Car Price Prediction.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "ff65fc83",
   "metadata": {},
   "source": [
    "## <u>About the Dataset</u>\n",
    "\n",
    "* The data contains various details and attributes associated with the old car. \n",
    "\n",
    "## <u>Data source</u>\n",
    "* Kaggle \n",
    "## <u>Problem Statement</u>\n",
    "* To predict the used car price, it's a regression Problem "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9d20c800",
   "metadata": {},
   "source": [
    "#### Importing the libraries "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "321ace6e",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd # for DataFrame \n",
    "import numpy as np # for Linear algebra \n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "from sklearn.preprocessing import OrdinalEncoder,OneHotEncoder\n",
    "from sklearn.impute import SimpleImputer"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "eeac9acc",
   "metadata": {},
   "source": [
    "#### Importing Dataset \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "1f01651b",
   "metadata": {},
   "outputs": [],
   "source": [
    "df=pd.read_csv('train.csv',parse_dates=['Year'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "273e962c",
   "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>Unnamed: 0</th>\n",
       "      <th>Name</th>\n",
       "      <th>Location</th>\n",
       "      <th>Year</th>\n",
       "      <th>Kilometers_Driven</th>\n",
       "      <th>Fuel_Type</th>\n",
       "      <th>Transmission</th>\n",
       "      <th>Owner_Type</th>\n",
       "      <th>Mileage</th>\n",
       "      <th>Engine</th>\n",
       "      <th>Power</th>\n",
       "      <th>Seats</th>\n",
       "      <th>New_Price</th>\n",
       "      <th>Price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>Hyundai Creta 1.6 CRDi SX Option</td>\n",
       "      <td>Pune</td>\n",
       "      <td>2015-01-01</td>\n",
       "      <td>41000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>19.67 kmpl</td>\n",
       "      <td>1582 CC</td>\n",
       "      <td>126.2 bhp</td>\n",
       "      <td>5.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>12.50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>Honda Jazz V</td>\n",
       "      <td>Chennai</td>\n",
       "      <td>2011-01-01</td>\n",
       "      <td>46000</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>13 km/kg</td>\n",
       "      <td>1199 CC</td>\n",
       "      <td>88.7 bhp</td>\n",
       "      <td>5.0</td>\n",
       "      <td>8.61 Lakh</td>\n",
       "      <td>4.50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>Maruti Ertiga VDI</td>\n",
       "      <td>Chennai</td>\n",
       "      <td>2012-01-01</td>\n",
       "      <td>87000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>20.77 kmpl</td>\n",
       "      <td>1248 CC</td>\n",
       "      <td>88.76 bhp</td>\n",
       "      <td>7.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>Audi A4 New 2.0 TDI Multitronic</td>\n",
       "      <td>Coimbatore</td>\n",
       "      <td>2013-01-01</td>\n",
       "      <td>40670</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Automatic</td>\n",
       "      <td>Second</td>\n",
       "      <td>15.2 kmpl</td>\n",
       "      <td>1968 CC</td>\n",
       "      <td>140.8 bhp</td>\n",
       "      <td>5.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>17.74</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>6</td>\n",
       "      <td>Nissan Micra Diesel XV</td>\n",
       "      <td>Jaipur</td>\n",
       "      <td>2013-01-01</td>\n",
       "      <td>86999</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>23.08 kmpl</td>\n",
       "      <td>1461 CC</td>\n",
       "      <td>63.1 bhp</td>\n",
       "      <td>5.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.50</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Unnamed: 0                              Name    Location       Year  \\\n",
       "0           1  Hyundai Creta 1.6 CRDi SX Option        Pune 2015-01-01   \n",
       "1           2                      Honda Jazz V     Chennai 2011-01-01   \n",
       "2           3                 Maruti Ertiga VDI     Chennai 2012-01-01   \n",
       "3           4   Audi A4 New 2.0 TDI Multitronic  Coimbatore 2013-01-01   \n",
       "4           6            Nissan Micra Diesel XV      Jaipur 2013-01-01   \n",
       "\n",
       "   Kilometers_Driven Fuel_Type Transmission Owner_Type     Mileage   Engine  \\\n",
       "0              41000    Diesel       Manual      First  19.67 kmpl  1582 CC   \n",
       "1              46000    Petrol       Manual      First    13 km/kg  1199 CC   \n",
       "2              87000    Diesel       Manual      First  20.77 kmpl  1248 CC   \n",
       "3              40670    Diesel    Automatic     Second   15.2 kmpl  1968 CC   \n",
       "4              86999    Diesel       Manual      First  23.08 kmpl  1461 CC   \n",
       "\n",
       "       Power  Seats  New_Price  Price  \n",
       "0  126.2 bhp    5.0        NaN  12.50  \n",
       "1   88.7 bhp    5.0  8.61 Lakh   4.50  \n",
       "2  88.76 bhp    7.0        NaN   6.00  \n",
       "3  140.8 bhp    5.0        NaN  17.74  \n",
       "4   63.1 bhp    5.0        NaN   3.50  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "3b4c77ac",
   "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>Unnamed: 0</th>\n",
       "      <th>Name</th>\n",
       "      <th>Location</th>\n",
       "      <th>Year</th>\n",
       "      <th>Kilometers_Driven</th>\n",
       "      <th>Fuel_Type</th>\n",
       "      <th>Transmission</th>\n",
       "      <th>Owner_Type</th>\n",
       "      <th>Mileage</th>\n",
       "      <th>Engine</th>\n",
       "      <th>Power</th>\n",
       "      <th>Seats</th>\n",
       "      <th>New_Price</th>\n",
       "      <th>Price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>5137</th>\n",
       "      <td>5286</td>\n",
       "      <td>BMW 3 Series 320d Corporate Edition</td>\n",
       "      <td>Chennai</td>\n",
       "      <td>2008-01-01</td>\n",
       "      <td>89000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Automatic</td>\n",
       "      <td>Second</td>\n",
       "      <td>16.07 kmpl</td>\n",
       "      <td>1995 CC</td>\n",
       "      <td>181 bhp</td>\n",
       "      <td>4.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6.30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3213</th>\n",
       "      <td>3317</td>\n",
       "      <td>Toyota Fortuner 4x2 AT</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>2014-01-01</td>\n",
       "      <td>89540</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Automatic</td>\n",
       "      <td>First</td>\n",
       "      <td>12.55 kmpl</td>\n",
       "      <td>2982 CC</td>\n",
       "      <td>168.5 bhp</td>\n",
       "      <td>7.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>16.80</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4856</th>\n",
       "      <td>5000</td>\n",
       "      <td>Toyota Etios Liva GD SP</td>\n",
       "      <td>Hyderabad</td>\n",
       "      <td>2015-01-01</td>\n",
       "      <td>69189</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>23.59 kmpl</td>\n",
       "      <td>1364 CC</td>\n",
       "      <td>67.06 bhp</td>\n",
       "      <td>5.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>5.30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1603</th>\n",
       "      <td>1655</td>\n",
       "      <td>Skoda Superb Elegance 1.8 TSI AT</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>2014-01-01</td>\n",
       "      <td>80000</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Automatic</td>\n",
       "      <td>First</td>\n",
       "      <td>13.7 kmpl</td>\n",
       "      <td>1798 CC</td>\n",
       "      <td>157.75 bhp</td>\n",
       "      <td>5.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>10.75</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2788</th>\n",
       "      <td>2877</td>\n",
       "      <td>Tata Tigor 1.05 Revotorq XZ Option</td>\n",
       "      <td>Kochi</td>\n",
       "      <td>2019-01-01</td>\n",
       "      <td>29279</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>24.7 kmpl</td>\n",
       "      <td>1047 CC</td>\n",
       "      <td>69 bhp</td>\n",
       "      <td>5.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>7.46</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      Unnamed: 0                                 Name   Location       Year  \\\n",
       "5137        5286  BMW 3 Series 320d Corporate Edition    Chennai 2008-01-01   \n",
       "3213        3317               Toyota Fortuner 4x2 AT      Delhi 2014-01-01   \n",
       "4856        5000              Toyota Etios Liva GD SP  Hyderabad 2015-01-01   \n",
       "1603        1655     Skoda Superb Elegance 1.8 TSI AT      Delhi 2014-01-01   \n",
       "2788        2877   Tata Tigor 1.05 Revotorq XZ Option      Kochi 2019-01-01   \n",
       "\n",
       "      Kilometers_Driven Fuel_Type Transmission Owner_Type     Mileage  \\\n",
       "5137              89000    Diesel    Automatic     Second  16.07 kmpl   \n",
       "3213              89540    Diesel    Automatic      First  12.55 kmpl   \n",
       "4856              69189    Diesel       Manual      First  23.59 kmpl   \n",
       "1603              80000    Petrol    Automatic      First   13.7 kmpl   \n",
       "2788              29279    Diesel       Manual      First   24.7 kmpl   \n",
       "\n",
       "       Engine       Power  Seats New_Price  Price  \n",
       "5137  1995 CC     181 bhp    4.0       NaN   6.30  \n",
       "3213  2982 CC   168.5 bhp    7.0       NaN  16.80  \n",
       "4856  1364 CC   67.06 bhp    5.0       NaN   5.30  \n",
       "1603  1798 CC  157.75 bhp    5.0       NaN  10.75  \n",
       "2788  1047 CC      69 bhp    5.0       NaN   7.46  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.sample(5)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8f79802a",
   "metadata": {},
   "source": [
    "### <u>Steps</u>\n",
    "\n",
    "* Basic details of Dataset\n",
    "* EDA \n",
    "* Feature Engineering and selection\n",
    "* Model Training"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3b624d41",
   "metadata": {},
   "source": [
    "#### Checking the data size"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "6f4706be",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(5847, 14)"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0a727179",
   "metadata": {},
   "source": [
    "####  Checking the inforamation of the columns "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "1f033d25",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 5847 entries, 0 to 5846\n",
      "Data columns (total 14 columns):\n",
      " #   Column             Non-Null Count  Dtype         \n",
      "---  ------             --------------  -----         \n",
      " 0   Unnamed: 0         5847 non-null   int64         \n",
      " 1   Name               5847 non-null   object        \n",
      " 2   Location           5847 non-null   object        \n",
      " 3   Year               5847 non-null   datetime64[ns]\n",
