{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 94,
   "id": "2d078b8b",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd \n",
    "import numpy as np \n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "id": "95bfec56",
   "metadata": {},
   "outputs": [],
   "source": [
    "USA_housing = pd.read_csv('datasets/USA_Housing.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "id": "7f131c94",
   "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>Avg. Area Income</th>\n",
       "      <th>Avg. Area House Age</th>\n",
       "      <th>Avg. Area Number of Rooms</th>\n",
       "      <th>Avg. Area Number of Bedrooms</th>\n",
       "      <th>Area Population</th>\n",
       "      <th>Price</th>\n",
       "      <th>Address</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>79545.45857</td>\n",
       "      <td>5.682861</td>\n",
       "      <td>7.009188</td>\n",
       "      <td>4.09</td>\n",
       "      <td>23086.80050</td>\n",
       "      <td>1.059034e+06</td>\n",
       "      <td>208 Michael Ferry Apt. 674\\nLaurabury, NE 3701...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>79248.64245</td>\n",
       "      <td>6.002900</td>\n",
       "      <td>6.730821</td>\n",
       "      <td>3.09</td>\n",
       "      <td>40173.07217</td>\n",
       "      <td>1.505891e+06</td>\n",
       "      <td>188 Johnson Views Suite 079\\nLake Kathleen, CA...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>61287.06718</td>\n",
       "      <td>5.865890</td>\n",
       "      <td>8.512727</td>\n",
       "      <td>5.13</td>\n",
       "      <td>36882.15940</td>\n",
       "      <td>1.058988e+06</td>\n",
       "      <td>9127 Elizabeth Stravenue\\nDanieltown, WI 06482...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>63345.24005</td>\n",
       "      <td>7.188236</td>\n",
       "      <td>5.586729</td>\n",
       "      <td>3.26</td>\n",
       "      <td>34310.24283</td>\n",
       "      <td>1.260617e+06</td>\n",
       "      <td>USS Barnett\\nFPO AP 44820</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>59982.19723</td>\n",
       "      <td>5.040555</td>\n",
       "      <td>7.839388</td>\n",
       "      <td>4.23</td>\n",
       "      <td>26354.10947</td>\n",
       "      <td>6.309435e+05</td>\n",
       "      <td>USNS Raymond\\nFPO AE 09386</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Avg. Area Income  Avg. Area House Age  Avg. Area Number of Rooms  \\\n",
       "0       79545.45857             5.682861                   7.009188   \n",
       "1       79248.64245             6.002900                   6.730821   \n",
       "2       61287.06718             5.865890                   8.512727   \n",
       "3       63345.24005             7.188236                   5.586729   \n",
       "4       59982.19723             5.040555                   7.839388   \n",
       "\n",
       "   Avg. Area Number of Bedrooms  Area Population         Price  \\\n",
       "0                          4.09      23086.80050  1.059034e+06   \n",
       "1                          3.09      40173.07217  1.505891e+06   \n",
       "2                          5.13      36882.15940  1.058988e+06   \n",
       "3                          3.26      34310.24283  1.260617e+06   \n",
       "4                          4.23      26354.10947  6.309435e+05   \n",
       "\n",
       "                                             Address  \n",
       "0  208 Michael Ferry Apt. 674\\nLaurabury, NE 3701...  \n",
       "1  188 Johnson Views Suite 079\\nLake Kathleen, CA...  \n",
       "2  9127 Elizabeth Stravenue\\nDanieltown, WI 06482...  \n",
       "3                          USS Barnett\\nFPO AP 44820  \n",
       "4                         USNS Raymond\\nFPO AE 09386  "
      ]
     },
     "execution_count": 96,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "USA_housing.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "id": "84a88864",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 5000 entries, 0 to 4999\n",
      "Data columns (total 7 columns):\n",
      " #   Column                        Non-Null Count  Dtype  \n",
      "---  ------                        --------------  -----  \n",
      " 0   Avg. Area Income              5000 non-null   float64\n",
      " 1   Avg. Area House Age           5000 non-null   float64\n",
      " 2   Avg. Area Number of Rooms     5000 non-null   float64\n",
      " 3   Avg. Area Number of Bedrooms  5000 non-null   float64\n",
      " 4   Area Population               5000 non-null   float64\n",
      " 5   Price                         5000 non-null   float64\n",
      " 6   Address                       5000 non-null   object \n",
      "dtypes: float64(6), object(1)\n",
      "memory usage: 273.6+ KB\n"
     ]
    }
   ],
   "source": [
    "USA_housing.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 98,
   "id": "88bf3097",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['Avg. Area Income', 'Avg. Area House Age', 'Avg. Area Number of Rooms',\n",
       "       'Avg. Area Number of Bedrooms', 'Area Population', 'Price', 'Address'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 98,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "USA_housing.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 99,
   "id": "e65640d0",
   "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>Avg. Area Income</th>\n",
