBi8fp2bOnXn755WueDwCAjmLEzWQAAKB5BDUAAAYjqAEAMBhBDQCAwQhqAAAMRlADAGAwghoAAIMR1AAAGIygBgDAYAQ1AAAGI6gBADAYQQ0AgMEIagAADEZQAwBgMIIaAACDEdQAABiMoAYAwGAENQAABiOoAQAwGEENAIDBCGoAAAxGUAMAYDCCGgAAgxHUAAAYjKAGAMBgBDUAAAYjqAEAMBhBDQCAwQhqAAAMRlADAGAwghoAAIMR1AAAGIygBgDAYAQ1AAAGI6gBADAYQQ0AgMHaFNR33XWX3n///Sb7q6qqdNddd91wUwAA4CNtCur33ntPjY2NTfb7fD797W9/u+GmAADARwJbU7xt2zb751dffVUul8t+3NjYqNdee0133nlnuzUHAMCtrlVBPXHiREmSw+HQlClT/Ma6dOmiO++8U8uWLWu/7gAAuMW1KqgvX74sSerdu7cOHjyoyMjIm9IUAAD4SKuC+mMnT55s7z4AAEAz2hTUkvTaa6/ptdde07lz5+yV9sd+/vOf33BjAACgjUH91FNP6Qc/+IEGDRqk2NhYORyO9u4LAACojb+e9dOf/lTr16/X/v379dJLL2nr1q1+2/VavHix7rvvPoWGhioqKkoTJ07U8ePH/Wosy1JeXp7i4uIUHBys4cOH68iRI341Pp9Ps2fPVmRkpEJCQpSZmakzZ8741VRWVsrtdsvlcsnlcsntdquqqsqv5tSpU5owYYJCQkIUGRmpnJwc1dfXt3J2AABoP20K6vr6eg0ZMuSGT75792498sgj2rdvn3bs2KEPP/xQaWlpqq2ttWueeeYZLV++XKtWrdLBgwcVExOjMWPG6NKlS3bNnDlztHXrVhUWFqq4uFg1NTXKyMjw+13vrKwslZaWyuPxyOPxqLS0VG632x5vbGzU+PHjVVtbq+LiYhUWFmrLli2aN2/eDV8nAABt1aa3vr/1rW9p06ZN+t73vndDJ/d4PH6Pn3/+eUVFRamkpERf+9rXZFmWVq5cqQULFmjSpEmSpBdeeEHR0dHatGmTZsyYIa/Xq3Xr1mnDhg0aPXq0JKmgoEDx8fHauXOn0tPTdezYMXk8Hu3bt08pKSmSpLVr1yo1NVXHjx9XQkKCioqKdPToUZ0+fVpxcXGSpGXLlmnq1KlauHChwsLCbuhaAQBoizYF9QcffKCf/exn2rlzpwYMGKAuXbr4jS9fvrxNzXi9XklSRESEpI/uLq+oqFBaWppd43Q6NWzYMO3Zs0czZsxQSUmJGhoa/Gri4uKUlJSkPXv2KD09XXv37pXL5bJDWpIGDx4sl8ulPXv2KCEhQXv37lVSUpId0pKUnp4un8+nkpISjRgxokm/Pp9PPp/PflxdXd2m6wYA4GraFNRvv/22vvjFL0qSysrK/MbaemOZZVmaO3euvvKVrygpKUmSVFFRIUmKjo72q42OjtZf//pXuyYoKEjh4eFNaj5+fkVFhaKiopqcMyoqyq/myvOEh4crKCjIrrnS4sWL9dRTT7X2UgEAuG5tCuo33nijvfvQrFmz9Pbbb6u4uLjJ2JXhb1nWNf9BcGVNc/Vtqfmk+fPna+7cufbj6upqxcfHt9gXAACtYcTXXM6ePVvbtm3TG2+8oR49etj7Y2JiJKnJivbcuXP26jcmJkb19fWqrKxssebs2bNNznv+/Hm/mivPU1lZqYaGhiYr7Y85nU6FhYX5bQAAtKc2BfWIESM0cuTIq27Xy7IszZo1Sy+++KJef/119e7d22+8d+/eiomJ0Y4dO+x99fX12r17t33XeXJysrp06eJXU15errKyMrsmNTVVXq9XBw4csGv2798vr9frV1NWVqby8nK7pqioSE6nU8nJya2YHQAA2k+b3vr++PPpjzU0NKi0tFRlZWVNvqyjJY888og2bdqk3/zmNwoNDbVXtC6XS8HBwXI4HJozZ44WLVqkPn36qE+fPlq0aJG6deumrKwsu3batGmaN2+eunfvroiICOXm5qp///72XeD9+vXT2LFjlZ2drTVr1kiSpk+froyMDCUkJEiS0tLSlJiYKLfbrSVLlujixYvKzc1VdnY2K2UAQKdpU1CvWLGi2f15eXmqqam57uOsXr1akjR8+HC//c8//7ymTp0qSXrsscdUV1enmTNnqrKyUikpKSoqKlJoaKhfP4GBgZo8ebLq6uo0atQorV+/XgEBAXbNxo0blZOTY98dnpmZqVWrVtnjAQEB2r59u2bOnKmhQ4cqODhYWVlZWrp06XVfDwAA7a3Nf+u7Of/xH/+h+++//7rDzbKsa9Y4HA7l5eUpLy/vqjVdu3ZVfn6+8vPzr1oTERGhgoKCFs/Vs2dPvfzyy9fsCQCAjtKuN5Pt3btXXbt2bc9DAgBwS2vTivrjvxL2McuyVF5erkOHDt3wXysDAAD/p01B7XK5/B7fdtttSkhI0A9+8AO/vxAGAABuTJuC+vnnn2/vPgAAQDNu6GaykpISHTt2TA6HQ4mJifrSl77UXn0BAAC1MajPnTunb37zm9q1a5c+97nPybIseb1ejRgxQoWFhbrjjjvau08AAG5Jbbrre/bs2aqurtaRI0d08eJFVVZWqqysTNXV1crJyWnvHgEAuGW1aUXt8Xi0c+dO9evXz96XmJio5557jpvJAABoR21aUV++fLnJd1BLUpcuXXT58uUbbgoAAHykTUE9cuRIPfroo/r73/9u7/vb3/6mb3/72xo1alS7NQcAwK2uTUG9atUqXbp0SXfeeae+8IUv6O6771bv3r116dKlFv+MJwAAaJ02fUYdHx+vP/zhD9qxY4feeecdWZalxMRE+9uqAABA+2jVivr1119XYmKiqqurJUljxozR7NmzlZOTo/vuu0/33nuv3nzzzZvSKAAAt6JWBfXKlSuv+v3MLpdLM2bM0PLly9utOQAAbnWtCuo//vGPGjt27FXH09LSVFJScsNNAQCAj7QqqM+ePdvsr2V9LDAwUOfPn7/hpgAAwEdaFdSf//zndfjw4auOv/3224qNjb3hpgAAwEdaFdRf//rX9f3vf18ffPBBk7G6ujo9+eSTysjIaLfmAAC41bXq17O++93v6sUXX1Tfvn01a9YsJSQkyOFw6NixY3ruuefU2NioBQsW3KxeAQC45bQqqKOjo7Vnzx7993//t+bPny/LsiRJDodD6enp+slPfqLo6Oib0igAALeiVv/Bk169eumVV15RZWWl/vznP8uyLPXp00fh4eE3oz8AAG5pbfrLZJIUHh6u++67rz17AQAAV2jT3/oGAAAdg6AGAMBgBDUAAAYjqAEAMBhBDQCAwQhqAAAMRlADAGAwghoAAIMR1AAAGIygBgDAYAQ1AAAGI6gBADAYQQ0AgMEIagAADEZQAwBgMIIaAACDEdQAABiMoAYAwGAENQAABiOoAQAwGEENAIDBCGoAAAzWqUH9u9/9ThMmTFBcXJwcDodeeuklv/GpU6fK4XD4bYMHD/ar8fl8mj17tiIjIxUSEqLMzEydOXPGr6ayslJut1sul0sul0tut1tVVVV+NadOndKECRMUEhKiyMhI5eTkqL6+/uZcOAAA16lTg7q2tlYDBw7UqlWrrlozduxYlZeX29srr7ziNz5nzhxt3bpVhYWFKi4uVk1NjTIyMtTY2GjXZGVlqbS0VB6PRx6PR6WlpXK73fZ4Y2Ojxo8fr9raWhUXF6uwsFBbtmzRvHnz2v+iAQBohcDOPPm4ceM0bty4FmucTqdiYmKaHfN6vVq3bp02bNig0aNHS5IKCgoUHx+vnTt3Kj09XceOHZPH49G+ffuUkpIiSVq7dq1SU1N1/PhxJSQkqKioSEePHtXp06cVFxcnSVq2bJmmTp2qhQsXKiwsrNnz+3w++Xw++3F1dXWr5wAAgJYY/xn1rl27FBUVpb59+yo7O1vnzp2zx0pKStTQ0KC0tDR7X1xcnJKSkrRnzx5J0t69e+VyueyQlqTBgwfL5XL51SQlJdkhLUnp6eny+XwqKSm5am+LFy+23053uVyKj49vt+sGAEAyPKjHjRunjRs36vXXX9eyZct08OBBjRw50l7FVlRUKCgoSOHh4X7Pi46OVkVFhV0TFRXV5NhRUVF+NdHR0X7j4eHhCgoKsmuaM3/+fHm9Xns7ffr0DV0vAABX6tS3vq/loYcesn9OSkrSoEGD1KtXL23fvl2TJk266vMsy5LD4bAff/LnG6m5ktPplNPpvOZ1AADQVkavqK8UGxurXr166cSJE5KkmJgY1dfXq7Ky0q/u3Llz9go5JiZGZ8+ebXKs8+fP+9VcuXKurKxUQ0NDk5U2AAAd6VMV1O+//75Onz6t2NhYSVJycrK6dOmiHTt22DXl5eUqKyvTkCFDJEmpqanyer06cOCAXbN//355vV6/mrKyMpWXl9s1RUVFcjqdSk5O7ohLAwCgWZ361ndNTY3+/Oc/249Pnjyp0tJSRUREKCIiQnl5eXrwwQcVGxur9957T0888YQiIyP1jW98Q5Lkcrk0bdo0zZs3T927d1dERIRyc3PVv39/+y7wfv36aezYscrOztaaNWskSdOnT1dGRoYSEhIkSWlpaUpMTJTb7daSJUt08eJF5ebmKjs7+6p3fAMA0BE6NagPHTqkESNG2I/nzp0rSZoyZYpWr16tw4cP6xe/+IWqqqoUGxurESNGaPPmzQoNDbWfs2LFCgUGBmry5Mmqq6vTqFGjtH79eiEwzTYAABa4SURBVAUEBNg1GzduVE5Ojn13eGZmpt/vbgcEBGj79u2aOXOmhg4dquDgYGVlZWnp0qU3ewoAAGhRpwb18OHDZVnWVcdfffXVax6ja9euys/PV35+/lVrIiIiVFBQ0OJxevbsqZdffvma5wMAoCN9qj6jBgDgVkNQAwBgMIIaAACDEdQAABiMoAYAwGAENQAABiOoAQAwGEENAIDBCGoAAAxGUAMAYDCCGgAAgxHUAAAYjKAGAMBgBDUAAAYjqAEAMBhBDQCAwQhqAAAMRlADAGAwghoAAIMR1AAAGIygBgDAYAQ1AAAGI6gBADAYQQ0AgMEIagAADEZQAwBgMIIaAACDEdQAABiMoAYAwGAENQAABiOoAQAwGEENAIDBCGoAAAxGUAMAYDCCGgAAgxHUAAAYjKAGAMBgBDUAAAYjqAEAMBhBDQCAwQhqAAAMRlADAGAwghoAAIMR1AAAGKxTg/p3v/udJkyYoLi4ODkcDr300kt+45ZlKS8vT3FxcQoODtbw4cN15MgRvxqfz6fZs2crMjJSISEhyszM1JkzZ/xqKisr5Xa75XK55HK55Ha7VVVV5Vdz6tQpTZgwQSEhIYqMjFROTo7q6+tvzoUDAHCdOjWoa2trNXDgQK1atarZ8WeeeUbLly/XqlWrdPDgQcXExGjMmDG6dOmSXTNnzhxt3bpVhYWFKi4uVk1NjTIyMtTY2GjXZGVlqbS0VB6PRx6PR6WlpXK73fZ4Y2Ojxo8fr9raWhUXF6uwsFBbtmzRvHnzbt7FAwBwHQI78+Tjxo3TuHHjmh2zLEsrV67UggULNGnSJEnSCy+8oOjoaG3atEkzZsyQ1+vVunXrtGHDBo0ePVqSVFBQoPj4eO3cuVPp6ek6duyYPB6P9u3bp5SUFEnS2rVrlZqaquPHjyshIUFFRUU6evSoTp8+rbi4OEnSsmXLNHXqVC1cuFBhYWHN9ujz+eTz+ezH1dXV7TY3AABIBn9GffLkSVVUVCgtLc3e53Q6NWzYMO3Zs0eSVFJSooaGBr+auLg4JSUl2TV79+6Vy+WyQ1qSBg8eLJfL5VeTlJRkh7Qkpaeny+fzqaSk5Ko9Ll682H473eVyKT4+vn0uHgCAfzI2qCsqKiRJ0dHRfvujo6PtsYqKCgUFBSk8PLzFmqioqCbHj4qK8qu58jzh4eEKCgqya5ozf/58eb1eezt9+nQrrxIAgJZ16lvf18PhcPg9tiyryb4rXVnTXH1baq7kdDrldDpb7AUAgBth7Io6JiZGkpqsaM+dO2evfmNiYlRfX6/KysoWa86ePdvk+OfPn/erufI8lZWVamhoaLLSBgCgIxkb1L1791ZMTIx27Nhh76uvr9fu3bs1ZMgQSVJycrK6dOniV1NeXq6ysjK7JjU1VV6vVwcOHLBr9u/fL6/X61dTVlam8vJyu6aoqEhOp1PJyck39ToBAGhJp771XVNToz//+c/245MnT6q0tFQRERHq2bOn5syZo0WLFqlPnz7q06ePFi1apG7duikrK0uS5HK5NG3aNM2bN0/du3dXRESEcnNz1b9/f/su8H79+mns2LHKzs7WmjVrJEnTp09XRkaGEhISJElpaWlKTEyU2+3WkiVLdPHiReXm5io7O/uqd3wDANAROjWoDx06pBEjRtiP586dK0maMmWK1q9fr8cee0x1dXWaOXOmKisrlZKSoqKiIoWGhtrPWbFihQIDAzV58mTV1dVp1KhRWr9+vQICAuyajRs3Kicnx747PDMz0+93twMCArR9+3bNnDlTQ4cOVXBwsLKysrR06dKbPQUAALSoU4N6+PDhsizrquMOh0N5eXnKy8u7ak3Xrl2Vn5+v/Pz8q9ZERESooKCgxV569uypl19++Zo9AwDQkYz9jBoAABDUAAAYjaAGAMBgBDUAAAYjqAEAMBhBDQCAwQhqAAAMRlADAGAwghoAAIMR1AAAGIygBgDAYAQ1AAAGI6gBADAYQQ0AgMEIagAADEZQAwBgMIIaAACDEdQAABiMoAYAwGAENQAABiOoAQAwGEENAIDBCGoAAAxGUAMAYDCCGgAAgxHUAAAYjKAGAMBgBDUAAAYjqAEAMBhBDQCAwQhqAAAMRlADAGAwghoAAIMR1AAAGIygBgDAYAQ1AAAGI6gBADAYQQ0AgMEIagAADEZQAwBgMIIaAACDEdQAABiMoAYAwGBGB3VeXp4cDoffFhMTY49blqW8vDzFxcUpODhYw4cP15EjR/yO4fP5NHv2bEVGRiokJESZmZk6c+aMX01lZaXcbrdcLpdcLpfcbreqqqo65BoBAGiJ0UEtSffee6/Ky8vt7fDhw/bYM888o+XLl2vVqlU6ePCgYmJiNGbMGF26dMmumTNnjrZu3arCwkIVFxerpqZGGRkZamxstGuysrJUWloqj8cjj8ej0tJSud3uDr1OAACaE9jZDVxLYGCg3yr6Y5ZlaeXKlVqwYIEmTZokSXrhhRcUHR2tTZs2acaMGfJ6vVq3bp02bNig0aNHS5IKCgoUHx+vnTt3Kj09XceOHZPH49G+ffuUkpIiSVq7dq1SU1N1/PhxJSQkdNzFAgBwBeNX1CdOnFBcXJx69+6tb37zm3r33XclSSdPnlRFRYXS0tLsWqfTqWHDhmnPnj2SpJKSEjU0NPjVxMXFKSkpya7Zu3evXC6XHdKSNHjwYLlcLrvmanw+n6qrq/02AADak9FBnZKSol/84hd69dVXtXbtWlVUVGjIkCF6//33VVFRIUmKjo72e050dLQ9VlFRoaCgIIWHh7dYExUV1eTcUVFRds3VLF682P5c2+VyKT4+vs3XCgBAc4wO6nHjxunBBx9U//79NXr0aG3fvl3SR29xf8zhcPg9x7KsJvuudGVNc/XXc5z58+fL6/Xa2+nTp695TQAAtIbRQX2lkJAQ9e/fXydOnLA/t75y1Xvu3Dl7lR0TE6P6+npVVla2WHP27Nkm5zp//nyT1fqVnE6nwsLC/DYAANrTpyqofT6fjh07ptjYWPXu3VsxMTHasWOHPV5fX6/du3dryJAhkqTk5GR16dLFr6a8vFxlZWV2TWpqqrxerw4cOGDX7N+/X16v164BAKCzGH3Xd25uriZMmKCePXvq3Llz+tGPfqTq6mpNmTJFDodDc+bM0aJFi9SnTx/16dNHixYtUrdu3ZSVlSVJcrlcmjZtmubNm6fu3bsrIiJCubm59lvpktSvXz+NHTtW2dnZWrNmjSRp+vTpysjI4I5vAECnMzqoz5w5o3/7t3/ThQsXdMcdd2jw4MHat2+fevXqJUl67LHHVFdXp5kzZ6qyslIpKSkqKipSaGiofYwVK1YoMDBQkydPVl1dnUaNGqX169crICDArtm4caNycnLsu8MzMzO1atWqjr1YAACaYXRQFxYWtjjucDiUl5envLy8q9Z07dpV+fn5ys/Pv2pNRESECgoK2tomAAA3zafqM2oAAG41BDUAAAYjqAEAMBhBDQCAwQhqAAAMRlADAGAwghoAAIMR1AAAGIygBgDAYAQ1AAAGI6gBADAYQQ0AgMEIagAADEZQAwBgMIIaAACDEdQAABiMoAYAwGAENQAABiOoAQAwGEENAIDBCGoAAAxGUAMAYDCCGgAAgxHUAAAYjKAGAMBgBDUAAAYjqAEAMBhBDQCAwQhqAAAMRlADAGAwghoAAIMR1AAAGIygBgDAYAQ1AAAGI6gBADAYQQ0AgMEIagAADEZQAwBgMIIaAACDEdQAABiMoAYAwGAENQAABiOoAQAwGEENAIDBCOor/OQnP1Hv3r3VtWtXJScn68033+zslgAAtzCC+hM2b96sOXPmaMGCBXrrrbf01a9+VePGjdOpU6c6uzUAwC2KoP6E5cuXa9q0afrWt76lfv36aeXKlYqPj9fq1as7uzUAwC0qsLMbMEV9fb1KSkr0+OOP++1PS0vTnj17mn2Oz+eTz+ezH3u9XklSdXX1DfVSU1MjSbr41+P60FfXpmNUV3z0LkBJSYl9vLa47bbbdPny5TY//7N2DJN64Rjm9sIxzOzl+PHjktrntbWmpuaGX+slKTQ0VA6Ho+UiC5ZlWdbf/vY3S5L1+9//3m//woULrb59+zb7nCeffNKSxMbGxsbG1qbN6/VeM59YUV/hyn/ZWJZ11X/tzJ8/X3PnzrUfX758WRcvXlT37t2v/S+kFlRXVys+Pl6nT59WWFhYm4/zWcX8tIz5aRnz0zLmp2XtPT+hoaHXrCGo/ykyMlIBAQGqqKjw23/u3DlFR0c3+xyn0ymn0+m373Of+1y79RQWFsb/KC1gflrG/LSM+WkZ89Oyjpwfbib7p6CgICUnJ2vHjh1++3fs2KEhQ4Z0UlcAgFsdK+pPmDt3rtxutwYNGqTU1FT97Gc/06lTp/Twww93dmsAgFtUQF5eXl5nN2GKpKQkde/eXYsWLdLSpUtVV1enDRs2aODAgR3eS0BAgIYPH67AQP4t1Rzmp2XMT8uYn5YxPy3r6PlxWJZldciZAABAq/EZNQAABiOoAQAwGEENAIDBCGoAAAxGUHeC1n6V5u7du5WcnKyuXbvqrrvu0k9/+tMO6rTztGaOXnzxRY0ZM0Z33HGHwsLClJqaqldffbUDu+14bf061t///vcKDAzUF7/4xZvcYedq7fz4fD4tWLBAvXr1ktPp1Be+8AX9/Oc/76BuO15r52fjxo0aOHCgunXrptjYWP3nf/6n3n///Q7qtuP87ne/04QJExQXFyeHw6GXXnrpms/pkNfnG/8r2WiNwsJCq0uXLtbatWuto0ePWo8++qgVEhJi/fWvf222/t1337W6detmPfroo9bRo0ettWvXWl26dLF+/etfd3DnHae1c/Too49a//M//2MdOHDA+tOf/mTNnz/f6tKli/WHP/yhgzvvGK2dn49VVVVZd911l5WWlmYNHDiwg7rteG2Zn8zMTCslJcXasWOHdfLkSWv//v1N/u7/Z0Vr5+fNN9+0brvtNuvHP/6x9e6771pvvvmmde+991oTJ07s4M5vvldeecVasGCBtWXLFkuStXXr1hbrO+r1maDuYPfff7/18MMP++275557rMcff7zZ+scee8y65557/PbNmDHDGjx48E3rsbO1do6ak5iYaD311FPt3ZoR2jo/Dz30kPXd737XevLJJz/TQd3a+fntb39ruVwu6/333++I9jpda+dnyZIl1l133eW379lnn7V69Ohx03o0wfUEdUe9PvPWdwf6+Ks009LS/Pa39FWae/fubVKfnp6uQ4cOqaGh4ab12lnaMkdXunz5si5duqSIiIib0WKnauv8PP/88/rLX/6iJ5988ma32KnaMj/btm3ToEGD9Mwzz+jzn/+8+vbtq9zcXNXVte1rEE3WlvkZMmSIzpw5o1deeUWWZens2bP69a9/rfHjx3dEy0brqNdn/uxMB7pw4YIaGxubfMlHdHR0ky8D+VhFRUWz9R9++KEuXLig2NjYm9ZvZ2jLHF1p2bJlqq2t1eTJk29Gi52qLfNz4sQJPf7443rzzTc/839pqi3z8+6776q4uFhdu3bV1q1bdeHCBc2cOVMXL178zH1O3Zb5GTJkiDZu3KiHHnpIH3zwgT788ENlZmYqPz+/I1o2Wke9PrOi7gSt+SrNq9U3t/+zpLVz9LFf/vKXysvL0+bNmxUVFXWz2ut01zs/jY2NysrK0lNPPaW+fft2VHudrjX//Vy+fFkOh0MbN27U/fffr69//etavny51q9f/5lcVUutm5+jR48qJydH3//+91VSUiKPx6OTJ0/yHQj/1BGvz5/tf14bpi1fpRkTE9NsfWBgoLp3737Teu0sbZmjj23evFnTpk3Tr371K40ePfpmttlpWjs/ly5d0qFDh/TWW29p1qxZkj4KJsuyFBgYqKKiIo0cObJDeu8IbfnvJzY2Vp///Oflcrnsff369ZNlWTpz5oz69OlzU3vuSG2Zn8WLF2vo0KH6zne+I0kaMGCAQkJC9NWvflU/+tGPPnPv6rVGR70+s6LuQG35Ks3U1NQm9UVFRRo0aJC6dOly03rtLG39utFf/vKXmjp1qjZt2vSZ/uystfMTFhamw4cPq7S01N4efvhhJSQkqLS0VCkpKR3Veodoy38/Q4cO1d///nfV1NTY+/70pz/ptttuU48ePW5qvx2tLfPzj3/8Q7fd5h8VAQEBkv5v9Xir6rDX53a9NQ3X9PGvRqxbt846evSoNWfOHCskJMR67733LMuyrMcff9xyu912/ce3/3/729+2jh49aq1bt+6W+fWs652jTZs2WYGBgdZzzz1nlZeX21tVVVVnXcJN1dr5udJn/a7v1s7PpUuXrB49elj/8i//Yh05csTavXu31adPH+tb3/pWZ13CTdXa+Xn++eetwMBA6yc/+Yn1l7/8xSouLrYGDRpk3X///Z11CTfNpUuXrLfeest66623LEnW8uXLrbfeesv+1bXOen0mqDvBc889Z/Xq1csKCgqyvvzlL1u7d++2x6ZMmWINGzbMr37Xrl3Wl770JSsoKMi68847rdWrV3dwxx2vNXM0bNgwS1KTbcqUKR3feAdp7X9Dn/RZD2rLav38HDt2zBo9erQVHBxs9ejRw5o7d671j3/8o4O77jitnZ9nn33WSkxMtIKDg63Y2Fjr3//9360zZ850cNc33xtvvNHia0lnvT7zNZcAABiMz6gBADAYQQ0AgMEIagAADEZQAwBgMIIaAACDEdQAABiMoAYAwGAENQAABiOoAVzT8OHDNWfOnOuq3bVrlxwOh6qqqm7onHfeeadWrlx5Q8cAPgsIagAADEZQAwBgMIIaQKsUFBRo0KBBCg0NVUxMjLKysnTu3Lkmdb///e81cOBAde3aVSkpKTp8+LDf+J49e/S1r31NwcHBio+PV05OjmprazvqMoBPDYIaQKvU19frhz/8of74xz/qpZde0smTJzV16tQmdd/5zne0dOlSHTx4UFFRUcrMzFRDQ4Mk6fDhw0pPT9ekSZP09ttva/PmzSouLtasWbM6+GoA8wV2dgMAPl3+67/+y/75rrvu0rPPPqv7779fNTU1uv322+2xJ598UmPGjJEkvfDCC+rRo4e2bt2qyZMna8mSJcrKyrJvUOvTp4+effZZDRs2TKtXr1bXrl079qIAg7GiBtAqb731lh544AH16tVLoaGhGj58uCTp1KlTfnWpqan2zxEREUpISNCxY8ckSSUlJVq/fr1uv/12e0tPT9fly5d18uTJDrsW4NOAFTWA61ZbW6u0tDSlpaWpoKBAd9xxh06dOqX09HTV19df8/kOh0OSdPnyZc2YMUM5OTlNanr27NnufQOfZgQ1gOv2zjvv6MKFC3r66acVHx8vSTp06FCztfv27bNDt7KyUn/60590zz33SJK+/OUv68iRI7r77rs7pnHgU4y3vgFct549eyooKEj5+fl69913tW3bNv3whz9stvYHP/iBXnvtNZWVlWnq1KmKjIzUxIkTJUn/7//9P+3du1ePPPKISktLdeLECW3btk2zZ8/uyMsBPhUIagDX7Y477tD69ev1q1/9SomJiXr66ae1dOnSZmuffvppPfroo0pOTlZ5ebm2bdumoKAgSdKAAQO0e/dunThxQl/96lf1pS99Sd/73vcUGxvbkZcDfCo4LMuyOrsJAADQPFbUAAAYjKAGAMBgBDUAAAYjqAEAMBhBDQCAwQhqAAAMRlADAGAwghoAAIMR1AAAGIygBgDAYAQ1AAAG+//tuf25rueDMwAAAABJRU5ErkJggg==",
      "text/plain": [
       "<Figure size 500x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.displot(df, x='label')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Index: 71537 entries, 0 to 72133\n",
      "Data columns (total 4 columns):\n",
      " #   Column      Non-Null Count  Dtype \n",
      "---  ------      --------------  ----- \n",
      " 0   Unnamed: 0  71537 non-null  int64 \n",
