linear regression.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "2cfffde8",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "e2d9b4bf",
   "metadata": {},
   "outputs": [],
   "source": [
    "df=pd.read_csv(\"https://raw.githubusercontent.com/stedy/Machine-Learning-with-R-datasets/master/insurance.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "b87d588c",
   "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>children</th>\n",
       "      <th>smoker</th>\n",
       "      <th>region</th>\n",
       "      <th>charges</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>19</td>\n",
       "      <td>female</td>\n",
       "      <td>27.900</td>\n",
       "      <td>0</td>\n",
       "      <td>yes</td>\n",
       "      <td>southwest</td>\n",
       "      <td>16884.92400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>18</td>\n",
       "      <td>male</td>\n",
       "      <td>33.770</td>\n",
       "      <td>1</td>\n",
       "      <td>no</td>\n",
       "      <td>southeast</td>\n",
       "      <td>1725.55230</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>28</td>\n",
       "      <td>male</td>\n",
       "      <td>33.000</td>\n",
       "      <td>3</td>\n",
       "      <td>no</td>\n",
       "      <td>southeast</td>\n",
       "      <td>4449.46200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>33</td>\n",
       "      <td>male</td>\n",
       "      <td>22.705</td>\n",
       "      <td>0</td>\n",
       "      <td>no</td>\n",
       "      <td>northwest</td>\n",
       "      <td>21984.47061</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>32</td>\n",
       "      <td>male</td>\n",
       "      <td>28.880</td>\n",
       "      <td>0</td>\n",
       "      <td>no</td>\n",
       "      <td>northwest</td>\n",
       "      <td>3866.85520</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   age     sex     bmi  children smoker     region      charges\n",
       "0   19  female  27.900         0    yes  southwest  16884.92400\n",
       "1   18    male  33.770         1     no  southeast   1725.55230\n",
       "2   28    male  33.000         3     no  southeast   4449.46200\n",
       "3   33    male  22.705         0     no  northwest  21984.47061\n",
       "4   32    male  28.880         0     no  northwest   3866.85520"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "c1a7ffe0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1338, 7)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "e034c753",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "age         0\n",
       "sex         0\n",
       "bmi         0\n",
       "children    0\n",
       "smoker      0\n",
       "region      0\n",
       "charges     0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "9b18d0cb",
   "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>children</th>\n",
       "      <th>smoker</th>\n",
       "      <th>region</th>\n",
       "      <th>charges</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Empty DataFrame\n",
       "Columns: [age, sex, bmi, children, smoker, region, charges]\n",
       "Index: []"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[df[\"charges\"]==0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "108c4f7f",
   "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>children</th>\n",
       "      <th>smoker</th>\n",
       "      <th>region</th>\n",
       "      <th>charges</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Empty DataFrame\n",
       "Columns: [age, sex, bmi, children, smoker, region, charges]\n",
       "Index: []"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[df[\"age\"]==0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "f0299916",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    " df.duplicated().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "4476c306",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0\n",
      "0\n",
      "0\n"
     ]
    }
   ],
   "source": [
    "for i in [\"age\",\"bmi\",\"charges\"]:\n",
    "    print(df[i][df[i]==0].count())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "39d48398",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['female' 'male']\n",
      "[0 1 3 2 5 4]\n",
      "['yes' 'no']\n",
      "['southwest' 'southeast' 'northwest' 'northeast']\n"
     ]
    }
   ],
   "source": [
    "for i in [\"sex\",\"children\",\"smoker\",\"region\"]:\n",
    "    print(df[i].unique())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "040df291",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.drop_duplicates(inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "876c10c3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.duplicated().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "3d7c2199",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['southwest', 'southeast', 'northwest', 'northeast'], dtype=object)"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.region.unique()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fe88260a",
   "metadata": {},
   "source": [
    "# one hot encoding "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "27c69aa3",
   "metadata": {},
   "outputs": [],
   "source": [
    "# 1.first way\n",
    "# df=pd.get_dummies(df,columns=[\"sex\",\"smoker\",\"region\"],drop_first=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "15684416",
   "metadata": {},
   "outputs": [],
   "source": [
    "# df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "44ea4cbe",
   "metadata": {},
   "source": [
    "# 2.second way"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "c7529a97",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[      sex_male\n",
       " 0            0\n",
       " 1            1\n",
       " 2            1\n",
       " 3            1\n",
       " 4            1\n",
       " ...        ...\n",
       " 1333         1\n",
       " 1334         0\n",
       " 1335         0\n",
       " 1336         0\n",
       " 1337         0\n",
       " \n",
       " [1337 rows x 1 columns],\n",
       "       smoker_yes\n",
       " 0              1\n",
       " 1              0\n",
       " 2              0\n",
       " 3              0\n",
       " 4              0\n",
       " ...          ...\n",
       " 1333           0\n",
       " 1334           0\n",
       " 1335           0\n",
       " 1336           0\n",
       " 1337           1\n",
       " \n",
       " [1337 rows x 1 columns],\n",
       "       region_northwest  region_southeast  region_southwest\n",
