{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "lxWg-88vlXNr"
   },
   "source": [
    "## <center>**Predict whether the Employee of an Organization should get Promotion or Not?**</center>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "UdHgRAPlLsBW"
   },
   "source": [
    "&nbsp;\n",
    "\n",
    "Our client is a large MNC and they have 9 broad verticals across the organisation. One of the problem our client is facing is around identifying the right people for promotion (only for manager position and below) and prepare them in time. Currently the process, they are following is:\n",
    "    * They first identify a set of employees based on recommendations/ past performance.\n",
    "    * Selected employees go through the separate training and evaluation program for each vertical. These programs are based on he required skill of each vertical\n",
    "    * At the end of the program, based on various factors such as training performance, an employee gets the promotion\n",
    "\n",
    "![image](https://corehr.files.wordpress.com/2013/02/wrong-promotion1.jpg?w=290)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 669,
   "metadata": {
    "id": "i0gPAqj5qtGh"
   },
   "outputs": [],
   "source": [
    "# lets import all the required libraries\n",
    "\n",
    "# for mathematical operations\n",
    "import numpy as np\n",
    "# for dataframe operations\n",
    "import pandas as pd\n",
    "\n",
    "# for data visualizations\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "# for machine learning\n",
    "import sklearn\n",
    "import imblearn\n",
    "\n",
    "# setting up the size of the figures\n",
    "plt.rcParams['figure.figsize'] = (16, 5)\n",
    "# setting up the style of the plot\n",
    "plt.style.use('fivethirtyeight')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 670,
   "metadata": {
    "id": "if4SIFymsqQY"
   },
   "outputs": [],
   "source": [
    "# reading the datasets\n",
    "\n",
    "train = pd.read_csv('train.csv')\n",
    "test = pd.read_csv('test.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 671,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 322
    },
    "id": "y-Oh5tZJM9kt",
    "outputId": "ff4d1cd9-c023-4d47-bace-11d2009f2ab9"
   },
   "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>employee_id</th>\n",
       "      <th>department</th>\n",
       "      <th>region</th>\n",
       "      <th>education</th>\n",
       "      <th>gender</th>\n",
       "      <th>recruitment_channel</th>\n",
       "      <th>no_of_trainings</th>\n",
       "      <th>age</th>\n",
       "      <th>previous_year_rating</th>\n",
       "      <th>length_of_service</th>\n",
       "      <th>awards_won?</th>\n",
       "      <th>avg_training_score</th>\n",
       "      <th>is_promoted</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>65438</td>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>region_7</td>\n",
       "      <td>Master's &amp; above</td>\n",
       "      <td>f</td>\n",
       "      <td>sourcing</td>\n",
       "      <td>1</td>\n",
       "      <td>35</td>\n",
       "      <td>5.0</td>\n",
       "      <td>8</td>\n",
       "      <td>0</td>\n",
       "      <td>49</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>65141</td>\n",
       "      <td>Operations</td>\n",
       "      <td>region_22</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>other</td>\n",
       "      <td>1</td>\n",
       "      <td>30</td>\n",
       "      <td>5.0</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>60</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>7513</td>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>region_19</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>sourcing</td>\n",
       "      <td>1</td>\n",
       "      <td>34</td>\n",
       "      <td>3.0</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>50</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2542</td>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>region_23</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>other</td>\n",
       "      <td>2</td>\n",
       "      <td>39</td>\n",
       "      <td>1.0</td>\n",
       "      <td>10</td>\n",
       "      <td>0</td>\n",
       "      <td>50</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>48945</td>\n",
       "      <td>Technology</td>\n",
       "      <td>region_26</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>other</td>\n",
       "      <td>1</td>\n",
       "      <td>45</td>\n",
       "      <td>3.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>73</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   employee_id         department     region         education gender  \\\n",
       "0        65438  Sales & Marketing   region_7  Master's & above      f   \n",
       "1        65141         Operations  region_22        Bachelor's      m   \n",
       "2         7513  Sales & Marketing  region_19        Bachelor's      m   \n",
       "3         2542  Sales & Marketing  region_23        Bachelor's      m   \n",
       "4        48945         Technology  region_26        Bachelor's      m   \n",
       "\n",
       "  recruitment_channel  no_of_trainings  age  previous_year_rating  \\\n",
       "0            sourcing                1   35                   5.0   \n",
       "1               other                1   30                   5.0   \n",
       "2            sourcing                1   34                   3.0   \n",
       "3               other                2   39                   1.0   \n",
       "4               other                1   45                   3.0   \n",
       "\n",
       "   length_of_service  awards_won?  avg_training_score  is_promoted  \n",
       "0                  8            0                  49            0  \n",
       "1                  4            0                  60            0  \n",
       "2                  7            0                  50            0  \n",
       "3                 10            0                  50            0  \n",
       "4                  2            0                  73            0  "
      ]
     },
     "execution_count": 671,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 672,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 206
    },
    "id": "sVYIq2H5NNMT",
    "outputId": "69079769-a2a9-4b14-ded5-cc29be43ef1e"
   },
   "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>employee_id</th>\n",
       "      <th>department</th>\n",
       "      <th>region</th>\n",
       "      <th>education</th>\n",
       "      <th>gender</th>\n",
       "      <th>recruitment_channel</th>\n",
       "      <th>no_of_trainings</th>\n",
       "      <th>age</th>\n",
       "      <th>previous_year_rating</th>\n",
       "      <th>length_of_service</th>\n",
       "      <th>awards_won?</th>\n",
       "      <th>avg_training_score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>8724</td>\n",
       "      <td>Technology</td>\n",
       "      <td>region_26</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>sourcing</td>\n",
       "      <td>1</td>\n",
       "      <td>24</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>77</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>74430</td>\n",
       "      <td>HR</td>\n",
       "      <td>region_4</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>f</td>\n",
       "      <td>other</td>\n",
       "      <td>1</td>\n",
       "      <td>31</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>51</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>72255</td>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>region_13</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>other</td>\n",
       "      <td>1</td>\n",
       "      <td>31</td>\n",
       "      <td>1.0</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>47</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>38562</td>\n",
       "      <td>Procurement</td>\n",
       "      <td>region_2</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>f</td>\n",
       "      <td>other</td>\n",
       "      <td>3</td>\n",
       "      <td>31</td>\n",
       "      <td>2.0</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "      <td>65</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>64486</td>\n",
       "      <td>Finance</td>\n",
       "      <td>region_29</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>sourcing</td>\n",
       "      <td>1</td>\n",
       "      <td>30</td>\n",
       "      <td>4.0</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>61</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   employee_id         department     region   education gender  \\\n",
       "0         8724         Technology  region_26  Bachelor's      m   \n",
       "1        74430                 HR   region_4  Bachelor's      f   \n",
       "2        72255  Sales & Marketing  region_13  Bachelor's      m   \n",
       "3        38562        Procurement   region_2  Bachelor's      f   \n",
       "4        64486            Finance  region_29  Bachelor's      m   \n",
       "\n",
       "  recruitment_channel  no_of_trainings  age  previous_year_rating  \\\n",
       "0            sourcing                1   24                   NaN   \n",
       "1               other                1   31                   3.0   \n",
       "2               other                1   31                   1.0   \n",
       "3               other                3   31                   2.0   \n",
       "4            sourcing                1   30                   4.0   \n",
       "\n",
       "   length_of_service  awards_won?  avg_training_score  \n",
       "0                  1            0                  77  \n",
       "1                  5            0                  51  \n",
       "2                  4            0                  47  \n",
       "3                  9            0                  65  \n",
       "4                  7            0                  61  "
      ]
     },
     "execution_count": 672,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "ScIy1lK3OdR9"
   },
   "source": [
    "We have observations of 54,808 employees that we want to analyse. And there are 14 features in our dataset on the top of which we are going to build our model to predict if the employee should be promoted or not."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 673,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 300
    },
    "id": "z4ngdw_TOaCR",
    "outputId": "472b1a15-9678-4ce9-b8c4-c9377b93fef4"
   },
   "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>employee_id</th>\n",
       "      <th>no_of_trainings</th>\n",
       "      <th>age</th>\n",
       "      <th>previous_year_rating</th>\n",
       "      <th>length_of_service</th>\n",
       "      <th>awards_won?</th>\n",
       "      <th>avg_training_score</th>\n",
       "      <th>is_promoted</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>54808.000000</td>\n",
       "      <td>54808.000000</td>\n",
       "      <td>54808.000000</td>\n",
       "      <td>50684.000000</td>\n",
       "      <td>54808.000000</td>\n",
       "      <td>54808.000000</td>\n",
       "      <td>54808.000000</td>\n",
       "      <td>54808.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>39195.830627</td>\n",
       "      <td>1.253011</td>\n",
       "      <td>34.803915</td>\n",
       "      <td>3.329256</td>\n",
       "      <td>5.865512</td>\n",
       "      <td>0.023172</td>\n",
       "      <td>63.386750</td>\n",
       "      <td>0.085170</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>22586.581449</td>\n",
       "      <td>0.609264</td>\n",
       "      <td>7.660169</td>\n",
       "      <td>1.259993</td>\n",
       "      <td>4.265094</td>\n",
       "      <td>0.150450</td>\n",
       "      <td>13.371559</td>\n",
       "      <td>0.279137</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>20.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>39.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>19669.750000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>29.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>51.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>39225.500000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>33.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>60.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>58730.500000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>39.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>76.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>78298.000000</td>\n",
       "      <td>10.000000</td>\n",
       "      <td>60.000000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>37.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>99.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        employee_id  no_of_trainings           age  previous_year_rating  \\\n",
       "count  54808.000000     54808.000000  54808.000000          50684.000000   \n",
       "mean   39195.830627         1.253011     34.803915              3.329256   \n",
       "std    22586.581449         0.609264      7.660169              1.259993   \n",
       "min        1.000000         1.000000     20.000000              1.000000   \n",
       "25%    19669.750000         1.000000     29.000000              3.000000   \n",
       "50%    39225.500000         1.000000     33.000000              3.000000   \n",
       "75%    58730.500000         1.000000     39.000000              4.000000   \n",
       "max    78298.000000        10.000000     60.000000              5.000000   \n",
       "\n",
       "       length_of_service   awards_won?  avg_training_score   is_promoted  \n",
       "count       54808.000000  54808.000000        54808.000000  54808.000000  \n",
       "mean            5.865512      0.023172           63.386750      0.085170  \n",
       "std             4.265094      0.150450           13.371559      0.279137  \n",
       "min             1.000000      0.000000           39.000000      0.000000  \n",
       "25%             3.000000      0.000000           51.000000      0.000000  \n",
       "50%             5.000000      0.000000           60.000000      0.000000  \n",
       "75%             7.000000      0.000000           76.000000      0.000000  \n",
       "max            37.000000      1.000000           99.000000      1.000000  "
      ]
     },
     "execution_count": 673,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 674,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "wF0G9Hm2O1qs",
    "outputId": "72cd8bb3-41e4-4a64-af26-8ed7235f310c"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 54808 entries, 0 to 54807\n",
      "Data columns (total 13 columns):\n",
      " #   Column                Non-Null Count  Dtype  \n",
      "---  ------                --------------  -----  \n",
      " 0   employee_id           54808 non-null  int64  \n",
      " 1   department            54808 non-null  object \n",
      " 2   region                54808 non-null  object \n",
      " 3   education             52399 non-null  object \n",
      " 4   gender                54808 non-null  object \n",
      " 5   recruitment_channel   54808 non-null  object \n",
      " 6   no_of_trainings       54808 non-null  int64  \n",
      " 7   age                   54808 non-null  int64  \n",
      " 8   previous_year_rating  50684 non-null  float64\n",
      " 9   length_of_service     54808 non-null  int64  \n",
      " 10  awards_won?           54808 non-null  int64  \n",
      " 11  avg_training_score    54808 non-null  int64  \n",
      " 12  is_promoted           54808 non-null  int64  \n",
      "dtypes: float64(1), int64(7), object(5)\n",
      "memory usage: 5.4+ MB\n"
     ]
    }
   ],
   "source": [
    "train.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 675,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 300
    },
    "id": "47Unz5Lmzf4I",
    "outputId": "3c49a465-baf4-4c0a-8fc2-f8c5f60c5ab7"
   },
   "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>employee_id</th>\n",
       "      <th>no_of_trainings</th>\n",
       "      <th>age</th>\n",
       "      <th>previous_year_rating</th>\n",
       "      <th>length_of_service</th>\n",
       "      <th>awards_won?</th>\n",
       "      <th>avg_training_score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>23490.000000</td>\n",
       "      <td>23490.000000</td>\n",
       "      <td>23490.000000</td>\n",
       "      <td>21678.000000</td>\n",
       "      <td>23490.000000</td>\n",
       "      <td>23490.000000</td>\n",
       "      <td>23490.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>39041.399149</td>\n",
       "      <td>1.254236</td>\n",
       "      <td>34.782929</td>\n",
       "      <td>3.339146</td>\n",
       "      <td>5.810387</td>\n",
       "      <td>0.022776</td>\n",
       "      <td>63.263133</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>22640.809201</td>\n",
       "      <td>0.600910</td>\n",
       "      <td>7.679492</td>\n",
       "      <td>1.263294</td>\n",
       "      <td>4.207917</td>\n",
       "      <td>0.149191</td>\n",
       "      <td>13.411750</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>3.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>20.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>39.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>19370.250000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>29.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>51.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>38963.500000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>33.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>60.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>58690.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>39.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>76.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>78295.000000</td>\n",
       "      <td>9.000000</td>\n",
       "      <td>60.000000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>34.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>99.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        employee_id  no_of_trainings           age  previous_year_rating  \\\n",
       "count  23490.000000     23490.000000  23490.000000          21678.000000   \n",
       "mean   39041.399149         1.254236     34.782929              3.339146   \n",
       "std    22640.809201         0.600910      7.679492              1.263294   \n",
       "min        3.000000         1.000000     20.000000              1.000000   \n",
       "25%    19370.250000         1.000000     29.000000              3.000000   \n",
       "50%    38963.500000         1.000000     33.000000              3.000000   \n",
       "75%    58690.000000         1.000000     39.000000              4.000000   \n",
       "max    78295.000000         9.000000     60.000000              5.000000   \n",
       "\n",
       "       length_of_service   awards_won?  avg_training_score  \n",
       "count       23490.000000  23490.000000        23490.000000  \n",
       "mean            5.810387      0.022776           63.263133  \n",
       "std             4.207917      0.149191           13.411750  \n",
       "min             1.000000      0.000000           39.000000  \n",
       "25%             3.000000      0.000000           51.000000  \n",
       "50%             5.000000      0.000000           60.000000  \n",
       "75%             7.000000      0.000000           76.000000  \n",
       "max            34.000000      1.000000           99.000000  "
      ]
     },
     "execution_count": 675,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 676,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "98c03csTzgJB",
    "outputId": "0957db5a-8029-464b-d0e3-ef772228d34c"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 23490 entries, 0 to 23489\n",
      "Data columns (total 12 columns):\n",
      " #   Column                Non-Null Count  Dtype  \n",
      "---  ------                --------------  -----  \n",
      " 0   employee_id           23490 non-null  int64  \n",
      " 1   department            23490 non-null  object \n",
      " 2   region                23490 non-null  object \n",
      " 3   education             22456 non-null  object \n",
      " 4   gender                23490 non-null  object \n",
      " 5   recruitment_channel   23490 non-null  object \n",
      " 6   no_of_trainings       23490 non-null  int64  \n",
      " 7   age                   23490 non-null  int64  \n",
      " 8   previous_year_rating  21678 non-null  float64\n",
      " 9   length_of_service     23490 non-null  int64  \n",
      " 10  awards_won?           23490 non-null  int64  \n",
      " 11  avg_training_score    23490 non-null  int64  \n",
      "dtypes: float64(1), int64(6), object(5)\n",
      "memory usage: 2.2+ MB\n"
     ]
    }
   ],
   "source": [
    "test.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 677,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "gmUkMcfgPgXd",
    "outputId": "ddf42d8e-cb38-47a5-a8a1-444311f274fa"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Shape of the Training Data : (54808, 13)\n",
      "Shape of the Test Data : (23490, 12)\n"
     ]
    }
   ],
   "source": [
    "# lets check the shape of the train and test datasets\n",
    "print(\"Shape of the Training Data :\", train.shape)\n",
    "print(\"Shape of the Test Data :\", test.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "4X-idqc5z0FO"
   },
   "source": [
    "## Descriptive Statistics\n",
    "\n",
    "* Descriptive Statistics is one of the most Important Step to Understand the Data and take out Insights\n",
    "* First we will the Descriptive Statistics for the Numerical Columns\n",
    "* for Numerical Columns we check for stats such as Max, Min, Mean, count, standard deviation, 25 percentile, 50 percentile, and 75 percentile.\n",
    "* Then we will check for the Descriptive Statistics for Categorical Columns\n",
    "* for Categorical Columns we check for stats such as count, frequency, top, and unique elements."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 678,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 0
    },
    "id": "uaSiIyPSy-jE",
    "outputId": "65d17ea9-3013-43c0-e385-1761f759ab1e"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style  type=\"text/css\" >\n",
       "#T_b80dd_row0_col0{\n",
       "            background-color:  #dd8c59;\n",
       "            color:  #000000;\n",
       "        }#T_b80dd_row0_col1,#T_b80dd_row0_col2,#T_b80dd_row0_col3,#T_b80dd_row0_col4,#T_b80dd_row0_col5,#T_b80dd_row0_col6,#T_b80dd_row0_col7,#T_b80dd_row7_col0{\n",
       "            background-color:  #ffc77f;\n",
       "            color:  #000000;\n",
       "        }#T_b80dd_row1_col0,#T_b80dd_row5_col0{\n",
       "            background-color:  #9e6440;\n",
       "            color:  #000000;\n",
       "        }#T_b80dd_row1_col1,#T_b80dd_row1_col2,#T_b80dd_row1_col3,#T_b80dd_row1_col4,#T_b80dd_row1_col5,#T_b80dd_row1_col6,#T_b80dd_row1_col7,#T_b80dd_row2_col1,#T_b80dd_row2_col2,#T_b80dd_row2_col3,#T_b80dd_row2_col4,#T_b80dd_row2_col5,#T_b80dd_row2_col6,#T_b80dd_row2_col7,#T_b80dd_row3_col0,#T_b80dd_row3_col1,#T_b80dd_row3_col2,#T_b80dd_row3_col3,#T_b80dd_row3_col4,#T_b80dd_row3_col5,#T_b80dd_row3_col6,#T_b80dd_row3_col7,#T_b80dd_row4_col1,#T_b80dd_row4_col2,#T_b80dd_row4_col3,#T_b80dd_row4_col4,#T_b80dd_row4_col5,#T_b80dd_row4_col6,#T_b80dd_row4_col7,#T_b80dd_row5_col1,#T_b80dd_row5_col2,#T_b80dd_row5_col3,#T_b80dd_row5_col4,#T_b80dd_row5_col5,#T_b80dd_row5_col6,#T_b80dd_row5_col7,#T_b80dd_row6_col1,#T_b80dd_row6_col2,#T_b80dd_row6_col3,#T_b80dd_row6_col4,#T_b80dd_row6_col5,#T_b80dd_row6_col6,#T_b80dd_row6_col7,#T_b80dd_row7_col1,#T_b80dd_row7_col2,#T_b80dd_row7_col3,#T_b80dd_row7_col4,#T_b80dd_row7_col5,#T_b80dd_row7_col6,#T_b80dd_row7_col7{\n",
       "            background-color:  #000000;\n",
       "            color:  #f1f1f1;\n",
       "        }#T_b80dd_row2_col0{\n",
       "            background-color:  #5a3924;\n",
       "            color:  #f1f1f1;\n",
       "        }#T_b80dd_row4_col0{\n",
       "            background-color:  #4f3220;\n",
       "            color:  #f1f1f1;\n",
       "        }#T_b80dd_row6_col0{\n",
       "            background-color:  #ed9660;\n",
       "            color:  #000000;\n",
       "        }</style><table id=\"T_b80dd_\" ><thead>    <tr>        <th class=\"blank level0\" ></th>        <th class=\"col_heading level0 col0\" >employee_id</th>        <th class=\"col_heading level0 col1\" >no_of_trainings</th>        <th class=\"col_heading level0 col2\" >age</th>        <th class=\"col_heading level0 col3\" >previous_year_rating</th>        <th class=\"col_heading level0 col4\" >length_of_service</th>        <th class=\"col_heading level0 col5\" >awards_won?</th>        <th class=\"col_heading level0 col6\" >avg_training_score</th>        <th class=\"col_heading level0 col7\" >is_promoted</th>    </tr></thead><tbody>\n",
       "                <tr>\n",
       "                        <th id=\"T_b80dd_level0_row0\" class=\"row_heading level0 row0\" >count</th>\n",
       "                        <td id=\"T_b80dd_row0_col0\" class=\"data row0 col0\" >54808.000000</td>\n",
       "                        <td id=\"T_b80dd_row0_col1\" class=\"data row0 col1\" >54808.000000</td>\n",
       "                        <td id=\"T_b80dd_row0_col2\" class=\"data row0 col2\" >54808.000000</td>\n",
       "                        <td id=\"T_b80dd_row0_col3\" class=\"data row0 col3\" >50684.000000</td>\n",
       "                        <td id=\"T_b80dd_row0_col4\" class=\"data row0 col4\" >54808.000000</td>\n",
       "                        <td id=\"T_b80dd_row0_col5\" class=\"data row0 col5\" >54808.000000</td>\n",
       "                        <td id=\"T_b80dd_row0_col6\" class=\"data row0 col6\" >54808.000000</td>\n",
       "                        <td id=\"T_b80dd_row0_col7\" class=\"data row0 col7\" >54808.000000</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_b80dd_level0_row1\" class=\"row_heading level0 row1\" >mean</th>\n",
       "                        <td id=\"T_b80dd_row1_col0\" class=\"data row1 col0\" >39195.830627</td>\n",
       "                        <td id=\"T_b80dd_row1_col1\" class=\"data row1 col1\" >1.253011</td>\n",
       "                        <td id=\"T_b80dd_row1_col2\" class=\"data row1 col2\" >34.803915</td>\n",
       "                        <td id=\"T_b80dd_row1_col3\" class=\"data row1 col3\" >3.329256</td>\n",
       "                        <td id=\"T_b80dd_row1_col4\" class=\"data row1 col4\" >5.865512</td>\n",
       "                        <td id=\"T_b80dd_row1_col5\" class=\"data row1 col5\" >0.023172</td>\n",
       "                        <td id=\"T_b80dd_row1_col6\" class=\"data row1 col6\" >63.386750</td>\n",
       "                        <td id=\"T_b80dd_row1_col7\" class=\"data row1 col7\" >0.085170</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_b80dd_level0_row2\" class=\"row_heading level0 row2\" >std</th>\n",
       "                        <td id=\"T_b80dd_row2_col0\" class=\"data row2 col0\" >22586.581449</td>\n",
       "                        <td id=\"T_b80dd_row2_col1\" class=\"data row2 col1\" >0.609264</td>\n",
       "                        <td id=\"T_b80dd_row2_col2\" class=\"data row2 col2\" >7.660169</td>\n",
       "                        <td id=\"T_b80dd_row2_col3\" class=\"data row2 col3\" >1.259993</td>\n",
       "                        <td id=\"T_b80dd_row2_col4\" class=\"data row2 col4\" >4.265094</td>\n",
       "                        <td id=\"T_b80dd_row2_col5\" class=\"data row2 col5\" >0.150450</td>\n",
       "                        <td id=\"T_b80dd_row2_col6\" class=\"data row2 col6\" >13.371559</td>\n",
       "                        <td id=\"T_b80dd_row2_col7\" class=\"data row2 col7\" >0.279137</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_b80dd_level0_row3\" class=\"row_heading level0 row3\" >min</th>\n",
       "                        <td id=\"T_b80dd_row3_col0\" class=\"data row3 col0\" >1.000000</td>\n",
       "                        <td id=\"T_b80dd_row3_col1\" class=\"data row3 col1\" >1.000000</td>\n",
       "                        <td id=\"T_b80dd_row3_col2\" class=\"data row3 col2\" >20.000000</td>\n",
       "                        <td id=\"T_b80dd_row3_col3\" class=\"data row3 col3\" >1.000000</td>\n",
       "                        <td id=\"T_b80dd_row3_col4\" class=\"data row3 col4\" >1.000000</td>\n",
       "                        <td id=\"T_b80dd_row3_col5\" class=\"data row3 col5\" >0.000000</td>\n",
       "                        <td id=\"T_b80dd_row3_col6\" class=\"data row3 col6\" >39.000000</td>\n",
       "                        <td id=\"T_b80dd_row3_col7\" class=\"data row3 col7\" >0.000000</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_b80dd_level0_row4\" class=\"row_heading level0 row4\" >25%</th>\n",
       "                        <td id=\"T_b80dd_row4_col0\" class=\"data row4 col0\" >19669.750000</td>\n",
       "                        <td id=\"T_b80dd_row4_col1\" class=\"data row4 col1\" >1.000000</td>\n",
       "                        <td id=\"T_b80dd_row4_col2\" class=\"data row4 col2\" >29.000000</td>\n",
       "                        <td id=\"T_b80dd_row4_col3\" class=\"data row4 col3\" >3.000000</td>\n",
       "                        <td id=\"T_b80dd_row4_col4\" class=\"data row4 col4\" >3.000000</td>\n",
       "                        <td id=\"T_b80dd_row4_col5\" class=\"data row4 col5\" >0.000000</td>\n",
       "                        <td id=\"T_b80dd_row4_col6\" class=\"data row4 col6\" >51.000000</td>\n",
       "                        <td id=\"T_b80dd_row4_col7\" class=\"data row4 col7\" >0.000000</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_b80dd_level0_row5\" class=\"row_heading level0 row5\" >50%</th>\n",
       "                        <td id=\"T_b80dd_row5_col0\" class=\"data row5 col0\" >39225.500000</td>\n",
       "                        <td id=\"T_b80dd_row5_col1\" class=\"data row5 col1\" >1.000000</td>\n",
       "                        <td id=\"T_b80dd_row5_col2\" class=\"data row5 col2\" >33.000000</td>\n",
       "                        <td id=\"T_b80dd_row5_col3\" class=\"data row5 col3\" >3.000000</td>\n",
       "                        <td id=\"T_b80dd_row5_col4\" class=\"data row5 col4\" >5.000000</td>\n",
       "                        <td id=\"T_b80dd_row5_col5\" class=\"data row5 col5\" >0.000000</td>\n",
       "                        <td id=\"T_b80dd_row5_col6\" class=\"data row5 col6\" >60.000000</td>\n",
       "                        <td id=\"T_b80dd_row5_col7\" class=\"data row5 col7\" >0.000000</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_b80dd_level0_row6\" class=\"row_heading level0 row6\" >75%</th>\n",
       "                        <td id=\"T_b80dd_row6_col0\" class=\"data row6 col0\" >58730.500000</td>\n",
       "                        <td id=\"T_b80dd_row6_col1\" class=\"data row6 col1\" >1.000000</td>\n",
       "                        <td id=\"T_b80dd_row6_col2\" class=\"data row6 col2\" >39.000000</td>\n",
       "                        <td id=\"T_b80dd_row6_col3\" class=\"data row6 col3\" >4.000000</td>\n",
       "                        <td id=\"T_b80dd_row6_col4\" class=\"data row6 col4\" >7.000000</td>\n",
       "                        <td id=\"T_b80dd_row6_col5\" class=\"data row6 col5\" >0.000000</td>\n",
       "                        <td id=\"T_b80dd_row6_col6\" class=\"data row6 col6\" >76.000000</td>\n",
       "                        <td id=\"T_b80dd_row6_col7\" class=\"data row6 col7\" >0.000000</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_b80dd_level0_row7\" class=\"row_heading level0 row7\" >max</th>\n",
       "                        <td id=\"T_b80dd_row7_col0\" class=\"data row7 col0\" >78298.000000</td>\n",
       "                        <td id=\"T_b80dd_row7_col1\" class=\"data row7 col1\" >10.000000</td>\n",
       "                        <td id=\"T_b80dd_row7_col2\" class=\"data row7 col2\" >60.000000</td>\n",
       "                        <td id=\"T_b80dd_row7_col3\" class=\"data row7 col3\" >5.000000</td>\n",
       "                        <td id=\"T_b80dd_row7_col4\" class=\"data row7 col4\" >37.000000</td>\n",
       "                        <td id=\"T_b80dd_row7_col5\" class=\"data row7 col5\" >1.000000</td>\n",
       "                        <td id=\"T_b80dd_row7_col6\" class=\"data row7 col6\" >99.000000</td>\n",
       "                        <td id=\"T_b80dd_row7_col7\" class=\"data row7 col7\" >1.000000</td>\n",
       "            </tr>\n",
       "    </tbody></table>"
      ],
      "text/plain": [
       "<pandas.io.formats.style.Styler at 0x1d3b236bdc0>"
      ]
     },
     "execution_count": 678,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# lets check descriptive statistics for numerical columns\n",
    "train.describe().style.background_gradient(cmap = 'copper')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 679,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 0
    },
    "id": "adu5VnFDzl1Q",
    "outputId": "6dd98237-ac7a-4c7f-e09c-af37bc8fa921"
   },
   "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>department</th>\n",
       "      <th>region</th>\n",
       "      <th>education</th>\n",
       "      <th>gender</th>\n",
       "      <th>recruitment_channel</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>54808</td>\n",
       "      <td>54808</td>\n",
       "      <td>52399</td>\n",
       "      <td>54808</td>\n",
       "      <td>54808</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>unique</th>\n",
       "      <td>9</td>\n",
       "      <td>34</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>top</th>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>region_2</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>other</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>freq</th>\n",
       "      <td>16840</td>\n",
       "      <td>12343</td>\n",
       "      <td>36669</td>\n",
       "      <td>38496</td>\n",
       "      <td>30446</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               department    region   education gender recruitment_channel\n",
       "count               54808     54808       52399  54808               54808\n",
       "unique                  9        34           3      2                   3\n",
       "top     Sales & Marketing  region_2  Bachelor's      m               other\n",
       "freq                16840     12343       36669  38496               30446"
      ]
     },
     "execution_count": 679,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# lets check descriptive statistics for categorical columns\n",
    "train.describe(include = 'object')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 680,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "a6JNNxXDzl4f",
    "outputId": "7b432ad5-d19c-4a2f-884f-b03f57357376"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "employee_id                0\n",
       "department                 0\n",
       "region                     0\n",
       "education               2409\n",
       "gender                     0\n",
       "recruitment_channel        0\n",
       "no_of_trainings            0\n",
       "age                        0\n",
       "previous_year_rating    4124\n",
       "length_of_service          0\n",
       "awards_won?                0\n",
       "avg_training_score         0\n",
       "is_promoted                0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 680,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 681,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "A_EMdxF2zl7s",
    "outputId": "485b36c9-97ef-4e8f-a6be-48ccaf3d47f1"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "employee_id                0\n",
       "department                 0\n",
       "region                     0\n",
       "education               1034\n",
       "gender                     0\n",
       "recruitment_channel        0\n",
       "no_of_trainings            0\n",
       "age                        0\n",
       "previous_year_rating    1812\n",
       "length_of_service          0\n",
       "awards_won?                0\n",
       "avg_training_score         0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 681,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 682,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 0
    },
    "id": "81FACUsszl-j",