      " 1   title       71537 non-null  object\n",
      " 2   text        71537 non-null  object\n",
      " 3   label       71537 non-null  int64 \n",
      "dtypes: int64(2), object(2)\n",
      "memory usage: 2.7+ MB\n"
     ]
    }
   ],
   "source": [
    "df = df.dropna()\n",
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.FacetGrid at 0x1a4040c9fd0>"
      ]
     },
     "execution_count": 87,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 500x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.displot(df, x='label')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "def removeStopwordsAndLower(text):\n",
    "    stop_words = set(stopwords.words('english')) \n",
    "    words = text.lower().split() \n",
    "    filtered_words = [word for word in words if word not in stop_words] \n",
    "    return ' '.join(filtered_words)\n",
    "def lemaAndStem(text):\n",
    "    stemmer = SnowballStemmer(\"english\")\n",
    "    # wnl = WordNetLemmatizer()\n",
    "    normalized_text = []\n",
    "    for word in text.split():\n",
    "        stemmed_word = stemmer.stem(word)\n",
    "        normalized_text.append(stemmed_word)\n",
    "    return ' '.join(normalized_text).replace(',', '')\n",
    "\n",
    "df['text'] = df['text'].apply(removeStopwordsAndLower)\n",
    "df['title'] = df['title'].apply(removeStopwordsAndLower)\n",
    "df['text'] = df['text'].apply(lemaAndStem)\n",
    "df['title'] = df['title'].apply(lemaAndStem)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 106,
   "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>Unnamed: 0</th>\n",
       "      <th>title</th>\n",
       "      <th>text</th>\n",
       "      <th>label</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>law enforc high alert follow threat cop white ...</td>\n",
       "      <td>comment expect barack obama member #fyf911 #fu...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>unbelievable! obama attorney general say charl...</td>\n",
       "      <td>demonstr gather last night exerci constitut pr...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>bobbi jindal rai hindu use stori christian con...</td>\n",
       "      <td>dozen polit activ pastor came privat dinner fr...</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4</td>\n",
       "      <td>satan 2: russia unv imag terrifi new supernuk ...</td>\n",
       "      <td>rs-28 sarmat missil dub satan 2 replac ss-18 f...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>5</td>\n",
       "      <td>time! christian group sue amazon splc design h...</td>\n",
       "      <td>say one time someon su southern poverti law ce...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>72129</th>\n",
       "      <td>72129</td>\n",
       "      <td>russian steal research trump hack u.s. democra...</td>\n",
       "      <td>washington (reuters) - hacker believ work russ...</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>72130</th>\n",
       "      <td>72130</td>\n",
       "      <td>watch: giuliani demand democrat apolog trump r...</td>\n",
       "      <td>know fantasyland republican never question cit...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>72131</th>\n",
       "      <td>72131</td>\n",
       "      <td>migrant refus leav train refug camp hungari</td>\n",
       "      <td>migrant refus leav train refug camp hungari th...</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>72132</th>\n",
       "      <td>72132</td>\n",
       "      <td>trump tussl give unpopular mexican leader much...</td>\n",
       "      <td>mexico citi (reuters) - donald trump combat st...</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>72133</th>\n",
       "      <td>72133</td>\n",
       "      <td>goldman sach endor hillari clinton presid</td>\n",
       "      <td>goldman sach endor hillari clinton presid gold...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>71537 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       Unnamed: 0                                              title  \\\n",
       "0               0  law enforc high alert follow threat cop white ...   \n",
       "2               2  unbelievable! obama attorney general say charl...   \n",
       "3               3  bobbi jindal rai hindu use stori christian con...   \n",
       "4               4  satan 2: russia unv imag terrifi new supernuk ...   \n",
       "5               5  time! christian group sue amazon splc design h...   \n",
       "...           ...                                                ...   \n",
       "72129       72129  russian steal research trump hack u.s. democra...   \n",
       "72130       72130  watch: giuliani demand democrat apolog trump r...   \n",
       "72131       72131        migrant refus leav train refug camp hungari   \n",
       "72132       72132  trump tussl give unpopular mexican leader much...   \n",
       "72133       72133          goldman sach endor hillari clinton presid   \n",
       "\n",
       "                                                    text  label  \n",
       "0      comment expect barack obama member #fyf911 #fu...      1  \n",
       "2      demonstr gather last night exerci constitut pr...      1  \n",
       "3      dozen polit activ pastor came privat dinner fr...      0  \n",
       "4      rs-28 sarmat missil dub satan 2 replac ss-18 f...      1  \n",
       "5      say one time someon su southern poverti law ce...      1  \n",
       "...                                                  ...    ...  \n",
       "72129  washington (reuters) - hacker believ work russ...      0  \n",
       "72130  know fantasyland republican never question cit...      1  \n",
       "72131  migrant refus leav train refug camp hungari th...      0  \n",
       "72132  mexico citi (reuters) - donald trump combat st...      0  \n",
       "72133  goldman sach endor hillari clinton presid gold...      1  \n",
       "\n",
       "[71537 rows x 4 columns]"
      ]
     },
     "execution_count": 106,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 107,
   "metadata": {},
   "outputs": [],
   "source": [
    "x = df[['text', 'title']]\n",
    "y = df['label']\n",
    "X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.2, stratify=y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 108,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Frecuencia')"
      ]
     },
     "execution_count": 108,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "words = []\n",
    "for text in df[df.label == 1]['text']:\n",
    "    words.extend(text.split())\n",
    "word_count = collections.Counter(words)\n",
    "top_words = dict(word_count.most_common(10))\n",
    "\n",
    "\n",
    "plt.bar(range(len(top_words)), list(top_words.values()), align = 'center')\n",
    "\n",
    "plt.xticks(range(len(top_words)), list(top_words.keys()))\n",
    "\n",
    "plt.grid(alpha = 0.5)\n",
    "\n",
    "plt.title('Palabras mas usadas', fontsize = 18)\n",
    "plt.xlabel('Palabra')\n",
    "plt.ylabel('Frecuencia')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 109,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Frecuencia')"
      ]
     },
     "execution_count": 109,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "words = []\n",
    "for text in df[df.label == 0]['text']:\n",
    "    words.extend(text.split())\n",
    "word_count = collections.Counter(words)\n",
    "top_words = dict(word_count.most_common(10))\n",
    "\n",
    "\n",
    "plt.bar(range(len(top_words)), list(top_words.values()), align = 'center')\n",
    "\n",
    "plt.xticks(range(len(top_words)), list(top_words.keys()))\n",
    "\n",
    "plt.grid(alpha = 0.5)\n",
    "\n",
    "plt.title('Palabras mas usadas', fontsize = 18)\n",
    "plt.xlabel('Palabra')\n",
    "plt.ylabel('Frecuencia')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 110,
   "metadata": {},
   "outputs": [],
   "source": [
    "count_vect = CountVectorizer()\n",
    "# transformer = make_column_transformer((count_vect, 'col 1'), (vectorizer, 'col 2'))\n",
    "\n",
    "# Define the CountVectorizer and TfidfTransformer separately for each column\n",
    "count_vect_text = CountVectorizer()\n",
    "count_vect_title = CountVectorizer()\n",
    "\n",
    "tfidf_transformer_text = TfidfTransformer(use_idf=False)\n",
    "tfidf_transformer_title = TfidfTransformer(use_idf=False)\n",
    "\n",
    "# Define the pipeline for each column\n",
    "text_pipeline = Pipeline([\n",
    "    ('count_vect_text', count_vect_text),\n",
    "    ('tfidf_transformer_text', tfidf_transformer_text)\n",
    "])\n",
    "\n",
    "title_pipeline = Pipeline([\n",
    "    ('count_vect_title', count_vect_title),\n",
    "    ('tfidf_transformer_title', tfidf_transformer_title)\n",
    "])\n",
    "\n",
    "# Use ColumnTransformer to apply the pipeline to each column\n",
    "preprocessor = ColumnTransformer(\n",
    "    transformers=[\n",
    "        ('text', text_pipeline, 'text'),\n",
    "        ('title', title_pipeline, 'title')\n",
    "    ]\n",
    ")\n",
    "\n",
    "# Fit and transform the data\n",
    "X_train_transformed = preprocessor.fit_transform(X_train)\n",
    "X_test_transformed = preprocessor.transform(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 169,
   "metadata": {},
   "outputs": [],
   "source": [
    "# pickle.dump(vcModel, open('transformModel_vcModel.pkl', 'wb'))\n",
    "# pickle.dump(tf_transformer, open('transformModel_tf_transformer.pkl', 'wb'))\n",
    "preprocessorFile = 'preprocessor.pkl'\n",
    "pickle.dump(preprocessor, open(preprocessorFile, 'wb'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 111,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-2 {color: black;}#sk-container-id-2 pre{padding: 0;}#sk-container-id-2 div.sk-toggleable {background-color: white;}#sk-container-id-2 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-2 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-2 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-2 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-2 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-2 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-2 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-2 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-2 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-2 div.sk-item {position: relative;z-index: 1;}#sk-container-id-2 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-2 div.sk-item::before, #sk-container-id-2 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-2 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-2 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-2 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-2 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-2 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-2 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-2 div.sk-label-container {text-align: center;}#sk-container-id-2 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-2 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomizedSearchCV(cv=2,\n",
       "                   estimator=XGBClassifier(base_score=None, booster=None,\n",
       "                                           callbacks=None,\n",
       "                                           colsample_bylevel=None,\n",
       "                                           colsample_bynode=None,\n",
       "                                           colsample_bytree=None, device=None,\n",
       "                                           early_stopping_rounds=None,\n",
       "                                           enable_categorical=False,\n",
       "                                           eval_metric=None, feature_types=None,\n",
       "                                           gamma=None, grow_policy=None,\n",
       "                                           importance_type=None,\n",
       "                                           interaction_constraints=None,\n",
       "                                           learning_rate...\n",
       "                                           max_cat_threshold=None,\n",
       "                                           max_cat_to_onehot=None,\n",
       "                                           max_delta_step=None, max_depth=None,\n",
       "                                           max_leaves=None,\n",
       "                                           min_child_weight=None, missing=nan,\n",
       "                                           monotone_constraints=None,\n",
       "                                           multi_strategy=None,\n",
       "                                           n_estimators=None, n_jobs=None,\n",
       "                                           num_parallel_tree=None,\n",
       "                                           random_state=None, ...),\n",