       " 0                    0                 0                 1\n",
       " 1                    0                 1                 0\n",
       " 2                    0                 1                 0\n",
       " 3                    1                 0                 0\n",
       " 4                    1                 0                 0\n",
       " ...                ...               ...               ...\n",
       " 1333                 1                 0                 0\n",
       " 1334                 0                 0                 0\n",
       " 1335                 0                 1                 0\n",
       " 1336                 0                 0                 1\n",
       " 1337                 1                 0                 0\n",
       " \n",
       " [1337 rows x 3 columns]]"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "one_hot=[]\n",
    "for i in [\"sex\",\"smoker\",\"region\"]:\n",
    "    i=pd.get_dummies(df[i],prefix=i,drop_first=True)\n",
    "    one_hot.append(i)\n",
    "one_hot\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "7aadfe3b",
   "metadata": {},
   "outputs": [],
   "source": [
    "for i in one_hot:\n",
    "    df=pd.concat((df,i),axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "27fec693",
   "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>children</th>\n",
       "      <th>smoker</th>\n",
       "      <th>region</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>19</td>\n",
       "      <td>female</td>\n",
       "      <td>27.900</td>\n",
       "      <td>0</td>\n",
       "      <td>yes</td>\n",
       "      <td>southwest</td>\n",
       "      <td>16884.92400</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>18</td>\n",
       "      <td>male</td>\n",
       "      <td>33.770</td>\n",
       "      <td>1</td>\n",
       "      <td>no</td>\n",
       "      <td>southeast</td>\n",
       "      <td>1725.55230</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>28</td>\n",
       "      <td>male</td>\n",
       "      <td>33.000</td>\n",
       "      <td>3</td>\n",
       "      <td>no</td>\n",
       "      <td>southeast</td>\n",
       "      <td>4449.46200</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>33</td>\n",
       "      <td>male</td>\n",
       "      <td>22.705</td>\n",
       "      <td>0</td>\n",
       "      <td>no</td>\n",
       "      <td>northwest</td>\n",
       "      <td>21984.47061</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>32</td>\n",
       "      <td>male</td>\n",
       "      <td>28.880</td>\n",
       "      <td>0</td>\n",
       "      <td>no</td>\n",
       "      <td>northwest</td>\n",
       "      <td>3866.85520</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   age     sex     bmi  children smoker     region      charges  sex_male  \\\n",
       "0   19  female  27.900         0    yes  southwest  16884.92400         0   \n",
       "1   18    male  33.770         1     no  southeast   1725.55230         1   \n",
       "2   28    male  33.000         3     no  southeast   4449.46200         1   \n",
       "3   33    male  22.705         0     no  northwest  21984.47061         1   \n",
       "4   32    male  28.880         0     no  northwest   3866.85520         1   \n",
       "\n",
       "   smoker_yes  region_northwest  region_southeast  region_southwest  \n",
       "0           1                 0                 0                 1  \n",
       "1           0                 0                 1                 0  \n",
       "2           0                 0                 1                 0  \n",
       "3           0                 1                 0                 0  \n",
       "4           0                 1                 0                 0  "
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "99cacff6",
   "metadata": {},
   "outputs": [],
   "source": [
    "for i in [\"sex\",\"smoker\",\"region\"]:\n",
    "    df.drop(i,axis=1,inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "7cca235f",
   "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>19</td>\n",
       "      <td>27.900</td>\n",
       "      <td>0</td>\n",
       "      <td>16884.92400</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>18</td>\n",
       "      <td>33.770</td>\n",
       "      <td>1</td>\n",
       "      <td>1725.55230</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>28</td>\n",
       "      <td>33.000</td>\n",
       "      <td>3</td>\n",
       "      <td>4449.46200</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>33</td>\n",
       "      <td>22.705</td>\n",
       "      <td>0</td>\n",
       "      <td>21984.47061</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>32</td>\n",
       "      <td>28.880</td>\n",
       "      <td>0</td>\n",
       "      <td>3866.85520</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   age     bmi  children      charges  sex_male  smoker_yes  region_northwest  \\\n",
       "0   19  27.900         0  16884.92400         0           1                 0   \n",
       "1   18  33.770         1   1725.55230         1           0                 0   \n",
       "2   28  33.000         3   4449.46200         1           0                 0   \n",
       "3   33  22.705         0  21984.47061         1           0                 1   \n",
       "4   32  28.880         0   3866.85520         1           0                 1   \n",
       "\n",
       "   region_southeast  region_southwest  \n",
       "0                 0                 1  \n",
       "1                 1                 0  \n",
       "2                 1                 0  \n",
       "3                 0                 0  \n",
       "4                 0                 0  "
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "c13c847a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "age                   int64\n",
       "bmi                 float64\n",
       "children              int64\n",
       "charges             float64\n",
       "sex_male              uint8\n",
       "smoker_yes            uint8\n",
       "region_northwest      uint8\n",
       "region_southeast      uint8\n",
       "region_southwest      uint8\n",
       "dtype: object"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "1a5f8bce",
   "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>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>age</th>\n",