      " 4   Kilometers_Driven  5847 non-null   int64         \n",
      " 5   Fuel_Type          5847 non-null   object        \n",
      " 6   Transmission       5847 non-null   object        \n",
      " 7   Owner_Type         5847 non-null   object        \n",
      " 8   Mileage            5845 non-null   object        \n",
      " 9   Engine             5811 non-null   object        \n",
      " 10  Power              5811 non-null   object        \n",
      " 11  Seats              5809 non-null   float64       \n",
      " 12  New_Price          815 non-null    object        \n",
      " 13  Price              5847 non-null   float64       \n",
      "dtypes: datetime64[ns](1), float64(2), int64(2), object(9)\n",
      "memory usage: 639.6+ KB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cf245f15",
   "metadata": {},
   "source": [
    "#### Checking if there are any missing data in the dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "12b3e4e5",
   "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>False</th>\n",
       "      <th>True</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Unnamed: 0</th>\n",
       "      <td>5847.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Name</th>\n",
       "      <td>5847.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Location</th>\n",
       "      <td>5847.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Year</th>\n",
       "      <td>5847.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Kilometers_Driven</th>\n",
       "      <td>5847.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Fuel_Type</th>\n",
       "      <td>5847.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Transmission</th>\n",
       "      <td>5847.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Owner_Type</th>\n",
       "      <td>5847.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Mileage</th>\n",
       "      <td>5845.0</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Engine</th>\n",
       "      <td>5811.0</td>\n",
       "      <td>36.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Power</th>\n",
       "      <td>5811.0</td>\n",
       "      <td>36.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Seats</th>\n",
       "      <td>5809.0</td>\n",
       "      <td>38.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>New_Price</th>\n",
       "      <td>815.0</td>\n",
       "      <td>5032.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Price</th>\n",
       "      <td>5847.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                    False   True \n",
       "Unnamed: 0         5847.0     NaN\n",
       "Name               5847.0     NaN\n",
       "Location           5847.0     NaN\n",
       "Year               5847.0     NaN\n",
       "Kilometers_Driven  5847.0     NaN\n",
       "Fuel_Type          5847.0     NaN\n",
       "Transmission       5847.0     NaN\n",
       "Owner_Type         5847.0     NaN\n",
       "Mileage            5845.0     2.0\n",
       "Engine             5811.0    36.0\n",
       "Power              5811.0    36.0\n",
       "Seats              5809.0    38.0\n",
       "New_Price           815.0  5032.0\n",
       "Price              5847.0     NaN"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isna().apply(pd.value_counts).T"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "52abb80d",
   "metadata": {},
   "source": [
    "#### <u> Observation</u>\n",
    "\n",
    "* In \"New_Price\" column 86% data is missing \n",
    "* \"Unnamed: 0\" is not useful for the analysis "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3b8724a1",
   "metadata": {},
   "source": [
    "#### Checking if is there any duplicate data in the dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "e918f269",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.duplicated().sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b1bd4585",
   "metadata": {},
   "source": [
    "#### How the data is looking mathematically"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "b7fdbc85",
   "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>Unnamed: 0</th>\n",
       "      <th>Kilometers_Driven</th>\n",
       "      <th>Seats</th>\n",
       "      <th>Price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>5847.000000</td>\n",
       "      <td>5.847000e+03</td>\n",
       "      <td>5809.000000</td>\n",
       "      <td>5847.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>3013.181461</td>\n",
       "      <td>5.841013e+04</td>\n",
       "      <td>5.286452</td>\n",
       "      <td>9.653742</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>1736.398890</td>\n",
       "      <td>9.237971e+04</td>\n",
       "      <td>0.806668</td>\n",
       "      <td>11.275966</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.710000e+02</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>0.440000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>1509.500000</td>\n",
       "      <td>3.346750e+04</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>3.550000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>3015.000000</td>\n",
       "      <td>5.257600e+04</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>5.750000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>4517.500000</td>\n",
       "      <td>7.249050e+04</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>10.250000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>6018.000000</td>\n",
       "      <td>6.500000e+06</td>\n",
       "      <td>10.000000</td>\n",
       "      <td>160.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        Unnamed: 0  Kilometers_Driven        Seats        Price\n",
       "count  5847.000000       5.847000e+03  5809.000000  5847.000000\n",
       "mean   3013.181461       5.841013e+04     5.286452     9.653742\n",
       "std    1736.398890       9.237971e+04     0.806668    11.275966\n",
       "min       1.000000       1.710000e+02     2.000000     0.440000\n",
       "25%    1509.500000       3.346750e+04     5.000000     3.550000\n",
       "50%    3015.000000       5.257600e+04     5.000000     5.750000\n",
       "75%    4517.500000       7.249050e+04     5.000000    10.250000\n",
       "max    6018.000000       6.500000e+06    10.000000   160.000000"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ed46cf06",
   "metadata": {},
   "source": [
    "#### Performing EDA "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "6ce7f461",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.drop(['Unnamed: 0','New_Price'],axis=1,inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "815ce9ac",
   "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>Name</th>\n",
       "      <th>Location</th>\n",
       "      <th>Year</th>\n",
       "      <th>Kilometers_Driven</th>\n",
       "      <th>Fuel_Type</th>\n",
       "      <th>Transmission</th>\n",
       "      <th>Owner_Type</th>\n",
       "      <th>Mileage</th>\n",
       "      <th>Engine</th>\n",
       "      <th>Power</th>\n",
       "      <th>Seats</th>\n",
       "      <th>Price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Hyundai Creta 1.6 CRDi SX Option</td>\n",
       "      <td>Pune</td>\n",
       "      <td>2015-01-01</td>\n",
       "      <td>41000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>19.67 kmpl</td>\n",
       "      <td>1582 CC</td>\n",
       "      <td>126.2 bhp</td>\n",
       "      <td>5.0</td>\n",
       "      <td>12.50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Honda Jazz V</td>\n",
       "      <td>Chennai</td>\n",
       "      <td>2011-01-01</td>\n",
       "      <td>46000</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>13 km/kg</td>\n",
       "      <td>1199 CC</td>\n",
       "      <td>88.7 bhp</td>\n",
       "      <td>5.0</td>\n",
       "      <td>4.50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Maruti Ertiga VDI</td>\n",
       "      <td>Chennai</td>\n",
       "      <td>2012-01-01</td>\n",
       "      <td>87000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>20.77 kmpl</td>\n",
       "      <td>1248 CC</td>\n",
       "      <td>88.76 bhp</td>\n",
       "      <td>7.0</td>\n",
       "      <td>6.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Audi A4 New 2.0 TDI Multitronic</td>\n",
       "      <td>Coimbatore</td>\n",
       "      <td>2013-01-01</td>\n",
       "      <td>40670</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Automatic</td>\n",
       "      <td>Second</td>\n",
       "      <td>15.2 kmpl</td>\n",
       "      <td>1968 CC</td>\n",
       "      <td>140.8 bhp</td>\n",
       "      <td>5.0</td>\n",
       "      <td>17.74</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Nissan Micra Diesel XV</td>\n",
       "      <td>Jaipur</td>\n",
       "      <td>2013-01-01</td>\n",
       "      <td>86999</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>23.08 kmpl</td>\n",
       "      <td>1461 CC</td>\n",
       "      <td>63.1 bhp</td>\n",
       "      <td>5.0</td>\n",
       "      <td>3.50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5842</th>\n",
       "      <td>Maruti Swift VDI</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>2014-01-01</td>\n",
       "      <td>27365</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>28.4 kmpl</td>\n",
       "      <td>1248 CC</td>\n",
       "      <td>74 bhp</td>\n",
       "      <td>5.0</td>\n",
       "      <td>4.75</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5843</th>\n",
       "      <td>Hyundai Xcent 1.1 CRDi S</td>\n",
       "      <td>Jaipur</td>\n",
       "      <td>2015-01-01</td>\n",
       "      <td>100000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>24.4 kmpl</td>\n",
       "      <td>1120 CC</td>\n",
       "      <td>71 bhp</td>\n",
       "      <td>5.0</td>\n",
       "      <td>4.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5844</th>\n",
       "      <td>Mahindra Xylo D4 BSIV</td>\n",
       "      <td>Jaipur</td>\n",
       "      <td>2012-01-01</td>\n",
       "      <td>55000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>Second</td>\n",
       "      <td>14.0 kmpl</td>\n",
       "      <td>2498 CC</td>\n",
       "      <td>112 bhp</td>\n",
       "      <td>8.0</td>\n",
       "      <td>2.90</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5845</th>\n",
       "      <td>Maruti Wagon R VXI</td>\n",
       "      <td>Kolkata</td>\n",
       "      <td>2013-01-01</td>\n",
       "      <td>46000</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>18.9 kmpl</td>\n",
       "      <td>998 CC</td>\n",
       "      <td>67.1 bhp</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2.65</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5846</th>\n",
       "      <td>Chevrolet Beat Diesel</td>\n",
       "      <td>Hyderabad</td>\n",
       "      <td>2011-01-01</td>\n",
       "      <td>47000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>25.44 kmpl</td>\n",
       "      <td>936 CC</td>\n",
       "      <td>57.6 bhp</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2.50</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5847 rows × 12 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                  Name    Location       Year  \\\n",