       "                   param_distributions={&#x27;learning_rate&#x27;: [1, 0.5, 0.1, 0.05],\n",
       "                                        &#x27;max_depth&#x27;: [3, 6, 8, 10],\n",
       "                                        &#x27;n_estimators&#x27;: [150, 200, 250]})</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" ><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomizedSearchCV</label><div class=\"sk-toggleable__content\"><pre>RandomizedSearchCV(cv=2,\n",
       "                   estimator=XGBClassifier(base_score=None, booster=None,\n",
       "                                           callbacks=None,\n",
       "                                           colsample_bylevel=None,\n",
       "                                           colsample_bynode=None,\n",
       "                                           colsample_bytree=None, device=None,\n",
       "                                           early_stopping_rounds=None,\n",
       "                                           enable_categorical=False,\n",
       "                                           eval_metric=None, feature_types=None,\n",
       "                                           gamma=None, grow_policy=None,\n",
       "                                           importance_type=None,\n",
       "                                           interaction_constraints=None,\n",
       "                                           learning_rate...\n",
       "                                           max_cat_threshold=None,\n",
       "                                           max_cat_to_onehot=None,\n",
       "                                           max_delta_step=None, max_depth=None,\n",
       "                                           max_leaves=None,\n",
       "                                           min_child_weight=None, missing=nan,\n",
       "                                           monotone_constraints=None,\n",
       "                                           multi_strategy=None,\n",
       "                                           n_estimators=None, n_jobs=None,\n",
       "                                           num_parallel_tree=None,\n",
       "                                           random_state=None, ...),\n",
       "                   param_distributions={&#x27;learning_rate&#x27;: [1, 0.5, 0.1, 0.05],\n",
       "                                        &#x27;max_depth&#x27;: [3, 6, 8, 10],\n",
       "                                        &#x27;n_estimators&#x27;: [150, 200, 250]})</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" ><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">estimator: XGBClassifier</label><div class=\"sk-toggleable__content\"><pre>XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
       "              colsample_bylevel=None, colsample_bynode=None,\n",
       "              colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
       "              enable_categorical=False, eval_metric=None, feature_types=None,\n",
       "              gamma=None, grow_policy=None, importance_type=None,\n",
       "              interaction_constraints=None, learning_rate=None, max_bin=None,\n",
       "              max_cat_threshold=None, max_cat_to_onehot=None,\n",
       "              max_delta_step=None, max_depth=None, max_leaves=None,\n",
       "              min_child_weight=None, missing=nan, monotone_constraints=None,\n",
       "              multi_strategy=None, n_estimators=None, n_jobs=None,\n",
       "              num_parallel_tree=None, random_state=None, ...)</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-4\" type=\"checkbox\" ><label for=\"sk-estimator-id-4\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">XGBClassifier</label><div class=\"sk-toggleable__content\"><pre>XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
       "              colsample_bylevel=None, colsample_bynode=None,\n",
       "              colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
       "              enable_categorical=False, eval_metric=None, feature_types=None,\n",
       "              gamma=None, grow_policy=None, importance_type=None,\n",
       "              interaction_constraints=None, learning_rate=None, max_bin=None,\n",
       "              max_cat_threshold=None, max_cat_to_onehot=None,\n",
       "              max_delta_step=None, max_depth=None, max_leaves=None,\n",
       "              min_child_weight=None, missing=nan, monotone_constraints=None,\n",
       "              multi_strategy=None, n_estimators=None, n_jobs=None,\n",
       "              num_parallel_tree=None, random_state=None, ...)</pre></div></div></div></div></div></div></div></div></div></div>"
      ],
      "text/plain": [
       "RandomizedSearchCV(cv=2,\n",
       "                   estimator=XGBClassifier(base_score=None, booster=None,\n",
       "                                           callbacks=None,\n",
       "                                           colsample_bylevel=None,\n",
       "                                           colsample_bynode=None,\n",
       "                                           colsample_bytree=None, device=None,\n",
       "                                           early_stopping_rounds=None,\n",
       "                                           enable_categorical=False,\n",
       "                                           eval_metric=None, feature_types=None,\n",
       "                                           gamma=None, grow_policy=None,\n",
       "                                           importance_type=None,\n",
       "                                           interaction_constraints=None,\n",
       "                                           learning_rate...\n",
       "                                           max_cat_threshold=None,\n",
       "                                           max_cat_to_onehot=None,\n",
       "                                           max_delta_step=None, max_depth=None,\n",
       "                                           max_leaves=None,\n",
       "                                           min_child_weight=None, missing=nan,\n",
       "                                           monotone_constraints=None,\n",
       "                                           multi_strategy=None,\n",
       "                                           n_estimators=None, n_jobs=None,\n",
       "                                           num_parallel_tree=None,\n",
       "                                           random_state=None, ...),\n",
       "                   param_distributions={'learning_rate': [1, 0.5, 0.1, 0.05],\n",
       "                                        'max_depth': [3, 6, 8, 10],\n",
       "                                        'n_estimators': [150, 200, 250]})"
      ]
     },
     "execution_count": 111,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "parameters = {\n",
    "    'learning_rate':[1, 0.5, 0.1, 0.05], \n",
    "    'n_estimators': [150, 200, 250],\n",
    "    'max_depth': [3, 6, 8, 10]\n",
    "}\n",
    "brt = XGBClassifier()\n",
    "clf = RandomizedSearchCV(estimator=brt, param_distributions=parameters, cv= 2)\n",
    "clf.fit(X_train_transformed, y_train)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 113,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-3 {color: black;}#sk-container-id-3 pre{padding: 0;}#sk-container-id-3 div.sk-toggleable {background-color: white;}#sk-container-id-3 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-3 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-3 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-3 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-3 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-3 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-3 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-3 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-3 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-3 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-3 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-3 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-3 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-3 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-3 div.sk-item {position: relative;z-index: 1;}#sk-container-id-3 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-3 div.sk-item::before, #sk-container-id-3 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-3 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-3 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-3 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-3 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-3 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-3 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-3 div.sk-label-container {text-align: center;}#sk-container-id-3 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-3 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-3\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomizedSearchCV(cv=2, estimator=RandomForestClassifier(),\n",
       "                   param_distributions={&#x27;criterion&#x27;: [&#x27;gini&#x27;, &#x27;entropy&#x27;,\n",
       "                                                      &#x27;log_loss&#x27;],\n",
       "                                        &#x27;max_depth&#x27;: [None, 4, 6, 10],\n",
       "                                        &#x27;n_estimators&#x27;: [100, 150, 200, 250]})</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-5\" type=\"checkbox\" ><label for=\"sk-estimator-id-5\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomizedSearchCV</label><div class=\"sk-toggleable__content\"><pre>RandomizedSearchCV(cv=2, estimator=RandomForestClassifier(),\n",
       "                   param_distributions={&#x27;criterion&#x27;: [&#x27;gini&#x27;, &#x27;entropy&#x27;,\n",
       "                                                      &#x27;log_loss&#x27;],\n",
       "                                        &#x27;max_depth&#x27;: [None, 4, 6, 10],\n",
       "                                        &#x27;n_estimators&#x27;: [100, 150, 200, 250]})</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-6\" type=\"checkbox\" ><label for=\"sk-estimator-id-6\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">estimator: RandomForestClassifier</label><div class=\"sk-toggleable__content\"><pre>RandomForestClassifier()</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-7\" type=\"checkbox\" ><label for=\"sk-estimator-id-7\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestClassifier</label><div class=\"sk-toggleable__content\"><pre>RandomForestClassifier()</pre></div></div></div></div></div></div></div></div></div></div>"
      ],
      "text/plain": [
       "RandomizedSearchCV(cv=2, estimator=RandomForestClassifier(),\n",
       "                   param_distributions={'criterion': ['gini', 'entropy',\n",
       "                                                      'log_loss'],\n",
       "                                        'max_depth': [None, 4, 6, 10],\n",
       "                                        'n_estimators': [100, 150, 200, 250]})"
      ]
     },
     "execution_count": 113,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "parameters2 = {\n",
    "    'criterion':['gini', 'entropy', 'log_loss'], \n",
    "    'n_estimators': [100, 150, 200, 250],\n",
    "    'max_depth': [None, 4, 6, 10]\n",
    "}\n",
    "brt2 = RandomForestClassifier()\n",
    "clf2 = RandomizedSearchCV(estimator=brt2, param_distributions=parameters2, cv= 2)\n",
    "clf2.fit(X_train_transformed, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 116,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "XGBoost best params:       {'n_estimators': 150, 'max_depth': 8, 'learning_rate': 0.5}\n",
      "Random Forets best params: {'n_estimators': 250, 'max_depth': None, 'criterion': 'gini'}\n"
     ]
    }
   ],
   "source": [
    "print('XGBoost best params:      ' ,clf.best_params_)\n",
