Car Prediction.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "_cell_guid": "b1076dfc-b9ad-4769-8c92-a6c4dae69d19",
    "_uuid": "8f2839f25d086af736a60e9eeb907d3b93b6e0e5"
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "_cell_guid": "79c7e3d0-c299-4dcb-8224-4455121ee9b0",
    "_uuid": "d629ff2d2480ee46fbb7e2d37f6b5fab8052498a"
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "df=pd.read_csv('cardekho.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "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>Car_Name</th>\n",
       "      <th>Year</th>\n",
       "      <th>Selling_Price</th>\n",
       "      <th>Present_Price</th>\n",
       "      <th>Kms_Driven</th>\n",
       "      <th>Fuel_Type</th>\n",
       "      <th>Seller_Type</th>\n",
       "      <th>Transmission</th>\n",
       "      <th>Owner</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>ritz</td>\n",
       "      <td>2014</td>\n",
       "      <td>3.35</td>\n",
       "      <td>5.59</td>\n",
       "      <td>27000</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>sx4</td>\n",
       "      <td>2013</td>\n",
       "      <td>4.75</td>\n",
       "      <td>9.54</td>\n",
       "      <td>43000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>ciaz</td>\n",
       "      <td>2017</td>\n",
       "      <td>7.25</td>\n",
       "      <td>9.85</td>\n",
       "      <td>6900</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>wagon r</td>\n",
       "      <td>2011</td>\n",
       "      <td>2.85</td>\n",
       "      <td>4.15</td>\n",
       "      <td>5200</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>swift</td>\n",
       "      <td>2014</td>\n",
       "      <td>4.60</td>\n",
       "      <td>6.87</td>\n",
       "      <td>42450</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Car_Name  Year  Selling_Price  Present_Price  Kms_Driven Fuel_Type  \\\n",
       "0     ritz  2014           3.35           5.59       27000    Petrol   \n",
       "1      sx4  2013           4.75           9.54       43000    Diesel   \n",
       "2     ciaz  2017           7.25           9.85        6900    Petrol   \n",
       "3  wagon r  2011           2.85           4.15        5200    Petrol   \n",
       "4    swift  2014           4.60           6.87       42450    Diesel   \n",
       "\n",
       "  Seller_Type Transmission  Owner  \n",
       "0      Dealer       Manual      0  \n",
       "1      Dealer       Manual      0  \n",
       "2      Dealer       Manual      0  \n",
       "3      Dealer       Manual      0  \n",
       "4      Dealer       Manual      0  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(301, 9)"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['Dealer' 'Individual']\n",
      "['Manual' 'Automatic']\n",
      "[0 1 3]\n",
      "['Petrol' 'Diesel' 'CNG']\n"
     ]
    }
   ],
   "source": [
    "print(df['Seller_Type'].unique())\n",
    "print(df['Transmission'].unique())\n",
    "print(df['Owner'].unique())\n",
    "print(df['Fuel_Type'].unique())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Car_Name         0\n",
       "Year             0\n",
       "Selling_Price    0\n",
       "Present_Price    0\n",
       "Kms_Driven       0\n",
       "Fuel_Type        0\n",
       "Seller_Type      0\n",
       "Transmission     0\n",
       "Owner            0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#check missing null values\n",
    "\n",
    "df.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Car_Name         0\n",
       "Year             0\n",
       "Selling_Price    0\n",
       "Present_Price    0\n",
       "Kms_Driven       0\n",
       "Fuel_Type        0\n",
       "Seller_Type      0\n",
       "Transmission     0\n",
       "Owner            0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "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>Year</th>\n",
       "      <th>Selling_Price</th>\n",
       "      <th>Present_Price</th>\n",
       "      <th>Kms_Driven</th>\n",
       "      <th>Owner</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>301.000000</td>\n",
       "      <td>301.000000</td>\n",
       "      <td>301.000000</td>\n",
       "      <td>301.000000</td>\n",
       "      <td>301.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>2013.627907</td>\n",
       "      <td>4.661296</td>\n",
       "      <td>7.628472</td>\n",
       "      <td>36947.205980</td>\n",
       "      <td>0.043189</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>2.891554</td>\n",
       "      <td>5.082812</td>\n",
       "      <td>8.644115</td>\n",
       "      <td>38886.883882</td>\n",
       "      <td>0.247915</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>2003.000000</td>\n",
       "      <td>0.100000</td>\n",
       "      <td>0.320000</td>\n",
       "      <td>500.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>2012.000000</td>\n",
       "      <td>0.900000</td>\n",
       "      <td>1.200000</td>\n",
       "      <td>15000.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>2014.000000</td>\n",
       "      <td>3.600000</td>\n",
       "      <td>6.400000</td>\n",
       "      <td>32000.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>2016.000000</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>9.900000</td>\n",
       "      <td>48767.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>2018.000000</td>\n",
       "      <td>35.000000</td>\n",
       "      <td>92.600000</td>\n",
       "      <td>500000.000000</td>\n",
       "      <td>3.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              Year  Selling_Price  Present_Price     Kms_Driven       Owner\n",
       "count   301.000000     301.000000     301.000000     301.000000  301.000000\n",
       "mean   2013.627907       4.661296       7.628472   36947.205980    0.043189\n",
       "std       2.891554       5.082812       8.644115   38886.883882    0.247915\n",
       "min    2003.000000       0.100000       0.320000     500.000000    0.000000\n",
       "25%    2012.000000       0.900000       1.200000   15000.000000    0.000000\n",
       "50%    2014.000000       3.600000       6.400000   32000.000000    0.000000\n",
       "75%    2016.000000       6.000000       9.900000   48767.000000    0.000000\n",
