Metroploitian Cities House Price prediction.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "banglore_dataset = pd.read_csv('Bangalore.csv')\n",
    "Mumbai_dataset = pd.read_csv('Mumbai.csv')\n",
    "Kolkata_dataset = pd.read_csv('Kolkata.csv')\n",
    "Delhi_dataset = pd.read_csv('Delhi.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "((1950, 44), (1397, 43), (74, 43), (2001, 43))"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "banglore_dataset.shape,Mumbai_dataset.shape,Kolkata_dataset.shape,Delhi_dataset.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "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>Unnamed: 0.1</th>\n",
       "      <th>Unnamed: 0.1.1</th>\n",
       "      <th>Unnamed: 0.1.1.1</th>\n",
       "      <th>Price</th>\n",
       "      <th>Area</th>\n",
       "      <th>Location</th>\n",
       "      <th>No. of Bedrooms</th>\n",
       "      <th>Resale</th>\n",
       "      <th>MaintenanceStaff</th>\n",
       "      <th>...</th>\n",
       "      <th>LiftAvailable</th>\n",
       "      <th>BED</th>\n",
       "      <th>VaastuCompliant</th>\n",
       "      <th>Microwave</th>\n",
       "      <th>GolfCourse</th>\n",
       "      <th>TV</th>\n",
       "      <th>DiningTable</th>\n",
       "      <th>Sofa</th>\n",
       "      <th>Wardrobe</th>\n",
       "      <th>Refrigerator</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.000000e-08</td>\n",
       "      <td>3340</td>\n",
       "      <td>JP Nagar Phase 1</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>7.888000e-09</td>\n",
       "      <td>1045</td>\n",
       "      <td>Dasarahalli on Tumkur Road</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>1.0</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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>4.866000e-09</td>\n",
       "      <td>1179</td>\n",
       "      <td>Kannur on Thanisandra Main Road</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>8.358000e-09</td>\n",
       "      <td>1675</td>\n",
       "      <td>Doddanekundi</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>4.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>6.845000e-09</td>\n",
       "      <td>1670</td>\n",
       "      <td>Kengeri</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 44 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   Unnamed: 0  Unnamed: 0.1  Unnamed: 0.1.1  Unnamed: 0.1.1.1         Price  \\\n",
       "0           0             0             0.0               0.0  3.000000e-08   \n",
       "1           1             1             1.0               1.0  7.888000e-09   \n",
       "2           2             2             2.0               2.0  4.866000e-09   \n",
       "3           3             3             3.0               3.0  8.358000e-09   \n",
       "4           4             4             4.0               4.0  6.845000e-09   \n",
       "\n",
       "   Area                         Location  No. of Bedrooms  Resale  \\\n",
       "0  3340                 JP Nagar Phase 1                4       0   \n",
       "1  1045       Dasarahalli on Tumkur Road                2       0   \n",
       "2  1179  Kannur on Thanisandra Main Road                2       0   \n",
       "3  1675                     Doddanekundi                3       0   \n",
       "4  1670                          Kengeri                3       0   \n",
       "\n",
       "   MaintenanceStaff  ...  LiftAvailable  BED  VaastuCompliant  Microwave  \\\n",
       "0               1.0  ...            1.0  0.0              0.0        0.0   \n",
       "1               0.0  ...            1.0  0.0              1.0        0.0   \n",
       "2               0.0  ...            1.0  0.0              0.0        0.0   \n",
       "3               0.0  ...            1.0  0.0              0.0        0.0   \n",
       "4               1.0  ...            1.0  0.0              0.0        0.0   \n",
       "\n",
       "   GolfCourse   TV  DiningTable  Sofa  Wardrobe  Refrigerator  \n",
       "0         0.0  0.0          0.0   0.0       0.0           0.0  \n",
       "1         0.0  0.0          0.0   0.0       0.0           0.0  \n",
       "2         0.0  0.0          0.0   0.0       0.0           0.0  \n",
       "3         0.0  0.0          0.0   0.0       0.0           0.0  \n",
       "4         0.0  0.0          0.0   0.0       0.0           0.0  \n",