       "      <th>Avg. Area House Age</th>\n",
       "      <th>Avg. Area Number of Rooms</th>\n",
       "      <th>Avg. Area Number of Bedrooms</th>\n",
       "      <th>Area Population</th>\n",
       "      <th>Price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>5000.000000</td>\n",
       "      <td>5000.000000</td>\n",
       "      <td>5000.000000</td>\n",
       "      <td>5000.000000</td>\n",
       "      <td>5000.000000</td>\n",
       "      <td>5.000000e+03</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>68583.108984</td>\n",
       "      <td>5.977222</td>\n",
       "      <td>6.987792</td>\n",
       "      <td>3.981330</td>\n",
       "      <td>36163.516039</td>\n",
       "      <td>1.232073e+06</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>10657.991214</td>\n",
       "      <td>0.991456</td>\n",
       "      <td>1.005833</td>\n",
       "      <td>1.234137</td>\n",
       "      <td>9925.650114</td>\n",
       "      <td>3.531176e+05</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>17796.631190</td>\n",
       "      <td>2.644304</td>\n",
       "      <td>3.236194</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>172.610686</td>\n",
       "      <td>1.593866e+04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>61480.562390</td>\n",
       "      <td>5.322283</td>\n",
       "      <td>6.299250</td>\n",
       "      <td>3.140000</td>\n",
       "      <td>29403.928700</td>\n",
       "      <td>9.975771e+05</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>68804.286405</td>\n",
       "      <td>5.970429</td>\n",
       "      <td>7.002902</td>\n",
       "      <td>4.050000</td>\n",
       "      <td>36199.406690</td>\n",
       "      <td>1.232669e+06</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>75783.338665</td>\n",
       "      <td>6.650808</td>\n",
       "      <td>7.665871</td>\n",
       "      <td>4.490000</td>\n",
       "      <td>42861.290770</td>\n",
       "      <td>1.471210e+06</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>107701.748400</td>\n",
       "      <td>9.519088</td>\n",
       "      <td>10.759588</td>\n",
       "      <td>6.500000</td>\n",
       "      <td>69621.713380</td>\n",
       "      <td>2.469066e+06</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       Avg. Area Income  Avg. Area House Age  Avg. Area Number of Rooms  \\\n",
       "count       5000.000000          5000.000000                5000.000000   \n",
       "mean       68583.108984             5.977222                   6.987792   \n",
       "std        10657.991214             0.991456                   1.005833   \n",
       "min        17796.631190             2.644304                   3.236194   \n",
       "25%        61480.562390             5.322283                   6.299250   \n",
       "50%        68804.286405             5.970429                   7.002902   \n",
       "75%        75783.338665             6.650808                   7.665871   \n",
       "max       107701.748400             9.519088                  10.759588   \n",
       "\n",
       "       Avg. Area Number of Bedrooms  Area Population         Price  \n",
       "count                   5000.000000      5000.000000  5.000000e+03  \n",
       "mean                       3.981330     36163.516039  1.232073e+06  \n",
       "std                        1.234137      9925.650114  3.531176e+05  \n",
       "min                        2.000000       172.610686  1.593866e+04  \n",
       "25%                        3.140000     29403.928700  9.975771e+05  \n",
       "50%                        4.050000     36199.406690  1.232669e+06  \n",
       "75%                        4.490000     42861.290770  1.471210e+06  \n",
       "max                        6.500000     69621.713380  2.469066e+06  "
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "USA_housing.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "id": "ec40779b",
   "metadata": {},
   "outputs": [],
   "source": [
    "USA_housing.drop('Address', axis=1, inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 101,
   "id": "bf194bf3",
   "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>Avg. Area House Age</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>5000.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>5.977222</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>0.991456</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>2.644304</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>5.322283</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>5.970429</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>6.650808</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>9.519088</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       Avg. Area House Age\n",
       "count          5000.000000\n",
       "mean              5.977222\n",
       "std               0.991456\n",
       "min               2.644304\n",
       "25%               5.322283\n",
       "50%               5.970429\n",
       "75%               6.650808\n",
       "max               9.519088"
      ]
     },
     "execution_count": 101,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "USA_housing.describe()[['Avg. Area House Age']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 102,
   "id": "1ad81483",