       "max    2018.000000      35.000000      92.600000  500000.000000    3.000000"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['Car_Name', 'Year', 'Selling_Price', 'Present_Price', 'Kms_Driven',\n",
       "       'Fuel_Type', 'Seller_Type', 'Transmission', 'Owner'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "final_dataset= df[[ 'Year', 'Selling_Price', 'Present_Price', 'Kms_Driven','Fuel_Type', 'Seller_Type', 'Transmission', 'Owner']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "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>Year</th>\n",
       "      <th>Selling_Price</th>\n",
       "      <th>Present_Price</th>\n",
       "      <th>Kms_Driven</th>\n",
       "      <th>Fuel_Type</th>\n",
       "      <th>Seller_Type</th>\n",
       "      <th>Transmission</th>\n",
       "      <th>Owner</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2014</td>\n",
       "      <td>3.35</td>\n",
       "      <td>5.59</td>\n",
       "      <td>27000</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2013</td>\n",
       "      <td>4.75</td>\n",
       "      <td>9.54</td>\n",
       "      <td>43000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2017</td>\n",
       "      <td>7.25</td>\n",
       "      <td>9.85</td>\n",
       "      <td>6900</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2011</td>\n",
       "      <td>2.85</td>\n",
       "      <td>4.15</td>\n",
       "      <td>5200</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2014</td>\n",
       "      <td>4.60</td>\n",
       "      <td>6.87</td>\n",
       "      <td>42450</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Year  Selling_Price  Present_Price  Kms_Driven Fuel_Type Seller_Type  \\\n",
       "0  2014           3.35           5.59       27000    Petrol      Dealer   \n",
       "1  2013           4.75           9.54       43000    Diesel      Dealer   \n",
       "2  2017           7.25           9.85        6900    Petrol      Dealer   \n",
       "3  2011           2.85           4.15        5200    Petrol      Dealer   \n",
       "4  2014           4.60           6.87       42450    Diesel      Dealer   \n",
       "\n",
       "  Transmission  Owner  \n",
       "0       Manual      0  \n",
       "1       Manual      0  \n",
       "2       Manual      0  \n",
       "3       Manual      0  \n",
       "4       Manual      0  "
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "final_dataset.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "final_dataset['Current_Year']=2020"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "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>Year</th>\n",
       "      <th>Selling_Price</th>\n",
       "      <th>Present_Price</th>\n",
       "      <th>Kms_Driven</th>\n",
       "      <th>Fuel_Type</th>\n",
       "      <th>Seller_Type</th>\n",
       "      <th>Transmission</th>\n",
       "      <th>Owner</th>\n",
       "      <th>Current_Year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2014</td>\n",
       "      <td>3.35</td>\n",
       "      <td>5.59</td>\n",
       "      <td>27000</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2020</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2013</td>\n",
       "      <td>4.75</td>\n",
       "      <td>9.54</td>\n",
       "      <td>43000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2020</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2017</td>\n",
       "      <td>7.25</td>\n",
       "      <td>9.85</td>\n",
       "      <td>6900</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2020</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2011</td>\n",
       "      <td>2.85</td>\n",
       "      <td>4.15</td>\n",
       "      <td>5200</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2020</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2014</td>\n",
       "      <td>4.60</td>\n",
       "      <td>6.87</td>\n",
       "      <td>42450</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2020</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Year  Selling_Price  Present_Price  Kms_Driven Fuel_Type Seller_Type  \\\n",
       "0  2014           3.35           5.59       27000    Petrol      Dealer   \n",
       "1  2013           4.75           9.54       43000    Diesel      Dealer   \n",
       "2  2017           7.25           9.85        6900    Petrol      Dealer   \n",
       "3  2011           2.85           4.15        5200    Petrol      Dealer   \n",
       "4  2014           4.60           6.87       42450    Diesel      Dealer   \n",
       "\n",
       "  Transmission  Owner  Current_Year  \n",
       "0       Manual      0          2020  \n",
       "1       Manual      0          2020  \n",
       "2       Manual      0          2020  \n",
       "3       Manual      0          2020  \n",
       "4       Manual      0          2020  "
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "final_dataset.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "final_dataset['no_years']= final_dataset['Current_Year']-final_dataset['Year']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "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>Year</th>\n",
       "      <th>Selling_Price</th>\n",
       "      <th>Present_Price</th>\n",
       "      <th>Kms_Driven</th>\n",
       "      <th>Fuel_Type</th>\n",
       "      <th>Seller_Type</th>\n",
       "      <th>Transmission</th>\n",
       "      <th>Owner</th>\n",
       "      <th>Current_Year</th>\n",
       "      <th>no_years</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2014</td>\n",
       "      <td>3.35</td>\n",
       "      <td>5.59</td>\n",
       "      <td>27000</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2020</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2013</td>\n",
       "      <td>4.75</td>\n",
       "      <td>9.54</td>\n",
       "      <td>43000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2020</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2017</td>\n",
       "      <td>7.25</td>\n",
       "      <td>9.85</td>\n",
       "      <td>6900</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2020</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2011</td>\n",