       "\n",
       "[5 rows x 44 columns]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "banglore_dataset.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Unnamed: 0</th>\n",
       "      <th>Unnamed: 0.1</th>\n",
       "      <th>Unnamed: 0.1.1</th>\n",
       "      <th>Price</th>\n",
       "      <th>Area</th>\n",
       "      <th>Location</th>\n",
       "      <th>No. of Bedrooms</th>\n",
       "      <th>Resale</th>\n",
       "      <th>MaintenanceStaff</th>\n",
       "      <th>Gymnasium</th>\n",
       "      <th>...</th>\n",
       "      <th>LiftAvailable</th>\n",
       "      <th>BED</th>\n",
       "      <th>VaastuCompliant</th>\n",
       "      <th>Microwave</th>\n",
       "      <th>GolfCourse</th>\n",
       "      <th>TV</th>\n",
       "      <th>DiningTable</th>\n",
       "      <th>Sofa</th>\n",
       "      <th>Wardrobe</th>\n",
       "      <th>Refrigerator</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4.850000e-09</td>\n",
       "      <td>720</td>\n",
       "      <td>Kharghar</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>1.0</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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>4.500000e-09</td>\n",
       "      <td>600</td>\n",
       "      <td>Kharghar</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>1.0</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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>2.0</td>\n",
       "      <td>6.700000e-09</td>\n",
       "      <td>650</td>\n",
       "      <td>Kharghar</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>1.0</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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>3.0</td>\n",
       "      <td>4.500000e-09</td>\n",
       "      <td>650</td>\n",
       "      <td>Kharghar</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</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>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>4.0</td>\n",
       "      <td>5.000000e-09</td>\n",
       "      <td>665</td>\n",
       "      <td>Kharghar</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>1.0</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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 43 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   Unnamed: 0  Unnamed: 0.1  Unnamed: 0.1.1         Price  Area  Location  \\\n",
       "0           0             0             0.0  4.850000e-09   720  Kharghar   \n",
       "1           1             1             1.0  4.500000e-09   600  Kharghar   \n",
       "2           2             2             2.0  6.700000e-09   650  Kharghar   \n",
       "3           3             3             3.0  4.500000e-09   650  Kharghar   \n",
       "4           4             4             4.0  5.000000e-09   665  Kharghar   \n",
       "\n",
       "   No. of Bedrooms  Resale  MaintenanceStaff  Gymnasium  ...  LiftAvailable  \\\n",
       "0                1       1               1.0        0.0  ...            1.0   \n",
       "1                1       1               1.0        1.0  ...            1.0   \n",
       "2                1       1               1.0        1.0  ...            1.0   \n",
       "3                1       1               1.0        0.0  ...            1.0   \n",
       "4                1       1               1.0        0.0  ...            1.0   \n",
       "\n",
       "   BED  VaastuCompliant  Microwave  GolfCourse   TV  DiningTable  Sofa  \\\n",
       "0  0.0              1.0        0.0         0.0  0.0          0.0   0.0   \n",
       "1  0.0              1.0        0.0         0.0  0.0          0.0   0.0   \n",
       "2  0.0              1.0        0.0         0.0  0.0          0.0   0.0   \n",
       "3  1.0              1.0        0.0         0.0  0.0          0.0   0.0   \n",
       "4  0.0              1.0        0.0         0.0  0.0          0.0   0.0   \n",
       "\n",
       "   Wardrobe  Refrigerator  \n",
       "0       0.0           0.0  \n",
       "1       0.0           0.0  \n",
       "2       0.0           0.0  \n",
       "3       1.0           0.0  \n",
       "4       0.0           0.0  \n",
       "\n",
       "[5 rows x 43 columns]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Mumbai_dataset.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Unnamed: 0</th>\n",