       "      <td>1337.0</td>\n",
       "      <td>39.222139</td>\n",
       "      <td>14.044333</td>\n",
       "      <td>18.0000</td>\n",
       "      <td>27.000</td>\n",
       "      <td>39.0000</td>\n",
       "      <td>51.00000</td>\n",
       "      <td>64.00000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>bmi</th>\n",
       "      <td>1337.0</td>\n",
       "      <td>30.663452</td>\n",
       "      <td>6.100468</td>\n",
       "      <td>15.9600</td>\n",
       "      <td>26.290</td>\n",
       "      <td>30.4000</td>\n",
       "      <td>34.70000</td>\n",
       "      <td>53.13000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>children</th>\n",
       "      <td>1337.0</td>\n",
       "      <td>1.095737</td>\n",
       "      <td>1.205571</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1.0000</td>\n",
       "      <td>2.00000</td>\n",
       "      <td>5.00000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>charges</th>\n",
       "      <td>1337.0</td>\n",
       "      <td>13279.121487</td>\n",
       "      <td>12110.359656</td>\n",
       "      <td>1121.8739</td>\n",
       "      <td>4746.344</td>\n",
       "      <td>9386.1613</td>\n",
       "      <td>16657.71745</td>\n",
       "      <td>63770.42801</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>sex_male</th>\n",
       "      <td>1337.0</td>\n",
       "      <td>0.504862</td>\n",
       "      <td>0.500163</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1.0000</td>\n",
       "      <td>1.00000</td>\n",
       "      <td>1.00000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>smoker_yes</th>\n",
       "      <td>1337.0</td>\n",
       "      <td>0.204936</td>\n",
       "      <td>0.403806</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>1.00000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>region_northwest</th>\n",
       "      <td>1337.0</td>\n",
       "      <td>0.242334</td>\n",
       "      <td>0.428655</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>1.00000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>region_southeast</th>\n",
       "      <td>1337.0</td>\n",
       "      <td>0.272251</td>\n",
       "      <td>0.445285</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>1.00000</td>\n",
       "      <td>1.00000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>region_southwest</th>\n",
       "      <td>1337.0</td>\n",
       "      <td>0.243082</td>\n",
       "      <td>0.429104</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>1.00000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                   count          mean           std        min       25%  \\\n",
       "age               1337.0     39.222139     14.044333    18.0000    27.000   \n",
       "bmi               1337.0     30.663452      6.100468    15.9600    26.290   \n",
       "children          1337.0      1.095737      1.205571     0.0000     0.000   \n",
       "charges           1337.0  13279.121487  12110.359656  1121.8739  4746.344   \n",
       "sex_male          1337.0      0.504862      0.500163     0.0000     0.000   \n",
       "smoker_yes        1337.0      0.204936      0.403806     0.0000     0.000   \n",
       "region_northwest  1337.0      0.242334      0.428655     0.0000     0.000   \n",
       "region_southeast  1337.0      0.272251      0.445285     0.0000     0.000   \n",
       "region_southwest  1337.0      0.243082      0.429104     0.0000     0.000   \n",
       "\n",
       "                        50%          75%          max  \n",
       "age                 39.0000     51.00000     64.00000  \n",
       "bmi                 30.4000     34.70000     53.13000  \n",
       "children             1.0000      2.00000      5.00000  \n",
       "charges           9386.1613  16657.71745  63770.42801  \n",
       "sex_male             1.0000      1.00000      1.00000  \n",
       "smoker_yes           0.0000      0.00000      1.00000  \n",
       "region_northwest     0.0000      0.00000      1.00000  \n",
       "region_southeast     0.0000      1.00000      1.00000  \n",
       "region_southwest     0.0000      0.00000      1.00000  "
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe().T"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "98ee4244",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "df[\"charges\"].plot(kind=\"box\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "4ea8d01d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        if (window._pyforest_update_imports_cell) { window._pyforest_update_imports_cell('import matplotlib.pyplot as plt'); }\n",
       "    "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        if (window._pyforest_update_imports_cell) { window._pyforest_update_imports_cell('import matplotlib.pyplot as plt'); }\n",
       "    "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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": [
    "plt.boxplot(df.charges)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "de355772",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        if (window._pyforest_update_imports_cell) { window._pyforest_update_imports_cell('import seaborn as sns\\nimport matplotlib.pyplot as plt'); }\n",
       "    "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.boxplot(data=df[\"charges\"],orient=\"v\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "793325f0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        if (window._pyforest_update_imports_cell) { window._pyforest_update_imports_cell('import seaborn as sns\\nimport matplotlib.pyplot as plt'); }\n",
       "    "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        if (window._pyforest_update_imports_cell) { window._pyforest_update_imports_cell('import seaborn as sns\\nimport matplotlib.pyplot as plt'); }\n",
       "    "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x720 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig,ax=plt.subplots(figsize=(10,10))\n",
    "sns.heatmap(df.corr(),annot=True,fmt=\".2g\",cmap=\"viridis\",cbar=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "id": "9d4e4b89",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        if (window._pyforest_update_imports_cell) { window._pyforest_update_imports_cell('import seaborn as sns\\nimport matplotlib.pyplot as plt'); }\n",
       "    "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        if (window._pyforest_update_imports_cell) { window._pyforest_update_imports_cell('import seaborn as sns\\nimport matplotlib.pyplot as plt'); }\n",