       "      <td>2.85</td>\n",
       "      <td>4.15</td>\n",
       "      <td>5200</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2020</td>\n",
       "      <td>9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2014</td>\n",
       "      <td>4.60</td>\n",
       "      <td>6.87</td>\n",
       "      <td>42450</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2020</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Year  Selling_Price  Present_Price  Kms_Driven Fuel_Type Seller_Type  \\\n",
       "0  2014           3.35           5.59       27000    Petrol      Dealer   \n",
       "1  2013           4.75           9.54       43000    Diesel      Dealer   \n",
       "2  2017           7.25           9.85        6900    Petrol      Dealer   \n",
       "3  2011           2.85           4.15        5200    Petrol      Dealer   \n",
       "4  2014           4.60           6.87       42450    Diesel      Dealer   \n",
       "\n",
       "  Transmission  Owner  Current_Year  no_years  \n",
       "0       Manual      0          2020         6  \n",
       "1       Manual      0          2020         7  \n",
       "2       Manual      0          2020         3  \n",
       "3       Manual      0          2020         9  \n",
       "4       Manual      0          2020         6  "
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "final_dataset.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "final_dataset.drop('Year', axis=1, inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "final_dataset.drop('Current_Year', axis=1, inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "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>Selling_Price</th>\n",
       "      <th>Present_Price</th>\n",
       "      <th>Kms_Driven</th>\n",
       "      <th>Fuel_Type</th>\n",
       "      <th>Seller_Type</th>\n",
       "      <th>Transmission</th>\n",
       "      <th>Owner</th>\n",
       "      <th>no_years</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3.35</td>\n",
       "      <td>5.59</td>\n",
       "      <td>27000</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4.75</td>\n",
       "      <td>9.54</td>\n",
       "      <td>43000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>7.25</td>\n",
       "      <td>9.85</td>\n",
       "      <td>6900</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2.85</td>\n",
       "      <td>4.15</td>\n",
       "      <td>5200</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4.60</td>\n",
       "      <td>6.87</td>\n",
       "      <td>42450</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Selling_Price  Present_Price  Kms_Driven Fuel_Type Seller_Type  \\\n",
       "0           3.35           5.59       27000    Petrol      Dealer   \n",
       "1           4.75           9.54       43000    Diesel      Dealer   \n",
       "2           7.25           9.85        6900    Petrol      Dealer   \n",
       "3           2.85           4.15        5200    Petrol      Dealer   \n",
       "4           4.60           6.87       42450    Diesel      Dealer   \n",
       "\n",
       "  Transmission  Owner  no_years  \n",
       "0       Manual      0         6  \n",
       "1       Manual      0         7  \n",
       "2       Manual      0         3  \n",
       "3       Manual      0         9  \n",
       "4       Manual      0         6  "
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "final_dataset.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Convert category in one hot lable"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "final_dataset=pd.get_dummies(final_dataset,drop_first=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "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>Selling_Price</th>\n",
       "      <th>Present_Price</th>\n",
       "      <th>Kms_Driven</th>\n",
       "      <th>Owner</th>\n",
       "      <th>no_years</th>\n",
       "      <th>Fuel_Type_Diesel</th>\n",
       "      <th>Fuel_Type_Petrol</th>\n",
       "      <th>Seller_Type_Individual</th>\n",
       "      <th>Transmission_Manual</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3.35</td>\n",
       "      <td>5.59</td>\n",
       "      <td>27000</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4.75</td>\n",
       "      <td>9.54</td>\n",
       "      <td>43000</td>\n",
       "      <td>0</td>\n",
       "      <td>7</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>7.25</td>\n",
       "      <td>9.85</td>\n",
       "      <td>6900</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2.85</td>\n",
       "      <td>4.15</td>\n",
       "      <td>5200</td>\n",
       "      <td>0</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4.60</td>\n",
       "      <td>6.87</td>\n",
       "      <td>42450</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Selling_Price  Present_Price  Kms_Driven  Owner  no_years  \\\n",
       "0           3.35           5.59       27000      0         6   \n",
       "1           4.75           9.54       43000      0         7   \n",
       "2           7.25           9.85        6900      0         3   \n",
       "3           2.85           4.15        5200      0         9   \n",
       "4           4.60           6.87       42450      0         6   \n",
       "\n",
       "   Fuel_Type_Diesel  Fuel_Type_Petrol  Seller_Type_Individual  \\\n",
       "0                 0                 1                       0   \n",
       "1                 1                 0                       0   \n",
       "2                 0                 1                       0   \n",
       "3                 0                 1                       0   \n",
       "4                 1                 0                       0   \n",
       "\n",
       "   Transmission_Manual  \n",
       "0                    1  \n",
       "1                    1  \n",
       "2                    1  \n",
       "3                    1  \n",
       "4                    1  "
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "final_dataset.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "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>Selling_Price</th>\n",