       "      <th>Unnamed: 0.1</th>\n",
       "      <th>Unnamed: 0.1.1</th>\n",
       "      <th>Price</th>\n",
       "      <th>Area</th>\n",
       "      <th>Location</th>\n",
       "      <th>No. of Bedrooms</th>\n",
       "      <th>Resale</th>\n",
       "      <th>MaintenanceStaff</th>\n",
       "      <th>Gymnasium</th>\n",
       "      <th>...</th>\n",
       "      <th>LiftAvailable</th>\n",
       "      <th>BED</th>\n",
       "      <th>VaastuCompliant</th>\n",
       "      <th>Microwave</th>\n",
       "      <th>GolfCourse</th>\n",
       "      <th>TV</th>\n",
       "      <th>DiningTable</th>\n",
       "      <th>Sofa</th>\n",
       "      <th>Wardrobe</th>\n",
       "      <th>Refrigerator</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.235000e-09</td>\n",
       "      <td>1016</td>\n",
       "      <td>Barasat</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3.665999e-09</td>\n",
       "      <td>1111</td>\n",
       "      <td>Keshtopur</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1.0</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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.774000e-09</td>\n",
       "      <td>1020</td>\n",
       "      <td>Rajarhat</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>3.0</td>\n",
       "      <td>2.524000e-09</td>\n",
       "      <td>935</td>\n",
       "      <td>Narendrapur</td>\n",
       "      <td>2.0</td>\n",
       "      <td>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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>4.0</td>\n",
       "      <td>8.300000e-09</td>\n",
       "      <td>1956</td>\n",
       "      <td>New Town</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>1.0</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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 43 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   Unnamed: 0  Unnamed: 0.1  Unnamed: 0.1.1         Price  Area     Location  \\\n",
       "0           0             0             0.0  2.235000e-09  1016      Barasat   \n",
       "1           1             1             1.0  3.665999e-09  1111    Keshtopur   \n",
       "2           2             2             2.0  3.774000e-09  1020     Rajarhat   \n",
       "3           3             3             3.0  2.524000e-09   935  Narendrapur   \n",
       "4           4             4             4.0  8.300000e-09  1956     New Town   \n",
       "\n",
       "   No. of Bedrooms  Resale  MaintenanceStaff  Gymnasium  ...  LiftAvailable  \\\n",
       "0              3.0       0               0.0        1.0  ...            1.0   \n",
       "1              2.0       0               1.0        1.0  ...            0.0   \n",
       "2              2.0       0               0.0        1.0  ...            1.0   \n",
       "3              2.0       0               0.0        1.0  ...            0.0   \n",
       "4              3.0       1               0.0        1.0  ...            1.0   \n",
       "\n",
       "   BED  VaastuCompliant  Microwave  GolfCourse   TV  DiningTable  Sofa  \\\n",
       "0  0.0              0.0        0.0         0.0  0.0          0.0   0.0   \n",
       "1  0.0              0.0        0.0         0.0  0.0          0.0   0.0   \n",
       "2  0.0              0.0        0.0         0.0  0.0          0.0   0.0   \n",
       "3  0.0              0.0        0.0         0.0  0.0          0.0   0.0   \n",
       "4  0.0              1.0        0.0         0.0  0.0          0.0   0.0   \n",
       "\n",
       "   Wardrobe  Refrigerator  \n",
       "0       0.0           0.0  \n",
       "1       0.0           0.0  \n",
       "2       0.0           0.0  \n",
       "3       0.0           0.0  \n",
       "4       0.0           0.0  \n",
       "\n",
       "[5 rows x 43 columns]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Kolkata_dataset.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Unnamed: 0</th>\n",
       "      <th>Unnamed: 0.1</th>\n",
       "      <th>Unnamed: 0.1.1</th>\n",
       "      <th>Price</th>\n",
       "      <th>Area</th>\n",
       "      <th>Location</th>\n",
       "      <th>No. of Bedrooms</th>\n",
       "      <th>Resale</th>\n",
       "      <th>MaintenanceStaff</th>\n",
       "      <th>Gymnasium</th>\n",
       "      <th>...</th>\n",