       "0     Hyundai Creta 1.6 CRDi SX Option        Pune 2015-01-01   \n",
       "1                         Honda Jazz V     Chennai 2011-01-01   \n",
       "2                    Maruti Ertiga VDI     Chennai 2012-01-01   \n",
       "3      Audi A4 New 2.0 TDI Multitronic  Coimbatore 2013-01-01   \n",
       "4               Nissan Micra Diesel XV      Jaipur 2013-01-01   \n",
       "...                                ...         ...        ...   \n",
       "5842                  Maruti Swift VDI       Delhi 2014-01-01   \n",
       "5843          Hyundai Xcent 1.1 CRDi S      Jaipur 2015-01-01   \n",
       "5844             Mahindra Xylo D4 BSIV      Jaipur 2012-01-01   \n",
       "5845                Maruti Wagon R VXI     Kolkata 2013-01-01   \n",
       "5846             Chevrolet Beat Diesel   Hyderabad 2011-01-01   \n",
       "\n",
       "      Kilometers_Driven Fuel_Type Transmission Owner_Type     Mileage  \\\n",
       "0                 41000    Diesel       Manual      First  19.67 kmpl   \n",
       "1                 46000    Petrol       Manual      First    13 km/kg   \n",
       "2                 87000    Diesel       Manual      First  20.77 kmpl   \n",
       "3                 40670    Diesel    Automatic     Second   15.2 kmpl   \n",
       "4                 86999    Diesel       Manual      First  23.08 kmpl   \n",
       "...                 ...       ...          ...        ...         ...   \n",
       "5842              27365    Diesel       Manual      First   28.4 kmpl   \n",
       "5843             100000    Diesel       Manual      First   24.4 kmpl   \n",
       "5844              55000    Diesel       Manual     Second   14.0 kmpl   \n",
       "5845              46000    Petrol       Manual      First   18.9 kmpl   \n",
       "5846              47000    Diesel       Manual      First  25.44 kmpl   \n",
       "\n",
       "       Engine      Power  Seats  Price  \n",
       "0     1582 CC  126.2 bhp    5.0  12.50  \n",
       "1     1199 CC   88.7 bhp    5.0   4.50  \n",
       "2     1248 CC  88.76 bhp    7.0   6.00  \n",
       "3     1968 CC  140.8 bhp    5.0  17.74  \n",
       "4     1461 CC   63.1 bhp    5.0   3.50  \n",
       "...       ...        ...    ...    ...  \n",
       "5842  1248 CC     74 bhp    5.0   4.75  \n",
       "5843  1120 CC     71 bhp    5.0   4.00  \n",
       "5844  2498 CC    112 bhp    8.0   2.90  \n",
       "5845   998 CC   67.1 bhp    5.0   2.65  \n",
       "5846   936 CC   57.6 bhp    5.0   2.50  \n",
       "\n",
       "[5847 rows x 12 columns]"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "20d8397a",
   "metadata": {},
   "source": [
    "#### Treating Mixed value Columns "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "7e692679",
   "metadata": {},
   "outputs": [],
   "source": [
    "df['Mileage_num']=df['Mileage'].str.split(\" \",expand=True)[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "82127ed4",
   "metadata": {},
   "outputs": [],
   "source": [
    "df['Mileage_cat']=df['Mileage'].str.split(' ',expand=True)[1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "c862fdf4",
   "metadata": {},
   "outputs": [],
   "source": [
    "df['Engine_num']=df['Engine'].str.split(' ',expand=True)[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "32acc150",
   "metadata": {},
   "outputs": [],
   "source": [
    "df['Engine_cat']=df['Engine'].str.split(' ',expand=True)[1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "6997e1ca",
   "metadata": {},
   "outputs": [],
   "source": [
    "df['Power_num']=df['Power'].str.split(' ',expand=True)[0]\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "c7e63b06",
   "metadata": {},
   "outputs": [],
   "source": [
    "df['Power_cat']=df['Power'].str.split(' ',expand=True)[1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "b743ef85",
   "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>Name</th>\n",
       "      <th>Location</th>\n",
       "      <th>Year</th>\n",
       "      <th>Kilometers_Driven</th>\n",
       "      <th>Fuel_Type</th>\n",
       "      <th>Transmission</th>\n",
       "      <th>Owner_Type</th>\n",
       "      <th>Mileage</th>\n",
       "      <th>Engine</th>\n",
       "      <th>Power</th>\n",
       "      <th>Seats</th>\n",
       "      <th>Price</th>\n",
       "      <th>Mileage_num</th>\n",
       "      <th>Mileage_cat</th>\n",
       "      <th>Engine_num</th>\n",
       "      <th>Engine_cat</th>\n",
       "      <th>Power_num</th>\n",
       "      <th>Power_cat</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>5472</th>\n",
       "      <td>Maruti Swift Dzire VDI</td>\n",
       "      <td>Hyderabad</td>\n",
       "      <td>2015-01-01</td>\n",
       "      <td>59572</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>26.59 kmpl</td>\n",
       "      <td>1248 CC</td>\n",
       "      <td>74 bhp</td>\n",
       "      <td>5.0</td>\n",
       "      <td>6.85</td>\n",
       "      <td>26.59</td>\n",
       "      <td>kmpl</td>\n",
       "      <td>1248</td>\n",
       "      <td>CC</td>\n",
       "      <td>74</td>\n",
       "      <td>bhp</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4862</th>\n",
       "      <td>Maruti Swift VDI BSIV</td>\n",
       "      <td>Chennai</td>\n",
       "      <td>2013-01-01</td>\n",
       "      <td>87192</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>25.2 kmpl</td>\n",
       "      <td>1248 CC</td>\n",
       "      <td>74 bhp</td>\n",
       "      <td>5.0</td>\n",
       "      <td>4.35</td>\n",
       "      <td>25.2</td>\n",
       "      <td>kmpl</td>\n",
       "      <td>1248</td>\n",
       "      <td>CC</td>\n",
       "      <td>74</td>\n",
       "      <td>bhp</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>231</th>\n",
       "      <td>Chevrolet Beat Diesel LT</td>\n",
       "      <td>Mumbai</td>\n",
       "      <td>2013-01-01</td>\n",
       "      <td>74000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>25.44 kmpl</td>\n",
       "      <td>936 CC</td>\n",
       "      <td>57.6 bhp</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2.65</td>\n",
       "      <td>25.44</td>\n",
       "      <td>kmpl</td>\n",
       "      <td>936</td>\n",
       "      <td>CC</td>\n",
       "      <td>57.6</td>\n",
       "      <td>bhp</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4472</th>\n",
       "      <td>Maruti Zen LXi - BS III</td>\n",
       "      <td>Hyderabad</td>\n",
       "      <td>2006-01-01</td>\n",
       "      <td>80000</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Manual</td>\n",
       "      <td>Second</td>\n",
       "      <td>17.3 kmpl</td>\n",
       "      <td>993 CC</td>\n",
       "      <td>60 bhp</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1.20</td>\n",
       "      <td>17.3</td>\n",
       "      <td>kmpl</td>\n",
       "      <td>993</td>\n",
       "      <td>CC</td>\n",
       "      <td>60</td>\n",
       "      <td>bhp</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5703</th>\n",
       "      <td>Maruti Swift VDI</td>\n",
       "      <td>Pune</td>\n",
       "      <td>2014-01-01</td>\n",
       "      <td>84000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>22.9 kmpl</td>\n",
       "      <td>1248 CC</td>\n",
       "      <td>74 bhp</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.25</td>\n",
       "      <td>22.9</td>\n",
       "      <td>kmpl</td>\n",
       "      <td>1248</td>\n",
       "      <td>CC</td>\n",
       "      <td>74</td>\n",
       "      <td>bhp</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                          Name   Location       Year  Kilometers_Driven  \\\n",
       "5472    Maruti Swift Dzire VDI  Hyderabad 2015-01-01              59572   \n",
       "4862     Maruti Swift VDI BSIV    Chennai 2013-01-01              87192   \n",
       "231   Chevrolet Beat Diesel LT     Mumbai 2013-01-01              74000   \n",
       "4472   Maruti Zen LXi - BS III  Hyderabad 2006-01-01              80000   \n",
       "5703          Maruti Swift VDI       Pune 2014-01-01              84000   \n",
       "\n",
       "     Fuel_Type Transmission Owner_Type     Mileage   Engine     Power  Seats  \\\n",
       "5472    Diesel       Manual      First  26.59 kmpl  1248 CC    74 bhp    5.0   \n",
       "4862    Diesel       Manual      First   25.2 kmpl  1248 CC    74 bhp    5.0   \n",
       "231     Diesel       Manual      First  25.44 kmpl   936 CC  57.6 bhp    5.0   \n",
       "4472    Petrol       Manual     Second   17.3 kmpl   993 CC    60 bhp    5.0   \n",
       "5703    Diesel       Manual      First   22.9 kmpl  1248 CC    74 bhp    5.0   \n",
       "\n",
       "      Price Mileage_num Mileage_cat Engine_num Engine_cat Power_num Power_cat  \n",
       "5472   6.85       26.59        kmpl       1248         CC        74       bhp  \n",
       "4862   4.35        25.2        kmpl       1248         CC        74       bhp  \n",
       "231    2.65       25.44        kmpl        936         CC      57.6       bhp  \n",
       "4472   1.20        17.3        kmpl        993         CC        60       bhp  \n",
       "5703   5.25        22.9        kmpl       1248         CC        74       bhp  "
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.sample(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "ec135d60",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "kmpl     5842\n",
       "km/kg       3\n",
       "Name: Mileage_cat, dtype: int64"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Mileage_cat'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "59cc08fe",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "CC    5811\n",
       "Name: Engine_cat, dtype: int64"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Engine_cat'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "feae3b0e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "bhp    5811\n",
       "Name: Power_cat, dtype: int64"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "df['Power_cat'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "e4801e6e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# There are 3 Km/Kg raws so droping those raws"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "997191ab",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1     km/kg\n",
       "24    km/kg\n",
       "56    km/kg\n",
       "Name: Mileage_cat, dtype: object"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Mileage_cat'][df['Mileage_cat']=='km/kg']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "2507b832",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.drop(index=[1,24,56],axis=0,inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "5dee20c1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "kmpl    5842\n",
       "Name: Mileage_cat, dtype: int64"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Mileage_cat'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "d1d07c2f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['Name', 'Location', 'Year', 'Kilometers_Driven', 'Fuel_Type',\n",
       "       'Transmission', 'Owner_Type', 'Mileage', 'Engine', 'Power', 'Seats',\n",
       "       'Price', 'Mileage_num', 'Mileage_cat', 'Engine_num', 'Engine_cat',\n",