       "      <th>Present_Price</th>\n",
       "      <th>Kms_Driven</th>\n",
       "      <th>Owner</th>\n",
       "      <th>no_years</th>\n",
       "      <th>Fuel_Type_Diesel</th>\n",
       "      <th>Fuel_Type_Petrol</th>\n",
       "      <th>Seller_Type_Individual</th>\n",
       "      <th>Transmission_Manual</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Selling_Price</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.878983</td>\n",
       "      <td>0.029187</td>\n",
       "      <td>-0.088344</td>\n",
       "      <td>-0.236141</td>\n",
       "      <td>0.552339</td>\n",
       "      <td>-0.540571</td>\n",
       "      <td>-0.550724</td>\n",
       "      <td>-0.367128</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Present_Price</th>\n",
       "      <td>0.878983</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.203647</td>\n",
       "      <td>0.008057</td>\n",
       "      <td>0.047584</td>\n",
       "      <td>0.473306</td>\n",
       "      <td>-0.465244</td>\n",
       "      <td>-0.512030</td>\n",
       "      <td>-0.348715</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Kms_Driven</th>\n",
       "      <td>0.029187</td>\n",
       "      <td>0.203647</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.089216</td>\n",
       "      <td>0.524342</td>\n",
       "      <td>0.172515</td>\n",
       "      <td>-0.172874</td>\n",
       "      <td>-0.101419</td>\n",
       "      <td>-0.162510</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Owner</th>\n",
       "      <td>-0.088344</td>\n",
       "      <td>0.008057</td>\n",
       "      <td>0.089216</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.182104</td>\n",
       "      <td>-0.053469</td>\n",
       "      <td>0.055687</td>\n",
       "      <td>0.124269</td>\n",
       "      <td>-0.050316</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>no_years</th>\n",
       "      <td>-0.236141</td>\n",
       "      <td>0.047584</td>\n",
       "      <td>0.524342</td>\n",
       "      <td>0.182104</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.064315</td>\n",
       "      <td>0.059959</td>\n",
       "      <td>0.039896</td>\n",
       "      <td>-0.000394</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Fuel_Type_Diesel</th>\n",
       "      <td>0.552339</td>\n",
       "      <td>0.473306</td>\n",
       "      <td>0.172515</td>\n",
       "      <td>-0.053469</td>\n",
       "      <td>-0.064315</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.979648</td>\n",
       "      <td>-0.350467</td>\n",
       "      <td>-0.098643</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Fuel_Type_Petrol</th>\n",
       "      <td>-0.540571</td>\n",
       "      <td>-0.465244</td>\n",
       "      <td>-0.172874</td>\n",
       "      <td>0.055687</td>\n",
       "      <td>0.059959</td>\n",
       "      <td>-0.979648</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.358321</td>\n",
       "      <td>0.091013</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Seller_Type_Individual</th>\n",
       "      <td>-0.550724</td>\n",
       "      <td>-0.512030</td>\n",
       "      <td>-0.101419</td>\n",
       "      <td>0.124269</td>\n",
       "      <td>0.039896</td>\n",
       "      <td>-0.350467</td>\n",
       "      <td>0.358321</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.063240</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Transmission_Manual</th>\n",
       "      <td>-0.367128</td>\n",
       "      <td>-0.348715</td>\n",
       "      <td>-0.162510</td>\n",
       "      <td>-0.050316</td>\n",
       "      <td>-0.000394</td>\n",
       "      <td>-0.098643</td>\n",
       "      <td>0.091013</td>\n",
       "      <td>0.063240</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                        Selling_Price  Present_Price  Kms_Driven     Owner  \\\n",
       "Selling_Price                1.000000       0.878983    0.029187 -0.088344   \n",
       "Present_Price                0.878983       1.000000    0.203647  0.008057   \n",
       "Kms_Driven                   0.029187       0.203647    1.000000  0.089216   \n",
       "Owner                       -0.088344       0.008057    0.089216  1.000000   \n",
       "no_years                    -0.236141       0.047584    0.524342  0.182104   \n",
       "Fuel_Type_Diesel             0.552339       0.473306    0.172515 -0.053469   \n",
       "Fuel_Type_Petrol            -0.540571      -0.465244   -0.172874  0.055687   \n",
       "Seller_Type_Individual      -0.550724      -0.512030   -0.101419  0.124269   \n",
       "Transmission_Manual         -0.367128      -0.348715   -0.162510 -0.050316   \n",
       "\n",
       "                        no_years  Fuel_Type_Diesel  Fuel_Type_Petrol  \\\n",
       "Selling_Price          -0.236141          0.552339         -0.540571   \n",
       "Present_Price           0.047584          0.473306         -0.465244   \n",
       "Kms_Driven              0.524342          0.172515         -0.172874   \n",
       "Owner                   0.182104         -0.053469          0.055687   \n",
       "no_years                1.000000         -0.064315          0.059959   \n",
       "Fuel_Type_Diesel       -0.064315          1.000000         -0.979648   \n",
       "Fuel_Type_Petrol        0.059959         -0.979648          1.000000   \n",
       "Seller_Type_Individual  0.039896         -0.350467          0.358321   \n",
       "Transmission_Manual    -0.000394         -0.098643          0.091013   \n",
       "\n",
       "                        Seller_Type_Individual  Transmission_Manual  \n",
       "Selling_Price                        -0.550724            -0.367128  \n",
       "Present_Price                        -0.512030            -0.348715  \n",
       "Kms_Driven                           -0.101419            -0.162510  \n",
       "Owner                                 0.124269            -0.050316  \n",
       "no_years                              0.039896            -0.000394  \n",
       "Fuel_Type_Diesel                     -0.350467            -0.098643  \n",
       "Fuel_Type_Petrol                      0.358321             0.091013  \n",
       "Seller_Type_Individual                1.000000             0.063240  \n",