       "      <th>LiftAvailable</th>\n",
       "      <th>BED</th>\n",
       "      <th>VaastuCompliant</th>\n",
       "      <th>Microwave</th>\n",
       "      <th>GolfCourse</th>\n",
       "      <th>TV</th>\n",
       "      <th>DiningTable</th>\n",
       "      <th>Sofa</th>\n",
       "      <th>Wardrobe</th>\n",
       "      <th>Refrigerator</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.050000e-08</td>\n",
       "      <td>1200</td>\n",
       "      <td>Sector 10 Dwarka</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>1.0</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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>6.000000e-09</td>\n",
       "      <td>1000</td>\n",
       "      <td>Uttam Nagar</td>\n",
       "      <td>3</td>\n",
       "      <td>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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.500000e-08</td>\n",
       "      <td>1350</td>\n",
       "      <td>Sarita Vihar</td>\n",
       "      <td>2</td>\n",
       "      <td>1</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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>3.0</td>\n",
       "      <td>2.500000e-09</td>\n",
       "      <td>435</td>\n",
       "      <td>Uttam Nagar</td>\n",
       "      <td>2</td>\n",
       "      <td>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>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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>4.0</td>\n",
       "      <td>5.800000e-09</td>\n",
       "      <td>900</td>\n",
       "      <td>Dwarka Mor</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 43 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   Unnamed: 0  Unnamed: 0.1  Unnamed: 0.1.1         Price  Area  \\\n",
       "0           0             0             0.0  1.050000e-08  1200   \n",
       "1           1             1             1.0  6.000000e-09  1000   \n",
       "2           2             2             2.0  1.500000e-08  1350   \n",
       "3           3             3             3.0  2.500000e-09   435   \n",
       "4           4             4             4.0  5.800000e-09   900   \n",
       "\n",
       "           Location  No. of Bedrooms  Resale  MaintenanceStaff  Gymnasium  \\\n",
       "0  Sector 10 Dwarka                2       1               0.0        1.0   \n",
       "1       Uttam Nagar                3       0               0.0        0.0   \n",
       "2      Sarita Vihar                2       1               0.0        0.0   \n",
       "3       Uttam Nagar                2       0               0.0        0.0   \n",
       "4        Dwarka Mor                3       0               0.0        0.0   \n",
       "\n",
       "   ...  LiftAvailable  BED  VaastuCompliant  Microwave  GolfCourse   TV  \\\n",
       "0  ...            1.0  0.0              1.0        0.0         0.0  0.0   \n",
       "1  ...            0.0  0.0              0.0        0.0         0.0  0.0   \n",
       "2  ...            0.0  0.0              0.0        0.0         0.0  0.0   \n",
       "3  ...            0.0  0.0              1.0        0.0         0.0  0.0   \n",
       "4  ...            1.0  0.0              0.0        0.0         0.0  0.0   \n",
       "\n",
       "   DiningTable  Sofa  Wardrobe  Refrigerator  \n",
       "0          0.0   0.0       0.0           0.0  \n",
       "1          0.0   0.0       0.0           0.0  \n",
       "2          0.0   0.0       0.0           0.0  \n",
       "3          0.0   0.0       0.0           0.0  \n",
       "4          0.0   0.0       0.0           0.0  \n",
       "\n",
       "[5 rows x 43 columns]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Delhi_dataset.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##Since for a set of houses, nothing was mentioned about certain amenities, '9' was used to mark such values, which could indicate the absence of information about the apartment but these values don't ascertain the absence of such a feature in real life.\n",
    "\n",
    "We will be dropping these values so that they don't cloud our analysis."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "banglore_dataset.replace(9,np.nan,inplace=True)\n",
    "Mumbai_dataset.replace(9,np.nan,inplace=True)\n",
    "Kolkata_dataset.replace(9,np.nan,inplace=True)\n",