       "       'Power_num', 'Power_cat'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "6089a501",
   "metadata": {},
   "outputs": [],
   "source": [
    "col_to_drop=['Mileage','Engine','Power','Mileage_cat','Engine_cat','Power_cat']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "dad20f81",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.drop(columns=col_to_drop,axis=1,inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "1062aaf0",
   "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>Name</th>\n",
       "      <th>Location</th>\n",
       "      <th>Year</th>\n",
       "      <th>Kilometers_Driven</th>\n",
       "      <th>Fuel_Type</th>\n",
       "      <th>Transmission</th>\n",
       "      <th>Owner_Type</th>\n",
       "      <th>Seats</th>\n",
       "      <th>Price</th>\n",
       "      <th>Mileage_num</th>\n",
       "      <th>Engine_num</th>\n",
       "      <th>Power_num</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Hyundai Creta 1.6 CRDi SX Option</td>\n",
       "      <td>Pune</td>\n",
       "      <td>2015-01-01</td>\n",
       "      <td>41000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>5.0</td>\n",
       "      <td>12.50</td>\n",
       "      <td>19.67</td>\n",
       "      <td>1582</td>\n",
       "      <td>126.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Maruti Ertiga VDI</td>\n",
       "      <td>Chennai</td>\n",
       "      <td>2012-01-01</td>\n",
       "      <td>87000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>7.0</td>\n",
       "      <td>6.00</td>\n",
       "      <td>20.77</td>\n",
       "      <td>1248</td>\n",
       "      <td>88.76</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Audi A4 New 2.0 TDI Multitronic</td>\n",
       "      <td>Coimbatore</td>\n",
       "      <td>2013-01-01</td>\n",
       "      <td>40670</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Automatic</td>\n",
       "      <td>Second</td>\n",
       "      <td>5.0</td>\n",
       "      <td>17.74</td>\n",
       "      <td>15.2</td>\n",
       "      <td>1968</td>\n",
       "      <td>140.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Nissan Micra Diesel XV</td>\n",
       "      <td>Jaipur</td>\n",
       "      <td>2013-01-01</td>\n",
       "      <td>86999</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>5.0</td>\n",
       "      <td>3.50</td>\n",
       "      <td>23.08</td>\n",
       "      <td>1461</td>\n",
       "      <td>63.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Toyota Innova Crysta 2.8 GX AT 8S</td>\n",
       "      <td>Mumbai</td>\n",
       "      <td>2016-01-01</td>\n",
       "      <td>36000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Automatic</td>\n",
       "      <td>First</td>\n",
       "      <td>8.0</td>\n",
       "      <td>17.50</td>\n",
       "      <td>11.36</td>\n",
       "      <td>2755</td>\n",
       "      <td>171.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5842</th>\n",
       "      <td>Maruti Swift VDI</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>2014-01-01</td>\n",
       "      <td>27365</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>5.0</td>\n",
       "      <td>4.75</td>\n",
       "      <td>28.4</td>\n",
       "      <td>1248</td>\n",
       "      <td>74</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5843</th>\n",
       "      <td>Hyundai Xcent 1.1 CRDi S</td>\n",
       "      <td>Jaipur</td>\n",
       "      <td>2015-01-01</td>\n",
       "      <td>100000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>5.0</td>\n",
       "      <td>4.00</td>\n",
       "      <td>24.4</td>\n",
       "      <td>1120</td>\n",
       "      <td>71</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5844</th>\n",
       "      <td>Mahindra Xylo D4 BSIV</td>\n",
       "      <td>Jaipur</td>\n",
       "      <td>2012-01-01</td>\n",
       "      <td>55000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>Second</td>\n",
       "      <td>8.0</td>\n",
       "      <td>2.90</td>\n",
       "      <td>14.0</td>\n",
       "      <td>2498</td>\n",
       "      <td>112</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5845</th>\n",
       "      <td>Maruti Wagon R VXI</td>\n",
       "      <td>Kolkata</td>\n",
       "      <td>2013-01-01</td>\n",
       "      <td>46000</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2.65</td>\n",
       "      <td>18.9</td>\n",
       "      <td>998</td>\n",
       "      <td>67.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5846</th>\n",
       "      <td>Chevrolet Beat Diesel</td>\n",
       "      <td>Hyderabad</td>\n",
       "      <td>2011-01-01</td>\n",
       "      <td>47000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2.50</td>\n",
       "      <td>25.44</td>\n",
       "      <td>936</td>\n",
       "      <td>57.6</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5844 rows × 12 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                   Name    Location       Year  \\\n",
       "0      Hyundai Creta 1.6 CRDi SX Option        Pune 2015-01-01   \n",
       "2                     Maruti Ertiga VDI     Chennai 2012-01-01   \n",
       "3       Audi A4 New 2.0 TDI Multitronic  Coimbatore 2013-01-01   \n",
       "4                Nissan Micra Diesel XV      Jaipur 2013-01-01   \n",
       "5     Toyota Innova Crysta 2.8 GX AT 8S      Mumbai 2016-01-01   \n",
       "...                                 ...         ...        ...   \n",
       "5842                   Maruti Swift VDI       Delhi 2014-01-01   \n",
       "5843           Hyundai Xcent 1.1 CRDi S      Jaipur 2015-01-01   \n",
       "5844              Mahindra Xylo D4 BSIV      Jaipur 2012-01-01   \n",
       "5845                 Maruti Wagon R VXI     Kolkata 2013-01-01   \n",
       "5846              Chevrolet Beat Diesel   Hyderabad 2011-01-01   \n",
       "\n",
       "      Kilometers_Driven Fuel_Type Transmission Owner_Type  Seats  Price  \\\n",
       "0                 41000    Diesel       Manual      First    5.0  12.50   \n",
       "2                 87000    Diesel       Manual      First    7.0   6.00   \n",
       "3                 40670    Diesel    Automatic     Second    5.0  17.74   \n",
       "4                 86999    Diesel       Manual      First    5.0   3.50   \n",
       "5                 36000    Diesel    Automatic      First    8.0  17.50   \n",
       "...                 ...       ...          ...        ...    ...    ...   \n",
       "5842              27365    Diesel       Manual      First    5.0   4.75   \n",
       "5843             100000    Diesel       Manual      First    5.0   4.00   \n",
       "5844              55000    Diesel       Manual     Second    8.0   2.90   \n",
       "5845              46000    Petrol       Manual      First    5.0   2.65   \n",
       "5846              47000    Diesel       Manual      First    5.0   2.50   \n",
       "\n",
       "     Mileage_num Engine_num Power_num  \n",
       "0          19.67       1582     126.2  \n",
       "2          20.77       1248     88.76  \n",
       "3           15.2       1968     140.8  \n",
       "4          23.08       1461      63.1  \n",
       "5          11.36       2755     171.5  \n",
       "...          ...        ...       ...  \n",
       "5842        28.4       1248        74  \n",
       "5843        24.4       1120        71  \n",
       "5844        14.0       2498       112  \n",
       "5845        18.9        998      67.1  \n",
       "5846       25.44        936      57.6  \n",
       "\n",
       "[5844 rows x 12 columns]"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "111af4ad",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.rename(columns={'Engine_num':'Engine','Mileage_num':'Mileage','Power_num':'Power'},inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "28112371",
   "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>Name</th>\n",
       "      <th>Location</th>\n",
       "      <th>Year</th>\n",
       "      <th>Kilometers_Driven</th>\n",
       "      <th>Fuel_Type</th>\n",
       "      <th>Transmission</th>\n",
       "      <th>Owner_Type</th>\n",
       "      <th>Seats</th>\n",
       "      <th>Price</th>\n",
       "      <th>Mileage</th>\n",
       "      <th>Engine</th>\n",
       "      <th>Power</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Hyundai Creta 1.6 CRDi SX Option</td>\n",
       "      <td>Pune</td>\n",
       "      <td>2015-01-01</td>\n",
       "      <td>41000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>5.0</td>\n",
       "      <td>12.50</td>\n",
       "      <td>19.67</td>\n",
       "      <td>1582</td>\n",
       "      <td>126.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Maruti Ertiga VDI</td>\n",
       "      <td>Chennai</td>\n",
       "      <td>2012-01-01</td>\n",
       "      <td>87000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>7.0</td>\n",
       "      <td>6.00</td>\n",
       "      <td>20.77</td>\n",
       "      <td>1248</td>\n",
       "      <td>88.76</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Audi A4 New 2.0 TDI Multitronic</td>\n",
       "      <td>Coimbatore</td>\n",
       "      <td>2013-01-01</td>\n",
       "      <td>40670</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Automatic</td>\n",
       "      <td>Second</td>\n",
       "      <td>5.0</td>\n",
       "      <td>17.74</td>\n",
       "      <td>15.2</td>\n",
       "      <td>1968</td>\n",
       "      <td>140.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Nissan Micra Diesel XV</td>\n",
       "      <td>Jaipur</td>\n",
       "      <td>2013-01-01</td>\n",
       "      <td>86999</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>5.0</td>\n",
       "      <td>3.50</td>\n",
       "      <td>23.08</td>\n",
       "      <td>1461</td>\n",
       "      <td>63.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Toyota Innova Crysta 2.8 GX AT 8S</td>\n",
       "      <td>Mumbai</td>\n",
       "      <td>2016-01-01</td>\n",
       "      <td>36000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Automatic</td>\n",
       "      <td>First</td>\n",
       "      <td>8.0</td>\n",
       "      <td>17.50</td>\n",
       "      <td>11.36</td>\n",
       "      <td>2755</td>\n",
       "      <td>171.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5842</th>\n",
       "      <td>Maruti Swift VDI</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>2014-01-01</td>\n",
       "      <td>27365</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>5.0</td>\n",
       "      <td>4.75</td>\n",
       "      <td>28.4</td>\n",
       "      <td>1248</td>\n",
       "      <td>74</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5843</th>\n",
       "      <td>Hyundai Xcent 1.1 CRDi S</td>\n",
       "      <td>Jaipur</td>\n",
       "      <td>2015-01-01</td>\n",
       "      <td>100000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>5.0</td>\n",
       "      <td>4.00</td>\n",
       "      <td>24.4</td>\n",
       "      <td>1120</td>\n",
       "      <td>71</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5844</th>\n",
       "      <td>Mahindra Xylo D4 BSIV</td>\n",