   "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>Avg. Area Income</th>\n",
       "      <th>Avg. Area House Age</th>\n",
       "      <th>Avg. Area Number of Rooms</th>\n",
       "      <th>Avg. Area Number of Bedrooms</th>\n",
       "      <th>Area Population</th>\n",
       "      <th>Price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>5000.000000</td>\n",
       "      <td>5000.000000</td>\n",
       "      <td>5000.000000</td>\n",
       "      <td>5000.000000</td>\n",
       "      <td>5000.000000</td>\n",
       "      <td>5.000000e+03</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>68583.108984</td>\n",
       "      <td>5.977222</td>\n",
       "      <td>6.987792</td>\n",
       "      <td>3.981330</td>\n",
       "      <td>36163.516039</td>\n",
       "      <td>1.232073e+06</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>10657.991214</td>\n",
       "      <td>0.991456</td>\n",
       "      <td>1.005833</td>\n",
       "      <td>1.234137</td>\n",
       "      <td>9925.650114</td>\n",
       "      <td>3.531176e+05</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>17796.631190</td>\n",
       "      <td>2.644304</td>\n",
       "      <td>3.236194</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>172.610686</td>\n",
       "      <td>1.593866e+04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>61480.562390</td>\n",
       "      <td>5.322283</td>\n",
       "      <td>6.299250</td>\n",
       "      <td>3.140000</td>\n",
       "      <td>29403.928700</td>\n",
       "      <td>9.975771e+05</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>68804.286405</td>\n",
       "      <td>5.970429</td>\n",
       "      <td>7.002902</td>\n",
       "      <td>4.050000</td>\n",
       "      <td>36199.406690</td>\n",
       "      <td>1.232669e+06</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>75783.338665</td>\n",
       "      <td>6.650808</td>\n",
       "      <td>7.665871</td>\n",
       "      <td>4.490000</td>\n",
       "      <td>42861.290770</td>\n",
       "      <td>1.471210e+06</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>107701.748400</td>\n",
       "      <td>9.519088</td>\n",
       "      <td>10.759588</td>\n",
       "      <td>6.500000</td>\n",
       "      <td>69621.713380</td>\n",
       "      <td>2.469066e+06</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       Avg. Area Income  Avg. Area House Age  Avg. Area Number of Rooms  \\\n",
       "count       5000.000000          5000.000000                5000.000000   \n",
       "mean       68583.108984             5.977222                   6.987792   \n",
       "std        10657.991214             0.991456                   1.005833   \n",
       "min        17796.631190             2.644304                   3.236194   \n",
       "25%        61480.562390             5.322283                   6.299250   \n",
       "50%        68804.286405             5.970429                   7.002902   \n",
       "75%        75783.338665             6.650808                   7.665871   \n",
       "max       107701.748400             9.519088                  10.759588   \n",
       "\n",
       "       Avg. Area Number of Bedrooms  Area Population         Price  \n",
       "count                   5000.000000      5000.000000  5.000000e+03  \n",
       "mean                       3.981330     36163.516039  1.232073e+06  \n",
       "std                        1.234137      9925.650114  3.531176e+05  \n",
       "min                        2.000000       172.610686  1.593866e+04  \n",
       "25%                        3.140000     29403.928700  9.975771e+05  \n",
       "50%                        4.050000     36199.406690  1.232669e+06  \n",
       "75%                        4.490000     42861.290770  1.471210e+06  \n",
       "max                        6.500000     69621.713380  2.469066e+06  "
      ]
     },
     "execution_count": 102,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "USA_housing.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "id": "5b5cca8e",
   "metadata": {},
   "outputs": [],
   "source": [
    "#sns.pairplot(USA_housing)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 104,
   "id": "79769628",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Axes: >"
      ]
     },
     "execution_count": 104,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.heatmap(USA_housing.corr(), cmap='viridis', annot=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "id": "34485b6a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.FacetGrid at 0x7f20f9186ee0>"
      ]
     },
     "execution_count": 105,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 500x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.displot(USA_housing['Price'], kde= True, bins = 1500)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 106,
   "id": "888f6a06",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['Avg. Area Income', 'Avg. Area House Age', 'Avg. Area Number of Rooms',\n",
       "       'Avg. Area Number of Bedrooms', 'Area Population', 'Price'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 106,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "USA_housing.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 107,
   "id": "02fac7e3",
   "metadata": {},
   "outputs": [],
   "source": [