    "Delhi_dataset.replace(9,np.nan,inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "banglore_dataset = banglore_dataset.dropna()\n",
    "Mumbai_dataset = Mumbai_dataset.dropna()\n",
    "Kolkata_dataset = Kolkata_dataset.dropna()\n",
    "Delhi_dataset = Delhi_dataset.dropna()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Banglore: (1949, 44)\n",
      "Mumbai: (1396, 43)\n",
      "Kolkata: (73, 43)\n",
      "Delhi: (2000, 43)\n"
     ]
    }
   ],
   "source": [
    "print(\"Banglore:\",banglore_dataset.shape)\n",
    "print(\"Mumbai:\",Mumbai_dataset.shape)\n",
    "print(\"Kolkata:\",Kolkata_dataset.shape)\n",
    "print(\"Delhi:\",Delhi_dataset.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Int64Index: 1949 entries, 0 to 1949\n",
      "Data columns (total 44 columns):\n",
      " #   Column               Non-Null Count  Dtype  \n",
      "---  ------               --------------  -----  \n",
      " 0   Unnamed: 0           1949 non-null   float64\n",
      " 1   Unnamed: 0.1         1949 non-null   int64  \n",
      " 2   Unnamed: 0.1.1       1949 non-null   float64\n",
      " 3   Unnamed: 0.1.1.1     1949 non-null   float64\n",
      " 4   Price                1949 non-null   float64\n",
      " 5   Area                 1949 non-null   int64  \n",
      " 6   Location             1949 non-null   object \n",
      " 7   No. of Bedrooms      1949 non-null   int64  \n",
      " 8   Resale               1949 non-null   int64  \n",
      " 9   MaintenanceStaff     1949 non-null   float64\n",
      " 10  Gymnasium            1949 non-null   float64\n",
      " 11  SwimmingPool         1949 non-null   float64\n",
      " 12  LandscapedGardens    1949 non-null   float64\n",
      " 13  JoggingTrack         1949 non-null   float64\n",
      " 14  RainWaterHarvesting  1949 non-null   float64\n",
      " 15  IndoorGames          1949 non-null   float64\n",
      " 16  ShoppingMall         1949 non-null   float64\n",
      " 17  Intercom             1949 non-null   float64\n",
      " 18  SportsFacility       1949 non-null   float64\n",
      " 19  ATM                  1949 non-null   float64\n",
      " 20  ClubHouse            1949 non-null   float64\n",
      " 21  School               1949 non-null   float64\n",
      " 22  24X7Security         1949 non-null   float64\n",
      " 23  PowerBackup          1949 non-null   float64\n",
      " 24  CarParking           1949 non-null   float64\n",
      " 25  StaffQuarter         1949 non-null   float64\n",
      " 26  Cafeteria            1949 non-null   float64\n",
      " 27  MultipurposeRoom     1949 non-null   float64\n",
      " 28  Hospital             1949 non-null   float64\n",
      " 29  WashingMachine       1949 non-null   float64\n",
      " 30  Gasconnection        1949 non-null   float64\n",
      " 31  AC                   1949 non-null   float64\n",
      " 32  Wifi                 1949 non-null   float64\n",
      " 33  Children'splayarea   1949 non-null   float64\n",
      " 34  LiftAvailable        1949 non-null   float64\n",
      " 35  BED                  1949 non-null   float64\n",
      " 36  VaastuCompliant      1949 non-null   float64\n",
      " 37  Microwave            1949 non-null   float64\n",
      " 38  GolfCourse           1949 non-null   float64\n",
      " 39  TV                   1949 non-null   float64\n",
      " 40  DiningTable          1949 non-null   float64\n",
      " 41  Sofa                 1949 non-null   float64\n",
      " 42  Wardrobe             1949 non-null   float64\n",
      " 43  Refrigerator         1949 non-null   float64\n",
      "dtypes: float64(39), int64(4), object(1)\n",
      "memory usage: 685.2+ KB\n"
     ]
    }
   ],
   "source": [
    "banglore_dataset.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Int64Index: 1396 entries, 0 to 1396\n",
      "Data columns (total 43 columns):\n",
      " #   Column               Non-Null Count  Dtype  \n",
      "---  ------               --------------  -----  \n",
      " 0   Unnamed: 0           1396 non-null   float64\n",
      " 1   Unnamed: 0.1         1396 non-null   int64  \n",
      " 2   Unnamed: 0.1.1       1396 non-null   float64\n",
      " 3   Price                1396 non-null   float64\n",
      " 4   Area                 1396 non-null   int64  \n",
      " 5   Location             1396 non-null   object \n",
      " 6   No. of Bedrooms      1396 non-null   int64  \n",