       "      <td>Jaipur</td>\n",
       "      <td>2012-01-01</td>\n",
       "      <td>55000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>Second</td>\n",
       "      <td>8.0</td>\n",
       "      <td>2.90</td>\n",
       "      <td>14.0</td>\n",
       "      <td>2498</td>\n",
       "      <td>112</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5845</th>\n",
       "      <td>Maruti Wagon R VXI</td>\n",
       "      <td>Kolkata</td>\n",
       "      <td>2013-01-01</td>\n",
       "      <td>46000</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2.65</td>\n",
       "      <td>18.9</td>\n",
       "      <td>998</td>\n",
       "      <td>67.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5846</th>\n",
       "      <td>Chevrolet Beat Diesel</td>\n",
       "      <td>Hyderabad</td>\n",
       "      <td>2011-01-01</td>\n",
       "      <td>47000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2.50</td>\n",
       "      <td>25.44</td>\n",
       "      <td>936</td>\n",
       "      <td>57.6</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5844 rows × 12 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                   Name    Location       Year  \\\n",
       "0      Hyundai Creta 1.6 CRDi SX Option        Pune 2015-01-01   \n",
       "2                     Maruti Ertiga VDI     Chennai 2012-01-01   \n",
       "3       Audi A4 New 2.0 TDI Multitronic  Coimbatore 2013-01-01   \n",
       "4                Nissan Micra Diesel XV      Jaipur 2013-01-01   \n",
       "5     Toyota Innova Crysta 2.8 GX AT 8S      Mumbai 2016-01-01   \n",
       "...                                 ...         ...        ...   \n",
       "5842                   Maruti Swift VDI       Delhi 2014-01-01   \n",
       "5843           Hyundai Xcent 1.1 CRDi S      Jaipur 2015-01-01   \n",
       "5844              Mahindra Xylo D4 BSIV      Jaipur 2012-01-01   \n",
       "5845                 Maruti Wagon R VXI     Kolkata 2013-01-01   \n",
       "5846              Chevrolet Beat Diesel   Hyderabad 2011-01-01   \n",
       "\n",
       "      Kilometers_Driven Fuel_Type Transmission Owner_Type  Seats  Price  \\\n",
       "0                 41000    Diesel       Manual      First    5.0  12.50   \n",
       "2                 87000    Diesel       Manual      First    7.0   6.00   \n",
       "3                 40670    Diesel    Automatic     Second    5.0  17.74   \n",
       "4                 86999    Diesel       Manual      First    5.0   3.50   \n",
       "5                 36000    Diesel    Automatic      First    8.0  17.50   \n",
       "...                 ...       ...          ...        ...    ...    ...   \n",
       "5842              27365    Diesel       Manual      First    5.0   4.75   \n",
       "5843             100000    Diesel       Manual      First    5.0   4.00   \n",
       "5844              55000    Diesel       Manual     Second    8.0   2.90   \n",
       "5845              46000    Petrol       Manual      First    5.0   2.65   \n",
       "5846              47000    Diesel       Manual      First    5.0   2.50   \n",
       "\n",
       "     Mileage Engine  Power  \n",
       "0      19.67   1582  126.2  \n",
       "2      20.77   1248  88.76  \n",
       "3       15.2   1968  140.8  \n",
       "4      23.08   1461   63.1  \n",
       "5      11.36   2755  171.5  \n",
       "...      ...    ...    ...  \n",
       "5842    28.4   1248     74  \n",
       "5843    24.4   1120     71  \n",
       "5844    14.0   2498    112  \n",
       "5845    18.9    998   67.1  \n",
       "5846   25.44    936   57.6  \n",
       "\n",
       "[5844 rows x 12 columns]"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "5f0355ee",
   "metadata": {},
   "outputs": [],
   "source": [
    "df['Brand']=df['Name'].str.split(' ',expand=True)[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "cd667b74",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Maruti           1132\n",
       "Hyundai          1057\n",
       "Honda             606\n",
       "Toyota            395\n",
       "Mercedes-Benz     316\n",
       "Volkswagen        314\n",
       "Ford              295\n",
       "Mahindra          269\n",
       "BMW               267\n",
       "Audi              235\n",
       "Tata              181\n",
       "Skoda             172\n",
       "Renault           145\n",
       "Chevrolet         120\n",
       "Nissan             87\n",
       "Land               60\n",
       "Jaguar             40\n",
       "Mitsubishi         27\n",
       "Mini               26\n",
       "Fiat               26\n",
       "Volvo              21\n",
       "Porsche            16\n",
       "Jeep               15\n",
       "Datsun             13\n",
       "Force               3\n",
       "ISUZU               2\n",
       "Ambassador          1\n",
       "Isuzu               1\n",
       "Bentley             1\n",
       "Lamborghini         1\n",
       "Name: Brand, dtype: int64"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Brand'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "24183ee4",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.drop('Name',axis=1,inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "c427507a",
   "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>Location</th>\n",
       "      <th>Year</th>\n",
       "      <th>Kilometers_Driven</th>\n",
       "      <th>Fuel_Type</th>\n",
       "      <th>Transmission</th>\n",
       "      <th>Owner_Type</th>\n",
       "      <th>Seats</th>\n",
       "      <th>Price</th>\n",
       "      <th>Mileage</th>\n",
       "      <th>Engine</th>\n",
       "      <th>Power</th>\n",
       "      <th>Brand</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Pune</td>\n",
       "      <td>2015-01-01</td>\n",
       "      <td>41000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>5.0</td>\n",
       "      <td>12.50</td>\n",
       "      <td>19.67</td>\n",
       "      <td>1582</td>\n",
       "      <td>126.2</td>\n",
       "      <td>Hyundai</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Chennai</td>\n",
       "      <td>2012-01-01</td>\n",
       "      <td>87000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>7.0</td>\n",
       "      <td>6.00</td>\n",
       "      <td>20.77</td>\n",
       "      <td>1248</td>\n",
       "      <td>88.76</td>\n",
       "      <td>Maruti</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Coimbatore</td>\n",
       "      <td>2013-01-01</td>\n",
       "      <td>40670</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Automatic</td>\n",
       "      <td>Second</td>\n",
       "      <td>5.0</td>\n",
       "      <td>17.74</td>\n",
       "      <td>15.2</td>\n",
       "      <td>1968</td>\n",
       "      <td>140.8</td>\n",
       "      <td>Audi</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Jaipur</td>\n",
       "      <td>2013-01-01</td>\n",
       "      <td>86999</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>5.0</td>\n",
       "      <td>3.50</td>\n",
       "      <td>23.08</td>\n",
       "      <td>1461</td>\n",
       "      <td>63.1</td>\n",
       "      <td>Nissan</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Mumbai</td>\n",
       "      <td>2016-01-01</td>\n",
       "      <td>36000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Automatic</td>\n",
       "      <td>First</td>\n",
       "      <td>8.0</td>\n",
       "      <td>17.50</td>\n",
       "      <td>11.36</td>\n",
       "      <td>2755</td>\n",
       "      <td>171.5</td>\n",
       "      <td>Toyota</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5842</th>\n",
       "      <td>Delhi</td>\n",
       "      <td>2014-01-01</td>\n",
       "      <td>27365</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>5.0</td>\n",
       "      <td>4.75</td>\n",
       "      <td>28.4</td>\n",
       "      <td>1248</td>\n",
       "      <td>74</td>\n",
       "      <td>Maruti</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5843</th>\n",
       "      <td>Jaipur</td>\n",
       "      <td>2015-01-01</td>\n",
       "      <td>100000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>5.0</td>\n",
       "      <td>4.00</td>\n",
       "      <td>24.4</td>\n",
       "      <td>1120</td>\n",
       "      <td>71</td>\n",
       "      <td>Hyundai</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5844</th>\n",
       "      <td>Jaipur</td>\n",
       "      <td>2012-01-01</td>\n",
       "      <td>55000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>Second</td>\n",
       "      <td>8.0</td>\n",
       "      <td>2.90</td>\n",
       "      <td>14.0</td>\n",
       "      <td>2498</td>\n",
       "      <td>112</td>\n",
       "      <td>Mahindra</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5845</th>\n",
       "      <td>Kolkata</td>\n",
       "      <td>2013-01-01</td>\n",
       "      <td>46000</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2.65</td>\n",
       "      <td>18.9</td>\n",
       "      <td>998</td>\n",
       "      <td>67.1</td>\n",
       "      <td>Maruti</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5846</th>\n",
       "      <td>Hyderabad</td>\n",
       "      <td>2011-01-01</td>\n",
       "      <td>47000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2.50</td>\n",
       "      <td>25.44</td>\n",
       "      <td>936</td>\n",
       "      <td>57.6</td>\n",
       "      <td>Chevrolet</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5844 rows × 12 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        Location       Year  Kilometers_Driven Fuel_Type Transmission  \\\n",
       "0           Pune 2015-01-01              41000    Diesel       Manual   \n",
       "2        Chennai 2012-01-01              87000    Diesel       Manual   \n",
       "3     Coimbatore 2013-01-01              40670    Diesel    Automatic   \n",
       "4         Jaipur 2013-01-01              86999    Diesel       Manual   \n",
       "5         Mumbai 2016-01-01              36000    Diesel    Automatic   \n",
       "...          ...        ...                ...       ...          ...   \n",
       "5842       Delhi 2014-01-01              27365    Diesel       Manual   \n",
       "5843      Jaipur 2015-01-01             100000    Diesel       Manual   \n",
       "5844      Jaipur 2012-01-01              55000    Diesel       Manual   \n",
       "5845     Kolkata 2013-01-01              46000    Petrol       Manual   \n",
       "5846   Hyderabad 2011-01-01              47000    Diesel       Manual   \n",
       "\n",
       "     Owner_Type  Seats  Price Mileage Engine  Power      Brand  \n",
       "0         First    5.0  12.50   19.67   1582  126.2    Hyundai  \n",
       "2         First    7.0   6.00   20.77   1248  88.76     Maruti  \n",
       "3        Second    5.0  17.74    15.2   1968  140.8       Audi  \n",
       "4         First    5.0   3.50   23.08   1461   63.1     Nissan  \n",
       "5         First    8.0  17.50   11.36   2755  171.5     Toyota  \n",
       "...         ...    ...    ...     ...    ...    ...        ...  \n",
       "5842      First    5.0   4.75    28.4   1248     74     Maruti  \n",