       "Transmission_Manual                   0.063240             1.000000  "
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "final_dataset.corr()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.PairGrid at 0x1fa222e2488>"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1620x1620 with 90 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.pairplot(final_dataset)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1440x1440 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "corrmat=final_dataset.corr()\n",
    "top_corr_feature=corrmat.index\n",
    "plt.figure(figsize=(20,20))\n",
    "g= sns.heatmap(final_dataset[top_corr_feature].corr(),annot=True,cmap='RdYlGn')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "#independent and dependent feature\n",
    "\n",
    "x=final_dataset.iloc[:,1:]\n",
    "y=final_dataset.iloc[:,0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    3.35\n",
       "1    4.75\n",
       "2    7.25\n",
       "3    2.85\n",
       "4    4.60\n",
       "Name: Selling_Price, dtype: float64"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "ExtraTreesRegressor()"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "###Feature Importance\n",
    "\n",
    "from sklearn.ensemble import ExtraTreesRegressor\n",
    "model=ExtraTreesRegressor()\n",
    "model.fit(x,y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0.38425476 0.04378303 0.00046289 0.07201644 0.23086007 0.01147321\n",
      " 0.12544699 0.1317026 ]\n"
     ]
    }
   ],
   "source": [
    "print(model.feature_importances_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "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": [
    "#plot graph of feature importance \n",
    "\n",
    "feat_importances= pd.Series(model.feature_importances_, index=x.columns)\n",
    "feat_importances.nlargest(5).plot(kind='barh')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(210, 8)"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_train.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.ensemble import RandomForestRegressor\n",
    "rf_random=RandomForestRegressor()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [],
   "source": [
    "###Hyperparameter Tuning - Randomize search CV\n",
    "import numpy as np\n",
    "n_estimators=[int(x) for x in np.linspace(start=100, stop=1500, num=15)]\n",
    "# Number of features to consider at every split\n",
    "max_features = ['auto', 'sqrt']\n",
    "# Maximum number of levels in tree\n",
    "max_depth = [int(x) for x in np.linspace(5, 50, num = 10)]\n",
    "# max_depth.append(None)\n",
    "# Minimum number of samples required to split a node\n",
    "min_samples_split = [2, 5, 10, 15, 100]\n",
    "# Minimum number of samples required at each leaf node\n",
    "min_samples_leaf = [1, 2, 5, 10]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import RandomizedSearchCV"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'n_estimators': [100, 200, 300, 400, 500, 600, 700, 800, 900, 1000, 1100, 1200, 1300, 1400, 1500], 'max_features': ['auto', 'sqrt'], 'max_depth': [5, 10, 15, 20, 25, 30, 35, 40, 45, 50], 'min_samples_split': [2, 5, 10, 15, 100], 'min_samples_leaf': [1, 2, 5, 10]}\n"
     ]
    }
   ],
   "source": [
    "# Create the random grid\n",
    "random_grid = {'n_estimators': n_estimators,\n",
    "               'max_features': max_features,\n",
    "               'max_depth': max_depth,\n",
    "               'min_samples_split': min_samples_split,\n",
    "               'min_samples_leaf': min_samples_leaf}\n",
    "\n",
    "print(random_grid)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Use the random grid to search for best hyperparameters\n",
    "# First create the base model to tune\n",
    "rf = RandomForestRegressor()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Random search of parameters, using 3 fold cross validation, \n",
    "# search across 100 different combinations\n",
    "rf_random = RandomizedSearchCV(estimator = rf, param_distributions = random_grid,scoring='neg_mean_squared_error', n_iter = 15, cv = 5, verbose=2, random_state=42, n_jobs = 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Fitting 5 folds for each of 15 candidates, totalling 75 fits\n",
      "[CV] n_estimators=600, min_samples_split=10, min_samples_leaf=10, max_features=auto, max_depth=10 \n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=1)]: Using backend SequentialBackend with 1 concurrent workers.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[CV]  n_estimators=600, min_samples_split=10, min_samples_leaf=10, max_features=auto, max_depth=10, total=   2.3s\n",
      "[CV] n_estimators=600, min_samples_split=10, min_samples_leaf=10, max_features=auto, max_depth=10 \n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=1)]: Done   1 out of   1 | elapsed:    2.2s remaining:    0.0s\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[CV]  n_estimators=600, min_samples_split=10, min_samples_leaf=10, max_features=auto, max_depth=10, total=   2.0s\n",
      "[CV] n_estimators=600, min_samples_split=10, min_samples_leaf=10, max_features=auto, max_depth=10 \n",
      "[CV]  n_estimators=600, min_samples_split=10, min_samples_leaf=10, max_features=auto, max_depth=10, total=   1.8s\n",
      "[CV] n_estimators=600, min_samples_split=10, min_samples_leaf=10, max_features=auto, max_depth=10 \n",
      "[CV]  n_estimators=600, min_samples_split=10, min_samples_leaf=10, max_features=auto, max_depth=10, total=   1.9s\n",
      "[CV] n_estimators=600, min_samples_split=10, min_samples_leaf=10, max_features=auto, max_depth=10 \n",
      "[CV]  n_estimators=600, min_samples_split=10, min_samples_leaf=10, max_features=auto, max_depth=10, total=   1.8s\n",
      "[CV] n_estimators=600, min_samples_split=100, min_samples_leaf=10, max_features=sqrt, max_depth=45 \n",
      "[CV]  n_estimators=600, min_samples_split=100, min_samples_leaf=10, max_features=sqrt, max_depth=45, total=   1.7s\n",
      "[CV] n_estimators=600, min_samples_split=100, min_samples_leaf=10, max_features=sqrt, max_depth=45 \n",
      "[CV]  n_estimators=600, min_samples_split=100, min_samples_leaf=10, max_features=sqrt, max_depth=45, total=   1.7s\n",