       "    "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        if (window._pyforest_update_imports_cell) { window._pyforest_update_imports_cell('import seaborn as sns\\nimport matplotlib.pyplot as plt'); }\n",
       "    "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='charges', ylabel='Count'>"
      ]
     },
     "execution_count": 60,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x720 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.style.use(\"seaborn\")\n",
    "fig,ax=plt.subplots(figsize=(10,10))\n",
    "sns.histplot(x=df.charges,color=\"purple\",kde=True)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "8edaf312",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        if (window._pyforest_update_imports_cell) { window._pyforest_update_imports_cell('import seaborn as sns\\nimport matplotlib.pyplot as plt'); }\n",
       "    "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        if (window._pyforest_update_imports_cell) { window._pyforest_update_imports_cell('import seaborn as sns\\nimport matplotlib.pyplot as plt'); }\n",
       "    "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "        if (window._pyforest_update_imports_cell) { window._pyforest_update_imports_cell('import seaborn as sns\\nimport matplotlib.pyplot as plt'); }\n",
       "    "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='bmi', ylabel='Count'>"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x720 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.style.use(\"seaborn\")\n",
    "fig,ax=plt.subplots(figsize=(10,10))\n",
    "sns.histplot(x=df.bmi,color=\"purple\",kde=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "bbf9bc18",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.linear_model import LinearRegression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "657f45ba",
   "metadata": {},
   "outputs": [],
   "source": [
    "x=df.drop(\"charges\",axis=1)\n",
    "y=df.charges"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "65a68af6",
   "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>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>19</td>\n",
       "      <td>27.900</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>18</td>\n",
       "      <td>33.770</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>28</td>\n",
       "      <td>33.000</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>33</td>\n",
       "      <td>22.705</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>32</td>\n",
       "      <td>28.880</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   age     bmi  children  sex_male  smoker_yes  region_northwest  \\\n",
       "0   19  27.900         0         0           1                 0   \n",
       "1   18  33.770         1         1           0                 0   \n",
       "2   28  33.000         3         1           0                 0   \n",
       "3   33  22.705         0         1           0                 1   \n",
       "4   32  28.880         0         1           0                 1   \n",
       "\n",
       "   region_southeast  region_southwest  \n",
       "0                 0                 1  \n",
       "1                 1                 0  \n",
       "2                 1                 0  \n",
       "3                 0                 0  \n",
       "4                 0                 0  "
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "f64dee24",
   "metadata": {},
   "outputs": [],
   "source": [
    "x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=.20,random_state=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "81f6401d",
   "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>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>435</th>\n",
       "      <td>60</td>\n",
       "      <td>33.110</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>202</th>\n",
       "      <td>60</td>\n",
       "      <td>24.035</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1183</th>\n",
       "      <td>48</td>\n",
       "      <td>27.360</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1291</th>\n",
       "      <td>19</td>\n",
       "      <td>34.900</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>773</th>\n",
       "      <td>19</td>\n",
       "      <td>28.880</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      age     bmi  children  sex_male  smoker_yes  region_northwest  \\\n",
       "435    60  33.110         3         1           0                 0   \n",
       "202    60  24.035         0         0           0                 1   \n",
       "1183   48  27.360         1         0           0                 0   \n",
       "1291   19  34.900         0         1           1                 0   \n",
       "773    19  28.880         0         0           1                 1   \n",
       "\n",
       "      region_southeast  region_southwest  \n",
       "435                  1                 0  \n",
       "202                  0                 0  \n",
       "1183                 0                 0  \n",
       "1291                 0                 1  \n",
       "773                  0                 0  "
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "255bff4c",
   "metadata": {},
   "outputs": [],
   "source": [
    "lr=LinearRegression()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "8848113e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "LinearRegression()"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lr.fit(x_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "469d7f4f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.7486381659434201"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lr.score(x_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "0a795e7a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.7497814388540697"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lr.score(x_test,y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "8482e32b",
   "metadata": {},
   "outputs": [],
   "source": [
    "pred=lr.predict(x_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "72c24d38",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        if (window._pyforest_update_imports_cell) { window._pyforest_update_imports_cell('import seaborn as sns\\nimport matplotlib.pyplot as plt'); }\n",