       "5843      First    5.0   4.00    24.4   1120     71    Hyundai  \n",
       "5844     Second    8.0   2.90    14.0   2498    112   Mahindra  \n",
       "5845      First    5.0   2.65    18.9    998   67.1     Maruti  \n",
       "5846      First    5.0   2.50   25.44    936   57.6  Chevrolet  \n",
       "\n",
       "[5844 rows x 12 columns]"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "88791ee0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2014-01-01    784\n",
       "2015-01-01    734\n",
       "2016-01-01    734\n",
       "2013-01-01    631\n",
       "2017-01-01    582\n",
       "2012-01-01    557\n",
       "2011-01-01    454\n",
       "2010-01-01    329\n",
       "2018-01-01    294\n",
       "2009-01-01    193\n",
       "2008-01-01    163\n",
       "2007-01-01    106\n",
       "2019-01-01    101\n",
       "2006-01-01     69\n",
       "2005-01-01     44\n",
       "2004-01-01     27\n",
       "2003-01-01     16\n",
       "2002-01-01     12\n",
       "2001-01-01      5\n",
       "2000-01-01      4\n",
       "1998-01-01      3\n",
       "1999-01-01      2\n",
       "Name: Year, dtype: int64"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Year'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "61e47f39",
   "metadata": {},
   "outputs": [],
   "source": [
    "### There is no impact of month and days hence converting into year"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "cb309336",
   "metadata": {},
   "outputs": [],
   "source": [
    "df['Year']=df['Year'].dt.year"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "7db3dd52",
   "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>Location</th>\n",
       "      <th>Year</th>\n",
       "      <th>Kilometers_Driven</th>\n",
       "      <th>Fuel_Type</th>\n",
       "      <th>Transmission</th>\n",
       "      <th>Owner_Type</th>\n",
       "      <th>Seats</th>\n",
       "      <th>Price</th>\n",
       "      <th>Mileage</th>\n",
       "      <th>Engine</th>\n",
       "      <th>Power</th>\n",
       "      <th>Brand</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Pune</td>\n",
       "      <td>2015</td>\n",
       "      <td>41000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>5.0</td>\n",
       "      <td>12.50</td>\n",
       "      <td>19.67</td>\n",
       "      <td>1582</td>\n",
       "      <td>126.2</td>\n",
       "      <td>Hyundai</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Chennai</td>\n",
       "      <td>2012</td>\n",
       "      <td>87000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>7.0</td>\n",
       "      <td>6.00</td>\n",
       "      <td>20.77</td>\n",
       "      <td>1248</td>\n",
       "      <td>88.76</td>\n",
       "      <td>Maruti</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Coimbatore</td>\n",
       "      <td>2013</td>\n",
       "      <td>40670</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Automatic</td>\n",
       "      <td>Second</td>\n",
       "      <td>5.0</td>\n",
       "      <td>17.74</td>\n",
       "      <td>15.2</td>\n",
       "      <td>1968</td>\n",
       "      <td>140.8</td>\n",
       "      <td>Audi</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Jaipur</td>\n",
       "      <td>2013</td>\n",
       "      <td>86999</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>5.0</td>\n",
       "      <td>3.50</td>\n",
       "      <td>23.08</td>\n",
       "      <td>1461</td>\n",
       "      <td>63.1</td>\n",
       "      <td>Nissan</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Mumbai</td>\n",
       "      <td>2016</td>\n",
       "      <td>36000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Automatic</td>\n",
       "      <td>First</td>\n",
       "      <td>8.0</td>\n",
       "      <td>17.50</td>\n",
       "      <td>11.36</td>\n",
       "      <td>2755</td>\n",
       "      <td>171.5</td>\n",
       "      <td>Toyota</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5842</th>\n",
       "      <td>Delhi</td>\n",
       "      <td>2014</td>\n",
       "      <td>27365</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>5.0</td>\n",
       "      <td>4.75</td>\n",
       "      <td>28.4</td>\n",
       "      <td>1248</td>\n",
       "      <td>74</td>\n",
       "      <td>Maruti</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5843</th>\n",
       "      <td>Jaipur</td>\n",
       "      <td>2015</td>\n",
       "      <td>100000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>5.0</td>\n",
       "      <td>4.00</td>\n",
       "      <td>24.4</td>\n",
       "      <td>1120</td>\n",
       "      <td>71</td>\n",
       "      <td>Hyundai</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5844</th>\n",
       "      <td>Jaipur</td>\n",
       "      <td>2012</td>\n",
       "      <td>55000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>Second</td>\n",
       "      <td>8.0</td>\n",
       "      <td>2.90</td>\n",
       "      <td>14.0</td>\n",
       "      <td>2498</td>\n",
       "      <td>112</td>\n",
       "      <td>Mahindra</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5845</th>\n",
       "      <td>Kolkata</td>\n",
       "      <td>2013</td>\n",
       "      <td>46000</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2.65</td>\n",
       "      <td>18.9</td>\n",
       "      <td>998</td>\n",
       "      <td>67.1</td>\n",
       "      <td>Maruti</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5846</th>\n",
       "      <td>Hyderabad</td>\n",
       "      <td>2011</td>\n",
       "      <td>47000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Manual</td>\n",
       "      <td>First</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2.50</td>\n",
       "      <td>25.44</td>\n",
       "      <td>936</td>\n",
       "      <td>57.6</td>\n",
       "      <td>Chevrolet</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5844 rows × 12 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        Location  Year  Kilometers_Driven Fuel_Type Transmission Owner_Type  \\\n",
       "0           Pune  2015              41000    Diesel       Manual      First   \n",
       "2        Chennai  2012              87000    Diesel       Manual      First   \n",
       "3     Coimbatore  2013              40670    Diesel    Automatic     Second   \n",
       "4         Jaipur  2013              86999    Diesel       Manual      First   \n",
       "5         Mumbai  2016              36000    Diesel    Automatic      First   \n",
       "...          ...   ...                ...       ...          ...        ...   \n",
       "5842       Delhi  2014              27365    Diesel       Manual      First   \n",
       "5843      Jaipur  2015             100000    Diesel       Manual      First   \n",
       "5844      Jaipur  2012              55000    Diesel       Manual     Second   \n",
       "5845     Kolkata  2013              46000    Petrol       Manual      First   \n",
       "5846   Hyderabad  2011              47000    Diesel       Manual      First   \n",
       "\n",
       "      Seats  Price Mileage Engine  Power      Brand  \n",
       "0       5.0  12.50   19.67   1582  126.2    Hyundai  \n",
       "2       7.0   6.00   20.77   1248  88.76     Maruti  \n",
       "3       5.0  17.74    15.2   1968  140.8       Audi  \n",
       "4       5.0   3.50   23.08   1461   63.1     Nissan  \n",
       "5       8.0  17.50   11.36   2755  171.5     Toyota  \n",
       "...     ...    ...     ...    ...    ...        ...  \n",
       "5842    5.0   4.75    28.4   1248     74     Maruti  \n",
       "5843    5.0   4.00    24.4   1120     71    Hyundai  \n",
       "5844    8.0   2.90    14.0   2498    112   Mahindra  \n",
       "5845    5.0   2.65    18.9    998   67.1     Maruti  \n",
       "5846    5.0   2.50   25.44    936   57.6  Chevrolet  \n",
       "\n",
       "[5844 rows x 12 columns]"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "82ff1076",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAfcAAAFuCAYAAACcHFGsAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAAAX9UlEQVR4nO3dbYxU9dn48WtZdIuyOxUQC2V5KGhFWahPUaTbQH2IW2OkFO/WqqGmprcJPhVNW0yT1tqyNUpjItGINRJild5aoGqLQlOBrWKja4jSogJCQVmrUN1ZKBl0d+4X3uy/+xdkZ/aR334+ybyYs78z5+KNX8/MmTMl+Xw+HwBAMvr19AAAQOcSdwBIjLgDQGLEHQASI+4AkBhxB4DEiDsAJEbcASAx4g4AiRF3AEhMj8V97dq1cckll8Tw4cOjpKQkli9fXvBr5PP5uOuuu+Kkk06KsrKyqKysjHnz5nX+sABwBOnfUwfeu3dvTJo0Ka6++ur4xje+UdRr3HjjjbFy5cq46667oqqqKhobG2PXrl2dPCkAHFlKesMPx5SUlMSyZcti+vTprdv2798fP/7xj+M3v/lNfPDBBzFhwoS44447YurUqRERsXHjxpg4cWJs2LAhvvjFL/bM4ADQC/Xaz9yvvvrqeO6552LJkiXxyiuvxGWXXRYXXXRRbNq0KSIinnzyyfjCF74QTz31VIwZMyZGjx4d11xzTfzrX//q4ckBoGf1yrhv2bIlHn300Xjssceiuro6xo4dG7fcckt8+ctfjoceeigiIt588834xz/+EY899lgsXrw4Fi1aFPX19TFz5swenh4AelaPfeb+aV5++eXI5/Nx0kkntdmey+Vi8ODBERHR0tISuVwuFi9e3LruwQcfjDPOOCNef/11b9UD0Gf1yri3tLREaWlp1NfXR2lpaZu/DRw4MCIihg0bFv3792/zPwDjx4+PiIjt27eLOwB9Vq+M+2mnnRbNzc3x7rvvRnV19UHXTJkyJT766KPYsmVLjB07NiIi3njjjYiIGDVqVLfNCgC9TY9dLb9nz57YvHlzRHwc81/96lcxbdq0GDRoUIwcOTKuvPLKeO6552L+/Plx2mmnxa5du+LPf/5zVFVVxde+9rVoaWmJs846KwYOHBh33313tLS0xOzZs6OioiJWrlzZE/8kAOgVeizuq1evjmnTpn1i+6xZs2LRokXx4Ycfxs9//vNYvHhxvP322zF48OCYPHly3HbbbVFVVRURETt37ozrr78+Vq5cGccee2zU1NTE/PnzY9CgQd39zwGAXqNXfM8dAOg8vfKrcABA8br9grqWlpbYuXNnlJeXR0lJSXcfHgCOWPl8PpqammL48OHRr9+hz8+7Pe47d+6MysrK7j4sACRjx44dMWLEiEP+vdvjXl5eHhEfD1ZRUdHdhweAI1Y2m43KysrWlh5Kt8f9wFvxFRUV4g4ARTjcx9ouqAOAxIg7ACRG3AEgMeIOAIkRdwBIjLgDQGJ65U++At2vubk56urqoqGhIYYNGxbV1dVRWlra02MBRXDmDsTSpUtj3LhxMW3atPj2t78d06ZNi3HjxsXSpUt7ejSgCOIOfdzSpUtj5syZUVVVFevWrYumpqZYt25dVFVVxcyZMwUejkDd/pOv2Ww2MplMNDY2ukMd9LDm5uYYN25cVFVVxfLly9v8EEVLS0tMnz49NmzYEJs2bfIWPfQC7W2oM3fow+rq6mLbtm1x6623fuIXpvr16xdz586NrVu3Rl1dXQ9NCBRD3KEPa2hoiIiICRMmHPTvB7YfWAccGcQd+rBhw4ZFRMSGDRsO+vcD2w+sA44M4g59WHV1dYwePTrmzZsXLS0tbf7W0tIStbW1MWbMmKiuru6hCYFiiDv0YaWlpTF//vx46qmnYvr06W2ulp8+fXo89dRTcdddd7mYDo4wbmIDfdyMGTPi8ccfj5tvvjnOPffc1u1jxoyJxx9/PGbMmNGD0wHF8FU4ICLcoQ6OBO1tqDN3ICI+fot+6tSpPT0G0Al85g4AiRF3AEiMuANAYsQdABIj7gCQGHEHgMSIOwAkRtwBIDHiDgCJEXcASIy4A0BiCo7722+/HVdeeWUMHjw4jjnmmPjSl74U9fX1XTEbAFCEgn445v33348pU6bEtGnTYsWKFTF06NDYsmVLfPazn+2i8QCAQhUU9zvuuCMqKyvjoYceat02evTozp4JAOiAgt6Wf+KJJ+LMM8+Myy67LIYOHRqnnXZaPPDAA5+6Ty6Xi2w22+YBAHSdguL+5ptvxn333RcnnnhiPPPMM3HttdfGDTfcEIsXLz7kPrW1tZHJZFoflZWVHR4aADi0knw+n2/v4qOPPjrOPPPMeP7551u33XDDDfHiiy/GunXrDrpPLpeLXC7X+jybzUZlZWU0NjZGRUVFB0YHgL4lm81GJpM5bEMLOnMfNmxYnHLKKW22jR8/PrZv337IfcrKyqKioqLNAwDoOgXFfcqUKfH666+32fbGG2/EqFGjOnUoAKB4BcX9+9//frzwwgsxb9682Lx5czzyyCOxcOHCmD17dlfNBwAUqKC4n3XWWbFs2bJ49NFHY8KECXH77bfH3XffHVdccUVXzQcAFKigC+o6Q3svBgAA2uqSC+oAgN5P3AEgMeIOAIkRdwBIjLgDQGLEHQASI+4AkBhxB4DEiDsAJEbcASAx4g4AiRF3AEiMuANAYsQdABIj7gCQGHEHgMSIOwAkRtwBIDHiDgCJEXcASIy4A0BixB0AEiPuAJAYcQeAxIg7ACRG3AEgMeIOAIkRdwBIjLgDQGLEHQASI+4AkBhxB4DEFBT3n/70p1FSUtLm8bnPfa6rZgMAitC/0B1OPfXU+NOf/tT6vLS0tFMHAgA6puC49+/f39k6APRiBX/mvmnTphg+fHiMGTMmvvWtb8Wbb775qetzuVxks9k2DwCg6xQU97PPPjsWL14czzzzTDzwwAPxzjvvxLnnnhu7d+8+5D61tbWRyWRaH5WVlR0eGgA4tJJ8Pp8vdue9e/fG2LFj4wc/+EHMmTPnoGtyuVzkcrnW59lsNiorK6OxsTEqKiqKPTQA9DnZbDYymcxhG1rwZ+7/6dhjj42qqqrYtGnTIdeUlZVFWVlZRw4DABSgQ99zz+VysXHjxhg2bFhnzQMAdFBBcb/llltizZo1sXXr1vjrX/8aM2fOjGw2G7Nmzeqq+QCAAhX0tvxbb70Vl19+eezatSuOP/74OOecc+KFF16IUaNGddV8AECBCor7kiVLumoOAKCTuLc8ACRG3AEgMeIOAIkRdwBIjLgDQGLEHQASI