      "[CV] n_estimators=600, min_samples_split=100, min_samples_leaf=10, max_features=sqrt, max_depth=45 \n",
      "[CV]  n_estimators=600, min_samples_split=100, min_samples_leaf=10, max_features=sqrt, max_depth=45, total=   1.7s\n",
      "[CV] n_estimators=600, min_samples_split=100, min_samples_leaf=10, max_features=sqrt, max_depth=45 \n",
      "[CV]  n_estimators=600, min_samples_split=100, min_samples_leaf=10, max_features=sqrt, max_depth=45, total=   1.9s\n",
      "[CV] n_estimators=600, min_samples_split=100, min_samples_leaf=10, max_features=sqrt, max_depth=45 \n",
      "[CV]  n_estimators=600, min_samples_split=100, min_samples_leaf=10, max_features=sqrt, max_depth=45, total=   1.8s\n",
      "[CV] n_estimators=700, min_samples_split=15, min_samples_leaf=2, max_features=sqrt, max_depth=45 \n",
      "[CV]  n_estimators=700, min_samples_split=15, min_samples_leaf=2, max_features=sqrt, max_depth=45, total=   2.1s\n",
      "[CV] n_estimators=700, min_samples_split=15, min_samples_leaf=2, max_features=sqrt, max_depth=45 \n",
      "[CV]  n_estimators=700, min_samples_split=15, min_samples_leaf=2, max_features=sqrt, max_depth=45, total=   1.9s\n",
      "[CV] n_estimators=700, min_samples_split=15, min_samples_leaf=2, max_features=sqrt, max_depth=45 \n",
      "[CV]  n_estimators=700, min_samples_split=15, min_samples_leaf=2, max_features=sqrt, max_depth=45, total=   2.1s\n",
      "[CV] n_estimators=700, min_samples_split=15, min_samples_leaf=2, max_features=sqrt, max_depth=45 \n",
      "[CV]  n_estimators=700, min_samples_split=15, min_samples_leaf=2, max_features=sqrt, max_depth=45, total=   2.1s\n",
      "[CV] n_estimators=700, min_samples_split=15, min_samples_leaf=2, max_features=sqrt, max_depth=45 \n",
      "[CV]  n_estimators=700, min_samples_split=15, min_samples_leaf=2, max_features=sqrt, max_depth=45, total=   2.6s\n",
      "[CV] n_estimators=200, min_samples_split=5, min_samples_leaf=2, max_features=sqrt, max_depth=45 \n",
      "[CV]  n_estimators=200, min_samples_split=5, min_samples_leaf=2, max_features=sqrt, max_depth=45, total=   0.9s\n",
      "[CV] n_estimators=200, min_samples_split=5, min_samples_leaf=2, max_features=sqrt, max_depth=45 \n",
      "[CV]  n_estimators=200, min_samples_split=5, min_samples_leaf=2, max_features=sqrt, max_depth=45, total=   0.7s\n",
      "[CV] n_estimators=200, min_samples_split=5, min_samples_leaf=2, max_features=sqrt, max_depth=45 \n",
      "[CV]  n_estimators=200, min_samples_split=5, min_samples_leaf=2, max_features=sqrt, max_depth=45, total=   0.6s\n",
      "[CV] n_estimators=200, min_samples_split=5, min_samples_leaf=2, max_features=sqrt, max_depth=45 \n",
      "[CV]  n_estimators=200, min_samples_split=5, min_samples_leaf=2, max_features=sqrt, max_depth=45, total=   0.6s\n",
      "[CV] n_estimators=200, min_samples_split=5, min_samples_leaf=2, max_features=sqrt, max_depth=45 \n",
      "[CV]  n_estimators=200, min_samples_split=5, min_samples_leaf=2, max_features=sqrt, max_depth=45, total=   0.6s\n",
      "[CV] n_estimators=800, min_samples_split=5, min_samples_leaf=5, max_features=auto, max_depth=35 \n",
      "[CV]  n_estimators=800, min_samples_split=5, min_samples_leaf=5, max_features=auto, max_depth=35, total=   2.7s\n",
      "[CV] n_estimators=800, min_samples_split=5, min_samples_leaf=5, max_features=auto, max_depth=35 \n",
      "[CV]  n_estimators=800, min_samples_split=5, min_samples_leaf=5, max_features=auto, max_depth=35, total=   2.4s\n",
      "[CV] n_estimators=800, min_samples_split=5, min_samples_leaf=5, max_features=auto, max_depth=35 \n",
      "[CV]  n_estimators=800, min_samples_split=5, min_samples_leaf=5, max_features=auto, max_depth=35, total=   2.5s\n",
      "[CV] n_estimators=800, min_samples_split=5, min_samples_leaf=5, max_features=auto, max_depth=35 \n",
      "[CV]  n_estimators=800, min_samples_split=5, min_samples_leaf=5, max_features=auto, max_depth=35, total=   2.5s\n",
      "[CV] n_estimators=800, min_samples_split=5, min_samples_leaf=5, max_features=auto, max_depth=35 \n",
      "[CV]  n_estimators=800, min_samples_split=5, min_samples_leaf=5, max_features=auto, max_depth=35, total=   2.5s\n",
      "[CV] n_estimators=300, min_samples_split=5, min_samples_leaf=2, max_features=auto, max_depth=30 \n",
      "[CV]  n_estimators=300, min_samples_split=5, min_samples_leaf=2, max_features=auto, max_depth=30, total=   1.0s\n",
      "[CV] n_estimators=300, min_samples_split=5, min_samples_leaf=2, max_features=auto, max_depth=30 \n",
      "[CV]  n_estimators=300, min_samples_split=5, min_samples_leaf=2, max_features=auto, max_depth=30, total=   1.3s\n",
      "[CV] n_estimators=300, min_samples_split=5, min_samples_leaf=2, max_features=auto, max_depth=30 \n",
      "[CV]  n_estimators=300, min_samples_split=5, min_samples_leaf=2, max_features=auto, max_depth=30, total=   1.3s\n",
      "[CV] n_estimators=300, min_samples_split=5, min_samples_leaf=2, max_features=auto, max_depth=30 \n",
      "[CV]  n_estimators=300, min_samples_split=5, min_samples_leaf=2, max_features=auto, max_depth=30, total=   1.1s\n",
      "[CV] n_estimators=300, min_samples_split=5, min_samples_leaf=2, max_features=auto, max_depth=30 \n",
      "[CV]  n_estimators=300, min_samples_split=5, min_samples_leaf=2, max_features=auto, max_depth=30, total=   1.3s\n",
      "[CV] n_estimators=500, min_samples_split=10, min_samples_leaf=1, max_features=sqrt, max_depth=50 \n",
      "[CV]  n_estimators=500, min_samples_split=10, min_samples_leaf=1, max_features=sqrt, max_depth=50, total=   1.9s\n",
      "[CV] n_estimators=500, min_samples_split=10, min_samples_leaf=1, max_features=sqrt, max_depth=50 \n",
      "[CV]  n_estimators=500, min_samples_split=10, min_samples_leaf=1, max_features=sqrt, max_depth=50, total=   2.3s\n",
      "[CV] n_estimators=500, min_samples_split=10, min_samples_leaf=1, max_features=sqrt, max_depth=50 \n",
      "[CV]  n_estimators=500, min_samples_split=10, min_samples_leaf=1, max_features=sqrt, max_depth=50, total=   1.9s\n",
      "[CV] n_estimators=500, min_samples_split=10, min_samples_leaf=1, max_features=sqrt, max_depth=50 \n",
      "[CV]  n_estimators=500, min_samples_split=10, min_samples_leaf=1, max_features=sqrt, max_depth=50, total=   1.5s\n",
      "[CV] n_estimators=500, min_samples_split=10, min_samples_leaf=1, max_features=sqrt, max_depth=50 \n",
