MedicalInsuranceCost.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Health Insurance Cost Prediction- A Machine Learning Approach"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Importing Libraries:\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>age</th>\n",
       "      <th>sex</th>\n",
       "      <th>bmi</th>\n",
       "      <th>smoker</th>\n",
       "      <th>region</th>\n",
       "      <th>children</th>\n",
       "      <th>charges</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>21.000000</td>\n",
       "      <td>male</td>\n",
       "      <td>25.745000</td>\n",
       "      <td>no</td>\n",
       "      <td>northeast</td>\n",
       "      <td>2</td>\n",
       "      <td>3279.868550</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>36.976978</td>\n",
       "      <td>female</td>\n",
       "      <td>25.744165</td>\n",
       "      <td>yes</td>\n",
       "      <td>southeast</td>\n",
       "      <td>3</td>\n",
       "      <td>21454.494239</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>18.000000</td>\n",
       "      <td>male</td>\n",
       "      <td>30.030000</td>\n",
       "      <td>no</td>\n",
       "      <td>southeast</td>\n",
       "      <td>1</td>\n",
       "      <td>1720.353700</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>37.000000</td>\n",
       "      <td>male</td>\n",
       "      <td>30.676891</td>\n",
       "      <td>no</td>\n",
       "      <td>northeast</td>\n",
       "      <td>3</td>\n",
       "      <td>6801.437542</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>58.000000</td>\n",
       "      <td>male</td>\n",
       "      <td>32.010000</td>\n",
       "      <td>no</td>\n",
       "      <td>southeast</td>\n",
       "      <td>1</td>\n",
       "      <td>11946.625900</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         age     sex        bmi smoker     region  children       charges\n",
       "0  21.000000    male  25.745000     no  northeast         2   3279.868550\n",
       "1  36.976978  female  25.744165    yes  southeast         3  21454.494239\n",
       "2  18.000000    male  30.030000     no  southeast         1   1720.353700\n",
       "3  37.000000    male  30.676891     no  northeast         3   6801.437542\n",
       "4  58.000000    male  32.010000     no  southeast         1  11946.625900"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_data = pd.read_csv('Train_Data.csv')\n",
    "# Top 5 records\n",
    "train_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(3630, 7)"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# No of rows & columns\n",
    "train_data.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "age         0\n",
       "sex         0\n",
       "bmi         0\n",
       "smoker      0\n",
       "region      0\n",
       "children    0\n",
       "charges     0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Cheacking for Missing Values\n",
    "train_data.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 3630 entries, 0 to 3629\n",
      "Data columns (total 7 columns):\n",
      "age         3630 non-null float64\n",
      "sex         3630 non-null object\n",
      "bmi         3630 non-null float64\n",
      "smoker      3630 non-null object\n",
      "region      3630 non-null object\n",
      "children    3630 non-null int64\n",
      "charges     3630 non-null float64\n",
      "dtypes: float64(3), int64(1), object(3)\n",
      "memory usage: 198.6+ KB\n"
     ]
    }
   ],
   "source": [
    "# Info of the dataset\n",
    "train_data.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>age</th>\n",
       "      <th>bmi</th>\n",
       "      <th>children</th>\n",
       "      <th>charges</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>3630.000000</td>\n",
       "      <td>3630.000000</td>\n",
       "      <td>3630.000000</td>\n",
       "      <td>3630.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>38.887036</td>\n",
       "      <td>30.629652</td>\n",
       "      <td>2.503581</td>\n",
       "      <td>12784.808644</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>12.151029</td>\n",
       "      <td>5.441307</td>\n",
       "      <td>1.712568</td>\n",
       "      <td>10746.166743</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>18.000000</td>\n",
       "      <td>15.960000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1121.873900</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>29.000000</td>\n",
       "      <td>26.694526</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>5654.818262</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>39.170922</td>\n",
       "      <td>30.200000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>9443.807222</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>48.343281</td>\n",
       "      <td>34.100000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>14680.407505</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>64.000000</td>\n",
       "      <td>53.130000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>63770.428010</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               age          bmi     children       charges\n",
       "count  3630.000000  3630.000000  3630.000000   3630.000000\n",
       "mean     38.887036    30.629652     2.503581  12784.808644\n",
       "std      12.151029     5.441307     1.712568  10746.166743\n",
       "min      18.000000    15.960000     0.000000   1121.873900\n",
       "25%      29.000000    26.694526     1.000000   5654.818262\n",
       "50%      39.170922    30.200000     3.000000   9443.807222\n",
       "75%      48.343281    34.100000     4.000000  14680.407505\n",
       "max      64.000000    53.130000     5.000000  63770.428010"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Description of dataset in Numerical\n",
    "train_data.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>sex</th>\n",
       "      <th>smoker</th>\n",
       "      <th>region</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>3630</td>\n",
       "      <td>3630</td>\n",
       "      <td>3630</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>unique</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>top</th>\n",
       "      <td>male</td>\n",
       "      <td>no</td>\n",
       "      <td>southeast</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>freq</th>\n",
       "      <td>2029</td>\n",
       "      <td>3070</td>\n",
       "      <td>1021</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         sex smoker     region\n",
       "count   3630   3630       3630\n",
       "unique     2      2          4\n",
       "top     male     no  southeast\n",
       "freq    2029   3070       1021"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Description of dataset in Categorical format\n",
    "train_data.describe(include=['O'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Medical Insurance Charges:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAfQAAAFSCAYAAAAEky15AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8vihELAAAACXBIWXMAAAsTAAALEwEAmpwYAABDHUlEQVR4nO3deXxcdb3/8ddnsjdJ07RN0nSje0tboJTSAmVfZBGpCyr+FAEX0IuKy9Urgtu94lXvletyhSuigogiggoie6FUEAotli5039MlSZesbZMm+fz+OCcwTSdrO5lk5v18POYxk+/5nnM+58xkPnO+3+85x9wdERER6d8iiQ5AREREjp4SuoiISBJQQhcREUkCSugiIiJJQAldREQkCSihi4iIJAEldOl3zGyMmbmZ3dOm/J6wfEwvxrLAzHTup+izIAmnhC6dCpOkm1mLmY3voN7zUXWv7cUQ+43WL30zOzfRsUjHzCzXzD5vZs+ZWYWZNZpZlZm9ama3mdm4RMcoEk0JXbqqCTDg47EmmtlE4JywXqLcDBwPbE9gDJIEzOw0YA3wP8BE4HHgv4F7gYPAvwGrzWxmwoIUaSM90QFIv1EO7ASuM7NvuHvbxP0JgoT/GPDuXo4NAHffSRCjSI+Z2RTgKSAP+Crww7afdzMbC3wfGNj7EYrEpiN06Y5fAMOAy6MLzSwDuAb4B7CyvZnNbLCZ/aeZrTKzA2ZWbWbzzewd7dTPN7PbzazMzA6a2Woz+yLtfG476kM3s9lm9gcz225mDWa208yeNrMPtKl3rZk9bGYbwxhrzOwlM/tIJ/vmqJjZ5vAxwMz+y8y2hnGuN7N/MzOLMc8V4f7bGdbdYWYvmNm/xFp2O+v9VqwugLBsgZkNM7O7w/3W3NqVYmaTzOx7ZrbYzCrD9W8xs7vMbGSM9ZwbLvNbZjbDzP4WNl/vD2M+o5340szsU+F7UB2+J+vDmCa2qZtuZv9iZq+E79t+M/unmX3GzLrzXfdTgkT9fXf/fowfr7j7Jnf/APByjJjTzexrZrYu3C/bzOz7ZpYZo+67zey3ZrbWzOrNrM7MlpjZ52LFHPUZH2dmnzWzZeE+WRBVZ1L4Gd4XLvMfZvbO8LMdszvMzEaa2f+Gn/sGM9tjZo+a2akx6uab2dfNbEW4n2vNbEP4/3VKF/avxImO0KU7fg/cTnA0/peo8iuAEoKjmQmxZjSz44AFwBjg78CTQC7Bj4MnzewGd/9FVP0sYD5wKvAGcD8wCPg6QdN+l5nZJ4E7gWbgUWAdUAzMAv4FeDCq+p3Am8BCgqP9IcBlwH1mNtndv96ddXdTBvA0MBx4gqD74t3A94Bs4NtR23Q98HNgF/BXYHe4TScC1wF3HIN4BgOvAHXAn4AWgpYagPcCnwKeJ/gh1whMI/hsvMvMZrl7rK6PWcBXCBLh3cBo4H3AfDOb4e5rorYxE/gbcCGwDfgdUEPwGXoP8CLBe9n6o/KvwMUETeW/I2gaP48gQc8Bru5sgy048r4wnPcHndV394YYxb8DziJ4D2sIPj9fIXh/rmtT93sE+3URQVdRAXA+8GOCz357Mf84XMffCLoDmsP4pwAvEbx3fwOWAeOAP4f1jmBBt8HT4TxPEbzXQwk+ey+a2Xvc/fGwrhH8757B2+9hEzAKOJfgf3tJOzFLvLm7Hnp0+AAcKAtft/4Dj4ya/iRQDQwAvhPWv7bNMhYQfHFd1aZ8ELAUOACURJV/LVzOw0AkqnwssDecdk+bZd0Tlo+JKpsKHArnmRZj20a2+Xt8jDqZBD8uDgEjYmyXd2NfLghjPLdN+eaw/HEgJ6q8GKgKHxlR5UuABqA4xjqGxlj25nbi+VY78Xj4+A2QHmO+EUBWjPJ3ECSXO9uUnxu1zLafjRvC8jvalH83LH+07bqALKAoxnb8FEiLKk8DfhlOm9eF9+fqsO6LPfg/aX1vlwCDo8pzgfXhfhnWhc9bhKCv3oE57XzGtwNjY8w7P5z+6Tbll8ba/wQHdesJfsCc02ae4eF6drbuf+CEcBl/bifuwu7uNz2O3UNN7tJdvyD4kvwYvHXkfRFwv7vvjzWDmZ1EcFT9sLs/ED3N3auAbxIcgb4vatJ1BD8AvuLuLVH1NwE/6Ua8nyb40voPdz+iO8Ddy9r8vSFGnUbgZ+FyLujGunvic+5+IGrdFcAjBEduk9vUbSL4kXEYd999jGJpBP7VYzc5b/cYR6fu/jRBt8vF7SzzJXe/p03Zrwi2ZXZrgZmlEbSeHAA+1XZd7t7g7pVh3QjwGYLWii+4e3NUvWbgSwRJ6MMdbm2gNHwu67BWx/7N3fdGxVBP0MIUIWihiN6OWJ+3FoIjcGh/P/4g/F94i5mNIji6X0/QehO9zCeAZ2Ms553AeOCn7v5Cm3l2ELRSDOPIz/2BNn/j7i3uvq+deKUXqMldusXdF5nZcuBjZvYdgibWCEGib8/p4XOBmX0rxvSi8Pl4CProCJrut8X6wiM4EvpmF