+4AkBhxB4DEiDsAJEbcASAx4g4AiRF3AEiMuANAYsQdABIj7gCQGHEHgMSIOwAkRtwBIDHiDgCJEXcASIy4A0BixB0AEiPuAJAYcQeAxIg7ACRG3AEgMeIOAIkRdwBIjLgDQGLEHQASI+4AkBhxB4DEdCjutbW1UVJSEjfddFMnjQMAdFTRcX/xxRdj4cKFMXHixM6cBwDooKLivmfPnrjiiivigQceiOOOO66zZwIAOqCouM+ePTsuvvjiOP/88w+7NpfLRTabbfMAALpO/0J3WLJkSbz88svx4osvtmt9bW1t3HbbbQUPBgAUp6Az9x07dsSNN94YDz/8cHzmM59p1z5z586NxsbG1seOHTuKGhQAaJ+SfD6fb+/i5cuXx9e//vUoLS1t3dbc3BwlJSXRr1+/yOVybf52MNlsNjKZTDQ2NkZFRUXxkwNAH9Pehhb0tvx5550Xr776apttV199dZx88snxwx/+8LBhBwC6XkFxLy8vjwkTJrTZduyxx8bgwYM/sR0A6BnuUAcAiSn4avn/3+rVqzthDACgszhzB4DEiDsAJEbcASAx4g4AiRF3AEiMuANAYsQdABIj7gCQGHEHgMSIOwAkRtwBIDHiDgCJEXcASIy4A0BixB0AEiPuAJAYcQeAxIg7ACRG3AEgMeIOAIkRdwBIjLgDQGLEHQASI+4AkBhxB4DEiDsAJEbcASAx4g4AiRF3AEiMuANAYsQdABIj7gCQmILift9998XEiROjoqIiKioqYvLkybFixYqumg0AKEJBcR8xYkT88pe/jJdeeileeuml+OpXvxqXXnpp/O1vf+uq+QCAApXk8/l8R15g0KBBceedd8Z3v/vddq3PZrORyWSisbExKioqOnJoAOhT2tvQ/sUeoLm5OR577LHYu3dvTJ48+ZDrcrlc5HK5NoMBAF2n4AvqXn311Rg4cGCUlZXFtddeG8uWLYtTTjnlkOtra2sjk8m0PiorKzs0MADw6Qp+W37//v2xffv2+OCDD+J3v/td/PrXv441a9YcMvAHO3OvrKz0tjwAFKi9b8t3+DP3888/P8aOHRv3339/pw4GALTV3oZ2+Hvu+Xy+zZk5ANCzCrqg7tZbb42ampqorKyMpqamWLJkSaxevTqefvrprpoPAChQQXH/5z//GVdddVU0NDREJpOJiRMnxtNPPx0XXHBBV80HABSooLg/+OCDXTUHANBJ3FseABIj7gCQGHEHgMSIOwAkRtwBIDHiDgCJEXcASIy4A0BixB0AEiPuAJAYcQeAxIg7ACRG3AEgMeIOAIkRdwBIjLgDQGLEHQASI+4AkBhxB4DEiDsAJEbcASAx4g4AiRF3AEiMuANAYsQdABIj7gCQGHEHgMSIOwAkRtwBIDHiDgCJEXcASIy4A0BixB0AElNQ3Gtra+Oss86K8vLyGDp0aEyfPj1ef/31rpoNAChCQXFfs2ZNzJ49O1544YVYtWpVfPTRR3HhhRfG3r17u2o+AKBAJfl8Pl/szu+9914MHTo01qxZE1/5ylcOuiaXy0Uul2t9ns1mo7KyMhobG6OioqLYQwNAn5PNZiOTyRy2oR36zL2xsTEiIgYNGnTINbW1tZHJZFoflZWVHTkkAHAYRZ+55/P5uPTSS+P999+Purq6Q65z5g4AnaO9Z+79iz3AddddF6+88kr85S9/+dR1ZWVlUVZWVuxhAIACFRX366+/Pp544olYu3ZtjBgxorNnAgA6oKC45/P5uP7662PZsmWxevXqGDNmTFfNBQAUqaC4z549Ox555JH4/e9/H+Xl5fHOO+9EREQmk4kBAwZ0yYAAQGEKuqCupKTkoNsfeuih+M53vtOu12jvxQAAQFtdckFdB74SDwB0E/eWB4DEiDsAJEbcASAx4g4AiRF3AEiMuANAYsQdABIj7gCQGHEHgMSIOwAkRtwBIDHiDgCJEXcASIy4A0BixB0AEiPuAJAYcQeAxIg7ACRG3AEgMeIOAIkRdwBIjLgDQGLEHQASI+4AkBhxB4DEiDsAJEbcASAx4g4AiRF3AEiMuANAYsQdABIj7gCQmILjvnbt2rjkkkti+PDhUVJSEsuXL++CsQCAYhUc971798akSZNiwYIFXTEPANBB/QvdoaamJmpqatq9PpfLRS6Xa32ezWYLPSQAUIAu/8y9trY2MplM66OysrKrDwkAfVqXx33u3LnR2NjY+tixY0dXHxIA+rSC35YvVFlZWZSVlXX1YQCA/+OrcACQGHEHgMQU/Lb8nj17YvPmza3Pt27dGuvXr49BgwbFyJEjO3U4oPs0NzdHXV1dNDQ0xLBhw6K6ujpKS0t7eiygCAXH/aWXXopp06a1Pp8zZ05ERMyaNSsWLVrUaYMB3Wfp0qVx8803x7Zt21q3jR49OubPnx8zZszoucGAopTk8/l8dx4wm81GJpOJxsbGqKio6M5DAwexdOnSmDlzZlx88cVRU1MTAwYMiH379sWKFSviD3/4Qzz++OMCD71Eexsq7tCHNTc3x7hx42LIkCGxa9euT5y5DxkyJHbv3h2bNm3yFj30Au1tqAvqoA+rq6uLbdu2RX19fVRVVcW6deuiqakp1q1bF1VVVVFfXx9bt26Nurq6nh4VKIC4Qx/29ttvR0TERRddFMuXL49zzjknBg4cGOecc04sX748LrroojbrgCODuEMf9t5770VExIwZM6Jfv7b/OejXr19Mnz69zTrgyCDu0Icdf/zxEfHxRXUffvhhrF69Oh599NFYvXp1fPjhh60/6XxgHXBk6PLbzwK91+c///mIiFixYkVkMpnYt29f698OXDX/n+uAI4Mzd+jDqqurY+jQoRERcagvzgwdOjSqq6u7cyygg5y5Qx93IOrnnXfeQb/nDhx5xB36sLq6unjvvfeitrY27r///jYxHzNmTMybNy9uvfXWqKuri6lTp/bcoEBBvC0PfVhDQ0NERFx33XWxefPmePbZZ+ORRx6JZ599NjZt2hTXXXddm3XAkUHcoQ8bNmxYRERs2LAhmpubY/369fH888/H+vXro7m5OTZs2NBmHXBkcPtZ6MMO3H62tLQ0tm3bFs3Nza1/Ky0tjdGjR0dLS4vbz0Iv4fazwGGVlpbGpEmTYsuWLW3CHvFx+Lds2RITJ04UdjjCiDv0Yfv3748nn3wyIj7+Xvt/OvD8ySefjP3793f7bEDxxB36sAULFkRLS0tMmjQpGhsb21xQ19jYGBMnToyWlpZYsGBBT48KFEDcoQ878Gtvv/jFL+Koo46KqVOnxuWXXx5Tp06No446Km6//fY264Ajg7hDH1ZeXh4REVu3bj3o3w/8vvuBdcCRwdXy0IetWrUqLrzwwjjuuOPirbfeioULF8aWLVti7Nix8b3vfS9GjBgR77//fqxcuTIuuOCCnh4X+rz2NlTcoQ9rbm6OwYMHR2Nj4yHXZDKZ2L17tyvmoRfwVTjgsEpLSw97W9mpU6cKOxxhnLlDH7Z///4YMGBAtLS0HHJNv379Yt++fXH00Ud342TAwThzBw7rnnvu+dSwR0S0tLTEPffc000TAZ1B3KEPW7t2baeuA3oHcYc+bPPmzZ26DugdxB36sI0bN3bqOqB3EHfow9p7PW03X3cLdJC4A0BixB0AEiPuAJCY/j09ANA5/v3vf8drr73WZa//8ssvF7zPySefHMccc0wXTAN8GnGHRLz22mtxxhlndNnrF/Pa9fX1cfrpp3fBNMCnEXfoBTZt2hRNTU0deo19+/bFww8/XNA+V155ZbvXFvraER/PVMwZ/wHl5eVx4oknFr0/9FVF3Vv+3nvvjTvvvDMaGhri1FNPjbvvvjuqq6vbta97y0Nbmze+Gv/11S/19Bi91v/8eX2MG1/V02NAr9DehhZ85v7b3/42brrpprj33ntjypQpcf/990dNTU38/e9/j5EjR3ZoaOiLmrbWx8v/PbCnx+i1Njb8LULcoSAFn7mfffbZcfrpp8d9993Xum38+PExffr0qK2t/cT6XC4XuVyu9Xk2m43Kykpn7vB/Hlp4b9zzk+t7eoxey5k7/D9dcua+f//+qK+vjx/96Edttl944YXx/PPPH3Sf2trauO222wo5DPQpl8z4r2jud3SHryzfuHFjQZ+hd4eHH344xo8fX/T+5eXlMc5n7lCwguK+a9euaG5ujhNOOKHN9hNOOCHeeeedg+4zd+7cmDNnTuvzA2fuwMeGDBkS11xzTYdf5+STT476+voOvca+ffti27ZtMXr06BgwYECnzOSrcND9irpavqSkpM3zfD7/iW0HlJWVRVlZWTGHAQpwzDHHdMrXzqZMmdIJ0wA9qaA71A0ZMiRKS0s/cZb+7rvvfuJsHgDoGQXF/eijj44zzjgjVq1a1Wb7qlWr4txzz+3UwQCA4hT8tvycOXPiqquuijPPPDMmT54cCxcujO3bt8e1117bFfMBAAUqOO7f/OY3Y/fu3fGzn/0sGhoaYsKECfHHP/4xRo0a1RXzAQAFKuoOdR3hDnUAUJz2NtRPvgJAYsQdABIj7gCQGHEHgMSIOwAkpqjbz3bEgYvzs9lsdx8aAI5oB9p5uC+6dXvcm5qaIiL8eAwAFKmpqSkymcwh/97t33NvaWmJnTt3Rnl5+SF/bAboGQd+tXHHjh3uQwG9UD6fj6amphg+fHj063foT9a7Pe5A7+UmU5AGF9QBQGLEHQASI+5Aq7KysvjJT34SZWVlPT0K0AE+cweAxDhzB4DEiDsAJEbcASAx4g4AiRF3AEiMuAOxdu3auOSSS2L48OFRUlISy5cv7+mRgA4QdyD27t0bkyZNigULFvT0KEAn6PZfhQN6n5qamqipqenpMYBO4swdABIj7gCQGHEHgMSIOwAkRtwBIDGulgdiz549sXnz5tbnW7dujfXr18egQYNi5MiRPTgZUAw/+QrE6tWrY9q0aZ/YPmvWrFi0aFH3DwR0iLgDQGJ85g4AiRF3AEiMuANAYsQdABIj7gCQGHEHgMSIOwAkRtwBIDHiDgCJEXcASIy4A0Bi/hdXChfc2/2kKwAAAABJRU5ErkJggg==",
      "text/plain": [
       "<Figure size 600x400 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(6,4))\n",
    "plt.boxplot(df['Kilometers_Driven'])\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "69a2dbb4",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Preparing the data for train test split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "fcfa7875",
   "metadata": {},
   "outputs": [],
   "source": [
    "x=df.drop(['Price'],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "16079158",
   "metadata": {},
   "outputs": [],
   "source": [
    "y=df['Price']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "3adb7470",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(5844, 11)"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "f964e4cc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(5844,)"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "bf925a17",
   "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,random_state=1,test_size=0.25)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "83d7aa3a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(4383, 11)"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_train.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "614e89ea",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1461, 11)"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_test.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "d63be8d7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(4383,)"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_train.shape\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "90bbfcce",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1461,)"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_test.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "id": "81c6b1aa",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Location              0\n",
       "Year                  0\n",
       "Kilometers_Driven     0\n",
       "Fuel_Type             0\n",
       "Transmission          0\n",
       "Owner_Type            0\n",
       "Seats                24\n",
       "Mileage               2\n",
       "Engine               23\n",
       "Power                23\n",
       "Brand                 0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_train.isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "id": "19fc172c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "First             4808\n",
       "Second             925\n",
       "Third              103\n",
       "Fourth & Above       8\n",
       "Name: Owner_Type, dtype: int64"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Owner_Type'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "6cc75754",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.compose import ColumnTransformer\n",
    "transformer=ColumnTransformer(transformers=[\n",
    "    ('si',SimpleImputer(),['Seats','Mileage','Engine','Power']),\n",
    "    ('OE',OrdinalEncoder(categories=[['First','Second','Third','Fourth & Above']]),['Owner_Type']),\n",
    "    ('OHE',OneHotEncoder(sparse_output=False,drop='first',handle_unknown='ignore'),['Location','Fuel_Type','Transmission','Brand'])\n",
    "    \n",
    "],remainder='passthrough')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "id": "33e63cdc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-1 {color: black;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 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-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 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-1 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-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 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-1 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-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 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-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 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-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 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-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
       "                  transformers=[(&#x27;si&#x27;, SimpleImputer(),\n",
       "                                 [&#x27;Seats&#x27;, &#x27;Mileage&#x27;, &#x27;Engine&#x27;, &#x27;Power&#x27;]),\n",
       "                                (&#x27;OE&#x27;,\n",
       "                                 OrdinalEncoder(categories=[[&#x27;First&#x27;, &#x27;Second&#x27;,\n",
       "                                                             &#x27;Third&#x27;,\n",
       "                                                             &#x27;Fourth &amp; &#x27;\n",
       "                                                             &#x27;Above&#x27;]]),\n",
       "                                 [&#x27;Owner_Type&#x27;]),\n",
       "                                (&#x27;OHE&#x27;,\n",
       "                                 OneHotEncoder(drop=&#x27;first&#x27;,\n",
       "                                               handle_unknown=&#x27;ignore&#x27;,\n",
       "                                               sparse_output=False),\n",
       "                                 [&#x27;Location&#x27;, &#x27;Fuel_Type&#x27;, &#x27;Transmission&#x27;,\n",
       "                                  &#x27;Brand&#x27;])])</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 sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" ><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">ColumnTransformer</label><div class=\"sk-toggleable__content\"><pre>ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
       "                  transformers=[(&#x27;si&#x27;, SimpleImputer(),\n",
       "                                 [&#x27;Seats&#x27;, &#x27;Mileage&#x27;, &#x27;Engine&#x27;, &#x27;Power&#x27;]),\n",
       "                                (&#x27;OE&#x27;,\n",
       "                                 OrdinalEncoder(categories=[[&#x27;First&#x27;, &#x27;Second&#x27;,\n",
       "                                                             &#x27;Third&#x27;,\n",
       "                                                             &#x27;Fourth &amp; &#x27;\n",