    "outputId": "d25d5fa7-22fe-4237-c09a-49e5ed9e4711"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 682,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABn0AAAMCCAYAAACsqQPvAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/NK7nSAAAACXBIWXMAAAsTAAALEwEAmpwYAAEAAElEQVR4nOzdebRXZaE+8OcMjIfJERUBZ8VZc0bNsrpmzqKZOSUOiQOYmpoapSgYIiKaCg44hVNG5lDd22Bdw/B6LTM15xhkUjwQh/EMvz9cnl9c1IOlHnz9fNZquXi/e3i3z3rzy3nO3ruitra2KQAAAAAAAHyiVbb2BAAAAAAAAPj3KX0AAAAAAAAKoPQBAAAAAAAogNIHAAAAAACgAEofAAAAAACAAih9AAAAAAAACqD0AQAAAAAAKIDS51OsqamptafAR0i+5ZNx2eRbPhmXTb7lk3HZ5AufbNZw2eRbPhmXTb4fPaXPp1hFRUWSpLGxsZVnwkdBvuWTcdneyZdyWcNlk2/5ZFw2+ZZryZIlftj0KWANl02+5ZNx2eT70atu7Qnw8Vq4cGFuv/32zJ49O0lywgknpHv37q08Kz4s8i2fjMu2aNGi/PSnP82sWbPS0NCQL3/5y+nVq1c6dOjQ2lPjQ2INl02+5ZNx2eRbvsbGxnzzm99Mz549c9FFF6W62o9ESmINl02+5ZNx2eT78aqora31Ky6fEgsXLszxxx+fDh06pKqqKnPmzMm8efNyww03ZIMNNmjt6fFvkm/5ZFy2BQsW5LjjjkvXrl1TVVWVJUuW5Lnnnsvhhx+eQw89NL169WrtKfJvsobLJt/yybhs8v10WLx4cQYOHJinnnoqX/va13LGGWekstIDUEpgDZdNvuWTcdnk+/Hz7eZT5IYbbkibNm0ybNiwXHPNNRk9enQ6d+6cO++8s7WnxodAvuWTcbmampoyYsSIVFdXZ8iQIbnmmmty880357DDDstdd92VMWPG5OWXX27tafJvsobLJt/yybhs8v10aNeuXXbaaae0b98+9957by655BKPeiuENVw2+ZZPxmWT78fPvcyfIjNmzMjqq6+eNddcM0my1lprpVevXunWrVueeeaZ1NTUpHPnzll99dVbeab8K+RbPhmXa8mSJfn73/+ePn36pHv37s0/fDj++OPzi1/8Ik8++WTat2+f/v37Z+21127l2fKvsobLJt/yybhs8i1fU1NTKioqssoqq6RHjx455phjctlll6WysjLnn3++R719wlnDZZNv+WRcNvl+/Hyr+RRp165dnnvuueY/NzU15dVXX80zzzyT+++/P/X19dlll11y/PHHp0+fPq04U/4V8i2fjMtVUVGRpUuXNj/btqKiIk1NTamsrMzWW2+dVVddNT/96U/Ts2fPHH300amoqGh+8SGfHNZw2eRbPhmXTb7le+e70y677JL77rsvG220Uc4888xcccUVqa6uzvnnn5+77747O+64o0fNfAJZw2WTb/lkXDb5fvyUPp8i/fr1y5NPPpmvfOUr2XbbbfPUU09l7bXXzgUXXJDNNtssjzzySO68885MmDAhm2yySSorK/1Q8RNEvuWTcbkqKyuz3Xbb5Re/+EXuu+++HHLIIamsrMwdd9yR1157LcOHD09FRUVuv/32/Md//EfWWmut1p4y/wJruGzyLZ+Myybfsr1zl09TU1Patm2bOXPmZPbs2Tn44IPTpk2bXH755Xn88cfT1NSU3XbbrbWny7/AGi6bfMsn47LJ9+NXUVtb6wG2BVq8eHGeeuqpLFy4MD169Mgmm2ySJHnppZfy4IMPpm3btpkwYUIuvfTSbL/99qmqqkqSXH311XnwwQdz//33p1OnTq15CbwP+ZZPxmVbsmRJnn322bz11ltZY401suWWW2bevHk5//zz8/e//z1VVVWpqanJ5MmTc/nll6dv376ZPHlyTjzxxBx++OHp379/a18CLbCGyybf8sm4bPIt36JFi/LHP/4xtbW1WX/99bP11lsn+f/lz0UXXZSNNtooxx57bJK3H6n73HPPZZdddsnIkSNbc+qsAGu4bPItn4zLJt+Vgzt9ClRXV5eTTjopc+fOzcKFC7Nw4cLst99++cpXvpJtttkmgwYNym9/+9vceuut2XDDDVNVVZX6+vpUV1ena9euWWWVVdK+ffvWvgzeg3zLJ+Oy1dXV5dRTT82iRYtSV1eX2bNnp2/fvvnGN76RK6+8Mv/5n/+Zv/zlL2nXrl2GDh2a3r17J0nWWWedtG/fPnPnzm3lK6Al1nDZ5Fs+GZdNvuWrq6vLgAEDMm/evPzjH/9IXV1djj766Jx00knNvznctWvXPPHEEzn22GMzePDgTJ06NUcddVTuu+++fOc738mQIUNSWVnZ2pfCu7CGyybf8sm4bPJdeSh9CtPQ0JBLLrkkXbt2zQUXXJBu3brlT3/6U66++uq88sor6devX/bZZ59069YtHTt2zCOPPJKvf/3rqa6uzvz58/PCCy+kZ8+eaWhoSFVVlVvpVjLyLZ+My1ZfX5+zzjorHTp0yHe+85306tUrkyZNysUXX5zzzjsvAwcOzH777Zf99tsvTU1NaWhoaN537ty5WXXVVZsf7fbOb6qycrGGyybf8sm4bPItX319fQYPHpwuXbrku9/9bjp06JDf/e53GTlyZHbffffmO3723HPPvPbaa/nWt76VZ555JiNHjsxGG22UNdZYI7fcckvmzJnjZdIrIWu4bPItn4zLJt+Vi9KnME1NTXn99dfz2c9+NptvvnmSt387fO21187o0aNz5513pm3bttljjz2yxRZb5L777ssrr7ySnj175plnnsmf/vSnjBkzJu3atWvlK+HdyLd8Mi7bG2+8kalTp+b444/PxhtvnIqKiuy55545++yzM3jw4Nx4441ZuHBhDjjggMyfPz/33ntv/vSnP2XnnXfOX//610yfPj177rlnkvgCtJKyhssm3/LJuGzyLd/ixYszZcqUfPnLX86GG26YJNlrr71y++23p76+PrW1tenWrVs22mijPPXUU6mpqckVV1yRLbbYIklywAEH5Mtf/nI6d+7cmpfBe7CGyybf8sm4bPJdubhfuSCNjY2pq6vL3LlzmxfIkiVL0tTUlO222y7f+ta30qZNm9xxxx2ZPHlyhgwZkh122CF//etf88gjj6SpqSk33HBDNthgg1a+Et6NfMsn4/LV1tZm9uzZWX311VNRUZHFixcnSWpqatKnT5907tw5P/7xj/PnP/85NTU1WWONNfKPf/wjP//5z/OPf/wj11xzTdZdd91WvgreizVcNvmWT8Zlk2/5GhsbM3/+/MyePXuZu6XbtGmT+fPn56qrrsrBBx+cb37zm/n1r3+d0aNH55prrslWW23VvG379u0VPispa7hs8i2fjMsm35VPRW1tbVNrT4IP1xVXXJGf//znufnmm9OrV680NDQ0P7v4qaeeykUXXZTPfOYz+f73v5+lS5emoaEh9fX1adu2bdq2bdva06cF8i2fjMvT2NiYysrKzJs3LwMGDEjnzp1zySWXND82ZOTIkVm6dGn22GOPfOc738mXvvSlnH/++c2PcFuwYEGqqqr8xssnhDVcNvmWT8Zlk2/5Ro4cmXvuuSfHHHNMVltttfzkJz9J27Zts88++6Rz5855+OGHM23atJxyyinZZ599Wnu6fEDWcNnkWz4Zl02+Kw93+nzC1dfX54033sjLL7/cPLb//vtnrbXWyogRIzJjxoxUVVWlsbGxuV0dOHBgfv7zn+dPf/pT2rRpk/bt26dTp04W10pIvuWTcdnq6+tTV1eX6dOnJ0m6dOmSL3/5y5kxY0YGDhyYkSNH5swzz8y9996bL3/5y9l1111zwgkn5IEHHsgLL7zQ/Ai3jh07KnxWUtZw2eRbPhmXTb7lW7x4cR5//PH853/+Z1544YU0NTXl+OOPz9FHH51HH300Dz74YGpra3PJJZfkiCOOyH777Zezzz47lZWVefbZZ1t7+rTAGi6bfMsn47LJd+Wm9PkEq6ury6BBg3LyySfnyCOPzKBBg/KnP/0pm266ab7yla/k9ddfz+jRozNz5sxUVVWlvr4+SbLrrrtm9dVXz0svvdTKV8D7kW/5ZFy2urq6nHPOOTnhhBNy5JFH5sILL8zs2bPz9a9/Pccff3x69uyZxx9/PPPmzct1113X/GiR7bbbLlVVVXn99ddb+QpoiTVcNvmWT8Zlk2/56urq0r9///zgBz/IhRdemEsvvTSTJ09O165dM2DAgNx+++3Zfffds8Yaa6RXr15pbGxMkmywwQZZZ511fNdayVnDZZNv+WRcNvmu/JQ+n1BLlizJoEGDUlVVlf79++fyyy/PSy+9lOuvvz5J8rWvfS3/8R//keeffz6XX355pk6dmjZt2iRJ3nrrrVRXV6empqY1L4H3Id/yybhsixcvzoABA1JfX59DDz00AwcOzGOPPZZrr702ydu//TJ06NDcdNNNueGGG7LNNtsss3+3bt08T34lZw2XTb7lk3HZ5Fu++vr6nH/++enatWsuvvji3H///bnooovSu3fv5m3atGmTefPmZcaMGXnjjTeaf9t49uzZWbx4cfr06dOKV8D7sYbLJt/yybhs8v1kqG7tCfCveeaZZzJz5sx873vfy/bbb58kaWhoyODBgzNz5sx07949J5xwQlZbbbXcfffdOfnkk3PKKadk8eLFefrpp1NfX59tt922dS+C9yTf8sm4bP/7v/+buXPn5vzzz89mm22WJKmtrc2Pf/zjzJs3Lx06dEibNm3SqVOnzJw5Mz/96U+b7/D5xS9+kfbt2y/zQwtWPtZw2eRbPhmXTb7le/PNNzN9+vSceOKJ2XLLLZMkf/nLX3LvvfdmwYIF2WyzzbLDDjtkr732ym9/+9sMHTo0J554Ympra/OrX/0q06dPzxe/+MVWvgreizVcNvmWT8Zlk+8ng9LnE2rBggWpra1dZqx9+/bp1q1bbrvttrzxxhvZfPPNc/TRR2errbbKnXfemREjRqRjx45ZbbXVMnLkyKy99tqtM3laJN/yybhs8+bNy9y5c7P66qs3j7Vt2zZLly7N6NGjM2vWrGyxxRY5/vjjU1NTkxdffDE33XRT1l577VRVVWXo0KHL7MvKxxoum3zLJ+Oyybd8jY2N+cc//pGqqqokya9+9atcdNFFWXvttTNr1qx06NAh22+/fYYOHZrjjz8+d999d4499th07949HTt2zMiRI9OrV69WvgreizVcNvmWT8Zlk+8nQ0VtbW1Ta0+CD27GjBk56qijsssuu+SAAw7IGmuskQsuuCB1dXXZeuut8+abb+aFF15Inz59MnLkyFRXV+f1119PTU1NKisrPTZoJSff8sm4bM8++2y+8Y1v5Lrrrsv222+fJUuW5Nhjj82SJUuy5ZZbZsaMGZkyZUp22GGHfP/7309FRUVeeOGFtG3bNl26dMmqq67a2pdAC6zhssm3fDIum3zLN3/+/Bx99NHZbbfdcs455+Soo47KXnvtlYMOOiidOnXK3Xffnfvuuy/bb799vv/976e2tjavvPJKVl111XTr1i3dunVr7UvgfVjDZZNv+WRcNvl+Mih9PiEWL16cF154oflF30nyhz/8IUOGDElVVVUWLlyYNddcM8OHD0+PHj3S1NSUu+++O2PHjs3gwYOz5557prGxMZWVXuO0MpJv+WRctoaGhsybNy8NDQ1p3759OnXqlEmTJmWTTTZJt27d8ve//z3jxo3Lcccdl969e6exsTE33HBDHnjggYwePTobbbRRa18CLbCGyybf8sm4bPItX1NTUyoqKpYZe+CBBzJ8+PD0798/kyZNyllnnZUNN9wwydul0B133JEHHngg11xzTTbYYIPWmDYryBoum3zLJ+OyyfeTyb/tT4jzzjsvQ4cOzR//+Mfmsd122y133nlnbrzxxmy88cbZfvvts/baa6e+vj4VFRXZf//9s3DhwkyfPj1JLK6VmHzLJ+Ny1dXV5bzzzstpp52WY445JhdeeGFefPHF7LTTTunSpUuSpHfv3jnnnHPSq1ev5i87hx9+eObMmZO///3vrXwFrAhruGzyLZ+Myybfsi1YsCDDhg3LmWeemYEDB+aRRx7J7Nmzs88+++Rzn/tc7rnnnrz44ovp2LFjkmTp0qXp1KlTvvrVrzb/tjErN2u4bPItn4zLJt9PJv/GPyE222yzvPLKK7n33nszceLE5vFVVlklnTt3ziuvvJLk7UVUXV2dhoaGTJ8+PT179sx6663XSrNmRcm3fDIu06JFi3LSSSdl3rx5OeSQQ3LwwQfnrbfeyjnnnJNp06alsrIyjY2NSZKOHTumoqKieWzq1KlZa621PMv2E8IaLpt8yyfjssm3XIsWLco3vvGNPPfcc+natWuWLFmS6667Lt/97nczc+bMfPOb38xGG22UefPm5eGHH06StGnTJknyxhtvZK211vLY3E8Aa7hs8i2fjMsm30+m6taeACvmndvjnnrqqcybNy9VVVXZaaedkrz9g8QvfvGL+fnPf55tttkmX/ziFzNt2rTcd999qa+vz/rrr9/Ks6cl8i2fjMv0s5/9LFVVVbnwwgvTs2fPJG/f1XPppZfmySefTI8ePZofRfL666/nrbfeyhZbbJHXX389Dz/8cKqrq7Pmmmu25iWwgqzhssm3fDIum3zL9ctf/jJVVVUZOnRoevTokSSZMGFCfvKTn2TAgAG55pprmn8DecyYMZk3b1723nvvNDQ05KGHHkpDQ0N69+7dyldBS6zhssm3fDIum3w/mbzTZyXX0NCQqqqq/P3vf88111yTQw45JEOGDMnaa6+d/v37Z9ddd02SvPrqqxk5cmQmTZqUNdZYI+3atcuCBQty1VVXZZNNNmnlq+C9yLd8Mi7btddem0cffTS33HJLampqmscPPvjgbLfddvnud7+bJKmvr89vfvObfPe7382qq66ampqaLFq0KFdccYV8V3LWcNnkWz4Zl02+5bv99ttz9913584770zXrl2bx//whz/kpptuyuzZs3PdddelY8eOufvuu/OjH/0oSdKlS5d07NgxQ4YMkfFKzBoum3zLJ+OyyfeTTemzElqwYEEefvjh9OvXr3ls0aJFOeSQQzJs2LDU1NTk1FNPTa9evXL66afngQceyHHHHZckefHFF/PMM89kvfXWy/bbb5911lmnla6C9yLf8sm4bP+c7w033JCf/OQnufXWW9O9e/fm9/WcdNJJqampyciRI5vHZs6cmb/+9a956aWX0qNHj2y33XbyXUlZw2WTb/lkXDb5lu+fM37ggQdy/fXX59prr83666+fpUuXNj++beLEiRkzZkzatWuXIUOGZPXVV8+0adPy2muvpUuXLllnnXWy2mqrtfLV8H9Zw2WTb/lkXDb5lkPps5KZP39+jjzyyGyzzTa54IIL0r59++Zm9bzzzst2222Xr371q3nppZcycODANDU15c0338y4cePSp0+f1p4+LZBv+WRctnfy3XrrrTNkyJD84x//yODBg3PYYYdl1113TX19faqrqzNo0KA0Njbm6quvbh5rampKRUVF8z9ZOVnDZZNv+WRcNvmW75+/a1188cVpaGjIEUcckXXXXTejRo1KkmWKnwcffDA333xzjjzyyGV+QMXKyRoum3zLJ+Oyybcsla09Af6/+fPn5+ijj06PHj1y+umnp3379mlqakpVVVWSZL311st//dd/pbGxMRtttFE23njjvPXWW9l4441TV1fXyrOnJfItn4zL9s/5nnHGGWlqakrnzp1zwQUXNN/WXF399qvy5s6d2/zDiOrq6tTV1eXqq6/Oiy++qPBZiVnDZZNv+WRcNvmW7/9+10qSNm3a5LTTTsv//u//5qKLLmoeW7p0aZJkv/32y4Ybbphf/OIXrTZvVow1XDb5lk/GZZNveZQ+K4m6urocffTR6dWrVwYPHrzci72bmpqy1VZbZfHixamsrMzgwYPz/PPP54ILLsjcuXMzYsSIPPnkk600e1oi3/LJuGzvlu875c0/PzaksbExydu3P3fo0CHJ21+errnmmvzoRz9S+KzErOGyybd8Mi6bfMv3bhlXVr7944rdd989J598cp544olceOGFSdL8yzVJsv7662fx4sWpr69vlbnTMmu4bPItn4zLJt8yVbf2BHjbLbfcktdffz3XXHNN1lprrSTJ//7v/+axxx5LbW1t1l133ey///6prq7OV7/61bz55pu54oorsu2222aDDTbI4MGDs/baa7fyVfBe5Fs+GZetpXxXW221HHvssampqcmiRYuyZMmSdOrUKQ0NDRk5cmR++ctf5vbbb89GG23UylfCe7GGyybf8sm4bPIt33tl/N///d/Nhc7Xvva13HvvvTnzzDPz7W9/O6uttlrq6ury8ssvZ80110xTkyfXr6ys4bLJt3wyLpt8y+SdPiuJN954I6eeemp69+6dH/zgB5k4cWK+9a1vZbPNNsvChQszY8aMVFdXZ8GCBdlwww3zrW99K9ttt13zC8KXLFmStm3btvZl8B7kWz4Zl62lfGfNmpVVVlklI0aMyHrrrZcjjzwy3bt3T/fu3fPQQw/lxhtvzKabbtral8H7sIbLJt/yybhs8i3fe2W86aabZuHChZk3b17atm2bo446Kj/+8Y/z1ltvZdVVV027du0yderU3HDDDdlwww1b+zJ4D9Zw2eRbPhmXTb5lUvqsJBobG/OLX/wi48aNS9++ffOnP/0pn/3sZ3PggQemc+fOefrpp3PLLbdk0qRJGTduXDbbbLNl9vdi8JWbfMsn47K1lO9f/vKXXHnllWlqasrtt9+ewYMH5+c//3lqamrywx/+cLm8WflYw2WTb/lkXDb5lm9FMh41alQaGhpyww035Mc//nFmzJiRmpqafOUrX0nv3r1b+xJ4H9Zw2eRbPhmXTb5l8k6flURlZWV22223bLnllvn973+fxYsXZ++99063bt1SVVWVLbbYIoceemhWXXXVzJ49e7n9La6Vm3zLJ+OyrUi+J554YqZPn57HH388u+66a9Zbb72MHTtW4fMJYQ2XTb7lk3HZ5Fu+ljLecsstc/zxx2f69Ol59tlnc/TRR+ecc87JgAEDFD6fANZw2eRbPhmXTb5lUvqsRLp27ZpvfOMbeeutt9KlS5d07949SdLQ0JC2bdvmM5/5TBYsWJAZM2a08kz5V8i3fDIu2/vl26ZNm2y33Xapr6/PjBkz0rdv3/zwhz/0mJFPGGu4bPItn4zLJt/ytfRda/vtt099fX1eeeWV5n28x+eTwxoum3zLJ+Oyybc81a09AZa17rrr5tZbb82SJUvSpk2bJElVVVWSt5+x2L1796y++uqtOUX+DfItn4zL1lK+a665Zrp06ZLOnTu35jT5N1jDZZNv+WRcNvmWb0UyXmONNZq399vFnyzWcNnkWz4Zl02+ZVH6rIR69OiRJJkyZUqeffbZrLvuumlqaspPfvKTzJ8/P3369GnlGfLvkG/5ZFy298u3rq4um2++eSvPkH+XNVw2+ZZPxmWTb/lkXDb5lk2+5ZNx2eRbDqXPSqqpqSlz5szJpZdemvr6+qy++urp0KFDRo4cmbXWWqu1p8e/Sb7lk3HZ5Fs+GZdNvuWTcdnkWz4Zl02+ZZNv+WRcNvmWoaK2ttZDcFdiL7/8cv7+97+nU6dO2WCDDdxGVxj5lk/GZZNv+WRcNvmWT8Zlk2/5ZFw2+ZZNvuWTcdnk+8mm9AEAAAAAAChAZWtPAAAAAAAAgH+f0gcAAAAAAKAASh8AAAAAAIACVH/QHX73u9/lu9/9bn7729++73Yvv/xyRowYkb/+9a/p0qVL+vXrl2OOOSYVFRX/6lwBAAAAAAA+dLW1tfnSl7603PjnP//5DBs2bLltv/rVr+bQQw/NSSed1Dw+b968jB49Oo899liWLFmSbbfdNmeeeWZ69OixzDYjR47M73//+zQ1NeVzn/tcBg0alE6dOjVv88orr+Sqq67KM888k44dO2avvfbKgAED0rFjxxav4wOVPk8//XQGDx6cpqam991uzpw5OfXUU7Phhhvmsssuy/PPP5/rr78+VVVVOeqooz7IKQEAAAAAAD5SL774YpJk9OjRy5QrXbt2XW7bK664Im+99dZy4xdeeGFeeOGFnH766enSpUvGjBmTAQMGZPz48c3HPPfcc/P666/nvPPOy6JFizJ69Oi8+eabGTlyZJK3S6HTTjstq6++ei6++OLU1tbm6quvzhtvvLFc+fRuVqj0WbJkSe66667ccMMN6dChQxobG993+/vuuy8NDQ0ZMWJE2rdvn759+2bp0qUZN25cjjjiiFRXf+AbjAAAAAAAAD4SL730UlZdddXsvPPO77vd73//+/zxj39Mu3btlhmfM2dOHn/88Vx44YX5yle+kiTp1atXDjvssEycODF77713/ud//idPPvlkbr755my55ZZJkjXXXDOnnXZann/++Wy22Wb54x//mDfeeCNjx45tvkNo6dKlGTp0aGpra9OtW7f3nd8KvdPnD3/4Q2699dacccYZOfzww1vcftKkSdlxxx3Tvn375rHPfvazmTdvXp599tkVOSUAAAAAAMDH4qWXXsrGG2/8vtvMnz8/l19+eQYOHJg2bdos89mSJUuSJDU1Nc1j79wlNG/evCRvdyerrrpqc+GTJDvssENqamoyceLEFo8zd+7cFq9jhUqfzTffPBMmTMhXv/rVFdk8kydPzrrrrrvM2DuN1OTJk1foGAAAAAAAAB+HF198MYsWLUr//v2z++67Z7/99svtt9++zOtuRo0alfXXXz/77bffcvuvtdZa2X333XPLLbfktddey5w5czJixIjU1NRkt912S/Lu3UllZWXWXnvt5u5kjz32yFprrZWRI0dmzpw5ee2113LjjTemT58+6dWrV4vXsULPWVtzzTVXZLNmdXV1y7RQSZqfV1dXV/eBjgUAAAAAAPBRaWhoyKuvvpoOHTrkjDPOyNprr53HHnss1157bRYvXpwTTjghTzzxRH75y1/mRz/60Xse56yzzsppp53W/MS0du3aZcSIEenevXuSt/uRf35f0Dtqamqau5MuXbrkvPPOy7nnnptHHnkkSbL22mtn7NixqaioaPFaPpKX6/xz8/V/tTSpKVOmZNGiRR/2lAAAAAAAgE+hlh7bliRXXnll1lprrfTs2TNJ8pnPfCYLFizIbbfdlqOOOiqXXXZZTjrppOanmv1fs2bNSv/+/bPKKqtk2LBhqampyYQJE3Luuefm6quvzlZbbZXkvTuSysq3H8w2ceLEnHXWWdljjz1yyCGHZOHChbnpppty2mmnZcyYMS2+0+cjKX06deqUBQsWLDP2zp87der0vvu+8y+0NXTt1rXVzt0a5ta2/Py/ksi3bJ+2fJNPX8at5cUXX1yhLwb8e6zh8n3aMpZv+WRctk9bvq3F96yPjzVcNvmWT8Zlk+/KoaqqKjvuuONy47vuumvuv//+XHTRRenUqVMOO+yw1NfXN3/e1NSU+vr6VFdX52c/+1nmzZuX2267rfnpaTvttFP69++f0aNHZ8yYMampqcmbb7653Hnq6uqaH912xx13ZP3118/QoUNTVVWVJNl2221z8MEH5+67787JJ5/8vteyQu/0+aB69uyZadOmLTP2zp979+79UZwSAAAAAADgA5s9e3Z+8pOf5K233lpmfPHixUnevvvmb3/7W3bffffstttu2W233TJ//vzcdNNNze/rmTVrVrp3777M63IqKiqyzTbb5NVXX02S9OrVa7nupLGxMdOnT2/uTmbOnJk+ffo0Fz5Jssoqq6RXr17Nx3k/H0nps+OOO+aJJ57IwoULm8ceffTRdO3aNZtssslHcUoAAAAAAIAPbMmSJRk6dGjzO3Te8etf/zq9evXKuHHjlvtfx44dc9BBB2XcuHFJ3i50ZsyYkZkzZy5zjGeeeSbrrLNOkmSHHXbIG2+8kb/+9a/Nn//P//xP6urqmu806tWrV/7617+moaGheZu5c+dmypQpzcd5Px/K492mTp2at956q/mZdP369cs999yTQYMG5aijjsqLL76YW2+9NaeeemratGnzYZwSAAAAAADg39ajR4986Utfyg033JDKysqst956+dWvfpXf/OY3GT58eDbaaKPl9qmsrMzqq6+ezTffPEmy//77Z/z48Rk0aFD69++fmpqaPPzww3n66aczfPjwJG/fMLPlllvm3HPPzemnn576+vpcffXV6du3b/r06ZMkOe644/LNb34z5557bg499NAsWrQo48aNS1VVVQ4//PAWr+VDKX1uuummPPTQQ5k0aVKSZPXVV88111yTK6+8Mueff35WXXXVfPOb38xRRx31YZwOAAAAAADgQ3PhhRfm5ptvzvjx4/Pmm29mvfXWy7Bhw7Lnnnuu0P5dunTJ2LFjM2rUqFx22WVpamrKxhtvnGuvvTY77LBDkrcf93bFFVfkiiuuyNChQ9OmTZvsueeeOfPMM5uPs/XWW+eaa67Jddddl29/+9upqanJtttum8suuyxrrbVWi/OoqK2tbfrX/hWUx0uzyibfsn3a8k0+fRm3Fi8Y/nhYw+X7tGUs3/LJuGyftnxbi+9ZHx9ruGzyLZ+MyyZfPmwfyTt9AAAAAAAA+HgpfQAAAAAAAAqg9AEAAAAAACiA0gcAAAAAAKAASh8AAAAAAIACKH0AAAAAAAAKoPQBAAAAAAAogNIHAAAAAACgAEofAAAAAACAAih9AAAAAAAACqD0AQAAAAAAKIDSBwAAAAAAoABKHwAAAAAAgAIofQAAAAAAAAqg9AEAAAAAACiA0gcAAAAAAKAASh8AAAAAAIACKH0AAAAAAAAKUN3aEwCAFdG1W9dWOe8O2aFVzju3dm6rnBcAAACATy53+gAAAAAAABRA6QMAAAAAAFAApQ8AAAAAAEABlD4AAAAAAAAFUPoAAAAAAAAUQOkDAAAAAABQAKUPAAAAAABAAZQ+AAAAAAAABVD6AAAAAAAAFEDpAwAAAAAAUAClDwAAAAAAQAGUPgAAAAAAAAVQ+gAAAAAAABRA6QMAAAAAAFAApQ8AAAAAAEABlD4AAAAAAAAFUPoAAAAAAAAUQOkDAAAAAABQgOrWngAAAADQerp269oq590hO7TKeefWzm2V8wIAfBzc6QMAAAAAAFAApQ8AAAAAAEABlD4AAAAAAAAFUPoAAAAAAAAUQOkDAAAAAABQAKUPAAAAAABAAZQ+AAAAAAAABVD6AAAAAAAAFEDpAwAAAAAAUAClDwAAAAAAQAGUPgAAAAAAAAVQ+gAAAAAAABRA6QMAAAAAAFAApQ8AAAAAAEABlD4AAAAAAAAFUPoAAAAAAAAUQOkDAAAAAABQAKUPAAAAAABAAZQ+AAAAAAAABVD6AAAAAAAAFEDpAwAAAAAAUAClDwAAAAAAQAGUPgAAAAAAAAVQ+gAAAAAAABRA6QMAAAAAAFAApQ8AAAAAAEABlD4AAAAAAAAFUPoAAAAAAAAUQOkDAAAAAABQAKUPAAAAAABAAZQ+AAAAAAAABVD6AAAAAAAAFEDpAwAAAAAAUAClDwAAAAAAQAGUPgAAAAAAAAVQ+gAAAAAAABRA6QMAAAAAAFAApQ8AAAAAAEABlD4AAAAAAAAFUPoAAAAAAAAUQOkDAAAAAABQAKUPAAAAAABAAZQ+AAAAAAAABVD6AAAAAAAAFEDpAwAAAAAAUAClDwAAAAAAQAGUPgAAAAAAAAVQ+gAAAAAAABRA6QMAAAAAAFAApQ8AAAAAAEABlD4AAAAAAAAFUPoAAAAAAAAUQOkDAAAAAABQAKUPAAAAAABAAZQ+AAAAAAAABVD6AAAAAAAAFEDpAwAAAAAAUAClDwAAAAAAQAGUPgAAAAAAAAVQ+gAAAAAAABRA6QMAAAAAAFAApQ8AAAAAAEABlD4AAAAAAAAFUPoAAAAAAAAUQOkDAAAAAABQAKUPAAAAAABAAVa49JkwYUIOPfTQ7LHHHjn++OPz9NNPv+/2Tz/9dE488cTstddeOeiggzJ27NjU19f/2xMGAAAAAAD4qCxZsiSHH354vv/97zePzZ8/P5dffnm+/OUvZ6+99srZZ5+dqVOnLrPfvHnzcumll2bffffNF77whZx99tmZNm3ae57nySefzM4775wnn3xymfGFCxfmiiuuyD777JO99torp5xySp5//vkVmvsKlT4PPvhghg0bln322SfDhg1L586dM3DgwPec7NSpU3P66aenQ4cOGTZsWL72ta/ltttuy7XXXrtCkwIAAAAAAGgNN954Y1577bVlxi666KI8+uijOf3003PppZdmzpw5+eY3v5n58+c3b3PhhRfm97//fU499dQMHjw4M2fOzIABA7JgwYLlzrFo0aJceumlaWpqWu6z888/P7/+9a9zxhln5LLLLkt9fX0GDhyY2traFude3dIGTU1NGTt2bA466KCceOKJSZKdd945/fr1y/jx43P22Wcvt8+vfvWrNDY25vLLL0+HDh2yyy675M0338y9996bM844IxUVFS1ODAAAAAAA4OP0t7/9LXfffXe6devWPPbKK6/ksccey+WXX57Pfe5zSZINNtggBx54YH7/+9/ny1/+cubMmZPHH388F154Yb7yla8kSXr16pXDDjssEydOzN57773Mea6//vosWbJkufNPmjQpEydOzM0335wtttgiSdKnT58cffTR+fOf/5zPfvaz7zv/Fu/0mTJlSqZPn54999yzeay6ujp9+/bNxIkT33WfpUuXprq6Ou3atWse69q1axYsWPCuFwEAAAAAANCa6uvrc8kll+Soo47KGmus0Tzeo0eP3Hzzzdltt92ax9q0aZMkzZ3HO/+sqalp3qZr165J3n7s2z975plncv/992fgwIHLzeHRRx/NJpts0lz4JMkqq6ySBx98sMXCJ1mB0mfy5MlJknXXXXeZ8R49emTatGlpaGhYbp999tknlZWVufbaazN37tw8++yzGT9+fPbaa69liiAAAAAAAICVwW233ZalS5fmuOOOW2a8Xbt22XLLLdOuXbvU19fnlVdeySWXXJJVV121uYhZa621svvuu+eWW27Ja6+9ljlz5mTEiBGpqalZpixaunRphgwZkuOOOy69e/debg4vvvhi1l9//dx333058MADs+uuu+bEE0/MSy+9tELX0OLj3erq6pIkHTt2XGa8Y8eOaWxszMKFC9OpU6dlPlt33XVzxhlnZOjQobn99tuTJJtttlkuuuiiFic0ZcqULFq0aIUm/6F7onVO22pebO0JfMzkW7ZPW76JjEsn3/LJuGzyLZ+Myybfsn3a8k1kXDr5lk/GZZPvx2LjjTducZtXX301t9xyS6699trmu3jezWWXXZYHH3wwlZWVufDCC5d5DNxZZ52V0047LYcffniSt8uiESNGpHv37s3b3HzzzamsrMwxxxyTV155Zbnj19bWZsqUKXnuuecycODAtGnTJjfccENOO+203Hfffcv1Mf/XCr3TJ8l7voensnL5m4UmTJiQyy67LAcffHC+8IUv5I033sgNN9yQM888M9dee23atm37nufr2bNnS1P6yHTt1rXVzt0a5tbObe0pfKzkW7ZPW76JjEsn3/LJuGzyLZ+Myybfsn3a8k1kXDr5lk/GZZPvyqGxsTGXXnppDjjggGy99dbvu+2hhx6afffdN48++mguvvji1NfX56CDDsqsWbPSv3//rLLKKhk2bFhqamoyYcKEnHvuubn66quz1VZb5cUXX8wdd9yR66+/PtXV717P1NfXp7a2NmPHjm1+Atumm26aQw45JPfff3+OOeaY951fi6XPO63RggULstpqqzWPL1iwIFVVVcvdAZS8fQtU3759c/755zeP9enTJ4cffnh+/vOf54ADDmjptAAAAAAAAB+5e+65JzNmzMjIkSNTX1/fPN7U1JT6+vplCpp33rWzww47ZNasWRk3blwOOuig/OxnP8u8efNy2223Zc0110yS7LTTTunfv39Gjx6d6667LkOGDMmBBx6YTTfdNPX19c2vz2loaEhDQ0OqqqrSoUOH9OrVa5lX7qy55ppZb7318vLLL7d4LS2WPu/ceTNt2rRl7sKZNm1aevXq9a77zJw5M1/5yleWGVtvvfXStWvXvPrqqy1OCgAAAAAA4OPw29/+NrNmzcree++9zPiLL76Yhx9+OD/5yU/y5JNPZv/991/mqWibbLJJHnvssSTJrFmz0r179+bCJ3n7CWrbbLNNHnzwwcycOTPPPfdcnnvuudxzzz3LnOe0007L9ttvn+uvvz49e/bMCy+8sNwc/7mMej8tlj69evVK9+7d8+ijj2aXXXZpPvhjjz2Wvn37vuc+Tz/99DJjU6ZMydy5c7POOuus0MQAAAAAAAA+aueff37q6uqWGfvud7+bXr165YQTTsjLL7+cIUOGZJ111skOO+yQ5O27gCZNmpQNN9wwydu9yAMPPJCZM2cu8w6fZ555Juuss07WWGONjBs3bplzTJ48Od/97ndz3nnn5TOf+UySZOedd86vf/3r/O1vf8umm26aJJk6dWr+/ve/57DDDmvxWlosfSoqKnLsscdm+PDh6dy5c7bZZpvce++9mTt3bo488sjmE7711lvZaqutkiT9+/fPd77znQwZMiRf+tKXMmfOnIwdOzZrr7129t133xYnBQAAAAAA8HHo3bv3cmPt2rVL165ds/nmm6e+vj5bbrllLr744pxyyinp1q1bfvrTn+bpp5/OVVddlSTZf//9M378+AwaNCj9+/dPTU1NHn744Tz99NMZPnx42rRpk80333yZc7zz2LjevXs3z2HffffNXXfdlW9/+9sZMGBA2rZtm+uvvz5rr732ck9Yezctlj5J0q9fvyxevDh33XVXxo8fn0022SSjRo1Kjx49kiQ33XRTHnrooUyaNClJ8oUvfCFVVVW5+eab88gjj2TVVVfNTjvtlFNPPTU1NTUrckoAAAAAAIBWV11dnSuvvDI//OEPc80112TevHnZbLPNMnr06OY7f7p06ZKxY8dm1KhRueyyy9LU1JSNN9441157bfM2K6Jdu3a57rrrMmrUqPzgBz9IY2Njdthhh5x99tlp3759i/tX1NbWNv3LV1qYrt26tvYUPlZza+e29hQ+VvIt26ct30TGpZNv+WRcNvmWT8Zlk2/ZPm35JjIunXzLJ+OyyZcPW2VrTwAAAAAAAIB/n9IHAAAAAACgAEofAAAAAACAAih9AAAAAAAACqD0AQAAAAAAKIDSBwAAAAAAoABKHwAAAAAAgAIofQAAAAAAAAqg9AEAAAAAACiA0gcAAAAAAKAASh8AAAAAAIACKH0AAAAAAAAKoPQBAAAAAAAogNIHAAAAAACgAEofAAAAAACAAih9AAAAAAAACqD0AQAAAAAAKIDSBwAAAAAAoABKHwAAAAAAgAIofQAAAAAAAAqg9AEAAAAAACiA0gcAAAAAAKAASh8AAAAAAIACKH0AAAAAAAAKoPQBAAAAAAAogNIHAAAAAACgAEofAAAAAACAAih9AAAAAAAACqD0AQAAAAAAKIDSBwAAAAAAoABKHwAAAAAAgAIofQAAAAAAAAqg9AEAAAAAACiA0gcAAAAAAKAASh8AAAAAAIACKH0AAAAAAAAKoPQBAAAAAAAogNIHAAAAAACgAEofAAAAAACAAih9AAAAAAAACqD0AQAAAAAAKIDSBwAAAAAAoABKHwAAAAAAgAIofQAAAAAAAAqg9AEAAAAAACiA0gcAAAAAAKAASh8AAAAAAIACKH0AAAAAAAAKoPQBAAAAAAAogNIHAAAAAACgAEofAAAAAACAAih9AAAAAAAACqD0AQAAAAAAKIDSBwAAAAAAoABKHwAAAAAAgAIofQAAAAAAAAqg9AEAAAAAACiA0gcAAAAAAKAASh8AAAAAAIACKH0AAAAAAAAKoPQBAAAAAAAogNIHAAAAAACgAEofAAAAAACAAih9AAAAAAAACqD0AQAAAAAAKIDSBwAAAAAAoABKHwAAAAAAgAIofQAAAAAAAAqg9AEAAAAAACiA0gcAAAAAAKAASh8AAAAAAIACKH0AAAAAAAAKoPQBAAAAAAAogNIHAAAAAACgAEofAAAAAACAAih9AAAAAAAACqD0AQAAAAAAKIDSBwAAAAAAoABKHwAAAAAAgAIofQAAAAAAAAqg9AEAAAAAACiA0gcAAAAAAKAASh8AAAAAAIACKH0AAAAAAAAKoPQBAAAAAAAogNIHAAAAAACgAEofAAAAAACAAih9AAAAAAAACqD0AQAAAAAAKIDSBwAAAAAAoABKHwAAAAAAgAIofQAAAAAAAAqg9AEAAAAAACiA0gcAAAAAAKAASh8AAAAAAIACKH0AAAAAAAAKoPQBAAAAAAAogNIHAAAAAACgAEofAAAAAACAAih9AAAAAAAACqD0AQAAAAAAKIDSBwAAAAAAoABKHwAAAAAAgAJUr+iGEyZMyO23355Zs2Zl4403zqBBg7L11lu/5/ZvvfVWrrrqqjz22GNpbGzMdtttlzPPPDPrrrvuhzJxAAAAAACAD8PSpUtz44035pFHHkltbW222GKLDBw4MJtttlmSZNGiRbn55pvzX//1X3nzzTfTs2fPHHvssfniF7/YfIx58+Zl9OjReeyxx7JkyZJsu+22OfPMM9OjR4/mbWbOnJmrrroqTz75ZCorK7Pzzjtn4MCBWXXVVd91Xg8++GAuvvjiTJgwIeuss06L17FCd/o8+OCDGTZsWPbZZ58MGzYsnTt3zsCBAzNt2rR33b6+vj6nnXZann322XznO9/Jd7/73UydOjWDBg3K0qVLV+SUAAAAAAAAH4uRI0fmnnvuyTHHHJPhw4enffv2OeWUUzJ9+vQkyeWXX5777rsvRxxxRIYPH55tt902F1xwQf7zP/+z+RgXXnhhfv/73+fUU0/N4MGDM3PmzAwYMCALFixI8nZ3cuaZZ+Zvf/tbzjvvvJxzzjn585//nLPPPjsNDQ3LzemNN97IVVdd9YGuo8U7fZqamjJ27NgcdNBBOfHEE5MkO++8c/r165fx48fn7LPPXm6fhx56KJMnT869996btdZaK0myzjrrZNCgQXnppZfSp0+fDzRJAAAAAACAj8L8+fMzYcKEnHrqqenXr1+SZJtttskXv/jFPPzwwzn44IPz0EMP5YILLsiBBx6YJNlpp50ybdq03HnnnfniF7+YOXPm5PHHH8+FF16Yr3zlK0mSXr165bDDDsvEiROz99575/nnn89LL72Ua6+9NjvuuGOSpKamJmeccUb+9re/ZfPNN19mXu+UT/PmzVvha2nxTp8pU6Zk+vTp2XPPPZvHqqur07dv30ycOPFd9/ntb3+bXXfdtbnwSZJNNtkkDz/8sMIHAAAAAABYabRv3z633HJL9t9//+ax6urqVFRUZOnSpVm4cGEOOeSQ7LLLLsvs16tXr7z++utJkiVLliR5u8R5R9euXZOkubRZkW3e8atf/SpPPfVUTjjhhA90LS2WPpMnT06S5d7F06NHj0ybNu1dbzl66aWXst5662Xs2LHZZ5990rdv35x55pmZMWPGB5ocAAAAAADAR6m6ujqbbrppunTpksbGxkybNi2XXHJJKioq8uUvfzk9evTIeeedl+7duzfv09DQkIkTJ6Z3795JkrXWWiu77757brnllrz22muZM2dORowYkZqamuy2225Jkq233jqbbrpprrvuusyYMSMzZszINddck+7du2fbbbdtPvbcuXMzfPjwfOtb30q3bt0+2LW0tEFdXV2SpGPHjsuMd+zYMY2NjVm4cGE6deq0zGe1tbX52c9+lrXXXjsXXnhhFi5cmGuuuSZnnnlmbr/99lRXt3haAAAAAACAj9VNN92UsWPHJklOPvnk5lLn/xozZkxee+21jBgxonnsrLPOymmnnZbDDz88SdKuXbuMGDGiuSyqrq7O+eefn0GDBuWAAw5IknTp0iXXX3992rdv33ycK6+8Mptuumn22Wef/Pa3v/1A81+hd/okSUVFxbt+Xlm5/M1C9fX1Wbp0aUaNGpXOnTsnefvOoOOOOy6/+c1v8sUvfvE9zzdlypQsWrRohSb/oXuidU7bal5s7Ql8zORbtk9bvomMSyff8sm4bPItn4zLJt+yfdryTWRcOvmWT8Zlk+/HYuONN17hbffaa6985jOfyf/8z//kxhtvzNKlS/PNb35zmW1uvfXW3HLLLfn617+ePfbYI0kya9as9O/fP6usskqGDRuWmpqaTJgwIeeee26uvvrqbLXVVnnhhRdyyimnZNNNN80xxxyTioqK3HHHHTnjjDNyww03pGfPnpk4cWIeffTRjB8//l+61hZLn3fu4lmwYEFWW2215vEFCxakqqpquTuAkqRDhw7ZcsstmwufJNl8883TuXPnvPzyy+9b+vTs2fMDXcCHqWu3rq127tYwt3Zua0/hYyXfsn3a8k1kXDr5lk/GZZNv+WRcNvmW7dOWbyLj0sm3fDIum3xXPu8URNtvv30WLFiQO+64IyeccEKqq6vT1NSUq666KuPHj0+/fv1yxhlnNO/3s5/9LPPmzcttt92WNddcM0my0047pX///hk9enTGjBmTe+65Jx06dMhVV13V3K3ssMMOOfzww3PjjTfm29/+doYOHZoTTzwxa6yxRurr65tvzGlsbExjY+O73ojzz1p8p887Jcy0adOWGZ82bVp69er1rvusu+66Wbp06XLjDQ0N73nHEAAAAAAAwMftjTfeyM9+9rPm1928Y9NNN82SJUtSW1ubxsbGfO9738v48eNz3HHH5dvf/vYyfcesWbPSvXv35sInefsJattss01effXVJMnMmTOzwQYbLHMzTbt27dKnT5+8+uqref755zNjxoyMGjUqu+22W3bbbbece+65SZJDDjkkl1xySYvX0uKdPr169Ur37t3z6KOPZpdddkny9uPbHnvssfTt2/dd99lll10yfvz4zJ49O2ussUaS5H//93+zYMGCbL311i1OCgAAAAAA4OMwf/785kJl//33bx5//PHHs+qqq2bVVVfNVVddlUceeSQDBw7M17/+9eWO0atXrzzwwAOZOXNm8zt8kuSZZ57JOuus07zNf/7nf2bBggXNxc/SpUvzt7/9LZtuumk222yzjBs3bpnjPvXUUxk1alRGjBiRDTfcsMVrabH0qaioyLHHHpvhw4enc+fO2WabbXLvvfdm7ty5OfLII5MkU6dOzVtvvZWtttoqSfK1r30tDzzwQAYOHJiTTjopixYtyujRo7P11ltn5513bnFSAAAAAAAAH4f11lsvn//85zNq1KgsXbo0PXr0yG9+85s88sgjueiii/LCCy/k7rvvzs4775ytt946f/nLX5r3raqqyuabb579998/48ePz6BBg9K/f//U1NTk4YcfztNPP53hw4cnebs7efjhhzNo0KAcddRRqaioyD333JPZs2fn0ksvTU1NTTbffPNl5jZr1qwkyYYbbthcHr2fFkufJOnXr18WL16cu+66K+PHj88mm2ySUaNGpUePHkmSm266KQ899FAmTZqUJFlllVVy44035qqrrsr3vve9VFdXZ4899si3vvWtFp83BwAAAAAA8HH63ve+l7Fjx+bWW2/NG2+8kfXXXz9Dhw7N3nvvnTFjxqSpqSl//OMf88c//nGZ/Tp06JBHH300Xbp0ydixYzNq1KhcdtllaWpqysYbb5xrr702O+ywQ5K3X40zZsyYXHPNNbnooovStm3b9OnTJzfffHM22WSTD+U6Kmpra5s+lCMVwEuzyibfsn3a8k1kXDr5lk/GZZNv+WRcNvmW7dOWbyLj0sm3fDIum3z5sLntBgAAAAAAoABKHwAAAAAAgAIofQAAAAAAAAqg9AEAAAAAACiA0gcAAAAAAKAASh8AAAAAAIACKH0AAAAAAAAKoPQBAAAAAAAogNIHAAAAAACgAEofAAAAAACAAih9AAAAAAAACqD0AQAAAAAAKIDSBwAAAAAAoABKHwAAAAAAgAIofQAAAAAAAAqg9AEAAAAAACiA0gcAAAAAAKAASh8AAAAAAIACKH0AAAAAAAAKoPQBAAAAAAAogNIHAAAAAACgAEofAAAAAACAAih9AAAAAAAACqD0AQAAAAAAKIDSBwAAAAAAoABKHwAAAAAAgAIofQAAAAAAAAqg9AEAAAAAACiA0gcAAAAAAKAASh8AAAAAAIACKH0AAAAAAAAKoPQBAAAAAAAogNIHAAAAAACgAEofAAAAAACAAih9AAAAAAAACqD0AQAAAAAAKIDSBwAAAAAAoABKHwAAAAAAgAIofQAAAAAAAAqg9AEAAAAAACiA0gcAAAAAAKAASh8AAAAAAIACKH0AAAAAAAAKoPQBAAAAAAAogNIHAAAAAACgAEofAAAAAACAAih9AAAAAAAACqD0AQAAAAAAKIDSBwAAAAAAoABKHwAAAAAAgAIofQAAAAAAAAqg9AEAAAAAACiA0gcAAAAAAKAASh8AAAAAAIACKH0AAAAAAAAKoPQBAAAAAAAogNIHAAAAAACgAEofAAAAAACAAih9AAAAAAAACqD0AQAAAAAAKIDSBwAAAAAAoABKHwAAAAAAgAIofQAAAAAAAAqg9AEAAAAAACiA0gcAAAAAAKAASh8AAAAAAIACKH0AAAAAAAAKoPQBAAAAAAAogNIHAAAAAACgAEofAAAAAACAAih9AAAAAAAACqD0AQAAAAAAKIDSBwAAAAAAoABKHwAAAAAAgAIofQAAAAAAAAqg9AEAAAAAACiA0gcAAAAAAKAASh8AAAAAAIACKH0AAAAAAAAKoPQBAAAAAAAogNIHAAAAAACgAEofAAAAAACAAih9AAAAAAAACqD0AQAAAAAAKIDSBwAAAAAAoABKHwAAAAAAgAIofQAAAAAAAAqg9AEAAAAAACiA0gcAAAAAAKAASh8AAAAAAIACKH0AAAAAAAAKoPQBAAAAAAAogNIHAAAAAACgAEofAAAAAACAAih9AAAAAAAACqD0AQAAAAAAKIDSBwAAAAAAoABKHwAAAAAAgAIofQAAAAAAAAqg9AEAAAAAACiA0gcAAAAAAKAASh8AAAAAAIACKH0AAAAAAAAKoPQBAAAAAAAowAqXPhMmTMihhx6aPfbYI8cff3yefvrpFT7J2LFjs9NOO/1LEwQAAAAAAPgoNTQ05M4778zhhx+ePffcM1/96ldzzz33pKmpablt77rrrhxxxBHLjU+ZMiVnn3129tprr3zpS1/KJZdcktra2mW2mTlzZi666KLsu+++2XvvvXPqqafm+eefX2abv/71rzn55JOz1157Zb/99suYMWNSX1+/QtexQqXPgw8+mGHDhmWfffbJsGHD0rlz5wwcODDTpk1rcd+XX34548aNW6HJAAAAAAAAfNxuuummXHfdddlnn31yxRVXZO+9987IkSNz++23L7Pdb37zm1x99dXL7V9bW5uTTz45L730Us4777xcdNFFeeWVVzJgwIAsXbo0SbJo0aKcfvrpeeGFF3LmmWfm4osvTkVFRU4++eTmvmXq1Kk57bTT0rFjxwwbNizf+MY3Mn78+IwaNWqFrqO6pQ2ampoyduzYHHTQQTnxxBOTJDvvvHP69euX8ePH5+yzz37PfRsaGnLJJZdklVVWyaxZs1ZoQgAAAAAAAB+XhoaGjB8/PkcddVSOP/74JMlOO+2U2tra3HnnnTnmmGNSV1eXm266KXfeeWc6d+683DEeeuihvPnmm7nrrruy/vrrJ0m22mqrHHTQQfnpT3+afv365b//+7/z2muv5cc//nF69uyZJPnMZz6TAw44ID/+8Y9zxhln5P7770+7du0ybNiwtGvXLkkyZ86c3HrrrRk4cGCqq9+/1mnxTp8pU6Zk+vTp2XPPPZvHqqur07dv30ycOPF99x0/fnwWLFiQww47rKXTAAAAAAAAfOzq6uqy77775nOf+9wy4717985bb72VhQsX5oEHHsjPf/7zXHzxxdljjz2WO8bkyZOz1lprNRc+SdKtW7f07t27uUvp3LlzjjjiiObCJ0nat2+f7t275/XXX0+SfP3rX8/VV1/dXPgkSZs2bdLQ0JDGxsYWr6XFO30mT56cJFl33XWXGe/Ro0emTZuWhoaGVFVVLbfflClTMmbMmFx99dV57rnnWpwIAAAAAADAx61Lly4555xzlhv//e9/nzXXXDMdOnTInnvumYMPPjjt27fP448/vty2a665Zmpra7No0aK0b98+SVJfX5+ZM2c2P95t5513zs4777zMftOmTcvLL7+cvn37JklWW221rLbaakmSBQsW5Mknn8ydd96Z/fbbL23btm3xWlq806euri5J0rFjx2XGO3bsmMbGxixcuHC5fZqamnLppZdm3333zbbbbtviJAAAAAAAAFYWEyZMyKRJk3L00UcneftGmHfKnHfzhS98IQ0NDfne976X6dOn54033sgPfvCDzJ8//117lCRZunRphgwZknbt2uWQQw5Z5rOGhobsvffeOeuss1JTU9P82LmWrNA7fZKkoqLiXT+vrFy+N7r//vszderUXHHFFSs0iX82ZcqULFq06APv96F4onVO22pebO0JfMzkW7ZPW76JjEsn3/LJuGzyLZ+Myybfsn3a8k1kXDr5lk/GZZPvx2LjjTf+QNv//Oc/z+WXX57Pf/7zOfzww1don969e+eSSy7J0KFDc+CBB6aysjL77rtv9thjj7z22mvLbb9kyZJ85zvfyZ/+9KcMHTo0a6655jKfNzY25qqrrsrChQtz88035xvf+EZuu+225bb7v1osfTp16pTk7duI3rml6J0/V1VVLXcH0MyZM3PNNdfkoosuSvv27VNfX9/8nLn6+vpUVla+a1H0jn9+lt3HrWu3rq127tYwt3Zua0/hYyXfsn3a8k1kXDr5lk/GZZNv+WRcNvmW7dOWbyLj0sm3fDIum3xXPnfeeWeuvvrq7LHHHrnkkkve84aYd/O5z30ue+65Z6ZOnZouXbpklVVWySmnnJIuXboss938+fNz9tln589//nMGDx6cvfbaa7ljtWnTpvlRcNtss00OOOCAPPDAAznhhBPedw4tlj7vlDDTpk1bppCZNm1aevXqtdz2TzzxROrq6nLeeect99luu+2WE044ISeddFJLpwUAAAAAAPjY/PCHP8y4ceOy77775sILL0x1dYsVSrPp06fniSeeyAEHHJDevXsneftunZdffjn/8R//0bxdbW1tBgwYkClTpuTyyy/PnnvuucxxJk2alIqKiuy4447NY6usskrWWGONzJ49u8V5tDjjXr16pXv37nn00Uezyy67JHn7jp3HHnus+cVC/2z33XfPuHHjlhn75S9/mR/96EcZN25c1lhjjRYnBQAAAAAA8HG56667Mm7cuBxxxBE588wzP9AdPkkye/bsDBkyJJtsskk222yzJMl//dd/pba2NrvvvnuSt7uVM888M6+//npGjRqV7bfffrnj/PSnP81zzz2Xe+65p7l0mjx5cqZPn56NNtqoxXm0WPpUVFTk2GOPzfDhw9O5c+dss802uffeezN37twceeSRSZKpU6fmrbfeylZbbZVu3bqlW7duyxzjz3/+c5Jk8803b3FCAAAAAAAAH5c33ngj11xzTTbaaKN88YtfzDPPPLPM53369Gnxrp8tttgim266aYYMGZIBAwZk9uzZufLKK7Pbbrs1P6btnnvuyV//+tccc8wxadOmTf7yl78079+lS5f07t07Rx11VE444YR85zvfySGHHJI333wzY8aMSc+ePbP//vu3eC0rdG9Sv379snjx4tx1110ZP358Ntlkk4waNSo9evRIktx000156KGHMmnSpBU5HAAAAAAAwErh8ccfz5IlS/LSSy+lf//+y33+y1/+crmbXf6vqqqqDB8+PFdccUUuuOCCdOzYMQcddFBOOeWU5m1+97vfJUluu+223Hbbbcvs37dv34wcOTJ9+vTJtddemx/+8Ic577zz0rZt2+yxxx45/fTT0759+xavpaK2trZpBa75U8FLs8om37J92vJNZFw6+ZZPxmWTb/lkXDb5lu3Tlm8i49LJt3wyLpt8+bBVtvYEAAAAAAAA+PcpfQAAAAAAAAqg9AEAAAAAACiA0gcAAAAAAKAASh8AAAAAAIACKH0AAAAAAAAKoPQBAAAAAAAogNIHAAAAAACgAEofAAAAAACAAih9AAAAAAAACqD0AQAAAAAAKIDSBwAAAAAAoABKHwAAAAAAgAIofQAAAAAAAAqg9AEAAAAAACiA0gcAAAAAAKAASh8AAAAAAIACKH0AAAAAAAAKoPQBAAAAAAAogNIHAAAAAACgAEofAAAAAACAAih9AAAAAAAACqD0AQAAAAAAKIDSBwAAAAAAoABKHwAAAAAAgAIofQAAAAAAAAqg9AEAAAAAACiA0gcAAAAAAKAASh8AAAAAAIACKH0AAAAAAAAKoPQBAAAAAAAogNIHAAAAAACgAEofAAAAAACAAih9AAAAAAAACqD0AQAAAAAAKIDSBwAAAAAAoABKHwAAAAAAgAIofQAAAAAAAAqg9AEAAAAAACiA0gcAAAAAAKAASh8AAAAAAIACKH0AAAAAAAAKoPQBAAAAAAAogNIHAAAAAACgAEofAAAAAACAAih9AAAAAAAACqD0AQAAAAAAKIDSBwAAAAAAoABKHwAAAAAAgAIofQAAAAAAAAqg9AEAAAAAACiA0gcAAAAAAKAASh8AAAAAAIACKH0AAAAAAAAKoPQBAAAAAAAogNIHAAAAAACgAEofAAAAAACAAih9AAAAAAAACqD0AQAAAAAAKIDSBwAAAAAAoABKHwAAAAAAgAIofQAAAAAAAAqg9AEAAAAAACiA0gcAAAAAAKAASh8AAAAAAIACKH0AAAAAAAAKoPQBAAAAAAAogNIHAAAAAACgAEofAAAAAACAAih9AAAAAAAACqD0AQAAAAAAKIDSBwAAAAAAoABKHwAAAAAAgAIofQAAAAAAAAqg9AEAAAAAACiA0gcAAAAAAKAASh8AAAAAAIACKH0AAAAAAAAKoPQBAAAAAAAogNIHAAAAAACgAEofAAAAAACAAih9AAAAAAAACqD0AQAAAAAAKIDSBwAAAAAAoABKHwAAAAAAgAIofQAAAAAAAAqg9AEAAAAAACiA0gcAAAAAAKAASh8AAAAAAIACKH0AAAAAAAAKoPQBAAAAAAAogNIHAAAAAACgAEofAAAAAACAAih9AAAAAAAACqD0AQAAAAAAKIDSBwAAAAAAoABKHwAAAAAAgAIofQAAAAAAAAqg9AEAAAAAACiA0gcAAAAAAKAASh8AAAAAAIACKH0AAAAAAAAKoPQBAAAAAAAogNIHAAAAAACgACtc+kyYMCGHHnpo9thjjxx//PF5+umn33f7p59+Oqeccko+//nPZ999983gwYPz5ptv/tsTBgAAAAAA+Kj87ne/y1577bXMWFNTU26++ebsv//+2WOPPXLaaafltddeW2abKVOm5Oyzz85ee+2VL33pS7nkkktSW1u7zDb19fUZM2ZM83GOO+64TJo06V3nUV9fn+OOOy533HHHCs99hUqfBx98MMOGDcs+++yTYcOGpXPnzhk4cGCmTZv2rtu/+uqrOfXUU9OxY8cMGTIkZ5xxRp5++umcccYZqa+vX+HJAQAAAAAAfFyefvrpDB48OE1NTcuM33jjjbnlllty1FFH5dJLL838+fNz6qmnZv78+UmS2tranHzyyXnppZdy3nnn5aKLLsorr7ySAQMGZOnSpc3HGTFiRH70ox/l2GOPzfDhw7PGGmvkrLPOWq5Aqq+vz/e+9708++yzH2j+1S1t0NTUlLFjx+aggw7KiSeemCTZeeed069fv4wfPz5nn332cvvce++9WW211XL55ZenuvrtU/Tq1SvHHXdc/vjHP6Zv374faJIAAAAAAAAflSVLluSuu+7KDTfckA4dOqSxsbH5s7q6utx555054YQT8tWvfjVJsu222+bAAw/MT3/603z961/PQw89lDfffDN33XVX1l9//STJVlttlYMOOig//elP069fv0yePDn3339/Lrvssuy9995Jks985jP5+te/nieeeCLrrbdekuSFF17IsGHDMnny5A98HS3e6TNlypRMnz49e+65Z/NYdXV1+vbtm4kTJ77rPhtssEG+/vWvNxc+ydulT5K8/vrrH3iSAAAAAAAAH5U//OEPufXWW3PGGWfk8MMPX+azZ555JgsWLFimJ+nSpUu22267PP7440mSyZMnZ6211moufJKkW7du6d27d3OX8rvf/S5dunTJ5z//+eZt2rRpk3vuuSeHHXZY89j3v//9dOjQIePGjfvA19HinT7vNEnrrrvuMuM9evTItGnT0tDQkKqqqmU+69ev33LH+e///u8kSe/evT/wJAEAAAAAAD4qm2++eSZMmJDOnTtnzJgxy3z2fj3J7373uyTJmmuumdra2ixatCjt27dP8vYj2mbOnNn8eLcXX3wx6623Xn7961/nhhtuyJQpU7LBBhvkrLPOyvbbb9983Isvvjgbbrjhv3QdLZY+dXV1SZKOHTsuM96xY8c0NjZm4cKF6dSp0/seY+bMmRk1alT69OmTHXfc8X23nTJlShYtWtTStD4aT7TOaVvNi609gY+ZfMv2acs3kXHp5Fs+GZdNvuWTcdnkW7ZPW76JjEsn3/LJuGzy/VhsvPHGLW6z5pprvudndXV1adu2bdq0abPMeMeOHZs7lC984Qu55ZZb8r3vfS8DBw5MmzZtMmbMmMyfPz8dOnRI8vZ7f6ZMmZKRI0fmlFNOyaqrrpo777wzAwcOzN1335111lknSf7lwidZwXf6JElFRcW7fl5Z+f5PiJs5c2YGDBiQpqamXHrppe95nHf07NmzpSl9ZLp269pq524Nc2vntvYUPlbyLdunLd9ExqWTb/lkXDb5lk/GZZNv2T5t+SYyLp18yyfjssn3k6Gpqek9u413xnv37p1LLrkkQ4cOzYEHHpjKysrsu+++2WOPPfLaa68lefvOnzlz5uT6669vvrNn2223zcEHH5zbb78955577r891xZLn3fu4lmwYEFWW2215vEFCxakqqpquTuA/tnLL7+cgQMHpr6+PqNHj17u1icAAAAAAICVWadOnbJkyZLU19enuvr/1yoLFixY5klon/vc57Lnnntm6tSp6dKlS1ZZZZWccsop6dKlS5KkQ4cOad++fbbbbrvmfTp06JCtttoqL7300ocy1/e/TSf//86badOmLTM+bdq09OrV6z33e+aZZ3LSSSelqqoqY8aMWaHbpwAAAAAAAFYmPXv2TFNT07v2JL17906STJ8+PQ888ECqqqrSu3fvrLLKKmlsbMzLL7+cTTbZpPk4jY2NaWhoWOY49fX1LT4lbUW1WPr06tUr3bt3z6OPPrrMBB577LHssMMO77rPtGnTMmjQoKy22mq58cYb37ccAgAAAAAAWFltvfXWadeu3TI9ybx58/LUU09lxx13TJLMnj07Q4YMyfPPP9+8zX/913+ltrY2u+++e5Jk5513zpIlS/L73/++eZt//OMf+ctf/pKtt976Q5lri493q6ioyLHHHpvhw4enc+fO2WabbXLvvfdm7ty5OfLII5MkU6dOzVtvvZWtttoqSTJy5MjU1dXlnHPOyYwZMzJjxozm46299tpZffXVP5TJAwAAAAAAfJQ6duyYww47LDfccEMqKyvTq1ev3HLLLampqcmBBx6YJNliiy2y6aabZsiQIRkwYEBmz56dK6+8Mrvttlt23nnnJG+XPjvuuGMuvfTSzJ07N2ussUbGjRuXJDniiCM+lLm2WPokSb9+/bJ48eLcddddGT9+fDbZZJOMGjUqPXr0SJLcdNNNeeihhzJp0qTmu4AaGhpy0UUXLXesM844I0cdddSHMnkAAAAAAICP2oABA1JZWZk77rgjCxcuzNZbb53Bgwc3v9Onqqoqw4cPzxVXXJELLrggHTt2zEEHHZRTTjml+RgVFRUZPnx4rr322lx//fVZsGBBttpqq9xwww0f2s0yFbW1tU0fypEK0LVb19aewsdqbu3c1p7Cx0q+Zfu05ZvIuHTyLZ+Myybf8sm4bPIt26ct30TGpZNv+WRcNvnyYWvxnT4AAAAAAACs/JQ+AAAAAAAABVD6AAAAAAAAFEDpAwAAAAAAUAClDwAAAAAAQAGUPgAAAAAAAAVQ+gAAAAAAABRA6QMAAAAAAFAApQ8AAAAAAEABlD4AAAAAAAAFUPoAAAAAAAAUQOkDAAAAAABQAKUPAAAAAABAAZQ+AAAAAAAABVD6AAAAAAAAFEDpAwAAAAAAUAClDwAAAAAAQAGUPgAAAAAAAAVQ+gAAAAAAABRA6QMAAAAAAFAApQ8AAAAAAEABlD4AAAAAAAAFUPoAAAAAAAAUQOkDAAAAAABQAKUPAAAAAABAAZQ+AAAAAAAABVD6AAAAAAAAFEDpAwAAAAAAUAClDwAAAAAAQAGUPgAAAAAAAAVQ+gAAAAAAABRA6QMAAAAAAFAApQ8AAAAAAEABlD4AAAAAAAAFUPoAAAAAAAAUQOkDAAAAAABQAKUPAAAAAABAAZQ+AAAAAAAABVD6AAAAAAAAFEDpAwAAAAAAUAClDwAAAAAAQAGUPgAAAAAAAAVQ+gAAAAAAABRA6QMAAAAAAFAApQ8AAAAAAEABlD4AAAAAAAAFUPoAAAAAAAAUQOkDAAAAAABQAKUPAAAAAABAAZQ+AAAAAAAABVD6AAAAAAAAFEDpAwAAAAAAUAClDwAAAAAAQAGUPgAAAAAAAAVQ+gAAAAAAABRA6QMAAAAAAFAApQ8AAAAAAEABlD4AAAAAAAAFUPoAAAAAAAAUQOkDAAAAAABQAKUPAAAAAABAAZQ+AAAAAAAABVD6AAAAAAAAFEDpAwAAAAAAUAClDwAAAAAAQAGUPgAAAAAAAAVQ+gAAAAAAABRA6QMAAAAAAFAApQ8AAAAAAEABlD4AAAAAAAAFUPoAAAAAAAAUQOkDAAAAAABQAKUPAAAAAABAAZQ+AAAAAAAABVD6AAAAAAAAFEDpAwAAAAAAUAClDwAAAAAAQAGUPgAAAAAAAAVQ+gAAAAAAABRA6QMAAAAAAFAApQ8AAAAAAEABlD4AAAAAAAAFUPoAAAAAAAAUQOkDAAAAAABQAKUPAAAAAABAAZQ+AAAAAAAABVD6AAAAAAAAFEDpAwAAAAAAUAClDwAAAAAAQAGUPgAAAAAAAAVQ+gAAAAAAABRA6QMAAAAAAFAApQ8AAAAAAEABlD4AAAAAAAAFUPoAAAAAAAAUQOkDAAAAAABQAKUPAAAAAABAAZQ+AAAAAAAABVD6AAAAAAAAFEDpAwAAAAAAUAClDwAAAAAAQAGUPgAAAAAAAAVQ+gAAAAAAABRghUufCRMm5NBDD80ee+yR448/Pk8//fT7bv/yyy9nwIAB+exnP5v9998/t956a5qamv7tCQMAAAAAAHzYPmgPsjJaodLnwQcfzLBhw7LPPvtk2LBh6dy5cwYOHJhp06a96/Zz5szJqaeemoqKilx22WU56KCDcv311+fOO+/8UCcPAAAAAADw7/qgPcjKqsXSp6mpKWPHjs1BBx2UE088MX379s2IESPStWvXjB8//l33ue+++9LQ0JARI0akb9++6d+/f4499tiMGzcu9fX1H/pFAAAAAAAA/Cv+lR5kZdVi6TNlypRMnz49e+65Z/NYdXV1+vbtm4kTJ77rPpMmTcqOO+6Y9u3bN4999rOfzbx58/Lss89+CNMGAAAAAAD49/0rPcjKqsXSZ/LkyUmSddddd5nxHj16ZNq0aWloaHjXfd5t+38+HgAAAAAAQGv7V3qQlVWLpU9dXV2SpGPHjsuMd+zYMY2NjVm4cOG77lNTU7Pc9v98PAAAAAAAgNb2r/QgK6vqljZoampKklRUVLzr55WVy/dG7+zzbt7rOCuDubVzW3sKfITkWzb5lk/GZZNv+WRcNvmWT8Zlk2/5ZFw2+ZZPxmWT78rhX+lBVlYtzrRTp05JkgULFiwzvmDBglRVVS3XfL2zz7tt/8/HAwAAAAAAaG3/Sg+ysmqx9OnZs2eSZNq0acuMT5s2Lb169XrPfd5t+yTp3bv3vzRRAAAAAACAD9u/0oOsrFosfXr16pXu3bvn0UcfbR6rr6/PY489lh122OFd99lxxx3zxBNPLPOcu0cffTRdu3bNJpts8iFMGwAAAAAA4N/3r/QgK6sW3+lTUVGRY489NsOHD0/nzp2zzTbb5N57783cuXNz5JFHJkmmTp2at956K1tttVWSpF+/frnnnnsyaNCgHHXUUXnxxRdz66235tRTT02bNm0+2isCAAAAAABYQSvSg3xSVNTW1jatyIZ33nln7rrrrtTW1maTTTbJwIEDs/XWWydJvv/97+ehhx7KpEmTmrd/9tlnc+WVV+b555/PqquumkMPPTTHHnvsR3MVAAAAAAAA/4b360E+KVa49AEAAAAAAGDl1eI7fQAAAAAAAFj5KX0+ZPX19a09BQAAAABYYU1NHgQEn3RLlixp7SmwklD6fIieffbZjBkzJjNnzmztqfARmDVrVv72t78p9gBWcv/3/6f9BbYcU6dObe0pAAAUqaKiYpk/NzY2ttJMgH/FK6+8klNPPTUvv/xya0+FlYDS50M0ceLE3Hrrrbnvvvsya9as1p4OH7Lf/va3GTx4cGbOnJlFixblv//7v1t7SnwE/u8XWz8shk+WxsbGVFdXp66uLjfddFOS5f8CyyfTnDlzctJJJ+XUU09t7akA8B4aGhpaewrAv2Dy5Ml54IEHctNNN2XChAlJksrKSn8fhk+Q559/PrNmzcrQoUPz6quvtvZ0aGVKnw9R//79c8IJJ+S2227L3XffnRkzZrT2lPgQ9e3bN+3bt8+AAQNy6KGH5g9/+IPbJgtTX1+fysrK1NfXZ9asWVm8eLEfFhfGDyLK1tDQ0LyGTz/99Dz++OP5+9//3trT4kPStm3bHH744Xn55ZdzzjnntPZ0+Ij4reJPJ7mXoampKVVVVVm8eHFuv/321p4OH4H3WquKgU+2p59+Ot/85jdz11135d57780PfvCDnHbaaUn88lRJ3uvvwv4bXI599903J598chYtWpTvfe97ee2111p7SrSiitraWv91/hAsXrw47dq1S5KMHj069913X4444ogccsgh6d69eyvPjg/Ls88+m2984xtp27ZtfvCDH2TXXXdt7SnxIWlsbExlZWXq6ury7W9/O6+//noaGxtzyimnZPfdd8//Y+++46o60sePf26hCUgXBAsq2Ess0dh7rFEssYAKgiA2FAuKiohgF7C3qLH33mLsLdaYxN5iLzQpUi9wy+8Pf/csGHeT7O43XLLz/mcj3Ht2zmuYOXPmmXnGwsKiqIso/Ic0Gg0KhQKAo0ePkpaWRqVKlWjUqFERl0z4b8rNzWX9+vXcvXuXoKAg3NzcirpIwn+BTqdDJpORmZnJwYMHWbduHXXr1mX+/PlFXTThv0itVqNUKsnLy+OXX35BrVZTsWJFnJycirpown+RSqXi559/Jjk5GQcHBxo0aCA9n4XiS99+NRoNu3btYt26dfTs2ZPAwMCiLprwX6Kv49zcXH799VfevXtHmTJlKF++PEqlUnpWC8VLQkICw4cP54svvsDT0xMLCwuuX7/OjBkzGDhwIP7+/kVdROG/QN9+VSoVt2/fJiEhgfLly1O+fHlKliwpzYcIxVdeXh7GxsYAbNiwgb1792JnZ8f06dMpV65cEZdOKArKoi7A34FWq8XExIT09HRmzJiBubk5KpWKLVu2oFar6dOnjwj8/E0kJCTQoEEDUlNTmTNnDnPmzKFatWpFXSzhP6QPBuTn5+Pv70+JEiVo3749jx49YubMmYwaNYrOnTuLwE8xpl95CjBx4kSuXbuGTCYjKyuLQYMG4ePjg7m5eRGXUvhvOHDgAHv27EGn02Fqagr84yVHKL5kMhk6nQ4LCwu6desGwNq1a5kwYYII/PxNFEzNOGrUKJKSksjNzSUgIICvvvpKWlwlFG9ZWVn4+/uTn59PXFwcVlZWWFlZMXXqVKpWrSomnIopjUYjtd9Fixbx4MEDMjIy2LBhA1qtluHDhxd1EYX/UME+OjAwkKysLN68eYOTkxPOzs7MmjULGxuboi6m8G94/vw5+fn5dO3aFRcXFwBatGhB9erVefPmTRGXTvhvKNh+/f39UalUJCQkYGtri4WFBTNmzMDd3b2oiyn8B7RaLcbGxqSnpzNlyhRyc3NRqVTcvXuX8PBwwsLCqFixYlEXU/iLiVH1f0in0yGXy8nPz2fs2LFkZmbSrl07li9fTq9evdixYwe7d+8mISGhqIsq/Bs+Pgy8devWREdHM2vWLKytrZk0aRL37t0rotIJ/y36NBRxcXGUL1+e6dOnM3z4cBYuXEjHjh1ZtGgRR44cITMzs6iLKvwbtFqttOrw8uXLPH36lIULF7J69WpGjx7Npk2bWLt2rajfYurjdCKNGjXCw8ODzMxMNmzYACCtPBaKJ33d6duxPvAzZMgQfvzxR5Hq7W9CLpeTm5vLsGHDMDU1Zfbs2cyYMUMK+KhUqqIuovAfUqvVTJ48GQsLCyIiIti/fz8LFy4kMTGRyMhIUlJSAJEmqjjSj6UDAwN59eoV3bp1Izo6ms8++4yTJ0+yaNGioi6i8B/Sz3mMHz8eCwsLpk6dyoEDBwgODuaXX35h9OjRZGVlAaINFzd5eXmkpqZKcx9qtRpjY2Ps7OxITU0FRPqv4k6f/nry5MlYWVkRERHB999/T2RkJElJSYwdO5a0tDRA1HVxpa/jsLAwVCoVgYGB7N27lzFjxqBUKomIiODp06dFXUzhLyaWvf4b7t+/z4MHD+jRo4c0AREfH098fDzjxo2jefPmANSvXx8HBwdWrVqFVqsVO36KGf2KtZycHNavX8+7d+9o3LgxjRo1wtXVlenTpzN9+nRCQ0OZP38+lStXLrSdUig+tFotkZGRnDp1Cmdn50I7eqZMmYJMJmPx4sUAdOnSRez4KWb0q4bXr1/Ps2fPqFmzJjVr1kShUFCxYkUUCgWxsbEA+Pr6ivotRvQ7ePTpRNRqNeXLl8fLywu1Ws2WLVuwsLBg9OjRKBSKQin+hOKhYCqKy5cvEx8fT/ny5XFzc6N///7I5XJWrlwpdvz8Tdy+fRu1Wk1oaChly5YlPz+fc+fOsW/fPjIzM+nfvz8dO3YUKYSKqeTkZN68ecOgQYOoXr06AD/++CPZ2dn07duXJ0+eYGxsTMmSJYu4pMK/Q5+yb8KECdSuXRuAqlWrsm7dOs6dO4eRkZHY8VPMvXnzhri4OEaNGkXdunWRyWT89NNPyGQyevbsyYMHD6hduzZGRkZFXVThT3ByckKr1XLnzh2qV68u7Y43MTHh5cuXAGIXZjFVcLyUmJjIq1ev8PHxoVatWsCHecycnBxGjBjBgwcPqFKlitixV4y9f/+eV69e0b9/f+rVqwdA//79KVOmDBs3biQyMpKIiAiR6u1/iAj6/Ak6nY7c3FyWLVsmNSC9d+/ekZSUJAV19Gf8DBgwgJSUFHbs2IGxsTFdunShTJkyRVF84U9SKBRkZ2czaNAgVCoVcrmcw4cP07NnTwYPHkyFChWIiIhg+vTpjBs3Dm9vb65evUqnTp1o06ZNURdf+BO0Wi1t27YlOTmZJ0+ekJaWhrW1tTTZOHnyZGQyGUuXLiUnJ4e+fftiZmZW1MUW/oSnT59y/fp17t27x5dfflkoANCnTx8AYmNjUSgUDBo0CEtLyyIusfB79IH57OxsFixYQHx8PMnJybRt25b27dtLE0s7d+4EEIGfYkin00mpKIYMGUJ2djb5+fmkp6dTtWpVevXqRd++fdFqtaxZs4aQkBDmzZtX1MUW/oSP22Nubi5Pnjzh3bt3PHz4kEOHDnHlyhXc3NwwNTUlIiKC0qVLU6dOnSIstfDvys3NJS0tTZqA+v777wkPD2f48OG0atVKSvE2cuRIEdgrhtLT08nKysLOzg6A/Px8bG1t8fX15enTp2zatAmZTMawYcOKuKTCvysrK4uUlBRKlCiBTCbj2LFjRERESOfBRERE0KZNG77++mvRhosJnU6Hu7s7kZGRmJmZoVAopLpzcXHh5s2bJCcnS+1aKD70cxn5+fkYGRmh0+lITU2lRIkSAHz33XdMnz6dYcOG0bx5cyIiIqhTpw5+fn4Aov0WQ/n5+eTm5hbatadUKmnevDlxcXFER0cTGRlJSEiISOf3P0KE6/8EmUyGqakp4eHh+Pr6olKpOH36NAB169alfPnyfPPNN+Tl5WFiYkJubi4ArVq1Ij8/n3Xr1nHt2rWivAXhD9BvZ9XpdFy6dAlHR0dWrVrF9u3bCQ0NZe/evaxdu5aEhARcXV2JjIzE2dmZpUuXkpycTIsWLYr4DoTf83GaJ6VSSYsWLRg8eDDm5uZMnDiRlJQUlEql9MAMDQ2lWbNmXLlyRTonRDBcH29Lr1ixIt7e3tSsWZODBw/y008/oVAopNRvffv2Zdy4cWzcuJFt27aJtBQGTF83CoWCnJwcvL29ef78OW5ubtSpU4czZ84QFBTEvXv3GDRoEH379mXXrl3Sbj0R8Ck+9Lu3wsPDsba2Zt68eRw9epRNmzaRmprK/PnzeffuHT169MDf35+ff/6ZgICAoi628Afpz1rLzc1lz549qFQq6tSpQ4MGDQgMDGTatGk8f/6cqKgoVq9eTXh4OHZ2drx69aqoiy78CSqVihcvXgBgaWmJubk5N2/e5OjRo0ybNo1hw4bh7e2NUqkkLi5OGneJySbD9qn0P+XLlycvL4/r168DYGRkJAV+vLy80Gq1nDp1inXr1v3VxRX+DZ9Ki+vo6IiJiQm3b9/mwoULhIeHExgYiLe3N6ampjx58oSMjAxAtGFDp2/D+npq06YNjRs3LvSZjh078vr1aw4cOPCXl0/4z+jP8MnOzmbAgAHs3r0bOzs7rK2tuXTpEmfOnGH69OkEBgbi4+ODhYUFL1++JDs7G5lMJtpvMfCpPtrJyYkyZcpw8OBBMjIyCs1ndenSBQcHB16/fs327dv/6uIKRUTs9Pk3ODg4oNPpiI2N5cyZM6SlpdGzZ088PDzYvn07S5cuZeTIkdKBsxkZGbRv357PPvuM7t27F3Hphd8jl8vJy8tj4sSJALi5uUkHGnp4eAAwe/Zs4EMqqLJly7JixQru3LlDzZo1kcvlYiW5AdPXjUql4tChQ7x8+RJbW1uqVq1K48aNCQsLk1asLV++HFtbW2mFxOzZs6UggVi9ZrgKtr/09HRSU1MpX748DRs2xMbGhnnz5jFu3Diio6OpV68eWq0WuVzO119/jZGREXXq1BF1a4D0O2hlMplUZzt37kShUDBjxgxcXFyQyWRER0ezc+dOkpOTqVq1KoMHD0Yul7Nx40acnJyknV1C8ZCXl8fLly/p1q0bbm5uALx+/Zo3b94QFhbG48ePcXZ2xsPDg6ysLG7duiX9fQiGS/9c1Wq1bNiwgcOHD5OVlcWAAQOYPn06169fx9LSEnd3d5ycnNDpdMTHx6NUKjE3Ny/q4gt/kEaj4ZtvvuHgwYOsXLmSSpUqERAQwJw5czh06BBBQUF4eXkBH9LOGBkZSWNuMc4yXPr2m5eXx+PHj7G2tsbKyooqVarQsWNHli9fjp2dHc2bN5fSfMXFxVGrVi2sra05efIknTt3xsnJqYjvRPhn9GPpnJwc9u7dK6VWbdWqFYMGDWL58uVotVomTpxIz549AUhISMDKyorSpUsXcemF31OwDT969IgSJUrg7OyMqalpoeezi4sLS5cuJT4+nqSkJJRKpUj9VQzox8H5+fls376dUqVKUbduXUxNTfHz82PevHkcOXKECRMm0Lt3b+DD2NrU1FRkJSom9O00NzeXn3/+mZycHEqUKEGjRo0YO3Ys48aNY8qUKURGRmJlZQXAo0ePKFWqFH369OHLL78s4jsQ/ioi6PNvkslkeHh48PbtW3bs2EGJEiXo168fb9684cyZMzx9+pSBAweSkJDAvn37sLOzkzpUERAwfHFxcWi1Wq5evUqFChWAf3SsBQM/CoUCT09PypQpI+WuFvVruPSrirOzsxk8eDD5+fkYGxuTnJyMWq3Gw8OD0aNHEx4eTkREBCNGjGDZsmXY2tpK9SqXy8WEogHTarVS+5s7dy43b97k6dOnlCtXjubNm+Pv709oaChz5879ZOBH374Fw3Lv3j22bt3KoEGDqFy5stT+4uPjKVGiBE5OTshkMk6cOMHOnTsZO3YsRkZGfPPNNwQGBtKrVy8cHR1F/RYzWq2W1NRU3rx5g6OjIwqFgqNHjxIREUFAQAAtW7YkODiYhg0b4u/vT//+/fH19S0UGBQMjz41Y1ZWFitWrOD+/fskJCTw7bffAtCvXz86d+4MwLVr13j58iV5eXls2LABW1tbsaO6mMjJyWHr1q3cuXOH9PR0pk6dysyZM+nSpQvx8fGsX7+e58+fc/HiRTIyMti5cyfGxsbSBLII+Bgm/erxrKwsRo0axevXr1EoFDRt2pQRI0YwaNAg4uPjpQVUDRo0ICUlhSNHjvDFF1/w1Vdf0aNHD+7fvy+CPgaq4PuSr68vOp0OIyMjTp48SY0aNWjXrh1v377l4MGDJCUl8fDhQ+Lj49mwYQMWFhZiMtHAFWzDI0aM4PXr1yiVSmrXrs3UqVMpWbJkofmMBg0akJ6ezpQpU6hUqRLBwcFFfAfC79EHfGbOnMnPP/9M586dqVSpEgCNGjWiX79+7Ny5k3v37vHTTz+RkJDArl27MDExEYvUi4GCbTgwMJDMzEzS0tLIzc2lRYsWdO3aldGjRxMbG4u/vz9t27ZFqVRy9uxZSpYsyZdffinmtP6HyNLS0kQOm3+DfvXZr7/+SkxMDElJSQQEBNC2bVv27t3L/v37efz4MaVLl6ZcuXLExMQUOmxaMCyf6vAePXrE6tWruXr1KtHR0TRs2LDQ5w4cOMCsWbMYNWoUAwYMKIpiC3+Cvu1pNBpmzJhBcnIy48ePx9XVlTdv3nDgwAE2bdqEl5cXI0eO5Pr168ydO5eMjAx27dolDhUuZiIjI7lx4wY9evTA1dWVY8eOcffuXSpVqsTs2bN5/fo1CxYs4OnTp0RFRdGwYcOiLrLwL5w7d46QkBDatWuHr6+v9OIyd+5cLl26xIEDBzh//jwTJkxg2LBh+Pj4sGPHDlavXs3GjRullePwjwC+YHj+2aKJ4cOHk5eXR+fOnZk3bx5Dhw5l8ODBAHh5eVGjRg0mT54sfV6MtQyfSqViyJAhWFpa0qJFCxwdHdm8eTMpKSl89dVXDBgwgKysLKZOncqNGzcoW7YspUqVYvHixSiVSrHAxsDl5OQwYMAA7OzscHV1JScnh6tXr2Jtbc3cuXOpUKEChw8fZuXKlajVaqysrChbtixz5swR9Wtg9P2pTqeTFtao1WqCg4PJy8ujR48e/Pzzz1y9epWqVasyefJk3r9/z+bNmzl06BDGxsYYGRlRtmxZli9fTmJiIsHBwURERFCzZs2ivj3hI/r61mq1zJo1ixcvXjB9+nRcXFxIT0+X3ocePXrE1atX2bBhA1qtFmtra8qUKSPNeYg2bJj0cxlqtZqQkBBycnLo2bMn9+7d4/z58zg4ODB37lysrKwKjZczMjI4ceIE3bp1E2PoYuL169esW7eOM2fO0Lx5c2bMmCH9LikpiUuXLrFu3TqysrKwtrbG1dVVPIMNXMH3G7VazahRo9DpdAQFBWFhYUFeXh5eXl40bdqUMWPGkJ+fz9KlS3n16hUmJia4uroSEREh7eQTAZ//DSLo8x/QN7rHjx8TGxtLUlISvr6+dOrUCYDHjx9ja2uLjY2N9HAVD0nDU/CAu/j4eN69e4e7uzsWFhbExcUxc+ZMbt26RUxMDA0aNCjUQV64cIHGjRuLejVQ9+7d49y5cwQGBkoPSI1Gg7e3N61bt5ZWhAOkpKSwbds29u3bx6xZs2jQoAEXL17k2LFjREZGioGPgcrLy+P9+/c4ODhIP/v1118JCQlh5MiRtGzZEoVCQV5eHnv27GHXrl00atSIkJAQbt++zYIFC0hLS2Pnzp1S6jDBsOiftWfPnmXixIm0bt0aHx8fqlatyo8//sjUqVNxdXXl559/JigoiL59+6JUKtmyZQtHjhxh2bJlIhVFMVAwTcG1a9dQKpXUrFkTS0tLqR6Tk5Px8fFh2LBhaLVaXr58ybhx4+jTpw99+/Yt6lsQ/oTLly8TGRnJvHnzpIlflUrF7NmzuX37Nt27d2fQoEFkZWXx8OFDSpQoQZUqVcR4upjYsGEDR48eJSYmRgq6nzlzhq1bt5Kens7s2bOpWLEiycnJZGZmYmJigqOjo3SOl6hfw5GSkoKtra3079zcXB49esTatWvx9fWVMh1s2LCBQ4cOUalSJSZOnIitrS2PHz8mPj4eExMTGjZsiE6nY+bMmdy8eZMVK1Zgb29fVLclFHD37l327t1LWFhYoZ/7+fnh5uZGaGgo8OE5rVAoSEpK4syZM9StWxdra2sSEhKwsLCgfPnyoo8uBvLy8vjxxx/ZsmULvr6+1K9fH4A9e/awfft2bG1tmTdvHlZWVp+c/Bf1a5g+VVcvX75ky5Yt7N+/H39/f4YMGVLo99nZ2cTFxWFubi6ewQYsKytLSm2sr+f4+HhGjRqFn5+ftHPn0qVLBAcHEx4ejrOzM9WqVcPExIS0tDQpPbKo4/89IrT3H9CvenJ3dyc4OBgHBwfWr1/Pnj17AHB3d8fOzk7aOicaluH5eGtkUFAQgYGB+Pr6Mnv2bBwdHQkLC+Ozzz5j7Nix3LhxQzqzB6B58+aFDkcTDINOp0Oj0bBjxw4UCkWhifyEhASeP3+OjY2N9NADsLW1xcPDA51Ox71795DL5TRt2pRZs2ahUCg+eVCeULTy8vLw8/Pj1KlThX6enJxMfHw8VapUQaFQSGn8evXqRaNGjTh79ixJSUnUrl2b8ePHs3r1akxNTUXAx0Dp22irVq0ICwvj7Nmz7Nq1i2fPnlGnTh1at27NgwcPqFOnDl5eXiiVSt68ecPJkycpX7481tbWRXsDwh+ifxb7+PgwY8YMxowZw9ixY/npp5/o0qULHh4eODo6cuvWLa5cucLu3buJiorC3NycXr16FXXxhT/p3bt3ZGRkUK5cOeDDRLKpqSmTJk3CxsaGb7/9lo0bN2JkZET9+vWpWrWqGE8XI6mpqeh0ukL9b+vWrenfvz+pqalMnjyZJ0+eYGdnR/ny5aUUnaJ+Dcvz58/x8PDgzp076HQf1olOnTqVIUOG8OTJk0Jnt3h7e9OtWzeePHnCnDlziIuLw93dnUaNGpGdnc2MGTMYNWoUFy9eZObMmSLgYyA0Gg3nzp0rtHgKPgT70tLSpDOZ9JOEMplMWj1+7949SpUqRa1atahQoYLoo4uJmTNnMm3aNF68eCHtnIcPZxf379+flJQUJk6cyPv37z/5Dizq1/DoA7J5eXncuXOH48eP8/TpU+zt7Rk1ahTdunVj7dq1bNq0SfpOfn4+JUqUoFKlSuIZbMDev3/P9u3buXHjBkChc4tfvnyJqakpcrmc77//nuDgYAIDA2nWrBmxsbHs378fAGtraywsLKT5a1HH/1tE0Oc/VDDwM3bsWBwcHFi1ahXnzp0r9Dmxdc4wyeVy8vLyGDVqFMbGxowZM4atW7fSqVMn9u/fz5gxY3B0dGTs2LF89tlnjB8/nsuXL/9mFYXoOA2LTCZDoVAQGhpKQEAAKpWKnTt3olarcXZ2pkGDBmzbto23b98WCtq5uLhga2tLeno6QKF6Fjt9DI+xsTHdu3fnq6++Aj4MigApF/WtW7cAMDIykgI/gwcPJiUlhdu3bwNQu3ZtkVPegGm1WoyMjMjMzMTPz49r166h0+mktEDJycmMGjWKDh06EBcXR//+/Rk5ciRjx45FrVYTGRkpPacFw6Tvf3U6HREREdjZ2TFz5kwWLVrE27dvWbhwIT///DMBAQH4+fkBMG7cOPbv34+9vT3r1q2TUlEIhkmr1f7mZ1WrVkWtVnPy5EkATExMyM3NxczMjAEDBpCTk8N3333HwYMH0Wg0UlBejKeLB0tLS9LT06W+Nz8/H4A2bdrQqFEjnj17Rnh4OM+ePQOQPifq17Dk5eUREhJCzZo1pXY8e/Zs6tWrR2JiIqdOnUKlUkmfHzRoEN27d+fly5dMmzaNlJQUqW5fvXpF5cqVWbVqFZUrVy6S+xF+S6FQ4OfnR2BgICqVilWrVqHT6bC1taVly5bs27ePR48e/eZ9qVy5ciQnJ//meqING6aC4+DRo0dTvXp1kpKS2LVrF3l5ecCHv4Xu3bvj6elJamoqAQEBZGVliXdgA1dwEXNAQAATJ04kLCwMb29vJk6cSEJCAsHBwXz11VcsX75cCvwYGRn95v1ItF/Dk5eXx9GjR9m0aRM3btwgODiYd+/eYWtrS/ny5bl58yZ79+5l2rRpDBs2jMGDByOTyUhLS/tkHy0Wuf7vEa36v0A/oeTm5saIESP48ssvadasWVEXS/iDHj16xLt37xg8eDDNmjWjUqVK2Nvbo1QqadWqFQ8ePMDV1ZVx48ZRvnx5Nm/eXNRFFv4AjUaDqakpAOvWrWPZsmWsXr0anU6Hh4cHeXl5LFq0iDdv3kh5TZ88eYJGo6F8+fJFXHrhX1Gr1cTFxQHQu3dvzM3NmT9/PjExMcTFxVG+fHlq167N3r17+eWXX4APA1uNRsOLFy+wt7enTJkyRXgHwh+lTxMyceJEjIyM6N27N1u2bGHq1KlcunSJJUuWkJ6ezrhx45gyZQo1a9akXLlydO3alW+//VaapBADXMOlVCrJycnhzJkz2NnZ0a9fPxo2bMgXX3zBkiVLSE1NJTY2lhs3btC9e3dWrFjB1q1b+eabb5g9e7ZUx2JSwjCp1WrpQOEHDx7w7t07cnJyqFChAq1atWLHjh2cP38e+BD4AUhMTKRBgwZYWlqye/duMjMzi/IWhD8gJyeHZcuWER0dzcGDB+nSpQumpqZERUUBSLsFAEqUKEHt2rUxMTFh7dq1qFQq0UcbmNTUVAAqV65Mly5dyMvLY8iQIWzduhWlUsnSpUupUqUK69ev5/z581JQD2DgwIG0bt0aJycnrK2tMTExoVWrVqxatYqgoCAxxjYwarVa6nuPHDnC+vXrmTFjBjqdDi8vL9zc3Bg1apQU+IEPO8Dy8vLEbq1i4OMFMTk5Odja2hIVFUX9+vU5cuSItLgCPgR+unXrRrdu3XB3d5fepQXDpR9jjR8/HktLS8LDwzlx4gSBgYG8f/+eSZMmER8fz8iRI+nWrRurV69m1apVgAgAFAcODg7MmjWLa9euMWHCBJKSkjA1NcXe3p6WLVuydetW5s6dy5AhQ/Dx8QE+jKMVCgVly5Yt2sILBkFsT/gv0Qd+qlWrRrVq1YB/rKgQnalhS01NJTU1FXt7exQKBd999x1RUVEMHz6cOnXqEB0dzcCBA2ncuDGRkZGFDgQXDFPBg2aVSiWenp4kJCRw/PhxjIyM8Pf35+3bt+zYsYPRo0fTp08fUlNTuXLlChYWFnTt2rWob0H4F/bu3SsFas3MzNDpdJiYmHDixAlKlixJYGAg/v7+hIeHs2bNGnr37k2rVq14/fo1J06cwMLCQryoFiOZmZnExcUxYMAA6ewANzc37OzsmDx5Mmq1mmHDhvHFF1/wxRdfFPquRqMROzGLgePHjzNr1iwAWrRoAXyYiKpYsSKLFy8mKCiIJUuWEBAQQJMmTQpNGopUFIar4OrTMWPG8Pr1a3Q6HZ07d2bQoEEMGjSIOXPmsGzZMhITE2nXrh3Pnz/n2LFjNGvWjG7dutG1a1d++eUXWrZsWdS3I/wTWVlZ+Pr6olKpUKvVnDp1ihs3btCvXz/Wr19PSEgIU6dORSaTkZKSwuPHj+ncuTOpqans27ePzMxMMbFoQHJzc/n222+xtbXFx8cHmUxGcnIylpaWrFy5EjMzM3r06MG6devw8fEhNjYWnU5HmzZtpODe0KFDpfP49OcPiBXkhkm/8GLnzp14eXmRnJzMwYMHiYqKIiwsjJCQEObOnYuPjw/du3dHo9Hw6NEjzMzM6NKlS1EXX/gX9G0vOzubb775hufPn6NSqWjZsiU9evRg/vz5jB8/ni1btgDQo0cPFAoFCoWC/v37I5PJCrVhwXC9evWKuLg4JkyYQP369VEoFHh5eVGmTBnWrl3L0qVLmTVrFgMHDiQrK4uffvpJ6qMFw6ZWq6lSpQo6nY6srCwsLS158eIFNWrUYMSIEWRnZ7N7927y8/O5evUqWVlZbNq0CSsrKzp37lzUxRcMgHhL/si/eqj9XsdY8PfJycnY2dn9n5RR+Pd9qn5dXFzQ6XTSCtTp06czbNgwvL29SUhI4ObNm7Rr1w5AipZrtVrx8mKg9HWsVqsZPHgwXbt2pW/fvowdO5bo6GgOHTqEXC7Hz8+PsmXLsm/fPhYvXky5cuWoWLEi06dPl/IXiwGuYbK0tCQ6OhqFQsGDBw9wd3cnKCgIgIMHD6LT6Rg9ejTTpk1jyZIlTJ48GSsrK0xNTcnJyWHx4sWify4mtFotGRkZvHnzBgsLC+BDmiClUkmTJk2YOHEiERERlCxZkq+++koKCumJNmyYPn6GtmvXDpVKxaJFi7hw4QKfffYZZmZmaLVaKlSowJIlSxgzZgzz5s0jMjKSWrVqSd8Vz2LDoR8Ha7VadDqd9CweM2YMMpmMoUOHcuvWLY4cOUJmZiZBQUFMmTKFLVu2EB0dzaJFizAxMaFcuXJ4eXnx5s0bnJ2dcXR0LOpbE/6JvLw86VzTCRMmYGVlRWRkJFeuXCErKwt/f3+2bt1Knz59sLCwkHYV9O7dmwsXLmBqavrJ9H9C0dHpdOTk5HD06FEAvv/+e6Kiohg1ahQbN25kwYIFwIcJ4vXr1+Pj48OiRYuQy+W0bNkSY2Nj4B8LIsVz2PD98MMPLF++nHr16jFw4EDy8vI4duwYM2fOZMqUKcTExLB161Z++OEHrKysqFKlChMmTJBSq4o6Nkz6gM/gwYMxNTXFzs4OCwsLYmNj+eGHH5g0aZIU+Nm2bRsymYzu3bujVCqlsZVow8XD69eviYuLK3SerZGRES1btuTly5esXr2a+Ph4XF1dGTVqFA4ODlIfLQI/hklfN/qFbRMnTqREiRKEh4ezatUqAgICqFmzJhMmTMDExIRz586xceNGKlSogIODAzExMWJOSwBE0KcQ/a6A3NxcfvrpJzIyMrC3t6dGjRqYmJj8y45Rp9NJD8etW7dy584dQkJCxAHSBuTj+rW1tcXR0ZGKFSvSoUMHoqKi0Gg0TJgwgd69ewMQHx+Po6NjoYNKQUwyGSp9HatUKn7++WcyMzNZsmQJ5ubmdO3alXHjxhEdHc2BAwfQaDQMGTKE5s2bExcXh52dHUZGRshkMuk6gmHq1KkTmZmZxMTEYGpqSp8+fQAKBX4ARo4cSUxMDLdv3+bu3btUqFCBBg0aiN16BuzjgalcLqds2bJ88cUXfPvtt9SoUQMXFxfpZaZq1aoolUoOHjyIk5PTb4I+guHR969qtZo3b95gb2+PmZkZffv2JScnh5UrV2JhYcGQIUMwNjZGq9Xi6urKggULWL16NdWrVy/qWxD+iZSUFOzs7KQxUm5uLm/evMHKygo/Pz+qVauGh4cHq1ev5uDBg2i1WkaMGEFERASDBw/m8ePHWFpa8sUXX6DT6di2bRvGxsZiZ6YBe/DgAe/fvycsLIzy5cuTnJyMqakpzs7OPH36lJIlS7Jy5UpOnjxJamoqtra29O3bF4CjR4/i6OiIubl5Ed+FUJCpqSlDhw5l+vTprF27FgsLC0qVKoWlpSUDBw5Ep9P9JvDj6+vL1KlTWbJkCQ0bNpSuJSYTi4eqVatSsWJFjh07xoQJExg4cCAAx44dIzIykqlTpxIUFMSgQYMKzW2I9yXDt2bNGszNzYmIiJAWr16+fJmQkBAWLFjAggULmDNnDpMmTWLp0qXY2trSunVr6fuiDRueT03iu7m5YWFhwe7duwkMDJTOszUyMqJz584sXbqUJ0+e4OrqKi2kEYuYDZe+b9VqteTm5mJkZETXrl1RKpVYW1szevRodDodAQEB1KpVi6CgIPr27UtKSgpWVlaULl1azGkJEvEX8P8VTEExdOhQMjIyyMrKIisri5YtW9KpUydatmz5TwM++p/v3LmTRYsWMXHiRBHwMTD6+g0MDOT169fI5XJatGjBiBEj8Pb2JjExkfv376NUKklJSeHXX3/lm2++wc7OrtALjGCYdDqdVMf+/v4olUpKlixJeno6UVFR5Obm0qtXLynwc/ToUdRqNQEBAYWCevrrCIYtPT0drVZLdnY2N27cwN3dHXt7+98EfgYNGkT79u1p3759URZX+AMKBm0PHz6MXC6XUqZ6eHiwZMkSlixZwqhRo6TAXUZGBs2bN6d9+/Yi/VMxUHCsFRISwqtXr6QUMT179sTHxwedTiflGtcHfjQaDW5ubsybNw/417uyhaLx9OlTgoODiYyMlIKv06dP5/Tp0zg4OBQaEwcEBAD/6Kd9fHxwdXXFycmJGzduEBkZSUpKCnfv3mXp0qUi6GPAUlNTSUlJkXZ3bN++nVevXhEcHMyhQ4c4cuQIFhYWDB06FHNzc3766SeOHDnCDz/8wPXr11m5cqUI+hgYjUaDvb092dnZmJqaUqJECQ4dOoSnpyeVK1dm0KBBACxYsACZTIaHhwfr1q1j5syZ1K9fv4hLL/yeT00ClilThr59+zJ37ly6dOlC9erVpXo+fvw4M2bMYNq0aYX6cfG+ZJgKjo80Gg1PnjyhfPnyUsBHrVbTuHFj5syZw9ixY9m7dy9ff/01s2bNYs2aNVKKXcEw6etXn5IxJSUFGxsbOnXqRP369Tl79izly5enU6dO0nm2Dx8+xNHR8TeLHkXAxzDpU5NnZ2czf/58Xr9+TVZWFhUqVCAgIICGDRtKqa+VSiWDBw+mTJky0lEjeiL9taAn/gr+P/1h0SEhIVhaWjJ58mQcHBxITU1l4MCBJCcn4+7ujrOzc6HvFQz47Nixg9jYWKZMmUK3bt2K4jaETyhYR6tWrcLa2poRI0Zw7do1Ll68yKxZswgLC2PcuHFs3LiRuXPnsnjxYiwtLXF2dmbJkiVia2QxoE8pEx0djbGxMWFhYVSqVIlHjx5x4MAB5s+fD0CvXr0YP3480dHR7NixA0dHR3r16lXoOoLh+bj9ff3113Tu3JmTJ0+ydOlSdDod/fr1w8HBQQr8fPfdd+Tk5BAQECDSAxUD+gGuj48P6enppKamUrp0aQYMGEDv3r2Ji4tj9+7djBkzhn79+pGZmcmZM2cwNjamdevWIu+4gdOvKMzLy2PkyJHIZDJ69+7N1atX2b59OxkZGXh7ezN48GAAVq9ejVwuZ/DgwdIh03qijg2PSqXC29ub2rVrS+0wJCSEnJwcLl++zM8//4ytra1UlwEBAchkMo4cOUJGRgYTJkygRIkSZGVl8ezZM2rWrMno0aNxdXUt2hsT/iU3Nzfc3NwoVaoUZ86cYdOmTcTGxlK3bl10Oh1Hjhxhx44dJCYmEhoayvbt23n06BHlypVj1apVVKpUqahvQfj/9O1W37+OHDkSuVzOunXr2L9/PzqdDi8vLypXrszAgQORyWTExMSQnZ2Np6cn4eHhha4jGB79JGBOTg4//vgjVatWxcHBAYDmzZtz7Ngxjhw5gqurKyVLlsTHxwe5XM6WLVsoW7Ysvr6+0rXE+5JhUigUqFQqMjIycHBwIDs7Wzr/VCaTSWlXmzZtSpMmTTh16hRdu3bF1taWkJAQQLRhQ6VPtadP2adQKFAqlSQnJ9OqVStGjhzJpEmT2LBhA8+ePaNHjx48evSIzZs34+LiQuXKlYv6FoQ/QN+G9e8/devW5f3799y8eRNfX18WLFjA559/zsKFCwkODubt27ckJSVRo0YNlixZIrV1EdQT9ETQp4C0tDQSEhLw8fGR8mE+f/4cgN69e5OQkIBCoZAmDz8V8Jk0aZII+BiQglsj5XI579+/p02bNtKB3/b29uzbt4+oqChCQ0OZNm0a/fv3Jy4uDltbW6pXry4FBEWk3PDl5+fz/PlzatSoIU0kVK5cWVpVPH/+fExMTOjatSvBwcGUKVMGDw+PIiyx8EcUfPm4ceMGeXl51KpVCycnJwYOHIhWq2X58uXodDo8PT2lHT86nY7Tp08zfPjwIr4D4V/R9686nY5Fixbh6OhIZGQk5ubmzJkzh23btgHg6elJuXLlOHz4MIsXL8bZ2ZmyZcsya9YscXZAMSCXy8nPz+f169dYWVkxatQoKlWqxKBBg5g5cybHjx9Hq9UyePBgBg8ejFwuZ/ny5Tg6OtKjR4+iLr7wO6pXr0716tXJy8tjwoQJfPHFF/Tv35/p06czduxYli9fjo2NDZ9//rk0nvL39ycrK0sac8nlcr788ku+/PJLkXakmHBxcWHu3LmULFmS7777jg4dOtC4cWPy8/N59OgRtWrVYsyYMdJ4evbs2eTk5KBUKjE1NS3q4gv/n/45nJeXxy+//IKlpSVubm6ULFmS4OBgYmNjOXDgAABeXl5UqVKFQYMGkZGRwYULF+jfv7+U6lw8hw1TwTpetmwZu3btol69erRo0YL+/ftjZ2dHs2bN2Lx5Mz4+PpQoUQILCwsGDBiAo6OjeF8qRubOncutW7fYvXs3tWrVYt++fdy6dYs6depIZ4TodDp0Oh1WVlaYmZkV+r5ow4ZJv8B1wYIFWFpaMnPmTGxsbNBoNFIdRkREsHbtWvbu3cuGDRtwcHCgTJkyLFmyBLlcLsZWBk4/v7xt2zbMzc2JjIyUdmjdu3eP5cuXSwvVGzVqJPXltWvXZuLEiYAIyAu/JWaxC3j//j2vXr3CxsYGhULBsWPHCA8PJyAggCZNmhAYGEivXr3o2bPnPw34iAGR4SiYRmbatGmoVCoeP35cKE+tp6cnAPv372fWrFkEBwfj7u6Ou7v7b64jGD6dToexsTGZmZmFfm5lZYWHhwfHjx9n5syZKBQKOnXqhJ+fH3K5XKxoMmAF62batGlcunSJjIwMqlSpwpAhQ2jatCne3t7IZDKWL1+OXC6nTZs2PH/+nFGjRuHj44OVlVUR34Xwr+hXne7btw+NRkO7du2oUqUKADNmzCAyMpKtW7ei0Wjo06cPzZo1IyEhAWtra4yNjUXO4mJCp9MRHBzMTz/9RNmyZaXVxQBTpkxh5syZnDx5EplMho+PD97e3tjb29OhQ4ciLLXwZ7169Yrs7Gy2b9+OmZkZHh4exMbGMnr0aGbNmsXkyZMLBX7GjBkjjakLTkaISYnio2TJkuTl5ZGUlCSly3379i3nzp3Dzc2NGjVqIJPJpPMFLCwsirjEQkH6VDJZWVkEBQXx7Nkz5HI5tWrVYtKkSVSoUIExY8awcOFCDh06hE6no3379mRmZjJq1CgqVKggJpkMnD4Vm36HQP/+/VmwYAEnT55k5cqVnD59mq+++orevXtz/vx5li1bxvTp04EP7VufEUG8Lxmmj8+cbtasGY8fP+b8+fP4+flx/fp1oqKimDJlCrVr10Yul/P8+XPevXtHs2bNirDkwp8ll8t5+fIlVapUoVSpUtKiN4CXL19y+/Zt/Pz8CA4O5uHDhzg5OeHm5iYWMRcT+nb8/PlzjIyMKFWqlNS+q1evzrBhw5gyZQqrV69m6tSp1K1bl+rVq0u76EUdC5/yP/tGpdVqf/PfDg4OuLu7c+7cOXbv3k14eDjDhg3D19cXMzMzsrOziYuLA/7RILds2cKSJUtEwMfA6CcO8vPz8fPzIykpCfiwEyQ2Npa3b99Kn/X09KRHjx7Ex8cTHh7Ou3fvCl1LTDwYJo1G85ufmZqa4u7uzg8//MDt27cL/a5SpUo4Ozvj7OzM9OnTuXHjhlS34gXGcBUM+Ny8eZORI0eyatUqkpOTWbduHRcvXkSr1TJo0CBGjhzJpk2bGD9+PFFRUcTHx4uATzHx6NEjFi1axKFDh8jPzwc+vMTa2toSHh5O+fLl2b17N1u3bkWtVuPo6IiJiYk0USwGuIZJ/yIKH8ZNo0ePplKlSrx9+5Y7d+6gVqul30+ZMoVGjRpx6tQpli5dSk5ODl26dEGpVBb6nGBYPn4WV6pUiaCgINzd3VmzZg379+/HysqKRYsWYWdnx+zZs/nxxx8L1al+0kKMt4ovY2NjvvzyS06dOkW/fv0YMWIEmZmZjB8/XqpfIyOjoi6m8An68yF8fX2Ry+WEhYXRt29f7t+/z4wZM4iPj6dixYqMGTMGJycnNm/eTLdu3Vi6dCkVK1aUVo+LwI9h0k8YqtVq9uzZg7m5OZUrV6Z58+ZMmjSJdevWYWlpyaZNm/Dy8sLW1pZnz57x9OnT31xLvC8ZHo1GI6U3zsnJAaBp06ZYW1uzY8cOzM3NiYiIwMTEhODgYEJCQpg2bRqhoaHAh7MTheJBo9GgUqmIj4//ZJ9ra2vL/PnzuXbtGo6OjrRo0YLKlStLfbR4VzJMBd+V9GPq9PR01Go1RkZGUv8NUKNGDWrWrMmvv/4qfVYf8BHnrAn/zP/k25VarZai3frdPfBhJUvr1q05cOAACxYsYPDgwfj4+ADw4sULdDqddAieVqvlxYsXLF68mODgYBHwMSAFzw24desWFStWZP78+SxdupSJEydibm7OpEmTpAAeQP/+/Wnbti1lypTB1ta2CEsv/BFqtVrKd/rdd9+xbds29u/fj0qlYvjw4bi6uhIREcGtW7ekB+mTJ0+QyWQMGTKEzz//nN27d5Obm1voQSsYphs3bnDv3j3CwsLw8PCgatWq1KtXj19//ZXly5fzww8/oNFoGDBgAPPnz6dHjx5s27btN2ewCYbj43ZXp04dli5dioWFBcePH+fZs2fSy4y1tTXh4eGUK1eOb7/9llOnThX6rpgoNkxqtVoKyun/7e7uzowZM7C1tWXFihU8fPiw0N/C5MmTqVKlCqmpqYVSP4mXGMNU8Fl85swZDh06RE5ODrVq1WLIkCFUqVLlN4Efe3t7xo4dy4MHDwpdS0wYF389evRg+vTp1KxZk+7du/Ptt99KQVtRv4ZJ3/9u2bIFKysroqKiaN26Nc2aNaNUqVI8ffqU6dOnS4Gf4OBg/P398ff3Z9WqVVK9iuew4dJPGPr6+rJ//35q1qxJ9erVgQ/B2kqVKjFv3jxmzJhBw4YN+fHHH3nw4AE///xzEZdc+CMUCgW5ubmMGDGCtWvX8uuvv2JqasqECRO4f/8+GzdupGLFiqxdu5auXbuSlZVFamoqDRs2ZP369SiVyk8upBSK3sf1otPpMDU1lc60PXfuHPCP8ZOpqSlubm6fXCgl+mjDpB8fqdVqVCqVFLjt1q0bd+7c4dtvvwWQUjLCh/dia2vr37wbiXGW8M/I0tLS/qdmPPXbkrOyspg0aRJv374lMTGRSpUq0bt3b7p27crChQvZtm0bvXr1ok2bNiQnJ7Njxw50Oh1r1qwptMrl9evXlClTpgjvSACIj48nJSVFGsSq1Wrmz5/PqVOnsLe3Z82aNVI6ie+++45NmzahVCqZO3eulIoC+GSKEcGw6OsoKysLX19f1Go1eXl5pKenU7ZsWXr06EGNGjWYN28er169olGjRlhaWvLzzz9jbm7O2rVrmTZtGqmpqSxZsqSob0f4Aw4fPsyKFSvYsWMHFhYW7N+/n5MnT9KrVy8WLlyIubk5Q4cOpXHjxhgbG4v0EwZOv/Vco9GQnp4OfJh4MDc35/Lly0yaNInPP/+cUaNGUb58eel7KSkpbN68mREjRoj6NXD6Os7OzmbhwoXExcXh7u7Ol19+SdWqVXny5AljxozBxsaGiRMnUr169UIvK/pn8McpSwTDk5WVxZAhQ0hMTCQzMxNnZ2fCwsKoV68eDx484JtvvuHhw4cMGTIEDw8P0tLSWLp0KaGhoaId/00VbLci1Yhh+rheZsyYQVJSEtHR0cjlcpYsWSKlENq9ezdVq1YlPDy8UFrOT11HMFzffvstK1eupHz58syaNQs3Nzfgt3X4yy+/8ODBA3r37i3qtph4/vw5gYGBqFQqSpUqhZ+fHx06dGDdunX8+OOPjBw5UpojycvLQ6FQSM9f0YYNk75ecnJy2LRpE69evaJu3bp07dqVX3/9lejoaDQaDYMHD6Zly5ZotVri4uIYO3Ysffv2pWfPnkV9C8LvKDinNXnyZBISEnB2dmbgwIHUrVuX8PBwLl++TL9+/fD19SU3N5eEhARCQ0OpU6cOISEhRX0LQjHxPxf0AcjNzcXPz4+SJUvSvn17ypUrx44dO7hy5Qq9e/cmKCiIZcuWcfXqVR4+fEjFihVxdHRkwYIF0kSVXC4XExEGQqfTcfDgQY4dO8aUKVMoU6YMycnJXL58mUOHDvHkyRM2btxYaNX/d999x+bNmzEyMiIqKqpQ4E5MMhk+jUbDxIkTef/+PZMnT8be3h5zc3O+/PJLHBwcmDt3Ls7OzqxcuZKHDx+SlZWFu7s7EyZMQKlUEhwcjLOzM8HBwSgUClHfBuRTAZuffvqJsLAwtm/fzuvXrwkICGDIkCF4e3tz+PBh6ZDDli1bMnr0aNGGDVjBhRdTp04lPj6e9PR0SpUqRUBAAI0bN+bKlStMnDjxk4Gfj68jGB59wCYrK0s6b8va2po3b97g6urK8OHDqVmzphT4sbW1ZeLEiVSrVu2TgR/B8OgnI3Q6HQsWLODFixcMGTKE/Px81qxZw6tXr4iMjKR+/fo8ePCANWvW8PjxY/r370+/fv2k64h2LAh/Pf0YKTMzk40bNzJs2DBmz55Namoq8+fPZ8eOHSxdupRVq1ZRvXp1Ro4cyfXr1zEyMmL16tXS5LFguP5Z37pjxw5iYmLo2LEjQ4cOld6NdTrdJ1NsioCAYfq4XnJzc1m/fj3Hjh3js88+4+jRo/Tq1YtSpUpx+vRpPDw86Nmz52/GVeJ9yTB9vMDV1NQUjUZDgwYN8PHxwdramosXL7JmzRpev35NmzZtUCqV3LlzB/gQ4BVjq+JBrVYzbNgwAJydnXn27BlpaWnMmDGDChUqsHDhQo4ePUq1atUwMjIiPT0dIyMjaZeeaMPCH/E/GfS5fPkys2fPZtasWVSrVg2FQiFNHEZFRVGrVi2cnJxIT08nPj4eGxsb7O3txWHRBuzcuXMsXrwYBwcHbt68KU0InzlzhuXLl6PT6Vi7di12dnbSd44dO8aiRYto0qQJYWFhRVh64Y8o+FDLycnBz8+Pzp074+npiVwu5/Lly4wZM4awsDBsbGxwdXXFxcUFgPfv35Ofn09KSgq7du3izJkzrFmzBldX1yK8I+FjBV9Sf/rpJ7KysrC3t6dSpUo8ePCA2rVrM2LECKysrJg1axYA69at49ixYzRs2JB+/fqJnZfFgEqlwtfXF3Nzczp16kR+fj737t3j2LFjhIaG4uHhweXLlwkNDaVhw4YEBgZSsWLFoi628Ceo1WomTJiAVqtlwoQJlClThpiYGI4ePUqVKlUIDAykVq1aPH36lODgYLRaLYsXL6ZChQpFXXThn3jx4gVyuVxKc6xSqdiyZQuPHz+mZcuWdOrUCYCEhATCw8N58eIFUVFR1K9fn4cPH7JgwQKsra2ZN2+eeEEVhCKiH2fpJ5qysrJYtGgRZmZmPH36FFdXV3r27MnQoUP5+uuv0el0jB07VkoD5uvrK96DDZx+rkKlUnHx4kXS0tIwMzOjQ4cOKJVKdu7cSXR0NL1798bT01N6VxKKl5ycHG7fvo2bmxu2tra8e/dO2uHTsWNHoqKisLW15fLly1haWrJ27VpR18WIRqNh2rRppKSkMG3aNCkzTWJiImlpaZQuXZrs7Gx2797N8ePHcXZ2xsXFhUmTJkmL1EXgxzAVnE9OS0sjKiqK4cOHU7FiRX7++WfWrVvHs2fPiIqK4rPPPuPs2bMcPHgQS0tLypQpw+DBg6XUueJ5LPwR/xN/JR83iDdv3vD+/Xvc3d1RKBQcPXqUqKgohg0bhqOjI7NnzyY0NBQnJydKliwpfU8cgGa4WrZsSXJyMgsWLMDCwoKKFSuiVCpp27YtMpmMVatWMWzYMFasWCEFfjp27IiVlRUNGzYs4tILv0ffhvPz83n//j0KhYLXr1+jUCiQy+UcP36csLAwhg4dSufOnRk6dChVq1Zl3LhxADx9+pRFixaRkpKCubk5y5cvFwEfA6PT6aTBaVhYGL/88guZmZnk5uayatUqateujU6nIzU1lRo1agCQmprKs2fPaNasGYGBgRgbGxflLQi/Q7/C8MKFC1JQoHLlygDs3r2bY8eOUbJkSRITE2ncuDGzZs0iODiYcuXKMXLkyCIuvfBnpKSkEB8fj6+vL2XKlCElJQWVSkWlSpWIi4tj+fLlBAUFUa1aNebPn8+aNWsoV65cURdb+ASdTkdycjJ9+vQhIiJCCvqcOXOGAwcO8O7dO/r06QN8eFY7OjoSGRlJWFgY06ZNIzIyknr16jF16lTKli2LTCYTKxMFoYjoz+DasGEDdnZ2hISESCnbateuzf3791EqldSpUwf4kMb8/fv3dOnShV69egFi94ch0x/knZWVhZ+fn9R/K5VK1qxZQ3BwMH369EGr1RIbGwuAl5eXOAOzGFq8eDF79+6lTZs29O/fn9q1axMWFkZ4eDhNmjRh/vz5nDx5kvfv33Pr1i2OHTuGn59fURdb+INycnJ48+YNXbp0oXTp0rx48YKTJ0+yefNmqQ9esWIFI0aMwM/Pr9A5mKKPNlwajUZK27d3716ysrJ49OgR5ubmANStWxcfHx/Wr1/P1KlTmTp1Kq1ataJVq1afvI4g/BH/E38p+rzyJ0+epFu3blSoUAG1Ws2dO3fIysoiIiKCYcOG4ePjw6tXr7hy5QqPHz/Gycmp0HVEmhHDo1/FkJuby9WrV6lTpw6JiYns3r0bOzs7ateuTevWrdHpdKxevfo3gZ/GjRsXuo5geAq+wAQEBNCzZ0+6dOlC/fr1uXLlCvn5+Sxbtozhw4czYMAAZDIZGo1GOggPPjxAvb29cXR0pFSpUtjb2xfhHQmfop8AXLp0Kbdv32b69OnY29uTlZUlpRLJysrC2dmZixcvolarSUhI4Mcff2TFihUi4GPA9P2r/hmamJhISkoKtra2ABw/fpz58+cTFBREqVKliIyMZNKkSTRp0oR169ZRpUqVoiy+8CfpdDqSkpJ4/fq1VMe7du3ixx9/ZMmSJVy/fp3Zs2ezcOFCevbsSYcOHZg3bx4gnsWGSCaTYW9vz+rVq6lTpw75+flkZWXRunVr3r9/z5o1a1i3bh316tWTVpc6ODgQGRlJeHg4w4YNY+PGjVI7Fmn7BKFonTlzhvXr1yOXy/H09AT+sZve1taW3Nxc1qxZQ+3atTl+/DgKhQIPDw/p+2KiyXDps5KEhYVhaWnJxIkTsbGxQalU0r9/f5YtW4abmxv9+vVDq9WyaNEi0tPTGT16tHg3KmYmTpyIq6srFy9eZMSIEQwZMoS6devSqVMnvvvuOwIDA+nVqxdffvklW7duxdvbu6iLLPwJRkZGlCxZksOHD/P8+XOuX7/Oixcv6NmzJ66urpw8eZI1a9YQFRWFkZGR9D39vIlgePQLXLOzs/H29iYlJQWAzMxMbt26Rfv27QGoX78+ABs2bGD27NkEBQXRtm3bQtcS70rCn/E/89Z16tQpZs6cyZMnT6hQoQJVqlRh1qxZhISEEBQUhI+PD1qtlqdPn+Lo6PibgI9gePSTQyqVCk9PT1QqFbGxsQwePJh3796xcuVKbt68iUKhoE2bNgQEBCCTyejTpw/v378vdC3RcRom/UuoRqNh69atGBsbU716dUxNTWnbti1Xr15l2bJleHl54e3tLe0AysjIkFaNazQaAFq3bk316tXFS40B02q13Llzh2bNmlG3bl3Kly8vBXzevXvHixcvaNeuHXZ2dpw6dYr4+HiWLVsmUn8ZMK1WKwXmFyxYAECpUqXIz89Hp9NJu/SGDRuGl5cXGRkZ/PLLL8TFxQFQo0YNaQu7YJj0fayeTCajRo0adOnSBWtra65evcq6desIDg7GxcWFJk2aYGxsTGpqKvv375fOEgDxLDZE+rqpU6cOGo0Gb29voqKiyMjIoFevXgwZMoQ7d+4wfvx44EMd6gM/4eHh9O7dWzowHMQCKkEoap9//jmjR49GqVSyZ88e1Go1MpkMrVaLvb0948aN4969e+zfvx9bW1u++eYbqV0Lhi89PZ24uDi+/PJL3NzcsLOz49q1a6SmptK/f3+ePXtGQkICnp6e+Pn58ebNG2mBhlA8aLVaAPr27cvUqVMZPnw4W7ZsYevWrTx48IAnT55w+/ZtlEolNjY2jBgxQoylixkTExM6deqEmZkZZ86coWzZsixdupSJEyfSt29fHB0dkcvlmJqaFho7i13Uhkmr1Uo73a9cuULp0qXZsGEDUVFRtGzZkrCwMC5duiR9vn79+tL5TceOHSvCkgt/B/8zYeDPPvuM6tWrc/78eQYPHoynpyfz58+nfPnyUg75u3fvsmXLFsqWLUulSpWKuMTC79FPJF66dIkKFSoQFBSEqakpXbt2BWDTpk2sWrVKOjS6devW5Obmcu3aNSwsLIq49MIfoQ/4+Pv7k5ubS8uWLalWrRoAXbt2JSsri5iYGF69esWBAwfIz8/n8OHDmJmZSasXxSSi4fp4VX9aWhq//vorn3/+OXK5vNDv09PT8ff3Z+HChcTGxpKdnY1MJsPS0rKoii/8Dn16AbVazdmzZ9m9ezdqtZoxY8bg4uLCkCFDSExMZMSIEQwaNAiAvLw87OzssLKyKnQtsWrNsOTl5WFsbCwF9VQqFd9//z2mpqY4OztTq1YtQkJCkMvlHDx4kC+++ILmzZuTl5fH3bt3cXd3Z/jw4dSvX196CRIMU8EJBIVCQZcuXVi8eDElS5aUVhIDfPPNN4wfP54FCxZIE8SOjo5MmDABELu4BMFQ2Nvb07FjR9RqNcuXL8fS0pLx48dLAdmuXbvSqlUrMjIycHJyEmfaFjMajYaUlBTy8vIApMU1w4cPp0OHDkyaNIlSpUoxZcoUAgIC8Pf3l4J+IihfPMjlcmlhpKOjI/3796dOnTqcOXOGa9eu8eDBA8LDw9m/f3+h8bRow8WDvm47depEw4YNpV2Yem/evOHVq1dSGk7B8MnlcvLy8hg3bhwajQZ3d3fKlClDmTJlsLe3l87Pi4mJoUmTJgDUq1ePyZMn4+7uXsSlF4q7v2XP/6mBadmyZalZsyZ79uzB09OTdu3aAbBlyxamTZuGQqHAzMwMW1tbli9fjlwuF4MfA6fVapk1axbHjh2jVq1aUso2QAr8bN68mWXLltG+fXvi4uLo2LGj9DsxAVE8KBQK/Pz8GDt2LCYmJnTp0kU6iLJv376Ymppy+vRpYmJiKF++PM7OzkRFRYlDDIsBfd3cv3+fqlWrYmtrS8OGDTl8+DAdO3bExcVF6s8rVqxI6dKluXv3Lg0bNix03ppgePRn4GVlZREZGUlcXBxKpZJ9+/aRnZ2Nv78/mzZtQqPR0K5dO9LS0khMTGTDhg2UK1dOLLwwYPoV4P369aNixYrk5OQwaNAgMjIySE1Nxc3NjT59+tC9e3fgQ9qCX3/9lezsbF69esWOHTtwdHSUAj5irGW4PvUM9fLywsTEhPnz56PT6Rg+fLgU+FmzZg0hISHMmzfvN98Tz2JBMBzW1tZ89dVX6HQ6li9fDiDt1tNoNFhYWEgL5MSZtobrU320sbExdnZ23Llzh927dzN//nyGDx+Ot7c32dnZJCcnF8pool94IZ7DxUvBBRk6nY7q1atToUIFevTowfz588nMzBSLXIupgmcf6ue3zp07x+7duylXrhy3b99Gq9USFBQEIM5JLCYSExMxMzPj4sWLhc6Wdnd3JyAgAIBx48YRExMjHUEhUiML/w1/yxGc/nCs69evF0rn5Ofnx6VLl1i7di3Dhw+nXbt2VK5cmYSEBF68eIGLiwsNGzZEoVCIFU0GquBDTavV0qpVK96+fcurV694/fo1VapUkequa9euyGQytmzZQmxsLLa2tgQGBkrXEhMQxUfTpk1ZtmwZI0aMYPv27Xh7e0vtunv37nTo0IH09HRKlCiBubm5WJVYjCxfvpwDBw4QEhJC27Zt6dSpEw8fPmTJkiUEBQVJh8smJiZiYmKCjY1NEZdY+CP0K5pGjhyJiYkJXl5elC1bll27dvHLL7+QmprKgAEDWLNmDb6+vhgZGVGiRAlKlChBTEyMWHhhwJ4+fcqBAwfQaDQMGDCAnTt34uTkxIwZM3j//j2bNm1i69at5Ofn07t3bzp27MiFCxf48ssvsbKyws7OjqVLl4qAj4HTP0NzcnJYu3YtKpWK0qVL069fP3r37g3A/PnzAaTAj0wmIyYmhqVLlzJy5MiiLL4gCL/DysqKbt26AbBixQrkcjljx479zfuR6KMNk76PVqlUnDt3jtevX9OmTRsqVKjAsGHDmDRpEqdPn8bf3186zyUpKQm1Wi2lwNYTE8bFm77+zMzMMDMzIzY2tlCKdDHnUfx83CbfvXsHwKNHj6hevTrjx4+XsimI+Q7D9PE7TpkyZQgMDMTIyIh9+/bx+eef07p1a+BD4Gfo0KHI5XLGjBnDmjVrqFWrlvRd8RwW/hOytLS0v2VOjdmzZ7N//34qVarE4MGD+eyzz3BwcCAmJoaHDx8SHR2NhYXFJyPj4uFomPQPNZ1OR15eHiYmJqjVam7cuMG8efOQy+WsWrUKW1vbQg/Ap0+fkp6eTq1atVAoFGKSqRi7evUqQUFBDB48mN69e0uBn4/bsVjxUnwkJCQQFBSEXC5n+PDhNG/enE2bNrFnzx5KlizJsGHDyMzM5MqVK1y5coXVq1dLO70Ew3b79m1CQ0MJCwujUaNGAGRkZHD48GF27dpFjRo1mDRpEufOnSMlJQVHR0fatGkjFl4UA4cOHSIqKgoPDw8SEhLo2LEjHTt2BODhw4esXLmS169fM3DgQLp168bDhw+5evUqFhYWdO/eXdSxgdOPk7Kyshg8eDB5eXmo1Wp0Oh0NGjSQdsjrV5F36dKFYcOGYWVlxfnz52nVqpWoW0EoJt6/f8/hw4dZvHgxY8aMoX///kVdJOF3FOyj/f39yc7ORqVS0a5dOwIDA7GwsGD37t0sXLiQFi1a0LRpU9RqNXv37kWn07Fu3TrRR/9NFZzHEnNafy9qtRq1Wo2pqan0b9GODZO+bvLy8nj9+jUJCQlUqFABBwcH0tLSmD17NpcvX2bOnDk0b95c+t79+/c5ffo0Q4cOFXUr/Nf8bYI+n5rIP3HiBOfOnePkyZPUqlWLDh060KhRI/r3709ISIi0ukkwfAVXnK5YsYJXr15Rr1492rdvj5OTE9euXWP27NmYmJiwbNky7OzsPvkgFIOf4u/KlSuMHj36N4EfwfB93Cb17fHdu3eMGDECrVbLmDFjaNq0KUePHmX//v3cvHkTBwcHrK2tmTZtGpUrVy7COxD+jBs3bjB27FgWL15MnTp1pPrPyMhg4cKFHD58GA8PD0JDQ4F/PMdFP224CtbNvn37mDNnDgARERFS0Ac+rERcsWIFr1+/ZsCAAVKqt09dRzBMeXl5jBo1CiMjI0JCQrCysmLmzJlcu3aNFi1aEB4eXijw07x5c6ZOnYq1tTUgJiMEoSh83Lf+0UVQaWlpXLlyhXbt2ol2W0zk5+czatQojI2NpRTYpUuXJjMzUzo0/M6dOyxcuJD09HRsbW0pW7asSIFt4P6Txali0aPh+3f6aP1nPs54IxYxG6aCQflRo0aRnJxMfHw8NjY21KpVi8jISFQqFVFRUVy6dIm5c+cWCvzoiXG08N/ytwj6FDwsOjk5mYSEBKpWrYqxsTEAly9f5uzZs3z//fdUr16dxMREbG1tmTlzJg4ODkVceuH3FOw4vb29pYO+7927R9u2bfH396dChQpS4MfU1JRly5Zha2srBj9/U1evXmX06NH07t2bIUOGSJNMguFRq9VkZWUVOkj06NGjtGzZEnNz898EftRqNWPHjqVp06YAPHjwABsbG0xNTQtdQzB8b968wcvLi379+kmpNfXP63v37jFkyBAsLS1p1qwZYWFhRVxa4ffo22rBF83Tp08TGhpKo0aNCA4OpkKFCtLnHz16xOrVq/nll1+YMmWKlMJAMFwFx0y3bt0iKiqKsLAwatWqRUpKCjExMbx9+5bExETq169PeHg4crmczZs3c/r0adasWSMmIQShiOj76JycHE6dOkXHjh3/rQkjnU4nzngpBuLi4hg3bhyBgYG0aNGCd+/eceHCBTZv3oxaraZx48aMGTOG/Px8srOzUSgU2NnZiRTYBqzg7oBbt26Rn59PxYoVcXR0/N3vFnx+79u3DxsbG1q1avV/XGLh36FSqTh58iTNmjXD2tr6TwV+AFJSUrC1tf0riir8mwounOrbty+urq4cOnSIY8eOYWlpydq1a8nKymLu3LlcvnyZ6dOn07Zt26IutvA3VexHcxqNRjosetSoUQQEBODv70+/fv2YP38+OTk50qBn27ZtODk5UaJECW7evMmTJ0+AD0EFwXDJ5XLUajWTJk3C2dmZFStW8O233+Ll5cXp06dZu3YtL168oGHDhoSGhpKXl0f//v1JT08XAZ+/qUaNGjF//nzu378vAgEGLD8/n9GjR7Ny5UpSUlIAuH79OhERESxdulR6CdVoNNjb27N8+XJyc3OJjY3l1KlTaLVaqlatiqOjo6jnYsjFxYWBAwfy7bffcvjwYQBpkuHVq1dUrVqV9u3b88svv3Dr1q2iLKrwO9RqNQqFApVKxYEDB1iyZAknTpygTZs2REREcPXqVTZu3MiLFy+k71SuXBlfX1+6detGixYtirD0wh+hVquRyWTk5+cDH1IxpqSkSAuotm3bxsuXLxk9ejSNGzfm2LFjREZGkpKSwoABA1i7dq10FpcgCH8trVaLQqEgNzcXPz8/Ll++THJy8h/+rt6jR4+QyWQi4FMMZGVl8fLlS169esXmzZsJDQ1l7ty5lClThoYNG7Jv3z5Onz6NpaUljo6O2NvbS2fpiYCP4dHXS1ZWFoGBgUyfPp3p06dz8eJF8vLy/uV3CwYEduzYwZw5c8jJyfkrii38QWq1GvhQV99++y1LlizhyJEjZGRkSLt4/pmC9btz504mTpxIWlraX1Fs4d907949EhMT8fX1pWnTppQtWxY/Pz+CgoLIzMxkxowZ2NjYMHLkSGrWrMmuXbuKusjC31ixf+LrB7ijRo2iRIkSDB06FFdXV7Zv387Fixd5+/Yts2fPlg62CwsLIz4+nmXLlrFixQrq1q2LiYlJUd+G8DsSExNJTU1l6NChODs7k5iYiEql4vPPP+fEiRPk5+czbNgwGjZsyLhx4zh48CDm5uZFXWzh/1Dz5s1p1qzZb7Y7C4bDyMhIOuPB3NwcLy8vPv/8cyZMmMCiRYsApL5brVZjZ2fHxIkTmTx5Mps2bQIQq16KuV69evHixQsiIyN5+fIljRo1Ijc3l23btlGtWjUGDx7M3r17efLkCbVr1y7q4gqfoNPpUCqVZGdn4+vri06nQ6VScfbsWVxcXOjYsSN5eXnMnDkTnU7H4MGDKV++PADVq1enevXqgEjpZsgKTjYNGjQIPz8/GjZsSJUqVShVqhRnzpxh06ZNxMbGUqdOHWQyGQcPHuTYsWNkZWUxb948ALE7QBCKiFwuJz8/nz179mBubs7gwYP/UPrjgm12x44dbNq0iUWLFlGpUqX/6yIL/yE3Nzd69uzJ4sWLMTU1xcXFhejoaBo1aoRSqeT+/fvSAteCRB9tePQ7qHNzcwkMDMTS0pJZs2aRlZVFvXr1MDY2RqVSYWpq+i/Psd2xYwcLFy5k8uTJdOrUqahuR/hIwUXqixcvJjExkbS0NDZu3AhAt27dsLS0/OR8xsf1GxMTw5QpU0SWEwNTMPOUUqkkMTGRxMREKlSoIC1gNzExoXnz5ty/f58jR46QlJREuXLlmDZt2h/azScI/65iF/RJTU3FyMgICwsLqRP86aefSE1NZdy4cVSrVg25XE5oaCi7du1i3759rFq1ipEjR0orl0qXLk3nzp2Jjo7m7du3hdKRCIYpJSWFx48fY2VlhUwmY+/evVy+fJl169Zx5coVpk+fjqmpKc2aNaN9+/Y0adIEEJNMf3ci4GO49C8ws2bNYvbs2Xz33XfodDoGDhxI7969AYiJiQFg5MiRUpA2JSUFd3d3SpUqRY0aNYqs/MJ/h7W1NePHj8fd3Z0NGzawa9cuTExMKFeuHGPGjCEzM5Py5cuLVKsGTCaTodFomDdvHiVLlmTKlCmUL1+ehIQE6SWlW7dumJmZMXXqVORyOQMGDKBixYqFriOexYZHf+6D/oX08OHDlCpVCldXV+zt7ZkzZw6WlpZ8//33tG/fnsaNG5Ofn8/9+/epWbMmY8eOpWrVqgDiOSwIRUin07FgwQIuXLiApaUlbm5uwL9+D/rUZGJoaKgI+BQD+robO3YsrVq1wtbWFmtra6ytrdFoNLx48YKcnBxKly5d1EUV/oknT57wyy+/0L17d5RKJTqdjps3b6LRaJg8eTJlypQhPz+f8+fPs3//frKysujfvz/t27f/5BkvO3bsIDY2lkmTJv3mHEWhaOkXqQ8dOhRzc3Pat29Phw4dOHjwIOvWrUOn09G9e/ffBH4+Vb+TJ08W55IbmIILp0JDQxkwYADly5dHo9Fw/vx5qY3rAz9dunRh8+bNPH/+HEdHR6mfFuc0Cf9XilXQ5/Xr1/j4+ODt7U2PHj2wsLAA4OXLl7x//56qVatKK53MzMz4+uuvefjwIRcuXMDf358SJUpI18rJyeHNmzckJCSIoI+B+VSHV6NGDfr06YO5uTmXLl3i22+/ZcGCBdjY2FC2bFkArly5glarpV27dtIDUkwy/f2JiSbDVHCbuqenJ/fv3+f7779HJpMxYMCAQoEffTDIyMiIu3fv8vnnnzNkyBCMjIyKqvjCf1HJkiUZOHAg7du3JzU1FbVaTa1atVCr1axcuZLs7Gzc3d2LupjCv5Cfn8/Tp0/5/PPPpV08+lXkCQkJnDhxgp49exIeHk5ERARlypT5TdBHMBz6fPD6sZZarSYoKIj4+Hi+/PJLaXeWhYUF+fn5JCUlYW9vj06n482bN5w9exY3NzeqV68uBQXFeEsQ/loFJwRlMhm9evUiMTGRS5cusWLFCoYNG/abc9g+9d2Ck4lisrh4KDjhX69ePQBOnDhBTk4O2dnZnDlzhhIlSuDh4VG0BRV+Q39m1sKFC3nw4AE6nQ4PDw+USiW5ubk8efKE1NRUHj58yKFDh7h8+TKVKlXC2NiY8PBwnJycqFWr1j8N+Ig6N0y3bt0iJSWFCRMmUKdOHQA6duxIeHg469atQyaTFdrx8/EuTBHQM0z656tarSY2Nha1Wo2DgwOWlpY0adKEbdu2YW9vT9OmTVEqlWi1Wp4/f46LiwtOTk6FriUCPsL/lWIV9ClTpgzVqlVj3bp1GBsb06VLFywsLHB2diY7O5tLly7RvHlzjIyMCgV+hg4dyvPnz6WX2Ddv3nD9+nWsrKxwdXUt2psSCil4gOGvv/7K+/fvqVSpEqVKlWLMmDEoFAq2bt1Ky5Ytad68ORqNhqSkJJo0acKAAQOoW7eu2P0hCAZAPwE4btw40tLSyM3NxcjIiO3btwPg5eVF7969kcvl0hk+FhYWpKens3LlShHw+RtycnLC0dGRs2fPMn78eNLS0nj79i0LFy4U29oNXE5ODllZWdK/dTqd1MZTU1NZv349ZcqUoXPnzlhaWtK4ceOiKqrwO/Lz81m+fDk2NjaMGDEC+DAuLl++PHfv3iUuLq5QEMfIyIiOHTuyYMEC+vTpQ05ODjY2NkyYMEEab4mAjyD8tfTvSxqNBpVKhUwmo3LlyowZMwaNRsOxY8ewtbWlb9++0llb+gklsTvAsD158oS4uDiaNWv2Lz9X8D03NzeXa9eucejQIcqVK4erqyvLli2T/kZEH204ZDIZMpmMyMhIpk6dyrZt29BoNPTq1Ys6depQr149hgwZglKpxN7enqioKBo3bkxycjLDhg3j9evX1KpVS6r/7du3s2jRIhHwMXBJSUmkpKRIuzD16foiIiIYMWIEGzZsAKB79+7SwnYQAT1DJ5fLycvLY+XKldy7dw9PT09pQ0Hv3r1ZuXIlixcvJikpiaZNm/Ls2TO2bt2Ki4uLtHBdEP6vFZugj37AsmTJEiZOnMjSpUsB6NKlC25ublSqVImdO3dia2tLjRo1MDIyQqvV8vLlS8qUKUOpUqWka7m4uNCpUyd8fHx+E2EVipZ+a+SwYcNITk7m3bt3ODk50ahRI0JCQoAPLzovXrzg9evXaDQatm3bhq2tLfXr1wfE1khBMBS7du3iwYMHzJkzh7Jly2Jtbc38+fM5f/68tLunZ8+eVKlShaNHj2JlZUWHDh2knQTC35N+h0jTpk1p27Yt5cqVK+ISCb/HxsaG6tWrc/ToUXr16oWzs7P0rK1atSpmZma8fPkS+HDeGvxjUlIwLDKZDFtbWw4fPoxOp+Pq1asEBwfTv39/jIyM2LFjB25ubgwcOFCaVGrfvj1WVlbcuHGDUqVK4e3tXSh3uSAIfx19u8vOzmbGjBnExcVJqc0rV65McHAwMTEx7N27F+A3gR+xO8Bw3bt3jyFDhjBhwgRyc3MxMTH5Q++1JiYmTJkyhUGDBmFubo6NjQ0ymUz00QZKpVJhbW3NzJkzCQkJ4cCBAygUCnr37s306dOlxclubm6ULl0anU5HfHw8xsbGhc4sPnPmDLGxsYSGhoo2bEA+1WZr1qyJmZkZ+/fvx8vLC1NTUynw061bN6ZNm8a2bduwsrKiY8eOKJVKtm3bJp3RJILyhuvOnTv88ssvPHnyhJSUFOnnTZo0QSaTsWfPHubMmSONv52dnYmNjf3NggxB+L8iS0tL0/3+xwxDwYFLSEgIly9fZtSoUfTp04fTp08zb9483N3d+frrr2nUqBEPHz5k8eLFlCxZkujoaLEDxIDp61an0xEaGkpKSgq+vr44Ojqya9cuLl68iJOTE8uXL+f06dMsW7aMzMxMLCwssLKyYt26ddL3Rf0KgmFYtmwZly9fZsWKFVhaWko/X7x4MQcPHsTDw4N+/fphb28vViIKgoHSv5C8ffuW0aNHY2Jiwty5c3FxcQE+rEqePHky/v7+tGvXrohLK/wRycnJLF68mBMnTlCyZEn279+Pqakpb968YevWrezevZsJEyZIaTg/RUwmCsJfT/+ek5WVxaBBgzAzM8PV1ZUXL14QFxfHokWLqFGjBk+fPiU2NpbExER69epFnz59Cl1n586dREdHi8lEA6JWq1m4cCGXLl1i165df2pM/KkzXsRkomHSv++8f/+enTt3cuvWLa5du4aNjQ3+/v7S+R8A165dQ6lUolKp+Pbbb9FoNHzzzTfS38bZs2dRKpW/uytM+Ovox0b5+fk8e/YMKysrSpUqhUqlIiwsjMTERAYPHkzr1q2l7+zdu5cbN26QkpLC27dv2bx5M4mJiYSEhDBgwAB69OhRhHckfOxTfeu1a9dYuXIl9+/fJyoqirZt20q/S0lJITExkefPn1OqVCk+++wzKSWcGEcLf4ViEfT5Z5OB48eP59KlSwQHB/P1119z5swZ1q1bx6NHjzA1NcXCwgJHR0dWr14t5VAUgx/DlZOTw3fffcfdu3epW7cuXbt2BSA7O5ujR4+yYcMG2rZty5gxYzh58iRv375FJpPRv39/seJUEIrYp/rXBQsWcPbsWQ4fPgxAXl4exsbGAAwfPpynT5/Spk0bfH19pd0fgiAYJo1Gw/Xr14mOjiYzM5OOHTsil8u5ceMGOp2OdevWicBtMVDwAPCHDx+i1Wrp0aMHAQEBAP808CMW1QiCYdBoNEybNo33798TFhaGo6MjO3fuZNGiRZQoUYLo6Ghq167N06dPWbx4MXfu3CE0NFSahEpISGDGjBl06NBBHAhuYKKjo9mzZw+hoaEsWrSIsLAwWrZs+Ye+W7CPFu/Ehi03N5chQ4Zgbm5Oq1atsLe3Z+PGjeTm5tKjRw969+5NWloaYWFh/PTTT1LWmiVLlog5DwNWMCg/atQo4uLiyMjIoG/fvnh7e/Pu3TtCQ0MxNTWlXbt2eHh48PjxYxYvXkyDBg3o168f3bt3JyoqiubNm/Ps2TNx5qmBKXgUxatXr0hJSaFu3boolUru3btHbGwsycnJBAcHS5kPPjWXLRa7Cn8lgw/66BtWbm4uly9fRq1WU6JECZo0aQJAaGgoZ8+eZezYsXz99dckJCTw5MkTXr16hbOzM02aNEGhUIiHYzFw6tQpJk+eDMDUqVP56quvCqUwWLhwITdu3GDr1q2YmJgU+q7oOAWh6BRsf7/++iupqak4OzuTmZnJuHHjaNGiRaH0jEqlkvDwcC5evEiVKlWIiorC1ta2KG9BEIQ/QKPREB8fz+rVq3nw4AFmZmZUrFiRyZMni7MDipmbN29iZGTEnj17uHr1Kl999RVDhw4F/hH42bt3L8OGDWPQoEFFXFpBEPTS0tIYOXIkX3/9Nd27dyc9PZ1ly5aRnp5OQkICL1++ZPHixVSvXp1nz56xf/9+goKCCvXNSUlJODg4FOFdCP+Ml5cXb9++xdbWlsWLF+Pi4vK7QfeCv9+1axdarZZevXqJuQ8DUrCOLl++TFRUFLNnz6Z27doAZGZmMnv2bJ4+fUrv3r3p1asXaWlpPHr0CAsLC6pWrSp2BxgorVYrnW+oVqsZOnQoxsbGdOjQgadPn7Jr1y66detGUFAQ7969Y/Xq1Vy6dImcnBwsLS0pW7Ysq1at4uXLl4wbN44ZM2ZIfxeC4fg4qPf27VtSU1NxcnKiZ8+e9OnTh2fPnrF48WISEhIYO3asFPgRhKJk0E8MnU4nnfHi6+tLTk4OqampaLVamjVrxvjx45k9ezaTJk0iNjYWgE6dOkkBIT2NRiMejgbo4wFskyZNCAsLY8GCBdIEhH41S4kSJejVqxcHDhzg0aNH1KpVq9C1xCSTIBSNgod4h4WFce/ePV6/fo2joyNmZmZUq1aNixcvYmRkRHBwMEqlkszMTPLz8xk+fDitW7cWAR9BKAIFJw7+6C4OhUKBi4sLERERvH//HjMzM2n3npiIKB70dV2nTh0ArKys0Ol0HDp0CJ1OR2BgIC4uLnh6epKdnc2FCxcKne8jCELRysvLIz8/n/fv3wMfzua5ePEi8+bNIz8/n6FDhzJx4kS8vLzo27cvwcHBwIf3Yf2ZPiLgY3j0iyYyMjLIz88nKyuLu3fv4ujo+C9TmBf8uT5t35QpU8Tz2IDox0f6/83JySE9PR07Ozvgw84fCwsLQkNDGTVqFN988w06nY7u3bvTsGFD6TparVbUqwF59+4d9vb2UqYLlUpFQkICZcqUwdPTkypVqgBQqlQpVq5ciU6nY/jw4UyfPp3k5GTu3LmDtbU1DRo0AJAWNjs7OxfZPQmfpu+fdTods2bNwtjYmEmTJuHo6MjGjRvZsWMHL1++ZMKECQwfPpwVK1awaNEicnNzReprocgZbK4zjUaDTCZDo9GwYsUKbGxsmDNnDmvXrmXSpEncvHmTiRMnkpKSwpw5c2jSpAlLly5lz5495OTkFLqWCAgYHrVajUwmQ6vVolKpUKlUmJiY0LVrV0aOHMmpU6dYtWoVgDS4iYuLo0yZMtIASRCEoqd/0YyJieHnn39m5MiRrFu3jqlTpyKTybhy5QqfffYZBw8eZNCgQYSEhDBp0iQuXrxIw4YNRcBHEIpAUlISe/bskQ4c/TMT+lqtFoCSJUtKAR/9Ih3BsOh0v93M/3Fdu7i44OfnR6NGjThy5AgrVqwgKSmJR48eMWDAAFatWiWdFSEIwl9Lo9H85me2trZ07tyZJk2acOfOHdatW8eECROoUaMGrq6u2NjYoFQqOXnyZKHvKRQKEbw1QPq+VR/wGTFiBHv27MHBwYHY2FhOnTpFfn7+J/vhggGfHTt2EBMTw5QpU0TaPgOiD9RkZWXh7e3N6dOnqVy5MgCnT58GwMTERAr8eHt78/79e7Zs2cKZM2cKXUscU2A4fv31V0aNGsVPP/0k/Wz+/Pn06dOHy5cvY2ZmJv18wIABDBs2jO+++44VK1YQFxeHk5MTzZo1Q6vVEh4ezvjx4zl//jyRkZEi5bkBUigUqFQqtmzZQm5uLr169aJVq1ZUq1aN2bNn07lzZy5fvsz+/fupXbs23t7eGBsbS21cEIqSwb6h6xvW4cOHefr0KY0bN6Z69eoAVK5cmQoVKjBu3DgWLFjArFmzWLBgAYGBgVy5ckWkoTBw+p1XWVlZREZGkpCQQEZGBlWrVmXQoEFS/vjo6GgSEhL44osvkMlkbNu2jVKlSuHk5FTEdyAIQkHv37/n7t279O7dm+bNm6NUKnn+/Dnx8fH079+fBg0a0K5dO06fPk1ycjJOTk6MGzeOsmXLFnXRBeF/Um5uLuvXr+fly5d4e3uzbds2PD09/9Dqb7lc/psVx2Ii0bAkJydjZmZGiRIl/tDnXVxc8PX1RSaTsXv3btavX0/t2rVZvXq1tEBHTDYJwl+rYIrz69evk5GRgbW1NY0bN8bb2xuAzZs3U7FiRSmFzIMHDyhVqhSzZ8/G2dlZChSIPtow6etYo9GgVqvR6XQ0b96cEiVKsGHDBgYOHMjChQuRyWS0bt0aIyMjqT4/DvjExsYyadIkEfAxIPpnp1qtZtOmTVhbW1O2bFns7Oz46quv2LBhA3Z2dnTu3FlKXf/u3Ts+++wzatWqVegweMGwKBQKevToQb169aR2HBAQQG5uLqdOneLhw4fSe65MJsPLywuAb775hszMTEaPHo2lpSXv3r0jKSmJSpUqMXLkSFxdXYvwroR/5ejRo2zatIm0tDS+/vpr4MPuLlNTU0aOHMnLly/ZtWsX/fr144svvqBkyZLSbi9BKEoGG/QBuHTpEvPnzwcolA9Rp9NRs2ZNhg0bxqJFi7h58yZ16tRh5cqVaLVaMcA1YPqHokqlwtfXF3Nzc1q0aEFGRgaPHj1i4MCBLFq0CA8PD+RyOYsWLeLIkSO0atWKUqVKERUVhVwuFxMQgmBAdDod8fHxUkD35cuXDBkyhCZNmtCnTx+WLVuGg4MD06dPBxDtVxCKWOnSpRkzZgyRkZEcPnyYevXqFVqV+K8UHF8dPnwYNzc3qlat+n9ZXOFP+OWXX4iNjWXcuHHUqlXrD4+FXVxcGDJkCI0bN+b169d4eXlJ42nRXwvCX6vg7gB/f3+ysrLIyckhIyODL774gs6dO9O+fXsyMzNJSEjg+vXrmJqasnHjRuzs7ChdurQI2Bq4jxdBvnnzhri4OOrUqUOHDh348ssv2bhxIz4+PsTExKDT6WjTpg1GRkaFzs8rGPDx8PAo2psSCpHL5eTn5zNz5kzu3LlDt27dcHd3B6Br164kJCSwYMEC4uLiaN68OampqRw9epQ6deowfPhwQJxbbIh0Oh0VKlSgQoUK5OXlMXXqVGrXrs2AAQMYPXo079+/Z968eVhZWdGwYUNp3Ozl5UVOTg43btyQ0sJ16NCBzp07i3ouBpo2bUpKSgqbN2/m6NGjNGrUCFNTUynw4+npyfDhw3nw4AFVq1aVNiyIuhWKmkGNAj/ewt6mTRtmzJhBiRIl+P777/n111+Bf6wodXd3Jy8vj7y8POk7+oCACPgYjidPnrB27VrgQ6o2rVbLkSNHkMlkhIWFMXjwYIKCgqR8ptnZ2ahUKnr27Mn48eMxMzPD1taWsLAwaTWUeIERBMOhVCopWbIkr1+/5smTJ/j6+tKwYUPCwsKwtrbmxYsXPH/+XPq86J8FoWgpFAqaNm2KXC5HpVJhYWHxh56rH58dEBkZyatXr/6viyv8QWlpaURFRWFvb0/t2rWlutKn5Ps9Tk5OtG3bFm9vb+n8AdFfC8JfT787YNKkSZQsWZJ58+axbds2duzYwZUrV9i2bRupqan06dOHkiVLMnr0aMaPH09OTg7z588XC+SKAX1WE39/f5KSkmjVqhV9+/YlOTmZiIgIdu3ahUKhYP369ZQqVYrFixfz3XffoVarCwV8Fi1aJAI+Buzly5fSWS9JSUnSz6tXr05AQABfffUVmzZtws/Pj8jISJRKJSNGjAAKn5sqGI6C46KkpCTi4uI4fPgwu3fvxsHBgfDwcNzd3Zk6dSrXrl0rlJpxyJAhLF++HLlcXmhOS9Sz4XN0dKRHjx54enpy5coVVqxYAYCpqSkACQkJODk5/eYoClG3QlEzmJ0++gioSqXi2rVr5Obm0r59ezp06IBGo2HJkiXs27ePnj17UqlSJQDy8/MpXbr0b1anigGu4dBoNGzcuJHLly8D4Ofnh1wuJyEhgZycHKlTPHHiBCtWrGDs2LGULFmSOXPmMG7cODp27IharZZeYIYNG4aFhUVR3pIgCB+xsLBg8ODBTJ8+naNHj9KxY0dCQ0MxNTUlNTUVpVIpbVcXuzAFoegUbH8qlUp6Jq9cuRIzMzOCgoL+6TP241QyCxcuZMqUKbRv3/4vK7/wr2VlZUlj4zdv3rBv3z5Gjhz5h8fFH/fP4pwmQSg6GRkZxMfHM2DAANzc3FAoFDx58gStVkufPn14/PgxlStXZuPGjVy4cAFzc3OaNm2KQqGQMisIhknf1x44cAC5XE5ERARlypQBoFWrVmzbto2lS5dia2tL27ZtWb9+PR4eHpw9e1ZK33bt2jViYmIIDQ0VAR8D8vGq/kqVKuHr64tSqWTnzp1UqFCBnj17AlClShXc3Nzo378/L1++xMLCgqpVq0pBX9GGDc/H9evi4kJ4eDiLFi1i586dAPTu3ZsZM2Ywbdo0wsLCiIqK4vPPP5e+ow8CiWBA8WNnZye13/3795OcnEy3bt1ITk5m+/bt4vxxwSAZzJNEoVCQnZ2Nr68vb9++JTc3l02bNhETE0Pnzp1Rq9WsWLGCx48f0759ezQaDcePH8fS0lLaOicYHoVCwciRI9FoNBw9epTc3FyGDx+OpaUlKpWKkiVLcurUKaZOncqwYcPo27cvR48e5YcffsDb2xsbGxu6du2KTCZj9uzZGBsbExQUJCaNBcHAtGjRAl9fXzZs2EDJkiV58+YN79+/5/Dhwzx//pypU6cCYpePIBSVgmcHZGZmYm9vj7e3NzqdTlpJDnwy8FNwxbg4O8Bwubi40KJFC3bv3s2JEyewsrIiICAAY2Pj3/1uwYDPTz/9RNmyZf/QGU+CIPx36CcT9W0xJSWFly9fUrJkSRQKBceOHSM8PJyAgACaN29OYGAgHTp0YMCAAXTq1KnQdcRksWHT97WvXr1CLpdTunRp6Tnr7u5Ov379+PXXXzl+/DhNmjTBzMyMAwcOFNq1WatWLVasWEG9evWK6jaEjxRMY3/+/HkyMjLo0KEDlStXZsiQIWg0GqKjozExMaFLly7Ah2evk5NToTOLRRs2TAXr98KFC+Tl5dGgQQPc3NwYM2YMsbGx7NixA/hH4CciIoKRI0eyfv16qlWrJl1LvA8XX/b29lLgZ9OmTRw6dIg2bdpQrlw5QkNDxU5bweAU+dOk4Evmli1bcHBwYOLEibx7945vvvmGESNGsHjxYrp164ZSqWT+/PncvHmTzz77jDp16kgrGEXDMky5ubk4ODgwZswYoqOjOXXqFFZWVrRr144dO3bg6enJs2fPCAoKwtPTE/jwN2Frayvt4DIyMqJz584olUpq1KghHpKCYIBMTU3p378/lpaWrFixghMnTmBsbIy5uTlLly6lXLlyRV1EQfifVfB8iLCwMN6+fYu5uTlDhw6lXr16dO/eHZ1OJ+2qHTFiBGq1GpVKRenSpT8Z8BEriw2Lfhw8btw4du7cSVZWFh4eHuTk5Pxu0KfgWHzbtm0sXLiQb775RgR9BOEvpFAoyM3NZcyYMYSGhlKpUiWqVq3K+fPnSUpKIjo6mmHDhuHt7Y1GoyEnJ4fk5ORPXkcoHmQyGcnJyWg0GoyNjaVJ5cqVK/PFF1+wd+9ecnNzMTExQS6Xo1AopOCgmZmZCPgYkIJnNAUEBBAfH09mZiZbt25l4sSJNGzYkICAAGQyGbNmzQKgS5cunwzuiDZseHQ6nVS/fn5+JCUlkZOTg4WFBXPmzKFevXoEBwdLgR+ZTEavXr2YOnUqmzdvpnLlykV9C8J/kb29Pb169QJg7969GBkZERERASCd8SMIhqJIoyT6XOFqtZqMjAxycnJo1qwZdevWpX379kyePBmdTkdQUBAJCQl07tyZyZMnY2VlRalSpWjbtq00+BEBH8Oj0WgwMTEhPT2drVu3kpKSwuvXr1m5ciX79+/H09MTjUZD2bJl8fT0RKVS8ezZM3bv3k2FChVwcXGRrmVsbEzXrl2pUKFCEd6RIAj/irm5OX379mXbtm1ERkYyZ84cli9fLga6glCE9MGAvLw8fH19SU5Opk6dOqhUKsLCwjh79iz5+fl4eHgQEhLCwYMHGT9+PCNGjGDDhg3SdfQp3UTAxzDp08GcP3+eNm3a0KxZMzZu3MiBAwdIS0v7p9/7OG3f0qVLmTRpErVr1/6LSi4Igt67d+9ISEjgxIkTwIeDo48ePUp0dDQ+Pj74+PgAH84J0Wg0YkFNMaU/36N58+bodDqio6OlgI9+N49CoaBcuXKYmZkVmucQAQHDpD+mIDAwEBsbG+bMmcOWLVvIz89n0aJFXLt2jQoVKuDv70+rVq2YO3cue/bsKepiC3+ARqNBJpOh1WpZvXo1Dg4OLFmyhAULFlC1alXGjx/P9evXqVSpEsHBwTg5ObFr1y42b96Mo6Mj48aNk9JuCn8f+lRvPXv25OzZs8yfPx9ABHwEg1NkO30KrjqdNGkS2dnZ3LlzhyFDhkifqVWrFpMnT2bWrFkEBQWxePFi2rdvj0qlYtmyZeTl5dG/f38+++yzoroN4V/Qr1gbOXIk5ubmdOzYER8fHzZu3MiVK1eoUqUK3bp1Y9u2bfTs2RMzMzO0Wi3GxsbMmTNHeriKgJ4gFC+lS5emdOnSRV0MQRD4EAzIz88nISGBsmXLMn78eJycnNBoNIwePZo5c+ag0+lo1aoV3bt3x9zcnO3bt1O6dGnGjx8PwLFjx4iJiWHy5Ml07969iO9IKKhgfnmlUkmLFi1o0aIFANOnT2fFihXodDq6d++OtbV1oe9+HPARu7gEoWg5OztTv359Tp06hZ+fHwEBAaSlpbFnzx7S0tK4fPkyaWlp7Nq1CysrK5Fis5jS97u1a9emZcuWXLp0iXnz5jF+/HhkMhmvXr3i0qVLVKhQARMTkyIurfBHnT9/XtpxW6FCBZ4/f07lypX55ZdfmDVrFpMnT6Zhw4b4+/vz/v17Tpw4Ie0WEAzLixcvMDExwcnJSZrT2rlzJ0+fPqVDhw7S8RIuLi4sXLiQkJAQ5s2bx+eff05wcDDh4eE8ePCg0DhLpOwzTP/JecP6HT8KhYLVq1cjk8mkdydBMBSytLQ03V/9f6p/Qc3Pz2fo0KGo1Wrc3Ny4e/cuKpWKqKgoatasiUwmQ6PRcOfOHWbPnk1ycjI7duzA1taW7777jhkzZvDll18yefJkMSAyUD/99BPTpk0jMjKSunXrApCSksLatWu5d+8en3/+OV27duXEiROoVCqcnJzw8PAQh5AKgiAIwn+BRqNh/Pjx3Lp1CxcXF1asWIG5uTnwYQHO6NGjuX//PhMnTqRly5YYGxujUqkwMTFBJpORn5/PnTt3SEtLo3Xr1kV8N0JB+vG0SqXi4MGDvHr1Cnt7e8qVKyfVVXh4OMePHycwMLBQ4OefndMkAj6C8Nf4+EBwveTkZPr27Uvfvn3x9/cHYMWKFVy/fp27d+9SqVIlHB0dmT9/vnROm9j9Ufzo++DMzExWrFjBmTNn0Gq12NraolKpKFGiBOvXr0epVP5Hk5LC/x39XIW+flavXs2BAwc4cuQIAIsWLeLRo0cEBAQwd+5ctFotQUFB1K9fn8zMTGxsbJDL5aJ+DUxaWhpfffUVkyZNks5e2r9/P5s2bSIpKYklS5ZQp04dqQ2/ePGChQsX8ssvv0iBn7dv3+Lk5CTq18AVbMP6HV1/9Hmq1WqRyWTIZDIuX77Mo0ePaN26tdiBKxicIgn6wIezXvSpvoKCgnB0dCQxMZFJkyahUqmYMWMG1apVkwI/P/30EwcOHCA8PBwjIyMAjh8/TpUqVShfvnxR3ILwB/zwww+EhoaycuVKqlevTn5+PkZGRqSkpDBt2jTu3LlDQECAdJ6PnniBEQRBEIT/nEql4vvvv2fnzp2oVCrWrFmDjY1NoVQyo0eP5vHjx4wcOZJ27dpJqQnEblvDpZ9EyM7OZvDgweTn52NsbExycjJarZb27dszadIk4B+Bn+HDh9O1a1dsbGyk6+zcuZOYmBgR8BGEIpCTk0NMTAwNGzakRYsWmJiYoNVqiY2N5fnz54SFhVGqVCkAMjIySExMxMrKCjs7OylFulggV3zpn7EqlYrbt29z4cIFdDodpUuXpk+fPiiVSlHHBk6lUrF8+XKCgoK4ceMG69atY9myZRw+fJg5c+awePFiGjZsyMqVK/n222+xsLAgICCAvn37AmKcZaju379PtWrVyM/PJzc3F1NTU3bs2MGaNWuoUKECixYtwtLSUvr8y5cvWbx4MRcuXGD9+vVUq1YNEPVryPTzjdnZ2SxdupTHjx9To0YNPD09pefuP1MwkLd161aOHz/O1KlTcXNz+yuKLgh/SpEFfcaPH8+FCxcoXbo0a9aswd7eHoBXr14RGhr6m8BPwQ5THzgQDN/Lly8ZMGAAgwYNklL36evv2rVrjB07FktLS/z8/Ojdu7dYCSEIgiAI/4FPLZpQqVScO3eO+fPnU61aNWJjYwtNJmm1Wnx8fLC1tWXhwoVFU3DhT9NoNMyYMYPk5GTGjx+Pq6srb9684eDBg2zatIkePXowYcIEACIjIzl8+DARERF07NgRgC1btrB48WKmTJki0kQJQhG4c+cOY8eOxdTUFEtLS4YPH07t2rVJSkpi0KBBTJ8+nXbt2n3yu2Iy8e/hX9WjWARp+J48eYKnpydTp07lq6++4vnz5zg7O+Pl5UWXLl3w8fFBp9OxcOFCUlJSqFy5Mp6enqJeiwGNRoOfnx/W1tZMnz4dS0tLtm/fzs6dO6lUqRIzZszAwsJC+vzTp085fPgww4cPF4FaA1dw4dSgQYMwNzfH1dUVMzMz/P39sbOzkz77cT/8cWrkmJgYQkNDxcIpwWD9ZSNFjUZT6N/jxo2jUaNGxMXF8fPPP5OXlwdA2bJlmT17NmZmZkRERHD79m10Ol2hwZAI+BQf5cqVw9PTk2+++YbDhw8D/6i/+Ph4qlSpwoABA+jZsyeACPgIgiAIwr9JrVZL6b6OHTvG2rVrOXXqFG/evKFDhw6EhIRIk4z6gI9arUYul7NhwwZiYmKK+haEP+nJkyfUrVtX2vXu4uJC37598fLy4sSJE5w/fx6AsLAwAgMDC00gazQaQkJCRMBHEIpIzZo1OXLkCKNGjaJUqVKEhYURHBzMmzdv6NGjB5s2bSIlJeWT3xUBn78HfT3qdDp0ug9rcbVaLVqtVgQGDNDHc1qVKlXCy8uLvXv38uLFC1xdXVGr1eTn50vzGq9fv+bWrVu4u7szcOBAFArFb64jGAZ9G4QP51P37NmTGzduEBMTQ0ZGBv369aNXr148ffqUadOmkZmZKX2+YsWKBAUFSWNrwbDExcXx7t07AGlTwZIlS7C3tyc6OpqIiAgmTZpEZmYmZ8+e5eLFi8CHvwP938WnzsKcPHmyCPgIBu0vCUHrJxZyc3O5efMmycnJlC5dmsmTJxMZGcmSJUuwtbWlTp06KJVKypYty6xZswgMDGTnzp3Url37ryim8H+kX79+vHnzhsjISF6+fEmDBg3Iz89n7969VKlSBU9PTymNnxjcCoIgCMKfp9PpUCqVZGVl4evrS15eHhqNBpVKRcmSJenfvz+9evVCp9Mxb948xo0bR3R0dKEzIT7eWS0YLq1Wy7t373j+/Dk2NjaFUj3Z2tri4eHB3r17efbsGS1atABg8ODBwD/G5YMGDSrKWxCE/3kajQYjIyPat29P+/btOXXqFFevXiUkJARbW1s0Gg3Pnj2T/lu8Jxm2f1ZHfzSThf4zubm5mJmZ/dfLJ/zn9Atrfv75Zxo3bgxAkyZNuHDhAtevX6d8+fJkZWVha2vLyZMnefToEa9evUKhUBRKZy/asuHRt199e9XpdHTr1g1jY2MiIiLQ6XSMGzcOLy8vAPbt28f0/9fenYdVWSb+H38fOKwqoCIIuGGIuZuaouMy5m41qYm7Im6omCiI4r6hpuSGKZkbWo5blltOk5nV2OiYmVOmpmmG+wYo+3LO+f3Rdc5I1kz9vgmIn9c/XZznnKf7uY73fZ7n/tzLrFnMmDEDNze3AufSTJ/i5f79+3Tv3p24uDhatWoF/BS43759G29vbzw9PTl9+jQfffQR27ZtA8DJyYm+ffsyfPhw27+Hnwc+MTExvPTSS0V2XSK/xSNf3s3aeZCRkcHw4cPJzc3l2rVruLu7U61aNSZNmsTMmTPJyMhg8uTJtuAH4ObNm3h6eupHsQRITU1l586dbN68GZPJhLu7Oz4+PqxcuVIbVIqIiPwBTCYTU6dOJTU1lcjISAIDA7lx4wbR0dGcO3eO3bt34+XlxUcffURcXBy+vr6sX79e91mPsaioKJKSkli+fDm+vr4F9n8IDg6mVatWjB07tohLKSL/zc/D9gsXLrB9+3YOHz5MlSpVSEhIKMLSyX+Tm5uLo6Oj7e/s7Gx2794NQO3atalduzb29vb/dUDFg8/BW7Zs4cCBA6xatcq2v54UHxaLheHDh/PNN9/Qo0cPxo4di4uLC+vXr+ett95i69ateHt7c/LkSTZt2kR6ejo+Pj5Mnz69wCAbKV6s905ZWVmsW7eOtLQ0atSoQfv27fHw8OCDDz5g9uzZtG/fnqioKMqUKcOWLVt488036dmzp+6zHgM//PAD/v7+5Ofnc+/ePcqXL8+rr77KV199hZeXF0lJSdy5c4dBgwZRu3ZtDh48yOXLl1m+fDmurq629vvBwEczfORx8MgjaDs7O/Lz84mJiaFMmTKMHTsWT09PkpOTGTZsGHFxcUybNo1Zs2Yxf/58pk6dSv369TEajXh7ewNaz7Yk8PDwYOjQoTz//PPcuXMHR0dHAgICbP8+NBpCRETk/8ZkMvHjjz/y3HPPUaNGDeCnzWgvXrzI5MmTOX/+PMnJyXTs2JGsrCw+/vhjDbh4zLVv3541a9awfPlyxo4di5+fH2azmR9++AGTyWRb9k1Eiq8HwwCz2cxTTz3F+PHjadeuHUuWLOHYsWM0bdq0CEsov+S7775jzZo1jBw5koCAALKzsxkwYADp6emkpKRQsWJFgoOD6dOnj23/vJ8HPz8fPR4fH8/EiRMV+BRTBoOBbt268cMPP/Duu+/y73//mwEDBtCuXTsuXrzIypUrmTx5Mg0bNqRmzZo4OjpiZ2dXYDauFC9ms9k2Uz40NNQ2U/6zzz7jzJkzhIeH2/ZCnD17NgaDgcjISPr06YOnpycdOnQo4iuQ38Lf3x+TycTgwYNp2LAh4eHhBAcHk56ezuXLl2ncuDHdunWzrTJ17tw5fvjhB4xGY4HAZ8mSJUyZMkUzfOSxUSi/Ordu3eL69euEhoZSp04dAL766ivMZjPt2rUjPT2dOXPm8OqrrxIVFcUbb7xBzZo1bZ9X4FNyVKxYkYoVK9r+tv7IioiIyP8/k8lESkoKd+7csS339f777zNnzhxGjBhBx44dmTp1Kr6+vtSuXZtOnTrZHli0pNvjx9pR2KVLF65du8b+/fuJiIigV69epKSkcPToUUqXLs0LL7xQ1EUVkd/Bzs4Os9mMs7MzgYGB3