0M+LXx+oiuVzWw0wQjmCwiag3PaVBnRxfX2RLW7r49Rvi18Lowqux/4IbDSzP4AvECQLCuPYTybwx8URwibXj8MXAucFMaWFlWlsZ1lLm5b4O6HzKycw7dvCsGPmEVhYunIJIKukXXArXbkcAMIEtDxnSwHgoGdEPwA6KkjtpHY7yFmNgT4MkGz/DiCo/lo7X3eXo1RNiN8fjn6R3CUFwm6E6K1/m8e187/Zus4heMJWo/eJGhR+1D4Y/6RcLmLwx++kkBK6NITvyA4Sr6E4Eh6ibv/s4P6Q8Lni8JHe/LC54Lwubyderu6GCcETfrQhVPZLDiv+FWCL92/E/QrVhM0lY4hGPiX1Y11d1dVO+WtR8hvJUx3v93MdhMcxX4O+DzgZvYC8GV3j5VUuquj/Xx7uM6dBP2u23n7qO1a4Lh25qtqp7yJw38QDAqfu3IKYuvnayId/9DL62Baq9YfD0cM7OuqsNWprSPeQzMbBLxG0I30KkH3xt6w7iDgJtr/vMV6bzr7v4lV3rrv3t/OPK3yIGjxMLPzgW8AVxKM9AeoNbN7gZvdva6TZUmcKKFLT9xH8I/8c4IjiH/vpH51+HyTu3eluby1fkk704d1YRmtqsLnEcDqTup+keAL7rq2zcJm9iGChN5nuPtvgN+EieEMgoFiHwOeMrPjo46uWwjGAcQyqKNVxCo0s2KCHxErgDPcvbbN9A91dRs6UBU+d6VFpPXz8md3f+9RrvfF8HmWmRW4e3WHtY/OJwiS+bfd/VvRE8zsdIKE3p5Y701N+Nze/02s8tbtm+fuj3awvrdXHDSrfwH4gplNIOhOu4Gg22MQXRh8KPGhPnTptvAI5CGCo5h6gtHvHXklfD6ri8uvJegHHGGxr0x3bpcCPXzdl3ahbusI/YdjTOvWyPre5O5V7v64u3+SYNDUYA7f1/uAknAkeFuzYpR1ZhzBd8fTMZL5yHD60VpNkNRPNLPhXax7Wjvb2GVhv/SzBGM6vtxZ/fBsjJ461p+31lay09s5Te/MGGXd+t9sy93Xu/svCeKtA+b1ZDlybCihS0/dSnBEeHHbL/W2wubfvwPvNbOPxapjZieER36tfk3w+fx+9JdTeFrR57oR550ETZhfN7OpMdYb3bS6OXw+t02diwmOpvoMM7vEzGK1sLXuw+gBiq8StMYddspUeD7y3B6sfnP4fGY4eK11eXkE3TFH3fIXDma7g2AMw/+1TZxmlmlmRWHdJoLR7aXAT8ys7bgHzKw01vvfjs8SHO3ebGZfirWfzWy0mT3A233QPbE5fD63zbJPJrjqYbe4+zaC8SUTCI6Yo5d5CUf2n0PQB74BuNHMLou1XDM73cwGhK/Hmtm0GNUKCboHjhgsJ71HTe7SI+6+FdjajVn+H/Ac8Esz+xzBebdVBEf5JwLTCb4cW5uJf0hwHuz7gNfN7CmCPsIPEpwjfkUX43zTggut/B/wTzN7hGDw1BCCo9NagnOVIUgg1wF/NLOHCfpvpxOMFXgwXHdf8QBw0MxeJEgMRnCUdSrBaVPRI5p/SrBdd5rZBQQDtE4iaKZ/jDYXCuqMu+8Kk9lVwFIze5rgvbmI4PSnpbw9QOtofJvg/PF3AWvN7DGC92sUwelxXyZokQD4D4Jt+hTBefDPEbx/xQR963OBWwgGdXW2favDH3EPE1zu9SYzm0/Qv54brmcuQbP399tdUOd+E27Dj8zsPILP5USC9+NP9OzzdiPBeeh3hAm69Tz09xEk73kEXTDAWwMS30swDuJvZvYPgvdvP8F+PjWcvzQsOwn4s5ktIehy2UEwqHUewXUUjmZ/yNFK9HlzevT9B1HnoXehbszz0MNp+QTnly8haJ47AGwiuADG9UBum/oDCQZfbSdIFKsJTkEaRxfPQ4+adjrBF3QFwQjsHQTnz1/Zpt4ZBD889hEkjxcJflicGy77W23qL+DYnYe+uZ15vtV2HoLE9WdgI8EX7V6CJtevAPkxlnEmwQ+h/QRHn38j+CF1xLKj3vMFHWzHAOA23j6HeRvBqX1DYu2T9vZfZ9tPcNDxGYJWhjqCLp51wF3AhDZ1jaD/dn64PxrDz86L4eduVDc/93kEfcXPh5+bQwR9zkuA/6TNeeAdfRYIBgrGOgd/KsF59hXhti0haA0aQzc/41F1phD8IKgKl/kywelp/xrO++4Y8xQTXORmRfgZqQv380PARwivRUDwA/y7BD8adhFcC6GM4CySS7v73aLHsX1Y+CaJiEgSM7P7CVrKpnjUFfkkeagPXUQkSZhZxMyOOAsk7Gr5IPCmknnyUh+6iEjyyAS2mdnzBF1UTQTX2L+IoAvixgTGJnGmJncRkSQRnnXwI4JLwI4kGOuwm2D8xPe84wtAST+nhC4iIpIE1IcuIiKSBPp1H/rQoUN9zJgxiQ5DRESk1yxZsmS3uxe1Le/XCX3MmDEsXnws7kEhIiLSP5jZlljlanIXERFJAkroIiIiSUAJXUREJAkooYuIiCQBJXQREZEkoIQuIiKSBJTQRUREkoASuoiISBJQQhcREUkCSugiIiJJQAldREQkCfTra7n3J5dePo/yyt3tTi8pGsoTjz3SixGJiEgyUULvJeWVu7n6O79ud/p9t17Xi9GIiEiyUZO7iIhIElBCFxERSQJK6CIiIklACV1ERCQJKKGLiIgkgbgndDNLM7N/mtlj4d+DzewZM1sXPhdG1b3ZzNab2RozuzjesYmIiCSL3jhCvwlYFfX3V4H57j4RmB/+jZlNBa4CpgGXAHeYWVovxCciItLvxTWhm9lI4J3A3VHF84B7w9f3Au+OKn/A3RvcfROwHpgdz/hERESSRbyP0H8EfAVoiSorcfedAOFzcVg+AtgWVa8sLBMREZFOxC2hm9nlQIW7L+nqLDHKPMZyrzezxWa2uLKy8qhiFBERSRbxPEKfC1xhZpuBB4Dzzey3QLmZlQKEzxVh/TJgVNT8I4EdbRfq7ne5+yx3n1VUVBTH8EVERPqPuCV0d7/Z3Ue6+xiCwW7PuftHgEeBa8Jq1wCtdyR5FLjKzLLMbCwwEXg1XvGJiIgkk0TcnOV7wINm9nFgK/B+AHdfaWYPAm8CTcCN7t6cgPhERET6nV5J6O6+AFgQvt4DXNBOvduA23ojJhERkWSiK8WJiIgkASV0ERGRJKCELiIikgSU0EVERJKAErqIiEgSUEIXERFJAkroIiIiSUAJXUREJAkooYuIiCQBJXQREZEkoIQuIiKSBJTQRUREkoASuoiISBJQQhcREUkCSugiIiJJQAldREQkCSihi4iIJAEldBERkSSghC4iIpIElNBFRESSgBK6iIhIElBCFxERSQJxS+hmlm1mr5rZG2a20sy+HZZ/y8y2m9nS8HFZ1Dw3m9l6M1tjZhfHKzYREZFkkx7HZTcA57t7nZllAC+a2RPhtP9x9/+OrmxmU4GrgGnAcOBZM5vk7s1xjFFERCQpxO0I3QN14Z8Z4cM7mGUe8IC7N7j7JmA9MDte8YmIiCSTuPahm1mamS0FKoBn3H1ROOkzZrbMzH5lZoVh2QhgW9TsZWGZiIiIdCKuCd3dm919BjASmG1m04E7gfHADGAn8MOwusVaRNsCM7vezBab2eLKysq4xC0iItLf9Mood3evAhYAl7h7eZjoW4Bf8HazehkwKmq2kcCOGMu6y91nufusoqKi+AYuIiLST8RzlHuRmQ0KX+cAFwKrzaw0qtp7gBXh60eBq8wsy8zGAhOBV+MVn4iISDKJ5yj3UuBeM0sj+OHwoLs/Zmb3mdkMgub0zcANAO6+0sweBN4EmoAbNcJdRESka+KW0N19GXByjPKrO5jnNuC2eMXUl23YsIGZc+bGnFZSNJQnHnuklyMSEZH+JJ5H6NINTS0tXP2dX8ecdt+t1/VyNCIi0t8ooae4Sy+fR3nl7pjT1DIgItJ/KKGnuPLK3WoZEBFJAro5i4iISBJQQhcREUkCSugiIiJJQAldREQkCSihi4iIJAEldBERkSSghC4iIpIElNBFRESSgBK6iIhIElBCFxERSQJK6CIiIklACV1ERCQJKKGLiIgkASV0ERGRJKCELiIikgSU0EVERJKAErqIiEgSUEIXERFJAkroIiIiSSBuCd3Mss3sVTN7w8xWmtm3w/LBZvaMma0Lnwuj5rnZzNab2RozuzhesYmIiCSbeB6hNwDnu/tJwAzgEjM7DfgqMN/dJwLzw78xs6nAVcA04BLgDjNLi2N8IiIiSSNuCd0DdeGfGeHDgXnAvWH5vcC7w9fzgAfcvcHdNwHrgdnxik9ERCSZxLUP3czSzGwpUAE84+6LgBJ33wkQPheH1UcA26JmLwvLREREpBNxTeju3uzuM4CRwGwzm95BdYu1iCMqmV1vZovNbHFlZeUxilRERKR/65VR7u5eBSwg6BsvN7NSgPC5IqxWBoyKmm0ksCPGsu5y91nuPquoqCieYYuIiPQb8RzlXmRmg8LXOcCFwGrgUeCasNo1wCPh60eBq8wsy8zGAhOBV+MVn4iISDJJj+OyS4F7w5HqEeBBd3/MzF4GHjSzjwNbgfcDuPtKM3sQeBNoAm509+Y4xiciIpI04pbQ3X0ZcHKM8j3ABe3McxtwW7xiEhERSVa6UpyIiEgSiGeTu/TQ/sYm9tY3kp2RRn6W3iIREemcskUfsmVPPYs27WVn9cG3yswgffr7+Pu6Ss6cMBSzWGf3iYhIqlNC7wPcnQEnv4u/LN1BQU4Gc8YOprQgm8amFsprGni9YSRX//JVLjy+hP949zRKC3ISHbKIiPQx6kPvAxasrST31PcyZVg+H54zmtPGDeG4IblMLMnnzIlDGfSP/+Vrl03hxfWVvOP2hTy1cleiQxYRkT5GCT3B1uyqZVlZNfuXPck7ppaQkXbkW2LezPVnj+fpz5/DuKJcbrhvCbc/s5aWliMupCciIilKCT2B9tY3Mn91OcMLsqlf9FCn/eOjhwzgDzeczpWnjOQn89fxr398g0PNLb0UrYiI9GXqQ08Qd+f51RWkRYxLp5fyRhevoZOdkcZ/XXkixw0ewA+fWcu+/Y3s+NP3qKwoj1m/pGgoTzz2SMxpIiKSPJTQE2Tr3v2UVR3gnElF5GV3720wMz57wUSG5GVxy1+Wk1Z6HjfceBHpMZrr77v1umMVsoiI9GFqck8Ad+cfG/aQn53O9BEDe7yc/zdnNN9/74k0DR7H35bvpKlFze8iIqlKCT0B1lfUUVHbwGnjhpAeObq34AOnjmLA6sfZvGc/TyzfRbMGyomIpCQl9ARYsnUfhQMymDIs/5gsL3vnUs6dVMTG3fU8uWKXRr+LiKQgJfReVlF7kPKaBk4cOYjIMbzq20mjBnHWxKGsr6zjuTUVuCupi4ikEg2K62XLt1eTFrFjdnQebeboQg4eaua1zfvIz05nztghx3wdIiLSNymh96LGphbW7KplUkke2RlpcVnH6eOGUHewiVc27qUgJyMu6xARkb5HCb0XrSmv5VCzc8KIgritw8y44PgSag428eyqCnLzhsVtXSIi0neoD70XrdpZw5DcTIYNzI7retIixmUnDGNAZhp1J1xJZW1DXNcnIiKJp4TeS1oy89hZfZBJJfm9cgvUAZnpXH5iKS0ZOXzpj29o5LuISJJTQu8ljUWTAZhQnNdr6yzOz2bA+mdZuLaSX720qdfWKyIivU8JvZc0Fk1hcG4mg3Mze3W9WTv+yTumlvD9J1ezYnt1r65bRER6jxJ6L6isbaBp0KhePTpvZcD333cihQMy+beHl9Gku7OJiCQlJfRe8PSbu8AiTExAQgcozM3k21dMY+WOGn75opreRUSSUdxOWzOzUcBvgGFAC3CXu//YzL4FfBKoDKt+zd0fD+e5Gfg40Ax8zt2fild8vempleVE9u9hSO6EXl/3hg0bmDlnLg5kTH8f//nYIe74xudIO1gFwMZNSvAiIskgnuehNwFfcvfXzSwfWGJmz4TT/sfd/zu6splNBa4CpgHDgWfNbJJ7F28U3kcdPNTMoo17yNizAbPTen39TS0tXP2dXwNQd7CJ37yymaFXfJnLTxwOwK0fPLPXYxIRkWMvbk3u7r7T3V8PX9cCq4ARHcwyD3jA3RvcfROwHpgdr/h6yysb99DQ1ELG3o2JDoW87HRmjRnMhsp6tu87kOhwRETkGOqVPnQzGwOcDCwKiz5jZsvM7FdmVhiWjQC2Rc1WRsc/APqFhWt3k5keIaNqa6JDAeDkUYPIy0pn4bpK3cBFRCSJxD2hm1ke8DDweXevAe4ExgMzgJ3AD1urxpj9iIxjZteb2WIzW1xZWRljlr5l4bpK5owdjLU0JToUADLSIpwxfggVtQ2sLa9LdDgiInKMxDWhm1kGQTK/393/BODu5e7e7O4twC94u1m9DBgVNftIYEfbZbr7Xe4+y91nFRUVxTP8o7aj6gDrK+o4e2LfinPKsHyG5GWyaNMeYv+OEhGR/iZuCd2C65v+Eljl7rdHlZdGVXsPsCJ8/ShwlZllmdlYYCLwarzi6w0L1wYtCOdM7lsJ3cyYPWYw+/YfInPsKYkOR0REjoF4jnKfC1wNLDezpWHZ14APmdkMgub0zcANAO6+0sweBN4kGCF/Y38f4b5wXSXDBmYn7PzzjkwozmPQgAwOnXw57t4r15cXEZH4iVtCd/cXid2e+3gH89wG3BavmHqTu/PKxr2cO7moTybLiBmnHjeYZ/Yfx+Y9+xk7NDfRIYmIyFHQleLiZF1FHXvrGzlt7JBEh9KuycPyaa7bw+tb9yU6FBEROUpdSuhmNrcrZfK2RRv3ADBn3OAER9K+tIhxYOVzlO07wJ463TNdRKQ/6+oR+k+7WCahVzbtZdjAbEYPHpDoUDp0cPVC0iLGG2W6E5uISH/WYR+6mZ0OnAEUmdkXoyYNBNLiGVh/5u4s2riXuROG9Mn+82jeUMekkjxW7axh7vghZGXobRUR6Y86O0LPBPIIEn9+1KMGuDK+ofVfG3fXs7uugTl9uP882oyRg2hqcd7cWZPoUEREpIc6PEJ39xeAF8zsHnff0ksx9XuLNu4F+nb/ebTigdkMG5jNyh01zBg1qM+3KoiIyJG6etpalpndBYyJnsfdz49HUP3dq5v2MDQvi3H96FSwqaUDeW5NBRW1DZQMzE50OCIi0k1dTeh/BP4PuJvgXuXSgdc272P22MJ+daQ7qSSPF9ZV8uaOGiV0EZF+qKsJvcnd74xrJEmivOYg26sO8LEzxyY6lG7JykhjfFEua8prOWviUNLTdIkCEZH+pKvf2n81s38xs1IzG9z6iGtk/dTrW4KLtMwcPSixgfTA1NKBNDS1sHF3faJDERGRburqEfo14fOXo8ocGHdsw+n/lmzZR2Z6hGnDCxIdSreNGjyAvKx0Vu2sYVJJfqLDERGRbuhSQnf3/tV+nECvb93HiSMKyEzvf03WETMmleSxdFsVBw9pqISISH/SpYRuZh+NVe7uvzm24fRvF7/rPaw5/lqyyxYz854vHzZt46ZNCYqqeyaV5PP61io2VNYlOhQREemGrja5nxr1Ohu4AHgdUEKPsuNgBkTSueCd72FC8dWHTbv1g2cmKKruKc7PoiAng7XlSugiIv1JV5vcPxv9t5kVAPfFJaJ+rKlgBAClBf33tC8Lm90Xb9lHQUbfvg69iIi8racdvfuBiccykGTQNHAkA7PTyc2K223me8XE4nzcobFocqJDERGRLupqH/pfCUa1Q3BTluOBB+MVVH/VPHA4w/rx0XmroXmZFA7IoLb4+ESHIiIiXdTVQ8n/jnrdBGxx97I4xNNvVdY20JI9MCmusmZmTCjO47W60eyrb6QwNzPRIYmISCe62of+gpmV8PbguHXxC6l/WrE9uJ94Sf6xT+gbNmxg5py57U6Pxwj6cUV5vLZ5H8+truB9p4w85ssXEZFjq6tN7h8A/gtYABjwUzP7srs/FMfY+pVlZdXgTlF+1jFfdlNLC1d/59ftTo/HCPqS/CzsYA1PrdylhC4i0g90tcn9FuBUd68AMLMi4FlACT20fHs1kf17yEyflOhQjgkzI3P3WhauG8SBxmZyMtMSHZKIiHSgq6PcI63JPLSnG/OmhOXbq0iv3ZnoMI6pzN1rOXiohYXrKhMdioiIdKKrSflJM3vKzK41s2uBvwGPdzSDmY0ys+fNbJWZrTSzm8LywWb2jJmtC58Lo+a52czWm9kaM7u4pxvV2ypqDlJe00B67a5Eh3JMpVdtpSAng6dXlic6FBER6USHCd3MJpjZXHf/MvBz4ETgJOBl4K5Olt0EfMndjwdOA240s6nAV4H57j4RmB/+TTjtKmAacAlwh5n1i3be5eGAuLQkO0I3b+G8yUUsWFNBS4t3PoOIiCRMZ0foPwJqAdz9T+7+RXf/AsHR+Y86mtHdd7r76+HrWmAVMAKYB9wbVrsXeHf4eh7wgLs3uPsmYD0wu5vbkxDLyqoxg/S65DuSPW9KMXvqG9/60SIiIn1TZwl9jLsva1vo7ouBMV1diZmNAU4GFgEl7r4zXM5OoDisNgLYFjVbWVjW563YXs2Eojys+VCiQznmzp5YhBk8t7qi88oiIpIwnSX0jk6qzunKCswsD3gY+Ly713RUNUbZEe28Zna9mS02s8WVlYkfrOXuLNtezQkj+t/9z7uiMDeTk0cNYsEaJXQRkb6ss4T+mpl9sm2hmX0cWNLZws0sgyCZ3+/ufwqLy82sNJxeCrRmijJgVNTsI4EdbZfp7ne5+yx3n1VUVNRZCHFXXtNAZW0DJ4xMzoQOcN7kYt4oq6aytiHRoYiISDs6S+ifB64zswVm9sPw8QLwCeCmjmY0MwN+Caxy99ujJj0KXBO+vgZ4JKr8KjPLMrOxBDd/ebVbW5MArX3LJyZzQp8S9IosXJv4FhEREYmtwwvLuHs5cIaZnQdMD4v/5u7PdWHZc4GrgeVmtjQs+xrwPeDB8Ch/K/D+cF0rzexB4E2CEfI3untzN7en1y0vqyJiMLU0eRP6tOEDKc7P4rk1ugysiEhf1dVruT8PPN+dBbv7i8TuFwe4oJ15bgNu6856Em359momFucn9ZXUzIxzJxfxxIpdNDW3kJ6mawqJiPQ1+mY+Cu7O8u3VTE/SAXHRzptcTO3BJl7fWpXoUEREJAYl9KOwq+Ygu+sak7r/vNWZE4eSHjGe12h3EZE+SQn9KCwrCwbEJfMI91b52RmcOmYwz+t8dBGRPkkJ/SgsL6smLWJMLR2Y6FB6xXlTili9q5YdVQcSHYqIiLShhH4UggFxeWRnJO+AuGjnTQ5OX1uwRqeviYj0NUroPdQ6IC5ZrxAXy4TiPEYW5ugysCIifZASeg/tqD7I3vrUGBDXqvX0tZc37KaxqSXR4YiISBQl9B5aXlYFwAkjByU0jt52zqRi6hubWbJlX6JDERGRKEroPbSsrJr0iDFlWH6iQ+lVp48fQnrEeEGXgRUR6VOU0Hto+fZqJpXkp8yAuFZ5WenMGlOohC4i0scoofdAKg6Ii3bOpGJW7ayhouZgokMREZGQEnoPlO07QNX+QylxQZlYzpkU3LZ24brdCY5ERERadenmLHK4VLhlKsCGDRuYOWfuEeUO2Bmf499/8TBXntLhXXRFRKSXKKH3wLKyajLSjMlJPiCuqaWFq7/z65jTnn5zF6u3RmhucdIi7d1UT0REeoua3HtgxfZqJg/LJys9tQbERTtucC6eMYBl4el7IiKSWEro3ZTqA+JajR4yANxZuFb96CIifYESejdt23uA6gOHOGHEoESHklA5GWmk1e7ghbW6DKyISF+ghN5Ny7ZXAck/IK4rMvZsZOm2Kqr2NyY6FBGRlKeE3k3Lt1eTmRZhUklyD4jrioy9G2lxeHG9mt1FRBJNCb2blpdVM6U0n8x07br02h0MzE5noa4aJyKScMpK3dA6IG56ig+Ia2XunDWxiBfWVuLuiQ5HRCSlKaF3w5Y9+6k92MSJSuhvOWdSEeU1Dawpr010KCIiKS1uCd3MfmVmFWa2IqrsW2a23cyWho/LoqbdbGbrzWyNmV0cr7iOxrLwCnGpesnXWM4OLwP7who1u4uIJFI8j9DvAS6JUf4/7j4jfDwOYGZTgauAaeE8d5hZn7tqy4rt1WSma0BctGEF2UwuyWfhOiV0EZFEiltCd/eFwN4uVp8HPODuDe6+CVgPzI5XbD21rKyK40sHkpGmnopo50wu4rVN+6hvaEp0KCIiKSsRmekzZrYsbJIvDMtGANui6pSFZX1GS4uzYnsNJ4wYmOhQ+pxzJhXR2NzCKxv3JDoUEZGU1dsJ/U5gPDAD2An8MCyPdXePmMOmzex6M1tsZosrK3uvmXfznnrqGpo4McWvEBfLrDGF5GSk8YJOXxMRSZheTejuXu7uze7eAvyCt5vVy4BRUVVHAjvaWcZd7j7L3WcVFRXFN+AoyzUgrl1Z6WmcPn6ITl8TEUmgXk3oZlYa9ed7gNYR8I8CV5lZlpmNBSYCr/ZmbJ1ZXlZNVnqEicV5iQ6lTzpvchFb9uxn4+76RIciIpKS4nY/dDP7PXAuMNTMyoBvAuea2QyC5vTNwA0A7r7SzB4E3gSagBvdvTlesfXEsu3VTB0+kHQNiIvpvCnF8MhKnltVwfgi/egREeltcUvo7v6hGMW/7KD+bcBt8Yqnqy69fB7llYdfm9yBfWd9icLq9cDchMTV140sHMCUYfnMX13OJ88el+hwRERSTtwSen9VXrmbq7/z68PK9tY3ct8rW2is2JigqPqH86cU8/OFG6k+cIiCnIxEhyMiklKU0LugouYgADvefI2Zc9o/Qt+4aVNvhdQnXXB8MXcs2MDCtZW866ThiQ5HRCSlKKF3QXltA+kRo3Hvdq6+Y2G79W794Jm9GFXfM2NUIYUDMnh+dYUSuohIL9MIry6oqDlIUX4WeEuiQ+nT0iLGuZOLeX5NBU3N2lciIr1JCb0TLe5U1jVQnJ+V6FD6hYumlrBv/yEWb9mX6FBERFKKEnon9tY3cqjZKRmYnehQ+oVzJhWRmR7hqZW7Eh2KiEhKUULvxK5wQNywAiX0rsjNSuesCUN5emW5rhonItKLlNA7UV59kKz0CIN0GlaXXTxtGNurDvDmzppEhyIikjKU0DtRXtNAycBszGLdP0ZiueD4YiIGT60sT3QoIiIpQwm9A4eaW9hd38Aw9Z93y5C8LGaNGczT6kcXEek1SugdqKhtwB1KBmqEe3ddMm0Yq3fVsqGyLtGhiIikBCX0DpRXBwPiNMK9+y47oRQzeOyNnYkORUQkJSihd2BXzUHys9PJzdIF9bprWEE2p44ZzGPLYt7WXkREjjEl9A6U1xxU//lReNeJpayrqGPNrtpEhyIikvSU0Nuxv7GJmoNNSuhH4ZLppUQM/vqGjtJFROJNCb0drReUUf95zxXlZ3HG+KE8tmyHLjIjIhJnSujtKK9uwAyKNcL9qFxx0nA279nP61urEh2KiEhS02ivduyqOciQ3Ewy0vSbpz0bNmxo9/7wJUVDeeKxR7jsxFK++ehKHlqyjVOOK+zlCEVEUocSegzuTnnNQSYW5yU6lD6tqaWFq7/z65jT7rv1OgDystK59IRhPPbGTr5x+TRyMtN6M0QRkZShw88Yqg4coqGphRLdkOWYeP8po6htaNId2ERE4kgJPYbWC8pohPuxMWfsYEYNzuGPS7YlOhQRkaSlhB7DrpqDZKQZg3MzEx1KUohEjCtnjuIfG/awZU99osMREUlKcUvoZvYrM6swsxVRZYPN7BkzWxc+F0ZNu9nM1pvZGjO7OF5xdcWumoMU52cT0R3WjpmrZo8izYzfvLwl0aGIiCSleB6h3wNc0qbsq8B8d58IzA//xsymAlcB08J57jCzhIyecktjd22jmtuPsZKB2Vx2QikPvraN+oamRIcjIpJ04pbQ3X0hsLdN8Tzg3vD1vcC7o8ofcPcGd98ErAdmxyu2jjTlD6PZnWEaEHfMXTt3DLUNTfzp9bJEhyIiknR6+7S1EnffCeDuO82sOCwfAbwSVa8sLOt1TQUjAShVQj8qsc5RdyDtlGv55u/2cP9tN/HkY48kJjgRkSTUV85Dj9VZHfNaoWZ2PXA9wOjRo495IE0FIynIydAd1o5Se+eor95Vw1MryynzwQmISkQkefX2KPdyMysFCJ8rwvIyYFRUvZFAzDt6uPtd7j7L3WcVFRUd0+DcnaaCkQwfpKPzeJlUnE9BTgYHxpyp67uLiBxDvZ3QHwWuCV9fAzwSVX6VmWWZ2VhgIvBqL8fGpt31eGYuwwtyenvVKSMSMWaPGUxz/jCeXVXR+QwiItIl8Txt7ffAy8BkMyszs48D3wMuMrN1wEXh37j7SuBB4E3gSeBGd2+OV2ztWbxlH6D+83ibMiyfyIF9/Hj+Wh2li4gcI3HrKHb3D7Uz6YJ26t8G3BaveLpiyeZ92KEDuqBMnEUiRs7ml1iRU8hfl+3kipOGJzokEZF+T1eKi7J4y17Sq8swXVAm7jJ3LWf6iIF892+rdF66iMgxoKHcob31jWyorCenWudI9wbD+fYV03jfnS/zs+fX85VLphyT5V56+TzKK3e3O731tq4iIslGCT108FAzH5g1kidf25ToUFLGKccN5r0zR3D33zfx7pNHMKkk/6iXWV65u91busLbt3UVEUk2anIPDR+Uww+uPIn0Ot3iszfdfOnx5Gen87nf/5ODh3p9HKSISNLQEbokVFF+Fv/9/pO47p7X+MGTa/jGu6Z2Ok9HzeobN6mFRURSkxK6JNx5U4q59owx/OqlTZw0qoB5Mzq+6m9Hzeq3fvDMeIQoItLnqcld+oSvXjqFOWMH869/fIOX1rc/qE1ERGJTQpc+ITsjjbs+OotxQ/O44b4lLN7c9kZ9IiLSESV06TMKcjK452OnUpyfxf+7exGPL9+Z6JBERPoNJXTpU0oLcnj402dw4ogCbvzd63z38VUa/S4i0gVK6NLnFOZm8ttPzOFDs0dz18KNvOunL6pfXUSkE0ro0idlZ6Tx3fecwL0fm83+xmY+fPciPnL3IhaurUS3cxEROZISuvRp50wqYv6XzuHrl09l1c4aPvqrV6k+7dO8tnmvrgEvIhJFCV36vOyMND5+5lj+cfP5/PiqGUQO1vCPDXv41UubeGzZDjZU1tHcouN2EUlturCM9BtZ6WnMmzGCby+9n3fe/HNW7Khmza7a4KY6GWlMLsknrVC3YhWR1KSELv3S4NxMzp5YxJnjh7Jl735W7axh+fZqBr//Nh5+vYyZowsZM2SAboUrIilDTe7Sr0UixtihuVx2QikfP2ssdYsepGr/IR59YwcPvLaNzbvrcVdzvIgkPyV0SRo5GWkceOMJrj1jDBceX0xDUwuPvLGDvyzdwZ66hkSHJyISV2pyl6STFjGmDS9gyrCBLCurYtGmvfzu1a3MHjMYN/2GFZHkpG83SVppEePk0YV89PTjmFCcxyub9lIz62MsK6tKdGgiIsecjtClz+nofufQ/XueD8hM59LppUwuqeOx12p5989e4oZzxvOFCyeRma7ftCKSHJTQpc/p6H7n0PN7no8ryqPg1bt4xxf+hzsXbOCl9bv58VUnM3Zobk9DFRHpMxJyeGJmm81suZktNbPFYdlgM3vGzNaFz4WJiE2SW6SpgR9ceRL/95GZbNmzn3f+5O/8cfE2jYQXkX4vke2N57n7DHefFf79VWC+u08E5od/i8TFJdNLefLzZ3HiyAK+/NAyPvP7f1J94FCiwxIR6bG+1IE4D7g3fH0v8O7EhSKpoLQgh/s/cRpfvngyT63YxWU//juvbd6b6LBERHokUQndgafNbImZXR+Wlbj7ToDwuThBsUkKSYsYN543gYc+fQbpacYHf/4ytz+zlqbmlkSHJiLSLYlK6HPdfSZwKXCjmZ3d1RnN7HozW2xmiysrK+MXoaSUGaMG8bfPncV7Th7JT+av4wM/f5lte/cnOiwRkS5LSEJ39x3hcwXwZ2A2UG5mpQDhc0U7897l7rPcfVZRUVFvhSwpIC8rnR9+4CR+fNUM1pXXcdmP/86f/1mmAXMi0i/0+mlrZpYLRNy9Nnz9DuDfgUeBa4Dvhc+P9HZskvw2bNjAzDlzY04rKRrKE489wrwZI5g5upDP/2EpX/jDGzy0pIxvXzGdCcV5vRytiEjXJeI89BLgz+FdsNKB37n7k2b2GvCgmX0c2Aq8PwGxSZJramlp9xz3+2697q3XowYP4MEbTud3i7bwX0+t4dIfL+QTZ43js+dPYECmLt8gIn1Pr38zuftG4KQY5XuAC3o7HkmMjo6Uu3sluHhJixhXnz6GS08o5T8fX82dCzbw59e38y/njecDs0aRnZGW6BBFRN6iQw1JiI6OlHt6Jbij1dGPDIDjjptG0XnX8o1HVvK/z63nU+eM50OzR5OT2Xli7+hytq1N/SIiR0MJXSTU0Y8MCJrkF3zqdF7euIefzF/Hvz/2Jj97fj1XnjKSD5w6ivFF7fexd3Q52+imfhGRnlJCF+kGM+OM8UM5Y/xQFm3cwy9f3MQvX9zEzxduJL1qK1k73yCjci2R5sPvv95XuhFEJHkpoYv00JxxQ5gzbggVtQc552O3kDX9YqoGjSYyNRhUN6E4j3FDcxmQmZ6wbgQRSR1K6CJHqTg/m5ytr/CRT17PrpqDrK+oY31FHfNXVfAcUFqQTc5Jl7K3vpHCARmEZ3hIAmgsgyQzJXSRY8TMKC3IobQghzMnDKWyroENFfVs2l1P3pwPcN8rWyjIyWDs0FzGDs1lxKAc0iJK7r1JYxkkmSmhi8SBmVGcn01xfjanjx/CNz52BVf++2/YtLue5durWbqtisy0CMcNGUBDyXT21TdSmJuZ6LBFpB9TQhfpBS31ezlx5CBOHDmIQ80tbN27n027g6P3/VOv4JTvPMPM0YVccHwJFx5fzITiPDXNi0i3KKGL9LKMtAjji/IYX5SHu3PPD27h2n/7LvNXlfP9J1fz/SdXM3rwAM6fUsyFx5cwe+xgMtP70p2O46ujfm44sq+7oamZ9RV1rN5Zy3d/9mtqmyJ4Vh4tmfm0ZOSARcKH0XzGTfz6pU1kZ6SRlREhJz2N/JwMBuVkcGjQcWyvOsDwguw+9WNK/f7SVUroIglkZqTX7uSLF03iixdNYmf1gWAw3eoKfv/qVu75x2bystI5e9JQLphSwnlTihmc5E3zHfVzuzv3fvdLPPjaNhZt2ssbZVVs2l1Pc0t4A52iGeRmZZCblU5uVjo5GWlEDCJmmMErTz7M8Avfw8FDzTQ0tVB+oIH1lXW0OHDyh5n7vefIy0pnyrB8ji8dGD7ymTwsP2GX/FW/v3SVErpIH1JakMNHTjuOj5x2HPsbm3hp/R7mrypn/uoKHl++i4jBzNGFnH98Me+YWsJnP/aRbh3N9kcNTc1s2RN0UWzdu5/9p32arzy8DGvcT3rNdjLqKsiuryC9rpItb77OTb+d3+6ynv3G/Vx806cPK2txp+5gEz+55UZKJkznUG4RS8tLWLyhGNKzgkruZDZWc+GsKUwZFiT6KcPyGVmY06eO5iW1KaGL9FEDMtO5aGoJF00toaXFWbGjmmdXVfDc6nJ+8OQafvDkGiJj38vMd05kQnEexflZRySX/noEt29/41tjDHZUHaDFITsjwujBA1jy0M/49L9+ncG5mZgdfluInpzvHzFjYE4GB7e/ySdvv+utcnen5mATlbUN7K5r4PVX17Jyx3AeX77rrTr5WelMHpbPlNJ8xg3NY9TgAYwanMOowgHkZunrVXqXPnEiXZSoG8rE6kMdlJVP45CJVOePZsnWoSzeso+8rHQmFOUxvjiX4YNyiPSjI8dDzS0s2bKP+avKqZp9A795eQsAQ3IzmTm6kLFDcxlWkE3EjJf+YwFD8r4T95jMjIKcDApyMphQnMeTt/yA/BXjKUzLoDm3iKa8Ehpzi1laXszrG0toSTu8K6RwQAajBg9geEEOixbO52B1JZGGOqyxlkhDHZHGOuzQAYYlQSuK9A1K6CJdFK8bynR2U5iNmzbxzfsXtLveW377Apt217Ohoo7lO6pZWlZFTkYa44pyaRwynoamZrLS+96d4ar2N/LC2krmr6pgwZoKag42kZFmRBqqOevkKYwdmktBTkaiw3xLR+//b269jmfnP8e2fQfYtnc/ZfsOsG3ffrbt3c+GyjqqBo7Dh0w7Yr6Iwe6aPYz/9F1EGuveSvSRhlos/Hvb9vJ4b5okCSV0kQTr7KYwnf1YyMlIY2rpQKaWDqSxqYUte+pZX1nHuvI6Gk/8IKf8x7OcN6WYi6eVcO7kYvIS1BTc2m2wYE0lL6yt5J9b99HiwVH4O6YN48LjizlzYhFnn30OM95/cUJi7CkDhuRlMSQvixmjBh0xfeacuXzo27+kvrGZ+oam4BG+fvGZlxh72kVvlR9oajls3oLZ8OuXNgXXNRiYRcnAbIYXZJOeljpnPkjXKKGLJJHM9AgTS/KZWJJPU0sL9/7oNi7/xJd55s1y/vrGDjLTI8wdP4S5E4Zy5sShTC7Jj+ugru1VB3ht014Wrq1k4bpKdtc1AnDiyAI+c94Ezp1SzIyRg4ikwBXz0tMiFOREjmh1eOKWu3nPp6996++m5hb2NzZT39hEXUMTD979Eya+62NU1AYj8gHSIsaIQTkcGDWH1btq4v4+Sv+ghC6SpNIjETL3buR77zuR297jLN68lydX7mLBmkqeX7MKgKF5mcwZN4QTRxQwfUQB04cXUDCgZ83ce+oaWFtex5pdNdx+36PUZRfRkl0AgDXuJ2PvRnL3biRj70YODRrAFz+TPP3GXek26ar0tAgDcyIMDBP/gTee4LKv3QLAwUPN7Kw+yNa9QXP+gQkXcMmP/s6YIQO49IRS3nlCKdOGD1RyT1FK6CJJrL1EU5A1kAGjpzPn8v/Ha5v38bdlO9+aNmJQDsMHZTOsIIdhA7Moys8iIy1CWsTeShRV9Y3sqW9kd10DFbUNbKioY09941vLsJwSJowqZfigHIYXZDM0P4tI1Ij0/jr6vj1H223SVdkZaW/dCwDg2x+/guEzL6CseAp3VtZx54INRA7sI7P8TbLKVzA81zTgLoUooYsksY4SzX23XsePrvovAPbWN7JyRzXLt1ezdlctO6sPsrysiqerD9LQpk+3VaS5ARrqiDTuJ7J/DwPqK0mr301afSWb1yznsnYG8kHizhhINofq9vLJG28C4MChZjZU1rGufADbcgo5OGYudbW7+MXCjVwxYzglA7MTHK3EmxK6iDA4N5OzJhZx1sSiw8rdndqGJpqbnRZ3mj24IltBTganzz27x6P+43XGQCrLyUhj+vCg26S+oYm15bW8tGQHtz2+iu8+sYozxg9h3owRXDJ9GAOz+87ZA3LsKKGLpKjO+n1brzKnL//+JzcrnZNHF7Lirnv442NP8cjSHTyydDtfeWgZt/5lBRceX8y8GSM4Z1IR2Rl975RG6RkldJEU1Vm/b7L1c6eq8UV5fPGiSXzhwoks3VbFI0t38Nc3dvD48l3kZKQxd8IQzptSzHmTixk+KCfR4cpR6HMJ3cwuAX4MpAF3u/v3EhySiEi/Z2acPLqQk0cXcss7j+cfG/bw3KpynltTwbOrKgAYOzSXU44r5JTjCpl1XCHji/JS4pTCZNGnErqZpQE/Ay4CyoDXzOxRd38zsZGJpJ5jeSqWJEZH72Frl8q33FlfUcfzayp4ddM+nltdwUNLyoDg+vnji/KYUJzHxOI8Rg/JZdjAbEoLgovc9MUrEKayPpXQgdnAenffCGBmDwDzACV0kV7WW6diSfx0dpYDBEfurRcjuv7sYCDkpt31LNmyjzW7allXUcfizft4ZOmOI5aRn53OwOwM8rPTyc9OJy8rnfzsDHKz0shMi5CRFiEjPUJmWoTM9AgZaRaUpUWImB12a9u0iL31OpgWTDezcBqHTXeCWN3BCZ5bPCw7bFpwR73W19HztLRElbVulL+9fa2lflhZ1Gs/vF6riBlpZkQiRloEzp9c0uPrO3RHX0voI4BtUX+XAXMSFIuISMoxM8YV5XHjdR8+7KZAhWkZNGcV4Fn57K5vZFDpGBozBlCZnkVFehbe+kjLotnSiKRn4JYGkTSI9LVU07ueuOmsXkno5u6d1+olZvZ+4GJ3/0T499XAbHf/bFSd64Hrwz8nA2u6uZqhQPs3kE4N2gfaB6B9kOrbD9oH0D/3wXHuXtS2sK/9bCoDRkX9PRI4rJ3H3e8C7qKHzGyxu8/q6fzJQPtA+wC0D1J9+0H7AJJrH/S12/W8Bkw0s7FmlglcBTya4JhERET6vD51hO7uTWb2GeApgtPWfuXuKxMcloiISJ/XpxI6gLs/Djwex1X0uLk+iWgfaB+A9kGqbz9oH0AS7YM+NShOREREeqav9aGLiIhID6RUQjezS8xsjZmtN7OvJjqeo2FmvzKzCjNbEVU22MyeMbN14XNh1LSbw+1eY2YXR5WfYmbLw2k/sfCG12aWZWZ/CMsXmdmYXt3ALjCzUWb2vJmtMrOVZnZTWJ4S+8HMss3sVTN7I9z+b4flKbH90cwszcz+aWaPhX+n1D4ws81h7EvNbHFYlmr7YJCZPWRmq8PvhNNTbR+EV81J/gfBILsNwDggE3gDmJrouI5ie84GZgIrosp+AHw1fP1V4Pvh66nh9mYBY8P9kBZOexU4HTDgCeDSsPxfgP8LX18F/CHR2xxjH5QCM8PX+cDacFtTYj+EseaFrzOARcBpqbL9bfbFF4HfAY+l6P/CZmBom7JU2wf3Ap8IX2cCg1JuHyQ6gF58s08Hnor6+2bg5kTHdZTbNIbDE/oaoDR8XQqsibWtBGcRnB7WWR1V/iHg59F1wtfpBBdesERvcyf74xGC+wCk3H4ABgCvE1xZMaW2n+B6FfOB83k7oafaPtjMkQk9ZfYBMBDY1DamVNoH7p5STe6xLis7IkGxxEuJu+8ECJ+Lw/L2tn1E+Lpt+WHzuHsTUA0MiVvkRyls/jqZ4Cg1ZfZD2NS8FKgAnnH3lNr+0I+ArwAtUWWptg8ceNrMllhwNU1IrX0wDqgEfh12vdxtZrmk1j5IqYQe6x6AqTLEv71t72if9Jv9ZWZ5wMPA5929pqOqMcr69X5w92Z3n0FwlDrbzKZ3UD3ptt/MLgcq3H1JV2eJUdav90ForrvPBC4FbjSzszuom4z7IJ2gC/JOdz8ZqCdoYm9PMu6DlEronV5WNgmUm1kpQPhcEZa3t+1l4eu25YfNY2bpQAGwN26R95CZZRAk8/vd/U9hccrtB3evAhYAl5Ba2z8XuMLMNgMPAOeb2W9JrX2Au+8InyuAPxPcuTKV9kEZUBa2UAE8RJDgU2kfpFRCT4XLyj4KXBO+voagT7m1/KpwlOZYYCLwatgEVWtmp4UjOT/aZp7WZV0JPOdh51FfEcb8S2CVu98eNSkl9oOZFZnZoPB1DnAhsJoU2X4Ad7/Z3Ue6+xiC/+nn3P0jpNA+MLNcM8tvfQ28A1hBCu0Dd98FbDOzyWHRBQS33U6ZfQCkzqC4cL9fRjASegNwS6LjOcpt+T2wEzhE8Mvx4wT9OfOBdeHz4Kj6t4TbvYZw1GZYPovgn38D8L+8fbGhbOCPwHqCUZ/jEr3NMfbBmQRNXsuApeHjslTZD8CJwD/D7V8BfCMsT4ntj7E/zuXtQXEpsw8I+o/fCB8rW7/bUmkfhDHOABaH/w9/AQpTbR/oSnEiIiJJIJWa3EVERJKWErqIiEgSUEIXERFJAkroIiIiSUAJXUREJAkooYukMDO7x8yuTHQcInL0lNBFpEcsoO8QkT5C/4wiKcTMPmpmyyy4h/p9YfHZZvYPM9vYerRuZnlmNt/MXg/vDT0vLB8T3mv6DoK7u40ys6+H96B+xsx+b2b/GtYdb2ZPhjcM+buZTQnL329mK8IYFiZgN4gkJV1YRiRFmNk04E8EN/LYbWaDgduBXOCDwBTgUXefEF6reoC715jZUOAVgstjHgdsBM5w91fMbBZwN8GtJ9MJkvzP3f2/zWw+8Cl3X2dmc4D/dPfzzWw5cIm7bzezQR5ch15EjlJ6ogMQkV5zPvCQu+8GcPe9weWq+Yu7twBvmllJWNeA74Z37WohuHVk67Qt7v5K+PpM4BF3PwBgZn8Nn/OAM4A/husAyAqfXwLuMbMHCX5giMgxoIQukjqM2Ld7bGhTB+DDQBFwirsfCu9mlh1Oq49Rv60IUOXBrV0P4+6fCo/Y3wksNbMZ7r6ny1shIjGpD10kdcwHPmBmQwDCJvf2FBDcZ/yQmZ1H0NQey4vAu8wsOzwqfyeAB/el32Rm7w/XZWZ2Uvh6vLsvcvdvALs5/DaWItJDOkIXSRHuvtLMbgNeMLNmgju1ted+4K9mtpjgLnar21nma2b2KMGdvrYQ3O2qOpz8YeBOM7sVyCC4X/kbwH+Z2USCo/v5YZmIHCUNihORo2Jmee5eZ2YDgIXA9e7+eqLjEkk1OkIXkaN1l5lNJehjv1fJXCQxdIQuIiKSBDQoTkREJAkooYuIiCQBJXQREZEkoIQuIiKSBJTQRUREkoASuoiISBL4/1NBnSmpvtx7AAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<Figure size 576x360 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Histrogram of Medical Insurance Charges:\n",
    "plt.figure(figsize=(8,5))\n",
    "sns.histplot(train_data['charges'], kde=True)\n",
    "plt.title('Medical Insurance Charges', fontsize=20)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Age:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x360 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Histrogram of Age:\n",
    "plt.figure(figsize=(8,5))\n",
    "sns.histplot(train_data['age'], kde=True)\n",
    "plt.title('Age', fontsize=20)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Body Mass Index:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x360 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Histrogram of Body Mass Index:\n",
    "plt.figure(figsize=(8,5))\n",
    "sns.histplot(train_data['bmi'], kde=True)\n",
    "plt.title('Body Mass Index', fontsize=20)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### children:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAfQAAAFSCAYAAAAEky15AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8vihELAAAACXBIWXMAAAsTAAALEwEAmpwYAAA6KUlEQVR4nO3dd3gc1b3/8fdX3ZasXi3ZlovcG7YxNg49gCnB1ARSIBVykwBJLiGUhAsEAiHlpvzSSAGHEBxCTEw3xpheXHCVq9xly6qWJVlWP78/dp2rGBmrrXZ39Hk9j55dzc7OfLVe72fnzJlzzDmHiIiIhLeIYBcgIiIiPadAFxER8QAFuoiIiAco0EVERDxAgS4iIuIBCnQREREPUKCLhBEzyzczZ2aPduE5n/c/5/PHLN9lZrsCuW8R6TsKdBEREQ+ICnYBIhJwTwPvASXBLkREAkeBLuJxzrlDwKFg1yEigaUmd5EQYmYzzezvZrbPzBrNrMTMXjazT3awbr6ZLTCzCjNrMLOVZnZxB+t1eA79I2oYZGY/M7Ni/3Y3m9m3Oc7nhZk96t/+CDO70czWmdkRM3ut3TqpZvaAmW3yP3bIzJaa2XkfVa+ZnWVmr5lZrZnVmNnzZjaug+dkmdlPzGyLmR02s2r//UfNbERn/m6RcKcjdJEQYWZfAX4LtALPANuATGAG8DXgyXarDwOWAzuAx4BU4FPAIjP7uHNuWTdriAWWAicDa4HHgWTg+8AZJ3j6L4DTgOeBF/x/B2Y2DHgNyAfeBF4C4oGLgZfM7Abn3B862N7FwDzgReB3wHjgQuBkMxvvnKvwb38g8DYwElgCPAsYvtdoHvAUvtdJxNMU6CIhwMzGA78BaoDTnHOFxzyed8xTzgTuds7d026dv+ELy+8A3Qp04L/xhflC4CrnXJt/2w8Cq07w3GnASc65nccsn48vXK9xzi1oV28yvqD/pZk945wrPeZ5lwLnO+eWtnvOA8BtwBeBh/yLz8EX5j93zn2r/QbMLAaIPUHdIp6gJneR0PBf+L5g/+DYMAdwzhUfs2g3cN8x6ywG9gAze1DHF4A24NajYe7f9k7glyd47kPHhrmZTcF3ZP/P9mHu32Y18D9AHHBFB9tb0D7M/R7233b0Nx45doFzrsk5V3uCukU8QUfoIqFhlv/2xU6uv8Y519rB8r3A7O4UYGaDgFHAXufc9g5WeQ1fAB/P8g6WHa0lyczu7uDxDP/th86LAys7WLbXf5vSbtnrwD7gNjObhq+5/22O/xqJeJICXSQ0JPtv93Vy/erjLG+h+y1vSf7bY5u+jzpwgud39Hia//Zc/8/xJHSwrPrYBc65FjMDiGy3rMbMZgH3AJcA5/sfqjCz3wD3OeeaT1C7SNhTk7tIaKj23+YGsYajl7ZlHefx7BM8333ENm92ztlH/HyhWxUf3bFzxc65L+HrRDgRuAmoBO7y/4h4ngJdJDS857+9IFgF+M81FwG5Zjayg1XO7MZmj/5dp3W3rq5wPoXOuV/xfy0Cl/bFvkWCTYEuEhp+i6+5/Pv+Hu//oYNe7oHyCL7PhR+Z2b8/H8xsOL6j3i5xzq3Ed6na5Wb2xY7WMbNJZpbZzXoxs4lmlt/BQ0dbGuq7u22RcKJz6CIhwDm30cy+hu9669Vmtgjfdehp+K5DrwXO6oNSforviPYK4AMzW4zv3PqngDfwnaPuqk8DrwJ/MrObgPfxnWLIAybjayKfDZR1s+aPAz8zs3eAzf7t5OG7Br0N+HE3tysSVhToIiHCOfcHM9sA3IKveftSoAJYB/yxj2poNLOPA3fjC/GbgV34LpF7mm4EunOu2MymAzfi+6LwGXyd2g4AG4FfAet7UPZi4OfA6fhCPBHfuPVLgJ85597pwbZFwoY511E/FhEREQknOocuIiLiAQp0ERERD1Cgi4iIeIACXURExAMU6CIiIh4Q1petpaenu/z8/GCXISIi0mdWrVpV4ZzLOHZ5WAd6fn4+K1d2NCGTiIiIN5nZ7o6Wq8ldRETEAxToIiIiHqBAFxER8QAFuoiIiAco0EVERDxAgS4iIuIBCnQREREPUKCLiIh4gAJdRETEAxToIiIiHqBAFxER8QAF+jGGDB2GmQXlZ8jQYcH+80VEJEyF9eQsgVC8dw8/e3lLUPb97fPGBGW/IiIS/nSELhJEahESkd6iI3SRIFKLkIj0loAeoZtZspk9ZWabzWyTmc02s1QzW2Jm2/y3Ke3Wv93Misxsi5mdH8jaRESkf+gvLWGBPkL/BfCSc+5KM4sBBgJ3AEudcw+a2W3AbcB3zWw8cDUwARgMvGJmo51zrQGuUUREPKy/tIQF7AjdzBKB04E/ATjnmpxz1cA8YL5/tfnApf7784AFzrlG59xOoAiYGaj6RCR4+ssRU6jR6+5tgTxCHwGUA4+Y2RRgFXAzkOWcKwFwzpWYWaZ//VzgvXbPL/YvExGP6S9HTKFGr7u3BfIcehQwDfitc+4k4DC+5vXjsQ6WuQ+tZHa9ma00s5Xl5eW9U6mIiEiYC2SgFwPFzrn3/b8/hS/gS80sB8B/W9Zu/SHtnp8H7D92o865h51zM5xzMzIyMgJWvIiISDgJWKA75w4Ae83saDvLOcBG4BngOv+y64BF/vvPAFebWayZDQcKgOWBqk9ERMRLAt3L/UbgcX8P9x3AF/B9iXjSzL4E7AGuAnDOFZrZk/hCvwX4unq4i4iIdE5AA905twaY0cFD5xxn/fuB+wNZk4iIiBdp6FcREREPUKCLiIh4gAJdRETEAxToIiIiHqBAFxER8QAFugAa41lEJNxpPnQBNMaziEi40xG6iIiIByjQRUREPECBLiIi4gEKdBEREQ9QoIuIiHiAAl1ERMQDFOgiIiIeoEAXERHxAAW6iIiIByjQRUREPECBLiIi4gEKdBEREQ9QoIuIiHiAAl1ERMQDFOgiIiIeoEAXERHxAAW6iIiIByjQRUREPECBLiIi4gEKdBEREQ9QoIuIiHiAAl1ERMQDFOgiIiIeoEAXERHxAAW6iIiIByjQRUREPCCggW5mu8xsvZmtMbOV/mWpZrbEzLb5b1ParX+7mRWZ2RYzOz+QtYmIiHhJXxyhn+Wcm+qcm+H//TZgqXOuAFjq/x0zGw9cDUwA5gK/MbPIPqhPREQk7AWjyX0eMN9/fz5wabvlC5xzjc65nUARMLPvyxMREQk/gQ50B7xsZqvM7Hr/siznXAmA/zbTvzwX2NvuucX+ZSIiInICUQHe/hzn3H4zywSWmNnmj1jXOljmPrSS74vB9QBDhw7tnSpFRETCXECP0J1z+/23ZcDT+JrQS80sB8B/W+ZfvRgY0u7pecD+Drb5sHNuhnNuRkZGRiDLFxERCRsBC3QzizezQUfvA+cBG4BngOv8q10HLPLffwa42sxizWw4UAAsD1R9IiIiXhLIJvcs4GkzO7qfvznnXjKzFcCTZvYlYA9wFYBzrtDMngQ2Ai3A151zrQGsT0RExDMCFujOuR3AlA6WVwLnHOc59wP3B6omERERr9JIcSIiIh6gQBcREfEABbqIiIgHKNBFREQ8QIEuIiLiAQp0ERERD1Cgi4iIeIACXURExAMU6CIiIh6gQBcREfEABbqIiIgHKNBFREQ8QIEuIiLiAQp0ERERD1Cgi4iIeIACXURExAMU6CIiIh6gQBcREfEABbqIiIgHKNBFREQ8QIEuIiLiAQp0ERERD1Cgi4iIeIACXURExAMU6CIiIh6gQBcREfEABbqIiIgHKNBFREQ8QIEuIiLiAQp0ERERD1Cgi4iIeIACXURExAMU6CIiIh4Q8EA3s0gzW21mz/l/TzWzJWa2zX+b0m7d282syMy2mNn5ga5NRETEK/riCP1mYFO7328DljrnCoCl/t8xs/HA1cAEYC7wGzOL7IP6REREwl5AA93M8oCLgD+2WzwPmO+/Px+4tN3yBc65RufcTqAImBnI+kRERLwi0EfoPwduBdraLctyzpUA+G8z/ctzgb3t1iv2LxMREZETCFigm9nFQJlzblVnn9LBMtfBdq83s5VmtrK8vLxHNYqIiHhFII/Q5wCXmNkuYAFwtpn9FSg1sxwA/22Zf/1iYEi75+cB+4/dqHPuYefcDOfcjIyMjACWLyIiEj4CFujOududc3nOuXx8nd1edc59FngGuM6/2nXAIv/9Z4CrzSzWzIYDBcDyQNUnIiLiJVFB2OeDwJNm9iVgD3AVgHOu0MyeBDYCLcDXnXOtQahPREQk7PRJoDvnXgNe89+vBM45znr3A/f3RU0iIiJeopHiREREPECBLiIi4gEKdBEREQ9QoIuIiHiAAl1ERMQDFOgiIiIeoEAXERHxAAW6iIiIByjQRUREPECBLiIi4gEKdBEREQ9QoIuIiHiAAl1ERMQDOhXoZjanM8tEREQkODp7hP6rTi4TERGRIPjI+dDNbDZwKpBhZt9u91AiEBnIwkRERKTzPjLQgRggwb/eoHbLa4ArA1WUiIiIdM1HBrpz7nXgdTN71Dm3u49qEhERkS460RH6UbFm9jCQ3/45zrmzA1GUiIiIdE1nA/0fwO+APwKtgStHREREuqOzgd7inPttQCsRERGRbuvsZWvPmtnXzCzHzFKP/gS0MhEREem0zh6hX+e//U67ZQ4Y0bvliIiISHd0KtCdc8MDXYiIiIh0X6cC3cyu7Wi5c+4vvVuOiIiIdEdnm9xPbnc/DjgH+ABQoIuIiISAzja539j+dzNLAh4LSEUiIiLSZd2dPrUeKOjNQkRERKT7OnsO/Vl8vdrBNynLOODJQBUlIiIiXdPZc+g/aXe/BdjtnCsOQD0iIiLSDZ1qcvdP0rIZ34xrKUBTIIsSERGRrulUoJvZJ4HlwFXAJ4H3zUzTp4qIiISIzja53wmc7JwrAzCzDOAV4KlAFSYiIiKd19le7hFHw9yv8kTPNbM4M1tuZmvNrNDM7vEvTzWzJWa2zX+b0u45t5tZkZltMbPzu/zXiIiI9FOdDfSXzGyxmX3ezD4PPA+8cILnNAJnO+emAFOBuWY2C7gNWOqcKwCW+n/HzMYDVwMTgLnAb8wssot/j4iISL90oqPsUWY2xzn3HeD3wGRgCvAu8PBHPdf51Pl/jfb/OGAeMN+/fD5wqf/+PGCBc67RObcTKAJmdvkvEhER6YdOdIT+c6AWwDm30Dn3befct/Adnf/8RBs3s0gzWwOUAUucc+8DWc65Ev82S4BM/+q5wN52Ty/2Lzt2m9eb2UozW1leXn6iEkRERPqFEwV6vnNu3bELnXMrgfwTbdw51+qcmwrkATPNbOJHrG4dbaKDbT7snJvhnJuRkZFxohJERET6hRMFetxHPDagsztxzlUDr+E7N15qZjkA/tujne2KgSHtnpYH7O/sPkRERPqzEwX6CjP7yrELzexLwKqPeqKZZZhZsv/+AODj+AaneQa4zr/adcAi//1ngKvNLNbMhuMbK355J/8OEU9oa3M0trRS39RCm/tQA5WIyHGd6Dr0bwJPm9ln+L8AnwHEAJed4Lk5wHx/T/UI4Enn3HNm9i7wpP9LwR58g9XgnCs0syeBjfiGl/26c661G39Tt1TUNXLPsxtJu+jbvLKplJykOEakJzAgRh3tJbDa2hxbSmspKqtjT1U9LW2+II+NiiAnKY5xOYkUZCZg1tFZKRERn48MdOdcKXCqmZ0FHD3//bxz7tUTbdh/7v2kDpZX4ptPvaPn3A/cf6JtB0JDcysb9h0iLm8828vrKNxfg1kZ43MSmTMyXcEuARE3dDJ/W76HysNNDIqLYsLgRBIHRBNpRkVdI3uq6nlxwwGWx8dwxugMhqQODHbJIa++qYXq+mYizIiLjiBpQLS+DHVDS1sbAFER3Z2UU/paZ+dDXwYsC3AtQZWXMpBlt5yJ2Vn8dPFmymob2VRSw7p9h9heVsc547IYlZkQ7DLFI9raHD9fuo2sa35Ic2sbF03KYWRG/IeCxznH1tI63t1RycLV+5g1IpWZ+akKqGM0tbSxtriazSW1VNX/51QTiXFRjMhIYPqwFBJiOzs4Zv9UWdfImuJq9lc3cPBwEw6IjjQyB8UxOiuB0VmDiIvWwc3xNLW0sflADTsqDlNyqIG2NsfQ/17I5gM1jM1ODPj+9e7ugJmRlRhHVmIcE3OTeGVTKc+vL+G0gnROGpKsD1PpkcaWVr7997U8v76EunVL+PpNXyUqsuOjIDNjTPYgRmTEs3RzGe/tqKKirom5E7KJjND70DlHYUkNbxdV0NDcRl7KAMblpJE+KBbnoLahmV2V9awrrmbDvkNMH5YCEfrYO1ZdYwvLNpexo+IwURHGkNSBjMpIIDLCqG9qYU9VPcu2lPPujkrmjExnwuBEfQ6245xjU0ktb2+voL6plaQB0YzJGkRMZASvPvkwKQMv6JM69M4+gfSEWK6clsfiwlLe3FZBQ3Mrp45MD3ZZEqZaWtu46YnVLC4s5Y4Lx3LDjy4m6ltfO+HzoiMjOH98FhkJsbxVVMFLHOj3od7U0sarW8rYcqCW3OQBfGxUOtlJH74wZ3JeMoeONPN2UQXv76wi6+r7qKhrJD0hNghVh56isjqWbiqlpc0xa3gqk4ckM+CYo3DnHGW1jby5rYKlm8vYUlrLRZNydLSO7324uPAAOyoOk50Yx8WTc8hOjPv3F56Fr88nK/HRPqlFJ0c6ISoyggsnZTNxcCIrdh1kzd7qYJckYaitzfHdf65ncWEpd108nutPH9ml55sZ04elcFpBOkVldSzZVIrrpz3hG5pbWbi6mK0Hapk9Io3Lp+V2GOZHJQ2I5sJJOZw/IYuY7AI+8au32F5ed9z1+4vVew7y/PoSkgZG8+lThnLKiLQPhTn8X6vlFdNyOWdcJiXVDfx9xV4O1