       "                                                             &#x27;Above&#x27;]]),\n",
       "                                 [&#x27;Owner_Type&#x27;]),\n",
       "                                (&#x27;OHE&#x27;,\n",
       "                                 OneHotEncoder(drop=&#x27;first&#x27;,\n",
       "                                               handle_unknown=&#x27;ignore&#x27;,\n",
       "                                               sparse_output=False),\n",
       "                                 [&#x27;Location&#x27;, &#x27;Fuel_Type&#x27;, &#x27;Transmission&#x27;,\n",
       "                                  &#x27;Brand&#x27;])])</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" ><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">si</label><div class=\"sk-toggleable__content\"><pre>[&#x27;Seats&#x27;, &#x27;Mileage&#x27;, &#x27;Engine&#x27;, &#x27;Power&#x27;]</pre></div></div></div><div class=\"sk-serial\"><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\" ><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer()</pre></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-4\" type=\"checkbox\" ><label for=\"sk-estimator-id-4\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">OE</label><div class=\"sk-toggleable__content\"><pre>[&#x27;Owner_Type&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-5\" type=\"checkbox\" ><label for=\"sk-estimator-id-5\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">OrdinalEncoder</label><div class=\"sk-toggleable__content\"><pre>OrdinalEncoder(categories=[[&#x27;First&#x27;, &#x27;Second&#x27;, &#x27;Third&#x27;, &#x27;Fourth &amp; Above&#x27;]])</pre></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-6\" type=\"checkbox\" ><label for=\"sk-estimator-id-6\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">OHE</label><div class=\"sk-toggleable__content\"><pre>[&#x27;Location&#x27;, &#x27;Fuel_Type&#x27;, &#x27;Transmission&#x27;, &#x27;Brand&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-7\" type=\"checkbox\" ><label for=\"sk-estimator-id-7\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">OneHotEncoder</label><div class=\"sk-toggleable__content\"><pre>OneHotEncoder(drop=&#x27;first&#x27;, handle_unknown=&#x27;ignore&#x27;, sparse_output=False)</pre></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-8\" type=\"checkbox\" ><label for=\"sk-estimator-id-8\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">remainder</label><div class=\"sk-toggleable__content\"><pre>[&#x27;Year&#x27;, &#x27;Kilometers_Driven&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-9\" type=\"checkbox\" ><label for=\"sk-estimator-id-9\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">passthrough</label><div class=\"sk-toggleable__content\"><pre>passthrough</pre></div></div></div></div></div></div></div></div></div></div>"
      ],
      "text/plain": [
       "ColumnTransformer(remainder='passthrough',\n",
       "                  transformers=[('si', SimpleImputer(),\n",
       "                                 ['Seats', 'Mileage', 'Engine', 'Power']),\n",
       "                                ('OE',\n",
       "                                 OrdinalEncoder(categories=[['First', 'Second',\n",
       "                                                             'Third',\n",
       "                                                             'Fourth & '\n",
       "                                                             'Above']]),\n",
       "                                 ['Owner_Type']),\n",
       "                                ('OHE',\n",
       "                                 OneHotEncoder(drop='first',\n",
       "                                               handle_unknown='ignore',\n",
       "                                               sparse_output=False),\n",
       "                                 ['Location', 'Fuel_Type', 'Transmission',\n",
       "                                  'Brand'])])"
      ]
     },
     "execution_count": 54,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "transformer.fit(x_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "id": "1c1969f2",
   "metadata": {},
   "outputs": [],
   "source": [
    "x_train_transformed=transformer.transform(x_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "id": "99c70302",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\HP\\anaconda3\\Lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:227: UserWarning: Found unknown categories in columns [3] during transform. These unknown categories will be encoded as all zeros\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "x_test_transformed=transformer.transform(x_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "id": "e7d60ca7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[5.000e+00, 2.036e+01, 1.197e+03, ..., 0.000e+00, 2.012e+03,\n",
       "        5.300e+04],\n",
       "       [5.000e+00, 1.720e+01, 1.396e+03, ..., 0.000e+00, 2.007e+03,\n",
       "        2.000e+05],\n",
       "       [5.000e+00, 1.981e+01, 1.086e+03, ..., 0.000e+00, 2.010e+03,\n",
       "        5.500e+04],\n",
       "       ...,\n",
       "       [5.000e+00, 1.080e+01, 2.354e+03, ..., 0.000e+00, 2.008e+03,\n",
       "        9.200e+04],\n",
       "       [5.000e+00, 2.400e+01, 1.120e+03, ..., 0.000e+00, 2.017e+03,\n",
       "        3.300e+04],\n",
       "       [5.000e+00, 1.470e+01, 1.150e+03, ..., 0.000e+00, 2.009e+03,\n",
       "        7.500e+04]])"
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_train_transformed"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b9f345ab",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "646c46f4",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "id": "30c3831c",
   "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>...</th>\n",
       "      <th>37</th>\n",
       "      <th>38</th>\n",
       "      <th>39</th>\n",
       "      <th>40</th>\n",
       "      <th>41</th>\n",
       "      <th>42</th>\n",
       "      <th>43</th>\n",
       "      <th>44</th>\n",
       "      <th>45</th>\n",
       "      <th>46</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>5.0</td>\n",
       "      <td>20.36</td>\n",
       "      <td>1197.0</td>\n",
       "      <td>78.90</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2012.0</td>\n",
       "      <td>53000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>5.0</td>\n",
       "      <td>17.20</td>\n",
       "      <td>1396.0</td>\n",
       "      <td>53.50</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2007.0</td>\n",
       "      <td>200000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>5.0</td>\n",
       "      <td>19.81</td>\n",
       "      <td>1086.0</td>\n",
       "      <td>68.05</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2010.0</td>\n",
       "      <td>55000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>5.0</td>\n",
       "      <td>14.16</td>\n",
       "      <td>1968.0</td>\n",
       "      <td>174.30</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2016.0</td>\n",
       "      <td>43000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>7.0</td>\n",
       "      <td>15.10</td>\n",
       "      <td>2179.0</td>\n",
       "      <td>140.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2014.0</td>\n",
       "      <td>31000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4378</th>\n",
       "      <td>5.0</td>\n",
       "      <td>15.68</td>\n",
       "      <td>1999.0</td>\n",
       "      <td>177.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2018.0</td>\n",
       "      <td>31427.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4379</th>\n",
       "      <td>5.0</td>\n",
       "      <td>18.60</td>\n",
       "      <td>1197.0</td>\n",
       "      <td>81.83</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2015.0</td>\n",
       "      <td>53000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4380</th>\n",
       "      <td>5.0</td>\n",
       "      <td>10.80</td>\n",
       "      <td>2354.0</td>\n",
       "      <td>152.00</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2008.0</td>\n",
       "      <td>92000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4381</th>\n",
       "      <td>5.0</td>\n",
       "      <td>24.00</td>\n",
       "      <td>1120.0</td>\n",
       "      <td>70.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2017.0</td>\n",
       "      <td>33000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4382</th>\n",
       "      <td>5.0</td>\n",
       "      <td>14.70</td>\n",
       "      <td>1150.0</td>\n",
       "      <td>76.00</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2009.0</td>\n",
       "      <td>75000.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4383 rows × 47 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       0      1       2       3    4    5    6    7    8    9   ...   37   38  \\\n",
       "0     5.0  20.36  1197.0   78.90  0.0  0.0  0.0  0.0  0.0  1.0  ...  0.0  0.0   \n",
       "1     5.0  17.20  1396.0   53.50  1.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0   \n",
       "2     5.0  19.81  1086.0   68.05  1.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0   \n",
       "3     5.0  14.16  1968.0  174.30  0.0  0.0  0.0  0.0  0.0  1.0  ...  0.0  0.0   \n",
       "4     7.0  15.10  2179.0  140.00  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0   \n",
       "...   ...    ...     ...     ...  ...  ...  ...  ...  ...  ...  ...  ...  ...   \n",
       "4378  5.0  15.68  1999.0  177.00  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0   \n",
       "4379  5.0  18.60  1197.0   81.83  0.0  1.0  0.0  0.0  0.0  0.0  ...  0.0  0.0   \n",
       "4380  5.0  10.80  2354.0  152.00  1.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0   \n",
       "4381  5.0  24.00  1120.0   70.00  0.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0   \n",
       "4382  5.0  14.70  1150.0   76.00  1.0  0.0  0.0  0.0  0.0  0.0  ...  0.0  0.0   \n",
       "\n",
       "       39   40   41   42   43   44      45        46  \n",
       "0     0.0  0.0  0.0  0.0  0.0  0.0  2012.0   53000.0  \n",
       "1     0.0  0.0  1.0  0.0  0.0  0.0  2007.0  200000.0  \n",
       "2     0.0  0.0  0.0  0.0  0.0  0.0  2010.0   55000.0  \n",
       "3     0.0  0.0  0.0  0.0  0.0  0.0  2016.0   43000.0  \n",
       "4     0.0  0.0  0.0  0.0  0.0  0.0  2014.0   31000.0  \n",
       "...   ...  ...  ...  ...  ...  ...     ...       ...  \n",
       "4378  0.0  0.0  0.0  0.0  0.0  0.0  2018.0   31427.0  \n",
       "4379  0.0  0.0  0.0  0.0  0.0  0.0  2015.0   53000.0  \n",
       "4380  0.0  0.0  0.0  0.0  0.0  0.0  2008.0   92000.0  \n",
       "4381  0.0  0.0  0.0  0.0  0.0  0.0  2017.0   33000.0  \n",
       "4382  0.0  0.0  0.0  0.0  0.0  0.0  2009.0   75000.0  \n",
       "\n",
       "[4383 rows x 47 columns]"
      ]
     },
     "execution_count": 58,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.DataFrame(x_train_transformed)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "257bb2c0",
   "metadata": {},
   "outputs": [],
   "source": [
    "df['Name'].nunique()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}