      "[CV]  n_estimators=500, min_samples_split=10, min_samples_leaf=1, max_features=sqrt, max_depth=50, total=   1.7s\n",
      "[CV] n_estimators=200, min_samples_split=5, min_samples_leaf=5, max_features=sqrt, max_depth=5 \n",
      "[CV]  n_estimators=200, min_samples_split=5, min_samples_leaf=5, max_features=sqrt, max_depth=5, total=   0.6s\n",
      "[CV] n_estimators=200, min_samples_split=5, min_samples_leaf=5, max_features=sqrt, max_depth=5 \n",
      "[CV]  n_estimators=200, min_samples_split=5, min_samples_leaf=5, max_features=sqrt, max_depth=5, total=   0.6s\n",
      "[CV] n_estimators=200, min_samples_split=5, min_samples_leaf=5, max_features=sqrt, max_depth=5 \n",
      "[CV]  n_estimators=200, min_samples_split=5, min_samples_leaf=5, max_features=sqrt, max_depth=5, total=   0.6s\n",
      "[CV] n_estimators=200, min_samples_split=5, min_samples_leaf=5, max_features=sqrt, max_depth=5 \n",
      "[CV]  n_estimators=200, min_samples_split=5, min_samples_leaf=5, max_features=sqrt, max_depth=5, total=   0.7s\n",
      "[CV] n_estimators=200, min_samples_split=5, min_samples_leaf=5, max_features=sqrt, max_depth=5 \n",
      "[CV]  n_estimators=200, min_samples_split=5, min_samples_leaf=5, max_features=sqrt, max_depth=5, total=   0.6s\n",
      "[CV] n_estimators=1000, min_samples_split=2, min_samples_leaf=10, max_features=sqrt, max_depth=45 \n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[CV]  n_estimators=1000, min_samples_split=2, min_samples_leaf=10, max_features=sqrt, max_depth=45, total=   3.7s\n",
      "[CV] n_estimators=1000, min_samples_split=2, min_samples_leaf=10, max_features=sqrt, max_depth=45 \n",
      "[CV]  n_estimators=1000, min_samples_split=2, min_samples_leaf=10, max_features=sqrt, max_depth=45, total=   4.1s\n",
      "[CV] n_estimators=1000, min_samples_split=2, min_samples_leaf=10, max_features=sqrt, max_depth=45 \n",
      "[CV]  n_estimators=1000, min_samples_split=2, min_samples_leaf=10, max_features=sqrt, max_depth=45, total=   5.2s\n",
      "[CV] n_estimators=1000, min_samples_split=2, min_samples_leaf=10, max_features=sqrt, max_depth=45 \n",
      "[CV]  n_estimators=1000, min_samples_split=2, min_samples_leaf=10, max_features=sqrt, max_depth=45, total=   6.6s\n",
      "[CV] n_estimators=1000, min_samples_split=2, min_samples_leaf=10, max_features=sqrt, max_depth=45 \n",
      "[CV]  n_estimators=1000, min_samples_split=2, min_samples_leaf=10, max_features=sqrt, max_depth=45, total=   3.9s\n",
      "[CV] n_estimators=200, min_samples_split=2, min_samples_leaf=10, max_features=auto, max_depth=40 \n",
      "[CV]  n_estimators=200, min_samples_split=2, min_samples_leaf=10, max_features=auto, max_depth=40, total=   1.1s\n",
      "[CV] n_estimators=200, min_samples_split=2, min_samples_leaf=10, max_features=auto, max_depth=40 \n",
      "[CV]  n_estimators=200, min_samples_split=2, min_samples_leaf=10, max_features=auto, max_depth=40, total=   1.2s\n",
      "[CV] n_estimators=200, min_samples_split=2, min_samples_leaf=10, max_features=auto, max_depth=40 \n",
      "[CV]  n_estimators=200, min_samples_split=2, min_samples_leaf=10, max_features=auto, max_depth=40, total=   1.0s\n",
      "[CV] n_estimators=200, min_samples_split=2, min_samples_leaf=10, max_features=auto, max_depth=40 \n",
      "[CV]  n_estimators=200, min_samples_split=2, min_samples_leaf=10, max_features=auto, max_depth=40, total=   0.8s\n",
      "[CV] n_estimators=200, min_samples_split=2, min_samples_leaf=10, max_features=auto, max_depth=40 \n",
      "[CV]  n_estimators=200, min_samples_split=2, min_samples_leaf=10, max_features=auto, max_depth=40, total=   1.4s\n",
      "[CV] n_estimators=1400, min_samples_split=5, min_samples_leaf=5, max_features=auto, max_depth=50 \n",
      "[CV]  n_estimators=1400, min_samples_split=5, min_samples_leaf=5, max_features=auto, max_depth=50, total=   4.5s\n",
      "[CV] n_estimators=1400, min_samples_split=5, min_samples_leaf=5, max_features=auto, max_depth=50 \n",
      "[CV]  n_estimators=1400, min_samples_split=5, min_samples_leaf=5, max_features=auto, max_depth=50, total=   6.8s\n",
      "[CV] n_estimators=1400, min_samples_split=5, min_samples_leaf=5, max_features=auto, max_depth=50 \n",
      "[CV]  n_estimators=1400, min_samples_split=5, min_samples_leaf=5, max_features=auto, max_depth=50, total=   8.0s\n",
      "[CV] n_estimators=1400, min_samples_split=5, min_samples_leaf=5, max_features=auto, max_depth=50 \n",
      "[CV]  n_estimators=1400, min_samples_split=5, min_samples_leaf=5, max_features=auto, max_depth=50, total=   9.6s\n",
      "[CV] n_estimators=1400, min_samples_split=5, min_samples_leaf=5, max_features=auto, max_depth=50 \n",
      "[CV]  n_estimators=1400, min_samples_split=5, min_samples_leaf=5, max_features=auto, max_depth=50, total=   7.9s\n",
      "[CV] n_estimators=1000, min_samples_split=100, min_samples_leaf=2, max_features=sqrt, max_depth=30 \n",
      "[CV]  n_estimators=1000, min_samples_split=100, min_samples_leaf=2, max_features=sqrt, max_depth=30, total=   4.9s\n",
      "[CV] n_estimators=1000, min_samples_split=100, min_samples_leaf=2, max_features=sqrt, max_depth=30 \n",
      "[CV]  n_estimators=1000, min_samples_split=100, min_samples_leaf=2, max_features=sqrt, max_depth=30, total=   3.1s\n",
      "[CV] n_estimators=1000, min_samples_split=100, min_samples_leaf=2, max_features=sqrt, max_depth=30 \n",
      "[CV]  n_estimators=1000, min_samples_split=100, min_samples_leaf=2, max_features=sqrt, max_depth=30, total=   3.2s\n",
      "[CV] n_estimators=1000, min_samples_split=100, min_samples_leaf=2, max_features=sqrt, max_depth=30 \n",
      "[CV]  n_estimators=1000, min_samples_split=100, min_samples_leaf=2, max_features=sqrt, max_depth=30, total=   3.1s\n",
      "[CV] n_estimators=1000, min_samples_split=100, min_samples_leaf=2, max_features=sqrt, max_depth=30 \n",
      "[CV]  n_estimators=1000, min_samples_split=100, min_samples_leaf=2, max_features=sqrt, max_depth=30, total=   3.1s\n",
      "[CV] n_estimators=700, min_samples_split=5, min_samples_leaf=5, max_features=auto, max_depth=30 \n",
      "[CV]  n_estimators=700, min_samples_split=5, min_samples_leaf=5, max_features=auto, max_depth=30, total=   2.7s\n",