    "print('Random Forets best params:' ,clf2.best_params_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 117,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-4 {color: black;}#sk-container-id-4 pre{padding: 0;}#sk-container-id-4 div.sk-toggleable {background-color: white;}#sk-container-id-4 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-4 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-4 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-4 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-4 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-4 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-4 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-4 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-4 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-4 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-4 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-4 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-4 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-4 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-4 div.sk-item {position: relative;z-index: 1;}#sk-container-id-4 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-4 div.sk-item::before, #sk-container-id-4 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-4 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-4 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-4 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-4 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-4 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-4 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-4 div.sk-label-container {text-align: center;}#sk-container-id-4 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-4 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-4\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
       "              colsample_bylevel=None, colsample_bynode=None,\n",
       "              colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
       "              enable_categorical=False, eval_metric=None, feature_types=None,\n",
       "              gamma=None, grow_policy=None, importance_type=None,\n",
       "              interaction_constraints=None, learning_rate=0.5, max_bin=None,\n",
       "              max_cat_threshold=None, max_cat_to_onehot=None,\n",
       "              max_delta_step=None, max_depth=8, max_leaves=None,\n",
       "              min_child_weight=None, missing=nan, monotone_constraints=None,\n",
       "              multi_strategy=None, n_estimators=150, n_jobs=None,\n",
       "              num_parallel_tree=None, random_state=None, ...)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-8\" type=\"checkbox\" checked><label for=\"sk-estimator-id-8\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">XGBClassifier</label><div class=\"sk-toggleable__content\"><pre>XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
       "              colsample_bylevel=None, colsample_bynode=None,\n",
       "              colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
       "              enable_categorical=False, eval_metric=None, feature_types=None,\n",
       "              gamma=None, grow_policy=None, importance_type=None,\n",
       "              interaction_constraints=None, learning_rate=0.5, max_bin=None,\n",
       "              max_cat_threshold=None, max_cat_to_onehot=None,\n",
       "              max_delta_step=None, max_depth=8, max_leaves=None,\n",
       "              min_child_weight=None, missing=nan, monotone_constraints=None,\n",
       "              multi_strategy=None, n_estimators=150, n_jobs=None,\n",
       "              num_parallel_tree=None, random_state=None, ...)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
       "              colsample_bylevel=None, colsample_bynode=None,\n",
       "              colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
       "              enable_categorical=False, eval_metric=None, feature_types=None,\n",
       "              gamma=None, grow_policy=None, importance_type=None,\n",
       "              interaction_constraints=None, learning_rate=0.5, max_bin=None,\n",
       "              max_cat_threshold=None, max_cat_to_onehot=None,\n",
       "              max_delta_step=None, max_depth=8, max_leaves=None,\n",
       "              min_child_weight=None, missing=nan, monotone_constraints=None,\n",
       "              multi_strategy=None, n_estimators=150, n_jobs=None,\n",
       "              num_parallel_tree=None, random_state=None, ...)"
      ]
     },
     "execution_count": 117,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model = XGBClassifier(learning_rate=0.5, n_estimators=150,max_depth= 8)\n",
    "model.fit(X_train_transformed, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 119,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-5 {color: black;}#sk-container-id-5 pre{padding: 0;}#sk-container-id-5 div.sk-toggleable {background-color: white;}#sk-container-id-5 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-5 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-5 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-5 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-5 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-5 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-5 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-5 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-5 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-5 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-5 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-5 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-5 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-5 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-5 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-5 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-5 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-5 div.sk-item {position: relative;z-index: 1;}#sk-container-id-5 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-5 div.sk-item::before, #sk-container-id-5 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-5 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-5 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-5 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-5 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-5 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-5 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-5 div.sk-label-container {text-align: center;}#sk-container-id-5 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-5 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-5\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestClassifier(n_estimators=250)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-9\" type=\"checkbox\" checked><label for=\"sk-estimator-id-9\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestClassifier</label><div class=\"sk-toggleable__content\"><pre>RandomForestClassifier(n_estimators=250)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "RandomForestClassifier(n_estimators=250)"
      ]
     },
     "execution_count": 119,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model2= RandomForestClassifier(criterion = 'gini', max_depth = None, n_estimators = 250)\n",
    "model2.fit(X_train_transformed, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 120,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "XGBoost score:      0.9829466032988537\n",
      "Random Fores score: 0.9545708694436679\n"
     ]
    }
   ],
   "source": [
    "print('XGBoost score:     ', model.score(X_test_transformed, y_test))\n",
    "print('Random Fores score:', model2.score(X_test_transformed, y_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 121,
   "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>Model</th>\n",
       "      <th>F1 score</th>\n",
       "      <th>Recall score</th>\n",
       "      <th>Precision_score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>XGBoost:</td>\n",
       "      <td>0.982943</td>\n",
       "      <td>0.982798</td>\n",
       "      <td>0.983162</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Random Forest:</td>\n",
       "      <td>0.954563</td>\n",
       "      <td>0.954421</td>\n",
       "      <td>0.954730</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Model  F1 score  Recall score  Precision_score\n",
       "0        XGBoost:   0.982943      0.982798         0.983162\n",
       "1  Random Forest:   0.954563      0.954421         0.954730"
      ]
     },
     "execution_count": 121,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "modelResult1 = ['XGBoost: ']\n",
    "modelResult2 = ['Random Forest: ']\n",
    "\n",
    "predictions = model.predict(X_test_transformed)\n",
    "predictions2 = model2.predict(X_test_transformed)\n",
    "\n",
    "modelResult1.append(f1_score(y_test, predictions, average='weighted'))\n",
    "modelResult2.append(f1_score(y_test, predictions2, average='weighted'))\n",
    "\n",
    "modelResult1.append(recall_score(y_test, predictions, average='macro'))\n",
    "modelResult2.append(recall_score(y_test, predictions2, average='macro'))\n",
    "\n",
    "modelResult1.append(precision_score(y_test, predictions, average='macro'))\n",
    "modelResult2.append(precision_score(y_test, predictions2, average='macro'))\n",
    "\n",
    "pd.DataFrame([modelResult1, modelResult2], columns=['Model', 'F1 score', 'Recall score', 'Precision_score']) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 122,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[Text(0, 0.5, 'Verdadero'),\n",
       " Text(0.5, 0, 'Predecido'),\n",
       " Text(0.5, 1.0, 'Matriz de confision modelo XGBoost')]"
      ]
     },
     "execution_count": 122,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAfYAAAHFCAYAAAAABdu/AAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAAPYQAAD2EBqD+naQAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjAsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy8GearUAAAgAElEQVR4nOzdeXhMZ/sH8O9km0RkRvYISQQVsZQmiFC1hJC2SkspbYi1qqilb38i9r6WetXSViy1VS1NlaKlNLWXUELUErRKEyQiQSZiyfb8/tBMTTYzmRlj5nw/rnNd5pnnnHOfMXLnfs5zzpEJIQSIiIjIIliZOgAiIiIyHCZ2IiIiC8LETkREZEGY2ImIiCwIEzsREZEFYWInIiKyIEzsREREFoSJnYiIyIIwsRMREVkQJnYDWr16NWQyGWQyGfbt21fqfSEE6tatC5lMhnbt2lVqH7GxsVi9erVO6+zbt6/cmAxl6tSpkMlkRtv+0zRx4kT4+vrCxsYG1apVAwC0a9dO53+zp/G5P6uK/y9cuXJF53UN/V0aOHAg5HI5Tp8+Xeq92bNnQyaT4YcfftBoV6lUmD17NkJCQlCtWjXY2trC09MTXbp0wfr16/Hw4UN13ytXrqj/3xcvCoUCTZo0wYIFC1BYWGiwY6msyvzcIPNlY+oALJGTkxNWrFhRKhHs378fly5dgpOTU6W3HRsbCzc3N0RFRWm9TlBQEBISEtCgQYNK71cqtm7dihkzZiAmJgYRERGQy+UAHn3uuuLn/mxYsGABdu/ejf79++Po0aOwtbUFAJw+fRpTpkxBVFQUunbtqu7/xx9/oEuXLsjIyMDQoUMRExMDZ2dnpKWlYdeuXRg4cCCSk5Px8ccfa+xn5MiR6Nu3LwDgzp072LZtG8aMGYPU1FR8+umnT++Ay1CZnxtkvpjYjaB3795Yt24dFi1aBIVCoW5fsWIFQkNDoVKpnkoc+fn56uqhZcuWT2Wf5u7MmTMAgFGjRsHDw0PdXpnkzM/92aBQKLBixQqEh4fjv//9L6ZNm4b8/HxERkbC09MTCxYsUPctKChA9+7dcevWLfz2228IDAzU2FavXr0wefJknDx5stR+fH19Nf69u3TpgjNnzmDDhg0mT+wkLRyKN4I+ffoAADZs2KBuy87OxqZNmzBw4MAy15k2bRpCQkLg4uIChUKBoKAgrFixAo8/o6dWrVo4e/Ys9u/frx7yq1WrFoB/h32//vprjBs3DjVq1IBcLseff/5Zaki4rKHDx5cn2b59O5o2bQq5XA5/f3/MnTu3zH5CCMTGxqJp06ZwcHCAs7Mzevbsib/++kubjxHnz59Hnz594OnpCblcDl9fX/Tr109jGPTMmTPo1q0bnJ2dYW9vj6ZNm+Krr77S2E7x8W/YsAExMTHw9vaGQqFAx44dceHCBY3Pd+LEiQAAT09PyGQyTJ06FUDZQ/GLFy9GkyZNULVqVTg5OaF+/fqYMGFCqf2WHIrftm0bQkNDUaVKFTg5OaFTp05ISEjQ6FM8HH327Fn06dMHSqUSnp6eGDhwILKzs5/42bVr1w6NGjVCQkICWrVqBQcHB9SqVQurVq0C8OjfMCgoCFWqVEHjxo2xc+fOUtv49ddfERYWBicnJ1SpUgWtWrXC9u3bS/U7cuQIWrduDXt7e3h7eyM6Ohr5+fllxhUXF4fQ0FA4OjqiatWq6Ny5c5lJsqSioiLMmTMH9evXh1wuh4eHB/r164erV68+cV0A6NixI4YNG4aZM2ciMTERU6dOxalTp7BixQoolUp1v++//x7nzp1DTExMqaRezM/PD927d9dqv0qlUj1CUJljWblyJZo0aQJ7e3u4uLjg9ddfR3Jyskafv/76C2+99Ra8vb0hl8vh6emJsLAwJCUlAaj45wZZKEEGs2rVKgFAHDt2TERGRooWLVqo31u8eLFwdHQUKpVKNGzYULRt21Zj3aioKLFixQoRHx8v4uPjxccffywcHBzEtGnT1H1OnDghateuLV544QWRkJAgEhISxIkTJ4QQQuzdu1cAEDVq1BA9e/YU27ZtEz/++KPIyspSv7d3714hhBAPHjxQr1+8bNu2TSgUChEYGFjhMf7yyy/C2tpavPjii2Lz5s1i48aNonnz5sLX11eU/DoNGTJE2NrainHjxomdO3eK9evXi/r16wtPT0+Rnp5e4X6SkpJE1apVRa1atcSSJUvE7t27xdq1a0WvXr2ESqUSQghx/vx54eTkJOrUqSPWrFkjtm/fLvr06SMAiE8++US9reLjr1Wrlnj77bfF9u3bxYYNG4Svr6947rnnREFBgfrzHTRokAAgdu7cKRISEkRqaqoQQoi2bdtq/Jtt2LBBABAjR44UP//8s/jll1/EkiVLxKhRo0rtt/hzF0KIdevWCQAiPDxcbNmyRcTFxYng4GBhZ2cnDh48qO43ZcoUAUAEBASIyZMni/j4eDFv3jwhl8vFgAEDKvzsiuN1dXUVAQEBYsWKFWLXrl3i1VdfFQDEtGnTROPGjcWGDRvEjh07RMuWLYVcLhfXrl1Tr79v3z5ha2srgoODRVxcnNiyZYsIDw8XMplMfPPNN+p+Z8+eFVWqVBENGjQQGzZsEFu3bhWdO3dWfx8uX76s7jtjxgwhk8nEwIEDxY8//ig2b94sQkNDhaOjozh79mypY3/c0KFDBQAxYsQIsXPnTrFkyRLh7u4ufHx8xM2bN5/4eQghxN27d0Xt2rVFrVq1hLW1tRg2bFipPkOGDBEAxIULF7TaphBCXL58Wf2dy8/PF/n5+SIzM1OsWLFC2NjYiJiYmEody8yZMwUA0adPH7F9+3axZs0aUbt2baFUKsXFixfV/QICAkTdunXF119/Lfbv3y82bdokxo0bp/7eVfRzgywTE7sBPZ7Yi3+onzlzRgghRPPmzUVUVJQQQpSZ2B9XWFgo8vPzxfTp04Wrq6soKipSv1feusX7e+mll8p97/EE87jc3FzRokULUb16dXHlypUKjzEkJER4e3uL+/fvq9tUKpVwcXHR+GGckJAgAIhPP/1UY/3U1FTh4OAgPvroowr306FDB1GtWjWRkZFRbp+33npLyOVykZKSotEeEREhqlSpIu7cuSOE+Pf4X375ZY1+3377rQAgEhIS1G3FSaVksiiZ2EeMGCGqVatW4TGU/NwLCwuFt7e3aNy4sSgsLFT3y8nJER4eHqJVq1al4pgzZ47GNocPHy7s7e01vhNladu2rQAgjh8/rm7LysoS1tbWwsHBQSOJJyUlCQDis88+U7e1bNlSeHh4iJycHHVbQUGBaNSokahZs6Z6/7179xYODg4av6gVFBSI+vXrayT2lJQUYWNjI0aOHKkRZ05OjvDy8hK9evUqdezFkpOTBQAxfPhwjXWPHj0qAIgJEyZU+Fk8bv369QKA8PLy0ji2Yl26dBEAxIMHDzTai4qK1Ek7Pz9f/cugEP8m9rKWqKgojb7aHsvt27eFg4NDqe9sSkqKkMvlom/fvkIIITIzMwUAsWDBggqP+0k/c8iycCjeSNq2bYs6depg5cqVOH36NI4dO1buMDwA7NmzBx07doRSqYS1tTVsbW0xefJkZGVlISMjQ+v99ujRQ6c4CwsL0bt3byQnJ2PHjh3w8/Mrt29ubi6OHTuGN954A/b29up2JycnjclHAPDjjz9CJpPhnXfeQUFBgXrx8vJCkyZNKpwpfu/ePezfvx+9evWCu7t7uf327NmDsLAw+Pj4aLRHRUXh3r17pYa3X3vtNY3Xzz//PADg77//Lncf5WnRogXu3LmDPn36YOvWrcjMzHziOhcuXMD169cRGRkJK6t//+tVrVoVPXr0wJEjR3Dv3r0nxvzgwQOtvhPVq1dHcHCw+rWLiws8PDzQtGlTeHt7q9uLh5yLP4fc3FwcPXoUPXv2RNWqVdX9rK2tERkZiatXr6pPYezduxdhYWHw9PTU6Ne7d2+NWHbt2oWCggL069dP4/tgb2+Ptm3bVvh92Lt3LwCUmvjVokULBAYGYvfu3U/8LIBHQ+Cff/45rKyskJGRgVOnTmm1HgAsXLgQtra26qVJkyal+nzwwQc4duwYjh07hr1792LmzJn49ttv1afmdDmWhIQE3L9/v1Q/Hx8fdOjQQd3PxcUFderUwf/+9z/MmzcPJ0+eRFFRkdbHRZaJid1IZDIZBgwYgLVr12LJkiWoV68e2rRpU2bf3377DeHh4QCAL7/8EocOHcKxY8cQExMDALh//77W+61evbpOcQ4bNgw7d+7Ed999h6ZNm1bY9/bt2ygqKoKXl1ep90q23bhxA0IIeHp6avxAtLW1xZEjRypMhLdv30ZhYSFq1qxZYTxZWVllHm9x0srKytJod3V11XhdPONdl8+3WGRkJFauXIm///4bPXr0gIeHB0JCQhAfH19hvEDZ/0be3t4oKirC7du3DRazi4tLqTY7O7tS7XZ2dgCABw8eAHj0+QshtPpss7KytP4+AEDz5s1LfR/i4uIq/D486XMr+e9cnrlz5yIhIQHr16/Hc889h4EDB5b6HH19fQGU/mWvb9++6qQdFBRU5vZr1qyJZs2aoVmzZmjXrh2io6MxadIkbNy4Ebt27dLpWLTtJ5PJsHv3bnTu3Blz5sxBUFAQ3N3dMWrUKOTk5Gj1uZDl4ax4I4qKisLkyZOxZMkSzJgxo9x+33zzDWxtbfHjjz9qVMJbtmzReZ+6XP87depULF++HKtWrVL/YlERZ2dnyGQypKenl3qvZJubmxtkMhkOHjyoTkaPK6utmIuLC6ytrZ84McrV1RVpaWml2q9fv66OwZgGDBiAAQMGIDc3FwcOHMCUKVPw6quv4uLFi2WOfBQn6fJitrKygrOzs1Fj1oazszOsrKy0+mxdXV21/j4AwHfffVfhqFBZHv/cSv6yd/36da3+nc+dO4fJkyejX79+6N27N/z8/NC6dWvExMRg3rx56n6dOnXCsmXLsG3bNnz44Yfqdg8PD/VVEk5OThoTOCtSPCp06tQpdO7cWetjedJ35fFj9vPzw4oVKwAAFy9exLfffoupU6ciLy8PS5Ys0SpOsiys2I2oRo0a+M9//oOuXbuif//+5faTyWSwsbGBtbW1uu3+/fv4+uuvS/WVy+WVqjBLWrFiBaZNm4bp06drfW2ro6MjWrRogc2bN6urOwDIyckpdYOPV199FUIIXLt2TV3FPL40bty43P04ODigbdu22LhxY4WVXFhYGPbs2aNONsXWrFmDKlWqPLVLzRwdHREREYGYmBjk5eXh7NmzZfYLCAhAjRo1sH79eo2rHXJzc7Fp0yb1THlTc3R0REhICDZv3qzxXSsqKsLatWtRs2ZN1KtXDwDQvn177N69W12RA49O78TFxWlss3PnzrCxscGlS5fK/D40a9as3Hg6dOgAAFi7dq1G+7Fjx5CcnIywsLAKj6egoAD9+/eHm5sbFi5cCABo2bIlxo4di4ULF+LQoUPqvq+//joaNGiAmTNn4vz58xVuVxvFM9OLfynQ9lhCQ0Ph4OBQqt/Vq1fVp6DKUq9ePUycOBGNGzfGiRMn1O2G+rlB5oEVu5HNnj37iX1eeeUVzJs3D3379sXQoUORlZWFuXPnllnVNm7cGN988w3i4uJQu3Zt2NvbV5gky5KQkIBhw4ahdevW6NSpE44cOaLxfkUJ8eOPP0aXLl3QqVMnjBs3DoWFhfjkk0/g6OiIW7duqfu1bt0aQ4cOxYABA3D8+HG89NJLcHR0RFpaGn799Vc0btwY7733Xrn7mTdvHl588UWEhIRg/PjxqFu3Lm7cuIFt27Zh6dKlcHJywpQpU/Djjz+iffv2mDx5MlxcXLBu3Tps374dc+bM0biMydCGDBkCBwcHtG7dGtWrV0d6ejpmzZoFpVKJ5s2bl7mOlZUV5syZg7fffhuvvvoq3n33XTx8+BD/+9//cOfOHa2+K0/LrFmz0KlTJ7Rv3x4ffvgh7OzsEBsbq74uu3hkaOLEidi2bRs6dOiAyZMno0qVKli0aBFyc3M1tlerVi1Mnz4dMTEx+Ouvv9ClSxc4Ozvjxo0b+O233+Do6Ihp06aVGUtAQACGDh2qPj8eERGBK1euYNKkSfDx8cGYMWOeeCzHjx/HTz/9pL6TIPDou/zDDz9g4MCBSEpKgoODA6ytrbFlyxZ07twZLVq0wJAhQ9CuXTs4Ozvjzp07OHr0KE6dOlXmpXApKSnq/0u5ublISEjArFmz4OfnhzfeeEOnY6lWrRomTZqECRMmoF+/fujTpw+ysrIwbdo02NvbY8qUKQCA33//HSNGjMCbb76J5557DnZ2dtizZw9+//13jB8/Xh2bIX5ukBkx7dw9y/L4rPiKlDVDdeXKlSIgIEDI5XJRu3ZtMWvWLLFixYpSlwxduXJFhIeHCycnJwFA+Pn5CSH+nYG9cePGUvsrOTu7OM7ylifZtm2beP7554WdnZ3w9fUVs2fPLvMSpeLjCgkJEY6OjsLBwUHUqVNH9OvXT2O2dnnOnTsn3nzzTeHq6qreV1RUlMaM5dOnT4uuXbsKpVIp7OzsRJMmTcSqVavKPP6Sn03xbObH+2s7K/6rr74S7du3F56ensLOzk54e3uLXr16id9//73UfktejbBlyxYREhIi7O3thaOjowgLCxOHDh3S6FNeHMX/do9/J8rStm1b0bBhw1Ltfn5+4pVXXinVDkC8//77Gm0HDx4UHTp0UP/btWzZUvzwww+l1j106JD6kjkvLy/xn//8RyxbtqzMOLds2SLat28vFAqFkMvlws/PT/Ts2VP88ssvpY79cYWFheKTTz4R9erVE7a2tsLNzU2888476ssRy5OUlCRsbW3FkCFDynw/ISFBWFlZiTFjxmi0Z2dni5kzZ4rmzZsLhUIhbGxshIeHh+jUqZNYtGiRyM3NVfcta1a8vb29qFevnhg9erRIS0ur9LEsX75c/X9NqVSKbt26aVwaeOPGDREVFSXq168vHB0dRdWqVcXzzz8v5s+frzEbv7yfG2SZZEI8NiZIREREZo3n2ImIiCwIEzsREZEFYWInIiKyIEzsREREFoSJnYiIyIIwsRMREVkQs75BTVFREa5fvw4nJyedbqVKRETPBiEEcnJy4O3trfFwJEN78OAB8vLy9N6OnZ2dxq2/n0kmvo5eL6mpqRXeaIULFy5cuJjH8qSbDenj/v37AjZVDBKnl5eXxmOrtbFo0SJRq1YtIZfLRVBQkDhw4EC5fYtvbFVySU5O1np/Zl2xOzk5AQDsWoyBzKb8h4oQmbPLW8c/uRORmcrJUSGgtq/657kx5OXlAQX3IG/QH7C2q/yGCvOQfu4r5OXlaV21x8XFYfTo0YiNjUXr1q2xdOlSRERE4Ny5c+qnCZblwoULUCgU6tcVPcK6JLNO7MXD7zIbOWQ2z/jQCFElPf6fm8hSPZXTqTb2kOmR2IVM91MF8+bNw6BBgzB48GAAwIIFC7Br1y4sXrwYs2bNKnc9Dw8PjWcb6IKT54iIiHSgUqk0lvIe45uXl4fExMRSj8UODw/H4cOHK9zHCy+8gOrVqyMsLAx79+7VKT4mdiIikgYZAJlMj+XRZnx8fKBUKtVLeZV3ZmYmCgsL4enpqdHu6emJ9PT0MtepXr06li1bhk2bNmHz5s0ICAhAWFgYDhw4oPVhmvVQPBERkdZkVo8WfdYHkJqaqnGKrKxHbGusVuI0gxCi3FMPAQEBCAgIUL8ODQ1Famoq5s6di5deekmrMFmxExGRNOhVrf+z4NG8l8eX8hK7m5sbrK2tS1XnGRkZpar4irRs2RJ//PGH1v2Z2ImIiIzAzs4OwcHBiI+P12iPj49Hq1attN7OyZMnUb16da37cyieiIikwUBD8boYO3YsIiMj0axZM4SGhmLZsmVISUnBsGHDAADR0dG4du0a1qxZA+DRrPlatWqhYcOGyMvLw9q1a7Fp0yZs2rRJ630ysRMRkTQ8Npxe6fV11Lt3b2RlZWH69OlIS0tDo0aNsGPHDvj5+QEA0tLSkJKSou6fl5eHDz/8ENeuXYODgwMaNmyI7du34+WXX9Y+TCGE0DnSZ4RKpYJSqYS81Xhex04WKzN+sqlDIDIalUoFb/dqyM7ONto9G9S5IngkZNaVv5mZKHyIh4mfGzVWQ2DFTkREEqHnULyZTEtjYiciImkwwVC8KZjHrx9ERESkFVbsREQkDSaYFW8KTOxERCQNHIonIiIic8OKnYiIpIFD8URERBZEIkPxTOxERCQNEqnYzSNKIiIi0gordiIikgaZTM+KnUPxREREzw4r2aNFn/XNAIfiiYiILAgrdiIikgaJTJ5jYiciImmQyOVu5vHrBxEREWmFFTsREUkDh+KJiIgsiESG4pnYiYhIGiRSsZtHlERERKQVVuxERCQNHIonIiKyIByKJyIiInPDip2IiKSBQ/FERESWRM+heDMZ5DaPKImIiEgrrNiJiEgaOBRPRERkQWQyPWfFm0di51A8ERGRBWHFTkRE0iCR69iZ2ImISBp4jp2IiMiCSKRiN48oiYiISCus2ImISBo4FE9ERGRBOBRPRERE5oYVOxERSQOH4omIiCyHTCaDTAKJnUPxREREFoQVOxERSYJUKnYmdiIikgbZP4s+65sBDsUTERFZEFbsREQkCRyKJyIisiBM7ERERBZEKomd59iJiIgsCCt2IiKSBKlU7EzsREQkDbzcjYiIiMwNK3YiIpIEDsUTERFZkEcPd9MnsRsuFmPiUDwREZEFYcVORESSIIOeQ/FmUrIzsRMRkSRI5Rw7h+KJiIgsCCt2IiKSBolcx87ETkRE0qDnULwwk6F4JnYiIpIEfc+x6zfx7unhOXYiIiILwoqdiIgkQSoVOxM7ERFJg0Qmz3EonoiIyIKwYiciIkmQylA8K3YiIpKE4sSuz1IZsbGx8Pf3h729PYKDg3Hw4EGt1jt06BBsbGzQtGlTnfbHxE5ERGQkcXFxGD16NGJiYnDy5Em0adMGERERSElJqXC97Oxs9OvXD2FhYTrvk4mdiIgkwRQV+7x58zBo0CAMHjwYgYGBWLBgAXx8fLB48eIK13v33XfRt29fhIaG6rxPJnYiIpIEQyV2lUqlsTx8+LDM/eXl5SExMRHh4eEa7eHh4Th8+HC5ca5atQqXLl3ClClTKnWcTOxEREQ68PHxgVKpVC+zZs0qs19mZiYKCwvh6emp0e7p6Yn09PQy1/njjz8wfvx4rFu3DjY2lZvfzlnxREQkDQa6jj01NRUKhULdLJfLK16txBC+EKLMYf3CwkL07dsX06ZNQ7169SodJhM7ERFJgqEud1MoFBqJvTxubm6wtrYuVZ1nZGSUquIBICcnB8ePH8fJkycxYsQIAEBRURGEELCxscHPP/+MDh06PHG/TOxERCQJT/s6djs7OwQHByM+Ph6vv/66uj0+Ph7dunUr1V+hUOD06dMabbGxsdizZw++++47+Pv7a7VfJnYiIiIjGTt2LCIjI9GsWTOEhoZi2bJlSElJwbBhwwAA0dHRuHbtGtasWQMrKys0atRIY30PDw/Y29uXaq8IEzsREUmCKe4817t3b2RlZWH69OlIS0tDo0aNsGPHDvj5+QEA0tLSnnhNu85xCiGEQbf4FKlUKiiVSshbjYfMxt7U4RAZRWb8ZFOHQGQ0KpUK3u7VkJ2drdV568ruQ6lUwnvIeljZVan0dory7uH6l32NGqsh8HI3IiIiC8KheCIikgSpPASGiV3iBr3WDCN7tYKnqxPOX8nAhNhdSDj95PM9IQ198OP8KCRfzsBL7y7VeG/YGyEY+Foz1PRQ4lb2PWw9kIzpy3/Bw/xCYx0GEQBg5XcH8MXa3biRpUKAf3XMGPMGQl+oW27/Qyf+wKQF3+PC5TR4uSkxIrIjBrzxovr983+lYfbS7Th1IRWpabfw39FvYFif9hrbWLD6Z/y47xT++PsGHOS2aN7YH5NHdMNzfqUvZyLTkkpiN/lQfGWfekP6e71dQ8wc3gWfrj+Itu8uRcLpFHw7623U9Kj43JHCUY7F47tj/4m/Sr33ZlhjTBnSEXPW7EfIgEUYOXcbXm/XEJMHdzTWYRABAL6PT0TM/M0YM6Az9q75P4Q2rYO3xizG1fRbZfb/+3om+oxZgtCmdbB3zf9hdFQ4Jnz6HX7Yk6Tuc+9BHvxquGHS8Nfg4Vr2/4vDJ//EoJ5tsGvFOHz32fsoKCzCm6MWIfd+2bcZJTI2kyb2yj71hgxjeM+WWPvTSXy94yQupmRiQuwuXMvIxsCuzStcb/6YV/Hd7jM4du5qqfeaN6iJo2dS8N2eM0i9kY29iX9h094zeCGgurEOgwgAsHjDXrz9Wigiu7VCPX8vzBjbA96ezli16dcy+6/efAg1vJwxY2wP1PP3QmS3VujbtSUWrdut7hPUwA/TRnXHG+HBkNuVPcD57cLh6PNqS9SvXR2N6tXE55PextX02zh1PtUox0mVJ4Oe94rX67Z1T49JE3tln3pD+rO1sULTet7Yc/ySRvvexL/QomHNctfr27kpalV3xidr9pX5/pEzKWhazxtBAd4AAL/q1dCpRV38fOQPg8VOVFJefgFOnU9F+5D6Gu3tW9THb6cvl7nOsdOX0b6FZv8OLQORlJyC/ILKnzZS3X0AAHBWVH72NRmHqZ7H/rSZ7Bx78VNvxo8fr9H+pKfekGG4KqvAxtoKN2/f1Wi/efsuPFzqlLlO7RoumDIkDC+PXoXCorKvkty89yxclY74aeFAyGSArY01Vmw9hgXfHDL4MRAVy7qTi8LCIri7OGm0u7s6IeOIqsx1MrJUcHct0d/FCQWFRci6cxdebkqd4xBCYNLCzWjZpDYC63jrvD6RIZgssVfmqTcPHz7UeDyeSlX2f1jSXsn0LIMMZd3ZwMpKhi8nvIHZq/fh0tWyz1kCQOsmfhj3dht8+Nl2JCZfg7+3C2a/3wXpt+5i7toDhg2eqITSD9sAKiqySg6tFn/3K1uZ/d//NuLcn9exfenoSq1PRmagh8A860w+K17bp94AwKxZszBt2rSnEZbFy8q+h4LCIng4V9Vod3N2LFXFA0BVBzsE1a+B55+rjjmjXgYAWMlksITPip8AACAASURBVLKS4ebPk/DGR1/jYNIVxAxoj2/jf8fXO04CAM5dzoCjgy3mj+mKT9cdKPOXBiJ9uVZzhLW1FTKyNH/Zz7yVA3eXsie9ebgqSve/nQMbayu4KB11jmH83I3YefA0flj6Abw9nXVen4xPKrPiTZbYdX3qDfDonrpjx45Vv1apVPDx8TFqnJYqv6AISRevo31wbWw/dF7d3i64Nn46dKFU/5x7D9FqUKxG26DXmqPNC/6ImvYt/k6/AwBwkNuiqET2LiwUkMke/acw4xsd0jPMztYGTer7YN9v5/FKuybq9n2/XUDES43LXKd5Y3/sOnhGo23v0fNoGugLWxtrrfcthMD4uRuxff/v2Bo7Cn7ebpU7CDI6JnYj0/WpN8CjZ94+6bm3pL3Y745gyfjXcfLidRw7dxX9XwlGTQ8lVv1wHAAweVAYqrs54b1PtkAIIPnKTY31b97JxcO8Ao32nQkXMbxnKH7/Mw3Hk6+hdg0XTBjQHj8dvoCics7LExnCe33aY/jUr9G0vi+aN/bHV1sO4dqNW4j657r0jxdtQ9rNO4id2g8AEPVGa6zYeAATF2xGv26tcOz0ZazbloBlH0ept5mXX4ALl9PVf0+7mY3TF6/C0UGO2j7uAICP/vctNu1KxNf/G4Kqjva48c8ogMLRHg72dk/vAyD6h0mH4p/01Bsyru/3nYWLwgEfRbaFp0tVJF/JQO/odUjNyAYAeLpWRU0P3SYQzV37aLg9ZkAHVHdzQtade9h55CI+XrH7ySsT6eH1TsG4nZ2LuSt34kamCvVrV8eG+e/Bp7oLAOBGVjau3rit7u/n7YYN84dh4oLNWPndQXi5KTBzXE907dBU3Sf9ZjbaR36ifr1o3W4sWrcbrYLqYtviDwBAfTldt/c+04jn80lvo8+rLY12vKS7RyOH+q1vDkz+EJjY2FjMmTNH/dSb+fPn46WXXtJqXT4EhqSAD4EhS/Y0HwJTe+R3sJLrPn+iWNHDXPz1ec9n/iEwJp88N3z4cAwfPtzUYRAREVkEkyd2IiKip0LPoXhe7kZERPQMkcqseJM/BIaIiIgMhxU7ERFJglRmxTOxExGRJFhZPbpbZmUJPdZ9mjgUT0REZEFYsRMRkSRwKJ6IiMiCSGVWPBM7ERFJglQqdp5jJyIisiCs2ImISBI4FE9ERGRBpJLYORRPRERkQVixExGRJEhl8hwTOxERSYIMeg7Fm8nj3TgUT0REZEFYsRMRkSRwKJ6IiMiCcFY8ERERmR1W7EREJAkciiciIrIgUhmKZ2InIiJJkErFznPsREREFoQVOxERSQKH4omIiCyJnkPxZnLjOQ7FExERWRJW7EREJAkciiciIrIgnBVPREREZocVOxERSQKH4omIiCwIh+KJiIjI7LBiJyIiSeBQPBERkQVhYiciIrIgPMdOREREZocVOxERSQKH4omIiCwIh+KJiIjI7LBiJyIiSeBQPBERkQWRQc+heINFYlwciiciIrIgrNiJiEgSrGQyWOlRsuuz7tPExE5ERJLAWfFERERkdlixExGRJHBWPBERkQWxkj1a9FnfHDCxExGRNMj0rLrNJLHzHDsREZEFYWInIiJJKJ4Vr89SGbGxsfD394e9vT2Cg4Nx8ODBcvv++uuvaN26NVxdXeHg4ID69etj/vz5Ou2PQ/FERCQJsn/+6LO+ruLi4jB69GjExsaidevWWLp0KSIiInDu3Dn4+vqW6u/o6IgRI0bg+eefh6OjI3799Ve8++67cHR0xNChQ7XaJyt2IiIiI5k3bx4GDRqEwYMHIzAwEAsWLICPjw8WL15cZv8XXngBffr0QcOGDVGrVi2888476Ny5c4VVfklM7EREJAnFs+L1WQBApVJpLA8fPixzf3l5eUhMTER4eLhGe3h4OA4fPqxVzCdPnsThw4fRtm1brY+z0kPxiYmJSE5OhkwmQ2BgIIKCgiq7KSIiIqMz1HXsPj4+Gu1TpkzB1KlTS/XPzMxEYWEhPD09Ndo9PT2Rnp5e4b5q1qyJmzdvoqCgAFOnTsXgwYO1jlPnxJ6RkYG33noL+/btQ7Vq1SCEQHZ2Ntq3b49vvvkG7u7uum6SiIjIbKSmpkKhUKhfy+XyCvuX/GVCCPHEXzAOHjyIu3fv4siRIxg/fjzq1q2LPn36aBWfzkPxI0eOhEqlwtmzZ3Hr1i3cvn0bZ86cgUqlwqhRo3TdHBER0VNhqFnxCoVCYykvsbu5ucHa2rpUdZ6RkVGqii/J398fjRs3xpAhQzBmzJgyRwTKo3Ni37lzJxYvXozAwEB1W4MGDbBo0SL89NNPum6OiIjoqSh+ups+iy7s7OwQHByM+Ph4jfb4+Hi0atVK6+0IIco9j18WnYfii4qKYGtrW6rd1tYWRUVFum6OiIjIYo0dOxaRkZFo1qwZQkNDsWzZMqSkpGDYsGEAgOjoaFy7dg1r1qwBACxatAi+vr6oX78+gEfXtc+dOxcjR47Uep86J/YOHTrggw8+wIYNG+Dt7Q0AuHbtGsaMGYOwsDBdN0dERPRUmOKxrb1790ZWVhamT5+OtLQ0NGrUCDt27ICfnx8AIC0tDSkpKer+RUVFiI6OxuXLl2FjY4M6depg9uzZePfdd7WPUwghdAkyNTUV3bp1w5kzZ+Dj4wOZTIaUlBQ0btwYW7duRc2aNXXZnF5UKhWUSiXkrcZDZmP/1PZL9DRlxk82dQhERqNSqeDtXg3Z2dkaE9IMvQ+lUonXFu2HrUPVSm8n//5dbHu/rVFjNQSdK3YfHx+cOHEC8fHxOH/+PIQQaNCgATp27GiM+IiIiAzCFBW7KeiU2AsKCmBvb4+kpCR06tQJnTp1MlZcREREVAk6JXYbGxv4+fmhsLDQWPEQEREZRWVmtpdc3xzofLnbxIkTER0djVu3bhkjHiIiIqOQGWAxBzqfY//ss8/w559/wtvbG35+fnB0dNR4/8SJEwYLjoiIiHSjc2Lv3r27MeIgIiIyKkPdK/5Zp3NinzJlijHiICIiMqrHn9BW2fXNQaUe23rnzh0sX75c41z7iRMncO3aNYMGR0RERLrRuWL//fff0bFjRyiVSly5cgVDhgyBi4sLvv/+e/z999/q2+IRERE9S6QyFK9zxT527FhERUXhjz/+gL39v3d7i4iIwIEDBwwaHBERkSHp+2Q3c6BzYj927FiZ96ytUaPGEx8cT0RERMal81C8vb09VCpVqfYLFy7A3d3dIEEREREZGofiy9GtWzdMnz4d+fn5AKB+CMz48ePRo0cPgwdIRERkCMWz4vVZzIHOiX3u3Lm4efMmPDw8cP/+fbRt2xZ169aFk5MTZsyYYYwYiYiI9FZcseuzmAOdh+IVCgV+/fVX7NmzBydOnEBRURGCgoL4dDciIqJngM6JvViHDh3QoUMHQ8ZCRERkNPre79086nUtE/tnn32m9QZHjRpV6WCIiIiMRSpPd9Mqsc+fP1/j9c2bN3Hv3j1Uq1YNwKM70VWpUgUeHh5M7ERERCak1eS5y5cvq5cZM2agadOmSE5Oxq1bt3Dr1i0kJycjKCgIH3/8sbHjJSIiqhR9bk5jTjep0XlW/KRJk/D5558jICBA3RYQEID58+dj4sSJBg2OiIjIUKQyK17nxJ6Wlqa+hv1xhYWFuHHjhkGCIiIiosrRObGHhYVhyJAhOH78OIQQAIDjx4/j3Xff5SVvRET0zOJQfDlWrlyJGjVqoEWLFrC3t4dcLkdISAiqV6+O5cuXGyNGIiIivRXPitdnMQc6X8fu7u6OHTt24OLFizh//jyEEAgMDES9evWMER8RERHpoNI3qKlXrx6TORERmQ19h9PNpGCvXGK/evUqtm3bhpSUFOTl5Wm8N2/ePIMERkREZEhSebqbzol99+7deO211+Dv748LFy6gUaNGuHLlCoQQCAoKMkaMT5TyQzQUCoVJ9k1kbM7NR5g6BCKjEYV5T+5kIFaoxMSyEuubA53jjI6Oxrhx43DmzBnY29tj06ZNSE1NRdu2bfHmm28aI0YiIiLSks6JPTk5Gf379wcA2NjY4P79+6hatSqmT5+OTz75xOABEhERGQJvUFMOR0dHPHz4EADg7e2NS5cuqd/LzMw0XGREREQGJJMBVnosZpLXdT/H3rJlSxw6dAgNGjTAK6+8gnHjxuH06dPYvHkzWrZsaYwYiYiISEs6J/Z58+bh7t27AICpU6fi7t27iIuLQ926dUs9BY6IiOhZUVx567O+OdA5sdeuXVv99ypVqiA2NtagARERERmDVC53M5fZ+0RERKQFrSp2Z2dnrX9TuXXrll4BERERGQOH4h+zYMEC9d+zsrLw3//+F507d0ZoaCgAICEhAbt27cKkSZOMEyUREZGeeEvZxxRftw4APXr0wPTp0zFixL93wxo1ahS++OIL/PLLLxgzZozhoyQiIiKt6HyOfdeuXejSpUup9s6dO+OXX34xSFBERESGJpXHtuqc2F1dXfH999+Xat+yZQtcXV0NEhQREZGhWRlgMQc6X+42bdo0DBo0CPv27VOfYz9y5Ah27tyJ5cuXGzxAIiIiQ+A59nJERUUhMDAQn332GTZv3gwhBBo0aIBDhw4hJCTEGDESERGRlnRK7Pn5+Rg6dCgmTZqEdevWGSsmIiIig7OCfufJrWAeJbtOpwxsbW3LPL9ORET0rCseitdnMQc6zwV4/fXXsWXLFmPEQkRERHrS+Rx73bp18fHHH+Pw4cMIDg6Go6OjxvujRo0yWHBERESGwjvPlWP58uWoVq0aEhMTkZiYqPGeTCZjYiciomfSo+ex6/MQGAMGY0Q6J/bLly8bIw4iIiIygEpfb5+Xl4cLFy6goKDAkPEQEREZBSfPlePevXsYNGgQqlSpgoYNGyIlJQXAo3Prs2fPNniAREREhlB8jl2fxRzonNijo6Nx6tQp7Nu3D/b29ur2jh07Ii4uzqDBERERkW50Pse+ZcsWxMXFoWXLlhrPaG/QoAEuXbpk0OCIiIgMRfbPH33WNwc6J/abN2/Cw8OjVHtubq5GoiciInqWSOVyN52H4ps3b47t27erXxcn8y+//FL9UBgiIqJnjVTOsWtdsSclJaFp06aYPXs2OnfujHPnzqGgoAALFy7E2bNnkZCQgP379xszViIiInoCrSv2oKAgBAcHIykpCTt27MC9e/dQp04d/Pzzz/D09ERCQgKCg4ONGSsREVGlyWQyvRdzoHXFfujQIaxcuRLjx49Hfn4+3njjDXz22Wfo0KGDMeMjIiIyCJ5jLyE0NBRffvkl0tPTsXjxYly9ehWdOnVCnTp1MGPGDFy9etWYcRIREZEWdJ485+DggP79+2Pfvn24ePEi+vTpg6VLl8Lf3x8vv/yyMWIkIiLSm1TuPKfz5W6Pq1OnDsaPHw8fHx9MmDABu3btMlRcREREBmUlk+n1EBh91n2aKp3Y9+/fj5UrV2LTpk2wtrZGr169MGjQIEPGRkRERDrSKbGnpqZi9erVWL16NS5fvoxWrVrh888/R69evUo9l52IiOhZIpXJc1on9k6dOmHv3r1wd3dHv379MHDgQAQEBBgzNiIiIsPR9zy5mSR2rSfPOTg4YNOmTbh69So++eQTJnUiIiItxMbGwt/fH