L9/nwsXLij0KYYyMjL4xz/+gclkYsyYMbz77rv4+voSHh6Om5sbCxcuZPfu3ZhMJvr37/9Q8PNrywVp9HjxYR18/OD31qBBA1q3bo2HhwfXr19n+/btlClTBg8PDzIzM/n++++pV68eDg4Otn4s6xK8UvzY2dmRm5vLhAkT8Pb2JioqimrVqjFhwgQOHz6MxWJhzJgxtuBn3rx53L9/n9jYWNtrGqT+eLC3tycsLIzo6GhcXV0ZMmQIs2bNws7OrsBz0I8//sjnn3+Ov78/Tk5OwE+rUO3bt0+Bjzx2CuWXJy8vj+TkZFtF+vvf/87MmTMZPXo0bdu2ZcqUKTRt2pQ5c+aQkJBAQEBAYRRLigF1MomIiPx+P3/AtLe3x9vbm/r167Nt2zYcHR2ZP38+YWFhDBkyBIC0tDTu3bsHUGAUsX6LHz8P7r80dOhQ/Pz8OHjwIPHx8VSpUoXq1asza9Ys24bR6owQeXxY2+SLFy9iNpu5ffu2bSNpzc4setY2tVGjRqxatYoJEyawcuVKDAYDbdu2tQ1enTNnDnPnzmXPnj0ABYIfg8GgwOcxYN3DZ8GCBfj7+zN48GAqV65Mo0aN2LJlC3PnziUlJYX333+f/fv3A1CqVCnq1atXIORRvS1+Hgxdv//+e5KTk5k0aRLVqlXj7t27lCpVCi8vL44fP87KlSt55ZVX6Ny5M9nZ2fztb3/D1dXVdi7dYz0+WrVqZZsdD9CzZ0+8vLw4ePAgmzdvxsnJiYyMDMxmM9OmTbPt5+Pt7c2SJUuoUKFCEV+ByO9TKKGPm5sbrq6unDp1CoBZs2YxatQoQkJCuH//PteuXSMtLQ0fHx/mzJkDKC0XERER+SXWe6SsrCzeeustnJycqF69Oq1ataJPnz7Mnj2befPmMXToUIYMGYLFYiEpKYm0tDTbBqby+LPOCLCzs6Nz58507tyZW7du4eHhgYODg5aTESki/5fn2Ac7Is+cOUOlSpV48cUX1WlcTNy5c4eNGzcydOhQPDw8aNy4McuXL2fixImkpKTQuHFj4Kfv0c3NjZkzZzJ79mz27t0LQL9+/XBwcLCdT4FP8fRgHb5z5w5Xr17l66+/5siRI0RGRvLiiy9y6tQppk+fzqZNm2jSpAlBQUHMnz+fpKQk7VdczFm/37y8PBwcHLh//z7Xr1+nXLlywE/18uLFi8yaNYsdO3bw3nvvYbFYCAkJoVu3bra6qpnyj6dmzZqxfPlyIiIiMBgMDBw4kEqVKlGjRg3S0tKoX78+w4cPx2g0kp+fb2sLFPjI48iQmppqKYz/0Z49e1i4cCH5+fmMHTuW/v37Az9tVDllyhR69erFyy+/rB9IERERkf8hOzubgQMHkp2dTWpqKj4+Prz00kv079+fd955hy1btuDk5MTw4cNJSkris88+Iy8vj/Xr1ysEKMEe7IBQZ4RI4bMGrTk5OZw4cYLbt2/bloL6Xx58Dj548CBXrlzh+eefx9PT8xGXWn6rjIwMhgwZQpkyZZg/fz4bN26kT58+pKSkEB0djZ+fH1OnTuWpp56yfSY9PZ25c+dy7NgxoqOj6dq1KwCbN2/m9ddfJyYmRssFFSPWOpyVlcXatWspXbo0+fn5NGjQgHXr1nH9+nVat27Nc889x/bt2wkICGDw4MEYjUYuXbpElSpVsLOzU79WMWW9N8rMzCQkJITevXvTpUsXpkyZwvTp0/nmm2+IiYlh6dKltGjRgjNnzjB48GA8PDyoW7cuixcv1ndbQhw9epSIiAhCQkIIDQ3FxcWlwHFNRJCSoNCe+jt06MCtW7dITEzk+vXrHDlyhPT0dLZs2YKzs7MtLVfjKSIiIvKwBzvx//GPf+Dn58fEiRPJzMwkMTGRd955B4PBQL9+/fDz8+Ovf/0rsbGx+Pj44O/vz8yZMzEajXqIKcb+Lx0JFoulQMijwEekcD24IXhYWBjp6elcv36d27dv07dvX9tyQL9Uz3++v8uSJUuYP3++Ap9ixsnJifHjxzN37ly6detGgwYN8PLyonLlysyfP5/o6Gji4+MZN24c/v7+AJQuXZpp06axadMmOnXqBMB3333Hzp07mTBhggKfYuTBOjxkyBCys7PJzc3FwcGBe/fusXr1anbs2MHHH3/M3r17qVy5MhkZGVy9epWqVatSrVo1QJ3FxZHZbAZ+ujfKy8tj+/btVKxYkWeeeYZSpUoRGxtLmTJlOHDgAJ06daJFixbk5ORw+vRp6tSpw8iRI2nSpAmgPsuSIigoiPj4eMaOHUtmZiZDhw6lbNmytuOqw1ISFFro4+LiQv/+/fH09GT16tV8+OGHeHh4UKlSJRYtWqQ1x0VERER+hXXkaW5uLnfv3iUpKYkyZcrg4+ODwWBg1KhRJCQksH37dsxmMwMGDKB58+ZcvXoVT09PHB0dtdxXMWf9bsxmMzk5OZhMJhwcHHBycvqfs3Ye7DDevXs3fn5+ts4JESkc1g3Bx40bR9myZYmJiaFixYq4urri4OBAfn4+gK2eW+v0zwOfZcuWMWXKFNq1a1dk1yIPswYC1v1aTCYT6enp5Ofn4+TkROPGjYmLi2PChAksW7asQPBTpkwZwsPDbefy8fFh0aJF2su4mLHW4fHjx1OhQgWio6Nxc3Nj3rx57Nq1C4vFQnR0NM8//zzbt29n8+bNnD9/ns8++4yBAwfazqM+reLjzp07lC9f3tbe5uXlERsby1dffUXnzp1ts/LKlCmD2WwmJSXFdp989epVDhw4QI0aNXj22WcxGAzqsyxhmjVrxmuvvUZiYuJvmpEr8rgp1Kd+FxcXunXrRsuWLUlLS8PR0RFfX191QoiIiIj8CovFYht5OmrUKK5evUpmZiZBQUG2jkI/Pz9Gjx7NqlWreO+998jJyWHo0KH4+fk9dB4pfkwmk+07njdvHteuXSMlJQV/f3+GDBlC/fr1f/WzvzRDwLpHpogUrnPnzpGcnMycOXOoU6cOWVlZHDx4kC1btuDo6EidOnUIDw+3LSPz8/pr3d9Fsz+KF2tIl5+fT2pqKsOHDwcgISGBV155hfj4eEqXLk3jxo157bXXmDhxIvHx8YSHhz8U7Fj3+3FzcyuKS5H/4ezZs9y7d4/p06dTtWpV7t69i7OzM4GBgRw6dIi8vDymTJnC4MGDeeaZZ/j666/p27dvURdbfkFeXh5bt27FbDYzduxYAJKTk3FwcCA9PZ0rV67Y3mvtj2zXrh2vvfYa3bt3x2Qy4e7uTnR0NAaDAYvFosCnBGrVqhUtW7a0fceaySUlSZGs++Dp6Ym/vz9+fn4YDAbbqBkRERER+Q+TyWS7V5o7dy6lSpVi1KhRtG7dmn/9618sXbrU9l5fX19Gjx5NnTp1ePvtt9m3b1+Bc+khpviyt7cnOzubYcOGcf36dVq0aMGf//xn7ty5w8iRI/nkk0+A/yxPYvVLHcZTpkyxLSEkIo+WdfaOlb29PTk5OXz77bfs2rWLyMhI5s6di4eHB6VKleLzzz/nyJEjwH/adygY+FiXPZfiwWQy2QKfIUOG8Omnn9K+fXu6dOlCTEwMN2/eZOzYsaSnpwPYZvz885//ZM+ePQ+dT7/FxVtKSgrJyck4OjoCsHXrVpKSkhg7dizNmzdn9+7dxMbGcu/ePRo0aMDAgQNtG75L8WIdXP7xxx8THx/PX/7yF27evMmgQYPo2rUrBw8eZNWqVQC2/si2bdsyd+5cWrRowUsvvcSGDRts36/qbsmlwEdKqmKRtGjNcREREZGCrEtIZGdns2fPHoxGI0OHDqVJkyb8+c9/pmLFivz973/H3t7eNoLR19eX4cOHU6lSJbp06VLEVyC/hfUh87333sPR0ZG5c+dSqVIlAC5evMj69euZMmUKa9eupXbt2g99DjRDQKSoWDd8f//993nhhReoWrUq/v7+vPnmm2RnZ+Pr68uCBQt47rnnyMrKonv37ly/fh34zxJQ1vo7efJk1d9ixjr6Pzs7m++++47U1FTWr1+Po6MjPXr0oHnz5kyaNImFCxcSERHB0qVLbbMDtm7dSpUqVYr6EuR3CggIICAgAC8vLw4dOsRbb73F0qVLadiwIWazmX379rF3714yMzOZP3++7XMaxFz8GI1GxowZw40bN9ixYwelSpWiYsWKeHl50bt3bywWC5s3b8bJyYmhQ4cCUL58eTp06ECHDh1s57HOxpaSTYGPlERquURERESKiTt37rBnzx569+5NqVKlyM/PZ/fu3axfv56srCxCQkKAn2ZN9+vXD4vFwv79+wFswU/lypUZMWIEoM2EHwfWh8xLly5hsVioUKGCLdCpXr06oaGhtvBn3rx5ODk5/WrgoxkCIoXv448/Ji4ujlu3bjF69GgWLFjAF198gbu7O1WqVMHT0xOAGzduULZs2QL7Bnz44YcsWbKEKVOmKPApZqxLomZmZhIaGoqLiwtly5bFYDCwZMkS8vLy6NOnDy1atCAmJoaFCxcycOBAnJ2dqVu3LtOnTwfQMvaPGT8/PxYuXIibmxt/+9vf6NSpE82bNycvL49z585Rr149xo0bR61atYq6qPI/WOteWloapUuXxtHRkXfffZeRI0dSuXJlevfuDcC6desAbMHPz+us7qNF5HGluw8RERGRImbtxL916xaHDh0iPz+fnj17cuLECf70pz+RnJzM22+/zTvvvMPkyZMB8Pb2pn///hgMBj744AMyMjJsx6z0oFo8PRjaWIO5nJwccnJycHJyAv7T6fDUU0/xzDPPcPjwYXJzc3Fycnpo03cFPiKF68E63KVLF1JTU3n99dexWCyEhYXRtm1bAI4ePcqRI0dwdnZm27ZtODg40LlzZ9t56taty6JFi2jTpk2RXIf8OutyP0uXLsXJyYlZs2ZRuXJlbty4wc6dO1m+fDkAvXv3pkWLFsycOZM9e/aQl5dX4LdYgc/jx83NjdzcXG7fvo2Pjw8A165d49NPPyUgIIA6depgMBg0sKaYs9Y96z5qa9eu5cCBA1gsFkaOHEmVKlXo3bs3BoOBxMREMjIyGDt2rOqsiJQYas1EREREilhaWhpubm5UqVKFgIAA9u/fz6ZNm6hZsybr1q2jW7du5Ofn8/bbb+Pq6kpERATwU/DTr18/0tPTuXXrltajfgxYwxyTyQT81HkM8OKLL/LRRx+xePFioqKiCnQ6lCpVCi8vLxwcHGyvHThwgCVLljB58mQFPiKF5OedvGazGTs7O/r27YvZbGblypXY29vTv39/HB0dWbduHRcuXMDd3Z1q1aoRFxeHvb29rf77+vri6+tbVJcj/0NeXh5JSUk8/fTTVKtWDfjpO7POrF2xYgUODg689NJLPPvsszz77LO232HN8Hm8OTo60rFjR5YtW0afPn1IT0+nbNmyTJgwwRYIKvAp3qx10bo0bnR0NHFxcbbgZ/To0VSpUsX2/Z4+fVr30SJSouguRERERKQIXbhwgWHDhrFmzRoCAgIIDw8nODjYNssjNzcXHx8fgoODMRgMbNu2DaBA8BMeHo6Hh4c2Ii3mrOvCZ2Zm8uqrr3Ljxg1q1KhBhw4daNy4Md27d+fvf/87FouFCRMmkJWVxa1btzh69Cg1atTA2dnZdi6z2UxcXBytW7cuwisSebJYZ+VFREQwatQoGjRoYAt++vfvD8DKlSsBGDlyJMuXL7ft4ePv74+dnZ3CgMeIvb09rq6u3Lp1q8DrFouF4OBgDh06xOuvv47RaKRbt26231/r0nDyeOvevTseHh58+eWXeHt7ExoaitFoVB1+TDx4L2w2m/Hw8GDChAm89tprHDp0CIvFQteuXbl+/TqhoaFUrlxZ99EiUqIYUlNTLUVdCBEREZEn1alTpzh79iw9e/YkPz+fmzdvsm7dOrKysjh79ixt2rRh5MiRODs7c/36dXbu3Mm2bdsIDg62jTa2snY+SvFj7UTIzs5m8ODB2NnZUaFCBS5cuICHhwdRUVE8/fTTJCQk8N577+Hl5YWLiwu5ubk4OjqSmJiI0WjUdyxSxE6fPs3s2bO5d+8eixcvpk6dOrZ6mZeXx6pVq9i6dSthYWH06tULV1dX22dVf4uvBzvyH+z0feONN9i5cyczZ86kefPmttkdeXl5jBgxgvv373P16lVWrFjBs88+W2Tll0fnwX8PCnweX9b2NyUlhcWLF3P8+HFSUlJ46qmn2Lx5MwaDQW20iJQoCn1EREREioHc3FxGjRrFiBEjaNasGenp6SxevJiTJ08WCH6s+wls2rSJyMhI20a0UnxZO4zMZjMHDx5k165dTJ48mUqVKnH06FHWrVtHZmYmUVFRNGrUiBMnTrBnzx5cXFzw8fGhX79+Gl0sUkR+qRPwyy+/JCEhgUuXLrF8+XLq1KljW/rtyJEjjBs3DoCJEyfy8ssvF0Gp5fewfneZmZmsXbuWlJQUateuTXBwMGazmUGDBpGVlcW4ceNo1aoV8NMs3djYWAYPHsyuXbvIzs627f+jWQIixZO1Pb937x5Hjx4lJSWFnj17YjQaNcNHREochT4iIiIiReTBTvxLly4xY8YMrly5wuzZs2nVqhVpaWksWbKEkydP0rZtW0aMGIGzszPff/89J0+epFu3bgoBHhMmk4mRI0fi6OhI2bJliY2NtR07cuQI69atIzs7m9GjR9OiRYtf/Lz2DxApXNY2Oj8/n7t373Lz5k0CAwNxdnbmzJkzxMXFkZSUxLJly6hbty4Ahw8f5vjx47Rq1YoGDRqojS7mrB29WVlZDBgwgPz8fBwcHLh8+TKdO3dm6tSp3L9/n6ioKG7cuEFgYCBeXl58/fXXlC5dmg0bNrBgwQKSkpJISEgo6ssReaI8GNT81tDml4J8DaoRkZJIoY+IiIhIEcrOzubixYvUrl2b7777joSEBL766itiY2Np1aoV6enpLFmyhBMnTuDv78/Nmzfp3bs3L730EqAH1cfJ4cOHiYqKIjAwkMWLF+Pl5WU7duTIEdavX09ubi4DBgygQ4cORVhSEbEGrRkZGUyYMIFr165x48YNfH19adOmDWPGjOHixYu8+uqrXLp0icmTJ+Po6Mjbb7+Nl5cX8+bNA9RGF2fWzl+z2cwnn3zCe++9x7Rp03BwcOCLL74gNjaW5557zvba+vXrOX36NBkZGVSvXp3IyEjs7e2ZMGECZcuWZdKkSdjb22u2gEghsNbfB9vY37o8m5ZxE5EngUIfERERkSI0adIkjh07xmuvvUbjxo05e/YsCQkJnDx5krlz59K6dWvS09NZtWoV586dw2w28+abb6oT8TF1/PhxwsPDCQkJoVevXnh6etqOHTlyhCVLllCvXj1mzJhRhKUUeXI9OFo8JyeHUaNG4erqSteuXalWrRpbt27l5MmTPP3008yfP5/vv/+ehIQEjh49ipubG5UqVWLNmjVqox8Tubm5xMbGcuXKFWrUqMHkyZNtxw4cOMCcOXNo06YN06ZNw9nZGYD79++Tnp7O/fv32bFjB59++ilr1qzB39+/qC5D5InyYOATFRVFUFAQffv2LXDs1zzYxh87dox69erh4uJSKOUWESlMCn1EREREitDdu3d55ZVXyMnJYfLkyTRp0qRA8GOd8ZObm0tWVhZubm4YDAaNHn+M/etf/2Ls2LEMHjyY4ODgAsHPqVOnqFWrlpZyEylkV69excnJ6aEgdtGiRcTGxlKrVi3s7OzIyspix44d7Ny5k44dOxIeHk5ubi5nz54lNzeXRo0aPTT6XIqv77//ntWrV3PixAm6du1KVFRUgU5ja/DTvn17wsPD8fT05OuvvyYhIYEff/yRcuXKMWPGDAIDA4v4SkSeDNa2NTc3l0OHDpGYmMiNGzeYOHEiXbp0AX49+Hkw8Nm2bRtLliwhISGBRo0aFeo1iIgUBs1nFBERESkk+fn5D/1dvnx5Vq1ahdFoZP78+Rw/fpynn36aUaNG8cwzzzBjxgwOHjyIo6Mj7u7uGAwGzGazOhMfY82aNWP58uUkJibyzjvvcOfOHduxunXrYm9vj8lkKsISijxZrly5wvDhw/nmm28KvJ6UlMS9e/d4+umnsbOzIy8vDxcXF4KDg6lbty4ff/wxmZmZODo6Ur9+fZo0aYKdnR0mk0ltdDFlNpsL/B0QEEBoaChNmjRh+/btHDhwoEBncYcOHZgxYwb79+9n9+7dANSvX5/Q0FCWLVtGfHy8Ah+RQmKxWDAajWRkZBAaGsqWLVuwWCxkZmayaNEidu7cCWBbtvHnn30w8Fm+fDmTJ09W4CMiJZZCHxEREZFCYH1QzcrKYu3atQC2DcI9PDx44403cHBwYMGCBQWCn6pVq/Luu+8WOJfWIX/8BQUFER8fT2JiIomJiaSmphY4rpk+IoWnUqVKREVF0bZtW/Lz80lJSQHA19eXzMxM/vnPfwLg4OBQIPi5cuUKly5deuh8qr/FU35+PnZ2duTm5nLp0iWOHTtGeno6tWrVIiIigpYtWzJ79mwOHDhQ4HMdOnRgxYoVhISE2F5r2rQpgYGBlCtXrrAvQ+SJZTAYMJlMzJs3DxcXF6ZNm8bWrVt58803admyJWvWrPnF4Ofngc/SpUuZOHEi3bp1K6pLERF55DT8SEREROQRsy5FkZ+fz+HDh1mzZg137twhJibG9nrZsmV5/fXXGTFiBMuWLWPs2LE0bdqU2bNnU7ly5aK+BHkEmjVrRlxcHImJibi7uxd1cUSeSCaTCXt7e9q1a0d+fj5jxoyhUqVKjBw5kpo1a1K9enW2b99OuXLlqFOnDg4ODpjNZpKSkqhUqRJeXl5FfQnyG1hnyGZkZPDKK69w9+5dbty4QYUKFWjdujXDhg1j4sSJLF68mNmzZwM/hT1WTZs2BdCyfSJF4MHl2kwmE5cuXSIoKIiAgAAAGjRoQJkyZQB4/fXXcXZ25vnnn39oqU1r4BMTE6PAR0RKPA0TFREREXmEHuxomjNnDmazmaioKPbu3cuCBQuA/8z4qVChAi+//DLnz59n4cKFnDlzhqpVq/7iMhVSMrRq1Yq1a9diMBiwWLTVpkhhs3Yk5ubmYjQaeeqppzh8+DCbN2/G3d2dsLAwzp8/zxtvvMFnn31GTk4Op06dYs+ePVStWpXy5csX8RXIb2Gd4RMREYGLiwsTJkxgz5499OzZk/379zNlyhS8vLwICwujRYsWxMbGsm/fvofOo8BHpHBZLBZb/b116xYGg4GcnBxbXczNzQWgevXqBAcHk5mZycKFC9m7dy/wnzq7fft2BT4ihwd1+wAAEN5JREFU8kTRHYuIiIjII2IdQZ6fn8/cuXNJSUmhYcOGuLi4YDKZWLFiBQCTJ0+2PZSaTCa6d++Ovb19gX0CtKRbyWUNfKxLj4hI4TEYDOTn5zNp0iRq1apFdHQ0gK3Df8yYMUydOpXVq1cTHR2Ns7MzpUuXxtvbm0WLFtn2WVMbXbzcvn0bg8GAp6en7bUff/yRmzdvMmnSJIKCgjAajfj6+pKTk8OLL77ImTNnCAwMJCwsjLS0NN5//31eeOGFIrwKEbG20TExMdSsWZOwsDCaNGnCjh07ePnll/H29iY3N9e2t5q/vz92dnZs2rQJT09Pmjdvzo4dO1i8eDFTp07lL3/5S1FfkohIoVDoIyIiIvKI2Nvbk5OTw+bNm7l16xb9+/fH29sbgOeffx7AFvyEhISQlpbG4cOH6dChA7169QL+ExxJyabAR6ToWCwWLBYLR44cYcSIEURHR2OxWGwjxUeOHEmtWrU4d+4cly9fxtfXlxYtWthCfc3+KF7S09Pp0aMHPXr0YODAgbbg5+bNm9y5cwd/f3+MRiPvv/8+c+bMISwsjFq1avHqq68ybNgwmjZtSkxMjJZWFSkmjEYjdnZ2HDx4kLCwMEJDQzl58iSjRo1i1apVVKxYEYDvvvsOV1dXOnfuzK5duzhx4gTPPvssJpNJgY+IPHF0dyoiIiLyCH311Vfs2rWLmzdvcuPGDdvrbm5uvPDCC9jZ2bFq1Sr27t2Lq6srPj4+9OjRw/Y+BT4iIn8s61KK1hHkDg4OREZGMmDAADZt2sSgQYOYOHEiBoPBNuOnf//+tGjRosB5TCaTAp9iqHTp0ixYsMA2Mys4OBhPT08CAwNxdnbmk08+oUqVKsyZM4dRo0YxePBg0tPTOX36ND/88ANNmzalatWqAJrFJVIEHpz9nJeXh4ODA+PGjSMsLIyNGzcSEhJCeHg4b775Jn379qVHjx7k5eVx4sQJnJyc6NWrF8eOHeP8+fMYjUZ69uyptlpEnjhq9URERET+QD+fmRMUFMSCBQuYPXs2GzduxMfHh+eeew6AMmXK0L17d4KCgjh06BAeHh688MILtj1+9IAqIvLHsnbiW9tYazvr6elJly5d+OKLL+jUqRPe3t5ER0djZ2fHBx98QFpaGmPGjMHDw8N2LoXyxVfLli1ZunQpERERALz88suUL1+e9u3bs2HDBtLS0oiIiKBfv36YzWYuXLhA+fLlqVKlSoHzKPARKVw/b6MdHBwA8PDwoHHjxnzxxRf069ePli1b8tRTT7Ft2zaOHDmCnZ0dNWrUYPLkyZhMJjIyMqhbty6gvbhE5Mmklk9ERETkD2INfLKyskhMTOTq1auUK1eOAQMGEBMTw5IlS3j77bdxcnLiT3/6E/BTp2HVqlUZPHhwgfPoAVVE5I9n3RB85MiRVKtWjZ49e1KzZk1cXV1p06YN0dHRnD171rYUZ1RUFGlpady9exd3d/ciLr38HkFBQSxfvpyIiAgsFgtDhgxhwIABXL58mcuXL5Ofn8+9e/c4ffo0GzZsoEKFCjRt2rSoiy3yRLO20ePGjaNUqVKMHj0aLy8vSpcuTa9evRg+fDjvv/8+3bp1w8/Pj8jISLKzs8nPzyc/P5/r16+zefNmLly4QExMTFFfjohIkTGkpqZairoQIiIiIiVFZmYmoaGhlC5d2rYG+eDBg2nWrBmHDx9m9erVGI1Ghg0bZgt+HlzGQkREHg1rW5uUlMT+/fvZu3cvpUuXpnr16kRERFCxYkWWLl3KsWPHiI+Pp0KFCrbPWkefa7mvx8/Ro0eJiIggJCSE4cOHc/XqVTZt2sRnn31GTk4O5cqVw8/Pj/j4eIxGo/bSEykCD9a71NRUNm/ezOeff05qaiqNGjVi0KBBBAYGsnLlSk6ePMnMmTOpVKkSAPn5+Zw+fZrp06fb7r3nzZtHYGBgUV6SiEiRUugjIiIi8gexWCzEx8fz5ZdfsmDBAvz8/EhPT6d06dK29/z73/9m0aJFODs7079/f9tSbyIi8mhYOxN/HrAnJyezZ88eDhw4wLVr1/jLX/6Ci4sL58+f54UXXqBt27a2/SRA+7s8zh4MfoYMGYK9vT13797l/PnzeHt7ExAQUGBJKREpPNZ6l5WVxdq1a3FwcMDT05Nu3bqxfft2Dh06xJkzZ+jXrx9ZWVmcPn2aESNG0KxZswLt8ocffoi3tze+vr4FQnsRkSeRQh8RERGRP4jJZGL8+PG4ubkRGxsL/KeT8O7du6xfv57g4GCSk5OZMWMGLVq0YMqUKUVcahGRkssa+GRmZrJ27VqSkpKws7OjdevWdO3a1dZZuG7dOk6dOsW3337LvXv3aNiwIatXry7i0ssfyRr8DB48mJ49ez7UKaxQT6TwWetdRkYGQ4YMITs7m7y8PMxmMx07diQyMhKAv/71rxw6dAiTycS3335LYGAgGzduVJ0VEfkVGsIiIiIi8gexWCw4Ojpy9+5dcnNzcXR0xM7Ozja6/KuvvrKtTx4bG0u9evWKusgiIiWadZ+1kJAQypQpg7u7O0ajkblz5/LJJ58waNAg6tevz9ChQ7l+/ToXL15k2bJlgEKAkiYoKIj4+HgiIiLIyMhg2LBheHh42I7ruxYpfNY9fMaPH0+FChWIjo7G3d2d2NhYdu3aRUZGBtOnT6dfv34EBQVx8+ZNli9fXmAWvYiIPEyhj4iIiMj/h19a899oNFKrVi0SExP59NNP+fOf/4yDgwMGg4Fy5crh4uJCRkYGAA0bNvzV84iIyB9nw4YNODg4MGvWLCpVqoSdnR0LFy5k9+7dDBo0iIyMDEqVKkXFihXx8fGhVq1aeHh4aA+fEqhZs2bExcWRmJiIu7t7URdHRICzZ89y7949pk+fTtWqVbl79y7Ozs4EBATwr3/9izlz5jBjxgyqV69O9erVadSoEQ4ODmqjRUT+C4U+IiIiIr+Tde3x7OxsDh06RGpqKq6urnTs2JGhQ4fyzTffsHjxYgDatGmDo6MjP/74I/n5+fj6+hY4lwIfEZE/1s/D9EuXLuHr60uVKlUA+OCDD9i1axcREREkJydz/vx5Xn75Zdv7y5UrB2imT0nVqlUrWrZsicFgeGifJxEpfCkpKSQnJ+Po6AjA1q1bSUpKIjIykr1797Jv3z6MRiPh4eG4u7vj5OQEqI0WEflvFPqIiIiI/A4WiwWj0Whbezw/P5/c3Fzu37/Ptm3b6NevHzNnzmTatGnMmTOH2rVrU758eS5evIjRaKR3795FfQkiIiWWNfDJzs7mzJkzPPPMMzg7O3PlyhUADh48yMyZMxk1ahR9+vRh48aNbNmyheeee67AUl+g5b5KMgU+IsVHQEAAAQEBeHl5cejQId566y2WLl1Kw4YNMZvN7Nu3j927d5ORkcG8efNsn1MbLSLy6xT6iIiIiPwOBoMBk8nEzJkzcXNzY8qUKXh6elKqVCk6duzIpk2baNSoEStXrmTjxo18++235OTk0KJFC0aPHo3RaNSSbiIij8CDgU/Pnj2pXbs2zzzzDDVq1ODw4cO8+uqr7N69m/DwcAYMGADA3bt3qVixIh4eHgoAnjD6vkWKBz8/PxYuXIibmxt/+9vf6NSpE82bNycvL49z585Rr149xo0bR61atYq6qCIijw2FPiIiIiK/wYMjgnNzc7l27Rpdu3alatWq2NnZceTIEdLS0hg3bhwXL17EbDYTEhKCyWTCYDDYRiNal4YTEZE/lr29PTk5ORw/fpzAwEBCQ0MBGDhwIMeOHeO9996ja9eu9O3bFzs7O5KSkjh16hQBAQEKAEREipCbmxu5ubncvn0bHx8fAK5du8ann35KQEAAderUsQ280sApEZH/TT0OIiIiIv+DNajJy8vj3r172Nvbc+XKFezt7bGzs+PDDz9k+vTphIWF0bVrV8LCwnj66aeJiop66MFUgY+IyKMzY8YMPvnkE/z9/W0dhwDz5s1j6tSp/OMf/2Dq1Kk4OTnx/fffY2dnR0xMDICW+xIRKUKOjo507NiRZcuW0adPH9LT0ylbtiwTJkywLcmowEdE5LdRr4OIiIjIf/HgHj4jRoygR48ePP/88zRu3JijR4+Sl5fHypUrGT16NAMGDLCNQszKyirqoouIPHEiIiK4f/8+//73vzly5Ajt2rXD0dERNzc3VqxYwbp16/jhhx/Izs6mTZs2DBs2DKPRqFmYIiLFQPfu3fHw8ODLL7/E29ub0NBQtdEiIv8f1GKKiIiI/ArrqG+TycRf//pXHB0dqV27Ns7OzrRr147Y2FiOHj1K//79CQkJAeDy5cukpaVRpUqVIi69iEjJZu0EtLbVZrMZX19fZs2aRWRkJAkJCXh5edGwYUPb6PChQ4c+dB6TyaTORBGRYsDZ2ZkuXbrQuXNn28xLBT4iIr+fITU11VLUhRAREREprkwmE8OHDycnJ4c2bdowYsQI27Ft27axZMkSWrduTcuWLcnLy2Pfvn2YzWbWr1+vB1QRkUfEuq9DZmYm69at48qVK5QtW5bGjRvToUMHbt68yfjx48nJyWHKlCm24EdLuImIiIhISafQR0REROR/+Pzzz4mMjKROnTrMnTsXPz8/27Hdu3fz8ccfc/LkSapWrYqvry+xsbEYjUZtNisi8ghYg5vs7GxCQkKws7PDw8OD9PR0zp07R69evYiMjOTWrVtERERgMpmYPHkyDRo0UJssIiIiIiWeQh8RERGR3+D48eOEh4fTq1cvQkJC8PT0tB3Lzs7m/v37uLq6UqpUKQwGg5aiEBF5BB5cyu2DDz5g+/btzJo1i2rVqnH79m0OHDjA66+/TnBwMOPHj+fmzZtERkZy/fp1EhISqFmzZlFfgoiIiIjII6WeCBEREZHfoEmTJsTHxzN27FhKlSpFz549bcGPk5MTXl5etvdaLBYFPiIij4B1n7WwsDAcHR0pW7Ys1apVA6BChQr06NEDi8XCihUraNSoEW3atCEuLo7Vq1cTEBBQtIUXERERESkEdkVdABEREZHHRbNmzVi+fDkbNmzgnXfe4c6dOwAP7Q+h/SJERB4de3t7Bg8ezJdffsnFixe5ffu27ZizszPt27fH39+f7777DgBfX19mz56Nvb09JpOpqIotIiIiIlIoFPqIiIiI/A5BQUHEx8eTmJhIYmIiqampRV0kEZEnTsuWLVm1ahU3btzgo48+IjMz03bM29sbZ2dnkpOTH/qc9vQRERERkZJOoY+IiIjI79SsWTPi4uI4c+YM7u7uRV0cEZEnUuPGjVm2bBkrVqxgz549tpDnwoULZGZmUrVq1SIuoYiIiIhI4TOkpqZairoQIiIiIo8j64bi1v+KiEjhO3LkCOPGjcPf359KlSqRnJxMXl4eGzZs0P5qIiIiIvLEUegjIiIi8n+gwEdEpOgdP36c8PBw6tSpQ6dOnejduzcA+fn5Cn5ERERE5Imi5d1ERERE/g8U+IiIFL0mTZqwYsUKzpw5Q0pKCmlpaQAKfERERETkiaPQR0RERERERB57TZs2ZenSpWzcuJE1a9Zw9+7doi6SiIiIiEihU+gjIiIiIiIiJUJQUBBxcXHs27cPOzs97oqIiIjIk0d7+oiIiIiIiEiJkpWVhYuLS1EXQ0RERESk0Gnok4iIiIiIiJQoCnxERERE5Eml0EdERERERERERERERKQEUOgjIiIiIiIiIiIiIiJSAij0ERERERERERERERERKQEU+oiIiIiIiIiIiIiIiJQACn1ERERERERERERERERKgP8HgKlkGkwLsoAAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 1800x720 with 3 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import missingno as msno\n",
    "msno.bar(train, color='magenta')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 683,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 0
    },
    "id": "g0NW0ot1zmEc",
    "outputId": "13e4d1de-3e83-4644-e5be-24f921b98d3e"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 683,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1800x720 with 3 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import missingno as msno\n",
    "msno.bar(test, color='crimson')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "vpjnR_0T1SKi"
   },
   "source": [
    "## Treatment of Missing Values\n",
    "\n",
    "* Treatment of Missing Values is very Important Step in any Machine Learning Model Creation \n",
    "* Missing Values can be cause due to varios reasons such as the filling incomplete forms, values not available, etc\n",
    "* There are so many types of Missing Values such as \n",
    "     * Missing values at Random\n",
    "     * Missing values at not Random\n",
    "     * Missing Values at Completely Random\n",
    "* What can we do to Impute or Treat Missing values to make a Good Machine Learning Model\n",
    "    * We can use Business Logic to Impute the Missing Values\n",
    "    * We can use Statistical Methods such as Mean, Median, and Mode.\n",
    "    * We can use ML Techniques to impute the Missing values\n",
    "    * We can delete the Missing values, when the Missing values percentage is very High.\n",
    "    \n",
    "* When to use Mean, and when to use Median?\n",
    "    * We use Mean, when we do not have Outliers in the dataset for the Numerical Variables.\n",
    "    * We use Median, when we have outliers in the dataset for the Numerical Variables.\n",
    "    * We use Mode, When we have Categorical Variables."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "Y6TzWaRW3r2_"
   },
   "source": [
    "## Analysing Target Column"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 684,
   "metadata": {
    "id": "UXSStiNdzmHS"
   },
   "outputs": [],
   "source": [
    "target = train['is_promoted'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 685,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 0
    },
    "id": "8HaqLwq1zmKh",
    "outputId": "6c94e9f3-6131-46c7-fabb-e978a96032e9"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1152x360 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "# Define the labels and sizes for the pie chart\n",
    "labels = ['Not Promoted', 'Promoted']\n",
    "sizes = [50140, 4668]\n",
    "\n",
    "# Define the colors for each category\n",
    "colors = ['#ffa600', '#003f5c']\n",
    "\n",
    "# Create the pie chart with a shadow and explosion effect\n",
    "fig1, ax1 = plt.subplots()\n",
    "ax1.pie(sizes, colors=colors, labels=labels, autopct='%1.1f%%', startangle=90, pctdistance=0.85, shadow=True, explode=(0.05, 0))\n",
    "\n",
    "# Add a circle in the middle to create a donut chart effect\n",
    "centre_circle = plt.Circle((0,0),0.70,fc='white')\n",
    "fig = plt.gcf()\n",
    "fig.gca().add_artist(centre_circle)\n",
    "\n",
    "# Add a title to the chart\n",
    "ax1.set_title(\"Target Distribution\", fontsize=16)\n",
    "\n",
    "# Set the font size for the labels\n",
    "plt.rcParams['font.size'] = 14\n",
    "\n",
    "# Remove the unnecessary border lines\n",
    "plt.rcParams['axes.spines.right'] = False\n",
    "plt.rcParams['axes.spines.top'] = False\n",
    "\n",
    "# Add a legend and adjust its position\n",
    "plt.legend(labels, loc=\"best\", fontsize=12)\n",
    "\n",
    "# Equal aspect ratio ensures that pie is drawn as a circle\n",
    "ax1.axis('equal')\n",
    "\n",
    "# Display the chart\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "MBXjErO9hzX5"
   },
   "source": [
    "## Treatment of missing values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 686,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "XdOXGPmYzmNp",
    "outputId": "cb36446d-4040-475a-af99-1866057d82ab"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Number of Missing Values Left in the Training Data : 0\n"
     ]
    }
   ],
   "source": [
    "# lets impute the missing values in the Training Data\n",
    "\n",
    "train['education'] = train['education'].fillna(train['education'].mode()[0])\n",
    "train['previous_year_rating'] = train['previous_year_rating'].fillna(train['previous_year_rating'].mode()[0])\n",
    "\n",
    "# lets check whether the Null values are still present or not?\n",
    "print(\"Number of Missing Values Left in the Training Data :\", train.isnull().sum().sum())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 687,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "ymISRYxozmQ1",
    "outputId": "b69776a8-c4a8-425e-c452-e78236106925"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Number of Missing Values Left in the Training Data : 0\n"
     ]
    }
   ],
   "source": [
    "# lets impute the missing values in the Testing Data\n",
    "\n",
    "test['education'] = test['education'].fillna(test['education'].mode()[0])\n",
    "test['previous_year_rating'] = test['previous_year_rating'].fillna(test['previous_year_rating'].mode()[0])\n",
    "\n",
    "# lets check whether the Null values are still present or not?\n",
    "print(\"Number of Missing Values Left in the Training Data :\", test.isnull().sum().sum())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 688,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "JNDyGqyT8UoI",
    "outputId": "19101e34-e622-40dd-e1b6-8ca5f11e972e"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Bachelor's          39078\n",
       "Master's & above    14925\n",
       "Below Secondary       805\n",
       "Name: education, dtype: int64"
      ]
     },
     "execution_count": 688,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train['education'].value_counts()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "lXzaIGjHiZP7"
   },
   "source": [
    "## Outlier Detection\n",
    "\n",
    "The presence of outliers in a classification or regression dataset can result in a poor fit and lower predictive modeling performance. Instead, automatic outlier detection methods can be used in the modeling pipeline and compared, just like other data preparation transforms that may be applied to the dataset."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 689,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 0
    },
    "id": "N_s_g9J2zmTl",
    "outputId": "f8691d37-5f65-4781-ff18-c5fca2eac00a"
   },
   "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>employee_id</th>\n",
       "      <th>no_of_trainings</th>\n",
       "      <th>age</th>\n",
       "      <th>previous_year_rating</th>\n",
       "      <th>length_of_service</th>\n",
       "      <th>awards_won?</th>\n",
       "      <th>avg_training_score</th>\n",
       "      <th>is_promoted</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>65438</td>\n",
       "      <td>1</td>\n",
       "      <td>35</td>\n",
       "      <td>5.0</td>\n",
       "      <td>8</td>\n",
       "      <td>0</td>\n",
       "      <td>49</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>65141</td>\n",
       "      <td>1</td>\n",
       "      <td>30</td>\n",
       "      <td>5.0</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>60</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>7513</td>\n",
       "      <td>1</td>\n",
       "      <td>34</td>\n",
       "      <td>3.0</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>50</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2542</td>\n",
       "      <td>2</td>\n",
       "      <td>39</td>\n",
       "      <td>1.0</td>\n",
       "      <td>10</td>\n",
       "      <td>0</td>\n",
       "      <td>50</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>48945</td>\n",
       "      <td>1</td>\n",
       "      <td>45</td>\n",
       "      <td>3.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>73</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   employee_id  no_of_trainings  age  previous_year_rating  length_of_service  \\\n",
       "0        65438                1   35                   5.0                  8   \n",
       "1        65141                1   30                   5.0                  4   \n",
       "2         7513                1   34                   3.0                  7   \n",
       "3         2542                2   39                   1.0                 10   \n",
       "4        48945                1   45                   3.0                  2   \n",
       "\n",
       "   awards_won?  avg_training_score  is_promoted  \n",
       "0            0                  49            0  \n",
       "1            0                  60            0  \n",
       "2            0                  50            0  \n",
       "3            0                  50            0  \n",
       "4            0                  73            0  "
      ]
     },
     "execution_count": 689,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Lets first analyze the Numberical Columns\n",
    "train.select_dtypes('number').head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 690,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 0
    },
    "id": "vtwXIwgUzmWp",
    "outputId": "8b222635-0fe3-4c8e-95dc-ede7673b3a09"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x360 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# lets check the boxplots for the columns where we suspect for outliers\n",
    "plt.rcParams['figure.figsize'] = (15, 5)\n",
    "plt.style.use('fivethirtyeight')\n",
    "\n",
    "# Box plot for average training score\n",
    "plt.subplot(1, 2, 1)\n",
    "sns.boxplot(train['avg_training_score'], color = 'red')\n",
    "plt.xlabel('Average Training Score', fontsize = 12)\n",
    "plt.ylabel('Range', fontsize = 12)\n",
    "\n",
    "# Box plot for length of service\n",
    "plt.subplot(1, 2, 2)\n",
    "sns.boxplot(train['length_of_service'], color = 'red')\n",
    "plt.xlabel('Length of Service', fontsize = 12)\n",
    "plt.ylabel('Range', fontsize = 12)\n",
    "\n",
    "plt.suptitle('Box Plot', fontsize = 20)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "r82qOjFsitxI"
   },
   "source": [
    "From the above box plots we can see that we have outliers in our Length of Service column. Let's handle this outliers in the next step"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 691,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "0tM2IOc68h89",
    "outputId": "433711ce-256a-443f-fa23-69528dc2e770"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Bachelor's          39078\n",
       "Master's & above    14925\n",
       "Below Secondary       805\n",
       "Name: education, dtype: int64"
      ]
     },
     "execution_count": 691,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train['education'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 692,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "WiuAXbNV8kSO",
    "outputId": "db54814b-eecb-4dad-bca9-22c344437de8"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "37       1\n",
       "34       4\n",
       "33       9\n",
       "32      10\n",
       "30      12\n",
       "31      20\n",
       "29      30\n",
       "28      30\n",
       "27      36\n",
       "26      41\n",
       "25      51\n",
       "22      61\n",
       "23      65\n",
       "24      70\n",
       "21      78\n",
       "20     128\n",
       "19     329\n",
       "18     392\n",
       "17     432\n",
       "16     548\n",
       "14     549\n",
       "15     593\n",
       "13     687\n",
       "12     794\n",
       "11     916\n",
       "10    2193\n",
       "9     2629\n",
       "8     2883\n",
       "1     4547\n",
       "6     4734\n",
       "7     5551\n",
       "5     5832\n",
       "2     6684\n",
       "4     6836\n",
       "3     7033\n",
       "Name: length_of_service, dtype: int64"
      ]
     },
     "execution_count": 692,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train['length_of_service'].value_counts().sort_values()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 693,
   "metadata": {
    "id": "syfxlTCgihr9"
   },
   "outputs": [],
   "source": [
    "# lets remove the outliers from the length of service column\n",
    "\n",
    "train = train[train['length_of_service'] <= 16]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 694,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "dbYm2GRf9H01",
    "outputId": "389ce7c7-d080-40e0-f8c1-331dca9571d3"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Bachelor's          38194\n",
       "Master's & above    14010\n",
       "Below Secondary       805\n",
       "Name: education, dtype: int64"
      ]
     },
     "execution_count": 694,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train['education'].value_counts()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "nzLqgLeCi95U"
   },
   "source": [
    "## Univariate Analysis\n",
    "\n",
    "Univariate analysis is perhaps the simplest form of statistical analysis. Like other forms of statistics, it can be inferential or descriptive. The key fact is that only one variable is involved. Univariate analysis can yield misleading results in cases in which multivariate analysis is more appropriate.\n",
    "\n",
    "* This is an Essential step, to understand the variables present in the dataset one by one.\n",
    "* First, we will check the Univariate Analysis for Numerical Columns to check for Outliers by using Box plots.\n",
    "* Then, we will use Distribution plots to check the distribution of the Numerical Columns in the Dataset.\n",
    "* After that we will check the Univariate Analysis for Categorical Columns using Pie charts, and Count plots.\n",
    "* We Use Pie charts, when we have very few categories in the categorical column, and we use count plots we have more categorises in the dataset."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 695,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 0
    },
    "id": "ZKC2yNvvi41y",
    "outputId": "87bdcc8e-dba0-4bae-d087-661f3687d0c4"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1152x360 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# lets plot pie chart for the columns where we have very few categories\n",
    "plt.rcParams['figure.figsize'] = (16,5)\n",
    "plt.style.use('fivethirtyeight')\n",
    "\n",
    "\n",
    "# plotting a pie chart to represent share of Previous year Rating of the Employees\n",
    "plt.subplot(1, 3, 2)\n",
    "labels = ['1', '2', '3', '4', '5']\n",
    "sizes = train['previous_year_rating'].value_counts()\n",
    "explode = [0, 0, 0, 0, 0.1]\n",
    "\n",
    "plt.pie(sizes, labels = labels, explode = explode, shadow = True, startangle = 90)\n",
    "plt.title('Previous year Ratings', fontsize = 20)\n",
    "\n",
    "# plotting a pie chart to represent share of Previous year Rating of the Employees\n",
    "plt.subplot(1, 3, 3)\n",
    "labels = ['0', '1']\n",
    "sizes = train['awards_won?'].value_counts()\n",
    "explode = [0,0.1]\n",
    "\n",
    "plt.pie(sizes, labels = labels, explode = explode, shadow = True, startangle = 90)\n",
    "plt.title('Awards Won?', fontsize = 20)\n",
    "\n",
    "\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 696,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "bTlTCReu23IG",
    "outputId": "1d3b159a-d6cf-4653-d3e5-82a6c0241e6f"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1     42806\n",
       "2      7808\n",
       "3      1744\n",
       "4       459\n",
       "5       124\n",
       "6        42\n",
       "7        11\n",
       "8         5\n",
       "9         5\n",
       "10        5\n",
       "Name: no_of_trainings, dtype: int64"
      ]
     },
     "execution_count": 696,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train['no_of_trainings'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 697,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 0
    },
    "id": "wcVZWzUVi5vh",
    "outputId": "e923a34d-ab32-459d-9a72-9379661c0c52"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x396 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Get the counts for each category\n",
    "counts = train['no_of_trainings'].value_counts()\n",
    "\n",
    "# Set the style of the plot\n",
    "plt.style.use('seaborn')\n",
    "\n",
    "# Create a bar chart with custom colors\n",
    "plt.bar(counts.index, counts.values, color=['#1f77b4', '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2'])\n",
    "\n",
    "# Add labels and title with custom fonts and sizes\n",
    "plt.xlabel('Number of Trainings', fontsize=12, fontweight='bold')\n",
    "plt.ylabel('Count', fontsize=12, fontweight='bold')\n",
    "plt.title('Training Counts', fontsize=14, fontweight='bold')\n",
    "\n",
    "# Customize the tick labels\n",
    "plt.xticks(counts.index, fontsize=10)\n",
    "plt.yticks(fontsize=10)\n",
    "\n",
    "# Remove the top and right spines\n",
    "plt.gca().spines['top'].set_visible(False)\n",
    "plt.gca().spines['right'].set_visible(False)\n",
    "\n",
    "# Add grid lines and set the alpha level\n",
    "plt.grid(axis='y', alpha=0.5)\n",
    "\n",
    "# Show the plot\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 698,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "XqjqPcki6uxP",
    "outputId": "2010fb29-6064-4b76-ab65-41ffff8941c6"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "30    3665\n",
       "32    3534\n",
       "31    3534\n",
       "29    3405\n",
       "33    3210\n",
       "28    3147\n",
       "34    3076\n",
       "27    2827\n",
       "35    2711\n",
       "36    2517\n",
       "37    2165\n",
       "26    2060\n",
       "38    1922\n",
       "39    1694\n",
       "40    1659\n",
       "25    1299\n",
       "41    1284\n",
       "42    1130\n",
       "43     956\n",
       "24     845\n",
       "44     796\n",
       "45     671\n",
       "46     555\n",
       "47     443\n",
       "23     428\n",
       "48     394\n",
       "50     350\n",
       "49     308\n",
       "51     275\n",
       "53     265\n",
       "52     247\n",
       "22     231\n",
       "54     222\n",
       "55     218\n",
       "56     177\n",
       "57     165\n",
       "60     143\n",
       "58     137\n",
       "59     133\n",
       "20     113\n",
       "21      98\n",
       "Name: age, dtype: int64"
      ]
     },
     "execution_count": 698,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train['age'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 699,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 0
    },
    "id": "Eshkgplx320Y",
    "outputId": "05dc9164-9097-49b4-c5fc-e7e89e147efe"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# lets check the Age of the Employees\n",
    "\n",
    "plt.rcParams['figure.figsize'] = (8, 4)\n",
    "plt.hist(train['age'], color = 'black')\n",
    "plt.title('Distribution of Age among the Employees', fontsize = 15)\n",
    "plt.xlabel('Age of the Employees')\n",
    "plt.grid()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 700,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 0
    },
    "id": "UEVtG9re4sO5",
    "outputId": "d1b4ab3e-69ab-4711-8764-a8c984bd22b5"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 864x432 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# lets check different Departments\n",
    "\n",
    "plt.rcParams['figure.figsize'] = (12, 6)\n",
    "sns.countplot(y = train['department'], palette = 'cividis', orient = 'v')\n",
    "plt.xlabel('')\n",
    "plt.ylabel('Department Name')\n",
    "plt.title('Distribution of Employees in Different Departments', fontsize = 15)\n",
    "plt.grid()\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "D59Tw21a47RA"
   },
   "source": [
    "Company has maximum number of employees in the sales and marketing department"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 701,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 0
    },
    "id": "JL_41Jj_42qr",
    "outputId": "45cd729b-230c-463e-fe82-95cba989ee21"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 864x1080 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# lets check distribution of different Regions\n",
    "\n",
    "plt.rcParams['figure.figsize'] = (12,15)\n",
    "plt.style.use('fivethirtyeight')\n",
    "sns.countplot(y = train['region'], palette = 'inferno', orient = 'v')\n",
    "plt.xlabel('')\n",
    "plt.ylabel('Region')\n",
    "plt.title('Different Regions', fontsize = 15)\n",
    "plt.xticks(rotation = 90)\n",
    "plt.grid()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "HCL24p_a5JCj"
   },
   "source": [
    "region 2 has the maximum number of employees working there"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 702,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "i-AWORwq5dle",
    "outputId": "61a6a6ed-3946-4362-f55c-9f5d39b2932c"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([\"Master's & above\", \"Bachelor's\", 'Below Secondary'], dtype=object)"
      ]
     },
     "execution_count": 702,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train['education'].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 703,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 0
    },
    "id": "z135NmLH5BQw",
    "outputId": "6aca6575-4d98-437f-c12a-ef67afc07799"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1152x360 with 3 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# lets plot pie chart for the columns where we have very few categories\n",
    "plt.rcParams['figure.figsize'] = (16,5)\n",
    "\n",
    "# plotting a pie chart to represent share of Previous year Rating of the Employees\n",
    "plt.subplot(1, 3, 1)\n",
    "labels = train['education'].value_counts().index\n",
    "sizes = train['education'].value_counts()\n",
    "colors = plt.cm.copper(np.linspace(0, 1, 5))\n",
    "explode = [0, 0, 0.1]\n",
    "\n",
    "plt.pie(sizes, labels = labels, colors = colors, explode = explode, shadow = True, startangle = 90)\n",
    "plt.title('Education', fontsize = 20)\n",
    "\n",
    "# plotting a pie chart to represent share of Previous year Rating of the Employees\n",
    "plt.subplot(1, 3, 2)\n",
    "labels = train['gender'].value_counts().index\n",
    "sizes = train['gender'].value_counts()\n",
    "colors = plt.cm.copper(np.linspace(0, 1, 5))\n",
    "explode = [0, 0]\n",
    "\n",
    "plt.pie(sizes, labels = labels, colors = colors, explode = explode, shadow = True, startangle = 90)\n",
    "plt.title('Gender', fontsize = 20)\n",
    "\n",
    "# plotting a pie chart to represent share of Previous year Rating of the Employees\n",
    "plt.subplot(1, 3, 3)\n",
    "labels = train['recruitment_channel'].value_counts().index\n",
    "sizes = train['recruitment_channel'].value_counts()\n",
    "colors = plt.cm.copper(np.linspace(0, 1, 5))\n",
    "explode = [0,0,0.1]\n",
    "\n",
    "plt.pie(sizes, labels = labels, colors = colors, explode = explode, shadow = True, startangle = 90)\n",
    "plt.title('Recruitment Channel', fontsize = 20)\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "qFf0Inym9nCi"