    "X = USA_housing[['Avg. Area Income', 'Avg. Area House Age', \n",
    "                 'Avg. Area Number of Rooms',\n",
    "       'Avg. Area Number of Bedrooms', 'Area Population']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 108,
   "id": "639f41db",
   "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>Avg. Area Income</th>\n",
       "      <th>Avg. Area House Age</th>\n",
       "      <th>Avg. Area Number of Rooms</th>\n",
       "      <th>Avg. Area Number of Bedrooms</th>\n",
       "      <th>Area Population</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>79545.45857</td>\n",
       "      <td>5.682861</td>\n",
       "      <td>7.009188</td>\n",
       "      <td>4.09</td>\n",
       "      <td>23086.80050</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>79248.64245</td>\n",
       "      <td>6.002900</td>\n",
       "      <td>6.730821</td>\n",
       "      <td>3.09</td>\n",
       "      <td>40173.07217</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>61287.06718</td>\n",
       "      <td>5.865890</td>\n",
       "      <td>8.512727</td>\n",
       "      <td>5.13</td>\n",
       "      <td>36882.15940</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>63345.24005</td>\n",
       "      <td>7.188236</td>\n",
       "      <td>5.586729</td>\n",
       "      <td>3.26</td>\n",
       "      <td>34310.24283</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>59982.19723</td>\n",
       "      <td>5.040555</td>\n",
       "      <td>7.839388</td>\n",
       "      <td>4.23</td>\n",
       "      <td>26354.10947</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Avg. Area Income  Avg. Area House Age  Avg. Area Number of Rooms  \\\n",
       "0       79545.45857             5.682861                   7.009188   \n",
       "1       79248.64245             6.002900                   6.730821   \n",
       "2       61287.06718             5.865890                   8.512727   \n",
       "3       63345.24005             7.188236                   5.586729   \n",
       "4       59982.19723             5.040555                   7.839388   \n",
       "\n",
       "   Avg. Area Number of Bedrooms  Area Population  \n",
       "0                          4.09      23086.80050  \n",
       "1                          3.09      40173.07217  \n",
       "2                          5.13      36882.15940  \n",
       "3                          3.26      34310.24283  \n",
       "4                          4.23      26354.10947  "
      ]
     },
     "execution_count": 108,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 109,
   "id": "5555cdae",
   "metadata": {},
   "outputs": [],
   "source": [
    "y = USA_housing['Price']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 110,
   "id": "1231da3f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    1.059034e+06\n",
       "1    1.505891e+06\n",
       "2    1.058988e+06\n",
       "3    1.260617e+06\n",
       "4    6.309435e+05\n",
       "Name: Price, dtype: float64"
      ]
     },
     "execution_count": 110,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 111,
   "id": "e3d8baeb",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: scikit-learn in /home/gptuser/.local/lib/python3.8/site-packages (1.3.2)\n",
      "Requirement already satisfied: scipy>=1.5.0 in /home/gptuser/.local/lib/python3.8/site-packages (from scikit-learn) (1.10.1)\n",
      "Requirement already satisfied: threadpoolctl>=2.0.0 in /home/gptuser/.local/lib/python3.8/site-packages (from scikit-learn) (3.3.0)\n",
      "Requirement already satisfied: numpy<2.0,>=1.17.3 in /home/gptuser/.local/lib/python3.8/site-packages (from scikit-learn) (1.24.4)\n",
      "Requirement already satisfied: joblib>=1.1.1 in /home/gptuser/.local/lib/python3.8/site-packages (from scikit-learn) (1.3.2)\n"
     ]
    }
   ],
   "source": [
    "!pip install scikit-learn "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 112,
   "id": "eed045f6",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 113,
   "id": "32a6a174",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "     X, y, test_size=0.3, random_state=101)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 114,
   "id": "39d9fe48",
   "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>Avg. Area Income</th>\n",
       "      <th>Avg. Area House Age</th>\n",
       "      <th>Avg. Area Number of Rooms</th>\n",
       "      <th>Avg. Area Number of Bedrooms</th>\n",
       "      <th>Area Population</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2654</th>\n",
       "      <td>86690.87330</td>\n",
       "      <td>6.259901</td>\n",
       "      <td>6.676265</td>\n",
       "      <td>3.23</td>\n",
       "      <td>42589.62439</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2468</th>\n",
       "      <td>59866.94770</td>\n",
       "      <td>5.870330</td>\n",
       "      <td>5.899076</td>\n",
       "      <td>4.16</td>\n",
       "      <td>32064.59716</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>290</th>\n",
       "      <td>74372.13845</td>\n",
       "      <td>6.562380</td>\n",
       "      <td>8.184511</td>\n",
       "      <td>6.35</td>\n",
       "      <td>34321.96015</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1463</th>\n",
       "      <td>61370.32349</td>\n",
       "      <td>6.529605</td>\n",
       "      <td>6.606744</td>\n",