vfvmbTrGlr4x6q97Kw4zOkF6XxyRh45SQOC1nqhQO8kM+OssZmMzIjn9a3lbCutDXZJEmZ++/p2/vlBMd/8eAFf/Njwbm9n2tAUZo9IY8uBWlbuPtiLFYaHI82tPL16HxW1TVw8OYeZw1OJ6OQH6NjsREofv5Xm1jY+/Yf32F15OMDVhq73dlTyxrYKRmUkcOX0PFIGxpzwOWbGxMFJXD4tl8aWNp5aVUx1Pw31+qYWFq4upuZIC5dMHcxJQ1OCfhpCgd4FEWbMnZBNTlIcSzaVcvBw/3wjt9fmHHur6lm2pYy/r9jLo+/sYv47u3hu3X5W7qricGNLsEsMCW9sLecnL29h3tTB3HxOQY+3d3J+CqOzEnhneyU7+tGRZktrG8+s2U/lYV+Yj8joekfVptLt/PXLp9DU0san//A+Bw41BKDS0LZmbzXv76xiXM4gLpiY3eWe7IOTB3Dl9Dycg4Wr91Hb0BygSkNTY0sr/1qzn9oGX5jnp8UHuyRAgd5lUZER//4P8Pz6Eppb24JdUtDsqjzM4+/tYeHqfWzcX0NUpJGVGEv6oFiqDjfx9vZKHnl7F0s2llLf1H+DfX/1EW5asJoxWYN44PJJvfIt3sz4+LgsMgfF8vLG0n7xgeqcY8mmUg7UNDB3Qjb56d3/EB2bnchjXzqF6vombnhsJQ3NfTbkRdBtL6/j9a3ljMyI5+PjsojoZj+M1PgYLp06mMbmNhat2U9TS//4LHTO8eKGA1TWNXLRpBxykzs9aGrAKdC7YVBcNOdPyKLycBNvbO1/E8Q0tbTx/PoSFq3ZT6tzzJ2QzfWnj+CKaXlcMDGHiyblcO3sfK6dNYyJuYlsOVDLX9/b0y9PU7S1OW75x1qaW9r47WenMzCm9/qhRvu/XLY5x+LCUs+PLLdi10G2ltYxZ2Rar1xCOjE3iZ99aipriw9xx8L1/aI/QnT6MF7acICsxFjOn5Dd6VMVx5OZGMdFk3OoOtzUb/p0vLezit2V9ZwxOqNHXyoDQYHeTcPS4pk+LIUN+2v61Xm4g/VN/H3FXraX13HqyDQ+N2sYY7IHEd3BZVcp8TGcOSaTa2YOIXFAFC9sOMC72yv7xX/6ox59ZxfvbK/k+xePZ3gA/vMnD4zhzNGZ7Ks+wioPn08vPljPezsqGZM9yHfpWS85f0I23/x4AQtX7+Nvy/f02nZD0eHGFjIuvY2YqAg+MXlwh/9nu2No6kDmjPJ11Fy1x7vvQYCdFYdZ7j9VMSk3KdjlfIgCvQdmDU8ldWAMr2wqo7HF+012lXWN/GNlMUeaW7lsai4n56d26rKptIRYrpo+hAmDE1m+q4pXNpV5/mgSfE2bP3ppM+eMzeRTJw858RO6aVzOIAoyE3h/RxWVdY0B20+wHGlqZXFhKUkDojl7TGavdzy66ewCTitI5wfPbaSozJv9EZxzfH/RBqJSc5k7IZv4Xh5gZ9rQZAoyfX06vNonob6phSUbS0lPiAnI+7A3KNB7ICoygnMnZHG4qYW3tlUEu5yAqqxr5J8f7CPC4KoZeV0egjQywjhnbCanDE9lY0kNr24u8/SRunOOOxauJzYqggeu6J3z5sdjZpw5JoPoKGPpZm99WXLOsXRzKUeaWrlgYjYxUb3/kRURYfz0qikMiI7k5gWrPfnl/Ll1JSz8YB+H3l4QkOGDzXz/v+NjolhceMBzfYuccyzdVEZTaxtzJ2QfdyCoYAvNqsJIdmIcJw1JZsP+Gs9+M61raOHpNb4wv6KTl7d0xMyYNSKNk/NTKNxfw9vbK3u50tDxj5XFvL+zijsuHEfmoI+ahbh3DIyJ4ozRGZQcamCth8ZJ2FJay/byw8wemUZmYuBex8zEOB66cgqF+2v49bLtAdtPMJTVNvD9RRuYMiSZQ+8sCNh+YqMjOX9CFtVHmnljm7f6Fm0s8Q3neurINNJCeEAiBXovOGV4GvExkSzb4q2jI4Dm1jaeXefrwTpvam63w7y92SPSmJSbxKrdB9mw/1AvVBlaKusauf+FTczMT+WTMwLX1H6sMVmDyE8byLs7KqnzwOWChxtbeH1Lue9L89DkgO/v3PFZzJs6mN++VkRRmTc6cPpaijZwpKmVn141BVxgj5zzUgYybWgyG/bVUHywPqD76iuHG1t4c1sFuckDOGlIcrDL+UgK9F4QExXBxwrSKattpHB/TbDL6TXOOV7eWEp5bSMXTMwhY1DvfDM92kQ8NHUgr20uJyZndK9sN1T85OUtHG5s4f7LJnb7kqDuMDPOGJ1Bm4O3isL/FNBrW8ppbnOcOz6rx72xO+v7F49nYEwUdyzcQFtb+H85f2H9AV7ZVMot543ps8mlZo1IIzEuilc3l/17xrZw9trWclraHOeMC83z5u0p0HvJmKxB5CYP4J2iCo545JrWtcWHKCqrY86o9F7voR1hxgUTs4mPjSTjsjup8EhnrsL9h1iwYi/Xzs6nIGtQn+8/eWAM04emsOVALfsOHunz/feWXZWHKSqvY+bwVFLje94q1FnpCbHcedE4lu+q4u8r9/bZfgPhcGMLP3huIxMGJ/ZoZMKuio6M4OyxmRysb2blrvDu9b6jvI6iMt/7sDdaJwNNgd5Ljh51Nra28Y4Hjo5Kaxp4c1s5w9PjmRag5s646EgunjyYyAGDuPWpdWHfSc45x73PbiR5QHSvjAbXXTPyUxgUF8VrW8vC8iizpbWN17aUkzIwmulDe+8Stc66anoes0ak8sMXNlFWE779Yn756jYO1DRw77yJfT6Jz7C0eEZnJbBy10GqwnREzebWNl7bWk5afExQ3ofdoUDvRekJsUzJ83WQKw3jD4KmljZe3HCA+NgozhufFdBmpoxBsRxc9mde3VzG/Hd2BWw/feGlDQd4f2cV3z5vDEkDo4NWR3RkBKcXZFBR18T6feHXR2HV7oMcOtLMmWMygzKbnJnxw8sm0djSxj3Pbezz/feGbaW1/OnNnXxyRl6vXrffFacXZBAVaWF7RcvK3QepbWjhzDEZYTOroQK9l80akcrAmEhe21Ielm9igDe3lXPoSDPnj8/uk+kRaz94jrPHZvLDFzez5UB4dkZqaG7l/hc2MSZrENcE8JrzzhqZEc/Q1IG8s6MyrIbdPXSkmRW7D1KQmcDQAFxe1VkjMhK48axRPL+uhGWby4JWR3c457hrUSHxsVF8d+7YoNURHxvFx0als6/6CBtLwqtv0aEjzazafZDRWQnkpQTvfdhVCvReFhsVyZyR6RyoaWBLGA51urPiMBv21zB9WAq5KX03RvFDV04mITaKW59aS0sYXsP6p7d2UnzwCHd9YnxIXKN6tINcS2sbbxeFx+WBzjle21JGhPmO7oLthjNGMjIjnv95pjCsxnp/dl0J7+6o5Dvnjwn6JVYTBicyOCmOt7ZVEDEgMai1dMUbW8uJMDhtVPDfh10R/E8eDxqXM4jMQbG8XVQZVgMsNDa3snRTKWnxMcwakdqn+05PiOXuSyawtvgQf3prZ5/uu6fKahr49bIizh2fxZxR6cEu599S42OYOiSZjSXhMUbCjorD7KqsZ9bwNBLiencks+6IiYrg3nkT2VNVz+9f3xHscjqltqGZ+57byKTcJK6ZOTTY5WBmnD02k6bWNpJPvzbY5XTKrorD7Kg4zMzhqSHxPuwKBXoAmBmnF2RQ19jC6j3VwS6n094sqqC+qZVzx2d1eTrF3vCJyTmcNz6Lny7ZyvYwmhL0ocVbaG5t484LxwW7lA+ZOdx3Cuj1raF9Cqi5tY3X/R2QpoTQtb5zRqVz8eQcfvNaEXurQv+66l+8so3yukZ+cGnfd4Q7nrSEWKYMSSZhynkhP+hRS5vvfZg8MJqThoRHR7j2FOgBkpsygFEZCazYVRUWg3zEDp1E4f4apg1NISuAI3J9FDPjvksnMiA6ku8+tS4semivK67mqVXFfHHO8JCbeQl8p4A+Nsp3CmhTSeieAlqxq4rahhbOClJHuI9y50XjiIww7nk2tDvIbTlQyyPv7OLqk4cyNYS+FAGcMjyV1sPV3LUotK/vX72nmuojzZw5Onw6wrWnQA+gjxWk4xy8sz20L2M70tRK2twbSRoQzSl93NR+rMzEOO66eDwrdx/kL+/uCmotJ3L0MrX0hBi+cfaoYJdzXGOzB5GdGMfb2ytCcpzyg/VNfLC7mrHZg/q030Zn5SQN4OZzCnhlUylLN5UGu5wOHZ18ZVBcFLeePybY5XxIbFQk1cv+zNriQyF7fX9tQzPLd1YxMiOeYWmh9+W8MxToAZQ0IJqpQ5LZVFIb0pex/fyVrUSnDOacsZm9NqViT1w+LZczx2Two5e2sKcydJs5n11XwsrdB7nlvDEMigveZWonYmacMSaD+qZWlu+sCnY5/8HXEa6cyEjjYyHU/+BYX5gznFGZCdzz7MaQ7CD3rzX7WL6ziu/OHUtKHw7E0xWHN77GzOGp/OilzRwMwWvT3yqqwAGnhUCHzO4K/qe3x508PIUB0ZG8sS00z2GuLz7EH97cQe3axQGZhak7zIwHLp9EZIRx+9OhOeBMfVMLD7ywifE5iVzVh+O1d1d2YhwTBieyZm91SA30sa2sjj1V9Zw6Iq3Xp/TsTTFREdx7yYSQ7CBX09DM/c9vZsqQZD4V4u/Fe+dNoLahhR+/vCXYpfyH4oP1bC2tY8awFJIGhO6X8xNRoAdYbFQks0eksb+6gaIQ6+jV3NrGrf9cR3qCb3CXUJKTNIDbLhjL20WV/GNlcbDL+ZDfvb6DkkMN3H3JhLA513bqyDSiIiJCpoNcY0srb2wtJ3NQLJPykoJdzgmd2q6DXCi1HP3vkq1UHm7kvnl9O3dAd4zNTuTa2cN4Yvke1hVXB7scAFrbfK1Eg+KimBGkQXh6iwK9D0wYnEhafAxvF1WG1GQFD7+xg00lNdw7byKu8XCwy/mQT88cyszhqfzg+Y0hdcqi+GA9v399O5+YMpiZw4Pb56ArBsZEMWtEKnuq6tlZEfx/7/e2V3G4qZWzxmb22eQrPfW9i8YTGWHc+1xhsEsBYOP+Gua/s4vPnDI0LL4UAXzr3NGkxcdy16LCkOggt3rPQSoPN3Hm6IyQGEOiJ8K7+jAREWGcVpDOoSPNrAmRyza2l9fxi6XbuGBiNnMnZge7nA5FRBgPXj6JppY27lq0Idjl/NsPX9iEGdx+QfBG4equyXnJpA6M4Y1tFRAZvKbFmKyRrC2uZlJuEtlBuqqiO7KT4vwd5MqC3kGutc1x+8J1pAyM4ZbzQq8j3PEkxkVzx4VjWbO3mn+sCm4HuZojzbzv7wg3IqNvZqMLJAV6HxmWFs/w9HhW7DwY9MvY2toct/9zPXFREdwzb0JQazmRERkJfOvc0SwuLOXF9SXBLod3t1fywvoD/NcZoxicHHo9sk8kMsI4fbTvy2XiyZcGpYbWNkfqeV8jLjqSOSPTglJDTxztIHf3s8EdQe4v7+5ibfEh7vrEeJLDYCaw9i47KZeT81P40UtbgtZBzjnHsi1lmMEZo8O3I1x7CvQ+dHpBOq3O8da24F7G9ug7u1i+q4rvXTSezEGhf3T05Y8NZ2JuIt9fVEh1ffA6dLW0tnHPs4XkJg/ghjNGBK2OnhqWFs/IjHiSZn8qKIOlPLF8D7GDx3B6QTqxfTBXQG872kFub9URfvf69qDUsK/6CD9evIUzRmdwyZTBQamhJ8yMH1w6kZojzdz3/Kag1LC93D8y4Yi0kL5KpSsU6H0oeWAM04elsKW0luKDwelUs6O8jocWb+asMRlcNSMvKDV0VVRkBA9dMYXq+qag/ecHXxBtPlDLnReN65NJawLp9NEZ4Nq44+n1fdpBrrSmgYde2kzD7nWMye77+eJ7y9EOcr99bXufd5BzznHXvzbgHNx36cSAzoYYSGOzE7nhjBH884PiPj/IaWrxjQiXnhDD1LzkPt13ICnQ+9jJw1JIjIti2ZbyPu8g19rmuOUfa4mNiuTBKyaH1QfB+MGJfPWMkTy1qpg3tpb3+f59QbSFOaPSuCBE+xx0RWJcNAdfn8+b2yp4evW+Ptmnc47bF66nqbWNysX/L6zefx353kXjiYow7vxX334penHDAZZuLuO/zxsdMpeadteNZxcwPD2eO55e36ezAr67o5K6xhbOGZsV8lcGdEXAAt3MhpjZMjPbZGaFZnazf3mqmS0xs23+25R2z7ndzIrMbIuZnR+o2oIpKjKCs8ZkUnW4iZW7Dvbpvv/w5g4+2FPNvfMmBG141574xtmjGJkRz+0L13O4j/sh3P1MIU2tbdx/6aSwD6Kj6la/wPRhKdz73EbK+uAqgoUf7OPVzWV85/yxtBzcH/D9BVp2Uhy3XTiON7dVsGBF33TuOnSkmf95ppCJuYl8/tT8PtlnIMVFR/Lg5ZPYe7CeB17Y3Cf73Fd9hDV7/R0yk8Lvc/CjBPIIvQX4b+fcOGAW8HUzGw/cBix1zhUAS/2/43/samACMBf4jZmFd7vmceSnxzM2exArdlVRUdfYJ/vccqCWn728lbkTssPynBv4/vM/dOVk9h860qdN70s2lvLihgPcdE5BSI7X3n2Oh66cTENzK7cEeOz8vVX13P1sISfnp/AFDwTRUZ+ZOZQ5o9K477mNfXIa7e5nCqmsa+TByyeH/SVWR50yIo0vzRnOY+/t5vUAt741tbTxcuEBkgZEh/TIhN0VsHeEc67EOfeB/34tsAnIBeYB8/2rzQcu9d+fByxwzjU653YCRcDMQNUXbKcXZBAbFckrm0ppDfC1mE0tbdzyj7UkxEVx32Xhe84NYPqwVG44fSRPLN/DSxsOBHx/lXWN3L5wPWOzB/GV08K3I9zxjMxI4HsXjeeNreXMD9DY+c2tbdy0YDUAP/vkVG81cUYYP7piMgDf/vtaWgI4XfKiNft4evU+bjqngIm54XHNeWfdcv4YCjIT+M4/1gZ0JMM3tpVT09DCeeOziInyxhei9vrkLzKzfOAk4H0gyzlXAr7QBzL9q+UC7dutiv3LPGlATCRnjcmgtKYx4ONrP/DiJtbvO8QPL5tEekJsQPfVF7597mgm5SZx28J1AZ3n2znHnU9voOZIM//7qame/AAA+MwpQzlnbCYPvLg5IKN3/eTlLazeU82Prpgc9ud8O5KXMpD7LpvI8l1V/GLptoDsY29VPd97egPTh6XwjbNCdyKg7oqLjuR/PzWV6vpmbl6wOiAHOZtLaijcX8OMYSlheclpZwT8E8rMEoB/At90ztV81KodLPvQv6qZXW9mK81sZXl533eO6k0FWYMYn5PI8l1VAWuue3F9CY+8vYvPn5ofsgPIdFVMVAS/uHoqTS1tfP1vH9DUEpijoqdWFfNS4QG+fd5oxuUkBmQfocDM+PFVU8hIiOWGx1b16mmgZ9bu5/ev7+Azpwzlwkk5vbbdUHPZSXl8ckYe/29ZEW9u693PpSNNrXz1r6sA+Pmnpnqmqf1YE3OTuPuSCby5rYJf9vIXo+j0YSzdXEZu8gBmjwi/sQ86K6DvDDOLxhfmjzvnFvoXl5pZjv/xHKDMv7wYaD+zQB7woZ4zzrmHnXMznHMzMjLCfzCAM0ZnkDwgmsWFpUTEJ/fqtreV1nLrU+uYOiSZOy4c16vbDrYRGQk8dOVkVu0+yA+e6/15qjfur+H7izYwa0SqJ5vaj5UaH8PvPzedg/VNfO3xD3plmtVVuw9yyz/WMjM/lbs+Mb4Xqgxtd18ygYLMBL7++AcUlfXOvA3OOW795zo2ltTwi2umerKFo71rZg7himl5/PLVbb02kFRlXSMZl91JTFQEF0zM9tQpn2MFspe7AX8CNjnnftbuoWeA6/z3rwMWtVt+tZnFmtlwoABYHqj6QkVMVAQXTMqmobmVzMu+12sjT5XVNvD5R1YQFxPJrz8zzZPNxRdPHsz1p4/gsfd288TyPb223UP1zXz1r6tIHhDDr66ZFjaTr/TUxNwkfnTFZJbvrOIbf1tNcw/OB285UMv1f1lJTlIcv/vcdGKjPNm/9T8MjIniT9edTHRkBF98dAWVvdDS8b+vbOPZtfu55bwxnD02qxeqDG1mxv2XTWTa0BRuXrCG93ZU9mh7dY0tfOHRFUQOSuPiyTkhPaNfbwjkp/wc4HPA2Wa2xv9zIfAgcK6ZbQPO9f+Oc64QeBLYCLwEfN05F3oTDwdA5qA4zhufRWzuWG5fuL7HvY3rGlv4yvyVVB1u4s/XnUyuR88XAdx6/hjOGJ3BnU+vZ3FhzzvJNTS38l+Pr6Lk0BF+89lpZAwK/z4HXTFvai73zpvAko2lfPPva7p1OmPj/hqu+cN7REYYj3z+ZFJDdH7uQBiSOpA/XjeD0poGrntkeY86eP3u9e38cuk2rpyex9fOHNmLVYa2uOhI/nTdDIamDeQr81eyanf3Lu893NjCDY+tpHB/DRWLHiQnybufg0cFspf7W845c85Nds5N9f+84JyrdM6d45wr8N9WtXvO/c65kc65Mc65FwNVWygqyBpE9RuP8fTqfdz5rw3dDvWahmau/dP7bNhfwy+vOSlsZmDqrqjICH772WlMzkvmxidW805R90ecam5t821jeyUPXTmZaUPDeyrF7rp2dj53XjiO59eV8Nk/vd+lc+qvbCzl6offJTYqgr/fMNsTE1501UlDU/jd56azrbSOqx9+l7LarnXcdM7x62VFPPjiZi6enMOPwmwQqN6QPDCGv3xxJmkJMXzmj++xZGPXJsIpr23k6off493tlTx0xWSObF8RoEpDi/faYcPYoXf/ztfO9F2SdcfT67vc5FlW28Bn//g+6/cd4tefPolzx3u/iQ58TZ2PfP5k8tMG8vlHVvD8uq6fezvS1MpNT6xmycZS7p03gctOCo9hcQPlK6eP4BdXT2Xt3mou+dVbvLThwEeOhlbT0My9z27ky39ZSV7KQJ68YTbDPXXNftecNSaTRz5/MsUHjzDv/73d6abjI02t3LRgDT9evIV5Uwfzv5+a2m9O+RxrcPIAnvqvUxmdNYgbHlvJjxdv7lTfjreLKrj0129TVFbHH66dwRXT+8//ZW+fUAhD3zl/DBFm/L9lRWwvr+NX10zr1GhG72yv4KYn1lDX2MzvPjudc8b1jzA/KiU+hidvmM2X56/kG098wM6K0Xz1jJGd6hFcVtPAV/6yknX7DvG9i8Zx7ez8wBccBuZNzWVEegLfenINX/3rKmbmp3LljDzOHJNBenwsLW2Owv2HWLa5jEff2UVNQwvXzh7GHReG/1j3veHUUek8ecNsbnxiNZ/+w3t8Yc5wbjhjRIcTIjnneGH9AX74wib2HzrCd+eO5atnjOh3R+bHSk+IZcH1s7hrUSG/XradlwtL+cbZo5g7MftD/TI27DvEn9/aycLV+xieHs+C62cxZUhycAoPEgV6iDEz3yALWQncvnA9c3/xBl87cySfm5XPgJgPf0jurarn569s4+nVxQxPj+fxL58S1pNe9ETywBj++uVT+M5T6/jJy1t5ZVMZ91068biDcLS2Of72/m5+