   },
   "source": [
    "## Bivariate Analysis\n",
    "\n",
    "Bivariate analysis is one of the simplest forms of quantitative analysis. It involves the analysis of two variables, for the purpose of determining the empirical relationship between them. Bivariate analysis can be helpful in testing simple hypotheses of association.\n",
    "\n",
    "* Types of Bivariate Analysis\n",
    "    * Categorical vs Categorical \n",
    "    * Categorical vs Numerical\n",
    "    * Numerical vs Numerical\n",
    "    \n",
    "* First, we will perform Categorical vs Categorical Analysis using Stacked and Grouped Bar Charts with the help of crosstab function.\n",
    "* Second, we will perform Categorical vs Numerical Analysis using Bar Charts, Box plots, Strip plots, Swarm plots, Boxen plots, Violin Plots, etc\n",
    "* Atlast, we will perform Numerical vs Numerical Analysis using Scatter plots."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "88IMsJjMBnWD"
   },
   "source": [
    "## For Gender vs Promotion"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 704,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 0
    },
    "id": "KK_bsZ3T5Yl4",
    "outputId": "977d4253-0193-49c9-c09b-159ef0179804"
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA84AAADwCAYAAADRjT0YAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/NK7nSAAAACXBIWXMAAAsTAAALEwEAmpwYAAAoZ0lEQVR4nO3deXRN9/7/8VcGiSEkirZUJEFwtaR+xmjEFFOLaFGteSg11NBSV0TTmKVXipSLlNSQVKqoS+eqKS5fbVUqioopieHeVjVBkPH8/rDs6zSxEySS6POxVtY6+/PZw3vvnLP2ep392fvYJCcnWwQAAAAAAHJlW9QFAAAAAABQnBGcAQAAAAAwQXAGAAAAAMAEwRkAAAAAABMEZwAAAAAATBCcAQAAAAAwYV/UBQAAShZ/f39duHAh176aNWsqOjpakrRv3z7NmzdPv//+u8aOHasaNWpYTffp0+e+6jh16pTOnz8vHx+fe15HaGiotm7dKhsbG23YsEGVKlXKMU9aWpqio6P1zTff6Ny5c8rOzpa7u7u6du2qnj17yta2cL+DfuGFF9S5c2eNGDGiULdzv5o1a2Y1bWtrq/Lly6tx48YaP368qlatWkSV5e7P7x9/f391795dw4YNK+LKAADFEcEZAHDXBg4cqJdeeilHu739/04ry5cvV40aNbR06VJVqFBBr732mtX0/XrzzTfVqVOnew7Op06d0kcffaQpU6aoRYsWuYbm1NRUjRw5UleuXNErr7wiLy8vSdIPP/ygZcuW6dixY3rrrbfuaz8eJm+++abatm0rSbJYLDp//rxmzZqlCRMmKDo6WjY2NkVc4f/8+f2zatUqlS5duoirAgAUVwRnAMBdK1OmjCpXrmw6z5UrV9SyZUtVq1Yt1+n7ZbFY7mv5K1euSJKaN29+x5rCwsJ04cIFRUdHW+2vq6ur3NzcNHLkSPXt21e1atW6r1oeFk5OTlbHqUqVKnrllVf01ltvKT4+XnXq1CnC6qz9+f1TsWLFIqoEAFAScI8zAKDANWvWTElJSVqxYoWaNWuWY1qS0tPTtXDhQnXp0kVt27bVq6++qri4OKv17N27V0OGDFGrVq3k7++vtWvXSpJGjhyps2fPasWKFfL398+1hszMTK1Zs0Y9e/aUj4+PXn75ZX3zzTeSpE8//VTDhw+XJD3//POaPn16juVTU1P1+eefq2/fvrl+SfD//t//08cff2wVmnfu3Km+ffvKx8dHvXv3VmRkpLKzsyVJ58+fV7NmzbR9+3YNGDBAzzzzjHr16qWdO3cay6elpekf//iH/Pz85Ofnp9WrV+fY7sGDBzVs2DC1atVKPXr00JIlS5SWlmZ17JcvX66uXbuqa9euunjxYo513LhxQ4sXL5a/v798fHw0ZMgQfffdd0b/9OnTNXPmTM2fP19+fn5q3bq1pk2bptTU1FyPtRk7OztJkoODg3EMPvjgA3Xq1EkvvviiMjIy9J///EeBgYHq2LGj2rRpo0mTJuncuXPGOm7978ePH2/sd0xMjHbs2KGePXuqdevWmjBhgpKTk41lTp48qQkTJqh9+/by8/PT22+/bfTn9v7x9/fXypUrjeV3796tgQMHqlWrVurWrZvCw8OVmZkpSTpw4IB8fHy0c+dO9e7dW88884z69++v2NjYuz4+AICSgeAMAChwn3/+uapWrap+/frp888/zzEtScHBwTp48KDmzJmjVatWqUmTJho1apQSEhIkSYcOHdIbb7yh5s2bKzIyUhMmTNCKFSu0efNmhYSEGOtbtWpVrjUsXLhQkZGRGj16tKKiotSxY0dNmzZN27dvl5+fn+bPny/p5hDdiRMn5lj+yJEjSktLU5MmTe64n25ubsbrf//73woKCtJLL72k6OhojR07VtHR0VZhTLp5FXv06NGKjo5WnTp1NH36dF2/fl2S9M4772jXrl2aPXu2li1bph9//FFnz541lj1+/LjGjRuntm3b6sMPP1RgYKBiYmIUEhJitY3Nmzfr3XffVUhISK6hPzAwUNu2bdOUKVMUGRmpp556SuPHj9fhw4eNeb788ktlZ2dr5cqVmjNnjmJiYoz71/MjOztbJ06cUEREhGrXrq0aNWoYfV9//bWWL1+uGTNmKC0tTa+88oouX76ssLAwLV26VKmpqXr11Vd19epVY5kVK1aoY8eOWrdunWrXrq2goCCtXbtWM2fOVGhoqA4fPmx8sXL+/Hm98sorqlChgsLDw/WPf/xD8fHxeu2115SVlZXn+2fHjh36+9//Lj8/P0VFRWncuHFav369FixYYMyTkZGhFStWaOrUqYqMjJSTk5Nmzpx53yMhAADFE0O1AQB3LSIiQmvWrMnRPmHCBD3//POqXLmy7OzsrIZ03z6dlJSkbdu2ad26dcYV2+HDh+unn37Shx9+qICAAK1fv15PP/20Ro4cKelmSL127Zrs7Ozk7OxsrC+3IbZXr17Vxo0bNXnyZLVv316SNGTIEMXHx2v16tVq166dcZ+1i4uLnJyccqzj0qVLRv/t2rVrp6ysLGN68ODBGjJkiFatWqVevXqpe/fukqTq1avr2rVrmj17ttUDp/r37y9vb29j2W3btun06dOqUaOGvvjiC02bNk3NmzeXdPPKb7du3YxlIyMjjaub0s0h4wEBARo+fLhGjx5tHOuuXbvecVj0qVOnFBMTo7CwMLVo0UKSNHHiRP3888+KjIzUvHnzJEnOzs6aOHGi7Ozs5ObmpmbNmlkF69zMnj3bWD49PV0Wi0VeXl6aOnWq1UPUevfuLXd3d0nShg0bdOXKFc2aNUvOzs6SpLlz56p79+764osv1Lt3b0mSr6+vnnvuOUlSjx49tHv3bo0ePVr169eXdPNK+6lTp4x1li9fXkFBQcZ997Nnz1afPn20b98++fj4mL5/Vq9erfbt22vgwIGSpBo1aiglJUWhoaEaNWqUpJtDvUePHq1GjRpJkl5++WW9+eabSk5OZtg3ADyECM4AgLvWq1cv9erVK0d7fgPDL7/8IkkaOnSoVXt6errS09MlSSdOnFDLli2t+m8Fp7wkJCQoKytLDRs2tGpv1KiRYmJi8rWOWyHu8uXLVu1r1qwxriqOGTNGGRkZkm7u05EjR7Rx40Zj3uzsbKWlpenChQvGg7Fuv/J6K7BnZGQoMTFRmZmZqlevntHv4uIiV1dXY/qXX35RUlKSWrdubbTdquX06dNGcH7iiSfuuF8nT56UpBzH5umnn9aePXuM6SeeeMIYZn2r1t9+++2O65WkUaNGydfXV9LNB8VVrFgx1wdu3V7fyZMn5ebmZhxv6eZ+e3h4GLVKsjoOZcqUkXTzy4lbHB0dlZKSIunmlwP169e3elidh4eHXFxcdPLkyTwfKHfy5Ek9++yzVm2NGjVSVlaWzpw5Y7Td6X8JAHj4EJwBAHetQoUKVkHmbpUqVUqStHLlSjk6Olr1OTg4SLJ+Qvfd+vM6b8nOzs73ev/2t7+pVKlSio2N1VNPPWW03x7Wbl9XqVKlNGDAAHXu3DnHuh599FEjdN7av9vdPrz3z0N9/7yN5557zrgServbh2Tfaf8l3fHJ0VlZWVbbyqvO3DzyyCP5el/cXl9+/1e3h/hb7vSU7vv9/+e2/K171e3t7Y17ym+9j2/HUG0AeDhxjzMA4IGrWbOmpJvDoV1dXY2/devWadeuXZIkd3d3HT161Gq5pUuXatKkSZLuHJqkm+G2VKlS+umnn6zaY2Nj5eHhka8anZ2d1aVLF0VFRen333/P0X/16lVdu3bNap+SkpKs9ufEiRNaunRpvsKUu7u7HBwcrB6QlpqaqqSkJKttnDlzxmobf/zxhxYtWpTvB3fd2v8/H5tDhw7l+9gUJA8PDyUkJBhXiyUpOTlZCQkJ91yPh4eHjhw5YjzMS7p5Ffry5cvGe8/s/ePh4aFDhw5Ztf30008qVaqU1RcnAIC/DoIzAOCuXb9+XRcvXsz1Lz8h0dXVVR06dNCcOXO0d+9enT17Vv/85z+1adMm497X/v376+DBg1q5cqWSkpK0fft2RUdHG0OBy5Ytq8TExFyHD5cuXVp9+/bVsmXL9O233yoxMVGrV6/Wjh071Ldv33zv5+uvv66qVatq0KBB2rx5sxISEpSQkKBPPvlE/fr1040bN4x7bIcOHaqvv/5aq1evVmJiovbs2aN58+bJ0dEx16u3f1a2bFm98MILWrZsmWJiYnTq1CnNnDlTN27cMOYZOHCgDh8+rAULFujMmTP68ccfNX36dF29ejXPnwe7pXr16urYsaNCQkL0f//3fzpz5owWLFigY8eOqU+fPvk+NgWlc+fOqlixoqZNm6Zjx47p2LFjCgwMVIUKFdSxY8d7Wmfv3r119epVzZgxQydPnlRsbKyCgoLk6emppk2bSjJ//wwdOlTbtm3TmjVrlJiYqG3btmn58uXy9/fP9X54AMDDj6HaAIC7tmbNmlwfDibdfGLynx+olZvAwEAtWbJEM2bMUGpqqtzd3RUSEmL8XFW9evUUEhKi5cuXKyIiQo8++qhGjx5tPHyrb9++mj9/vvbv36+vvvrK6uFTkvTqq6/K1tZWCxYsUHJystzd3TVr1iz5+fnlez/LlSun8PBwbdq0SVu2bFFYWJgyMjKM8Pniiy+qSpUqkiRvb28FBwdrzZo1Cg8PV8WKFfXss88aD5PKj3HjxsnR0VGzZs1Senq6unfvrieffNLor127thYsWKDly5dr48aNcnJyko+Pj8aNG5fvbUjS1KlT9d577+ntt9/WtWvXVLduXYWFheW47/lBcHR0VFhYmBYuXKhXX31VdnZ2atq0qZYvX67y5cvf0zorVaqkxYsXKywsTIMHD1bp0qXl6+ursWPHGkO1//z+ud2t/+UHH3ygZcuWqUqVKnrppZc0aNCg+95fAEDJZJOcnMzNOAAAAAAA3AFDtQEAAAAAMEFwBgAAAADABMEZAAAAAAATBGcAAAAAAEwQnAHkKrffrQUAAPeG8ypQshGcAeTq0qVLRV0CAAAPDc6rQMlGcAYAAAAAwATBGQAAAAAAEwRnAAAAAABMEJwBAAAAADBBcAYAAAAAwATBGQAAAAAAEwRnAAAAAABM2Bd1AQAAAPifXhVfKeoSUAjmfvf3oi4BwH0gOKNAcJJ/+HCCBwAAKN7Onz+vHj16aOPGjXJ1dS3qcgrFpUuXdODAAXXo0OGelg8KCpKdnZ3efvvt+6qDodoAAAAAUAI99thj+vzzz1WtWrWiLqXQLF68WDExMUVdBlecAQAAAKAksrOzU+XKlYu6jEJlsViKugRJXHEGAAAAgBLp/PnzatasmZKSkvTtt9+qT58+8vHxUc+ePbV169Z8rePAgQPq3LmzPv74Y3Xo0EGdOnXSihUrjP7w8HBNnDhRo0aNUvv27bVv3z6lpaVp8eLF6tq1q3x9ffXGG2/owoULVjXt3r1b/v7+at26tRYuXKgTJ05o4MCB8vX11cSJE3X9+nVjG59++qn69OmjVq1aaeDAgTpw4ICx7c8++0xffvml/P39JUlXr15VcHCw2rZtq86dO2vOnDlKTU011nXw4EH169dPrVq1UmBgoNLS0u77OEsEZwAAAAAo0S5fvqy33npLL7/8sj7++GMNHjxYs2fP1pkzZ/K1fEpKirZu3ar33ntPAQEBioqK0oYNG4z+mJgYtW3bVsuWLVPDhg01b9487dixQ8HBwYqIiFBWVpYmTpyorKwsY5nVq1dr/vz5mjJlij788ENNmTJFr732mhYuXKgff/xRW7ZskXQzNL/zzjsaOHCgIiMj1bx5c02YMEH/+c9/1L9/f/n5+aldu3ZatWqVJGnmzJlKSUlReHi4FixYoISEBM2YMUOS9Mcff+iNN95Q8+bNFRkZKTc3N+3YsaNAjjFDtQEAAACgBLOxsVFmZqaqVKmiqlWrqlu3bnr88cf1yCOP5Gv5rKwsBQYGqm7duqpXr56OHz+uTz75RL169ZIkOTs768UXX5R0M6R/8cUXevfdd9WkSRNJ0owZM9StWzft27dPNWvWlCQNHTpUnp6e8vT0VGhoqDp27KhmzZpJkho3bqyEhARJ0kcffaTevXvrueeekySNGTNGBw4c0Pr16zVu3Dg5OjoqKytLFStW1NmzZ7Vz5059/fXXcnZ2liQFBwfL399f//3vf7V79245Oztr7NixsrGx0YgRI7Rnz54COcYEZwAAAAAowZycnOTr66vXX39d1atXl4+Pj7p27aoKFSrka3lHR0fVrVvXmP7b3/6m1atXG9NVq1Y1XicmJio7O1tPPvmk0ebs7Cw3NzedOXPGCM5PPPGE0V+6dGk9/vjjVttLT0+XJJ05c0ZDhw61qqdBgwY6ffp0jjpPnz4ti8Wi7t275+hLSEjQ6dOnVbt2bdnY2Fjty61t3Q+CMwAAAACUYDY2Npo/f76OHTum3bt3KyYmRhs3blRoaKhatGiR5/J2dnZW01lZWbK1/d9dvY6Ojrm+/vMytw/V/vM6b1/f7XJbX3Z2trKzs3PdRtmyZbV27docfZUrV9bOnTtzPEzM3t6+QIIz9zgDAAAAQAmWnp6uhQsXql69ehoxYoTWrl2rp59+Wjt37szX8teuXdPZs2eN6aNHj6p27dq5zlu9enXZ2dnp559/NtqSk5OVlJQkNze3u67dzc1Nhw8ftmo7fPiwsa7brx67ubnp2rVrys7Olqurq/Hb1QsXLlRqaqpq1qypX375RZmZmcYyx48fv+uackNwBgAAAIAS7MqVK9q0aZPCw8N17tw5/fDDDzpx4oTq1auX73XMnj1bJ0+e1Pbt27V+/Xr17t071/nKlCmjF154QaGhocZ2goOD9eijj8rb2/uua+/Xr582bNigzz77TAkJCVqyZIni4+ONp2iXKVNGFy5c0K+//ioPDw95e3vr7bff1uHDh3X8+HEFBwfr0qVLqly5sjp27Kj09HTNnz9fCQkJWr16teLi4u66ptwwVBsAAAAASrBKlSopJCRES5Ys0dq1a1WhQgX17NnTCJ/54ePjoxEjRqhMmTIaOXKknn322TvOO3bsWEnSlClTlJmZqaZNm+qf//znHYdxm2nXrp0uXryo8PBw/f7776pTp47CwsJUq1YtSdJzzz2nHTt2qF+/fvr66681ffp0hYaGGg8Aa9asmSZNmiRJqlChgsLCwhQSEqL+/furUaNG6tKly13XlBub5OTk4vGL0ijRelV8pahLQAGb+93f5enpWdRlAMBfDufUhxPnVRRXBw4c0KhRo7R3717Z23Nd9U4Yqg0AAAAAgAm+UgAAAACAh9ClS5f0/PPPm84zY8aMB1RNyUZwBgAAAICHkLOzsyIjI03neeKJJ/Tdd989oIpKLoIzAAAAADyE7OzsjJ9swv3hHmcAAAAAAEzkecU5OztbISEhio+Pl4ODgwIDA62+tYiKitJXX30lGxsbDR48WG3bti3UggEAAAAAeJDyDM67du1Senq6IiIiFBcXp0WLFmn+/PmSbv7QdnR0tDZt2qTr16+rf//+BGcAAAAAwEMlz+AcGxsrb29vSVKDBg109OhRo69MmTJ6/PHHdf36dV2/fl02NjaFVykAAAAAoFAV9G/Jb/hjhWl/XiOci4s8g3NqaqqcnJyMaVtbW2VmZho/jv3YY4+pT58+ys7O1qBBg/K94fj4+HsoF8CDxOcUAICCw3kVf0V5ve+///57Xbx4UQEBAYqPj9fs2bM1ceLEB1RdTp6enrm25xmcy5Urp9TUVGPaYrEYoXnv3r36/ffftXnzZknSuHHj5OXlpSeffPKeCwJQfPA5BQCg4HBexV9RXu/7Tz/9VJ06dZKnp6c8PT21ZMmSYvlZyfOp2l5eXtq7d68kKS4uTrVq1TL6ypcvL0dHRzk4OMjR0VHly5fXlStXCq9aAAAAAMBD404jnIubPK84t2nTRvv379ewYcNksVgUFBSkqKgoubq6ytfXV99//72GDh0qGxsbPf3002revPmDqBsAAAAAUMKZjXAuTvKsyNbWVgEBAVZt7u7uxusRI0ZoxIgRBV4YAAAAAODh5uXlpZiYGHXo0CHHCOfipPhFeQAAAADAX0JuI5yLI4IzAAAAAEBS3j8fVdByG+FcHOX5cDAAAAAAAP7KCM4AAAAAAJggOAMAAAAAYILgDAAAAACACYIzAAAAAAAmCM4AAAAAAJjg56gAAAAAAJKk54a+X6Dr+yxieL7mO3z4sBYvXqxly5YV6PYLCsEZAAAAAFBk1qxZoy+++EJlypQp6lLuiKHaAAAAAIAiU716dYWEhBR1GaYIzgAAAACAItOuXTvZ2xfvwdAEZwAAAAAATBCcAQAAAAAwQXAGAAAAAMBE8R5IDgAAAAB4YPL781EFrVq1aoqIiCiSbecHV5wBAAAAADBBcAYAAAAAwATBGQAAAAAAEwRnAAAAAABMEJwBAAAAADBBcAYAAAAAwATBGQAAAAAAEwRnAAAAAABMEJwBAAAAADBBcAYAAAAAwATBGQAAAAAAEwRnAAAAAABMEJwBAAAAADBhn9cM2dnZCgkJUXx8vBwcHBQYGChXV1ejf+/evVqxYoUsFovq1aunyZMny8bGplCLBgAAAADgQcnzivOuXbuUnp6uiIgIjRkzRosWLTL6UlNTFRYWpnfffVcffPCBqlatquTk5MKsFwAAAACAByrPK86xsbHy9vaWJDVo0EBHjx41+g4dOqTatWtr4cKFOnfunPz9/VWxYsV8bTg+Pv4eSwbwoPA5BQCg4HBeBYo/T0/PXNvzDM6pqalycnIypm1tbZWZmSl7e3ulpKTohx9+UGRkpMqWLasRI0aoQYMGcnNzu+eCABQffE4BACg4nFeBkivPodrlypVTamqqMW2xWGRvfzNvOzs7q379+qpcubLKli2rRo0a6fjx44VXLQAAAAAAD1iewdnLy0t79+6VJMXFxalWrVpGX926dXXy5EklJycrMzNThw8fVs2aNQuvWgAAAAAAHrA8h2q3adNG+/fv17Bhw2SxWBQUFKSoqCi5urrK19dXY8aM0bhx4yRJ7du3twrWAAAAAACUdHkGZ1tbWwUEBFi1ubu7G687duyojh07FnhhAAAAAAAUB3kO1QYAAAAA4K+M4AwAAAAAgAmCMwAAAAAAJgjOAAAAAACYIDgDAAAAAGCC4AwAAAAAgAmCMwAAAAAAJgjOAAAAAACYIDgDAAAAAGCC4AwAAAAAgAmCMwAAAAAAJgjOAAAAAACYIDgDAAAAAGCC4AwAAAAAgAmCMwAAAAAAJgjOAAAAAACYIDgDAAAAAGCC4AwAAAAAgAmCMwAAAAAAJgjOAAAAAACYIDgDAAAAAGCC4AwAAAAAgAmCMwAAAAAAJgjOAAAAAACYIDgDAAAAAGCC4AwAAAAAgAmCMwAAAAAAJgjOAAAAAACYyDM4Z2dna+7cuRo6dKhGjhyppKSkXOcZP368Nm7cWChFAgAAAABQVPIMzrt27VJ6eroiIiI0ZswYLVq0KMc8y5Yt05UrVwqlQAAAAAAAilKewTk2Nlbe3t6SpAYNGujo0aNW/d9++61sbGzUokWLwqkQAAAAAIAiZJ/XDKmpqXJycjKmbW1tlZmZKXt7e508eVJfffWV5s2bpxUrVtzVhuPj4+++WgAPFJ9TAAAKDudVoPjz9PTMtT3P4FyuXDmlpqYa0xaLRfb2Nxf77LPP9Ntvv2n06NG6cOGC7O3tVa1aNeMK9b0UBKD44HMKAEDB4bwKlFx5BmcvLy/FxMSoQ4cOiouLU61atYy+cePGGa/Dw8NVqVKlfIVmAAAAAABKijyDc5s2bbR//34NGzZMFotFQUFBioqKkqurq3x9fR9EjQAAAAAAFJk8g7Otra0CAgKs2tzd3XPMN2LEiAIrCgAAAACA4iLPp2oDAAAAAPBXRnAGAAAAAMAEwRkAAAAAABMEZwAAAAAATBCcAQAAAAAwQXAGAAAAAMAEwRkAAAAAABMEZwAAAAAATBCcAQAAAAAwQXAGAAAAAMAEwRkAAAAAABMEZwAAAAAATBCcAQAAAAAwQXAGAAAAAMAEwRkAAAAAABMEZwAAAAAATBCcAQAAAAAwQXAGAAAAAMAEwRkAAAAAABMEZwAAAAAATBCcAQAAAAAwQXAGAAAAAMAEwRkAAAAAABMEZwAAAAAATBCcAQAAAAAwQXAGAAAAAMAEwRkAAAAAABMEZwAAAAAATNjnNUN2drZCQkIUHx8vBwcHBQYGytXV1ej/8MMP9c0330iSWrZsqeHDhxdetQAAAAAAPGB5XnHetWuX0tPTFRERoTFjxmjRokVG37lz5/Tll19qxYoVioiI0P79+xUfH1+oBQMAAAAA8CDlecU5NjZW3t7ekqQGDRro6NGjRt9jjz2msLAw2dnZSZIyMzPl4OBQSKUCAAAAAPDg5RmcU1NT5eTkZEzb2toqMzNT9vb2sre3l4uLiywWi8LCwlS3bl25ubnla8NcmQaKPz6nAAAUHM6rQPHn6emZa3uewblcuXJKTU01pi0Wi+zt/7dYWlqaZs6cqXLlymny5Mn3XRCA4oPPKQAABYfzKlBy5XmPs5eXl/bu3StJiouLU61atYw+i8WiSZMmydPTUwEBAcaQbQAAAAAAHhZ5XnFu06aN9u/fr2HDhslisSgoKEhRUVFydXVVVlaWDh48qIyMDO3bt0+SNHr0aDVs2LDQCwcAAAAA4EHIMzjb2toqICDAqs3d3d14vWfPngIvCgAAAACA4iLPodoAAAAAAPyVEZwBAAAAADBBcAYAAAAAwATBGQAAAAAAEwRnAAAAAABMEJwBAAAAADBBcAYAAAAAwATBGQAAAAAAEwRnAAAAAABMEJwBAAAAADBBcAYAAAAAwATBGQAAAAAAEwRnAAAAAABMEJwBAAAAADBBcAYAAAAAwIR9URcAoHiaMHenpJ1FXAUK0mcRw4u6BAAAgBKJ4AwAAAAUMr6QfvjwhfRfC0O1AQAAAAAwQXAGAAAAAMAEwRkAAAAAABMEZwAAAAAATBCcAQAAAAAwQXAGAAAAAMAEwRkAAAAAABMEZwAAAAAATBCcAQAAAAAwQXAGAAAAAMAEwRkAAAAAABMEZwAAAAAATNjnNUN2drZCQkIUHx8vBwcHBQYGytXV1ejfvHmzNm3aJHt7ew0ZMkStWrUq1IIBAAAAAHiQ8gzOu3btUnp6uiIiIhQXF6dFixZp/vz5kqSLFy/qo48+0urVq5Wenq7hw4erefPmcnBwKPTCUbxs+GNFUZcAAMBDgXMqABQ/eQ7Vjo2Nlbe3tySpQYMGOnr0qNF35MgRNWzYUA4ODnJyclL16tV14sSJwqsWAAAAAIAHLM/gnJqaKicnp/8tYGurzMzMXPvKli2rq1evFkKZAAAAAAAUjTyDc7ly5ZSammpMWywW2dvbG33Xrl0z+q5du2YVpAEAAAAAKOnyDM5eXl7au3evJCkuLk61atUy+urXr6/Y2FilpaXp6tWrOnPmjFU/AAAAAAAlnU1ycrLFbIZbT9U+ceKELBaLgoKC9O9//1uurq7y9fXV5s2b9cknn8hisWjw4MFq167dg6odAAAAAIBCl2dwBgAAAADgryzPodoAAAAAAPyVEZwBAAAAADBBcAbAz8gBAAAAJgjOAPT6669LkubNm1fElQAAAADFj31RFwCg6Nnb22vQoEFKSkpSfHy8pJu/2W5jY6OVK1cWcXUAAJRMMTEx2rJlizIyMoy2hQsXFl1BAO4ZT9UGoKysLP32228KCQnR5MmTrfqqVq1aRFUBAFCy9erVSwEBASpfvrzRVqdOnSKsCMC94oozANnZ2enxxx/XggULiroUAAAeGjVr1lTjxo2LugwABYDgDAAAABQCX19fDR06VB4eHkbbW2+9VYQVAbhXBGcAAACgEKxfv14DBgyQk5NTUZcC4D4RnAEAAIBCUKlSJXXo0KGoywBQAAjOAAAAQCFwdHTUuHHjVLduXdnY2EiSRo8eXcRVAbgXBGcAAACgEPj4+BR1CQAKCD9HBQAAAACACduiLgAAAAAAgOKM4AwAAAAAgAnucQYAoBAlJiZqw4YN2rdvn3799VfZ2NjIzc1NHTp0UK9evVS6dOkHUkdQUJB++ukn/etf/3og2wMA4GFCcAYAoJBs375d06dPV/Xq1dWnTx95eHgoIyND33//vd5//31t375dy5Ytk4ODQ1GXCgAATBCcAQAoBImJiQoODlbTpk0VEhIie/v/nXJbtGih1q1ba8SIEVq3bp0GDRpUhJUCAIC8cI8zAACFYO3atbJYLAoICLAKzbc0bNhQffr0UZkyZYy2rVu36uWXX9Yzzzyjrl27asmSJcrIyDD6w8PD9cILL2jfvn0aMGCAfHx85O/vr6ioKKt1p6SkKDg4WH5+fvLz89OSJUuUnZ2do4aYmBgNHjxYrVq1UqdOnTRv3jxdvXrV6P/000/l7e2tLVu2qEuXLmrfvr2OHj1aEIcHAIAShSvOAAAUgh07dqhp06aqXLnyHed5/fXXjddr167Ve++9p169emn8+PE6efKkli9frrNnz2ru3LnGfBcvXtScOXM0ZMgQubq66l//+pcWLVokDw8PtWzZUtnZ2Ro/frwuXLigcePGycXFRWvXrtXPP/+sKlWqGOv55ptvNG3aNPn5+WnEiBH69ddftXTpUsXHx2v58uVG2M/KytKaNWs0depUpaSkqG7duoVwtAAAKN4IzgAAFLArV67o8uXLcnNzy9GXmZmZo+3GjRt6//331a1bN02ePFnSzeHcjz76qAIDA3Xo0CE1bNjQmHfevHlq2bKlJMnLy0u7du3S7t271bJlS+3du1dHjhxRaGioWrVqJUlq0qSJ/P39je1ZLBaFhYWpcePGmj17ttFeu3ZtDR06VN9++606depktN+6Kg0AwF8VQ7UBAChgWVlZkiQbGxur9uTkZLVs2TLHX1xcnG7cuKHWrVsrMzPT+GvZsqVsbW21f/9+q/XcCtGS5ODgIBcXF12/fl2SFBsbKzs7OyNYS1LZsmXl7e1tTCcmJuq///1vju3Vq1dPlStXzrG9OnXqFMyBAQCghOKKMwAABczFxUVly5bV+fPnrdqdnJy0atUqY3rjxo3aunWrUlJSJEmTJk3KdX2//fab1fSff8LK1tZWFotFknT58mWVL19ednZ2VvPcPmQ8OTlZkhQaGqrQ0NA8t3f7fdgAAPwVEZwBACgEvr6+iomJUWpqqsqVKydJsre3V/369Y15du3aJelmoJak4OBgubu751iXi4tLvrfr4uKiy5cvKzMz0+qhZLfC8u3bGzNmjJo2bZpjHbfqBQAANzFUGwCAQjB48GBlZWVp5syZSk9Pz9GfmZmphIQESdJTTz2lUqVK6ddff1X9+vWNPycnJy1evFhnzpzJ93abNGmi7Oxs7dixw2hLS0vTd999Z0y7u7vrkUce0fnz5622V716dS1dulRxcXH3vuMAADyEuOIMAEAhqFmzpmbNmqXg4GD1799f/v7+8vT0lMVi0c8//6ytW7fq3Llz6tKli1xcXDRgwAC9//77unbtmpo0aaJLly4Z03fzJOtmzZqpefPmmjt3rlJSUlS1alVFR0crJSVFjzzyiCTJzs5OI0eO1Ny5c2VnZydfX19dv35dH3zwgRITE62e9g0AAAjOAAAUGl9fX61bt04bN27UZ599pgsXLigzM1PVqlWTt7e3evToYTx4a+TIkapcubI2bNigqKgolS9fXo0bN9bIkSNVqVKlu9ruO++8o7CwMIWHhysjI0MdOnRQjRo1tGfPHmOeHj16yMnJSWvXrtWWLVtUunRpNWjQQFOnTlXNmjUL9DgAAFDS2SQnJ1uKuggAAAAAAIor7nEGAAAAAMAEwRkAAAAAABMEZwAAAAAATBCcAQAAAAAwQXAGAAAAAMAEwRkAAAAAABMEZwAAAAAATBCcAQAAAAAw8f8BxiY7pSGsckwAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 1080x216 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import warnings\n",
    "warnings.filterwarnings('ignore')\n",
    "\n",
    "plt.rcParams['figure.figsize'] = (15, 3)\n",
    "x = pd.crosstab(train['gender'], train['is_promoted'])\n",
    "colors = plt.cm.viridis(np.linspace(0, 1, 5))\n",
    "x.div(x.sum(1).astype(float), axis = 0).plot(kind = 'bar', stacked = False, color = colors) #stacked parameter is set to False to create a horizontal bar chart with bars side by side\n",
    "plt.title('Effect of Gender on Promotion', fontsize = 15)\n",
    "plt.xlabel('Gender')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 705,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 0
    },
    "id": "czihxpcN9qGy",
    "outputId": "747dc547-ca3c-4d0b-c602-338de10796bb"
   },
   "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>is_promoted</th>\n",
       "      <th>0</th>\n",
       "      <th>1</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>gender</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>f</th>\n",
       "      <td>14321</td>\n",
       "      <td>1428</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>m</th>\n",
       "      <td>34141</td>\n",
       "      <td>3119</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "is_promoted      0     1\n",
       "gender                  \n",
       "f            14321  1428\n",
       "m            34141  3119"
      ]
     },
     "execution_count": 705,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "h = pd.crosstab(train['gender'], train['is_promoted'])\n",
    "h"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 706,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 0
    },
    "id": "y8SgS96aAMcx",
    "outputId": "39e1d3b0-f6f9-4ae0-b90f-a9b45ac4e62f"
   },
   "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>is_promoted</th>\n",
       "      <th>0</th>\n",
       "      <th>1</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>gender</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>f</th>\n",
       "      <td>0.909328</td>\n",
       "      <td>0.090672</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>m</th>\n",
       "      <td>0.916291</td>\n",
       "      <td>0.083709</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "is_promoted         0         1\n",
       "gender                         \n",
       "f            0.909328  0.090672\n",
       "m            0.916291  0.083709"
      ]
     },
     "execution_count": 706,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "h.div(x.sum(1).astype(float), axis = 0)   #This normalizes the contingency table by dividing each row by the sum of its values. \n",
    "                                          #This converts the frequency counts into proportions that can be easily compared across categories\n",
    "                                          # i.e. 14321/(14321+1428) and 1428/(14321+1428)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "W6e8teZhBsBK"
   },
   "source": [
    "## Departments vs Promotion"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 707,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 0
    },
    "id": "gC2fbemQBCNL",
    "outputId": "855e270e-2ab3-4f8c-b054-9597e630fc8f"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# lets compare the effect of different Departments and Promotion\n",
    "\n",
    "plt.rcParams['figure.figsize'] = (15,4)\n",
    "x = pd.crosstab(train['department'], train['is_promoted'])\n",
    "colors = plt.cm.autumn(np.linspace(0, 1, 3))\n",
    "x.div(x.sum(1).astype(float), axis = 0).plot(kind = 'bar', stacked = False, color = colors)\n",
    "plt.title('Effect of Department on Promotion', fontsize = 15)\n",
    "plt.xticks(rotation = 20)\n",
    "plt.xlabel(' ')\n",
    "plt.show()\n",
    "\n",
    "plt.rcParams['figure.figsize'] = (15,4)\n",
    "x = pd.crosstab(train['department'], train['is_promoted'])\n",
    "colors = plt.cm.autumn(np.linspace(0, 1, 3))\n",
    "x.div(x.sum(1).astype(float), axis = 0).plot(kind = 'area', stacked = False, color = colors)\n",
    "plt.title('Effect of Department on Promotion', fontsize = 15)\n",
    "plt.xticks(rotation = 20)\n",
    "plt.xlabel(' ')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "1qJW5MhoDWxo"
   },
   "source": [
    "## Age vs Promotion"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 708,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 0
    },
    "id": "psp8l51iByVA",
    "outputId": "787deb4b-8995-4b2b-b37d-f7a91574df06"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1440x576 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Effect of Age on the Promotion\n",
    "\n",
    "plt.rcParams['figure.figsize'] = (20, 8)\n",
    "sns.boxenplot(x='is_promoted', y='age', data=train, palette='PuRd')\n",
    "plt.title('Effect of Age on Promotion', fontsize=15)\n",
    "plt.xlabel('Is the Employee Promoted?', fontsize=10)\n",
    "plt.ylabel('Age of the Employee', fontsize=10)\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "5j7hvZLRGcdC"
   },
   "source": [
    "## Department Vs Average Training Score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 709,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 0
    },
    "id": "zHHN4u0EEPNU",
    "outputId": "123a67a8-267f-48fc-bffc-0846ecac67a5"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1152x504 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Department Vs Average Training Score\n",
    "\n",
    "plt.rcParams['figure.figsize'] = (16, 7)\n",
    "sns.boxplot(x = 'department', y = 'avg_training_score',data=train, palette = 'autumn')\n",
    "plt.title('Average Training Scores from each Department', fontsize = 15)\n",
    "plt.ylabel('Promoted or not', fontsize = 10)\n",
    "plt.xlabel('Departments', fontsize = 10)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "qD4e62KaHmHd"
   },
   "source": [
    "## Multivariate Analysis\n",
    "\n",
    "Multivariate analysis is based on the principles of multivariate statistics, which involves observation and analysis of more than one statistical outcome variable at a time.\n",
    "\n",
    "* First, we will use the Correlation Heatmap to check the correlation between the Numerical Columns\n",
    "* Then we will check the ppscore or the Predictive Score to check the correlation between all the columns present in the data.\n",
    "* Then, we will use Bubble Charts, split Violin plots, Hue with Bivariate Plots."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 710,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 0
    },
    "id": "Wca9y5aPGfDi",
    "outputId": "321ed1eb-1d0b-4cff-c777-dc067fcf7aad"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x576 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# lets check the Heat Map for the Data with respect to correlation.\n",
    "\n",
    "plt.rcParams['figure.figsize'] = (15, 8)\n",
    "sns.heatmap(train.corr(), annot = True, linewidth = 0.5, cmap = 'Wistia')\n",
    "plt.title('Correlation Heat Map', fontsize = 15)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "pNVxExZFHt4v"
   },
   "source": [
    "## Department vs Promotion vs Won awards?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 711,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "-vbntAU7IQKk",
    "outputId": "4cf50c16-2775-41e1-8c95-4227efd3b922"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0        0\n",
       "1        0\n",
       "2        0\n",
       "3        0\n",
       "4        0\n",
       "        ..\n",
       "54802    0\n",
       "54804    0\n",
       "54805    0\n",
       "54806    0\n",
       "54807    0\n",
       "Name: awards_won?, Length: 53009, dtype: int64"
      ]
     },
     "execution_count": 711,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train['awards_won?']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 712,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 0
    },
    "id": "ii5T0QC3HopM",
    "outputId": "bbaaa8e2-fb28-4bea-8d70-75497cc1e83a"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1152x504 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# lets check the relation of Departments and Promotions when they won awards ?\n",
    "\n",
    "plt.rcParams['figure.figsize'] = (16, 7)\n",
    "sns.barplot(x = 'department', y = 'is_promoted',data=train, hue = train['awards_won?'], palette = 'cool')\n",
    "plt.title('Chances of Promotion in each Department when they have won some Awards too', fontsize = 15)\n",
    "plt.ylabel('Promoted or not', fontsize = 10)\n",
    "plt.xlabel('Departments', fontsize = 10)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "VeapLdGohlAh"
   },
   "source": [
    "## **Answering Some Key Questions**"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "StWmelfOZe3q"
   },
   "source": [
    "### Does Older Employees getting more Promotion than Younger Employees?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 713,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "HFVTlIxEaQEv",
    "outputId": "6910c39b-daba-4491-a8aa-be84beed120d"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    53009.000000\n",
       "mean        34.254315\n",
       "std          7.120853\n",
       "min         20.000000\n",
       "25%         29.000000\n",
       "50%         33.000000\n",
       "75%         38.000000\n",
       "max         60.000000\n",
       "Name: age, dtype: float64"
      ]
     },
     "execution_count": 713,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train['age'].describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 714,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 0
    },
    "id": "MLRIc1VuZkVF",
    "outputId": "c74774be-5369-4242-8032-21d8c9a102f6"
   },
   "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>employee_id</th>\n",
       "      <th>department</th>\n",
       "      <th>region</th>\n",
       "      <th>education</th>\n",
       "      <th>gender</th>\n",
       "      <th>recruitment_channel</th>\n",
       "      <th>no_of_trainings</th>\n",
       "      <th>age</th>\n",
       "      <th>previous_year_rating</th>\n",
       "      <th>length_of_service</th>\n",
       "      <th>awards_won?</th>\n",
       "      <th>avg_training_score</th>\n",
       "      <th>is_promoted</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>49017</td>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>region_7</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>f</td>\n",
       "      <td>sourcing</td>\n",
       "      <td>1</td>\n",
       "      <td>35</td>\n",
       "      <td>5.0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>50</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39</th>\n",
       "      <td>58304</td>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>region_28</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>sourcing</td>\n",
       "      <td>1</td>\n",
       "      <td>33</td>\n",
       "      <td>5.0</td>\n",
       "      <td>6</td>\n",
       "      <td>0</td>\n",
       "      <td>51</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>71</th>\n",
       "      <td>24040</td>\n",
       "      <td>Technology</td>\n",
       "      <td>region_22</td>\n",
       "      <td>Master's &amp; above</td>\n",
       "      <td>m</td>\n",
       "      <td>other</td>\n",
       "      <td>1</td>\n",
       "      <td>34</td>\n",
       "      <td>5.0</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>78</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75</th>\n",
       "      <td>54782</td>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>region_2</td>\n",
       "      <td>Master's &amp; above</td>\n",
       "      <td>m</td>\n",
       "      <td>sourcing</td>\n",
       "      <td>1</td>\n",
       "      <td>38</td>\n",
       "      <td>4.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>49</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>85</th>\n",
       "      <td>47498</td>\n",
       "      <td>Operations</td>\n",
       "      <td>region_11</td>\n",
       "      <td>Master's &amp; above</td>\n",
       "      <td>f</td>\n",
       "      <td>sourcing</td>\n",
       "      <td>1</td>\n",
       "      <td>42</td>\n",
       "      <td>5.0</td>\n",
       "      <td>11</td>\n",
       "      <td>0</td>\n",
       "      <td>60</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",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54722</th>\n",
       "      <td>47608</td>\n",
       "      <td>Procurement</td>\n",
       "      <td>region_10</td>\n",
       "      <td>Master's &amp; above</td>\n",
       "      <td>m</td>\n",
       "      <td>sourcing</td>\n",
       "      <td>1</td>\n",
       "      <td>34</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>72</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54734</th>\n",
       "      <td>11685</td>\n",
       "      <td>Operations</td>\n",
       "      <td>region_15</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>sourcing</td>\n",
       "      <td>1</td>\n",
       "      <td>31</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>56</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54757</th>\n",
       "      <td>14502</td>\n",
       "      <td>Technology</td>\n",
       "      <td>region_7</td>\n",
       "      <td>Master's &amp; above</td>\n",
       "      <td>m</td>\n",
       "      <td>other</td>\n",
       "      <td>1</td>\n",
       "      <td>54</td>\n",
       "      <td>4.0</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>81</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54792</th>\n",
       "      <td>994</td>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>region_14</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>other</td>\n",
       "      <td>1</td>\n",
       "      <td>59</td>\n",
       "      <td>3.0</td>\n",
       "      <td>11</td>\n",
       "      <td>0</td>\n",
       "      <td>65</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54796</th>\n",
       "      <td>12592</td>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>region_25</td>\n",
       "      <td>Master's &amp; above</td>\n",
       "      <td>m</td>\n",
       "      <td>other</td>\n",
       "      <td>1</td>\n",
       "      <td>34</td>\n",
       "      <td>3.0</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>60</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2997 rows × 13 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       employee_id         department     region         education gender  \\\n",
       "11           49017  Sales & Marketing   region_7        Bachelor's      f   \n",
       "39           58304  Sales & Marketing  region_28        Bachelor's      m   \n",
       "71           24040         Technology  region_22  Master's & above      m   \n",
       "75           54782  Sales & Marketing   region_2  Master's & above      m   \n",
       "85           47498         Operations  region_11  Master's & above      f   \n",
       "...            ...                ...        ...               ...    ...   \n",
       "54722        47608        Procurement  region_10  Master's & above      m   \n",
       "54734        11685         Operations  region_15        Bachelor's      m   \n",
       "54757        14502         Technology   region_7  Master's & above      m   \n",
       "54792          994  Sales & Marketing  region_14        Bachelor's      m   \n",
       "54796        12592  Sales & Marketing  region_25  Master's & above      m   \n",
       "\n",
       "      recruitment_channel  no_of_trainings  age  previous_year_rating  \\\n",
       "11               sourcing                1   35                   5.0   \n",
       "39               sourcing                1   33                   5.0   \n",
       "71                  other                1   34                   5.0   \n",
       "75               sourcing                1   38                   4.0   \n",
       "85               sourcing                1   42                   5.0   \n",
       "...                   ...              ...  ...                   ...   \n",
       "54722            sourcing                1   34                   5.0   \n",
       "54734            sourcing                1   31                   3.0   \n",
       "54757               other                1   54                   4.0   \n",
       "54792               other                1   59                   3.0   \n",
       "54796               other                1   34                   3.0   \n",
       "\n",
       "       length_of_service  awards_won?  avg_training_score  is_promoted  \n",
       "11                     3            0                  50            1  \n",
       "39                     6            0                  51            1  \n",
       "71                     7            0                  78            1  \n",
       "75                     2            0                  49            1  \n",
       "85                    11            0                  60            1  \n",
       "...                  ...          ...                 ...          ...  \n",
       "54722                  2            0                  72            1  \n",
       "54734                  1            0                  56            1  \n",
       "54757                  7            0                  81            1  \n",
       "54792                 11            0                  65            1  \n",
       "54796                  7            0                  60            1  \n",
       "\n",
       "[2997 rows x 13 columns]"
      ]
     },
     "execution_count": 714,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "old = train[(train['age']>30) & (train['is_promoted']==1)]\n",
    "old"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 715,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 0
    },
    "id": "cxsHE3xuZkey",
    "outputId": "12b67c9e-e19d-48a3-e7e1-faa860e2cec0"
   },
   "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>employee_id</th>\n",
       "      <th>department</th>\n",
       "      <th>region</th>\n",
       "      <th>education</th>\n",
       "      <th>gender</th>\n",
       "      <th>recruitment_channel</th>\n",
       "      <th>no_of_trainings</th>\n",
       "      <th>age</th>\n",
       "      <th>previous_year_rating</th>\n",
       "      <th>length_of_service</th>\n",
       "      <th>awards_won?</th>\n",
       "      <th>avg_training_score</th>\n",
       "      <th>is_promoted</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>66</th>\n",
       "      <td>77981</td>\n",
       "      <td>Finance</td>\n",
       "      <td>region_22</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>other</td>\n",
       "      <td>1</td>\n",
       "      <td>27</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>58</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>67</th>\n",
       "      <td>16502</td>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>region_22</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>sourcing</td>\n",
       "      <td>1</td>\n",
       "      <td>27</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>61</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>69</th>\n",
       "      <td>45624</td>\n",
       "      <td>Analytics</td>\n",
       "      <td>region_31</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>other</td>\n",
       "      <td>1</td>\n",
       "      <td>30</td>\n",
       "      <td>3.0</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>84</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>79</th>\n",
       "      <td>59147</td>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>region_22</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>sourcing</td>\n",
       "      <td>1</td>\n",
       "      <td>30</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>58</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>84</th>\n",
       "      <td>44575</td>\n",
       "      <td>Legal</td>\n",
       "      <td>region_7</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>other</td>\n",
       "      <td>1</td>\n",
       "      <td>29</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>65</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",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54624</th>\n",
       "      <td>57131</td>\n",
       "      <td>Finance</td>\n",
       "      <td>region_2</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>other</td>\n",
       "      <td>1</td>\n",
       "      <td>24</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54713</th>\n",
       "      <td>56396</td>\n",
       "      <td>Procurement</td>\n",
       "      <td>region_22</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>sourcing</td>\n",
       "      <td>1</td>\n",
       "      <td>30</td>\n",
       "      <td>4.0</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>67</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54720</th>\n",
       "      <td>38719</td>\n",
       "      <td>Analytics</td>\n",
       "      <td>region_4</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>sourcing</td>\n",
       "      <td>1</td>\n",
       "      <td>29</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>88</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54730</th>\n",
       "      <td>51059</td>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>region_2</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>other</td>\n",
       "      <td>1</td>\n",
       "      <td>29</td>\n",
       "      <td>5.0</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>58</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54761</th>\n",
       "      <td>8278</td>\n",
       "      <td>Procurement</td>\n",
       "      <td>region_13</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>f</td>\n",
       "      <td>sourcing</td>\n",
       "      <td>1</td>\n",
       "      <td>30</td>\n",
       "      <td>4.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>86</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1550 rows × 13 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       employee_id         department     region   education gender  \\\n",
       "66           77981            Finance  region_22  Bachelor's      m   \n",
       "67           16502  Sales & Marketing  region_22  Bachelor's      m   \n",
       "69           45624          Analytics  region_31  Bachelor's      m   \n",
       "79           59147  Sales & Marketing  region_22  Bachelor's      m   \n",
       "84           44575              Legal   region_7  Bachelor's      m   \n",
       "...            ...                ...        ...         ...    ...   \n",
       "54624        57131            Finance   region_2  Bachelor's      m   \n",
       "54713        56396        Procurement  region_22  Bachelor's      m   \n",
       "54720        38719          Analytics   region_4  Bachelor's      m   \n",