       "      <td>4.30</td>\n",
       "      <td>20600.51100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4508</th>\n",
       "      <td>52652.65234</td>\n",
       "      <td>5.688943</td>\n",
       "      <td>7.217268</td>\n",
       "      <td>4.06</td>\n",
       "      <td>34776.58591</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      Avg. Area Income  Avg. Area House Age  Avg. Area Number of Rooms  \\\n",
       "2654       86690.87330             6.259901                   6.676265   \n",
       "2468       59866.94770             5.870330                   5.899076   \n",
       "290        74372.13845             6.562380                   8.184511   \n",
       "1463       61370.32349             6.529605                   6.606744   \n",
       "4508       52652.65234             5.688943                   7.217268   \n",
       "\n",
       "      Avg. Area Number of Bedrooms  Area Population  \n",
       "2654                          3.23      42589.62439  \n",
       "2468                          4.16      32064.59716  \n",
       "290                           6.35      34321.96015  \n",
       "1463                          4.30      20600.51100  \n",
       "4508                          4.06      34776.58591  "
      ]
     },
     "execution_count": 114,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 115,
   "id": "626e9ba8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "3500"
      ]
     },
     "execution_count": 115,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(X_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 116,
   "id": "eaed79a7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2654    1.723730e+06\n",
       "2468    1.039381e+06\n",
       "290     1.648247e+06\n",
       "1463    8.245409e+05\n",
       "4508    9.282108e+05\n",
       "Name: Price, dtype: float64"
      ]
     },
     "execution_count": 116,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 117,
   "id": "3260b480",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.linear_model import LinearRegression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 118,
   "id": "d53b1a47",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Instantiate a model\n",
    "lm = LinearRegression()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 119,
   "id": "2909d83b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-3 {color: black;}#sk-container-id-3 pre{padding: 0;}#sk-container-id-3 div.sk-toggleable {background-color: white;}#sk-container-id-3 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-3 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-3 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-3 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-3 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-3 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-3 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-3 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-3 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-3 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-3 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-3 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-3 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-3 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-3 div.sk-item {position: relative;z-index: 1;}#sk-container-id-3 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-3 div.sk-item::before, #sk-container-id-3 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-3 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-3 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-3 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-3 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-3 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-3 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-3 div.sk-label-container {text-align: center;}#sk-container-id-3 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-3 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-3\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LinearRegression()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" checked><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LinearRegression</label><div class=\"sk-toggleable__content\"><pre>LinearRegression()</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "LinearRegression()"
      ]
     },
     "execution_count": 119,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Train the model\n",
    "lm.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 120,
   "id": "7016160e",
   "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>Avg. Area Income</th>\n",
       "      <th>Avg. Area House Age</th>\n",
       "      <th>Avg. Area Number of Rooms</th>\n",
       "      <th>Avg. Area Number of Bedrooms</th>\n",
       "      <th>Area Population</th>\n",
       "      <th>Price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>5000.000000</td>\n",
       "      <td>5000.000000</td>\n",
       "      <td>5000.000000</td>\n",
       "      <td>5000.000000</td>\n",
       "      <td>5000.000000</td>\n",
       "      <td>5.000000e+03</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>68583.108984</td>\n",
       "      <td>5.977222</td>\n",
       "      <td>6.987792</td>\n",
       "      <td>3.981330</td>\n",
       "      <td>36163.516039</td>\n",