      "[CV] n_estimators=700, min_samples_split=5, min_samples_leaf=5, max_features=auto, max_depth=30 \n",
      "[CV]  n_estimators=700, min_samples_split=5, min_samples_leaf=5, max_features=auto, max_depth=30, total=   2.6s\n",
      "[CV] n_estimators=700, min_samples_split=5, min_samples_leaf=5, max_features=auto, max_depth=30 \n",
      "[CV]  n_estimators=700, min_samples_split=5, min_samples_leaf=5, max_features=auto, max_depth=30, total=   3.3s\n",
      "[CV] n_estimators=700, min_samples_split=5, min_samples_leaf=5, max_features=auto, max_depth=30 \n",
      "[CV]  n_estimators=700, min_samples_split=5, min_samples_leaf=5, max_features=auto, max_depth=30, total=   2.4s\n",
      "[CV] n_estimators=700, min_samples_split=5, min_samples_leaf=5, max_features=auto, max_depth=30 \n",
      "[CV]  n_estimators=700, min_samples_split=5, min_samples_leaf=5, max_features=auto, max_depth=30, total=   2.5s\n",
      "[CV] n_estimators=1000, min_samples_split=100, min_samples_leaf=5, max_features=sqrt, max_depth=25 \n",
      "[CV]  n_estimators=1000, min_samples_split=100, min_samples_leaf=5, max_features=sqrt, max_depth=25, total=   3.3s\n",
      "[CV] n_estimators=1000, min_samples_split=100, min_samples_leaf=5, max_features=sqrt, max_depth=25 \n",
      "[CV]  n_estimators=1000, min_samples_split=100, min_samples_leaf=5, max_features=sqrt, max_depth=25, total=   4.4s\n",
      "[CV] n_estimators=1000, min_samples_split=100, min_samples_leaf=5, max_features=sqrt, max_depth=25 \n",
      "[CV]  n_estimators=1000, min_samples_split=100, min_samples_leaf=5, max_features=sqrt, max_depth=25, total=   3.4s\n",
      "[CV] n_estimators=1000, min_samples_split=100, min_samples_leaf=5, max_features=sqrt, max_depth=25 \n",
      "[CV]  n_estimators=1000, min_samples_split=100, min_samples_leaf=5, max_features=sqrt, max_depth=25, total=   6.5s\n",
      "[CV] n_estimators=1000, min_samples_split=100, min_samples_leaf=5, max_features=sqrt, max_depth=25 \n",
      "[CV]  n_estimators=1000, min_samples_split=100, min_samples_leaf=5, max_features=sqrt, max_depth=25, total=   5.5s\n",
      "[CV] n_estimators=1100, min_samples_split=15, min_samples_leaf=2, max_features=auto, max_depth=5 \n",
      "[CV]  n_estimators=1100, min_samples_split=15, min_samples_leaf=2, max_features=auto, max_depth=5, total=   6.5s\n",
      "[CV] n_estimators=1100, min_samples_split=15, min_samples_leaf=2, max_features=auto, max_depth=5 \n",
      "[CV]  n_estimators=1100, min_samples_split=15, min_samples_leaf=2, max_features=auto, max_depth=5, total=   6.3s\n",
      "[CV] n_estimators=1100, min_samples_split=15, min_samples_leaf=2, max_features=auto, max_depth=5 \n",
      "[CV]  n_estimators=1100, min_samples_split=15, min_samples_leaf=2, max_features=auto, max_depth=5, total=   5.6s\n",
      "[CV] n_estimators=1100, min_samples_split=15, min_samples_leaf=2, max_features=auto, max_depth=5 \n",
      "[CV]  n_estimators=1100, min_samples_split=15, min_samples_leaf=2, max_features=auto, max_depth=5, total=   4.3s\n",
      "[CV] n_estimators=1100, min_samples_split=15, min_samples_leaf=2, max_features=auto, max_depth=5 \n",
      "[CV]  n_estimators=1100, min_samples_split=15, min_samples_leaf=2, max_features=auto, max_depth=5, total=   4.0s\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=1)]: Done  75 out of  75 | elapsed:  3.5min finished\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "RandomizedSearchCV(cv=5, estimator=RandomForestRegressor(), n_iter=15, n_jobs=1,\n",
       "                   param_distributions={'max_depth': [5, 10, 15, 20, 25, 30, 35,\n",
       "                                                      40, 45, 50],\n",
       "                                        'max_features': ['auto', 'sqrt'],\n",
       "                                        'min_samples_leaf': [1, 2, 5, 10],\n",
       "                                        'min_samples_split': [2, 5, 10, 15,\n",
       "                                                              100],\n",
       "                                        'n_estimators': [100, 200, 300, 400,\n",
       "                                                         500, 600, 700, 800,\n",
       "                                                         900, 1000, 1100, 1200,\n",
       "                                                         1300, 1400, 1500]},\n",
       "                   random_state=42, scoring='neg_mean_squared_error',\n",
       "                   verbose=2)"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rf_random.fit(x_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'n_estimators': 300,\n",
       " 'min_samples_split': 5,\n",
       " 'min_samples_leaf': 2,\n",
       " 'max_features': 'auto',\n",
       " 'max_depth': 30}"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rf_random.best_params_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "-2.5780482010893526"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rf_random.best_score_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [],
   "source": [
    "predictions=rf_random.predict(x_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x1fa29007748>"
      ]
     },
     "execution_count": 44,
     "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.distplot(y_test-predictions)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0x1fa27b50b48>"
      ]
     },
     "execution_count": 45,
     "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": [
    "plt.scatter(y_test,predictions)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MAE: 0.6826175333681378\n",
      "MSE: 3.719937814909894\n",
      "RMSE: 1.928714031397577\n"
     ]
    }
   ],
   "source": [
    "from sklearn import metrics\n",
    "print('MAE:', metrics.mean_absolute_error(y_test, predictions))\n",
    "print('MSE:', metrics.mean_squared_error(y_test, predictions))\n",
    "print('RMSE:', np.sqrt(metrics.mean_squared_error(y_test, predictions)))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle\n",
    "# open a file, where you ant to store the data\n",
    "file = open('random_forest_regression_model.pkl', 'wb')\n",
    "\n",
    "# dump information to that file\n",
    "pickle.dump(rf_random, file)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}