       "54730        51059  Sales & Marketing   region_2  Bachelor's      m   \n",
       "54761         8278        Procurement  region_13  Bachelor's      f   \n",
       "\n",
       "      recruitment_channel  no_of_trainings  age  previous_year_rating  \\\n",
       "66                  other                1   27                   3.0   \n",
       "67               sourcing                1   27                   3.0   \n",
       "69                  other                1   30                   3.0   \n",
       "79               sourcing                1   30                   3.0   \n",
       "84                  other                1   29                   3.0   \n",
       "...                   ...              ...  ...                   ...   \n",
       "54624               other                1   24                   3.0   \n",
       "54713            sourcing                1   30                   4.0   \n",
       "54720            sourcing                1   29                   2.0   \n",
       "54730               other                1   29                   5.0   \n",
       "54761            sourcing                1   30                   4.0   \n",
       "\n",
       "       length_of_service  awards_won?  avg_training_score  is_promoted  \n",
       "66                     1            1                  58            1  \n",
       "67                     1            0                  61            1  \n",
       "69                     7            0                  84            1  \n",
       "79                     3            0                  58            1  \n",
       "84                     1            0                  65            1  \n",
       "...                  ...          ...                 ...          ...  \n",
       "54624                  1            0                  71            1  \n",
       "54713                  4            0                  67            1  \n",
       "54720                  3            0                  88            1  \n",
       "54730                  4            0                  58            1  \n",
       "54761                  2            0                  86            1  \n",
       "\n",
       "[1550 rows x 13 columns]"
      ]
     },
     "execution_count": 715,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "young = train[(train['is_promoted']==1) & (train['age']<=30)]\n",
    "young"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 716,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 0
    },
    "id": "8foRTcOaZklA",
    "outputId": "688912fd-81d9-4eea-e70b-823b38b6889f"
   },
   "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>employee_id</th>\n",
       "      <th>department</th>\n",
       "      <th>region</th>\n",
       "      <th>education</th>\n",
       "      <th>gender</th>\n",
       "      <th>recruitment_channel</th>\n",
       "      <th>no_of_trainings</th>\n",
       "      <th>age</th>\n",
       "      <th>previous_year_rating</th>\n",
       "      <th>length_of_service</th>\n",
       "      <th>awards_won?</th>\n",
       "      <th>avg_training_score</th>\n",
       "      <th>is_promoted</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>49017</td>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>region_7</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>f</td>\n",
       "      <td>sourcing</td>\n",
       "      <td>1</td>\n",
       "      <td>35</td>\n",
       "      <td>5.0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>50</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39</th>\n",
       "      <td>58304</td>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>region_28</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>sourcing</td>\n",
       "      <td>1</td>\n",
       "      <td>33</td>\n",
       "      <td>5.0</td>\n",
       "      <td>6</td>\n",
       "      <td>0</td>\n",
       "      <td>51</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>66</th>\n",
       "      <td>77981</td>\n",
       "      <td>Finance</td>\n",
       "      <td>region_22</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>other</td>\n",
       "      <td>1</td>\n",
       "      <td>27</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>58</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>67</th>\n",
       "      <td>16502</td>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>region_22</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>sourcing</td>\n",
       "      <td>1</td>\n",
       "      <td>27</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>61</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>69</th>\n",
       "      <td>45624</td>\n",
       "      <td>Analytics</td>\n",
       "      <td>region_31</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>other</td>\n",
       "      <td>1</td>\n",
       "      <td>30</td>\n",
       "      <td>3.0</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>84</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",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54734</th>\n",
       "      <td>11685</td>\n",
       "      <td>Operations</td>\n",
       "      <td>region_15</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>sourcing</td>\n",
       "      <td>1</td>\n",
       "      <td>31</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>56</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54757</th>\n",
       "      <td>14502</td>\n",
       "      <td>Technology</td>\n",
       "      <td>region_7</td>\n",
       "      <td>Master's &amp; above</td>\n",
       "      <td>m</td>\n",
       "      <td>other</td>\n",
       "      <td>1</td>\n",
       "      <td>54</td>\n",
       "      <td>4.0</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>81</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54761</th>\n",
       "      <td>8278</td>\n",
       "      <td>Procurement</td>\n",
       "      <td>region_13</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>f</td>\n",
       "      <td>sourcing</td>\n",
       "      <td>1</td>\n",
       "      <td>30</td>\n",
       "      <td>4.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>86</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54792</th>\n",
       "      <td>994</td>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>region_14</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>other</td>\n",
       "      <td>1</td>\n",
       "      <td>59</td>\n",
       "      <td>3.0</td>\n",
       "      <td>11</td>\n",
       "      <td>0</td>\n",
       "      <td>65</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54796</th>\n",
       "      <td>12592</td>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>region_25</td>\n",
       "      <td>Master's &amp; above</td>\n",
       "      <td>m</td>\n",
       "      <td>other</td>\n",
       "      <td>1</td>\n",
       "      <td>34</td>\n",
       "      <td>3.0</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>60</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4547 rows × 13 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       employee_id         department     region         education gender  \\\n",
       "11           49017  Sales & Marketing   region_7        Bachelor's      f   \n",
       "39           58304  Sales & Marketing  region_28        Bachelor's      m   \n",
       "66           77981            Finance  region_22        Bachelor's      m   \n",
       "67           16502  Sales & Marketing  region_22        Bachelor's      m   \n",
       "69           45624          Analytics  region_31        Bachelor's      m   \n",
       "...            ...                ...        ...               ...    ...   \n",
       "54734        11685         Operations  region_15        Bachelor's      m   \n",
       "54757        14502         Technology   region_7  Master's & above      m   \n",
       "54761         8278        Procurement  region_13        Bachelor's      f   \n",
       "54792          994  Sales & Marketing  region_14        Bachelor's      m   \n",
       "54796        12592  Sales & Marketing  region_25  Master's & above      m   \n",
       "\n",
       "      recruitment_channel  no_of_trainings  age  previous_year_rating  \\\n",
       "11               sourcing                1   35                   5.0   \n",
       "39               sourcing                1   33                   5.0   \n",
       "66                  other                1   27                   3.0   \n",
       "67               sourcing                1   27                   3.0   \n",
       "69                  other                1   30                   3.0   \n",
       "...                   ...              ...  ...                   ...   \n",
       "54734            sourcing                1   31                   3.0   \n",
       "54757               other                1   54                   4.0   \n",
       "54761            sourcing                1   30                   4.0   \n",
       "54792               other                1   59                   3.0   \n",
       "54796               other                1   34                   3.0   \n",
       "\n",
       "       length_of_service  awards_won?  avg_training_score  is_promoted  \n",
       "11                     3            0                  50            1  \n",
       "39                     6            0                  51            1  \n",
       "66                     1            1                  58            1  \n",
       "67                     1            0                  61            1  \n",
       "69                     7            0                  84            1  \n",
       "...                  ...          ...                 ...          ...  \n",
       "54734                  1            0                  56            1  \n",
       "54757                  7            0                  81            1  \n",
       "54761                  2            0                  86            1  \n",
       "54792                 11            0                  65            1  \n",
       "54796                  7            0                  60            1  \n",
       "\n",
       "[4547 rows x 13 columns]"
      ]
     },
     "execution_count": 716,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train[train['is_promoted']==1]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "lXyva9GtbaJV"
   },
   "source": [
    "Out of the total 4547 employees which got promotion, older employees with age greater than 30 years got promoted more than the younger employees between the age 20 t0 30."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "Vfr_CfqecpCY"
   },
   "source": [
    "### What is the Probability to get Promoted, If an employeed has won an award?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 717,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 0
    },
    "id": "OS_3E_YhcuH8",
    "outputId": "46588454-4fcc-470e-b486-88fd4600ccc1"
   },
   "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>employee_id</th>\n",
       "      <th>department</th>\n",
       "      <th>region</th>\n",
       "      <th>education</th>\n",
       "      <th>gender</th>\n",
       "      <th>recruitment_channel</th>\n",
       "      <th>no_of_trainings</th>\n",
       "      <th>age</th>\n",
       "      <th>previous_year_rating</th>\n",
       "      <th>length_of_service</th>\n",
       "      <th>awards_won?</th>\n",
       "      <th>avg_training_score</th>\n",
       "      <th>is_promoted</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>66</th>\n",
       "      <td>77981</td>\n",
       "      <td>Finance</td>\n",
       "      <td>region_22</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>other</td>\n",
       "      <td>1</td>\n",
       "      <td>27</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>58</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>122</th>\n",
       "      <td>38052</td>\n",
       "      <td>Procurement</td>\n",
       "      <td>region_34</td>\n",
       "      <td>Master's &amp; above</td>\n",
       "      <td>m</td>\n",
       "      <td>sourcing</td>\n",
       "      <td>1</td>\n",
       "      <td>37</td>\n",
       "      <td>5.0</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>92</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>138</th>\n",
       "      <td>51164</td>\n",
       "      <td>Technology</td>\n",
       "      <td>region_14</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>f</td>\n",
       "      <td>other</td>\n",
       "      <td>1</td>\n",
       "      <td>31</td>\n",
       "      <td>4.0</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>78</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>140</th>\n",
       "      <td>7606</td>\n",
       "      <td>Technology</td>\n",
       "      <td>region_29</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>f</td>\n",
       "      <td>other</td>\n",
       "      <td>2</td>\n",
       "      <td>30</td>\n",
       "      <td>3.0</td>\n",
       "      <td>7</td>\n",
       "      <td>1</td>\n",
       "      <td>76</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>200</th>\n",
       "      <td>53630</td>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>region_23</td>\n",
       "      <td>Master's &amp; above</td>\n",
       "      <td>f</td>\n",
       "      <td>sourcing</td>\n",
       "      <td>1</td>\n",
       "      <td>34</td>\n",
       "      <td>4.0</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>94</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",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54641</th>\n",
       "      <td>2467</td>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>region_27</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>other</td>\n",
       "      <td>1</td>\n",
       "      <td>42</td>\n",
       "      <td>2.0</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>47</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54702</th>\n",
       "      <td>4952</td>\n",
       "      <td>Operations</td>\n",
       "      <td>region_28</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>other</td>\n",
       "      <td>1</td>\n",
       "      <td>28</td>\n",
       "      <td>3.0</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>62</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54772</th>\n",
       "      <td>34501</td>\n",
       "      <td>Operations</td>\n",
       "      <td>region_27</td>\n",
       "      <td>Master's &amp; above</td>\n",
       "      <td>m</td>\n",
       "      <td>other</td>\n",
       "      <td>1</td>\n",
       "      <td>37</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>57</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54797</th>\n",
       "      <td>62450</td>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>region_11</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>sourcing</td>\n",
       "      <td>1</td>\n",
       "      <td>28</td>\n",
       "      <td>5.0</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>47</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54799</th>\n",
       "      <td>68093</td>\n",
       "      <td>Procurement</td>\n",
       "      <td>region_2</td>\n",
       "      <td>Master's &amp; above</td>\n",
       "      <td>f</td>\n",
       "      <td>other</td>\n",
       "      <td>1</td>\n",
       "      <td>50</td>\n",
       "      <td>5.0</td>\n",
       "      <td>6</td>\n",
       "      <td>1</td>\n",
       "      <td>67</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1253 rows × 13 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       employee_id         department     region         education gender  \\\n",
       "66           77981            Finance  region_22        Bachelor's      m   \n",
       "122          38052        Procurement  region_34  Master's & above      m   \n",
       "138          51164         Technology  region_14        Bachelor's      f   \n",
       "140           7606         Technology  region_29        Bachelor's      f   \n",
       "200          53630  Sales & Marketing  region_23  Master's & above      f   \n",
       "...            ...                ...        ...               ...    ...   \n",
       "54641         2467  Sales & Marketing  region_27        Bachelor's      m   \n",
       "54702         4952         Operations  region_28        Bachelor's      m   \n",
       "54772        34501         Operations  region_27  Master's & above      m   \n",
       "54797        62450  Sales & Marketing  region_11        Bachelor's      m   \n",
       "54799        68093        Procurement   region_2  Master's & above      f   \n",
       "\n",
       "      recruitment_channel  no_of_trainings  age  previous_year_rating  \\\n",
       "66                  other                1   27                   3.0   \n",
       "122              sourcing                1   37                   5.0   \n",
       "138                 other                1   31                   4.0   \n",
       "140                 other                2   30                   3.0   \n",
       "200              sourcing                1   34                   4.0   \n",
       "...                   ...              ...  ...                   ...   \n",
       "54641               other                1   42                   2.0   \n",
       "54702               other                1   28                   3.0   \n",
       "54772               other                1   37                   5.0   \n",
       "54797            sourcing                1   28                   5.0   \n",
       "54799               other                1   50                   5.0   \n",
       "\n",
       "       length_of_service  awards_won?  avg_training_score  is_promoted  \n",
       "66                     1            1                  58            1  \n",
       "122                    3            1                  92            1  \n",
       "138                    4            1                  78            0  \n",
       "140                    7            1                  76            0  \n",
       "200                    5            1                  94            1  \n",
       "...                  ...          ...                 ...          ...  \n",
       "54641                  4            1                  47            0  \n",
       "54702                  2            1                  62            0  \n",
       "54772                  2            1                  57            0  \n",
       "54797                  3            1                  47            0  \n",
       "54799                  6            1                  67            0  \n",
       "\n",
       "[1253 rows x 13 columns]"
      ]
     },
     "execution_count": 717,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "award_won = train[train['awards_won?']==1]\n",
    "award_won"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 718,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 0
    },
    "id": "zv8Lrii1ct86",
    "outputId": "8d862c79-8f10-48b8-d58b-382853537877"
   },
   "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>employee_id</th>\n",
       "      <th>department</th>\n",
       "      <th>region</th>\n",
       "      <th>education</th>\n",
       "      <th>gender</th>\n",
       "      <th>recruitment_channel</th>\n",
       "      <th>no_of_trainings</th>\n",
       "      <th>age</th>\n",
       "      <th>previous_year_rating</th>\n",
       "      <th>length_of_service</th>\n",
       "      <th>awards_won?</th>\n",
       "      <th>avg_training_score</th>\n",
       "      <th>is_promoted</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>66</th>\n",
       "      <td>77981</td>\n",
       "      <td>Finance</td>\n",
       "      <td>region_22</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>other</td>\n",
       "      <td>1</td>\n",
       "      <td>27</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>58</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>122</th>\n",
       "      <td>38052</td>\n",
       "      <td>Procurement</td>\n",
       "      <td>region_34</td>\n",
       "      <td>Master's &amp; above</td>\n",
       "      <td>m</td>\n",
       "      <td>sourcing</td>\n",
       "      <td>1</td>\n",
       "      <td>37</td>\n",
       "      <td>5.0</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>92</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>200</th>\n",
       "      <td>53630</td>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>region_23</td>\n",
       "      <td>Master's &amp; above</td>\n",
       "      <td>f</td>\n",
       "      <td>sourcing</td>\n",
       "      <td>1</td>\n",
       "      <td>34</td>\n",
       "      <td>4.0</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>94</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>230</th>\n",
       "      <td>62923</td>\n",
       "      <td>Operations</td>\n",
       "      <td>region_13</td>\n",
       "      <td>Master's &amp; above</td>\n",
       "      <td>f</td>\n",
       "      <td>other</td>\n",
       "      <td>1</td>\n",
       "      <td>38</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>93</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>317</th>\n",
       "      <td>22865</td>\n",
       "      <td>Analytics</td>\n",
       "      <td>region_20</td>\n",
       "      <td>Master's &amp; above</td>\n",
       "      <td>m</td>\n",
       "      <td>other</td>\n",
       "      <td>1</td>\n",
       "      <td>40</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>83</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",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54017</th>\n",
       "      <td>69878</td>\n",
       "      <td>Analytics</td>\n",
       "      <td>region_26</td>\n",
       "      <td>Master's &amp; above</td>\n",
       "      <td>m</td>\n",
       "      <td>sourcing</td>\n",
       "      <td>1</td>\n",
       "      <td>41</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>90</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54024</th>\n",
       "      <td>3752</td>\n",
       "      <td>HR</td>\n",
       "      <td>region_2</td>\n",
       "      <td>Master's &amp; above</td>\n",
       "      <td>m</td>\n",
       "      <td>sourcing</td>\n",
       "      <td>1</td>\n",
       "      <td>60</td>\n",
       "      <td>5.0</td>\n",
       "      <td>8</td>\n",
       "      <td>1</td>\n",
       "      <td>50</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54146</th>\n",
       "      <td>37302</td>\n",
       "      <td>Operations</td>\n",
       "      <td>region_2</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>other</td>\n",
       "      <td>1</td>\n",
       "      <td>37</td>\n",
       "      <td>5.0</td>\n",
       "      <td>7</td>\n",
       "      <td>1</td>\n",
       "      <td>79</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54503</th>\n",
       "      <td>10882</td>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>region_25</td>\n",
       "      <td>Master's &amp; above</td>\n",
       "      <td>m</td>\n",
       "      <td>sourcing</td>\n",
       "      <td>2</td>\n",
       "      <td>32</td>\n",
       "      <td>4.0</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>92</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54507</th>\n",
       "      <td>43314</td>\n",
       "      <td>Analytics</td>\n",
       "      <td>region_25</td>\n",
       "      <td>Master's &amp; above</td>\n",
       "      <td>m</td>\n",
       "      <td>other</td>\n",
       "      <td>1</td>\n",
       "      <td>35</td>\n",
       "      <td>5.0</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>81</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>552 rows × 13 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       employee_id         department     region         education gender  \\\n",
       "66           77981            Finance  region_22        Bachelor's      m   \n",
       "122          38052        Procurement  region_34  Master's & above      m   \n",
       "200          53630  Sales & Marketing  region_23  Master's & above      f   \n",
       "230          62923         Operations  region_13  Master's & above      f   \n",
       "317          22865          Analytics  region_20  Master's & above      m   \n",
       "...            ...                ...        ...               ...    ...   \n",
       "54017        69878          Analytics  region_26  Master's & above      m   \n",
       "54024         3752                 HR   region_2  Master's & above      m   \n",
       "54146        37302         Operations   region_2        Bachelor's      m   \n",
       "54503        10882  Sales & Marketing  region_25  Master's & above      m   \n",
       "54507        43314          Analytics  region_25  Master's & above      m   \n",
       "\n",
       "      recruitment_channel  no_of_trainings  age  previous_year_rating  \\\n",
       "66                  other                1   27                   3.0   \n",
       "122              sourcing                1   37                   5.0   \n",
       "200              sourcing                1   34                   4.0   \n",
       "230                 other                1   38                   5.0   \n",
       "317                 other                1   40                   5.0   \n",
       "...                   ...              ...  ...                   ...   \n",
       "54017            sourcing                1   41                   5.0   \n",
       "54024            sourcing                1   60                   5.0   \n",
       "54146               other                1   37                   5.0   \n",
       "54503            sourcing                2   32                   4.0   \n",
       "54507               other                1   35                   5.0   \n",
       "\n",
       "       length_of_service  awards_won?  avg_training_score  is_promoted  \n",
       "66                     1            1                  58            1  \n",
       "122                    3            1                  92            1  \n",
       "200                    5            1                  94            1  \n",
       "230                    2            1                  93            1  \n",
       "317                    5            1                  83            1  \n",
       "...                  ...          ...                 ...          ...  \n",
       "54017                  5            1                  90            1  \n",
       "54024                  8            1                  50            1  \n",
       "54146                  7            1                  79            1  \n",
       "54503                  5            1                  92            1  \n",
       "54507                  3            1                  81            1  \n",
       "\n",
       "[552 rows x 13 columns]"
      ]
     },
     "execution_count": 718,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "award_won[award_won['is_promoted']==1]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "gU_pPk5hdRUO"
   },
   "source": [
    "The Probability of getting promoted when award is won by the employee is = 552/1253 = 0.4405\n",
    "\n",
    "That means there is 44% chances of getting promotion if an award was won by an employee."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "2cdW8hRtfuf6"
   },
   "source": [
    "### What is the Average Training Score of those Employees who got Promotion?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 719,
   "metadata": {
    "id": "IGzLisBMmVn0"
   },
   "outputs": [],
   "source": [
    "data = train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 720,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "jVlgfHnIctzE",
    "outputId": "5b09be59-ef71-47a8-c290-b132e78b4754"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The Average Training Score for the Employees who got Promotion is 71\n"
     ]
    }
   ],
   "source": [
    "promoted_employees = data[data['is_promoted'] == 1]\n",
    "avg_training_score_promoted_emp = promoted_employees['avg_training_score'].mean()\n",
    "print(\"The Average Training Score for the Employees who got Promotion is {0:.0f}\".format(avg_training_score_promoted_emp))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "ZsNinGbPgcCL"
   },
   "source": [
    "### What is the impact of gender on promotion?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 721,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "5jTMHwdAggSz",
    "outputId": "f9f16b5e-3bb1-4563-9008-f8d0f3badef0"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "m    37260\n",
       "f    15749\n",
       "Name: gender, dtype: int64"
      ]
     },
     "execution_count": 721,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# lets check the gender gap in total employees\n",
    "\n",
    "data['gender'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 722,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "DVHrbS1wggI7",
    "outputId": "937b135a-8f90-48ab-eba2-fb2090e74413"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "m    3119\n",
       "f    1428\n",
       "Name: gender, dtype: int64"
      ]
     },
     "execution_count": 722,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# lets check the Gender Gap in Promotion\n",
    "\n",
    "promoted_employees['gender'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 723,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "Av1Jv7Fygf9A",
    "outputId": "f6de0e7e-2e24-4909-fd67-f5a43f3461bd"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.08315149625935161 0.08993379107405591\n"
     ]
    }
   ],
   "source": [
    "m_prom = 3201/38496\n",
    "f_prom = 1467/16312\n",
    "print(m_prom, f_prom) "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "GD7MVkb1gzKX"
   },
   "source": [
    "### What is the Probability of Freshers getting Promoted?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 724,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "zhy5WvKog4FJ",
    "outputId": "e83e5a06-6854-4007-af7e-52a5c370a283"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    8057\n",
       "1     743\n",
       "Name: is_promoted, dtype: int64"
      ]
     },
     "execution_count": 724,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# lets consider the employees who have worked for less than equal to two years\n",
    "\n",
    "freshers = data[(data['length_of_service'] <= 2) & (data['age'] <= 30)]\n",
    "freshers['is_promoted'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 725,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "dkJboWxJg3-_",
    "outputId": "e0f140ff-f415-42be-ad0a-0a8ed3bf7bc7"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Probability of a Fresher being Promoted is 8.44%\n"
     ]
    }
   ],
   "source": [
    "# lets check the Percentage also\n",
    "\n",
    "prob = 743/(8057+743)\n",
    "print(\"Probability of a Fresher being Promoted is {0:.2f}%\".format(prob*100))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "LERiuw5mI2c8"
   },
   "source": [
    "## Feature Engineering\n",
    "\n",
    "Feature engineering is the process of using domain knowledge to extract features from raw data via data mining techniques. These features can be used to improve the performance of machine learning algorithms. Feature engineering can be considered as applied machine learning itself.\n",
    "\n",
    "* There are mutliple ways of performing feature engineering.\n",
    "* So many people in the Industry consider it the most important step to improve the Model Performance.\n",
    "* We should always understand the columns well to make some new features using the old existing features.\n",
    "* Let's discuss the ways how we can perform feature engineering\n",
    "    * We can perform Feature Engineering by Removing Unnecassary Columns\n",
    "    * We can do it by Extracting Features from the Date and Time Features.\n",
    "    * We can do it by Extracting Features from the Categorcial Features.\n",
    "    * We can do it by Binnning the Numerical and Categorical Features.\n",
    "    * We can do it by Aggregating Multiple Features together by using simple Arithmetic operations\n",
    "    \n",
    "* Here, we are only going to perform Feature Engineering by Aggregating some features together."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 726,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "DD-RZqRZKjir",
    "outputId": "6d7ffc2c-64c8-4298-e1ec-80983b2633e6"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "3.0    22032\n",
       "5.0    11359\n",
       "4.0     9517\n",
       "1.0     6020\n",
       "2.0     4081\n",
       "Name: previous_year_rating, dtype: int64"
      ]
     },
     "execution_count": 726,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train['previous_year_rating'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 727,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "qL36DV6BLKdH",
    "outputId": "3052883f-b69a-49eb-eb7e-41b1c2c60085"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "50    2629\n",
       "49    2602\n",
       "48    2340\n",
       "51    2274\n",
       "60    2080\n",
       "      ... \n",
       "98      35\n",
       "99      33\n",
       "41      25\n",
       "40       4\n",
       "39       2\n",
       "Name: avg_training_score, Length: 61, dtype: int64"
      ]
     },
     "execution_count": 727,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train['avg_training_score'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 728,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "-vgJ54xGLLP8",
    "outputId": "2da4400a-d701-4bd5-971a-f5b87d7a930d"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1     42806\n",
       "2      7808\n",
       "3      1744\n",
       "4       459\n",
       "5       124\n",
       "6        42\n",
       "7        11\n",
       "8         5\n",
       "9         5\n",
       "10        5\n",
       "Name: no_of_trainings, dtype: int64"
      ]
     },
     "execution_count": 728,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train['no_of_trainings'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 729,
   "metadata": {
    "id": "YBoLaB3DHx93"
   },
   "outputs": [],
   "source": [
    "# lets create some extra features from existing features to improve our Model\n",
    "\n",
    "# creating a Metric of Sum\n",
    "train['sum_metric'] = train['awards_won?']+ train['previous_year_rating']\n",
    "test['sum_metric'] = test['awards_won?']+ test['previous_year_rating']\n",
    "\n",
    "# creating a total score column\n",
    "train['total_score'] = train['avg_training_score'] * train['no_of_trainings']\n",
    "test['total_score'] = test['avg_training_score'] * test['no_of_trainings']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 730,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "JWdCV-fWL1Zz",
    "outputId": "9f821275-4603-452b-eefb-5b5b9d71b9ea"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['department', 'education', 'gender', 'no_of_trainings', 'age',\n",
       "       'previous_year_rating', 'length_of_service', 'awards_won?',\n",
       "       'avg_training_score', 'is_promoted', 'sum_metric', 'total_score'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 730,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# lets remove some of the columns which are not very useful for predicting the promotion.\n",
    "\n",
    "# we already know that the recruitment channel is very least related to promotion of an employee, so lets remove this column\n",
    "# even the region seems to contribute very less, when it comes to promotion, so lets remove it too.\n",
    "# also the employee id is not useful so lets remove it.\n",
    "\n",
    "train = train.drop(['recruitment_channel', 'region', 'employee_id'], axis = 1)\n",
    "test = test.drop(['recruitment_channel', 'region', 'employee_id'], axis = 1)\n",
    "\n",
    "# lets check the columns in train and test data set after feature engineering\n",
    "train.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 731,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 0
    },
    "id": "33M5FA7LL7ue",
    "outputId": "6af206f4-bebb-4855-a04f-d3bf871b18ac"
   },
   "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>department</th>\n",
       "      <th>education</th>\n",
       "      <th>gender</th>\n",
       "      <th>no_of_trainings</th>\n",
       "      <th>age</th>\n",
       "      <th>previous_year_rating</th>\n",
       "      <th>length_of_service</th>\n",
       "      <th>awards_won?</th>\n",
       "      <th>avg_training_score</th>\n",
       "      <th>is_promoted</th>\n",
       "      <th>sum_metric</th>\n",
       "      <th>total_score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>573</th>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>Master's &amp; above</td>\n",
       "      <td>f</td>\n",
       "      <td>1</td>\n",
       "      <td>39</td>\n",
       "      <td>1.0</td>\n",
       "      <td>10</td>\n",
       "      <td>0</td>\n",
       "      <td>52</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>52</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3451</th>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>1</td>\n",
       "      <td>24</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>50</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4888</th>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>1</td>\n",
       "      <td>42</td>\n",
       "      <td>1.0</td>\n",
       "      <td>10</td>\n",
       "      <td>0</td>\n",
       "      <td>50</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11803</th>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>1</td>\n",
       "      <td>42</td>\n",
       "      <td>1.0</td>\n",
       "      <td>14</td>\n",
       "      <td>0</td>\n",