       "      <td>1.232073e+06</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>10657.991214</td>\n",
       "      <td>0.991456</td>\n",
       "      <td>1.005833</td>\n",
       "      <td>1.234137</td>\n",
       "      <td>9925.650114</td>\n",
       "      <td>3.531176e+05</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>17796.631190</td>\n",
       "      <td>2.644304</td>\n",
       "      <td>3.236194</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>172.610686</td>\n",
       "      <td>1.593866e+04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>61480.562390</td>\n",
       "      <td>5.322283</td>\n",
       "      <td>6.299250</td>\n",
       "      <td>3.140000</td>\n",
       "      <td>29403.928700</td>\n",
       "      <td>9.975771e+05</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>68804.286405</td>\n",
       "      <td>5.970429</td>\n",
       "      <td>7.002902</td>\n",
       "      <td>4.050000</td>\n",
       "      <td>36199.406690</td>\n",
       "      <td>1.232669e+06</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>75783.338665</td>\n",
       "      <td>6.650808</td>\n",
       "      <td>7.665871</td>\n",
       "      <td>4.490000</td>\n",
       "      <td>42861.290770</td>\n",
       "      <td>1.471210e+06</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>107701.748400</td>\n",
       "      <td>9.519088</td>\n",
       "      <td>10.759588</td>\n",
       "      <td>6.500000</td>\n",
       "      <td>69621.713380</td>\n",
       "      <td>2.469066e+06</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       Avg. Area Income  Avg. Area House Age  Avg. Area Number of Rooms  \\\n",
       "count       5000.000000          5000.000000                5000.000000   \n",
       "mean       68583.108984             5.977222                   6.987792   \n",
       "std        10657.991214             0.991456                   1.005833   \n",
       "min        17796.631190             2.644304                   3.236194   \n",
       "25%        61480.562390             5.322283                   6.299250   \n",
       "50%        68804.286405             5.970429                   7.002902   \n",
       "75%        75783.338665             6.650808                   7.665871   \n",
       "max       107701.748400             9.519088                  10.759588   \n",
       "\n",
       "       Avg. Area Number of Bedrooms  Area Population         Price  \n",
       "count                   5000.000000      5000.000000  5.000000e+03  \n",
       "mean                       3.981330     36163.516039  1.232073e+06  \n",
       "std                        1.234137      9925.650114  3.531176e+05  \n",
       "min                        2.000000       172.610686  1.593866e+04  \n",
       "25%                        3.140000     29403.928700  9.975771e+05  \n",
       "50%                        4.050000     36199.406690  1.232669e+06  \n",
       "75%                        4.490000     42861.290770  1.471210e+06  \n",
       "max                        6.500000     69621.713380  2.469066e+06  "
      ]
     },
     "execution_count": 120,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "USA_housing.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 121,
   "id": "76aa7aa7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([2.16176350e+01, 1.65221120e+05, 1.21405377e+05, 1.31871878e+03,\n",
       "       1.52251955e+01])"
      ]
     },
     "execution_count": 121,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lm.coef_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 122,
   "id": "808fe176",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "-2641372.6672760616"
      ]
     },
     "execution_count": 122,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lm.intercept_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 123,
   "id": "6fcc9019",
   "metadata": {},
   "outputs": [],
   "source": [
    "coef_df = pd.DataFrame(lm.coef_, X.columns, columns=['Coefficients'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 124,
   "id": "ef2fc0d8",
   "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>Coefficients</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Avg. Area Income</th>\n",
       "      <td>21.617635</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Avg. Area House Age</th>\n",
       "      <td>165221.119873</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Avg. Area Number of Rooms</th>\n",
       "      <td>121405.376593</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Avg. Area Number of Bedrooms</th>\n",
       "      <td>1318.718781</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Area Population</th>\n",
       "      <td>15.225196</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                               Coefficients\n",
       "Avg. Area Income                  21.617635\n",
       "Avg. Area House Age           165221.119873\n",
       "Avg. Area Number of Rooms     121405.376593\n",
       "Avg. Area Number of Bedrooms    1318.718781\n",
       "Area Population                   15.225196"
      ]
     },
     "execution_count": 124,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "coef_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 125,
   "id": "d92f95ae",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Index: 1500 entries, 1718 to 790\n",