8vJWmlvbePhzM/pNq0ZnTcpL4qWbT+OJFXv57bIibn1q3b8fM4OjB+3njs/iZg8OeNJTE3OTeO7Gj/GD5zbyyNs7eey93cydkM10/7XQhxtb2FRSw+LCA+yqrGdcTiI//eQUZnn40qquGhgTxU+umsLFk3O4+5lCbl6whuSB0UzKTSIvZQDV9c0UldWxrayOmKgI/uvMkdx8TkG//FKpQA9R86bmMmFwEvc+t5EfvrCZ37y2nTkj0zlpaDJREUb1kWbe2V7Jqt0HiYowvvSx4Xzz46M934vzROKiI/nl1VM5d3wWdy3awMW/eotThqdy8eQcxuUkMiAmkqrDTby7vZLn1pWwp6qeU0emce+8iYzK7H/nezsjKjKCz80axmdPGUrh/hre809s0drmGJeTyIxhKWSG4dwAfSU+NooHr5jMV88Yye/f2MErm0p5Zu3/XZEbHWnMHpnOjWcXcOlJuf22if1EzhyTyav/ncHb2yv41+r9FJXV8vL+GpIHRpOXMpDPzhrGpVNzSRrojalQu6N/f/qHuFGZCfzlizNZuauKx9/fw7vbK3m+3bWZE3MTueH0EVw7O99zkwz0hJlxyZTBnFGQwd9X7mH+O7v5/qLC/1gnMsI4dWQat18wlrkTs/t902ZnmBkTc5N0FN5N+enxPHD5JH7oJrL/UAOVdY3Ex0aRlRhHQj//It5ZERHGaQUZnFYQ/mOQBILeRWFgRn4qM/JTcc5RXd8MQGx0BANj9M/3UZIGRnP96SP5ymkjKDnUwKaSGppb20gZGMOozATSPDAMroQfMyM3eYCnLyeV4FAihBEzI6UfXdPbW8yMwckDPDt+s4gI6LI1ERERT1Cgi4iIeIACXURExAMU6CIiIh6gQBcREfEABbqIiIgHKNBFREQ8QIEuIiLiAQp0ERERD1Cgi4iIeIACXURExAMU6CIiIh6gQBcREfEABbqIiIgHKNBFREQ8QIEuIiLiAQp0ERERD1Cgi4iIeIACXURExAMU6CIiIh6gQBcREfEABbqIiIgHKNBFREQ8QIEuIiLiAQp0ERERD1Cgi4iIeEDAAt3M/mxmZWa2od2yVDNbYmbb/Lcp7R673cyKzGyLmZ0fqLpERES8KJBH6I8Cc49Zdhuw1DlXACz1/46ZjQeuBib4n/MbM4sMYG0iIiKeErBAd869AVQds3geMN9/fz5wabvlC5xzjc65nUARMDNQtYmIiHhNX59Dz3LOlQD4bzP9y3OBve3WK/YvExERkU4IlU5x1sEy1+GKZteb2UozW1leXh7gskRERMJDXwd6qZnlAPhvy/zLi4Eh7dbLA/Z3tAHn3MPOuRnOuRkZGRkBLVZERCRc9HWgPwNc579/HbCo3fKrzSzWzIYDBcDyPq5NREQkbEUFasNm9gRwJpBuZsXA/wAPAk+a2ZeAPcBVAM65QjN7EtgItABfd861Bqo2ERERrwlYoDvnrjnOQ+ccZ/37gfsDVY+IiIiXhUqnOBEREekBBbqIiIgHKNBFREQ8QIEuIiLiAQp0ERERD1Cgi4iIeIACXURExAMU6CIiIh6gQBcREfEABbqIiIgHKNBFREQ8QIEuIiLiAQp0ERERD1Cgi4iIeIACXURExAMU6CIiIh6gQBcREfEABbqIiIgHKNBFREQ8QIEuIiLiAQp0ERERD1Cgi4iIeIACXURExAMU6CIiIh6gQBcREfEABbqIiIgHKNBFREQ8QIEuIiLiAQp0ERERD1Cgi4iIeIACXURExAMU6CIiIh6gQBcREfGAkAt0M5trZlvMrMjMbgt2PSIiIuEgpALdzCKBXwMXAOOBa8xsfHCrEhERCX0hFejATKDIObfDOdcELADmBbkmERGRkBdqgZ4L7G33e7F/mYiIiHwEc84Fu4Z/M7OrgPOdc1/2//45YKZz7sZ261wPXO//dQywpZfLSAcqenmb/Y1ew57Ta9hzeg17Tq9hzwXiNRzmnMs4dmFUL++kp4qBIe1+zwP2t1/BOfcw8HCgCjCzlc65GYHafn+g17Dn9Br2nF7DntNr2HN9+RqGWpP7CqDAzIabWQxwNfBMkGsSEREJeSF1hO6cazGzbwCLgUjgz865wiCXJSIiEvJCKtABnHMvAC8EsYSANef3I3oNe06vYc/pNew5vYY912evYUh1ihMREZHuCbVz6CIiItINCnQ/DTnbc2b2ZzMrM7MNwa4lXJnZEDNbZmabzKzQzG4Odk3hxszizGy5ma31v4b3BLumcGVmkWa22syeC3Yt4cjMdpnZejNbY2YrA74/Nbn/e8jZrcC5+C6dWwFc45zbGNTCwoyZnQ7UAX9xzk0Mdj3hyMxygBzn3AdmNghYBVyq92LnmZkB8c65OjOLBt4CbnbOvRfk0sKOmX0bmAEkOucuDnY94cbMdgEznHN9ci2/jtB9NORsL3DOvQFUBbuOcOacK3HOfeC/XwtsQqMldonzqfP/Gu3/0ZFLF5lZHnAR8Mdg1yKdo0D30ZCzEnLMLB84CXg/yKWEHX9T8RqgDFjinNNr2HU/B24F2oJcRzhzwMtmtso/ymlAKdB9rINl+kYvQWNmCcA/gW8652qCXU+4cc61Ouem4httcqaZ6RRQF5jZxUCZc25VsGsJc3Occ9PwzSD6df9pyYBRoPuccMhZkb7iP+/7T+Bx59zCYNcTzpxz1cBrwNzgVhJ25gCX+M8BLwDONrO/Brek8OOc2++/LQOexnd6N2AU6D4aclZCgr9D15+ATc65nwW7nnBkZhlmluy/PwD4OLA5qEWFGefc7c65POdcPr7Pw1edc58Ncllhxczi/R1bMbN44DwgoFcAKdDxDTkLHB1ydhPwpIac7TozewJ4FxhjZsVm9qVg1xSG5gCfw3dEtMb/c2GwiwozOcAyM1uH78v6EuecLruSvpYFvGVma4HlwPPOuZcCuUNdtiYiIuIBOkIXERHxAAW6iIiIByjQRUREPECBLiIi4gEKdBEREQ9QoIv0Y2b2qJld2cHywWb2lP/+mcebbcs/m1R6oOsUkROLCnYBIhJ6/CNcfSjoO8M/OI455zQGuEgf0hG6SD9iZtea2Tr/XOGP+RefbmbvmNmOo0frZpbf0bz2ZpZmZi/758j+Pf55EPzrbzKz3wAfAEPM7DtmtsK/v3uOWe8P/rnKX/aP5iYiPaRAF+knzGwCcCdwtnNuCnCz/6Ec4GPAxcCDJ9jM/wBvOedOwjc88tB2j40B/uJ/bAxQgG/s6qnA9HYTUxQAv3bOTQCqgSt69peJCKjJXaQ/ORt4yjlXAeCcq/K1jvMvf/P4RjPLOsE2Tgcu9z//eTM72O6x3c659/z3z/P/rPb/noAvyPcAO51za/zLVwH5PfmjRMRHgS7SfxgdTwvceMw6J3K88aIPH7OdB5xzv/+PAnxzvLffXyugJneRXqAmd5H+YynwSTNLAzCz1G5s4w3gM/7nXwCkHGe9xcAX/fO6Y2a5ZpbZjf2JSCfpCF2kn3DOFZrZ/cDrZtbK/zWHd8U9wBNm9gHwOr4m9I729bKZjQPe9Tfr1wGfxXdELiIBoNnWREREPEBN7iIiIh6gQBcREfEABbqIiIgHKNBFREQ8QIEuIiLiAQp0ERERD1Cgi4iIeIACXURExAP+P5me25Lvf04oAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<Figure size 576x360 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Histrogram of children:\n",
    "plt.figure(figsize=(8,5))\n",
    "sns.histplot(train_data['children'], kde=True)\n",
    "plt.title('childrens', fontsize=20)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Sex:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Male   : 2029\n",
      "Female : 1601\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\Nayan\\Anaconda3\\lib\\site-packages\\seaborn\\_decorators.py:43: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.\n",
      "  FutureWarning\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Value Counts:\n",
    "print(\"Male   :\", train_data['sex'].value_counts()[0])\n",
    "print(\"Female :\", train_data['sex'].value_counts()[1])\n",
    "\n",
    "# Visualization:\n",
    "plt.figure(figsize=(6,4))\n",
    "sns.countplot(train_data['sex'])\n",
    "plt.title('Sex', fontsize=20)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Smokers:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Smokers     : 560\n",
      "Non-Smokers : 3070\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\Nayan\\Anaconda3\\lib\\site-packages\\seaborn\\_decorators.py:43: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.\n",
      "  FutureWarning\n",
      "C:\\Users\\Nayan\\Anaconda3\\lib\\site-packages\\seaborn\\_decorators.py:43: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.\n",
      "  FutureWarning\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Value Counts:\n",
    "print(\"Smokers     :\", train_data['smoker'].value_counts()[1])\n",
    "print(\"Non-Smokers :\", train_data['smoker'].value_counts()[0])\n",
    "\n",
    "# Visualization:\n",
    "sns.countplot(train_data['smoker'])\n",
    "sns.countplot(train_data['smoker'])\n",
    "plt.title('Smokers', fontsize=20)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.heatmap(train_data.corr(),annot = True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Region:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "South-East region : 1021\n",
      "North-West region : 911\n",
      "South-West region : 850\n",
      "North-East region : 848\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\Nayan\\Anaconda3\\lib\\site-packages\\seaborn\\_decorators.py:43: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.\n",
      "  FutureWarning\n",
      "C:\\Users\\Nayan\\Anaconda3\\lib\\site-packages\\seaborn\\_decorators.py:43: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.\n",
      "  FutureWarning\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYsAAAEbCAYAAAArhqjIAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8vihELAAAACXBIWXMAAAsTAAALEwEAmpwYAAAZq0lEQVR4nO3deZhldX3n8feHRRBxaUKDCMRGbUWMKx1UFEVxFHUURsXg86CgOBgH14lmIKNxSYgaTcZlgoIbbfQRCYpgMirYCiou0CxR2aQFhZYW2ogKLijwnT/Or8K1uMUpqrvurer7fj3Pfe65v/M7537r1Kn63LPeVBWSJN2RzcZdgCRp4TMsJEm9DAtJUi/DQpLUy7CQJPUyLCRJvQwLaQySVJIzx12HNFuGhTZp7Z/y4OOWJD9LcmaSw5Jk3DVKi8EW4y5AGpG3tOctgQcA/w14IrACeMUY6nkw8OsxvK80J/EKbm3KkhRAVWVa++OArwIB7l9VV46hPGnRcDeUJlJVnQ1cShcWe04fn+TRSU5O8pMkv0tydZLjktxn2PyS/GmS05PckOSXSb6U5LFJ3tx2f+07rf/QYxZJ7pnkbUkuS/LbJNcn+WKSpwzpu2+bz5uTPCLJvyX5eZJfJzkryd5Dprl7kjcm+V6r84YkP0jyqSS3Ww7SFHdDaZJNbW38/g8akxcDHwRuAk4DrgaWAy8FnpXkMVV11UD/fYDT6XZxfRr4AfBQ4CvAl2ddTHIv4GxgD+Bc4N3A9sDzgdOTvLyqjhsy6QrgL4FvAh8C/hh4LrAqySOq6rI2/wBfAPYe6HszsCuwL/A14LzZ1qsJU1U+fGyyD6C61fx27U8AbqELhJ0G2h8I/A5YA+w8bZont2lOGWjbDLi8vc/Tp/X/86n3B/YdUteZ09qOa+3H0XYRt/blwC9arcsG2vcdmP9h0+b1stZ+7EDbQ1vbKUOWx2bAknH/vnws3Ie7oTQR2q6aNyc5JsmngC/RbVm8rqrWDXR9Od0Wwqur6seD86iqL9NtaTwryd1b8950B8y/UlWfn/a2xwPfn2V9WwKHADcCR1fVfx5MrKrLgfcCdwFeNGTys6vqhGltH6HbathrSP/fTG+oqlur6vrZ1KrJ5G4oTYo3TXtdwOFV9dFp7Y9tz09M8qdD5rMDsDndFsh5wCNb+9end6yqW5N8o/XtszuwDd0//p8NGf9l4A0D7zdo9ZD3/n2Sa4ElA80XAxcCL0hyX+DUVvfqqvrdLGrUBDMsNBGqnQ2V5G50gfBh4ANJftS2GKb8UXt+fc8st23P92zP187Qb6b26abms26G8VPt9xoy7uczTHMzXbABUFW3JHky8NfA84B3tFE3JFlJt0Vz4yzr1YRxN5QmSlX9qqq+BDyL7h/pyiTbDHT5RXu+Z1XlDh5ntX6/bM87zvCWM7VPN/W+955h/E7T+s1JVV1fVa+tql257aD9pXTXmrx/Q+atTZthoYlUVd+hO+NpF+C1A6O+1Z73meWsLmjPj58+IslmdMc0ZuMyuov0HpFkyZDxT2rP589yfr2qak1VfZju4sQbgQM21ry16TEsNMn+Fvgt8LqBf9D/l+5U2v+T5HbHGpLcpZ0qO+VsulNln5Tk6dO6H8HsjlfQjhl8gm731lunvef9gVe1uv55NvMbJsluSR4yZNQSYCuGHPiWpnjMQhOrqn6c5Djg1XTXKRxdVZcmeQnd2UQXJfkC3RlNW9Jdv7APsJ7ugPTUQeyX0l2/cFqSqessHgb8F+DzwNOBW2dR0lFt/q9oB9e/wm3XWdwdeEVt2JXmDwdOSXIe8D3gGmAp3RbFltx2DEO6HbcsNOneRrf751VJdgSoqo/TXdX9Cbp/+q+gO631AcDJwP8YnEFVnUm3K+dM4Jl0WwF3pdt1dEXr9kt6tLOgHgv8Pd2B9v8JHAScA+xfVcfO+afsrKb7eW8C9gf+gi7IzgOeUVX/uIHz1ybMe0NJ8yjJ2cCj6Q6Y/2rc9Uhz5ZaFtIGSbNNu1TG9/TC6A9ynGxRa7NyykDZQkt3pzoo6g+42IVvQXTz3eLprIPauqkvGVqC0ERgW0gZqZ1K9k+64xb3pziz6Cd0tRY6pqh+MsTxpozAsJEm9NtlTZ7fffvtatmzZuMuQpEXlvPPO+2lVLZ3evsmGxbJly1i9+nb3V5Mk3YEkPxrW7tlQkqRehoUkqZdhIUnqZVhIknoZFpKkXoaFJKmXYSFJ6mVYSJJ6GRaSpF6b7BXcGq2r3vrQcZewYPzxX3933CVIG928bVkk+UiS65J8b6BtuyRnJLm8PS8ZGHd0kjVJLkvytIH2PZN8t417b5LMV82SpOHmczfUCXRf3TjoKGBVVS0HVrXXJNkDOBh4SJvm2CSbt2neT/fF98vbY/o8JUnzbN7Coqq+CvxsWvMBwMo2vBI4cKD9xKq6qX0h/RpgryQ7Afeoqm9Wdy/1jw1MI0kakVEf4N6xqtYBtOcdWvvOwNUD/da2tp3b8PT2oZIckWR1ktXr16/fqIVL0iRbKGdDDTsOUXfQPlRVHV9VK6pqxdKlt7sduyRpjkYdFte2XUu05+ta+1pg14F+uwDXtPZdhrRLkkZo1GFxGnBoGz4UOHWg/eAkWyXZje5A9jltV9UNSR7TzoJ60cA0kqQRmbfrLJJ8EtgX2D7JWuBNwNuBk5IcDlwFHARQVRclOQm4GLgZOLKqbmmzejndmVV3BT7fHpKkEZq3sKiqF8wwar8Z+h8DHDOkfTXwJxuxNEnSnbRQDnBLkhYww0KS1MuwkCT1MiwkSb0MC0lSL8NCktTLsJAk9TIsJEm9DAtJUi/DQpLUy7CQJPUyLCRJvebtRoKS5uZx73vcuEtYMM5+5dnjLkGNWxaSpF6GhSSpl2EhSeplWEiSehkWkqRehoUkqZdhIUnqZVhIknoZFpKkXoaFJKmXYSFJ6uW9oSRt0s56whPHXcKC8cSvnjXnaSc2LPZ8/cfGXcKCcd47XzTuEiQtcO6GkiT1MiwkSb0MC0lSL8NCktTLsJAk9RpLWCR5bZKLknwvySeTbJ1kuyRnJLm8PS8Z6H90kjVJLkvytHHULEmTbORhkWRn4FXAiqr6E2Bz4GDgKGBVVS0HVrXXJNmjjX8IsD9wbJLNR123JE2yce2G2gK4a5ItgG2Aa4ADgJVt/ErgwDZ8AHBiVd1UVVcCa4C9RluuJE22kYdFVf0YeBdwFbAO+EVVnQ7sWFXrWp91wA5tkp2Bqwdmsba1SZJGZBy7oZbQbS3sBtwHuFuSQ+5okiFtNcO8j0iyOsnq9evXb3ixkiRgPLuhngJcWVXrq+r3wGeAvYFrk+wE0J6va/3XArsOTL8L3W6r26mq46tqRVWtWLp06bz9AJI0acYRFlcBj0myTZIA+wGXAKcBh7Y+hwKntuHTgIOTbJVkN2A5cM6Ia5akiTbyGwlW1beTnAycD9wMXAAcD2wLnJTkcLpAOaj1vyjJScDFrf+RVXXLqOuWpEk2lrvOVtWbgDdNa76JbitjWP9jgGPmuy5J0nBewS1J6mVYSJJ6GRaSpF6GhSSpl2EhSeplWEiSehkWkqRehoUkqZdhIUnqZVhIknoZFpKkXoaFJKmXYSFJ6mVYSJJ6GRaSpF6GhSSpl2EhSeplWEiSehkWkqRehoUkqZdhIUnqZVhIknoZFpKkXoaFJKmXYSFJ6mVYSJJ6GRaSpF6GhSSpl2EhSeplWEiSehkWkqRehoUkqddYwiLJvZKcnOTSJJckeWyS7ZKckeTy9rxkoP/RSdYkuSzJ08ZRsyRNsnFtWbwH+EJV7Q48HLgEOApYVVXLgVXtNUn2AA4GHgLsDxybZPOxVC1JE2rkYZHkHsATgA8DVNXvqurnwAHAytZtJXBgGz4AOLGqbqqqK4E1wF6jrFmSJt04tizuB6wHPprkgiQfSnI3YMeqWgfQnndo/XcGrh6Yfm1ru50kRyRZnWT1+vXr5+8nkKQJM46w2AJ4FPD+qnok8CvaLqcZZEhbDetYVcdX1YqqWrF06dINr1SSBMwyLJKsmk3bLK0F1lbVt9vrk+nC49okO7V57wRcN9B/14HpdwGumeN7S5Lm4A7DIsnWSbYDtk+ypJ2xtF2SZcB95vKGVfUT4OokD2pN+wEXA6cBh7a2Q4FT2/BpwMFJtkqyG7AcOGcu7y1Jmpstesa/DHgNXTCcx227hH4J/NMGvO8rgU8kuQtwBfBiuuA6KcnhwFXAQQBVdVGSk+gC5WbgyKq6ZQPeW5J0J91hWFTVe4D3JHllVb1vY71pVV0IrBgyar8Z+h8DHLOx3l+SdOf0bVkAUFXvS7I3sGxwmqr62DzVJUlaQGYVFkn+Gbg/cCEwtQuoAMNCkibArMKCbpfRHlU19JRVSdKmbbbXWXwPuPd8FiJJWrhmu2WxPXBxknOAm6Yaq+rZ81KVJGlBmW1YvHk+i5AkLWyzPRvqrPkuRJK0cM32bKgbuO1+THcBtgR+VVX3mK/CJEkLx2y3LO4++DrJgXibcEmaGHO662xVfRZ48sYtRZK0UM12N9RzBl5uRnfdhddcSNKEmO3ZUM8aGL4Z+CHdN9hJkibAbI9ZvHi+C5EkLVyz/fKjXZKckuS6JNcm+XSSXea7OEnSwjDbA9wfpfsSovvQff/151qbJGkCzDYsllbVR6vq5vY4AfBLriVpQsw2LH6a5JAkm7fHIcB/zGdhkqSFY7Zh8RLg+cBPgHXA8+i+ClWSNAFme+rs3wCHVtX1AEm2A95FFyKSpE3cbLcsHjYVFABV9TPgkfNTkiRpoZltWGyWZMnUi7ZlMdutEknSIjfbf/j/AHwjycl0t/l4PnDMvFUlSVpQZnsF98eSrKa7eWCA51TVxfNamSRpwZj1rqQWDgaEJE2gOd2iXJI0WQwLSVIvw0KS1MuwkCT1MiwkSb0MC0lSL8NCktTLsJAk9RpbWLTvxbggyb+219slOSPJ5e158F5URydZk+SyJE8bV82SNKnGuWXxauCSgddHAauqajmwqr0myR7AwcBDgP2BY5NsPuJaJWmijSUskuwCPBP40EDzAcDKNrwSOHCg/cSquqmqrgTWAHuNqFRJEuPbsng38JfArQNtO1bVOoD2vENr3xm4eqDf2tZ2O0mOSLI6yer169dv9KIlaVKNPCyS/Ffguqo6b7aTDGmrYR2r6viqWlFVK5YuXTrnGiVJf2gcX2D0OODZSZ4BbA3cI8nHgWuT7FRV65LsBFzX+q8Fdh2YfhfgmpFWLEkTbuRbFlV1dFXtUlXL6A5cf7mqDgFOAw5t3Q4FTm3DpwEHJ9kqyW7AcuCcEZctSRNtIX016tuBk5IcDlwFHARQVRclOYnuuzRuBo6sqlvGV6YkTZ6xhkVVnQmc2Yb/A9hvhn7H4Ne4StLYeAW3JKmXYSFJ6mVYSJJ6GRaSpF6GhSSpl2EhSeplWEiSehkWkqRehoUkqZdhIUnqZVhIknoZFpKkXoaFJKmXYSFJ6mVYSJJ6GRaSpF6GhSSpl2EhSeplWEiSehkWkqRehoUkqZdhIUnqZVhIknoZFpKkXoaFJKmXYSFJ6mVYSJJ6GRaSpF6GhSSpl2EhSeplWEiSeo08LJLsmuQrSS5JclGSV7f27ZKckeTy9rxkYJqjk6xJclmSp426ZkmadOPYsrgZ+IuqejDwGODIJHsARwGrqmo5sKq9po07GHgIsD9wbJLNx1C3JE2skYdFVa2rqvPb8A3AJcDOwAHAytZtJXBgGz4AOLGqbqqqK4E1wF4jLVqSJtxYj1kkWQY8Evg2sGNVrYMuUIAdWredgasHJlvb2obN74gkq5OsXr9+/bzVLUmTZmxhkWRb4NPAa6rql3fUdUhbDetYVcdX1YqqWrF06dKNUaYkiTGFRZIt6YLiE1X1mdZ8bZKd2vidgOta+1pg14HJdwGuGVWtkqTxnA0V4MPAJVX1jwOjTgMObcOHAqcOtB+cZKskuwHLgXNGVa8kCbYYw3s+Dngh8N0kF7a2vwLeDpyU5HDgKuAggKq6KMlJwMV0Z1IdWVW3jLxqSZpgIw+Lqvo6w49DAOw3wzTHAMfMW1GSpDvkFdySpF6GhSSpl2EhSeplWEiSehkWkqRehoUkqZdhIUnqZVhIknoZFpKkXoaFJKmXYSFJ6mVYSJJ6GRaSpF6GhSSpl2EhSeplWEiSehkWkqRehoUkqZdhIUnqZVhIknoZFpKkXoaFJKmXYSFJ6mVYSJJ6GRaSpF6GhSSpl2EhSeplWEiSehkWkqRehoUkqZdhIUnqZVhIknotmrBIsn+Sy5KsSXLUuOuRpEmyKMIiyebAPwFPB/YAXpBkj/FWJUmTY1GEBbAXsKaqrqiq3wEnAgeMuSZJmhipqnHX0CvJ84D9q+ql7fULgUdX1Sum9TsCOKK9fBBw2UgLnZvtgZ+Ou4hNhMty43J5blyLZXnet6qWTm/cYhyVzEGGtN0u5arqeOD4+S9n40myuqpWjLuOTYHLcuNyeW5ci315LpbdUGuBXQde7wJcM6ZaJGniLJawOBdYnmS3JHcBDgZOG3NNkjQxFsVuqKq6OckrgC8CmwMfqaqLxlzWxrKodpstcC7LjcvluXEt6uW5KA5wS5LGa7HshpIkjZFhIUnqZVjMsyQHDl5tnuTMJPN2+lyS1yTZZr7mP25J9k2y98DrE9p1OPP1focluc98zX+cRr1uDrzPJrmOjnrdHHifkayjhsU8SrIFcCDdLUpG5TXAJveHOGBfYO++ThvRYcAmFxZjWjenvIZNcx3dl9Gum1MOYxTraFX5uIMHsAy4BPggcBFwOnBX4BHAt4DvAKcAS1r/M4G/A84C/jfwM+BK4ELg/m38O4BzgO8D+7TpNgfeSXea8HeAl7X2bYFVwPnAd4EDWvvdgH8D/h34HvBnwKuA37V+Xxn3shuyLIfVvB9wQav5I8BWre8Pge3b8Iq23JYBPwF+3JbnPsAJwHuBbwBXAM8beL/XDyzPtwy0fxY4r/0+jxhY/ie0ur4LvBZ4HnAj3Z0ALgTuOu5lOKZ18/8BD2vDFwB/3Yb/BnjpTMt6Ma2jo1w3gWOBZ7fhU+jO7gQ4HPjbNnxI+z1cCBzX1s+xrqNj/yUt9EdbCW4GHtFen9R+kd8Bntja3gq8uw2fCRw7MP0J/OE/sDOBf2jDzwC+1IaPAN7QhrcCVgO70Z3efI/Wvj2whu6K9ucCHxyY7z2nr8gL7TGsZuBq4IHt9ceA10z/Oab+INvwm4HXTVu+/0K3lbwH3T3EAJ5Kd6pi2rh/BZ7Qxm3Xnu/a/vD+CNgTOGNgvvca+H2tGPeyG/O6eRRwJHAPukD4Ymv/Ct1tdYYu68W0jo543TwYeGcbPgf4Vhv+KPA04MHA54AtW/uxwIvGvY66G2p2rqyqC9vweXSfwu5VVWe1tpV0fxxTPtUzv88MzGtZG34q8KIkFwLfpvsHtpzuD/DvknwH+BKwM7Aj3SeLpyR5R5J9quoXc/vRRuoPaqb72a+squ+38dOX42x9tqpuraqL6ZYNdMvzqXSfDM8HdqdbngCvSvLvdJ++d23tVwD3S/K+JPsDv5xDHeMwinXza20ej6f79L1tO+awrKouY+ZlvZjW0VGum18D9mnHiy4Grk2yE/BYuq2Q/eiC4dz2/2A/4H6MeR1dFBflLQA3DQzfAtyrp/+vZjm/W7jtdxDglVX1xcGOSQ4DlgJ7VtXvk/wQ2Lqqvp9kT7pPgG9LcnpVvbXvBxmn6TXT7TaZyc3cdkxt655ZD/5+MvD8tqo6brBjkn2BpwCPrapfJzmTbnlen+ThdJ/sjgSeD7yk72daAEaxbp5L9wn6CuAMui3c/04XKDDDsgZYLOvoKNfNqvpxkiXA/sBXge3o1rcbq+qGJAFWVtXR02c2znXULYu5+QVwffsEAvBCuv3Aw9wA3H0W8/wi8PIkWwIkeWCSu9FtDl/XguJJwH3b+PsAv66qjwPvAh51J99v5IbUvDewLMkDWpfB5fhDuk9X0O0imHJnludLkmzb3nvnJDvQLc/rW1DsDjymjd8e2KyqPg28kUWwPGew0dfN6r4W4Gq6f07fovtk/Lr2DDMs68W0jo543QT4Jt2B/q9y++W5CnheW19Jsl2S+457HXXLYu4OBT7QNsevAF48Q78TgQ8meRXdwaiZfIhu0/f89sliPd3ZKp8APpdkNd0BrEtb/4cC70xyK/B74OWt/Xjg80nWVdWT5vajzZthNd8T+Jd2ds65wAda37cAH07yV3S75aZ8Djg5yQHAK2d6o6o6PcmDgW92i5Mb6fbnfwH487Zb7zK6f37Q7d77aJKpD1BTn+pOoPs9/4Zua+Q3c/3hR2hjr5vQ/SPbr4Xs1+hu5vk1uMNl/QAWzzo6snWz+Rrw1Kpak+RHdFsXU8vz4iRvAE5v6+Pv6bYkfsMY11Fv9yFJ6uVuKElSL8NCktTLsJAk9TIsJEm9DAtJUi/DQhqDJG9N8pRx1yHNlqfOShuoXReTqrp13LVI88UtC2kOkixLckmSY+nuh/TGJOcm+U6Stwz0e2OSS5OckeSTSV7X2v/zuw6S7JfkgiTfTfKRJFu19h8meUuS89u43cfxs0pgWEgb4kF0dyP9X3RXgO9Fd3vwPZM8Id0XCT0XeCTwHLr7K/2BJFvTXYH7Z1X1ULq7Krx8oMtPq+pRwPvpbgkhjYVhIc3dj6rqW8x819XHA6dW1W+q6ga620FM9yDu+O6mw+4CK42c94aS5m7qDq4z3eH2tbOYR3rGD7sLrDRybllIG26mO9x+HXhWkq3buGcOmfZSZr67qbRg+ElF2kAz3XW1qs5NchrdV3X+iO7bD38xbdrfJnkxw+9uKi0YnjorzaMk21bVje124V+l+87v88ddl3RnuWUhza/j29dnbk337WcGhRYltywkSb08wC1J6mVYSJJ6GRaSpF6GhSSpl2EhSer1/wEpBCRHfx5EjQAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Value Counts:\n",
    "print(\"South-East region :\", train_data['region'].value_counts()[0])\n",
    "print(\"North-West region :\", train_data['region'].value_counts()[1])\n",
    "print(\"South-West region :\", train_data['region'].value_counts()[2])\n",
    "print(\"North-East region :\", train_data['region'].value_counts()[3])\n",
    "\n",
    "# Visualization:\n",
    "sns.countplot(train_data['region'])\n",
    "sns.countplot(train_data['region'])\n",
    "plt.title('Regions', fontsize=20)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>age</th>\n",
       "      <th>sex</th>\n",
       "      <th>bmi</th>\n",
       "      <th>smoker</th>\n",
       "      <th>region</th>\n",
       "      <th>children</th>\n",
       "      <th>charges</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>21.000000</td>\n",
       "      <td>male</td>\n",
       "      <td>25.745000</td>\n",
       "      <td>no</td>\n",
       "      <td>northeast</td>\n",
       "      <td>2</td>\n",
       "      <td>3279.868550</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>36.976978</td>\n",
       "      <td>female</td>\n",
       "      <td>25.744165</td>\n",
       "      <td>yes</td>\n",
       "      <td>southeast</td>\n",
       "      <td>3</td>\n",
       "      <td>21454.494239</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>18.000000</td>\n",
       "      <td>male</td>\n",
       "      <td>30.030000</td>\n",
       "      <td>no</td>\n",
       "      <td>southeast</td>\n",
       "      <td>1</td>\n",
       "      <td>1720.353700</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>37.000000</td>\n",
       "      <td>male</td>\n",
       "      <td>30.676891</td>\n",
       "      <td>no</td>\n",
       "      <td>northeast</td>\n",
       "      <td>3</td>\n",
       "      <td>6801.437542</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>58.000000</td>\n",
       "      <td>male</td>\n",
       "      <td>32.010000</td>\n",
       "      <td>no</td>\n",
       "      <td>southeast</td>\n",
       "      <td>1</td>\n",
       "      <td>11946.625900</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         age     sex        bmi smoker     region  children       charges\n",
       "0  21.000000    male  25.745000     no  northeast         2   3279.868550\n",
       "1  36.976978  female  25.744165    yes  southeast         3  21454.494239\n",
       "2  18.000000    male  30.030000     no  southeast         1   1720.353700\n",
       "3  37.000000    male  30.676891     no  northeast         3   6801.437542\n",
       "4  58.000000    male  32.010000     no  southeast         1  11946.625900"
      ]
     },
     "execution_count": 78,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# top 5 records\n",
    "train_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Rounding up & down Age:\n",
    "train_data['age'] = round(train_data['age'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>age</th>\n",
       "      <th>sex</th>\n",
       "      <th>bmi</th>\n",
       "      <th>smoker</th>\n",
       "      <th>region</th>\n",
       "      <th>children</th>\n",
       "      <th>charges</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>21.0</td>\n",
       "      <td>male</td>\n",
       "      <td>25.745000</td>\n",
       "      <td>no</td>\n",
       "      <td>northeast</td>\n",
       "      <td>2</td>\n",
       "      <td>3279.868550</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>37.0</td>\n",
       "      <td>female</td>\n",
       "      <td>25.744165</td>\n",
       "      <td>yes</td>\n",
       "      <td>southeast</td>\n",
       "      <td>3</td>\n",
       "      <td>21454.494239</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>18.0</td>\n",