       "      <td>49</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>49</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12241</th>\n",
       "      <td>Legal</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>1</td>\n",
       "      <td>31</td>\n",
       "      <td>1.0</td>\n",
       "      <td>6</td>\n",
       "      <td>0</td>\n",
       "      <td>56</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>56</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16807</th>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>1</td>\n",
       "      <td>35</td>\n",
       "      <td>1.0</td>\n",
       "      <td>10</td>\n",
       "      <td>0</td>\n",
       "      <td>57</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>57</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17281</th>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>1</td>\n",
       "      <td>30</td>\n",
       "      <td>1.0</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>49</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>49</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19582</th>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>2</td>\n",
       "      <td>27</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>46</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>92</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21266</th>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>1</td>\n",
       "      <td>34</td>\n",
       "      <td>1.0</td>\n",
       "      <td>10</td>\n",
       "      <td>0</td>\n",
       "      <td>52</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>52</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23209</th>\n",
       "      <td>Operations</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>1</td>\n",
       "      <td>37</td>\n",
       "      <td>1.0</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>58</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>58</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24564</th>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>2</td>\n",
       "      <td>30</td>\n",
       "      <td>1.0</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>45</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>90</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27296</th>\n",
       "      <td>Operations</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>1</td>\n",
       "      <td>43</td>\n",
       "      <td>1.0</td>\n",
       "      <td>13</td>\n",
       "      <td>0</td>\n",
       "      <td>59</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>59</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31860</th>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>1</td>\n",
       "      <td>27</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>58</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>58</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>33769</th>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>1</td>\n",
       "      <td>37</td>\n",
       "      <td>1.0</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>50</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>45455</th>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>Master's &amp; above</td>\n",
       "      <td>m</td>\n",
       "      <td>1</td>\n",
       "      <td>39</td>\n",
       "      <td>1.0</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>51</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>51</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>47782</th>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>Master's &amp; above</td>\n",
       "      <td>m</td>\n",
       "      <td>1</td>\n",
       "      <td>34</td>\n",
       "      <td>1.0</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>48</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>48</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>51374</th>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "      <td>1</td>\n",
       "      <td>31</td>\n",
       "      <td>1.0</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>58</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>58</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              department         education gender  no_of_trainings  age  \\\n",
       "573    Sales & Marketing  Master's & above      f                1   39   \n",
       "3451   Sales & Marketing        Bachelor's      m                1   24   \n",
       "4888   Sales & Marketing        Bachelor's      m                1   42   \n",
       "11803  Sales & Marketing        Bachelor's      m                1   42   \n",
       "12241              Legal        Bachelor's      m                1   31   \n",
       "16807  Sales & Marketing        Bachelor's      m                1   35   \n",
       "17281  Sales & Marketing        Bachelor's      m                1   30   \n",
       "19582  Sales & Marketing        Bachelor's      m                2   27   \n",
       "21266  Sales & Marketing        Bachelor's      m                1   34   \n",
       "23209         Operations        Bachelor's      m                1   37   \n",
       "24564  Sales & Marketing        Bachelor's      m                2   30   \n",
       "27296         Operations        Bachelor's      m                1   43   \n",
       "31860  Sales & Marketing        Bachelor's      m                1   27   \n",
       "33769  Sales & Marketing        Bachelor's      m                1   37   \n",
       "45455  Sales & Marketing  Master's & above      m                1   39   \n",
       "47782  Sales & Marketing  Master's & above      m                1   34   \n",
       "51374  Sales & Marketing        Bachelor's      m                1   31   \n",
       "\n",
       "       previous_year_rating  length_of_service  awards_won?  \\\n",
       "573                     1.0                 10            0   \n",
       "3451                    1.0                  3            0   \n",
       "4888                    1.0                 10            0   \n",
       "11803                   1.0                 14            0   \n",
       "12241                   1.0                  6            0   \n",
       "16807                   1.0                 10            0   \n",
       "17281                   1.0                  4            0   \n",
       "19582                   1.0                  2            0   \n",
       "21266                   1.0                 10            0   \n",
       "23209                   1.0                  5            0   \n",
       "24564                   1.0                  7            0   \n",
       "27296                   1.0                 13            0   \n",
       "31860                   1.0                  2            0   \n",
       "33769                   1.0                  7            0   \n",
       "45455                   1.0                  7            0   \n",
       "47782                   1.0                  7            0   \n",
       "51374                   1.0                  5            0   \n",
       "\n",
       "       avg_training_score  is_promoted  sum_metric  total_score  \n",
       "573                    52            1         1.0           52  \n",
       "3451                   50            1         1.0           50  \n",
       "4888                   50            1         1.0           50  \n",
       "11803                  49            1         1.0           49  \n",
       "12241                  56            1         1.0           56  \n",
       "16807                  57            1         1.0           57  \n",
       "17281                  49            1         1.0           49  \n",
       "19582                  46            1         1.0           92  \n",
       "21266                  52            1         1.0           52  \n",
       "23209                  58            1         1.0           58  \n",
       "24564                  45            1         1.0           90  \n",
       "27296                  59            1         1.0           59  \n",
       "31860                  58            1         1.0           58  \n",
       "33769                  50            1         1.0           50  \n",
       "45455                  51            1         1.0           51  \n",
       "47782                  48            1         1.0           48  \n",
       "51374                  58            1         1.0           58  "
      ]
     },
     "execution_count": 731,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "'''\n",
    "lets check the no. of employee who did not get an award, did not acheive 80+ KPI, previous_year_rating as 1\n",
    "and avg_training score is less than 40\n",
    "but, still got promotion.\n",
    "''' \n",
    "\n",
    "train[(train['previous_year_rating'] == 1.0) & \n",
    "      (train['awards_won?'] == 0) & (train['avg_training_score'] < 60) & (train['is_promoted'] == 1)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 732,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "VEGSb20CMD0_",
    "outputId": "33d5526a-ecde-4b19-987a-c4b8875b9ee1"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Before Deleting the above two rows : (53009, 12)\n",
      "After Deletion of the above two rows : (52992, 12)\n"
     ]
    }
   ],
   "source": [
    "# lets remove the above two rows as they have a huge negative effect on our training data\n",
    "\n",
    "# lets check shape of the train data before deleting two rows\n",
    "print(\"Before Deleting the above two rows :\", train.shape)\n",
    "\n",
    "train = train.drop(train[(train['previous_year_rating'] == 1.0) & \n",
    "      (train['awards_won?'] == 0) & (train['avg_training_score'] < 60) & (train['is_promoted'] == 1)].index)\n",
    "\n",
    "# lets check the shape of the train data after deleting the two rows\n",
    "print(\"After Deletion of the above two rows :\", train.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "zfwVT0hzMbRV"
   },
   "source": [
    "## Dealing with Categorical Columns\n",
    "\n",
    "Categorical variables are known to hide and mask lots of interesting information in a data set. It’s crucial to learn the methods of dealing with such variables. If you won’t, many a times, you’d miss out on finding the most important variables in a model. It has happened with me. Initially, I used to focus more on numerical variables. Hence, never actually got an accurate model. But, later I discovered my flaws and learnt the art of dealing with such variables.\n",
    "\n",
    "* There are various ways to encode categorical columns into Numerical columns\n",
    "* This is an Essential Step, as we Machine Learning Models only works with Numerical Values.\n",
    "* Here, we are going to use Business Logic to encode the education column\n",
    "* Then we will use the Label Encoder, to Department and Gender Columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 733,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 206
    },
    "id": "w_3kl0JSMOrJ",
    "outputId": "d9d58fdf-3376-4a81-d2e1-41356fd5f2b4"
   },
   "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>department</th>\n",
       "      <th>education</th>\n",
       "      <th>gender</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>Master's &amp; above</td>\n",
       "      <td>f</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Operations</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Sales &amp; Marketing</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Technology</td>\n",
       "      <td>Bachelor's</td>\n",
       "      <td>m</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          department         education gender\n",
       "0  Sales & Marketing  Master's & above      f\n",
       "1         Operations        Bachelor's      m\n",
       "2  Sales & Marketing        Bachelor's      m\n",
       "3  Sales & Marketing        Bachelor's      m\n",
       "4         Technology        Bachelor's      m"
      ]
     },
     "execution_count": 733,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "## Lets check the categorical columns present in the data\n",
    "train.select_dtypes('object').head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 734,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "qAIBc8ewMjF8",
    "outputId": "38a8a4f3-3446-4fcd-f27b-81429bfe38bc"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Bachelor's          38180\n",
       "Master's & above    14007\n",
       "Below Secondary       805\n",
       "Name: education, dtype: int64"
      ]
     },
     "execution_count": 734,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# lets check the value counts for the education column\n",
    "train['education'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 735,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "0ur3VhvfMlZF",
    "outputId": "a3b36e21-2c37-40e5-c85c-b8efbafeb7bd"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Index([], dtype='object')\n",
      "Index([], dtype='object')\n"
     ]
    }
   ],
   "source": [
    "# lets start encoding these categorical columns to convert them into numerical columns\n",
    "\n",
    "# lets encode the education in their degree of importance \n",
    "train['education'] = train['education'].replace((\"Master's & above\", \"Bachelor's\", \"Below Secondary\"),\n",
    "                                                (3, 2, 1))\n",
    "test['education'] = test['education'].replace((\"Master's & above\", \"Bachelor's\", \"Below Secondary\"),\n",
    "                                                (3, 2, 1))\n",
    "\n",
    "# lets use Label Encoding for Gender and Department to convert them into Numerical\n",
    "from sklearn.preprocessing import LabelEncoder\n",
    "\n",
    "le = LabelEncoder()\n",
    "train['department'] = le.fit_transform(train['department'])\n",
    "test['department'] = le.fit_transform(test['department'])\n",
    "train['gender'] = le.fit_transform(train['gender'])\n",
    "test['gender'] = le.fit_transform(test['gender'])\n",
    "\n",
    "# lets check whether we still have any categorical columns left after encoding\n",
    "print(train.select_dtypes('object').columns)\n",
    "print(test.select_dtypes('object').columns)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "A4-2EVf8NJqS"
   },
   "source": [
    "In the above case, since the 'department' and 'gender' columns have a relatively small number of categories, using LabelEncoder is a simpler and more efficient way to convert the categorical data into numerical data. If the number of categories in a column is large, one hot encoding might be a better choice"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 736,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 143
    },
    "id": "_15fLQ_-Mtqa",
    "outputId": "050c0099-2b57-4750-c3f7-2ac626d404f3"
   },
   "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>department</th>\n",
       "      <th>education</th>\n",
       "      <th>gender</th>\n",
       "      <th>no_of_trainings</th>\n",
       "      <th>age</th>\n",
       "      <th>previous_year_rating</th>\n",
       "      <th>length_of_service</th>\n",
       "      <th>awards_won?</th>\n",
       "      <th>avg_training_score</th>\n",
       "      <th>is_promoted</th>\n",
       "      <th>sum_metric</th>\n",
       "      <th>total_score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>7</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>35</td>\n",
       "      <td>5.0</td>\n",
       "      <td>8</td>\n",
       "      <td>0</td>\n",
       "      <td>49</td>\n",
       "      <td>0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>49</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>30</td>\n",
       "      <td>5.0</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>60</td>\n",
       "      <td>0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>60</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>7</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>34</td>\n",
       "      <td>3.0</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>50</td>\n",
       "      <td>0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>50</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   department  education  gender  no_of_trainings  age  previous_year_rating  \\\n",
       "0           7          3       0                1   35                   5.0   \n",
       "1           4          2       1                1   30                   5.0   \n",
       "2           7          2       1                1   34                   3.0   \n",
       "\n",
       "   length_of_service  awards_won?  avg_training_score  is_promoted  \\\n",
       "0                  8            0                  49            0   \n",
       "1                  4            0                  60            0   \n",
       "2                  7            0                  50            0   \n",
       "\n",
       "   sum_metric  total_score  \n",
       "0         5.0           49  \n",
       "1         5.0           60  \n",
       "2         3.0           50  "
      ]
     },
     "execution_count": 736,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# lets check the data after encoding\n",
    "train.head(3)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "8smpApdCNRuH"
   },
   "source": [
    "## Splitting the Data\n",
    "\n",
    "This is one of the most Important step to perform Machine Learning Prediction on a Dataset,\n",
    "We have to separate the Target and Independent Columns.\n",
    "* We store the Target Variable in y, and then we store the rest of the columns in x, by deleting the target column from the data\n",
    "* Also, we are changing the name of test dataset to x_test for ease of understanding."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 737,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "zO1xf974NOZD",
    "outputId": "2999918d-d9bc-4044-e69a-69725336f005"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Shape of the x : (52992, 11)\n",
      "Shape of the y : (52992,)\n",
      "Shape of the x Test : (23490, 11)\n"
     ]
    }
   ],
   "source": [
    "# lets split the target data from the train data\n",
    "\n",
    "y = train['is_promoted']\n",
    "x = train.drop(['is_promoted'], axis = 1)\n",
    "x_test = test\n",
    "\n",
    "# lets print the shapes of these newly formed data sets\n",
    "print(\"Shape of the x :\", x.shape)\n",
    "print(\"Shape of the y :\", y.shape)\n",
    "print(\"Shape of the x Test :\", x_test.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "aGO_BTN4Nf-U"
   },
   "source": [
    "## Resampling\n",
    "\n",
    "Resampling is the method that consists of drawing repeated samples from the original data samples. The method of Resampling is a nonparametric method of statistical inference.\n",
    "\n",
    "* Earlier, in this Problem we noticed that the Target column is Highly Imbalanced, we need to balance the data by using some Statistical Methods.\n",
    "* There are many Statistical Methods we can use for Resampling the Data such as:\n",
    "    * Over Samping\n",
    "    * Cluster based Sampling\n",
    "    * Under Sampling.\n",
    "    \n",
    "Oversampling and undersampling in data analysis are techniques used to adjust the class distribution of a data set. These terms are used both in statistical sampling, survey design methodology and in machine learning. Oversampling and undersampling are opposite and roughly equivalent techniques\n",
    "    \n",
    "* We are going to use Over Sampling. \n",
    "* We will not use Under Sampling to avoid data loss."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 738,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "xyyc3HnfNWQ_",
    "outputId": "c2eb376b-3acf-48f9-9d78-d2879e48400c"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    48462\n",
       "1     4530\n",
       "Name: is_promoted, dtype: int64"
      ]
     },
     "execution_count": 738,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train['is_promoted'].value_counts()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "_KERkbTJNoUA"
   },
   "source": [
    "There is quite a large difference between our both the classes so we have to do oversampling of our minority class in order to create a good model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 739,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "suLE1cCVNnG7",
    "outputId": "57edc6e7-a9c4-434d-be53-547f53fe7599"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(96924, 11)\n",
      "(96924,)\n"
     ]
    }
   ],
   "source": [
    "# Here We are going to use Over Sampling Technique to resample the data.\n",
    "# lets import the SMOTE algorithm to do the same.\n",
    "\n",
    "from imblearn.over_sampling import SMOTE\n",
    "\n",
    "x_resample, y_resample  = SMOTE().fit_resample(x, y.values.ravel())\n",
    "\n",
    "# lets print the shape of x and y after resampling it\n",
    "print(x_resample.shape)\n",
    "print(y_resample.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 740,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "4TXhSYBANz38",
    "outputId": "8444b4d5-5460-4f3e-acb6-2878f01c72d4"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Before Resampling :\n",
      "0    48462\n",
      "1     4530\n",
      "Name: is_promoted, dtype: int64\n",
      "After Resampling :\n",
      "0    48462\n",
      "1    48462\n",
      "Name: 0, dtype: int64\n"
     ]
    }
   ],
   "source": [
    "# lets also check the value counts of our target variable4\n",
    "\n",
    "print(\"Before Resampling :\")\n",
    "print(y.value_counts())\n",
    "\n",
    "print(\"After Resampling :\")\n",
    "y_resample = pd.DataFrame(y_resample)\n",
    "print(y_resample[0].value_counts())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 741,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "-zl044ocN_S2",
    "outputId": "ce7e38ff-fb0a-4018-ebad-56de5abfe030"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Shape of the x Train : (77539, 11)\n",
      "Shape of the y Train : (77539, 1)\n",
      "Shape of the x Valid : (19385, 11)\n",
      "Shape of the y Valid : (19385, 1)\n",
      "Shape of the x Test : (23490, 11)\n"
     ]
    }
   ],
   "source": [
    "# lets create a validation set from the training data so that we can check whether the model that we have created is good enough\n",
    "# lets import the train_test_split library from sklearn to do that\n",
    "\n",
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "x_train, x_valid, y_train, y_valid = train_test_split(x_resample, y_resample, test_size = 0.2, random_state = 0)\n",
    "\n",
    "# lets print the shapes again \n",
    "print(\"Shape of the x Train :\", x_train.shape)\n",
    "print(\"Shape of the y Train :\", y_train.shape)\n",
    "print(\"Shape of the x Valid :\", x_valid.shape)\n",
    "print(\"Shape of the y Valid :\", y_valid.shape)\n",
    "print(\"Shape of the x Test :\", x_test.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "zxNiwALSOPQ8"
   },
   "source": [
    "## Feature Scaling\n",
    "\n",
    "Feature scaling is a method used to normalize the range of independent variables or features of data. In data processing, it is also known as data normalization and is generally performed during the data preprocessing step"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 742,
   "metadata": {
    "id": "lMUG3P01OILu"
   },
   "outputs": [],
   "source": [
    "# It is very import to scale all the features of the dataset into the same scale\n",
    "# Here, we are going to use the standardization method, which is very commonly used.\n",
    "\n",
    "# lets import the standard scaler library from sklearn to do that\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "\n",
    "sc = StandardScaler()\n",
    "x_train = sc.fit_transform(x_train)\n",
    "x_valid = sc.transform(x_valid)\n",
    "x_test = sc.transform(x_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "zPEDc1Y6OX6H"
   },
   "source": [
    "##  Machine Learning Predictive Modelling\n",
    "\n",
    "Predictive modeling is a process that uses data and statistics to predict outcomes with data models. These models can be used to predict anything from sports outcomes and TV ratings to technological advances and corporate earnings. Predictive modeling is also often referred to as: Predictive analytics."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "4A0xWsSpObKQ"
   },
   "source": [
    "## Logistic Regression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 743,
   "metadata": {
    "id": "dAKuASiAOS4g"
   },
   "outputs": [],
   "source": [
    "from sklearn.linear_model import LogisticRegression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 744,
   "metadata": {
    "id": "gnLlkjQrOS6-"
   },
   "outputs": [],
   "source": [
    "lg = LogisticRegression()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 745,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 0
    },
    "id": "5eCWzdy6OS9s",
    "outputId": "569006c4-a40a-44cc-bc47-68f1277ddd1a"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-15 {color: black;background-color: white;}#sk-container-id-15 pre{padding: 0;}#sk-container-id-15 div.sk-toggleable {background-color: white;}#sk-container-id-15 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-15 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-15 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-15 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-15 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-15 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-15 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-15 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-15 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-15 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-15 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-15 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-15 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-15 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-15 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-15 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-15 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-15 div.sk-item {position: relative;z-index: 1;}#sk-container-id-15 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-15 div.sk-item::before, #sk-container-id-15 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-15 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-15 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-15 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-15 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-15 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-15 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-15 div.sk-label-container {text-align: center;}#sk-container-id-15 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-15 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-15\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LogisticRegression()</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-17\" type=\"checkbox\" checked><label for=\"sk-estimator-id-17\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LogisticRegression</label><div class=\"sk-toggleable__content\"><pre>LogisticRegression()</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "LogisticRegression()"
      ]
     },
     "execution_count": 745,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lg.fit(x_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 746,
   "metadata": {
    "id": "7IoF8UcOOTAW"
   },
   "outputs": [],
   "source": [
    "y_pred_lg = lg.predict(x_valid)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 747,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "8lW8AciSOzGP",
    "outputId": "676d7fcf-1c52-46dd-bb6c-cc71cf3cabf8"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 0, 1, ..., 0, 1, 0], dtype=int64)"
      ]
     },
     "execution_count": 747,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_pred_lg"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 748,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 0
    },
    "id": "CyN3wH3lO4GW",
    "outputId": "cab71ccf-a9ee-4e08-b620-2a2534f2bd16"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training Accuracy : 0.6913424212331859\n",
      "Testing Accuracy : 0.6919267474851689\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 216x216 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from sklearn.metrics import confusion_matrix, classification_report\n",
    "\n",
    "print(\"Training Accuracy :\", lg.score(x_train, y_train))\n",
    "print(\"Testing Accuracy :\", lg.score(x_valid, y_valid))\n",
    "\n",
    "cm = confusion_matrix(y_valid, y_pred_lg)\n",
    "plt.rcParams['figure.figsize'] = (3, 3)\n",
    "sns.heatmap(cm, annot = True, cmap = 'Wistia', fmt = '.8g')\n",
    "plt.xlabel('Predicted Values')\n",
    "plt.ylabel('Actual Values')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 749,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "HP8PKV3tQWAz",
    "outputId": "e7a636ad-f932-40f4-e2c4-04d72d335218"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.68      0.71      0.70      9633\n",
      "           1       0.70      0.67      0.69      9752\n",
      "\n",
      "    accuracy                           0.69     19385\n",
      "   macro avg       0.69      0.69      0.69     19385\n",
      "weighted avg       0.69      0.69      0.69     19385\n",
      "\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import classification_report\n",
    "\n",
    "print(classification_report(y_valid, y_pred_lg))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 750,
   "metadata": {
    "id": "n5wOsY2FZVNW"
   },
   "outputs": [],
   "source": [
    "y_pred_lg = list(y_pred_lg)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 751,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "y0w2PdxQZX3U",
    "outputId": "820548a4-4727-4051-c3c1-ae37f2b45e41"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " ...]"
      ]
     },
     "execution_count": 751,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_valid_lg = []\n",
    "for i in y_valid[0]:\n",
    "  y_valid_lg.append(i)\n",
    "y_valid_lg"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 752,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 0
    },
    "id": "BUwYQcFwZX6Z",
    "outputId": "bd5f2537-d4ce-478b-ee1b-5e68b4e87d48"
   },
   "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>Actual Values</th>\n",
       "      <th>Predicted Values</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19380</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19381</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19382</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19383</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19384</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>19385 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       Actual Values  Predicted Values\n",
       "0                  1                 0\n",
       "1                  1                 0\n",
       "2                  1                 1\n",
       "3                  0                 0\n",
       "4                  0                 0\n",
       "...              ...               ...\n",
       "19380              1                 1\n",
       "19381              1                 1\n",
       "19382              0                 0\n",
       "19383              1                 1\n",
       "19384              1                 0\n",
       "\n",
       "[19385 rows x 2 columns]"
      ]
     },
     "execution_count": 752,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "compare_lg = pd.DataFrame({'Actual Values': y_valid_lg, 'Predicted Values': y_pred_lg})\n",
    "\n",
    "compare_lg"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 753,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 0
    },
    "id": "ipGc1MZ-ZX9U",
    "outputId": "77bc2152-f233-4dd2-85d4-6fe35c04cb80"
   },
   "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>Actual Values</th>\n",
       "      <th>Predicted Values</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19369</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19370</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19376</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19377</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19384</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5972 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       Actual Values  Predicted Values\n",
       "0                  1                 0\n",
       "1                  1                 0\n",
       "10                 0                 1\n",
       "13                 1                 0\n",
       "15                 0                 1\n",
       "...              ...               ...\n",
       "19369              0                 1\n",
       "19370              1                 0\n",
       "19376              1                 0\n",
       "19377              0                 1\n",
       "19384              1                 0\n",
       "\n",
       "[5972 rows x 2 columns]"
      ]
     },
     "execution_count": 753,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "compare_lg[compare_lg['Actual Values'] != compare_lg['Predicted Values']]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "V5IC40_qPtQW"
   },
   "source": [
    "## KNN"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 754,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 74
    },
    "id": "2z24CBILPNCL",
    "outputId": "6e80b90e-54bd-42d1-dbd5-9c822feb083c"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-16 {color: black;background-color: white;}#sk-container-id-16 pre{padding: 0;}#sk-container-id-16 div.sk-toggleable {background-color: white;}#sk-container-id-16 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-16 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-16 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-16 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-16 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-16 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-16 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-16 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-16 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-16 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-16 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-16 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-16 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-16 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-16 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-16 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-16 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-16 div.sk-item {position: relative;z-index: 1;}#sk-container-id-16 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-16 div.sk-item::before, #sk-container-id-16 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-16 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-16 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-16 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-16 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-16 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-16 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-16 div.sk-label-container {text-align: center;}#sk-container-id-16 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-16 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-16\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>KNeighborsClassifier()</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-18\" type=\"checkbox\" checked><label for=\"sk-estimator-id-18\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">KNeighborsClassifier</label><div class=\"sk-toggleable__content\"><pre>KNeighborsClassifier()</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "KNeighborsClassifier()"
      ]
     },
     "execution_count": 754,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "knn = KNeighborsClassifier(n_neighbors = 5, metric = 'minkowski', p = 2)\n",
    "knn.fit(x_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 755,
   "metadata": {
    "id": "2Dyfr1BEP_rz"
   },
   "outputs": [],
   "source": [
    "y_pred_knn = knn.predict(x_valid)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 756,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "R01FaGtZQIJs",
    "outputId": "04114229-ff6f-4e7c-9278-5d972ebb631b"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1, 1, 1, ..., 1, 1, 1], dtype=int64)"
      ]
     },
     "execution_count": 756,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_pred_knn"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 757,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 277
    },
    "id": "NC2DP2b3QOmS",
    "outputId": "5831240d-970c-4afa-eb5e-9ec578b2b1a8"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training Accuracy : 0.9042030462090045\n",
      "Testing Accuracy : 0.8568480784111426\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 216x216 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "print(\"Training Accuracy :\", knn.score(x_train, y_train))\n",
    "print(\"Testing Accuracy :\", knn.score(x_valid, y_valid))\n",
    "\n",
    "cm = confusion_matrix(y_valid, y_pred_knn)\n",
    "plt.rcParams['figure.figsize'] = (3, 3)\n",
    "sns.heatmap(cm, annot = True, cmap = 'Wistia', fmt = '.8g')\n",
    "plt.xlabel('Predicted Values')\n",
    "plt.ylabel('Actual Values')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 758,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "AwHceIK8Qyau",
    "outputId": "5f430582-5e02-4171-f708-df3d7ee4c8fd"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.88      0.82      0.85      9633\n",
      "           1       0.84      0.89      0.86      9752\n",
      "\n",
      "    accuracy                           0.86     19385\n",