      "Data columns (total 5 columns):\n",
      " #   Column                        Non-Null Count  Dtype  \n",
      "---  ------                        --------------  -----  \n",
      " 0   Avg. Area Income              1500 non-null   float64\n",
      " 1   Avg. Area House Age           1500 non-null   float64\n",
      " 2   Avg. Area Number of Rooms     1500 non-null   float64\n",
      " 3   Avg. Area Number of Bedrooms  1500 non-null   float64\n",
      " 4   Area Population               1500 non-null   float64\n",
      "dtypes: float64(5)\n",
      "memory usage: 70.3 KB\n"
     ]
    }
   ],
   "source": [
    "X_test.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "af73348c",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 126,
   "id": "fea796dc",
   "metadata": {},
   "outputs": [],
   "source": [
    "predictions = lm.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 127,
   "id": "4dfc1e9a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1500"
      ]
     },
     "execution_count": 127,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(predictions)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 128,
   "id": "d1f92a53",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1258934.89517874,  822694.63393623, 1742214.39531853,\n",
       "        972937.00473099,  994545.99156145,  644486.33953343,\n",
       "       1078071.03851577,  854756.03238178, 1445901.3446677 ,\n",
       "       1203355.11909779])"
      ]
     },
     "execution_count": 128,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "predictions[:10]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 129,
   "id": "f3254a9e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Model Evaluation "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 130,
   "id": "267b5219",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn import metrics"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 131,
   "id": "cb329e41",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MSE:  10169125564.694378\n"
     ]
    }
   ],
   "source": [
    "print('MSE: ', metrics.mean_squared_error(y_test, predictions))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 132,
   "id": "34c961fb",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "RMSE:  100842.08231038458\n"
     ]
    }
   ],
   "source": [
    "print('RMSE: ', np.sqrt(metrics.mean_squared_error(y_test, predictions)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 133,
   "id": "197260cd",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1232072.6541453"
      ]
     },
     "execution_count": 133,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "USA_housing['Price'].mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 134,
   "id": "ee16c3c0-5882-4112-94b3-21a9461f4ebd",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['Avg. Area Income', 'Avg. Area House Age', 'Avg. Area Number of Rooms',\n",
       "       'Avg. Area Number of Bedrooms', 'Area Population', 'Price'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 134,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "USA_housing.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 135,
   "id": "a277aa57",
   "metadata": {},
   "outputs": [],
   "source": [
    "new_data = np.array([66774.99581, 5.717143, 7.79521, 4.3, 36788.980327])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 136,
   "id": "071ee315",
   "metadata": {},
   "outputs": [],
   "source": [
    "new_data = new_data.reshape(1, -1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 137,
   "id": "cee45a03",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1, 5)"
      ]
     },
     "execution_count": 137,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_data.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 138,
   "id": "6d0ca53c-4e3b-41f9-9268-b28be0ea2cf9",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Column labels, excluding 'Price'\n",
    "column_labels = ['Avg. Area Income', 'Avg. Area House Age', 'Avg. Area Number of Rooms',\n",
    "                 'Avg. Area Number of Bedrooms', 'Area Population']\n",
    "\n",
    "# Convert to DataFrame with feature names\n",
    "new_data_df = pd.DataFrame(new_data, columns=column_labels)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 139,
   "id": "09b94ca4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1258907.9020365])"
      ]
     },
     "execution_count": 139,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lm.predict(new_data_df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 140,
   "id": "022b72e0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.FacetGrid at 0x7f20fda7ba60>"
      ]
     },
     "execution_count": 140,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 500x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.displot(y_test - predictions, kde=False, bins=50) # Distribution of residuals"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 141,
   "id": "26db7c71",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0x7f210b793c40>"
      ]
     },
     "execution_count": 141,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(y_test, predictions)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python (ai-env4)",
   "language": "python",
   "name": "ai-env4"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}