       "      <td>male</td>\n",
       "      <td>30.030000</td>\n",
       "      <td>no</td>\n",
       "      <td>southeast</td>\n",
       "      <td>1</td>\n",
       "      <td>1720.353700</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>37.0</td>\n",
       "      <td>male</td>\n",
       "      <td>30.676891</td>\n",
       "      <td>no</td>\n",
       "      <td>northeast</td>\n",
       "      <td>3</td>\n",
       "      <td>6801.437542</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>58.0</td>\n",
       "      <td>male</td>\n",
       "      <td>32.010000</td>\n",
       "      <td>no</td>\n",
       "      <td>southeast</td>\n",
       "      <td>1</td>\n",
       "      <td>11946.625900</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    age     sex        bmi smoker     region  children       charges\n",
       "0  21.0    male  25.745000     no  northeast         2   3279.868550\n",
       "1  37.0  female  25.744165    yes  southeast         3  21454.494239\n",
       "2  18.0    male  30.030000     no  southeast         1   1720.353700\n",
       "3  37.0    male  30.676891     no  northeast         3   6801.437542\n",
       "4  58.0    male  32.010000     no  southeast         1  11946.625900"
      ]
     },
     "execution_count": 80,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# top 5 records, after rounding up & down Age:\n",
    "train_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Encoding:\n",
    "train_data = pd.get_dummies(train_data, drop_first=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>age</th>\n",
       "      <th>bmi</th>\n",
       "      <th>children</th>\n",
       "      <th>charges</th>\n",
       "      <th>sex_male</th>\n",
       "      <th>smoker_yes</th>\n",
       "      <th>region_northwest</th>\n",
       "      <th>region_southeast</th>\n",
       "      <th>region_southwest</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>21.0</td>\n",
       "      <td>25.745000</td>\n",
       "      <td>2</td>\n",
       "      <td>3279.868550</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>37.0</td>\n",
       "      <td>25.744165</td>\n",
       "      <td>3</td>\n",
       "      <td>21454.494239</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    age        bmi  children       charges  sex_male  smoker_yes  \\\n",
       "0  21.0  25.745000         2   3279.868550         1           0   \n",
       "1  37.0  25.744165         3  21454.494239         0           1   \n",
       "\n",
       "   region_northwest  region_southeast  region_southwest  \n",
       "0                 0                 0                 0  \n",
       "1                 0                 1                 0  "
      ]
     },
     "execution_count": 82,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# top 2 records, after encoding:\n",
    "train_data.head(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['age', 'bmi', 'children', 'charges', 'sex_male', 'smoker_yes',\n",
       "       'region_northwest', 'region_southeast', 'region_southwest'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 83,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Columns of dataset:\n",
    "train_data.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>age</th>\n",
       "      <th>sex_male</th>\n",
       "      <th>smoker_yes</th>\n",
       "      <th>bmi</th>\n",
       "      <th>children</th>\n",
       "      <th>region_northwest</th>\n",
       "      <th>region_southeast</th>\n",
       "      <th>region_southwest</th>\n",
       "      <th>charges</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>21.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>25.745000</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3279.868550</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>37.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>25.744165</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>21454.494239</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    age  sex_male  smoker_yes        bmi  children  region_northwest  \\\n",
       "0  21.0         1           0  25.745000         2                 0   \n",
       "1  37.0         0           1  25.744165         3                 0   \n",
       "\n",
       "   region_southeast  region_southwest       charges  \n",
       "0                 0                 0   3279.868550  \n",
       "1                 1                 0  21454.494239  "
      ]
     },
     "execution_count": 84,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Rearranging columns to see better: \n",
    "train_data = train_data[['age','sex_male','smoker_yes','bmi','children','region_northwest','region_southeast','region_southwest','charges']]\n",
    "train_data.head(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Splitting Independent & Dependent Feature:\n",
    "X = train_data.iloc[:, :-1]\n",
    "y = train_data.iloc[:, -1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>age</th>\n",
       "      <th>sex_male</th>\n",
       "      <th>smoker_yes</th>\n",
       "      <th>bmi</th>\n",
       "      <th>children</th>\n",
       "      <th>region_northwest</th>\n",
       "      <th>region_southeast</th>\n",
       "      <th>region_southwest</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>21.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>25.745000</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>37.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>25.744165</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    age  sex_male  smoker_yes        bmi  children  region_northwest  \\\n",
       "0  21.0         1           0  25.745000         2                 0   \n",
       "1  37.0         0           1  25.744165         3                 0   \n",
       "\n",
       "   region_southeast  region_southwest  \n",
       "0                 0                 0  \n",
       "1                 1                 0  "
      ]
     },
     "execution_count": 86,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# top 2 records of Independent feature:\n",
    "X.head(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0     3279.868550\n",
       "1    21454.494239\n",
       "Name: charges, dtype: float64"
      ]
     },
     "execution_count": 87,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# top 2 records of Dependent Feature:\n",
    "y.head(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Train Test Split (# 80% training and 20% test)\n",
    "from sklearn.model_selection import train_test_split\n",
    "X_train, X_test, y_train, y_test = train_test_split(X,y, test_size=0.2, random_state=0)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Model Building:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Importing Performance Metrics:\n",
    "from sklearn.metrics import mean_squared_error, r2_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.7482602892322038\n",
      "30898859.035960782\n"
     ]
    }
   ],
   "source": [
    "# Linear Regression:\n",
    "from sklearn.linear_model import LinearRegression\n",
    "LinearRegression = LinearRegression()\n",
    "LinearRegression = LinearRegression.fit(X_train, y_train)\n",
    "\n",
    "\n",
    "y_pred = LinearRegression.predict(X_test)\n",
    "\n",
    "\n",
    "print(r2_score(y_test, y_pred))\n",
    "print(mean_squared_error(y_test, y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.9053832333651239\n",
      "11613384.816295853\n"
     ]
    }
   ],
   "source": [
    "# Random Forest Regressor:\n",
    "from sklearn.ensemble import RandomForestRegressor\n",
    "RandomForestRegressor = RandomForestRegressor()\n",
    "RandomForestRegressor = RandomForestRegressor.fit(X_train, y_train)\n",
    "\n",
    "y_pred = RandomForestRegressor.predict(X_test)\n",
    "\n",
    "\n",
    "print(r2_score(y_test, y_pred))\n",
    "print(mean_squared_error(y_test, y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.8327030324826395\n",
      "20534247.062954478\n"
     ]
    }
   ],
   "source": [
    "# Decision Tree Regressor\n",
    "from sklearn.tree import DecisionTreeRegressor\n",
    "clf = DecisionTreeRegressor()\n",
    "clf.fit(X_train, y_train)\n",
    "\n",
    "y_pred = clf.predict(X_test)\n",
    "\n",
    "print(r2_score(y_test, y_pred))\n",
    "print(mean_squared_error(y_test, y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "-0.09107366776897252\n",
      "133919798.96782704\n"
     ]
    }
   ],
   "source": [
    "from sklearn.svm import SVR\n",
    "clf = SVR()\n",
    "clf.fit(X_train, y_train)\n",
    "\n",
    "y_pred = clf.predict(X_test)\n",
    "\n",
    "print(r2_score(y_test, y_pred))\n",
    "print(mean_squared_error(y_test, y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.529165520422765\n",
      "57790835.499712594\n"
     ]
    }
   ],
   "source": [
    "# KNN Regressor\n",
    "from sklearn.neighbors import KNeighborsRegressor\n",
    "clf = KNeighborsRegressor()\n",
    "\n",
    "clf.fit(X_train, y_train)\n",
    "\n",
    "y_pred = clf.predict(X_test)\n",
    "\n",
    "print(r2_score(y_test, y_pred))\n",
    "print(mean_squared_error(y_test, y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Creating a pickle file for the classifier\n",
    "import pickle\n",
    "filename = 'MedicalInsuranceCost.pkl'\n",
    "pickle.dump(RandomForestRegressor, open(filename, 'wb'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}