       "    "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='charges', ylabel='Count'>"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x396 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.histplot(y_test-pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "28f2022f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "\n",
       "        if (window._pyforest_update_imports_cell) { window._pyforest_update_imports_cell('import seaborn as sns\\nimport matplotlib.pyplot as plt'); }\n",
       "    "
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0x17dea181ee0>"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAe8AAAFJCAYAAACyzKU+AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjQuMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/MnkTPAAAACXBIWXMAAAsTAAALEwEAmpwYAAA9dUlEQVR4nO3da3RT55kv8L8kS/JFku+eBIzTYCPShNjYuECKgUCduO0pLVNoiN2hzWSSJrSkhRkYJ2mAUEhSpiUr08ziTJuTnK7DlNtKerKypmdWJlwC4dpgbAhuwEBS7uArWPJlS5b2+aBI+LL3lmR02Vv6/74kaG/LW69Aj953P8/z6kRRFEFERESaoY/3BRAREVF4GLyJiIg0hsGbiIhIYxi8iYiINIbBm4iISGMYvImIiDQmJd4XEKq2NkfYP5OdnY6urt4oXI22cBx8OA4+HAcfjoMPx8FHreOQn2+VfDyhZ94pKYZ4X4IqcBx8OA4+HAcfjoMPx8FHa+OQ0MGbiIgoETF4ExERaQyDNxERkcYweBMREWkMgzcREZHGMHgTERFpDIM3ERGRxjB4ExElEcHtQWtXLwS3J96XQrdBMx3WiIhImuD24KZTQKbFDLNRutmIx+vF9t1n0djShs5uATk2M8rt+Vj6SHmMr5YigcGbiEij5ALyorklMOiHLqxu330WO49eCvy5o1vAzqOXkJ5mwvwZX4rxldPt4rI5EZFG+QNyR7cAEbcC8vbdZ4ecJ7g9aGxpk3yOwyevcgldg0IK3h0dHZg9ezbOnTuH8+fPo7a2FnV1dVizZg28Xi8AYMeOHfjud7+LRx55BHv27AEA9Pf345lnnkFdXR2efPJJdHZ2AgCamprwve99D48++ij+7d/+LUovjYgocSkF5MaW9iEB+aZTQGe3IHlu+40+3HRKHyP1Chq83W43Vq9ejdTUVADAK6+8gmXLlmHLli0QRRG7du1CW1sbNm/ejG3btuHNN9/Eq6++CpfLha1bt8Jut2PLli2YP38+Nm3aBABYs2YNNm7ciK1bt+L48eNobm6O7qskIkowSgG5y9E/JCBnWszIsZklz83LSkOmRfoYqVfQ4L1hwwY8+uijKCgoAAA0Nzdj6tSpAIBZs2bh4MGDOHHiBMrLy2EymWC1WlFUVIRTp06hoaEBM2fODJx76NAhOJ1OuFwuFBUVQafToaqqCocOHYriSyQiSjxKATnbmjokIJuNBpTb8yXPnT7pTtkkN1IvxYS1P/7xj8jJycHMmTPxu9/9DgAgiiJ0Oh0AICMjAw6HA06nE1brrT1HMzIy4HQ6hzw++FyLxTLk3IsXLwa90Ozs9FFt2Sa3F2qy4Tj4cBx8OA4+Wh+HGWVj8d5Hn0k8PgaFY7KGPLb0kXKkp5lw+ORVtN/oQ15WGqZPuhOPz7sPBgPTnwBt/X1QDN7vvPMOdDodDh06hE8//RT19fWB+9YA0NPTA5vNBovFgp6eniGPW63WIY8rnWuz2YJe6Gg2Sc/Pt6KtzRH2zyUajoMPx8GH4+Cj5XHwl4Y9XDkWvX0uNLa0o8vRj2xrKsrteZj3QJHka5s/40v4xtRxQ8rKDAa9ZschktT690HuC4Vi8P7DH/4Q+P/FixfjxRdfxK9+9SscOXIE06ZNw759+zB9+nSUlpbitddegyAIcLlcOHfuHOx2OyoqKrB3716UlpZi3759mDJlCiwWC4xGIy5cuIBx48Zh//79WLp0aWRfLRFRApIrDVv7D1Ph7HUp1nn7mY0GFGSnx+iKKVrCrvOur6/HqlWr8Oqrr2L8+PGoqamBwWDA4sWLUVdXB1EUsXz5cpjNZtTW1qK+vh61tbUwGo3YuHEjAGDt2rVYsWIFPB4PqqqqUFZWFvEXRkSUaORqtQGgrtoer8uiONCJoijG+yJCMZrlDLUug8Qax8GH4+DDcfDR2jgIbg9eeOMwOiQyzHNtqVj/5LRRJZ5pbRyiRa3jILdsziwFIiINCKc0jBIfgzcRkQaEUxpGiY/Bm4hIA5RqtcvteazVTjLcmISISCMWzS0BgBGlYf7HKXkweBMRqYjS9p4GvR511XYsmF0cdAtQSmwM3kREKhDO9p6s1SYGbyIiFWANN4WDCWtERHEWzvaeRACDNxFR3LGGm8LF4E1EFGes4aZwMXgTEcUZa7gpXExYIyJSAdZwUzgYvImIYkCpfhtgDTeFh8GbKMEECxIUW+HUbwOs4abQMHgTJYhwgwTFBuu3KRr4L5ooQfiDREe3ABG3gsT23WfjfWkJT3B70NrVO6Iem/XbFC2ceRMlgGBBYsHsYi6hR0Gw1Y5Q6re5RE6jwZk3UQJgk4/YGD7DDrbawfptihbOvIkSgD9IdEgEcAaJ2yc1wy4tycPxM8FXO8rt+UPuefuxfptuB2feRAmATT6iS2qGvefYZXQ6XJLnD17tWDS3BNWVhci1pUKvA3JtqaiuLGT9Nt0WzryJEgSbfESHUj6BTgeI4sjHB692sH6booHBmyhBMEhEh1I+gVTgBqRXO1i/TZHE4E2UYBgkIkspn2C4XBtXOyg2GLyJiAYZ3qFOKelssGyLGasfq4Q13RSjK6VkxuBNRATlmu1Fc0tw+sINXGx1yv78zR4BfcIAgzfFBIM3ERGU25gumF2M3n634s+zJI9iiaViRDEg1z6T1EG5Q10bTp/vlE1a82NJHsUSZ95EURSJzUK4S1j0KWWUd3QLeO3tT6CXKQvT64DZk8cwSY1iisGbKIq27TqDXQ2XA3/2L8WKoojvPzRR8We5S1jshJJR7pUpC5tdPhaLH1Z+L4kijZ8ARFEiuD048Mk1yWMHPrkWdAmdu4RFV79rIHArQ6lD3XB6na85i79TWl31hChfKdFInHkTRUnbjT70u6QDdL/Lg7YbfSjMt0ge5y5h0SG4Pejs7sfOoxfR/NcutHX1BVY0Fj44HoBvfDsd/bINWEQRWPHoZIwfm8n3gOKGwZsoWuQ+/UM4zq0kI2vwLYjhS+ODs8r9HerabvThtR1Nkr3LMy0mFBZYGLgprrhsThQl+dnpSDVJ/xNLNRmQrxB8uZVkZA2+BSGnsaU9sIRemG9BxcQCyfNuOF34xe8/xpadLfB4vdG6ZCJFDN5EUWI2GvDV+++UPPbV++9QnLlxl7DIUboFMdjwfc8H7wY2HPMPKN4YvImiqPZrE1BdWYgcqxk6ADlWM6orC1H7teBJTtxKMjKUbkEMNnxFw7/Ry+rHKpEts9Lhn60TxRrveRNF0e3s9MVdwiIj02KG2WSQTR70k1vR6BMGcMPJ/ANSFwZvohi4nZ2+uEtYJMgnB+YOqp+XolQDzvwDihcumxNRQrvpFNDvkk8s+9nCUtRV22Ub3zD/gNSIM2+i28DWpeqXaTEjV2bmnGtLVcz69/PPyhtb2tHl6Ee2lft2U3wxeBONAluXaofSftyhzpyZf0Bqw+BNNApK20fWVdvjdVn0heErIlIz5xllYzDvgaKwnpf5B6QWDN5EYWLrUvVSWhEZPnMuHJOFtjZHvC+ZaFS4vkcUgsH7cYfSupTiI9hmLv6ZM79ckdZx5k2kwD+TO3a6FZ0OF3KsJpSV5CHbapLse51lMbN0KE64IkLJhDNvIgVbd53BzqOXAoG60+HCnsYrcA1Ilx5lpBkZIOLkplOQ7V3e2c0VEYquwatzscCZN5EMwe3BwU+uSh5z9g1IPt7b7w5sbkGxlWkxI9Wkl6zpNpsMXBGhqIhX5Qln3kQSBLcHp893KTb3kNLlEDjDixOX2wORm3xRjAXLs4gWzryJBlHa9zkUbJcZe/737OipVggytzNcXyQassyLIimeeRYM3kSDDK/flmPQAx6JOMF2mbEXynvGL1UUDaFUnkTrCyODN9EXQt33GQBmTR4Dg17PdplxFup7xi9VFA3x3LSGwZvoC8H2fdYBI5JR2C4zvoK9Z9kWM6bcI79jGNHtiETr3dFi8Cb6gtK36ByrGcseKUN+VtqQf5BslxlfSu9ZlsWEFx//CqzppjhcGSWLeG1aw+BN9AWlb9EVE/NRmG+Jw1WREqX3rPKeAgZuirp4bVrD4E00CLd+VJ9g267yPSM1iPUqHIM30SDc+lE9Qm1+wfeMkhGDN5EE3suOv3C3XR38ngWbrRNpXdDg7fF48MILL+Dzzz+HwWDAK6+8AlEU8eyzz0Kn02HChAlYs2YN9Ho9duzYgW3btiElJQVLlizBnDlz0N/fj5UrV6KjowMZGRnYsGEDcnJy0NTUhJdeegkGgwFVVVVYunRpLF4vEamc4Pag7UYfjp1ulTyu1PwiXq0qiWItaPDes2cPAGDbtm04cuRIIHgvW7YM06ZNw+rVq7Fr1y5MnjwZmzdvxjvvvANBEFBXV4cZM2Zg69atsNvteOaZZ/CnP/0JmzZtwgsvvIA1a9bg9ddfx7hx4/CjH/0Izc3NuO+++6L+golInYYHXlHmPKXmF+HO1om0KuhX0erqaqxbtw4AcOXKFeTl5aG5uRlTp04FAMyaNQsHDx7EiRMnUF5eDpPJBKvViqKiIpw6dQoNDQ2YOXNm4NxDhw7B6XTC5XKhqKgIOp0OVVVVOHToUBRfJhGp3fAe0XLkml8Ea1UZq92eiGIhpHWklJQU1NfXY926daipqYEoitDpdACAjIwMOBwOOJ1OWK3WwM9kZGTA6XQOeXzwuRaLZci5Docjkq+LiDQknO52cs0vQmlVSZQoQk5Y27BhA1asWIFHHnkEgnDrH0FPTw9sNhssFgt6enqGPG61Woc8rnSuzWZT/P3Z2elISQk/8SQ/3xr8pCTAcfDhOPiobRyutveg06Hc3S4/Ow3TJ92Jx+fdB4Nh5LzDmpmG/Ow0tHb1jTiWl5WG4i/lItU09CNPbeMQLxwHHy2NQ9Dg/e677+L69et46qmnkJaWBp1Oh0mTJuHIkSOYNm0a9u3bh+nTp6O0tBSvvfYaBEGAy+XCuXPnYLfbUVFRgb1796K0tBT79u3DlClTYLFYYDQaceHCBYwbNw779+8PmrDW1dUb9ovLz7eirY0zeo6DD8fBR43j4HF7kGOV7pSWazPjZwtLkZ+dDrPRgM7OHoln8CktzpVs2FJanAvHzT4MftVqHId44Dj4qHUc5L5QBA3eDz/8MJ577jl8//vfx8DAAJ5//nkUFxdj1apVePXVVzF+/HjU1NTAYDBg8eLFqKurgyiKWL58OcxmM2pra1FfX4/a2loYjUZs3LgRALB27VqsWLECHo8HVVVVKCsri+wrJiLNUO4RnY/CgtBmRGzYQslCJ4qiUm6IaozmG5Fav0nFGsfBh+Pgo9ZxuJVtPjLwhlvmFUqdt1rHIdY4Dj5qHYdRz7yJiGIhkp3S2GSHEh2DNxGpCgMvUXBsOURERKQxDN6UMAS3B61dvWzGQUQJj8vmpHnsZ01EyYbBmzSP/ayJKNlwWkKaxn7WRJSMGLxJ09jPmoiSEYM3aVqmxYwc28gdpgD53acofphUSBQZvOdNmqbcVlN69ymKPSYVEkUWgzdpHvtZqx+TCokii8GbNC+SbTUp8oIlFS6YXcz3iyhMXK8iVbmde6L+tpoMBOrCpEKiyOPMm1SB90QTx/AdvfxJhVJ7dTOpkGh0GLxJFXhPVPuUvoAxqZAoshi8Ke54TzQxKH0BY1IhUWQxeFPchXJPlFtEqlsoX8CYVEgUObyZSHHHRivaF2pSGpMKiSKDwZvizt9oRQrviWoDv4ARxRaDN6nCorklqK4sRK4tFXodkGtLxZyKsZhTPpatNDWAX8CIYov3vEkVBjda6ezux86jF3HibDs+PHaZZWMawaQ0othh8CZVMRsN2NN4GXsarwQeY9mYNrDTHVHscBpDqiK4PTh2ulXy2LHTbVxC1wAmpRFFH4M3qcpNp4BOh0vyWKdDYCtNIiIweJPKpJlToNdJH9PrfMeJiJIdgzepSp8wAK8ofcwr+o4TESU7Bm9SlUyLGbky9cK5NjPrhYmIwOBNUTLarT2V64XzmQRFRASWilGERWJrT9YLExEpY/CmiIrE1p6sFyYiUsZlc4qYYDtLjWYJnfXCREQjMXhTxIS6sxQREd0eBm+KGO4sRUQUGwzeFDHcWYqIKDaYsEYRxUxxIqLoY/CmiGKmOBFR9DF4U1T4M8WJiCjyeM+biIhIYxi8iYiINIbBm4iISGMYvImIiDSGwZuIiEhjGLyJiIg0hsGbiIhIYxi8iYiINIbBm4iISGMYvImIiDSGwZuIiEhjGLyJiIg0hsGbiIhIYxi8iYiINIbBm4iISGMYvImIiDSGwZuIiEhjGLyJiIg0hsGbiIhIYxi8iYiINCZF6aDb7cbzzz+Py5cvw+VyYcmSJSgpKcGzzz4LnU6HCRMmYM2aNdDr9dixYwe2bduGlJQULFmyBHPmzEF/fz9WrlyJjo4OZGRkYMOGDcjJyUFTUxNeeuklGAwGVFVVYenSpbF6vURERJqnOPN+7733kJWVhS1btuCNN97AunXr8Morr2DZsmXYsmULRFHErl270NbWhs2bN2Pbtm1488038eqrr8LlcmHr1q2w2+3YsmUL5s+fj02bNgEA1qxZg40bN2Lr1q04fvw4mpubY/JiSR0EtwetXb0Q3J54XwoRkSYpzry//vWvo6amJvBng8GA5uZmTJ06FQAwa9YsHDhwAHq9HuXl5TCZTDCZTCgqKsKpU6fQ0NCAJ554InDupk2b4HQ64XK5UFRUBACoqqrCoUOHcN9990XrNZJKeLxebN99Fo0tbejsFpBjM6Pcno9Fc0tg0PMODhFRqBSDd0ZGBgDA6XTipz/9KZYtW4YNGzZAp9MFjjscDjidTlit1iE/53Q6hzw++FyLxTLk3IsXLwa90OzsdKSkGMJ+gfn51uAnJQE1jMMb736CnUcvBf7c0S1g59FLSE8z4cn598fkGtQwDmrAcfDhOPhwHHy0NA6KwRsArl69ip/85Ceoq6vDvHnz8Ktf/SpwrKenBzabDRaLBT09PUMet1qtQx5XOtdmswW90K6u3rBeGOB7I9raHGH/XKJRwzgIbg8OHL8seezA8Sv4xtRxMBvD/3IWDjWMgxpwHHw4Dj4cBx+1joPcFwrFtcr29nY8/vjjWLlyJRYuXAgAuPfee3HkyBEAwL59+1BZWYnS0lI0NDRAEAQ4HA6cO3cOdrsdFRUV2Lt3b+DcKVOmwGKxwGg04sKFCxBFEfv370dlZWUkXyuNQrTvQ990CujsFiSPdTn6cdMpfYyIiEZSnHn/+7//O7q7u7Fp06ZAstnPf/5zrF+/Hq+++irGjx+PmpoaGAwGLF68GHV1dRBFEcuXL4fZbEZtbS3q6+tRW1sLo9GIjRs3AgDWrl2LFStWwOPxoKqqCmVlZdF/pSQpVvehMy1m5NjM6JAI4NnWVGRazBH7XUREiU4niqIY74sIxWiWM9S6DBJrSuOwZWfLkPvQftWVhairtkf0OmL5u6Tw74MPx8GH4+DDcfBR6ziMatmcEpvg9qCxpU3yWGNLu+QS+u0sry+aW4LqykLk2lKh1wG5tlRUVxZi0dySsJ+LiCiZBU1Yo8QVyn3ogux0AJFZXjfo9airtmPB7GLcdArItJijnqRGRJSIGLyTWDj3obfvPitZ5gUg7CVvs9EQ+FJARETh47J5EjMbDSi350seK7fnBWbFo1leJyKi6OHMO8n57zc3trSjy9GPbGsqyu15Q+5Dh7O8TkRE0cfgneRCuQ+dZk5BpsWEG07XiJ9nmRcRUewxeBMA6fvQg5PUpAI3MHR5nYiIYoPBm2QNT1IbLNc2cnmdiIhig8GbJCklqWVbzFj9WCWs6aYYXxUREQHMNicZSklqN3sE9AkDMb4iIiLyY/BOQJHYZMRfAy6FSWpERPHFZfMEItcFbekj5WE/l78GXOqeN5PUiIjii8E7gch1QUtPM2H+jC+F/Xyh1IATEVHsMXgnCKUEs8Mnr+IbU8eFPVsOVgMuuD3sUU5EFAcM3glCKcGs/UbfbXVBMxsNyLSYA4E6xaCLyR7gREQkjcE7QShtMpKXlTbqBLPh99GzrSaYjSm42tkbOEdqkxLOyomIoofBO0EoJZhNn3SnZAANJcAOv4/e6XABkO621tjSjvkz78a7H33OWTkRURQxeGtIsGArl2D2+Lz70NnZEzgv1L25le6jS+ly9GPLB2dw8OS1wGP+WbnHK6LmK+M4EyciigAGbw0INdgOTzBLM6egTxiA2+Md8nyh7s2tdB9dSrbVjFPnOyWP7W28jD3HLiOXM3EiotvG4K0BoQZbvxSDDjsbLuHY6VZ0OlzIz0pFWYmvxGvAIyruzb1gdnFgZmxJN8Fs0qPf5ZU8f7h7irJxYNCsezCvGNq1ExFRcJz6qJzS0nVjS7tkF7Wtu85g59FLX9yfBtpu9GPn0UvYuutMSHtz+7370WchBe5cmxnVlYWofciOVFNof6Xkrp2IiIJj8Fa5cIIt4Av2Bz+5Knn+wU+uIc2cItv2NDPDjDRzSuB5Qrnf/dVJd2D9k9NRV22HQa8DoAv6M3LXTqMTiXa4RKQtXDZXOaUSMKke421dvbKz5X6XL+FNLiu9yyngF7//GOX2fMwpH6t4v9uabkTlxHwseLAYbTf6AFEEdDoIrtACCPuj375QcyGIKPEweKtc2D3GdUFmvjodFs0tgcfjReOZdtxwDi37CmSHe7yyXxr0OsDZ68ah5mvYd/wK/PlwZqMOJpMeQghL7eyPfvvCzYUgosTBr+casGhuCaorC5FrS4VeB+TaUlFdWSjZYzw/Kw2pJumgmGoyIMeWiu27z+LEuQ7cdLpkY/2Jc50oLcmTPOYVARFAv8uLwYnsglsMKXCPK7CwP/ptGk0uBBElDs68NSBYj/HBzEYDZtx/B3Y1XB5xbMb9d+Ddjz4bOosXpX9nl6Mf1VMKYdDr0NjSjs7ufrlTJa5Bj4w0o+yye2//AAY8Igz86jhqoeRCjLYdLhGpHz8+NcRsNKAgOz3ocvPfzirGjEl3IMdmhk4HFGSnobqyEH87a3zITVeyranIsaWirtqO9U9OQ/kE6Vm4FJfbix88PFH2OJPVbh/3WydKbpx5JxCpPuQP3HcHfvZoOXqcAlq7ekNuulJu9wXr1q5epJlT8Ndr3SFfR7bVjLvH2JAbRqIdhYf7rRMlNwZvFQjW9jTUTT6k+pAfPHkNee+fxvwZX1LMXNfrfAnjObZUlE3IhSiKeOGNw+jsFpBpMY1IbFNSMTEf1nQTg0uUcb91ouTF4B1HwUp9wikFCnU/b7mAOvXLf4NvTi9CfnY6tu8+gw8brwSOhRq4U00GfPX+OwLBg8ElusLJhSCixMLgHUfBSn3CKQUKdT/v4QHVZDQAEHH4L9dx5tINpJpTcLmtR/J5pMypGIs55WMBUUT+sPvxDC6x4c+FIKLkwYS1OAlW6uPodYVVCqSUwDR4P29/QF3/5DRMv+8O9Ls8gaYuHd1C0MCdZTENKVerq56AwnwLCgusihnwoSTaERFRaDjzjpNgpT6XWp1hlQIpLYlXfvlvJGe+py90hX3dS787CZY0E2fRRERxxOAdJ8HanhYWWMJqiwpI3WM2Iz3ViI//cg3/dfCvQ+6Zh7vdJ+C7pz02X36GTUREscFl8zjxz5SllNvzAtnacselAujgJfGXfzQdpcW5uNjqRNsNX4MV/z3z7bvPItNihjEltE1E/L56/x2B38vNMIiI4ocz7zhaNLcEbo8Xhz+5BmHAd9851WSAKIrweL0jZtJZFjPuuSsb82feLfuc/rKyNHMKTpzrkDynsaUd8776JYghtkwzG/WYWTbG1xNdIQN+wCMyMY2IKAYYvOPEHwSPNN8K3IBv569dDZeh0+lQV21HXbUd82eOx9YPWnDqQhcOnbyG0xe6RpSMDQ+qWRYzumS6mPnvqbs9ytE7K8OIe+/ORd1DE5BuNgIAtuxskcyAP33hBnr73ara3SrU+ngiIq1h8I6T4WVgwzW2tGPB7GKYjQa8+9FnOHDyWuCYVMnY8OeTC9zArXvqch3QACAv04xVP/wKrOmmwBJ5mjlFNgP+YqtT8fpiSW51YOkj5TG/FrXiFxsibWPwjgOlMjE/f0Z5psWsWDK2YHbxF/8fWs9yAJhYlAWTQnY6ALTfFLD29x8jI9WInj4Xuhwuxdm80vXFOjjI1cenp5kwf8aXYnotauPxevHGu5/gwPHLqlolIaLw8F9rHISS6e3PKA9l96hgzzf8M/ngyWt44Y3D8Hq9KMzPgF4mb62zW8DFVic6HS6IUJ7NK11fLAXrNJfsCXbbd5/Fex99ho5uYUQSIxFpB4N3HKSZU5AVZGMOf0Z5KLtHZVrMyLaaZJ/LK7HFdke3gN3HruBSWw+8oe71GaZ4bEASSqe5ZMU9wIkSB4N3DHm8XmzZ2YJf/P5j2VlsqsmA6srCQKa52WhAaYn0dpz+AG82GnDPXTlRu24lqSYDxhVYJI/FYwOSUDvNJaNQVnGISBt4zzuGlJLUcqy+MrDBmd29ghtbPjiDT//qK/nS6wCvCOQOuk/pV/fQBDScboXglphmR1G6OQX136/Aux99pooNSJQ6zU2fdGfEvkxoMeErWGOgZP5iQ6Q1DN4xorRkmWUxYc3f+zK7gVvZ0vtPXEW/69ZSpn95u7Q4d0QWd7rZiMqJBUOy0mPhhlOAs9elqg1I5HYze3zefejsvNW7fTQBOJyd3tSGe4ATJQ4G7xhRWrLs7nGhTxgIBO9gZWQnznUG7k8ODj4LHizGx6da4RqI7OzbbNRBcEvfGB88Y1PL7lZyu5kZDPI18ZPteairnhA0AIez05saLZpbgvQ0Ew4cvxL3VRIiGj0G7xjweL14/88XoNNBsqvZ4AAYahnZ5vdP4/SFrsDsLz3VCGevIBu4zUZ90CX1bIsJlnRToDQs22pGxcR8zJ85Hls+aMFBiVm9mmdscl8mpGri9xy7jLOXbmL1Y5WyATxYwlc8yuLCZdDr8eT8+/GNqeNUsUpCRKPD4B0D23efxZ7GK7LH/QHQ4/Vi8/unZRun+JmMhiGBtKNbkP2ZXFsqZpSNwYNld2Dd7xsUy70m2/Ox+OGJI5aTBbcH/+OBu2A26nHiXKemZ2xKAfhiqxNbPmjB4pp7JI+HkvClhpWHUKhllYSIRofBO8qUgoUOwMzJdwYC4PbdZyVntyOFVttlTtFj9WOVGH9XLppbruNGkGziE2c7IMzxBD7Y/dnxg+/vlpbkoXpKIXJsqZqcsQWriW88045H5nokXxsTvohILdSdYZMAlIKFCOCTs53YvvssegU3jp1uVXyuVJMBMybdgX5XaPe0hQFvoPwnzZyCTIt8LTgwslzIv7w8uKHHnmOXsfPoRdx0CpqsC860mBVr7G86XbIlU8F2gtPilxki0ibOvKNMabYG+O637jx6Cb39A+h0uGSfp8Keh8f/x70w6HU4daEr6NK6n0cU8dv/ewI7/3w+aNAP9d773qYr+LDxiiZn4majAZPtedhz7LLk8Ryb8gxaLpNda7cPiEjbGLxvU7ByI6XynME+/WtnoI5bikEPuNwDcLm9uOeuLBz45HpI17en8TL2NV0N6dzJE3IDr0FpxcB/jf6Z+J5jl4fUnqutZMr/Hlkz0wAAddUTcPbSzSGbqfgFm0HLZbIH+91MDCOiSGLwHqVw6n3nz7x7RM32cDecLsU72R+fasfHp9oB+O6Vh6rxdOgblvT2uSG4PUPasoY6w1djydTw9yg/Ow2lxblYNLcEqx+rxJYPWtB4ph03nS7k2MKbQQdL+NJyPTgRqR+D9yiFU+/r7HVDUAjcAJBtNQM6BN2wBAg1Xc3H0TcQ8rmH/tKK0xdvoGJiARbNLcHkCXnY1SC9vCxHTSVTw9+j1q6+Ie/R4pp78Mjc6MyMtV4PTkTqxinAKIS7wYNSv22/spJcfLkoO2LXOFqdDhd2Hr2ELR+0oK8/9MDvp5Ye2aG+R/4ZdCQDdyJuAOLf012L106UiDjzHoVw632V7nubjXoUZKfjxLkOdHQLITVTiYUPG6+ENcP3U0vJVDxrshOpHpzL/0TqxOA9CqOp9x2epZxl8W1EYjLq8eGgBi5qCNxAeEvzg6mlZCqSNdnhJp0lUj04l/+J1Cmk4H38+HH8+te/xubNm3H+/Hk8++yz0Ol0mDBhAtasWQO9Xo8dO3Zg27ZtSElJwZIlSzBnzhz09/dj5cqV6OjoQEZGBjZs2ICcnBw0NTXhpZdegsFgQFVVFZYuXRrt1xlRoWzwMPwD36DXY8HsYswqGwOIIvK/mHm98MbhiF9fqkkfci34aNnSjZhsz0PzZ12qLJmKxCYco511JsoGIInQDpYoUQUN3m+88Qbee+89pKX5ymxeeeUVLFu2DNOmTcPq1auxa9cuTJ48GZs3b8Y777wDQRBQV1eHGTNmYOvWrbDb7XjmmWfwpz/9CZs2bcILL7yANWvW4PXXX8e4cePwox/9CM3Nzbjvvvui/mIjSa7ed