/b29ggODsbBgwfL7bt582Z06tQJ7u7uUCgUCA0N1Xn+mtaJfdu2bejWrRusra112gEREdGzwAoyvRddxcXFYfTo0YiJicHJkyfRpk0bREREqB95XtKBAwfQqVMn7NixA4mJiWjfvj26du2KkydPar1PmRBC6BzpM0KlUkGpVOJGVjYUCoWpwyEyCufmI0wdApHRiMI8PDz9JbKzjfdzvDhXzP35dzg4OlV6O/dzc/Bh+PM6xRoSEoKgoCAsXrxY3RYYGIju3btj1qxZWm2jYcOG6N27NyZPnqxVf52vYyciIjJHT/shMHl5eUhMTER4eLhGe3h4OA4fPqzVNoqKipCTkwMXFxet96vXdexERERSo1KpNF7L5XLI5fJS/TIzM1FYWAhPT0+Ndk9PT6Snp2u1r08//RS5ubno1auX1vGxYiciIkkovkGNPgsA+Pj4QKlUqpcnDamXfHiMEEKrB8ps2LABU6dORVxcHDw8PLQ+TlbsREQkCfreFrZ43dTUVI1z7GVV6wDg5uYGa2vrUtV5RkZGqSq+pLi4OAwaNAgbN25Ex44ddYqTFTsREZEOFAqFxlJeYrezs0NwcDDi4+M12uPj49GqVatyt79hwwZERUVh/fr1eOWVV3SOjxU7ERFJghX0vFd8JS53Gzt2LCIjI9GsWTOEhoZi2bJlSElJwbBhwwAA0dHRuHbtGtasWQPgUVLv168fFi5ciJYtW6qrfQcHByiVSq32ycRORESSYKiheF307t0bWVlZmD59OtLS0tCoUSPs2LEDfn5+AIC0tDSNa9qXLl2KgoICvP/++3j//ffV7f3798fq1au12icTOxERkRENHz4cw4cPL/O9ksl63759eu+PiZ2IiCTBCvpNLDOXSWlM7EREJAkymUyry8wqWt8cmMsvIERERKQFVuxERCQJMuj35FXzqNeZ2ImISCIev3tcZdc3B0zsREQkGeaRmvXDc+xEREQWhBU7ERFJgiluUGMKTOxERCQJvNyNiIiIzA4rdiIikgTeeY6IiMiCcCieiIiIzA4rdiIikgTeeY6IiMiCcCieiIiIzA4rdiIikgTOiiciIrIgUhmKZ2InIiJJkMrkOXMZWSAiIiItsGInIiJJ4ENgiIiILIgVZLDSY0Bdn3WfJg7FExERWRBW7EREJAkciiciIrIgsn/+6LO+OeBQPBERkQVhxU5ERJLAoXgiIiILItNzVry5DMUzsRMRkSRIpWLnOXYiIiILwoqdiIgkQSoVOxM7ERFJAi93IyIiIrPDip2IiCTBSvZo0Wd9c8DETkREksCheCIiIjI7rNiJiEgSOCueiIjIgsig33C6meR1DsUTERFZElbsREQkCZwVT2Zv+cYD+HztbtzIzEb92tUxc2wPtHqhbrn9DyX+gZgFm3H+rzR4uSkxql9HDOzRRqPPtj0nMXPJdly+mgn/mm6Y+F5XvNq+ifr92cu245Mvf9JYx8PFCRd2zVK//mFPElZ//yuSklNxKzsXB9aOR+OAmgY6aiJNg3q2wch3wuDppsT5v9IwYd4mJCRdKrNv66Dn8OPSD0q1t+j5Mf74+wYAoH5tL0S/+yqa1veBr7croud9hyUb9hnzEMhAOCv+KThw4AC6du0Kb29vyGQybNmyxZThWJTNPydiwrxNGDegM/avHY/QpnXQ64NYpKbfKrP/39cy0Wv0YoQ2rYP9a8dj7IDOGD/3O2zbc1Ld57ff/8LACavQK6I5Dq4fj14RzTEgegWOn7misa36tavj/E8z1cuhbyZovJ/7IA8hz9fBlBHdDH7cRI97vVMQZo7tgU9X7ULbd2YjIekSvl04HDU9nStcr1mP6QjoEq1eLqVmqN9zsLfD39cyMe2LbUjPzDb2IZABFU+e02cxByZN7Lm5uWjSpAm++OILU4ZhkWLX78E73ULRr3srBPh7Yda4nqjh6YyV3x0ss//Kzb+ippczZo3riQB/L/Tr3gpvv9YSX6zdre6zZMM+tGtRH2MHdEa9Wl4YO6Az2jYPwOINezW2ZWNtBU83hXpxc3bSeP+tl1vgoyERaNciwPAHTvSY4X07YO3WBHy9NQEXr9zAhHmbcO3GbQzs2abC9W7eykFG1r9LUZFQv3fyXAomf7YFm+MTkZdXYOxDINKZSYfiIyIiEBERYcoQLFJefgGSzqdidP9wjfb2IYH47ffLZa5z7PRltA8J1GgLa9kAa7cmIL+gELY21vjt9GUM79teo0+H0MBSif2v1JsIjJgAOztbBDf0w+Thr6FWTTcDHBmR9mxtrNG0vg8WfPWzRvveo8lo8bx/heseWPt/kMttceFyOuau2IlfE/8wZqj0lMig38x2MynYzesc+8OHD/Hw4UP1a5VKZcJonl1Zd+6isLAI7i6albK7qxMyssr+zDKyVHB3LdHfxQkFhUXIunMXXm7KR31KbtPFCRlZOerXwQ1rYfG0SNTx9cDNrBzMXbkTnQd9ioS4GLhUq2qgIyR6MtdqVWFjY42bt3I02m9m5cDDVVHmOjeysvHBjPVISk6B3M4WvV9ujq2xI9F12EIcPln2eXkyH1aQwUqP8XQrM0ntZpXYZ82ahWnTppk6DLNR8vsrhICsgi91yXcExD/t/75Tcn0hNPfTqXXDf1/UBZo/74+g7lOxYftRvP92mE7xExmCEJqvZTIZRMnGf/z5dwb+/Pvf8+nHTl9GDU9njHinIxM7mQ2zuo49Ojoa2dnZ6iU1NdXUIT2TXKtVhbW1lUYlDQCZt+6WqriLebgqyuxvY20Fl2qOj/XRrPgzb+eUu00AcHSQo0Fdb1xKvVmZQyGqtKw7d1FQUAiPEiNRbi5VS1XxFTl++gpq+7gbOjwyAZkBFnNgVoldLpdDoVBoLFSana0Nmtb3wd6j5zXa9/12vtxzi80b+2Pfb5r99xxNxgsNfGFrYw0AaNHYv9Q29xw5jxbP1y43lod5+bh45Qa8XJWVORSiSssvKETS+VS0D6mv0d6uRf1y55qUpXFATdzg7HfLIJHMblZD8aS94X07YNiUNXihgS+aN/bHV98fwtX0Wxjwz3Xp077YirSb2VgyrR8AYOAbL2L5twcQM38T+nVvjWOnL2Pt1gQsnxGl3ua7b7XDK+8uwIKv4vFy28bYsf809v92Hj8tH6vuM2nBZnRp0xg1vZxx8/ZdzF2xEzm5D/DWqyHqPrezc3E1/TbS/vlhWXx9sIfro1n0RIYSu34Plkzrh5PnUnDs9GX0f701anq5YNWmR1eHTH7/NVR3V+K9qV8DAIb1aYeU67dw/q802Nlao1dEC3QLewGRH32p3qatjTUCans9+rutDbzdq6FRvRrIvfcQl69mPv2DJCrBpIn97t27+PPPP9WvL1++jKSkJLi4uMDX19eEkZm/N8KDcSs7F3OW/4QbmSoE1qmOuAXD4VvdBQBwI1OFq49d0+5Xww3fLngPE+ZvwvKNB+HlrsTsD3vitQ4vqPuENKmNFTMGYMbiHzFzyY/wr+mGlTMHolmjWuo+1zLuYPDEVci6kws356po1qgWfl45Tr1fAPjpwGm8P32t+vWgmFUAgP8bEoHxQ18x1kdCEvR9/Am4KB3x0eAIeLopkHwpDb1HxyI1/TYAwNNNgZpe/3437Wxs8PEHr6O6uxIPHubj/F9p6PVBLOIPn1P38XJX4uC6aPXrkZEdMTKyI35N/ANdhy18egdHOpPKDWpkorxZJE/Bvn370L59+1Lt/fv3x+rVq5+4vkqlglKpxI2sbA7Lk8Vybj7C1CEQGY0ozMPD018iO9t4P8eLc8XupBRUdar8Pu7mqBDW1NeosRqCSSv2du3alTs7lYiIiHTHc+xERCQJvEENERGRJZFIZmdiJyIiSZDK5Dmzuo6diIiIKsaKnYiIJEHfR6+ay2NbmdiJiEgSJHKKnUPxREREloQVOxERSYNESnYmdiIikgTOiiciIiKzw4qdiIgkQSqz4lmxExGRJJjqceyxsbHw9/eHvb09goODcfDgwXL7pqWloW/fvggICICVlRVGjx6t8/6Y2ImIiIwkLi4Oo0ePRkxMDE6ePIk2bdogIiICKSkpZfZ/+PAh3N3dERMTgyZNmlRqn0zsREQkDSYo2efNm4dBgwZh8ODBCAwMxIIFC+Dj44PFixeX2b9WrVpYuHAh+vXrB6VSqfsOwcROREQSITPAH13k5eUhMTER4eHhGu3h4eE4fPiwIQ9NAyfPERGRJBhq8pxKpdJol8vlkMvlpfpnZmaisLAQnp6eGu2enp5IT0+vfCBPwIqdiIhIBz4+PlAqlepl1qxZFfaXlfhtQghRqs2QWLETEZEkGOrGc6mpqVAoFOr2sqp1AHBzc4O1tXWp6jwjI6NUFW9IrNiJiEgaDDR5TqFQaCzlJXY7OzsEBwcjPj5eoz0+Ph6tWrUy9NGpsWInIiIykrFjxyIyMhLNmjVDaGgoli1bhpSUFAwbNgwAEB0djWvXrmHNmjXqdZKSkgAAd+/exc2bN5GUlAQ7Ozs0aNBAq30ysRMRkSSY4l7xvXv3RlZWFqZPn460tDQ0atQIO3bsgJ+fH4BHN6QpeU37Cy+8oP57YmIi1q9fDz8/P1y5ckWrfTKxExGRJJjqlrLDhw/H8OHDy3xv9erVpdqEEJXb0T94jp2IiMiCsGInIiJJkMjj2JnYiYhIIiSS2TkUT0REZEFYsRMRkSSYYla8KTCxExGRJJhqVvzTxsRORESSIJFT7DzHTkREZElYsRMRkTRIpGRnYiciIkmQyuQ5DsUTERFZEFbsREQkDXrOijeTgp2JnYiIpEEip9g5FE9ERGRJWLETEZE0SKRkZ2InIiJJ4Kx4IiIiMjus2ImISBJ4r3giIiILIpFT7EzsREQkERLJ7DzHTkREZEFYsRMRkSRIZVY8EzsREUmCDHpOnjNYJMbFoXgiIiILwoqdiIgkQSJz55jYiYhIGqRyHTuH4omIiCwIK3YiIpIIaQzGM7ETEZEkcCieiIiIzA4rdiIikgRpDMQzsRMRkURIZSieiZ2IiCRBKreU5Tl2IiIiC8KKnYiIpEEiJ9mZ2ImISBIkktc5FE9ERGRJWLETEZEkcFY8ERGRBeGseCIiIjI7rNiJiEgaJDJ7jomdiIgkQSJ5nUPxREREloQVOxERSQJnxRMREVkU/WbFm8tgPBM7ERFJglQqdp5jJyIisiBM7ERERBaEQ/FERCQJHIonIiIis8OKnYiIJEEq94pnYiciIkngUDwRERGZHVbsREQkCVK5VzwTOxERSYNEMjuH4omIiCwIK3YiIpIEzoonIiKyIFKZFc/ETkREkiCRU+w8NNdD5gAACLxJREFUx05ERGRJWLETEZE0SKRkZ2InIiJJkMrkOQ7FExERWRCzrtiFEACAHJXKxJEQGY8ozDN1CERGU/z9Lv55bkw5OSq9Zrbn5JhHrjHrxJ6TkwMAqOvvY+JIiIhIHzk5OVAqlUbZtp2dHby8vPCcAXKFl5cX7OzsDBCV8cjE0/g1yUiKiopw/fp1ODk5QWYuFxiaOZVKBR8fH6SmpkKhUJg6HCKD4vf76RNCICcnB97e3rCyMt7Z4QcPHiAvT//RLzs7O9jb2xsgIuMx64rdysoKNWvWNHUYkqRQKPiDjywWv99Pl7Eq9cfZ29s/8wnZUDh5joiIyIIwsRMREVkQJnbSiVwux5QpUyCXy00dCpHB8ftNlsCsJ88RERGRJlbsREREFoSJnYiIyIIwsRMREVkQJnYiIiILwsROWouNjYW/vz/s7e0RHByMgwcPmjokIoM4cOAAunbtCm9vb8hkMmzZssXUIRFVGhM7aSUuLg6jR49GTEwMTp48iTZt2iAiIgIpKSmmDo1Ib7m5uWjSpAm++OILU4dCpDde7kZaCQkJQVBQEBYvXqxuCwwMRPfu3TFr1iwTRkZkWDKZDN9//z26d+9u6lCIKoUVOz1RXl4eEhMTER4ertEeHh6Ow4cPmygqIiIqCxM7PVFmZiYKCwvh6emp0e7p6Yn09HQTRUVERGVhYietlXw0rhCCj8slInrGMLHTE7m5ucHa2rpUdZ6RkVGqiiciItNiYqcnsrOzQ3BwMOLj4zXa4+Pj0apVKxNFRUREZbExdQBkHsaOHYvIyEg0a9YMoaGhWLZsGVJSUjBs2DBTh0akt7t37+LPP/9Uv758+TKSkpLg4uICX19fE0ZGpDte7kZai42NxZw5c5CWloZGjRph/vz5eOmll0wdFpHe9u3bh/bt25dq79+/P1avXv30AyLSAxM7ERGRBeE5diIiIgvCxE5ERGRBmNiJiIgsCBM7ERGRBWFiJyIisiBM7ERERBaEiZ2IiMiCMLETPQOmTp2Kpk2bPtXtRUVF8ZnjRBaIiZ2oAlFRUZDJZJDJZLC1tUXt2rXx4YcfIjc319ShVejDDz/E7t27TR0GEZkA7xVP9ARdunTBqlWrkJ+fj4MHD2Lw4MHIzc3F4sWLNfrl5+fD1tbWRFFqqlq1KqpWrWrqMIjIBFixEz2BXC6Hl5cXfHx80LdvX7z99tvYsmWLerh75cqVqF27NuRyOYQQyM7OxtChQ+Hh4QGFQoEOHTrg1KlTGtucPXs2PD094eTkhEGDBuHBgwel9rtq1SoEBgbC3t4e9evXR2xsrMb7V69exVtvvQUXFxc4OjqiWbNmOHr0KIDSQ/GFhYUYO3YsqlWrBldXV3z00UcoeTfphw8fYtSoUfDw8IC9vT1efPFFHDt2zFAfIxE9JUzsRDpycHBAfn4+AODPP//Et99+i02bNiEpKQn/394dhES1xXEc/045Eo1paWF3rMSaiAkskiG5FIoURLVoIihchKEtcpOhNC0kJihtMmoTESIJLmwRRBAxoBC0cFEwY7qIWU0uApUkS5KwRua06L1LN3vPHvjeq+H3gVn8zznzP2fO5s+9514G4PDhw0xOThKPx0kmk1RVVbFv3z6mp6cBuH//PtFolI6ODhKJBJZlLSjaPT09tLe309HRQSqVorOzk4sXL9LX1wd8/Tey2tpaxsfHefToEaOjo0QiEbLZ7A/XfOPGDXp7e7l79y5DQ0NMT0/z8OFD15hIJMKDBw/o6+tjeHiYQCDAgQMHnHWLyG/CiMhfamhoMEeOHHHi58+fm5KSEnP8+HETjUaN1+s1b968cfqfPHliCgsLzdzcnCvPli1bTHd3tzHGGNu2zZkzZ1z91dXVZufOnU68ceNGc+/ePdeYy5cvG9u2jTHGdHd3m1WrVpm3b9/+cN3RaNSVz7IsE4vFnDiTyZgNGzY4v212dtZ4vV7T39/vjPn8+bPx+/2mq6vrb3ZIRH41umIXWcTjx48pKChgxYoV2LZNTU0Nt27dAqC8vJx169Y5Y5PJJLOzs5SUlDjn3AUFBYyNjZFOpwFIpVLYtu2a49t4amqK169f09TU5Mpx5coVJ8fIyAi7du2iuLh40fXPzMwwMTHhmiMvL49QKOTE6XSaTCbDnj17nDav18vu3btJpVL/ZLtE5H+mh+dEFlFXV8edO3fwer34/X7XA3I+n881NpvNYlkWT58+XZBn9erVPzXfn7fTe3p6qK6udvUtX74c+HocsJTMH+ftHo9nQfv3bSLya9MVu8gifD4fgUCA8vLyRZ96r6qqYnJykry8PAKBgOuzdu1aAILBIM+ePXN979u4tLSUsrIyXr16tSBHRUUFADt27GBkZOSnzr+LioqwLMs1x/z8PMlk0okDgQD5+fkMDQ05bZlMhkQiQTAYXHQOEfl16IpdZAnt378f27YJh8Ncu3aNbdu2MT4+TjweJxwOEwqFaGlpoaGhgVAoxN69e+nv7+fly5ds3rzZyXPp0iXOnj1LYWEhBw8e5NOnTyQSCd69e0drayv19fV0dnYSDoe5evUqlmXx4sUL/H7/gtv8AC0tLcRiMbZu3UowGOTmzZu8f//e6ff5fDQ3N3P+/HmKi4vZtGkTXV1dfPz4kaampv9k70Rkaaiwiywhj8dDPB6nvb2dxsZGpqamWL9+PTU1NZSWlgJw4sQJ0uk0Fy5cYG5ujmPHjtHc3MzAwICT5/Tp06xcuZLr168TiUTw+XxUVlZy7tw5APLz8xkcHKStrY1Dhw4xPz/P9u3buX379g/X1dbWxsTEBKdOnWLZsmU0NjZy9OhRZmZmnDGxWIxsNsvJkyf58OEDoVCIgYEB1qxZ8y/umIgsNY8x373MKiIiIr8tnbGLiIjkEBV2ERGRHKLCLiIikkNU2EVERHKICruIiEgOUWEXERHJISrsIiIiOUSFXUREJIeosIuIiOQQFXYREZEcosIuIiKSQ1TYRUREcsgXHtI5ywKkWkkAAAAASUVORK5CYII=",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "cm = confusion_matrix(y_test, predictions, normalize='all')\n",
    "cmd = ConfusionMatrixDisplay(cm, display_labels=[0, 1])\n",
    "cmd.plot(cmap=plt.cm.Blues)\n",
    "cmd.ax_.set(xlabel='Predecido', ylabel='Verdadero', title='Matriz de confision modelo XGBoost')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 123,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[Text(0, 0.5, 'Verdadero'),\n",
       " Text(0.5, 0, 'Predecido'),\n",
       " Text(0.5, 1.0, 'Matriz de confision modelo Random Forest')]"
      ]
     },
     "execution_count": 123,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAfYAAAHFCAYAAAAABdu/AAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAAPYQAAD2EBqD+naQAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjAsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy8GearUAAAgAElEQVR4nOzdeXxM1/sH8M9kmywyQyKZJCQRFLFUCCK0iCWalm6U0iKqVVX1U7pI7Vql2qKqsS+lpVEhVBWxb2lLSKsa2ipNkIhEmQjZJuf3h2a+JpuZzEzGzP28ve7rJWfOnfvcyZ158px77lyZEEKAiIiIbIKdpQMgIiIi02FiJyIisiFM7ERERDaEiZ2IiMiGMLETERHZECZ2IiIiG8LETkREZEOY2ImIiGwIEzsREZENsfnEvmbNGshkMshkMhw4cKDc40IING7cGDKZDN26davWNmJjY7FmzRqD1jlw4EClMZnK9OnTIZPJzPb8NWny5MkICAiAg4MDateuDQDo1q2bwb+zmnjdH1Sl74WLFy8avK6pj6V735cymQwODg7w9fXF888/jz///NNk2zHUg/aeKT1eK1r69+9v6fAqVJ3PQzItB0sHUFPc3d2xcuXKcong4MGDOH/+PNzd3av93LGxsahbty6io6P1Xqdt27ZISkpC8+bNq71dqdi6dStmzZqFSZMmISoqCnK5HMDd191QfN0fLKtXr0azZs2Qn5+Po0ePYtasWdi/fz/Onj2LOnXqWDq8B8aHH36IiIgInTZPT08LRVO16nwekmlJJrEPHDgQX3/9Nb744gsoFApt+8qVKxEeHg61Wl0jcRQVFUEmk0GhUKBjx441sk1r99tvvwEAxo4dC29vb217dZIzX/cHS8uWLdGuXTsAd0dgNBoNpk2bhoSEBAwfPtzC0T04HnroIbMct3fu3IGzs/MDNUpBxrP5ofhSgwYNAgBs2LBB23bz5k3Ex8fjpZdeqnCdGTNmICwsDB4eHlAoFGjbti1WrlyJe++b06BBA5w5cwYHDx7UDpE1aNAAwP+G0datW4cJEyagXr16kMvl+Ouvv8oNCV+8eLHSITd93nTff/89QkJCIJfLERQUhE8++aTCfkIIxMbGIiQkBC4uLqhTpw769++Pv//+W5+XEWfPnsWgQYOgUqkgl8sREBCAoUOHoqCgQNvnt99+w1NPPYU6derA2dkZISEh+PLLL3Wep3T/N2zYgEmTJsHPzw8KhQI9e/bEuXPndF7fyZMnAwBUKhVkMhmmT58OoOKh+MWLF6N169aoVasW3N3d0axZM7z33nvltlt2KH7btm0IDw+Hq6sr3N3d0atXLyQlJen0KR2mPXPmDAYNGgSlUgmVSoWXXnoJN2/evO9r161bN7Rs2RJJSUno1KkTXFxc0KBBA6xevRrA3d9h27Zt4erqilatWmHnzp3lnuPIkSPo0aMH3N3d4erqik6dOuH7778v1+/HH39E586d4ezsDD8/P8TExKCoqKjCuOLi4hAeHg43NzfUqlULvXv3xqlTp+67PyUlJZg7dy6aNWsGuVwOb29vDB06FJcuXbrvupUpTfJXr17VtuXn52PChAkICQmBUqmEh4cHwsPDsXXr1nLry2QyjBkzBuvWrUNwcDBcXV3RunVrbN++vVxffd8z+fn5iImJQVBQEJycnFCvXj28/vrruHHjhk6/Bg0aoE+fPti+fTvatGkDFxcXBAcHa7e9Zs0aBAcHw83NDR06dMCJEyeq/TqVpc9xUXr6Y/fu3XjppZfg5eUFV1dX7XtXn+Pg77//xvPPPw8/Pz/I5XKoVCr06NEDKSkp2tegss9DqkHCxq1evVoAEMePHxdDhgwRHTp00D62ePFi4ebmJtRqtWjRooXo2rWrzrrR0dFi5cqVIjExUSQmJor3339fuLi4iBkzZmj7nDx5UjRs2FC0adNGJCUliaSkJHHy5EkhhBD79+8XAES9evVE//79xbZt28T27dtFTk6O9rH9+/cLIYTIz8/Xrl+6bNu2TSgUChEcHFzlPu7Zs0fY29uLRx55RGzevFl8++23on379iIgIECU/RW/8sorwtHRUUyYMEHs3LlTrF+/XjRr1kyoVCqRmZlZ5XZSUlJErVq1RIMGDcSSJUvE3r17xVdffSUGDBgg1Gq1EEKIs2fPCnd3d9GoUSOxdu1a8f3334tBgwYJAOKjjz7SPlfp/jdo0EC88MIL4vvvvxcbNmwQAQEB4qGHHhLFxcXa13fEiBECgNi5c6dISkoS6enpQgghunbtqvM727BhgwAg3njjDbF7926xZ88esWTJEjF27Nhy2y193YUQ4uuvvxYARGRkpEhISBBxcXEiNDRUODk5icOHD2v7TZs2TQAQTZs2FVOnThWJiYli3rx5Qi6Xi+HDh1f52pXG6+npKZo2bSpWrlwpdu3aJfr06SMAiBkzZohWrVqJDRs2iB07doiOHTsKuVwuLl++rF3/wIEDwtHRUYSGhoq4uDiRkJAgIiMjhUwmE998842235kzZ4Srq6to3ry52LBhg9i6davo3bu39ni4cOGCtu+sWbOETCYTL730kti+fbvYvHmzCA8PF25ubuLMmTPl9v1eI0eOFADEmDFjxM6dO8WSJUuEl5eX8Pf3F9euXavytbj3fXmvRYsWCQAiPj5e23bjxg0RHR0t1q1bJ/bt2yd27twp3nrrLWFnZye+/PJLnfVLj6kOHTqIjRs3ih07dohu3boJBwcHcf78eW0/fd8zJSUlonfv3sLBwUFMmTJF7N69W3zyySfCzc1NtGnTRuTn52v7BgYGivr164uWLVtqf49hYWHC0dFRTJ06VXTu3Fls3rxZbNmyRTRp0kSoVCpx+/btKl+n0uM1Li5OFBUV6Syl9D0uSl/zevXqiZEjR4offvhBbNq0SRQXF+t9HDRt2lQ0btxYrFu3Thw8eFDEx8eLCRMmaN9PVX0eUs2RVGIvfZP89ttvQggh2rdvL6Kjo4UQosLEfi+NRiOKiorEzJkzhaenpygpKdE+Vtm6pdvr0qVLpY/dm2DulZeXJzp06CB8fX3FxYsXq9zHsLAw4efnJ+7cuaNtU6vVwsPDQ+dDKikpSQAQn376qc766enpwsXFRbzzzjtVbqd79+6idu3aIisrq9I+zz//vJDL5SItLU2nPSoqSri6uoobN24IIf63/48//rhOv40bNwoAIikpSdtWmlTKJouyiX3MmDGidu3aVe5D2dddo9EIPz8/0apVK6HRaLT9cnNzhbe3t+jUqVO5OObOnavznKNHjxbOzs46x0RFunbtKgCIEydOaNtycnKEvb29cHFx0UniKSkpAoBYuHChtq1jx47C29tb5ObmatuKi4tFy5YtRf369bXbHzhwoHBxcdH5Q624uFg0a9ZMJ7GnpaUJBwcH8cYbb+jEmZubK3x8fMSAAQPK7Xup1NRUAUCMHj1aZ92ffvpJABDvvfdela9F6fvyxx9/FEVFRSI3N1fs3LlT+Pj4iC5duugkrrKKi4tFUVGRGDFihGjTpo3OYwCESqXS/qEphBCZmZnCzs5OzJ49W9um73tm586dFf7O4+LiBACxbNkybVtgYKBwcXERly5d0raV/h59fX1FXl6etj0hIUEAENu2bavydSo9Xita/vzzTyGE/sdF6Ws+dOhQnW3oexxkZ2cLAGLBggVVxny/z1IyP8kMxQNA165d0ahRI6xatQqnT5/G8ePHKx2GB4B9+/ahZ8+eUCqVsLe3h6OjI6ZOnYqcnBxkZWXpvd1+/foZFKdGo8HAgQORmpqKHTt2IDAwsNK+eXl5OH78OJ599lk4Oztr293d3dG3b1+dvtu3b4dMJsOLL76I4uJi7eLj44PWrVtXOVP89u3bOHjwIAYMGAAvL69