      "   macro avg       0.86      0.86      0.86     19385\n",
      "weighted avg       0.86      0.86      0.86     19385\n",
      "\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import classification_report\n",
    "\n",
    "print(classification_report(y_valid, y_pred_knn))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 759,
   "metadata": {
    "id": "6XhXOSWAYI7a"
   },
   "outputs": [],
   "source": [
    "y_pred_knn = list(y_pred_knn)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 760,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "mWw34sBSYI-O",
    "outputId": "b093c05e-f4dd-4d9a-f23b-9c1fd1aa3d27"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " ...]"
      ]
     },
     "execution_count": 760,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_valid_knn = []\n",
    "for i in y_valid[0]:\n",
    "  y_valid_knn.append(i)\n",
    "y_valid_knn"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 761,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 423
    },
    "id": "md7qFbHIYJBJ",
    "outputId": "fe3e6f70-60ca-4665-9e42-409c763ffc60"
   },
   "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>Actual Values</th>\n",
       "      <th>Predicted Values</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19380</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19381</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19382</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19383</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19384</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>19385 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       Actual Values  Predicted Values\n",
       "0                  1                 1\n",
       "1                  1                 1\n",
       "2                  1                 1\n",
       "3                  0                 0\n",
       "4                  0                 0\n",
       "...              ...               ...\n",
       "19380              1                 1\n",
       "19381              1                 1\n",
       "19382              0                 1\n",
       "19383              1                 1\n",
       "19384              1                 1\n",
       "\n",
       "[19385 rows x 2 columns]"
      ]
     },
     "execution_count": 761,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "compare_knn = pd.DataFrame({'Actual Values': y_valid_knn, 'Predicted Values': y_pred_knn})\n",
    "\n",
    "compare_knn"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 762,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 423
    },
    "id": "oH68cE2SZFrt",
    "outputId": "7108b316-72ba-4254-800e-ce24fddf6191"
   },
   "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>Actual Values</th>\n",
       "      <th>Predicted Values</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>55</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19365</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19369</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19370</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19371</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19382</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2775 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       Actual Values  Predicted Values\n",
       "6                  0                 1\n",
       "10                 0                 1\n",
       "13                 1                 0\n",
       "30                 0                 1\n",
       "55                 1                 0\n",
       "...              ...               ...\n",
       "19365              0                 1\n",
       "19369              0                 1\n",
       "19370              1                 0\n",
       "19371              0                 1\n",
       "19382              0                 1\n",
       "\n",
       "[2775 rows x 2 columns]"
      ]
     },
     "execution_count": 762,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "compare_knn[compare_knn['Actual Values'] != compare_knn['Predicted Values']]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "qQUuNH71VDCL"
   },
   "source": [
    "## Random Forest Classifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 763,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 74
    },
    "id": "dnyooP7gVBVZ",
    "outputId": "141ff7ae-e4ed-4d67-c52d-3537a43c6b7b"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-17 {color: black;background-color: white;}#sk-container-id-17 pre{padding: 0;}#sk-container-id-17 div.sk-toggleable {background-color: white;}#sk-container-id-17 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-17 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-17 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-17 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-17 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-17 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-17 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-17 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-17 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-17 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-17 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-17 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-17 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-17 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-17 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-17 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-17 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-17 div.sk-item {position: relative;z-index: 1;}#sk-container-id-17 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-17 div.sk-item::before, #sk-container-id-17 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-17 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-17 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-17 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-17 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-17 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-17 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-17 div.sk-label-container {text-align: center;}#sk-container-id-17 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-17 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-17\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestClassifier(random_state=0)</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-19\" type=\"checkbox\" checked><label for=\"sk-estimator-id-19\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestClassifier</label><div class=\"sk-toggleable__content\"><pre>RandomForestClassifier(random_state=0)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "RandomForestClassifier(random_state=0)"
      ]
     },
     "execution_count": 763,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.ensemble import RandomForestClassifier\n",
    "rf = RandomForestClassifier(random_state = 0)\n",
    "rf.fit(x_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 764,
   "metadata": {
    "id": "xQGWGDk8VUtL"
   },
   "outputs": [],
   "source": [
    "y_pred_rf = rf.predict(x_valid)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 765,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "YOPdihaYVZO8",
    "outputId": "2f41b05d-ae1d-4334-e09d-6da8631a8a5f"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1, 1, 1, ..., 1, 1, 1], dtype=int64)"
      ]
     },
     "execution_count": 765,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_pred_rf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 766,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 277
    },
    "id": "_um_Hj2BVagp",
    "outputId": "83f4f6b6-e6b7-4572-bcaf-08247f29d076"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training Accuracy : 0.9778692013051496\n",
      "Testing Accuracy : 0.9305132834665979\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 216x216 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "print(\"Training Accuracy :\", rf.score(x_train, y_train))\n",
    "print(\"Testing Accuracy :\", rf.score(x_valid, y_valid))\n",
    "\n",
    "cm = confusion_matrix(y_valid, y_pred_rf)\n",
    "plt.rcParams['figure.figsize'] = (3, 3)\n",
    "sns.heatmap(cm, annot = True, cmap = 'Wistia', fmt = '.8g')\n",
    "plt.xlabel('Predicted Values')\n",
    "plt.ylabel('Actual Values')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 767,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "yvF_OtmyVhwD",
    "outputId": "200ca000-92df-4185-97d6-db86b4f62017"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.94      0.92      0.93      9633\n",
      "           1       0.92      0.94      0.93      9752\n",
      "\n",
      "    accuracy                           0.93     19385\n",
      "   macro avg       0.93      0.93      0.93     19385\n",
      "weighted avg       0.93      0.93      0.93     19385\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(classification_report(y_valid, y_pred_rf))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 768,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "7ELpqSkkVofb",
    "outputId": "e4e8abdb-c1f6-4d94-c51f-45a3f098e9cb"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1, 1, 1, ..., 1, 1, 1], dtype=int64)"
      ]
     },
     "execution_count": 768,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_pred_rf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 769,
   "metadata": {
    "id": "LFHQB3j3W1cw"
   },
   "outputs": [],
   "source": [
    "y_pred_rf = list(y_pred_rf)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 770,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "jrUwSH6AWIiQ",
    "outputId": "02456ac0-db5f-46ba-dc2a-1aba5938f6af"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " ...]"
      ]
     },
     "execution_count": 770,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_valid_rf = []\n",
    "for i in y_valid[0]:\n",
    "  y_valid_rf.append(i)\n",
    "y_valid_rf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 771,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 423
    },
    "id": "TbTzzfm-WKbr",
    "outputId": "e834badf-6a86-497b-ec1c-b9cb63257f1b"
   },
   "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>Actual Values</th>\n",
       "      <th>Predicted Values</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19380</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19381</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19382</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19383</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19384</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>19385 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       Actual Values  Predicted Values\n",
       "0                  1                 1\n",
       "1                  1                 1\n",
       "2                  1                 1\n",
       "3                  0                 0\n",
       "4                  0                 0\n",
       "...              ...               ...\n",
       "19380              1                 1\n",
       "19381              1                 1\n",
       "19382              0                 1\n",
       "19383              1                 1\n",
       "19384              1                 1\n",
       "\n",
       "[19385 rows x 2 columns]"
      ]
     },
     "execution_count": 771,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "compare_rf = pd.DataFrame({'Actual Values': y_valid_rf, 'Predicted Values': y_pred_rf})\n",
    "\n",
    "compare_rf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 772,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 423
    },
    "id": "WNhu7lArXQzu",
    "outputId": "37448d40-0efa-45ae-c7aa-74a33f142ef4"
   },
   "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>Actual Values</th>\n",
       "      <th>Predicted Values</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>55</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>58</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>91</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>95</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19345</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19355</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19357</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19377</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19382</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1347 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       Actual Values  Predicted Values\n",
       "10                 0                 1\n",
       "55                 1                 0\n",
       "58                 0                 1\n",
       "91                 1                 0\n",
       "95                 1                 0\n",
       "...              ...               ...\n",
       "19345              0                 1\n",
       "19355              1                 0\n",
       "19357              1                 0\n",
       "19377              0                 1\n",
       "19382              0                 1\n",
       "\n",
       "[1347 rows x 2 columns]"
      ]
     },
     "execution_count": 772,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "compare_rf[compare_rf['Actual Values'] != compare_rf['Predicted Values']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 773,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "XMGOj4lgjcrJ",
    "outputId": "98413a22-2ad9-41ba-c620-c22e74833673"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "((77539, 11), (77539, 1))"
      ]
     },
     "execution_count": 773,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_train.shape, y_train.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 774,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 394
    },
    "id": "RDj6zFb9_rbd",
    "outputId": "d38db945-53cf-4780-ff2f-772d09e94676"
   },
   "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>feature</th>\n",
       "      <th>importance</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>sum_metric</td>\n",
       "      <td>0.200714</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>age</td>\n",
       "      <td>0.161918</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>previous_year_rating</td>\n",
       "      <td>0.154727</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>avg_training_score</td>\n",
       "      <td>0.136921</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>length_of_service</td>\n",
       "      <td>0.110861</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>total_score</td>\n",
       "      <td>0.109354</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>department</td>\n",
       "      <td>0.070437</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>gender</td>\n",
       "      <td>0.024362</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>education</td>\n",
       "      <td>0.016129</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>no_of_trainings</td>\n",
       "      <td>0.010493</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>awards_won?</td>\n",
       "      <td>0.004085</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                 feature  importance\n",
       "9             sum_metric    0.200714\n",
       "4                    age    0.161918\n",
       "5   previous_year_rating    0.154727\n",
       "8     avg_training_score    0.136921\n",
       "6      length_of_service    0.110861\n",
       "10           total_score    0.109354\n",
       "0             department    0.070437\n",
       "2                 gender    0.024362\n",
       "1              education    0.016129\n",
       "3        no_of_trainings    0.010493\n",
       "7            awards_won?    0.004085"
      ]
     },
     "execution_count": 774,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# extracting feature importances\n",
    "importances = rf.feature_importances_\n",
    "\n",
    "# creating a dataframe with feature names and their corresponding importances\n",
    "feature_importances_df = pd.DataFrame({'feature': ['department', 'education', 'gender', 'no_of_trainings', 'age',\n",
    "                                                   'previous_year_rating', 'length_of_service', 'awards_won?',\n",
    "                                                   'avg_training_score','sum_metric', 'total_score'], \n",
    "                                       'importance': importances})\n",
    "\n",
    "# sorting the dataframe by feature importances in descending order\n",
    "feature_importances_df = feature_importances_df.sort_values(by=['importance'], ascending=False)\n",
    "\n",
    "\n",
    "feature_importances_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 775,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 441
    },
    "id": "Y_a8X68QBpGw",
    "outputId": "231fcbfe-9b46-4953-a255-498cfe58926f"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x432 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# creating a bar plot of feature importances\n",
    "sns.set_style('whitegrid')\n",
    "plt.figure(figsize=(10, 6))\n",
    "ax = sns.barplot(x='importance', y='feature', data=feature_importances_df, color='crimson')\n",
    "plt.xlabel('Importance')\n",
    "plt.ylabel('Feature')\n",
    "plt.title('Feature Importances')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "A3z1A39Of-a0"
   },
   "source": [
    "## Predicting on unknown data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "94fECOIDhGzX"
   },
   "source": [
    "Now we will perform Real Time Predictions using the Model which we have created.\n",
    "\n",
    "So, lets get started, \n",
    "* First, we we will check the descriptive summary of the data again, so that we can analyze the columns and values which we can provide to the Model as Input and expect the Model to return Output whether the Employee should get a promotion or not.\n",
    "\n",
    "* Then we will define the value for which we want the predction, and then finally we will predict the values."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 776,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 364
    },
    "id": "McS2kot8hWYS",
    "outputId": "a9bb53ea-6fc3-4eef-a4bd-ab2718248132"
   },
   "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>department</th>\n",
       "      <th>education</th>\n",
       "      <th>gender</th>\n",
       "      <th>no_of_trainings</th>\n",
       "      <th>age</th>\n",
       "      <th>previous_year_rating</th>\n",
       "      <th>length_of_service</th>\n",
       "      <th>awards_won?</th>\n",
       "      <th>avg_training_score</th>\n",
       "      <th>is_promoted</th>\n",
       "      <th>sum_metric</th>\n",
       "      <th>total_score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>52992.000000</td>\n",
       "      <td>52992.000000</td>\n",
       "      <td>52992.000000</td>\n",
       "      <td>52992.000000</td>\n",
       "      <td>52992.000000</td>\n",
       "      <td>52992.000000</td>\n",
       "      <td>52992.000000</td>\n",
       "      <td>52992.000000</td>\n",
       "      <td>52992.000000</td>\n",
       "      <td>52992.000000</td>\n",
       "      <td>52992.000000</td>\n",
       "      <td>52992.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>4.958296</td>\n",
       "      <td>2.249132</td>\n",
       "      <td>0.702823</td>\n",
       "      <td>1.255944</td>\n",
       "      <td>34.254321</td>\n",
       "      <td>3.304725</td>\n",
       "      <td>5.381869</td>\n",
       "      <td>0.023645</td>\n",
       "      <td>63.431273</td>\n",
       "      <td>0.085485</td>\n",
       "      <td>3.328370</td>\n",
       "      <td>80.021588</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>2.516290</td>\n",
       "      <td>0.466317</td>\n",
       "      <td>0.457019</td>\n",
       "      <td>0.611910</td>\n",
       "      <td>7.121299</td>\n",
       "      <td>1.214213</td>\n",
       "      <td>3.352458</td>\n",
       "      <td>0.151942</td>\n",
       "      <td>13.404240</td>\n",
       "      <td>0.279604</td>\n",
       "      <td>1.227811</td>\n",
       "      <td>44.125775</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>20.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>39.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>39.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>4.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>29.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>51.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>53.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>5.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>33.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>60.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>64.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>7.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>38.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>76.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>84.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>8.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>10.000000</td>\n",
       "      <td>60.000000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>16.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>99.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>710.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         department     education        gender  no_of_trainings  \\\n",
       "count  52992.000000  52992.000000  52992.000000     52992.000000   \n",
       "mean       4.958296      2.249132      0.702823         1.255944   \n",
       "std        2.516290      0.466317      0.457019         0.611910   \n",
       "min        0.000000      1.000000      0.000000         1.000000   \n",
       "25%        4.000000      2.000000      0.000000         1.000000   \n",
       "50%        5.000000      2.000000      1.000000         1.000000   \n",
       "75%        7.000000      3.000000      1.000000         1.000000   \n",
       "max        8.000000      3.000000      1.000000        10.000000   \n",
       "\n",
       "                age  previous_year_rating  length_of_service   awards_won?  \\\n",
       "count  52992.000000          52992.000000       52992.000000  52992.000000   \n",
       "mean      34.254321              3.304725           5.381869      0.023645   \n",
       "std        7.121299              1.214213           3.352458      0.151942   \n",
       "min       20.000000              1.000000           1.000000      0.000000   \n",
       "25%       29.000000              3.000000           3.000000      0.000000   \n",
       "50%       33.000000              3.000000           5.000000      0.000000   \n",
       "75%       38.000000              4.000000           7.000000      0.000000   \n",
       "max       60.000000              5.000000          16.000000      1.000000   \n",
       "\n",
       "       avg_training_score   is_promoted    sum_metric   total_score  \n",
       "count        52992.000000  52992.000000  52992.000000  52992.000000  \n",
       "mean            63.431273      0.085485      3.328370     80.021588  \n",
       "std             13.404240      0.279604      1.227811     44.125775  \n",
       "min             39.000000      0.000000      1.000000     39.000000  \n",
       "25%             51.000000      0.000000      3.000000     53.000000  \n",
       "50%             60.000000      0.000000      3.000000     64.000000  \n",
       "75%             76.000000      0.000000      4.000000     84.000000  \n",
       "max             99.000000      1.000000      6.000000    710.000000  "
      ]
     },
     "execution_count": 776,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 777,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "QnJBOq1KC9Lm",
    "outputId": "18d1695a-caaf-4535-e8cc-d2ff19f7e758"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['department', 'education', 'gender', 'no_of_trainings', 'age',\n",
       "       'previous_year_rating', 'length_of_service', 'awards_won?',\n",
       "       'avg_training_score', 'is_promoted', 'sum_metric', 'total_score'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 777,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 778,
   "metadata": {
    "id": "gBjIxdERgB4g"
   },
   "outputs": [],
   "source": [
    "new_data = np.array([(2, #department code\n",
    "                      3, #masters degree\n",
    "                      1, #male\n",
    "                      1, #1 training\n",
    "                      30, #30 years old\n",
    "                      5, #previous year rating\n",
    "                      10, #length of service\n",
    "                      1, #awards won\n",
    "                      95, #avg training score\n",
    "                      7, #sum of metric \n",
    "                      700 #total score\n",
    "                     )])\n",
    "new_data = sc.transform(new_data)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 779,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "zDShgB6ogwMl",
    "outputId": "f2642ee7-6f67-486d-f127-759b1a7d5c15"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Whether the Employee should get a Promotion : 1-> Promotion, and 0-> No Promotion : [1]\n"
     ]
    }
   ],
   "source": [
    "final_prediction = rf.predict(new_data)\n",
    "print(\"Whether the Employee should get a Promotion : 1-> Promotion, and 0-> No Promotion :\", final_prediction)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "ww4cyuQloMhH"
   },
   "source": [
    "## Predicting for our test data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 780,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "ptnv2JiOmrSZ",
    "outputId": "c62b86a2-786c-4865-e09e-c484a60ab0c1"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Whether the Employee should get a Promotion : 1-> Promotion, and 0-> No Promotion : [0 0 0 ... 0 0 1]\n"
     ]
    }
   ],
   "source": [
    "test_data_final_prediction = rf.predict(x_test)\n",
    "print(\"Whether the Employee should get a Promotion : 1-> Promotion, and 0-> No Promotion :\", test_data_final_prediction)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 781,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "d7Qz2wKrmyS9",
    "outputId": "b8d72939-ddea-40e3-cf8d-3c2433295c28"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 1,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " 0,\n",
       " ...]"
      ]
     },
     "execution_count": 781,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_data_final_prediction = list(test_data_final_prediction)\n",
    "test_data_final_prediction"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 782,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "B_K0LVfcnRN7",
    "outputId": "f314fa23-4cae-4397-ab32-bb5ea0a8be29"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "23490"
      ]
     },
     "execution_count": 782,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(test_data_final_prediction)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 783,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "quovkFc2nF-j",
    "outputId": "da77b9f5-add1-4701-a11f-967bff6e7ba7"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "23490"
      ]
     },
     "execution_count": 783,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(x_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 784,
   "metadata": {
    "id": "Yli6T0HTnWc8"
   },
   "outputs": [],
   "source": [
    "test['is_promoted'] = test_data_final_prediction"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 785,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 206
    },
    "id": "VLCjrx5unqJg",
    "outputId": "df9701a5-e516-4c51-f2fe-d73f7cb3e33e"
   },
   "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>department</th>\n",
       "      <th>education</th>\n",
       "      <th>gender</th>\n",
       "      <th>no_of_trainings</th>\n",
       "      <th>age</th>\n",
       "      <th>previous_year_rating</th>\n",
       "      <th>length_of_service</th>\n",
       "      <th>awards_won?</th>\n",
       "      <th>avg_training_score</th>\n",
       "      <th>sum_metric</th>\n",
       "      <th>total_score</th>\n",
       "      <th>is_promoted</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>8</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>24</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>77</td>\n",
       "      <td>3.0</td>\n",
       "      <td>77</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>31</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>51</td>\n",
       "      <td>3.0</td>\n",
       "      <td>51</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>7</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>31</td>\n",
       "      <td>1.0</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>47</td>\n",
       "      <td>1.0</td>\n",
       "      <td>47</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>31</td>\n",
       "      <td>2.0</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "      <td>65</td>\n",
       "      <td>2.0</td>\n",
       "      <td>195</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>30</td>\n",
       "      <td>4.0</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>61</td>\n",
       "      <td>4.0</td>\n",
       "      <td>61</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   department  education  gender  no_of_trainings  age  previous_year_rating  \\\n",
       "0           8          2       1                1   24                   3.0   \n",
       "1           2          2       0                1   31                   3.0   \n",
       "2           7          2       1                1   31                   1.0   \n",
       "3           5          2       0                3   31                   2.0   \n",
       "4           1          2       1                1   30                   4.0   \n",
       "\n",
       "   length_of_service  awards_won?  avg_training_score  sum_metric  \\\n",
       "0                  1            0                  77         3.0   \n",
       "1                  5            0                  51         3.0   \n",
       "2                  4            0                  47         1.0   \n",
       "3                  9            0                  65         2.0   \n",
       "4                  7            0                  61         4.0   \n",
       "\n",
       "   total_score  is_promoted  \n",
       "0           77            0  \n",
       "1           51            0  \n",
       "2           47            0  \n",
       "3          195            0  \n",
       "4           61            0  "
      ]
     },
     "execution_count": 785,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 786,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 423
    },
    "id": "3HGgbV5jnr0-",
    "outputId": "ccdc9861-7c18-48cf-c9ed-c7758a81a791"
   },
   "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>department</th>\n",
       "      <th>education</th>\n",
       "      <th>gender</th>\n",
       "      <th>no_of_trainings</th>\n",
       "      <th>age</th>\n",
       "      <th>previous_year_rating</th>\n",
       "      <th>length_of_service</th>\n",
       "      <th>awards_won?</th>\n",
       "      <th>avg_training_score</th>\n",
       "      <th>sum_metric</th>\n",
       "      <th>total_score</th>\n",
       "      <th>is_promoted</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>8</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>29</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>76</td>\n",
       "      <td>5.0</td>\n",
       "      <td>76</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>7</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>37</td>\n",
       "      <td>5.0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>47</td>\n",
       "      <td>5.0</td>\n",
       "      <td>47</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>40</th>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>26</td>\n",
       "      <td>5.0</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>90</td>\n",
       "      <td>5.0</td>\n",
       "      <td>90</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>63</th>\n",
       "      <td>8</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>23</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>81</td>\n",
       "      <td>3.0</td>\n",
       "      <td>81</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>67</th>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>28</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>59</td>\n",
       "      <td>3.0</td>\n",
       "      <td>59</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",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23461</th>\n",
       "      <td>7</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>27</td>\n",
       "      <td>4.0</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>48</td>\n",
       "      <td>4.0</td>\n",
       "      <td>96</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23470</th>\n",
       "      <td>7</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>36</td>\n",
       "      <td>5.0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>49</td>\n",
       "      <td>5.0</td>\n",
       "      <td>49</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23472</th>\n",
       "      <td>8</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>29</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>87</td>\n",
       "      <td>3.0</td>\n",
       "      <td>87</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23475</th>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>28</td>\n",
       "      <td>3.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>61</td>\n",
       "      <td>3.0</td>\n",
       "      <td>61</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23489</th>\n",
       "      <td>8</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>40</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>89</td>\n",
       "      <td>5.0</td>\n",
       "      <td>267</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2471 rows × 12 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       department  education  gender  no_of_trainings  age  \\\n",
       "9               8          2       1                1   29   \n",
       "20              7          3       1                1   37   \n",
       "40              0          2       1                1   26   \n",
       "63              8          1       1                1   23   \n",
       "67              4          2       1                1   28   \n",
       "...           ...        ...     ...              ...  ...   \n",
       "23461           7          2       0                2   27   \n",
       "23470           7          2       1                1   36   \n",
       "23472           8          2       0                1   29   \n",
       "23475           3          2       0                1   28   \n",
       "23489           8          3       1                3   40   \n",
       "\n",
       "       previous_year_rating  length_of_service  awards_won?  \\\n",
       "9                       5.0                  2            0   \n",
       "20                      5.0                  3            0   \n",
       "40                      5.0                  4            0   \n",
       "63                      3.0                  1            0   \n",
       "67                      3.0                  3            0   \n",
       "...                     ...                ...          ...   \n",
       "23461                   4.0                  4            0   \n",
       "23470                   5.0                  3            0   \n",
       "23472                   3.0                  3            0   \n",
       "23475                   3.0                  2            0   \n",
       "23489                   5.0                  5            0   \n",
       "\n",
       "       avg_training_score  sum_metric  total_score  is_promoted  \n",
       "9                      76         5.0           76            1  \n",
       "20                     47         5.0           47            1  \n",
       "40                     90         5.0           90            1  \n",
       "63                     81         3.0           81            1  \n",
       "67                     59         3.0           59            1  \n",
       "...                   ...         ...          ...          ...  \n",
       "23461                  48         4.0           96            1  \n",
       "23470                  49         5.0           49            1  \n",
       "23472                  87         3.0           87            1  \n",
       "23475                  61         3.0           61            1  \n",
       "23489                  89         5.0          267            1  \n",
       "\n",
       "[2471 rows x 12 columns]"
      ]
     },
     "execution_count": 786,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test[test['is_promoted']==1]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "qM7Mrf2Cny9v"
   },
   "source": [
    "### There are 2495 people who will get promotion according to our model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 787,
   "metadata": {
    "id": "gjDT5oKinxpb"
   },
   "outputs": [],
   "source": [
    "import pickle\n",
    "\n",
    "# Save the model to a file using pickle\n",
    "with open('rf.pkl', 'wb') as file:\n",
    "    pickle.dump(rf, file)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 788,
   "metadata": {
    "id": "24fAvRKPpyae"
   },
   "outputs": [],
   "source": [
    "import pickle\n",
    "\n",
    "# Save the standard scaler object to a file using pickle\n",
    "with open('sc.pkl', 'wb') as file:\n",
    "    pickle.dump(sc, file)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "qJoj2-ZnqPQy"
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "provenance": []
  },
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}