+GD40d0JSubkAcdgKYz7UOCwJzysSElqAXjzz73Z0x7RRG7w0w0C5ezz41vTrsLtV+zq7YUavh7lJd1K9s8FLcz60yEevBEWv4nSjRBg3dRURFef/11/PM//zMAoLm5GVOnTgUAzJo1CwcOHIBer0d5eTlMJhNMJhOKiopw6tQpNDQ04Iknngicu2nTJjidTrhcLhQVFQEAqqqqcOjQIc0Fb7l63y07W0Z84A8PpP4g4B7whlWOJcdk1GPKxILAXuAerxd6nQ4ff9qKmz3yjV9uh3/5V809soe/R8VfyoXjZl9IP3u7s85w68HVKJGW/4kSTdDgXVNTg0uXbgUjURSh0/nmehkZGXA4HHA6nbBarYFzMjIy4HQ6hzw++FyLxTLk3IsXLwa90OzsdKSkhP/hl59vDX7SbSr84r/9rgGcONcR8s99dOIKigqsIQfvvEwz7rk7B39uvgbXoC06BbcXB09eQ152Op6cfz88Hi/S00wwGqOXUDSjbAwKx2RF7fkjzf8epYb49+Fqew86HfKzToPJiPy8jLB+t5qE+u9iRtlYvPfRZxKPa+v9lxOLzwct4Dj4aGkcwk5Y0w+619fT0wObzQaLxYKenp4hj1ut1iGPK51rs9mC/t6urt5wLxX5+Va0tTnC/rnRau3qRVtXaDM7APB6gb9ec2BcgQW9/QOB5dX01BTJ7l+lJXkQRcAts7f2hw2XMHPS3+D9jy8G7eg2nNx9cr0OGJOXgd7+AdxwCoHl33kPFMV0bCMhnL8PHrcHOVb5WafH5dbc6/cLZxzmPVCE3j7XiOV/Lb7/w8X680GtOA4+ah0HuS8UYQfve++9F0eOHMG0adOwb98+TJ8+HaWlpXjttdcgCAJcLhfOnTsHu92OiooK7N27F6Wlpdi3bx+mTJkCi8UCo9GICxcuYNy4cdi/f7/mEtbkhNuVzK+nz401f/8V9AkDyLSYodOJeOn/HMPlNie8oi+Ajs23QBRF7Dkmv7Vod68L//w/D0GpgifHZobL7UFP3wBE3Hru4kIbPpR47tmTx2BxzT1J1+YzUZLOblciLP8TJaKw11Xr6+vx+uuvY9GiRXC73aipqUF+fj4WL16Muro6/PCHP8Ty5cthNptRW1uLM2fOoLa2Ftu3bw8E6bVr12LFihVYuHAh7r33XpSVlUX8hcWD0q5TSjodAnbsPovcTN/mHm9/+BkutjoDPcS9om+v6UMhbBcqAvDIJJrrAEwozILzi8A9+Ll1AMYVWKD/IvtNr/P9edHXSgKvLdLNTNRu0dwSVFcWIteWCr3Otzd6dWWhppLOIiUZ338iNdOJojjakt6YGs1yRjyWQW6VF91aZiybkAuvV8S+piuyG48AQHVlIRbMLsYLbxy+7SQ2Kbk2M0RRlNy9LNVkkOy9Xl1ZmDD1vKP9+5Boqw5qXR6MNY6DD8fBR63jELFlc1KmtMyoA7CnUX7Zu7GlHbNK74xI+ZiUCYVZOPIX6d3I5DZNYT1v8E1IiIhijf0NI8zfAxrAiGXGuofs+OqkO2R/tqO7Hx4RyLaaInIt2RYjAATugbdcugGzKby3XC29yomI6BbOvCMklG5cBr0ei2sm4vSFLtll8Y1bG+EcxYYgw40rsKCkMBN7jl2G94t74Eozerllc9bzEhGpD2feEeLvxtXRLUDErUYs23efHXJeikGHNLP8d6ZIBG6DXoefLZyEE2fbJY+nmgzIsZqHJGHNuF96RSCZMquJiLSCM+8ICKcb1/bdZ3GprUfy3EgRRRHXO/tlZ9outwfPL54CU4o+cE/e4/VCp9Npup0nEVGyYPAOIpRMY6Ue0J2Ofnx2+SbGj80EANkgH0nZ1lQUFlgUW1vmZ6UNeT2s5yUi0g4Gbxnh7Cil1JxFB+BX25qQazNjYlH2bWeSm1P0EAaUdwwrt+fBmm4aVZMRZlYTEakfg7eMcHaUMhsNmDwhD7skdvLy13V3dAs4ePKabGJYqGaU3Qn9oOVt0xdBWHB5AruK+Ze6/f89ca4D7Tf6uBRORJQgGLwljGZHqWh3utHrgDvzMjCnfAzyMtOHLG8DkFzq9i+FP7UgDef+2sGlcCKiBMHgLSHcfYwFtwfHz0hndg8nuDyYfm8B/vxpq2y3NR1GfhnwisDlth6s+l8fI1diCV9pqTvVlMKlcCKiBMJSMQn+e9hS/HXP/mYsHTf70HCqNeR2pjm2VPzwG1/G7MljZM+ZNXkMsizyjVrkytD81yS4R78sT0RE6seZtwSz0YDS4lzJVqaTJ+Tinb3n0HDqOrqc7rCf258sVveQHTq9Dgc/uRa4B55qMmDG/XdgbkUh9jXJt1H18y/hpxh0ISfXERGR9jF4D+PPMj9xrgOA716zVwRyrGZUTMzHgNeLDyUS04Lxb7258MHxAHz3o//uoYn43oMlaOvqBXS6QPmW4PaEtLWofwl/Z8Ml2eS6BbOLcbW9Bx63h/e7iYgSBIP3MMOzzP33pcsm5GHB7GIs+81Ho3pe/9abb3/4Geqq7UPqxwsLhu4ao7SX9GDZ1lSkmVNkk+v2n7jqm407BORYORsnIkoUDN7w3Stuu9EHl3tANhCeONsOZ68bglu5xjqYxpY2eDxenDjXobjE7S/namxpR0d3v+Rzldvz0CcMyCbX9bs8gSV5pVI3IiLSlqQO3h6vF9t2ncGBQfed5XR0C+jobr3t39nRLQy5ly4XVAd3POvs7sfOhks4cbZjROvSAY8Y0hK7H7f4JCLSvqQO3tt3n5VsrCLFf+/7dsk9z7HTbZhVNmZE21Kz0YA7czOw+OGJEOaMbNVq0COkJXY/qVI3tQmlJe1onouIKFEkbfBWasQiJRKBW+l5Oh0C1rz5Z8VMcbnWpbeW2NuCzsDVvMVnOC1pR/NcM8rGYt4DRbznT0Sal7SfYkqNWAbLtaVi9uQx0MXgmgZvJfr7/3cq5Hpt/xL7zxaWBj032Baf8awVD3Vb1dE+13sffTaq5yIiUpuknXkrbSbil2UxYfVjlegTBrA3hLrrSDpw8ho+Pd+JiokFIc8887PTkSvzmvQ6YHb5WNm+5pGc9Y7GaFrSxuK5iIjUKGln3v7NRJR097jQJwwg02JGrkzHtdEyGfVBZ/OdDldYM09/iZmU2ZPHYPHDE2UDcSRnvaMRSkvaeDwXEZEaJW3wBoJvJuK/P6wUFEcrw5yCn/9wSkhfCo6eaoWj1xXS8y6aW4LqykLk2lKh1/mW/b89czzqHpIvDws2U43FEnooLWnj8VxERGqUtMvmoWwmMvj+8KK5JfB4vNjbdCUiyWs3e1ywpBpDyhS/4XThxbc+xpR7gi9jDy4xCzSBGZOFtjaH/LWEuRFLNCg1pgl2nz6az0VEpEZJG7yDJaxV2PMwf+b4wJ8Nej0W19wD6HTYcyz89qjD+WeAoWaKdznDa7Iil5kuRen+fyxnqoMb0wyvZ4/Ec80oG4N5DxRF9JqJiOIhaYN3psUMs8kg25zlWEs7zl87MiJpq656AgBgb+PlkGbgZqNesivb4Bmgf6a8+f3TOHjymuLzRSPhSi0zValVg9H+7tGsQBARaUXSBm8AEEXl6CvV/cyg12PxwxMhil582Hg16O94YNIdSDHog84mzUYD/v6b9yA9NQVHT7XihlP6Hne0lrEjOeu9XeGsGsTyuYiI1CJpg/dNpxByn3Kp2a4+xPKphyrH4c7cjKCzScHtQVtXL2aVjUHNV8bh5c3H0CWRFR2tZexIznqJiCi6kjZ4m4yhJ9p3dPfjs8s3MX5sZmDLzmDJboAv0zvHlgpAfgbo8XqxddcZHPzkKvpdvi8TqSYD8rJSJYN3tJexOVMlIlK/pA3eb3/4WVjn/2pbE3KsJlRMLMCc8rEhdWcrLckNOovdvvssdg/rr97v8uBSaw/GFVjQ2z8Q92VsUpdI9n4nIm1KyuAtuD04db4z7J/zN01xe7yK3dmyrWZY0ow4fqYNHx67LNutTHB7cOy0/E5lvf1urH7sK4FGMfygTm7x7oJHROqRlP/ibzoFdDpCa3oi5UjzdZQW58oe7+lz4WKrE50Ol2K3smDX0ekQ0CcMoCA7nYGb4t4Fj4jUIymDd6bFjCyLadQ/3+/y4IFJd2D6vQWSz+MakM5ibzjVNqRTWqbFjByr/HXkWM3sBkYA1NEFj4jUIymDt9loQHmQvubB/HrrMRz+i3xJl5Qup4A1b/0ZW3a2wOP1wmw0oGJigez55fZ8zrgJAPu1E9FQSRm8AaDuITvGFVhG/fOugdH93A3n0M1GFs0twdwpY5FquhWkU00GfG2K/A5glHzYr52IBkvKhDXAV9e8+rFKbNl5Bk0t7ZJlWdE0uHb87x6aiO89WIK2rl5Ap0N+Vhpn3DSEWrrgEZE6JG3wBm51S4MoYk9j8P26U/TAQGh9XYIa3inNbDSgsMAamScfBZYfqZ+auuARUXwldfAGfEHrxLmOkM6NVOAG1LPUGUr5UbIGdrW9bnbBIyK/pA3e/g/mnj53SA1XRkOvA+7My8Dltp4Rx9Sy1OkvP/Ib3M990dySpKwrVns9NbvgEVHSBW//B/Ox063odLigAxCB7bkliQB+PH8S9jReVuVSZ7DyI4/HO+R2gtRGLYlI6QtNIr9uItKOpAvewz+Ybydw6wD8+G8nYduuM5Ld1nKsvt7mal3qVCo/6nT0o1Gmf3s0tiVVi2BfaBL1dRORtsR/DTCGlD6YRyPHlopJ43NRbs+XPD54ady/1KmmD36l8qOsDHPQbUkTEeupiUgLkip4K30wj8bkCbkwGw1YNLcE1ZWFyLWlQq/z7SY2p3wM5pSPVXXnK3/5kZTJ9jzkJmFdMeupiUgLkmrZ3P/BLLehSLh6+wcguD0wGw2BpfHO7n7sbLiEE2fb8WHjFdUlOw2nVH5k0OuSrq6Y9dREpAVJFbyVPpilrPrBFORlpWH1m0dws8c94vih5utouXgjEJzNRgP2NF7GnmO3tvhUe7KTUvlRstYVJ+vrJiLtSKrgDdz6YD766XXckAjIg+3/5CpmlY2RDNx+g4PzgtnFmk12kio/Sta64mR93USkHepbx40y/wfzPz5aHvTcPY1XsGHLsZCet7GlHW03+hIy2UmNyXaxkKyvm4jUL+mCt19+VhoyM4xBz+t3hdZWrcvRD4gik52IiCjqkjZ4m40GlJXkRuz5sq1m5Genh1Q2RkREdDuS7p73YJ9ddUTsuXr63Xhn7zksfHA8ACY7ERFR9CRt8Hb0unBFouf4aPW7vEOyypnsRERE0ZK0y+aXWp3wRqGpeWNLe6D2m8lOREQUDUkbvAsLLNDrpI/JPBwSLWeVExGRNiRt8Lamm5Bulr5rIAIwyEX2IJhVTkRE0Za0wVtwe+AakO877hnlmjqzyomIKNqSNni3dfXCNaAcoFNNBuTYzNDpgByrCeMKLLKbdfjPnz/z7khfKhER0RBJm20OXfBlcZfbg+f/rgImoyGQNX6p1YHVb30se76z1410c/DmL0RERKMVt+Dt9Xrx4osv4vTp0zCZTFi/fj3uuuuumP3+zAxT0HOyranIH5Yxnp+djlyZncl4v5uIiGIhbsvmO3fuhMvlwvbt2/FP//RP+OUvfxnT398nDAQ9R+r+tdIe2LzfTUREsRC3mXdDQwNmzpwJAJg8eTJOnjwZ09+faTHLzqD1OmD25DGyXdG4ZSQREcVT3IK30+mExWIJ/NlgMGBgYAApKbG5JKW9vY0pehgM8osS3DKSiIjiKW7B22KxoKfnVntSr9erGLizs9ORkhJ+gMzPt8oeW/pIOdLTTPjgzxeGLKMLbl+r0/Q0E56cf7/i8xeGfUXxoTQOyYTj4MNx8OE4+HAcfLQ0DnEL3hUVFdizZw+++c1voqmpCXa7XfH8rq7esH9Hfr4VbW3Km498Y+o47Dt2AX0STdEOHL+Cb0wdp/lZdSjjkAw4Dj4cBx+Ogw/HwUet4yD3hSJuwfuhhx7CgQMH8Oijj0IURbz88ssxvwbXwAB+8b+P4kaPdPKav9VpQXZ6jK+M4klwe3g7hIhULW7BW6/X4xe/+EW8fj0A4KX/cwxXO+Vn9Cz9Si4erxfbd59FY0sbOrsF5NjMKLfnY9HcEhj0SdvPiIhUKGk/kRy9LlxucyqeU1qcg5tOAYJbvo0qJY7tu89i59FL6OgWIALo6Baw8+glbN99Nt6XRkQ0RNJ2WAtlS9Dj5zrwYeMVzsCSgOD2oLGlTfJYY0s7Fswu5hI6EalG0kaiwgJL0HM6OQNLGjedAjolav4BbvNKROqTtMEbgOx+3nIaW9q5hJ6gMi1m5MhsOsPcByJSm6QL3h6vF1t2tmDNW38Oumw+HGdgiYttb4lIS5Lunrc/KWk0OANLbGx7S0RakVTBWykpaTBLWgqcfSNrvzkDS2xse0tEWpFUwVspKQkAbBlGTJlYgEVzi/H2h59xBpakzEYDG/MQkaolVfD2JyVJ7SSWZTFh7eNTYU337fPNGRgREalVUiWsKSUlVd5TEAjcg88vyE5n4CYiIlVJqpk3wKQkIiLSvqQL3kxKIiIirUu64O3HpCQiItKqpLrnTURElAgYvImIiDSGwZuIiEhjGLyJiIg0hsGbiIhIYxi8iYiINIbBm4iISGMYvImIiDRGJ4qiGO+LICIiotBx5k1ERKQxDN5EREQaw+BNRESkMQzeREREGsPgTUREpDEM3kRERBqTkPt5e71evPjiizh9+jRMJhPWr1+Pu+66K96XFTHHjx/Hr3/9a2zevBnnz5/Hs88+C51OhwkTJmDNmjXQ6/XYsWMHtm3bhpSUFCxZsgRz5sxBf38/Vq5ciY6ODmRkZGDDhg3IyclBU1MTXnrpJRgMBlRVVWHp0qXxfomK3G43nn/+eVy+fBkulwtLlixBSUlJ0o0DAHg8Hrzwwgv4/PPPYTAY8Morr0AUxaQci46ODnz3u9/FW2+9hZSUlKQcAwCYP38+rFYrAKCwsBBPP/10Uo7Fb3/7W+zevRtutxu1tbWYOnVqYo2DmIDef/99sb6+XhRFUWxsbBSffvrpOF9R5Pzud78Tv/Wtb4nf+973RFEUxaeeeko8fPiwKIqiuGrVKvG///u/xdbWVvFb3/qWKAiC2N3dHfj/t956S/zNb34jiqIo/ud//qe4bt06URRF8dvf/rZ4/vx50ev1ik888YR48uTJ+Ly4EL399tvi+vXrRVEUxc7OTnH27NlJOQ6iKIoffPCB+Oyzz4qiKIqHDx8Wn3766aQcC5fLJf74xz8WH374YfHs2bNJOQaiKIr9/f3id77znSGPJeNYHD58WHzqqadEj8cjOp1O8Te/+U3CjUNCLps3NDRg5syZAIDJkyfj5MmTcb6iyCkqKsLrr78e+HNzczOmTp0KAJg1axYOHjyIEydOoLy8HCaTCVarFUVFRTh16tSQcZk1axYOHToEp9MJl8uFoqIi6HQ6VFVV4dChQ3F5baH6+te/jp/97GeBPxsMhqQcBwCorq7GunXrAABXrlxBXl5eUo7Fhg0b8Oijj6KgoABAcv67AIBTp06hr68Pjz/+OH7wgx+gqakpKcdi//79sNvt+MlPfoKnn34aDz74YMKNQ0IGb6fTCYvFEvizwWDAwMBAHK8ocmpqapCScutuhyiK0Ol0AICMjAw4HA44nc7Aspn/cafTOeTxwecOHiv/42qWkZEBi8UCp9OJn/70p1i2bFlSjoNfSkoK6uvrsW7dOtTU1CTdWPzxj39ETk5O4MMWSM5/FwCQmpqKf/iHf8Cbb76JtWvXYsWKFUk5Fl1dXTh58iT+9V//NWHHISGDt8ViQU9PT+DPXq93SMBLJHr9rbewp6cHNpttxOvv6emB1Wod8rjSuTabLXYvYJSuXr2KH/zgB/jOd76DefPmJe04+G3YsAHvv/8+Vq1aBUEQAo8nw1i88847OHjwIBYvXoxPP/0U9fX16OzsDBxPhjHwu/vuu/Htb38bOp0Od999N7KystDR0RE4nixjkZWVhaqqKphMJowfPx5ms3lIoE2EcUjI4F1RUYF9+/YBAJqammC32+N8RdFz77334siRIwCAffv2obKyEqWlpWhoaIAgCHA4HDh37hzsdjsqKiqwd+/ewLlTpkyBxWKB0WjEhQsXIIoi9u/fj8rKyni+pKDa29vx+OOPY+XKlVi4cCGA5BwHAHj33Xfx29/+FgCQlpYGnU6HSZMmJdVY/OEPf8B//Md/YPPmzfjyl7+MDRs2YNasWUk1Bn5vv/02fvnLXwIArl+/DqfTiRkzZiTdWEyZMgUfffQRRFHE9evX0dfXhwceeCChxiEhNybxZ5u3tLRAFEW8/PLLKC4ujvdlRcylS5fwj//4j9ixYwc+//xzrFq1Cm63G+PHj8f69ethMBiwY8cObN++HaIo4qmnnkJNTQ36+vpQX1+PtrY2GI1GbNy4Efn5+WhqasLLL78Mj8eDqqoqLF++PN4vUdH69evxX//1Xxg/fnzgsZ///OdYv359Uo0DAPT29uK5555De3s7BgYG8OSTT6K4uDjp/k74LV68GC+++CL0en1SjoHL5cJzzz2HK1euQKfTYcWKFcjOzk7KsfiXf/kXHDlyBKIoYvny5SgsLEyocUjI4E1ERJTIEnLZnIiIKJExeBMREWkMgzcREZHGMHgTERFpDIM3ERGRxjB4ExERaQyDNxERkcYweBMREWnM/wcllAZp0R/zrgAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 576x396 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(y_test,pred)\n",
    "plt.plot()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "id": "37b69266",
   "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>19</td>\n",
       "      <td>27.900</td>\n",
       "      <td>0</td>\n",
       "      <td>16884.92400</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>18</td>\n",
       "      <td>33.770</td>\n",
       "      <td>1</td>\n",
       "      <td>1725.55230</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>28</td>\n",
       "      <td>33.000</td>\n",
       "      <td>3</td>\n",
       "      <td>4449.46200</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>33</td>\n",
       "      <td>22.705</td>\n",
       "      <td>0</td>\n",
       "      <td>21984.47061</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>32</td>\n",
       "      <td>28.880</td>\n",
       "      <td>0</td>\n",
       "      <td>3866.85520</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   age     bmi  children      charges  sex_male  smoker_yes  region_northwest  \\\n",
       "0   19  27.900         0  16884.92400         0           1                 0   \n",
       "1   18  33.770         1   1725.55230         1           0                 0   \n",
       "2   28  33.000         3   4449.46200         1           0                 0   \n",
       "3   33  22.705         0  21984.47061         1           0                 1   \n",
       "4   32  28.880         0   3866.85520         1           0                 1   \n",
       "\n",
       "   region_southeast  region_southwest  \n",
       "0                 0                 1  \n",
       "1                 1                 0  \n",
       "2                 1                 0  \n",
       "3                 0                 0  \n",
       "4                 0                 0  "
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "id": "1017ed7d",
   "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>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>19</td>\n",
       "      <td>27.900</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>18</td>\n",
       "      <td>33.770</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>28</td>\n",
       "      <td>33.000</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>33</td>\n",
       "      <td>22.705</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>32</td>\n",
       "      <td>28.880</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   age     bmi  children  sex_male  smoker_yes  region_northwest  \\\n",
       "0   19  27.900         0         0           1                 0   \n",
       "1   18  33.770         1         1           0                 0   \n",
       "2   28  33.000         3         1           0                 0   \n",
       "3   33  22.705         0         1           0                 1   \n",
       "4   32  28.880         0         1           0                 1   \n",
       "\n",
       "   region_southeast  region_southwest  \n",
       "0                 0                 1  \n",
       "1                 1                 0  \n",
       "2                 1                 0  \n",
       "3                 0                 0  \n",
       "4                 0                 0  "
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "id": "bce685f8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([25245.76135224])"
      ]
     },
     "execution_count": 54,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lr.predict([[19,27.900,0,0,1,0,0,1]])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "id": "29b955bb",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle as pk"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "id": "dbac727d",
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(\"Linear_model.sav\",\"wb\") as file:\n",
    "    pk.dump(lr,file)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "id": "b9bdd101",
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(\"Linear_model.sav\",\"rb\") as file:\n",
    "    model=pk.load(file)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f02b4986",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.9.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}