K++3btw89evSAv7+/Tnt0dDRu375dbnj7ySef1Pn54YcfBgD8888/lW6jMh06dMCNGzcwaNAgbN26FdnZ2fdd59y5c7hy5QqGDBkCO7v/vR1q1aqFfv364ccff8Tt27fvG3N+fr5ex4Svry9CQ0O1P3t4eMDb2xshISHw8/PTtgcHBwP43+uQl5eHn376Cf3790etWrW0/ezt7TFkyBBcunRJewpj//796NGjB1QqlU6/gQMH6sSya9cuFBcXY+jQoTrHg7OzM7p27Vrl8bB//34AKDdBqkOHDggODsbevXvv+1oAQMeOHeHo6Ah3d3c89thjqFOnDrZu3QoHB93pP99++y06d+6MWrVqwcHBAY6Ojli5ciVSU1PLPWdERITOZFiVSgVvb2+d11Lf98y+ffsq3M/nnnsObm5u5fYzJCQE9erV0/5c+nvs1q0bXF1dy7Xre5x/9NFHOH78uM7i7+9v0HFRquznkb7HgYeHBxo1aoSPP/4Y8+bNw6lTp1BSUqJX/FSzJDN5Drh7/m348OFYuHAh8vPz0aRJEzz66KMV9v35558RGRmJbt26Yfny5ahfvz6cnJyQkJCAWbNm4c6dO3pv19fX16A4R40ahZ07d2rPAVbl33//RUlJCXx8fMo9Vrbt6tWrEELofODfq2HDhlVuR6PRoH79+lXGk5OTU+H+liatnJwcnfayM3tLZ7wb8vqWGjJkCIqLi7F8+XL069cPJSUlaN++PT744AP06tWr0niBin9Hfn5+KCkpwb///qvzoWxMzB4eHuXanJycyrU7OTkBuHt+F7j7+gsh9Hptc3Jy9D4eAKB9+/YVxnrvHzpl3e910zdhrV27FsHBwcjNzUVcXByWLl2KQYMG4YcfftD22bx5MwYMGIDnnnsOb7/9Nnx8fODg4IDFixdj1apV5Z6zotnicrlc+/sx5D2Tk5MDBweHcn/MymQy+Pj4lDueK/s93u/3ez8NGzbUzj+417Vr1/Q+LkqV7avvcSCTybB3717MnDkTc+fOxYQJE+Dh4YEXXngBs2bNMurKIjItSSV24O5f3lOnTsWSJUswa9asSvt98803cHR0xPbt23X+qk9ISDB4m4bMOJ0+fTpWrFiB1atXIzIy8r7969SpA5lMhszMzHKPlW2rW7cuZDIZDh8+rE1G96qorZSHhwfs7e3vOzHK09MTGRkZ5dqvXLmijcGchg8fjuHDhyMvLw+HDh3CtGnT0KdPH/zxxx8VjnyUJoHKYrazs3sgLruqU6cO7Ozs9HptPT099T4eAGDTpk1VjgpV5N7Xrewfe1euXNH79xwcHKxNWBEREdBoNFixYgU2bdqkvU77q6++QlBQEOLi4nTeS/dO2DSEIe8ZT09PFBcX49q1azrJXQiBzMzMSpNhTTHkuChV9vPIkOMgMDAQK1euBAD88ccf2LhxI6ZPn47CwkIsWbKk2vtBpiWpoXgAqFevHt5++2307dsXw4YNq7Rf6Zdm2Nvba9vu3LmDdevWlet7bzVgjJUrV2LGjBmYOXOm3teAls6w3bx5s85f/7m5ufjuu+90+vbp0wdCCFy+fBnt2rUrt7Rq1arS7bi4uKBr16749ttvqxzi7tGjB/bt26f9UCm1du1auLq61tilZm5uboiKisKkSZNQWFiIM2fOVNivadOmqFevHtavX69ztUNeXh7i4+O1M+Utzc3NDWFhYdi8ebPOsVZSUoKvvvoK9evXR5MmTQDcTZB79+7VmVmu0WgQFxen85y9e/eGg4MDzp8/X+HxUFGFWKp79+4A7ibdex0/fhypqano0aNHtfZz7ty5qFOnDqZOnaod5pXJZHByctJJSJmZmRXOiteHIe+Z0v0ou5/x8fHIy8ur9n6aiiHHRWWqexw0adIEkydPRqtWrXDy5Eltu6k+D6n6JFexA8CcOXPu2+eJJ57AvHnzMHjwYIwcORI5OTn45JNPKqxqW7VqhW+++QZxcXFo2LAhnJ2dq0ySFUlKSsKoUaPQuXNn9OrVCz/++KPO41UlxPfffx+PPfYYevXqhQkTJkCj0eCjjz6Cm5sbrl+/ru3XuXNnjBw5EsOHD8eJEyfQpUsXuLm5ISMjA0eOHEGrVq3w2muvVbqdefPm4ZFHHkFYWBgmTpyIxo0b4+rVq9i2bRuWLl0Kd3d3TJs2Ddu3b0dERASmTp0KDw8PfP311/j+++8xd+5cKJVKg14XQ7zyyitwcXFB586d4evri8zMTMyePRtKpbLKYca5c+fihRdeQJ8+ffDqq6+ioKAAH3/8MW7cuKHXsVJTZs+ejV69eiEiIgJvvfUWnJycEBsbi99++w0bNmzQJr7Jkydj27Zt6N69O6ZOnQpXV1d88cUXyMvL03m+Bg0aYObMmZg0aRL+/vtv7Tnuq1ev4ueff4abmxtmzJhRYSxNmzbFyJEj8fnnn8POzg5RUVG4ePEipkyZAn9/f7z55pvV2sc6deogJiYG77zzDtavX48XX3wRffr0webNmzF69Gj0798f6enpeP/99+Hr61vtb6nT9z3Tq1cv9O7dG++++y7UajU6d+6MX3/9FdOmTUObNm0wZMiQam3flPQ9Liqj73Hw66+/YsyYMXjuuefw0EMPwcnJCfv27cOvv/6KiRMnap/PFJ+HZCRLztyrCZVdVlNWRTM5V61aJZo2bSrkcrlo2LChmD17tli5cmW5S4YuXrwoIiMjhbu7uwAgAgMDhRD/m9H67bffltte2dnZpXFWttzPtm3bxMMPPyycnJxEQECAmDNnToWXKJXuV1hYmHBzcxMuLi6iUaNGYujQoTqztSvz+++/i+eee054enpqtxUdHa1z2c/p06dF3759hVKpFE5OTqJ169Zi9erVFe5/2dfmwoULAoBOf31nxX/55ZciIiJCqFQq4eTkJPz8/MSAAQPEr7/+Wm67Za9GSEhIEGFhYcLZ2Vm4ubmJHj16iKNHj+r0qSyO0t/dvcdERbp27SpatGhRrj0wMFA88cQT5doBiNdff12n7fDhw6J79+7a313Hjh3Fd999V27do0ePai+Z8/HxEW+//bZYtmxZhXEmJCSIiIgIoVAohFwuF4GBgaJ///5iz5495fb9XhqNRnz00UeiSZMmwtHRUdStW1e8+OKL2ssRq1LV+/LOnTvlLnucM2eOaNCggZDL5SI4OFgsX768wpgqes2EuPsaDxs2TKdN3/fMnTt3xLvvvisCAwOFo6Oj8PX1Fa+99pr4999/y21D399j6XH+8ccfV/4iiao/Q+6lz3Fxv8/C+x0HV69eFdHR0aJZs2bCzc1N1KpVSzz88MNi/vz52t+TEJV/HlLNkQlxz/gjERERWTXJnWMnIiKyZUzsRERENoSJnYiIyIYwsRMREdkQJnYiIiIbwsRORERkQ6z6C2pKSkpw5coVuLu7G/S1rURE9GAQQiA3Nxd+fn5V3p/AWPn5+SgsLDT6eZycnHS+ZvxBZNWJ/cqVK+XuIkZERNYnPT39vjeZqq78/Hy4uHsCxbfv3/k+fHx8cOHChQc6uVt1Yi+9m5BThzchc6j8BiZE1uzC1on370RkpXJz1WjaMMCsd4crLCwEim9D3nwYYO9U/SfSFCLz9y9RWFjIxG4upcPvMgc5ZA4P7otMZAyFQmHpEIjMrkZOpzo4Q2ZEYhcy65iWZh1REhERkV6sumInIiLSmwyAMSMDVjJHm4mdiIikQWZ3dzFmfSvAxE5ERNIgkxlZsVtHyW4df34QERGRXlixExGRNHAonoiIyIZwKJ6IiIisDSt2IiKSCCOH4q2kFmZiJyIiaeBQPBEREVkbVuxERCQNnBVPRERkQzgUT0RERNaGFTsREUkDh+KJiIhsiESG4pnYiYhIGiRSsVtHlERERKQXVuxERCQNMpmRFTuH4omIiB4cdrK7izHrWwEOxRMREdkQVuxERCQNEpk8x8RORETSIJHL3azjzw8iIiLSCyt2IiKSBg7FExER2RCJDMUzsRMRkTRIpGK3jiiJiIhIL6zYiYhIGjgUT0REZEM4FE9ERETWhhU7ERFJA4fiiYiIbImRQ/FWMshtHVESERGRXlixExGRNHAonoiIyIbIZEbOireOxM6heCIiIhvCip2IiKRBItexM7ETEZE08Bw7ERGRDZFIxW4dURIREZFeWLETEZE0cCieiIjIhnAonoiIiKwNK3YiIpIGDsUTERHZDplMBpkEEjuH4omIiGwIK3YiIpIEqVTsTOxERCQNsv8WY9a3AhyKJyIisiGs2ImISBI4FE9ERGRDmNiJiIhsiFQSO8+xExER2RBW7EREJAlSqdiZ2ImISBp4uRsRERFZG1bsREQkCRyKJyIisiF3b+5mTGI3XSzmxKF4IiIiG8KKnYiIJEEGI4firaRkZ2InIiJJkMo5dg7FExER2RBW7EREJA28jp2IiMiG/DcUX92lukPxsbGxCAoKgrOzM0JDQ3H48GG91jt69CgcHBwQEhJi0PaY2ImISBKMSerVPT8fFxeHcePGYdKkSTh16hQeffRRREVFIS0trcr1bt68iaFDh6JHjx4Gb5OJnYiIyEzmzZuHESNG4OWXX0ZwcDAWLFgAf39/LF68uMr1Xn31VQwePBjh4eEGb5OJnYiIJMFUFbtardZZCgoKKtxeYWEhkpOTERkZqdMeGRmJY8eOVRrn6tWrcf78eUybNq1a+8nETkRE0iAzwQLA398fSqVSu8yePbvCzWVnZ0Oj0UClUum0q1QqZGZmVrjOn3/+iYkTJ+Lrr7+Gg0P15rdzVjwREZEB0tPToVAotD/L5fIq+5c9Ny+EqPB8vUajweDBgzFjxgw0adKk2vExsRMRkSQY+wU1pesqFAqdxF6ZunXrwt7evlx1npWVVa6KB4Dc3FycOHECp06dwpgxYwAAJSUlEELAwcEBu3fvRvfu3e+7XSZ2IiKSBFMldn05OTkhNDQUiYmJeOaZZ7TtiYmJeOqpp8r1VygUOH36tE5bbGws9u3bh02bNiEoKEiv7TKxExERmcn48eMxZMgQtGvXDuHh4Vi2bBnS0tIwatQoAEBMTAwuX76MtWvXws7ODi1bttRZ39vbG87OzuXaq8LETkREklDTFTsADBw4EDk5OZg5cyYyMjLQsmVL7NixA4GBgQCAjIyM+17TbnCcQghh0mesQWq1GkqlEvJOEyFzcLZ0OERmkZ041dIhEJmNWq2Gn1dt3Lx5U6/z1tXdhlKphCp6HeycXKv9PCWFt3F1zRCzxmoKvNyNiIjIhnAonoiIpEEiN4FhYiciIkmwxDl2S2BiJyIiSZBKYuc5diIiIhvCip2IiCRBKhU7EzsREUmDRCbPcSieiIjIhrBiJyIiSeBQPEnCiCfb4Y0BnaDydMfZi1l4L3YXkk7f/+sNw1r4Y/v8aKReyEKXV5fqPKZwk2PKiB7o80gz1HZ3wT8Z/2LKkt1I/Pkvc+0GEQBg1aZDWPTVXlzNUaNpkC9mvfkswts0rrT/0ZN/YsqCLTh3IQM+dZUYM6Qnhj/7iPbxtQlHsXHHz0j9OwMA0LqZPya/1hdtWzTQeZ6MrBuY8cVW7D32O/ILitAowBsLJg1GSHCAWfaTqkcqid3iQ/GxsbEICgqCs7MzQkNDcfjwYUuHJBnPdGuBD0c/hk/XH0bXV5ci6XQaNs5+AfW9q/6qRIWbHIsnPo2DJ/8u95ijgx22zB2CAJUS0TO+RYdhizBu3nfIyM41124QAQC2JCZj0vzNeHN4b+xf+y7CQxrh+TcX41Lm9Qr7/3MlG4PeXILwkEbYv/ZdjIuOxHufbsJ3+1K0fY6e/AvPRoYiIXYsdq4Yj/oqD/QfG4uMrBvaPjfUt/H4yPlwtLdH3ILXcPSbSZj5f89A6e5i9n0mqohFK/a4uDiMGzcOsbGx6Ny5M5YuXYqoqCj8/vvvCAjgX7rmNrp/R3z1wyms23EKAPBe7C50b9cIL/Vtj5kr91a63vw3+2DT3t+gKSnBE52b6Tz24mNtUEfhgt5jV6FYUwIASM+6ab6dIPrP4g378cKT4RjyVCcAwKzx/bDvp1Ssjj+CKa8/Wa7/ms1HUc+nDmaN7wcAaBLkg5TUNHzx9V707R4CAFg6c5jOOvPfG4Rt+1Jw6MQ5DHw8DACwcF0i6nnXxudTX9T2C/DzNMs+knFkMLJit5LZcxat2OfNm4cRI0bg5ZdfRnBwMBYsWAB/f38sXrzYkmFJgqODHUKa+GHfifM67fuT/0aHFvUrXW9w7xA08K2Dj9YeqPDxqE5Ncfz3S/h47OM4t2kCjq14DeMHPwI7O+t4Q5B1Kiwqxi9n0xERpvuHZkSHZvj59IUK1zl++gIiOuj2794xGCmpaSgq1lS4zu38QhRrNKitcNO27Tz0G1oHB+ClmJVo9lgMIoZ8hLUJR43cIzKH0qF4YxZrYLHEXlhYiOTkZERGRuq0R0ZG4tixYxaKSjo8la5wsLfDtX9v6bRf+/cWvD1qVbhOw3oemPZKD4ycvRmakopvChjoWwdPdmkOe3s7DIhZj0++PoTXnwvHhBceNfk+EJXKuZEHjaYEXh7uOu1enu7IylFXuE5WjhpenmX6e7ijWFOCnBu3Klzn/S+2wddLia7tm2rb/rmSjTWbj6Chvxc2fjYaw57pjPfmxSNux09G7hVR9VhsKD47OxsajQYqlUqnXaVSITMzs8J1CgoKUFBQoP1Zra74DUv6K5ueZZChohv52tnJsPy9ZzFnzQGcv1TxOcvSftn/5mHcvO9QUiLwy58Z8PF0xxsDOuHjdYdMGzxRGWUrKiGAqoqsskOrpcd+RZXZwnV7sDkxGVtjx8JZ7qhtLykRCAkOwOTRd4f7H27qj3MXMrE6/oh2uJ4eEBK5jt3is+LLvxFFpcMds2fPxowZM2oiLJuXc/M2ijUl8K6jW53XreNWrooHgFouTmjbrB4efsgXc8c+DgCwk8lgZyfDtd1T8Ow763A45SKu5uSiqLgEJfdU9H+kZcPH0x2ODnYoKi4x746RJHnWdoO9vV256jz7ei68PCqeDOrtqSjf/99cONjbwUPpptO+6Ku9WLBmN+IXjUGLh+rpPKaqq0CTIB+dtocaqPDd/hTQg4Wz4s2sbt26sLe3L1edZ2VllaviS8XExODmzZvaJT09vSZCtUlFxSVI+eMKIkIb6rR3C22In89cKtc/93YBOo2IRZeRS7TL6u9O4I+0bHQZuQTJZy8DAGlZLEIAACAASURBVH46k46G9Tx0qqRG9T2RkZ3LpE5m4+TogNbN/HHg57M67Qd+PocOrYIqXKd9qyAc+PmcTtv+n84iJDgAjg722rbP1+3Bp6t2YuOC19CmgsvXOjzcEOf/uarTdj4tC/4+HtXdHTITnmM3MycnJ4SGhiIxMVGnPTExEZ06dapwHblcDoVCobNQ9cVu+hFDHm+LFx4LQZOAupj1Wm/U91Zi9XcnAABTR/TA4nefBnB3iDL14jWd5dqNPBQUFiP14jXczi8CAKzadgJ1FC6Y83oUGtX3QGTYQxg/+BGs3HrcYvtJ0vDaoAh8tTUJX29Lwh8XMjFpfjwuX72O6P+uS3//i20YPX2ttn/0s51xKfM6Ji/YjD8uZOLrbXfXff2FHto+C9ftweyl32Ph5Bfg7+eJqzlqXM1R49bt/50SHDUoAid+u4j5a3bh7/Rr2LTrBNYlHMNL/TmvhCzDokPx48ePx5AhQ9CuXTuEh4dj2bJlSEtLw6hRoywZlmRsOXAGHgoXvDOkK1QetZB6MQsDY77WXp6m8qyF+t5Kg57z8jU1+r37FWa91htHlr+GjGw1lm7+CQu+4SxhMq9neoXi35t5+GTVTlzNVqNZQ19smP8a/H3vVs5Xc27i0tV/tf0D/epiw/xRmLxgM1ZtOgyfugp8OKG/9lI3AFgdfxiFRcUYHrNSZ1tvvxyFd1+5e0qqbfNAfDn3FXwQuw2frNyJAD9PfPDms3jusfY1sNdkCJms6jkX+qxvDWRCVDRVqubExsZi7ty5yMjIQMuWLTF//nx06dJFr3XVajWUSiXknSZC5uBs5kiJLCM7caqlQyAyG7VaDT+v2rh586bZRmFLc0XDNzbBTu52/xUqUVKQh78/72/WWE3B4pPnRo8ejdGjR1s6DCIiIptg8cRORERUI4wciuflbkRERA8QXu5GREREVocVOxERSYJUZsUzsRMRkSTY2cmMuiGVsJKbWXEonoiIyIawYiciIkngUDwREZENkcqseCZ2IiKSBKlU7DzHTkREZENYsRMRkSRwKJ6IiMiGSCWxcyieiIjIhrBiJyIiSZDK5DkmdiIikgQZjByKt5Lbu3EonoiIyIawYiciIkngUDwREZEN4ax4IiIisjqs2ImISBI4FE9ERGRDpDIUz8RORESSIJWKnefYiYiIbAgrdiIikgQOxRMREdkSI4fireSL5zgUT0REZEtYsRMRkSRwKJ6IiMiGcFY8ERERWR1W7EREJAkciiciIrIhHIonIiIiq8OKnYiIJIFD8URERDaEiZ2IiMiG8Bw7ERERWR1W7EREJAkciiciIrIhHIonIiIiq8OKnYiIJIFD8URERDZEBiOH4k0WiXlxKJ6IiMiGsGInIiJJsJPJYGdEyW7MujWJiZ2IiCSBs+KJiIjI6rBiJyIiSZDKrHhW7EREJAl2MuOX6oiNjUVQUBCcnZ0RGhqKw4cPV9r3yJEj6Ny5Mzw9PeHi4oJmzZph/vz5Bm2PFTsREUmDzMiquxqrxsXFYdy4cYiNjUXnzp2xdOlSREVF4ffff0dAQEC5/m5ubhgzZgwefvhhuLm54ciRI3j11Vfh5uaGkSNH6rVNVuxERERmMm/ePIwYMQIvv/wygoODsWDBAvj7+2Px4sUV9m/Tpg0GDRqEFi1aoEGDBnjxxRfRu3fvKqv8spjYiYhIEkpnxRuzGKKwsBDJycmIjIzUaY+MjMSxY8f0eo5Tp07h2LFj6Nq1q97b5VA8ERFJguy/f8asDwBqtVqnXS6XQy6Xl+ufnZ0NjUYDlUql065SqZCZmVnlturXr49r166huLgY06dPx8svv6x3nKzYiYiIDODv7w+lUqldZs+eXWX/suf1hRD3Pdd/+PBhnDhxAkuWLMGCBQuwYcMGveNjxU5ERJJgzMz20vUBID09HQqFQtteUbUOAHXr1oW9vX256jwrK6tcFV9WUFAQAKBVq1a4evUqpk+fjkGDBukVZ7UTe3JyMlJTUyGTyRAcHIy2bdtW96mIiIjMzlTXsSsUCp3EXhknJyeEhoYiMTERzzzzjLY9MTERTz31lN7bFUKgoKBA7/4GJ/asrCw8//zzOHDgAGrXrg0hBG7evImIiAh888038PLyMvQpiYiIbNL48eMxZMgQtGvXDuHh4Vi2bBnS0tIwatQoAEBMTAwuX76MtWvXAgC++OILBAQEoFmzZgDuXtf+ySef4I033tB7mwYn9jfeeANqtRpnzpxBcHAwAOD333/HsGHDMHbsWIPOAxAREdUUS3xX/MCBA5GTk4OZM2ciIyMDLVu2xI4dOxAYGAgAyMjIQFpamrZ/SUkJYmJicOHCBTg4OKBRo0aYM2cOXn31Vf3jFEIIQ4JUKpXYs2cP2rdvr9P+888/IzIyEjdu3DDk6YyiVquhVCoh7zQRMgfnGtsuUU3KTpxq6RCIzEatVsPPqzZu3ryp1/B2dbehVCrR5/MDcHSpVe3nKbpzC9vf6GbWWE3B4FnxJSUlcHR0LNfu6OiIkpISkwRFRERE1WNwYu/evTv+7//+D1euXNG2Xb58GW+++SZ69Ohh0uCIiIhMpaa/oMZSDE7sixYtQm5uLho0aIBGjRqhcePGCAoKQm5uLj7//HNzxEhERGS00lnxxizWwODJc/7+/jh58iQSExNx9uxZCCHQvHlz9OzZ0xzxERERmYQlJs9ZgkGJvbi4GM7OzkhJSUGvXr3Qq1cvc8VFRERE1WBQYndwcEBgYCA0Go254iEiIjILO5kMdkaU3casW5MMPsc+efJkxMTE4Pr16+aIh4iIyCxkJlisgcHn2BcuXIi//voLfn5+CAwMhJubm87jJ0+eNFlwREREZBiDE/vTTz9tjjiIiIjMylTfFf+gMzixT5s2zRxxEBERmZWp7u72oKvW/dhv3LiBFStW6JxrP3nyJC5fvmzS4IiIiMgwBlfsv/76K3r27AmlUomLFy/ilVdegYeHB7Zs2YJ//vlHe4caIiKiB4lUhuINrtjHjx+P6Oho/Pnnn3B2/t+NV6KionDo0CGTBkdERGRKtv51skA1Evvx48crvH1cvXr1kJmZaZKgiIiIqHoMHop3dnaGWq0u137u3Dl4eXmZJCgiIiJT41B8JZ566inMnDkTRUVFAO7uaFpaGiZOnIh+/fqZPEAiIiJTKJ0Vb8xiDQxO7J988gmuXbsGb29v3LlzB127dkXjxo3h7u6OWbNmmSNGIiIio/HubpVQKBQ4cuQI9u3bh5MnT6KkpARt27bl3d2IiIgeAAYn9lLdu3dH9+7dTRkLERGR2Rj7fe/WUa/rmdgXLlyo9xOOHTu22sEQERGZi1Tu7qZXYp8/f77Oz9euXcPt27dRu3ZtAHe/ic7V1RXe3t5M7ERERBak1+S5CxcuaJdZs2YhJCQEqampuH79Oq5fv47U1FS0bdsW77//vrnjJSIiqhZjvpzGmr6kxuBZ8VOmTMHnn3+Opk2batuaNm2K+fPnY/LkySYNjoiIyFSkMive4MSekZGhvYb9XhqNBlevXjVJUERERFQ9Bif2Hj164JVXXsGJEycghAAAnDhxAq+++ioveSMiogcWh+IrsWrVKtSrVw8dOnSAs7Mz5HI5wsLC4OvrixUrVpgjRiIiIqOVzoo3ZrEGBl/H7uXlhR07duCPP/7A2bNnIYRAcHAwmjRpYo74iIiIyADV/oKaJk2aMJkTEZHVMHY43UoK9uol9kuXLmHbtm1IS0tDYWGhzmPz5s0zSWBERESmJJW7uxmc2Pfu3Ysnn3wSQUFBOHfuHFq2bImLFy9CCIG2bduaI8b7SvsuBgqFwiLbJjK3Ou3HWDoEIrMRmsL7dzIRO1RjYlmZ9a2BwXHGxMRgwoQJ+O233+Ds7Iz4+Hikp6eja9eueO6558wRIxEREenJ4MSempqKYcOGAQAcHBxw584d1KpVCzNnzsRHH31k8gCJiIhMgV9QUwk3NzcUFBQAAPz8/HD+/HntY9nZ2aaLjIiIyIRkMsDOiMVK8rrh59g7duyIo0ePonnz5njiiScwYcIEnD59Gps3b0bHjh3NESMRERHpyeDEPm/ePNy6dQsAMH36dNy6dQtxcXFo3LhxubvAERERPShKK29j1rcGBif2hg0bav/v6uqK2NhYkwZERERkDlK53M1aZu8TERGRHvSq2OvUqaP3XyrXr183KiAiIiJz4FD8PRYsWKD9f05ODj744AP07t0b4eHhAICkpCTs2rULU6ZMMU+URERERuJXyt6j9Lp1AOjXrx9mzpyJMWP+921YY8eOxaJFi7Bnzx68+eabpo+SiIiI9GLwOfZdu3bhscceK9feu3dv7NmzxyRBERERmZpUbttqcGL39PTEli1byrUnJCTA09PTJEERERGZmp0JFmtg8OVuM2bMwIgRI3DgwAHtOfYff/wRO3fuxIoVK0weIBERkSnwHHsloqOjERwcjIULF2Lz5s0QQqB58+Y4evQowsLCzBEjERER6cmgxF5UVISRI0diypQp+Prrr80VExERkcnZwbjz5HawjpLdoFMGjo6OFZ5fJyIietCVDsUbs1gDg+cCPPPMM0hISDBHLERERGQkg8+xN27cGO+//z6OHTuG0NBQuLm56Tw+duxYkwVHRERkKvzmuUqsWLECtWvXRnJyMpKTk3Uek8lkTOxERPRAuns/dmNuAmPCYMzI4MR+4cIFc8RBREREJlDt6+0LCwtx7tw5FBcXmzIeIiIis+DkuUrcvn0bI0aMgKurK1q0aIG0tDQAd8+tz5kzx+QBEhERmULpOXZjFmtgcGKPiYnBL7/8ggMHDsDZ2Vnb3rNnT8TFxZk0OCIiIjKMwefYExISEBcXh44dO+rco7158+Y4f/68SYMjIiIyFdl//4xZ3xoYnNivXbsGb2/vcu15eXk6iZ6IiOhBIpXL3Qweim/fvj2+//577c+lyXz58uXam8IQERE9aKRyjl3vij0lJQUhISGYM2cOevfujd9//x3FxcX47LPPcObMGSQlJeHgwYPmjJWIiIjuQ++KvW3btggNDUVKSgp27NiB27dvo1GjRti9ezdUKhWSkpIQGhpqzliJiIiqTSaTGb1YA70r9qNHj2LVqlWYOHEiioqK8Oyzz2LhwoXo3r27OeMjIiIyCZ5jLyM8PBzLly9HZmYmFi9ejEuXLqFXr15o1KgRZs2ahUuXLpkzTiIiItKDwZPnXFxcMGzYMBw4cAB//PEHBg0ahKVLlyIoKAiPP/64OWIkIiIymlS+ec7gy93u1ahRI0ycOBH+/v547733sGvXLlPFRUREZFJ2MplRN4ExZt2aVO3EfvDgQaxatQrx8fGwt7fHgAEDMGLECFPGRkRERAYyKLGnp6djzZo1WLNmDS5cuIBOnTrh888/x4ABA8rdl52IiOhBIpXJc3on9l69emH//v3w8vLC0KFD8dJLL6Fp06bmjI2IiMh0jD1PbmuJ3cXFBfHx8ejTpw/s7e3NGRMRERFVk96Jfdu2beaMg4iIyKzsIIOdEWW3MevWJKNmxRMREVkLYy9Zs5JJ8YZfx05ERGSNLHUTmNjYWAQFBcHZ2RmhoaE4fPhwpX03b96MXr16wcvLCwqFAuHh4QZfSs7ETkREZCZxcXEYN24cJk2ahFOnTuHRRx9FVFQU0tLSKux/6NAh9OrVCzt27EBycjIiIiLQt29fnDp1Su9tyoQQwlQ7UNPUajWUSiWu5tyEQqGwdDhEZlGn/RhLh0BkNkJTiILTy3Hzpvk+x0tzxYI9p+Hi5l7t57mTl4txPVsZFGtYWBjatm2LxYsXa9uCg4Px9NNPY/bs2Xo9R4sWLTBw4EBMnTpVr/6s2ImISBJM9ZWyarVaZykoKKhwe4WFhUhOTkZkZKROe2RkJI4dO6ZXzCUlJcjNzYWHh4fe+8nETkREZAB/f38olUrtUlnlnZ2dDY1GA5VKpdOuUqmQmZmp17Y+/fRT5OXlYcCAAXrHx1nxREQkCXYw8rvi/7vcLT09XWcoXi6XV7le2fu4CyH0urf7hg0bMH36dGzduhXe3t56x8nETkREkmCqy90UCoVe59jr1q0Le3v7ctV5VlZWuSq+rLi4OIwYMQLffvstevbsaVCcHIonIiIyAycnJ4SGhiIxMVGnPTExEZ06dap0vQ0bNiA6Ohrr16/HE088YfB2WbETEZEk2MG4arY6644fPx5DhgxBu3btEB4ejmXLliEtLQ2jRo0CAMTExODy5ctYu3YtgLtJfejQofjss8/QsWNHbbXv4uICpVKp1zaZ2ImISBJkMple57arWt9QAwcORE5ODmbOnImMjAy0bNkSO3bsQGBgIAAgIyND55r2pUuXori4GK+//jpef/11bfuwYcOwZs0avbbJxE5ERGRGo0ePxujRoyt8rGyyPnDggNHbY2InIiJJkMG4O69ayVfFM7ETEZE02MmMvNzNSu4Cw8RORESSYR2p2Ti83I2IiMiGsGInIiJJkMr92JnYiYhIEixxuZslcCieiIjIhrBiJyIiSbDEN89ZAhM7ERFJAofiiYiIyOqwYiciIkngN88RERHZEA7FExERkdVhxU5ERJLAWfFEREQ2RCpD8UzsREQkCVKZPGctIwtERESkB1bsREQkCbwJDBERkQ2xgwx2RgyoG7NuTeJQPBERkQ1hxU5ERJLAoXgiIiIbIvvvnzHrWwMOxRMREdkQVuxERCQJHIonIiKyITIjZ8Vby1A8EzsREUmCVCp2nmMnIiKyIazYiYhIEqRSsTOxExGRJPByNyIiIrI6rNiJiEgS7GR3F2PWtwZM7EREJAkciiciIiKrw4qdiIgkgbPiiYiIbIgMxg2nW0le51A8ERGRLWHFTkREksBZ8SQJK749hM+/2our2TfRrKEvPhzfD53aNK60/9HkPzFpwWac/TsDPnWVGDu0J17q96j28S+3HMU3O35G6vkrAICQZgGY8npfhLZoYO5dIarQiP6P4o0Xe0BVV4mzf2fgvXnxSEo5f9/1wh5uiO1L/w+pf2egywtztO0O9nZ4c3gkBj0RBl+v2vjrn6uYvmgr9ialmnM3yAQ4K74GHDp0CH379oWfnx9kMhkSEhIsGY7kbN6djPfmxWPC8N44+NVEhIc0woD/i0V65vUK+/9zORsDxi1GeEgjHPxqIsYP742Jn2zCtn2ntH2OJP+JfpGh+G7x/2H3qgmo71MHz475AleybtTUbhFpPdOrLT4c3w+frt6Fri/OQVLKeWz8bDTqq+pUuZ7CzRmLZwzBweN/lHts8mt9Ef3MI3j342/RceAHWL35CNbNfQWtmtQ3126QiZROnjNmsQYWTex5eXlo3bo1Fi1aZMkwJCt2/T68+FQ4hj7dCU2DfDB7Qn/UU9XBqk2HK+y/avMR1Pepg9kT+qNpkA+GPt0JLzzZEYu+2qvts/yDaLz8XBe0alofTRr44LNJgyGEwKHj52pqt4i0Rg/ujq+2JmHd1iT8cfEq3psXj8tX/8VL/R+tcr357w3Cpl0ncPz0hXKPDXi8A+av2Y3EY7/jn8s5WBV/BPt+TMWYF7ubazeIDGLRxB4VFYUPPvgAzz77rCXDkKTComKknE1H97BgnfaIsGD8/Gv5DzMAOH76AiLK9O/RsTlO/Z6GomJNhevczi9EUbEGtRWupgmcSE+ODvYIaeaPfT/pDpHv/ykVHR4OqnS9wX07okH9uvho+Q8VPi53dEB+QZFOW35BETq2bmR80GRWMhMs1sCqzrEXFBSgoKBA+7NarbZgNNYt58YtaDQl8PJw12n38nRHVk7Fr2tWjhpenmX6e7ijWFOCnBu34FNXWW6dGYu2wtdLiW4dmpkueCI9eNauBQcHe1y7nqvTfi0nF96eigrXaejvhWmvP4nHRy6ARlNSYZ99P6Zi9AvdcezUX7hwKRtd2zdFVNeHYW8tM6skzA4y2Bkxnm5nJandqi53mz17NpRKpXbx9/e3dEhWr+wxLoSArIoDv+wjAuK/9vLrfLY2EfG7k7F27itwljsaGypRtQih+7NMJoMo2wjAzk6G5R9EY86yHTifllXp8038dBP+TsvCz99OQdaxBZj7znNY/92P0JSUf04iS7Cqij0mJgbjx4/X/qxWq5ncq8mzdi3Y29shK0e3msm+fqtcFV/K21NRYX8Hezt41HbTaf983R7MW70bCV+MQcuH6pk2eCI95Ny4heJiDbzLjDLV9ahVrooHgFquzmjbPBAPN6mPuW8/B+Busrezs8O1pM/w7Btf4PCJP5Bz4xZefHs55E4O8FC6IePaTUwf8xT+uZJTI/tF1WfscLp11OtWltjlcjnkcrmlw7AJTo4OCGnmj/0/nUWfiNba9gM/n0VUl1YVrtO+VRB2Hf5Np23fT6lo0zwAjg722raF6/bgk5U7Ef/562jTPNA8O0B0H0XFGqScTUdEWDN8f+BXbXu3Ds3ww6HT5frn5uWj0/OzdNpG9H8Uj7ZrguiJK/HPZd3EXVBYjIxrN+Fgb4e+3UOQsOekeXaETEcimd2qEjuZ1ujB3TFq2lq0aR6A9q2C8OWWo7iUeR3D/7sufcairci4dhNLZgwFALz07CNYsfEQJs2Px9CnO+P46Qv4amsSVsyK1j7nZ2sT8eGS77H8g2EI8PXE1ey75+vdXOWo5co/yqhmxa7fhyUzhuLU72k4fvoChj3TGfV9PLA6/u6VH1NffxK+Xkq8Nn0dhBBIPZ+hs/6167dQUFis0x7aIhC+3rVx+o9L8POqjXdHPg47Oxk+W7unRveNqDIWTey3bt3CX3/9pf35woULSElJgYeHBwICAiwYmTQ8GxmK6zfzMHfFD7iarUZwI1/ELRiNAF8PAMDVbDUu3XNNe2C9uti44DW8Nz8eK749DB8vJea81R9Pdm+j7bNy02EUFhVj2Lsrdbb17itRmDjyiZrZMaL/bEk8CQ+lG955OQqqugqkns/AwHGxSM/8FwCgqqtAfR8Pg55TLnfEpFF90KBeXeTdKUDi0TMYNXUt1LfumGMXyISk8gU1MlHRLJIacuDAAURERJRrHzZsGNasWXPf9dVqNZRKJa7m3IRCUfEsVyJrV6f9GEuHQGQ2QlOIgtPLcfOm+T7HS3PF3pQ01HKv/jZu5arRIyTArLGagkUr9m7dulU4O5WIiIiqh+fYiYhIEiQyd46JnYiIJEIimZ2JnYiIJEEqk+es6pvniIiIqGqs2ImISBKMvfWqtdy2lYmdiIgkQSKn2DkUT0REZEtYsRMRkTRIpGRnYiciIkngrHgiIiKyOqzYiYhIEjgrnoiIyIZI5BQ7h+KJiIhsCSt2IiKSBomU7EzsREQkCVKZFc/ETkREkiCVyXM8x05ERGRDWLETEZEkSOQUOyt2IiKSCJkJlmqIjY1FUFAQnJ2dERoaisOHD1faNyMjA4MHD0bTpk1hZ2eHcePGGbw9JnYiIiIziYuLw7hx4zBp0iScOnUKjz76KKKiopCWllZh/4KCAnh5eWHSpElo3bp1tbbJxE5ERJIgM8E/Q82bNw8jRozAyy+/jODgYCxYsAD+/v5YvHhxhf0bNGiAzz77DEOHDoVSqazWfjKxExGRJJTOijdmMURhYSGSk5MRGRmp0x4ZGYljx46ZcM90cfIcERGRAdRqtc7Pcrkccrm8XL/s7GxoNBqoVCqddpVKhczMTLPFx4qdiIgkwVRz5/z9/aFUKrXL7Nmzq95umVJfCFGuzZRYsRMRkTSY6Hq39PR0KBQKbXNF1ToA1K1bF/b29uWq86ysrHJVvCmxYiciIjKAQqHQWSpL7E5OTggNDUViYqJOe2JiIjp16mS2+FixExGRJFjiu+LHjx+PIUOGoF27dggPD8eyZcuQlpaGUaNGAQBiYmJw+fJlrF27VrtOSkoKAODWrVu4du0aUlJS4OTkhObNm+u1TSZ2IiKSBEt8V/zAgQORk5ODmTNnIiMjAy1btsSOHTsQGBgI4O4X0pS9pr1Nmzba/ycnJ2P9+vUIDAzExYsX9domEzsREUmCpb5SdvTo0Rg9enSFj61Zs6ZcmxCimlu6i+fYiYiIbAgrdiIikgaJ3AWGiZ2IiCTBEpPnLIFD8URERDaEFTsREUmDkbPiraRgZ2InIiJpkMgpdg7FExER2RJW7EREJA0SKdmZ2ImISBI4K56IiIisDit2IiKSBEt8V7wlMLETEZEkSOQUOxM7ERFJhEQyO8+xExER2RBW7EREJAlSmRXPxE5ERJIgg5GT50wWiXlxKJ6IiMiGsGInIiJJkMjcOSZ2IiKSBqlcx86heCIiIhvCip2IiCRCGoPxTOxERCQJHIonIiIiq8OKnYiIJEEaA/FM7EREJBFSGYpnYiciIkmQylfK8hw7ERGRDWHFTkRE0iCRk+xM7EREJAkSyesciiciIrIlrNiJiEgSOCueiIjIhnBWPBEREVkdVuxERCQNEpk9x8RORESSIJG8zqF4IiIiW8KKnYiIJIGz4omIiGyKcbPirWUwnomdiIgkQSoVO8+xExER2RAmdiIiIhvCoXgiIpIEDsUTERGR1WHFTkREkiCV74pnYiciIkngUDwRERFZHVbsREQkCVL5rngmdiIikgaJZHYOxRMREdkQVuxERCQJnBVPRERkQ6QyK56JnYiIJEEip9h5jp2IiMiWsGInIiJpkEjJzsRORESSIJXJcxyKJyIisiFWXbELIQAAuWq1hSMhMh+hKbR0CERmU3p8l36em1Nurtqome25udaRa6w6sefm5gIAGgf5WzgSIiIyRm5uLpRKpVme28nJCT4+PnjIBLnCx8cHTk5OJojKfGSiJv5MMpOSkhJcuXIF7u7ukFnLBYZWTq1Ww9/fH+np6VAoFJYOh8ikeHzXPCEEcnNz4efnBzs7850dzs/PR2Gh8aNfTk5OcHZ2NkFE5mPVFbudnR3q169v6TAkSaFQ8IOPbBaP75plrkr9Xs7Ozg98+bMnFQAAB8tJREFUQjYVTp4jIiKyIUzsRERENoSJnQwil8sxbdo0yOVyS4dCZHI8vskWWPXkOSIiItLFip2IiMiGMLETERHZECZ2IiIiG8LETkREZEOY2ElvsbGxCAoKgrOzM0JDQ3H48GFLh0RkEocOHULfvn3h5+cHmUyGhIQES4dEVG1M7KSXuLg4jBs3DpMmTcKpU6fw6KOPIioqCmlpaZYOjchoeXl5aN26NRYtWmTpUIiMxsvdSC9hYWFo27YtFi9erG0LDg7G008/jdmzZ1swMiLTkslk2LJlC55++mlLh0JULazY6b4KCwuRnJyMyMhInfbIyEgcO3bMQlEREVFFmNjpvrKzs6HRaKBSqXTaVSoVMjMzLRQVERFVhImd9Fb21rhCCN4ul4joAcPETvdVt25d2Nvbl6vOs7KyylXxRERkWUzsdF9OTk4IDQ1FYmKiTntiYiI6depkoaiIiKgiDpYOgKzD+PHjMWTIELRr1w7h4eFYtmwZ0tLSMGrUKEuHRmS0W7du4a+//tL+fOHCBaSkpMDDwwMBAQEWjIzIcLzcjfQWGxuLuXPnIiMjAy1btsT8+fPRpUsXS4dFZLQDBw4gIiKiXPuwYcOwZs2amg+IyAhM7ERERDaE59iJiIhsCBM7ERGRDWFiJyIisiFM7ERERDaEiZ2IiMiGMLETERHZECZ2IiIiG8LETvQAmD59OkJCQmr0+aKjo3nPcSIbxMROVIXo6GjIZDLIZDI4OjqiYcOGeOutt5CXl2fp0Kr01ltvYe/evZYOg4gsgN8VT3Qfjz32GFavXo2ioiIcPnwYL7/8MvLy8rB48WKdfkVFRXB0dLRQlLpq1aqFWrVqWToMIrIAVuxE9yGXy+Hj4wN/f38MHjwYL7zwAhISErTD3atWrULDhg0hl8shhMDNmzcxcuRIeHt7Q6FQoHv37vjll190nnPOnDlQqVRwd3fHiBEjkJ+fX267q1evRnBwMJydndGsWTPExsbqPH7p0iU8//zz8PDwgJubG9q1a4effvoJQPmheI1Gg/Hjx6N27drw9PTEO++8g7LfJl1QUICxY8fC29sbzs7OeOSRR3D8+HFTvYxEVEOY2IkM5OLigqKiIgDAX3/9hY0bNyI+Ph4pKSkAgCeeeAKZmZnYsWMHkpOT0bZtW/To0QPXr18HAGzcuBHTpk3DrFmzcOLECfj6+pZL2suXL8ekSZMwa9YspKam4sMPP8SUKVPw5ZdfArh7N7KuXbviypUr2LZtG3755Re88847KCkpqTDmTz/9FKtWrcLKlStx5MgRXL9+HVu2bNHp88477yA+Ph5ffvklTp48icaNG6N3797auInISggiqtSwYcPEU089pf35p59+Ep6enmLAgAFi2rRpwtHRUWRlZWkf37t3r1AoFCI/P1/neRo1aiSWLl0qhBAiPDxcjBo1SufxsLAw0bp1a+3P/v7+Yv369Tp93n//fREeHi6EEGLp0v9v335ektniMIA/lko09ssKG4ukMMKgoBgKKYSgTa2MFtEiCm3jJiOpFi1qEWUGbSLi0tr/IARbtWjRQslNuLIWQQYSJUlUinMX932H5u3l9b3gvbc7PB9wcc4cv2c8m4eZc/xDrqmpkR8eHn563xsbG6p6oijKwWBQaefzebmtrU35bblcTjYYDHI4HFbGvL+/y1arVQ6FQr9YISL6avjETlTCyckJTCYTqqqq4HQ64XK5cHBwAACw2Wxobm5WxsbjceRyOTQ2Nir73CaTCTc3N0ilUgCAZDIJp9OpmuNjO5PJ4Pb2Fl6vV1Vja2tLqZFIJNDf3w+z2Vzy/rPZLNLptGoOvV4PSZKUdiqVQj6fx/DwsNJnMBgwODiIZDL5d5aLiP5jPDxHVMLo6CiOjo5gMBhgtVpVB+QEQVCNLRaLEEURZ2dnn+rU19f/1nzfX6cfHx9jaGhIda2yshLAX9sB5SR/22/X6XSf+n/sI6KvjU/sRCUIggC73Q6bzVby1PvAwADu7++h1+tht9tVn6amJgCAw+HAxcWF6nsf2xaLBa2trbi+vv5Uo6OjAwDQ19eHRCLxW/vfdXV1EEVRNUehUEA8HlfadrsdRqMR5+fnSl8+n0csFoPD4Sg5BxF9HXxiJyqjsbExOJ1OuN1u7O7uoru7G3d3d4hEInC73ZAkCX6/H3Nzc5AkCSMjIwiHw7i6ukJnZ6dSZ3NzE4uLi6itrcX4+Dje3t4Qi8Xw+PiI5eVlzMzMYHt7G263Gzs7OxBFEZeXl7BarZ9e8wOA3+9HMBhEV1cXHA4H9vf38fT0pFwXBAE+nw8rKyswm81ob29HKBTCy8sLvF7vv7J2RFQeDHaiMtLpdIhEIlhfX4fH40Emk0FLSwtcLhcsFgsAYHp6GqlUCmtra3h9fcXU1BR8Ph+i0ahSZ2FhAdXV1djb28Pq6ioEQUBvby+WlpYAAEajEaenpwgEApiYmEChUEBPTw8ODw9/el+BQADpdBrz8/OoqKiAx+PB5OQkstmsMiYYDKJYLGJ2dhbPz8+QJAnRaBQNDQ3/4IoRUbnpZPmHP7MSERHR/xb32ImIiDSEwU5ERKQhDHYiIiINYbATERFpCIOdiIhIQxjsREREGsJgJyIi0hAGOxERkYYw2ImIiDSEwU5ERKQhDHYiIiINYbATERFpyJ9BXbd/z52amgAAAABJRU5ErkJggg==",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "cm = confusion_matrix(y_test, predictions2, normalize='all')\n",
    "cmd = ConfusionMatrixDisplay(cm, display_labels=[0, 1])\n",
    "cmd.plot(cmap=plt.cm.Blues)\n",
    "cmd.ax_.set(xlabel='Predecido', ylabel='Verdadero', title='Matriz de confision modelo Random Forest')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 181,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[0.6461203  0.35387972]]\n"
     ]
    }
   ],
   "source": [
    "dfForTest = pd.DataFrame([[''' Luke Mosseau The Warren County Finance and Budget Committee passed a resolution that will give the county greater flexibility to spend what is left of the $12 million the county received in federal ARPA money. The resolution attempts to make sure that ARPA funds that have gone unused make it back to the county’s general fund. During the COVID-19 Pandemic, Warren County was awarded roughly $12 million from ARPA, the American Rescue Plan Act, according to Warren County Administrator John Taflan. As groups such as local housing and healthcare providers came forward with requests to use that money, the county voted to “obligate” the funds to those groups, meaning under federal rules that “obligated” money is under contract with one of the groups or projects. If the county does not obligate all of the money, or if the group ends up not spending their money by the end of 2026, the federal government could require that the money is returned. The Wednesday May 8 resolution would move the unspent money into the general fund at the end of 2024. “We want to ensure that what’s not being obligated and/or expended by any ARPA recipient has a means to come back and stay here,” County Attorney Larry Elmen said. The county still has $3.3 million from the federal government that is obligated to groups and projects, but has either not yet been distributed to those entities or the entities have gotten the money but have not yet spent it, Taflan said. The resolution that passed this week replaces one approved at the end of last year. That resolution had said that any unspent ARPA money would have gone to mental health and homelessness issues at the end of this year. However, roughly $400,000 has already been obligated for mental health issues and has not yet been spent. “We think there are adequate resources for mental health and wellness,” Taflan said. “What we would like to do is ensure that money that is obligated is going to be spent by asking the people who have received the ARPA funding, if they’re confident enough that they’re going to spend the money by 2026.” The Warren County Planning Department reaches out to organizations like Glens Falls Hospital and Ascend Mental Wellness to review the progress of ARPA expenditure. “On a quarterly basis we reach out to everyone that’s received funding and we get a project status update to understand where they’re at with their project,” said Ethan Gaddy, Warren County planner. “We collect all the receipts from expenditures, have them self-report any obstacles to spending their funds, and then that helps us stay on top of where they are.” “This process has served us well because we have a clearer idea of where people are at with their projects and understanding where people are at with expenditures past 2024,” Gaddy added. If there are no plans to spend that money, Warren County would like to recoup the funds from these organizations—a complicated process since the funds are under contract. Recouping would involve going through the county attorney’s office and the county planning department, as well as coming to an agreement with the ARPA recipient, according to Taflan. The county established an ARPA committee that allocate those funds over a three-year period. The ARPA committee ended at the end of 2023 and all ARPA responsibility fell to the Warren County Finance and Budget Committee. The resolution to transfer unspent or un-obligated ARPA funds to the general fund at the end of 2024 will need to go before the Warren County Board of Supervisors for final approval.''', '''County moves to recalculate how ARPA funding is spent''']],\n",
    "                  columns=['text', 'title'])\n",
    "\n",
    "dfForTest['text'] = dfForTest['text'].apply(removeStopwordsAndLower)\n",
    "dfForTest['title'] = dfForTest['title'].apply(removeStopwordsAndLower)\n",
    "dfForTest['text'] = dfForTest['text'].apply(lemaAndStem)\n",
    "dfForTest['title'] = dfForTest['title'].apply(lemaAndStem)\n",
    "\n",
    "dfForTest = preprocessor.transform(dfForTest)\n",
    "print(model.predict_proba(dfForTest))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 166,
   "metadata": {},
   "outputs": [],
   "source": [
    "modelFileSave = 'trained_model_XGBoost.pkl'\n",
    "pickle.dump(model, open(modelFileSave, 'wb'))\n",
    "#Evaluar el modelo para evitar sobreentrenarlo."
   ]
  }
 ],
 "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": "3.11.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}