      " 7   Resale               1396 non-null   int64  \n",
      " 8   MaintenanceStaff     1396 non-null   float64\n",
      " 9   Gymnasium            1396 non-null   float64\n",
      " 10  SwimmingPool         1396 non-null   float64\n",
      " 11  LandscapedGardens    1396 non-null   float64\n",
      " 12  JoggingTrack         1396 non-null   float64\n",
      " 13  RainWaterHarvesting  1396 non-null   float64\n",
      " 14  IndoorGames          1396 non-null   float64\n",
      " 15  ShoppingMall         1396 non-null   float64\n",
      " 16  Intercom             1396 non-null   float64\n",
      " 17  SportsFacility       1396 non-null   float64\n",
      " 18  ATM                  1396 non-null   float64\n",
      " 19  ClubHouse            1396 non-null   float64\n",
      " 20  School               1396 non-null   float64\n",
      " 21  24X7Security         1396 non-null   float64\n",
      " 22  PowerBackup          1396 non-null   float64\n",
      " 23  CarParking           1396 non-null   float64\n",
      " 24  StaffQuarter         1396 non-null   float64\n",
      " 25  Cafeteria            1396 non-null   float64\n",
      " 26  MultipurposeRoom     1396 non-null   float64\n",
      " 27  Hospital             1396 non-null   float64\n",
      " 28  WashingMachine       1396 non-null   float64\n",
      " 29  Gasconnection        1396 non-null   float64\n",
      " 30  AC                   1396 non-null   float64\n",
      " 31  Wifi                 1396 non-null   float64\n",
      " 32  Children'splayarea   1396 non-null   float64\n",
      " 33  LiftAvailable        1396 non-null   float64\n",
      " 34  BED                  1396 non-null   float64\n",
      " 35  VaastuCompliant      1396 non-null   float64\n",
      " 36  Microwave            1396 non-null   float64\n",
      " 37  GolfCourse           1396 non-null   float64\n",
      " 38  TV                   1396 non-null   float64\n",
      " 39  DiningTable          1396 non-null   float64\n",
      " 40  Sofa                 1396 non-null   float64\n",
      " 41  Wardrobe             1396 non-null   float64\n",
      " 42  Refrigerator         1396 non-null   float64\n",
      "dtypes: float64(38), int64(4), object(1)\n",
      "memory usage: 479.9+ KB\n"
     ]
    }
   ],
   "source": [
    "Mumbai_dataset.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Int64Index: 73 entries, 0 to 73\n",
      "Data columns (total 43 columns):\n",
      " #   Column               Non-Null Count  Dtype  \n",
      "---  ------               --------------  -----  \n",
      " 0   Unnamed: 0           73 non-null     float64\n",
      " 1   Unnamed: 0.1         73 non-null     int64  \n",
      " 2   Unnamed: 0.1.1       73 non-null     float64\n",
      " 3   Price                73 non-null     float64\n",
      " 4   Area                 73 non-null     int64  \n",
      " 5   Location             73 non-null     object \n",
      " 6   No. of Bedrooms      73 non-null     float64\n",
      " 7   Resale               73 non-null     int64  \n",
      " 8   MaintenanceStaff     73 non-null     float64\n",
      " 9   Gymnasium            73 non-null     float64\n",
      " 10  SwimmingPool         73 non-null     float64\n",
      " 11  LandscapedGardens    73 non-null     float64\n",
      " 12  JoggingTrack         73 non-null     float64\n",
      " 13  RainWaterHarvesting  73 non-null     float64\n",
      " 14  IndoorGames          73 non-null     float64\n",
      " 15  ShoppingMall         73 non-null     float64\n",
      " 16  Intercom             73 non-null     float64\n",
      " 17  SportsFacility       73 non-null     float64\n",
      " 18  ATM                  73 non-null     float64\n",
      " 19  ClubHouse            73 non-null     float64\n",
      " 20  School               73 non-null     float64\n",
      " 21  24X7Security         73 non-null     float64\n",
      " 22  PowerBackup          73 non-null     float64\n",
      " 23  CarParking           73 non-null     float64\n",
      " 24  StaffQuarter         73 non-null     float64\n",
      " 25  Cafeteria            73 non-null     float64\n",
      " 26  MultipurposeRoom     73 non-null     float64\n",
      " 27  Hospital             73 non-null     float64\n",
      " 28  WashingMachine       73 non-null     float64\n",
      " 29  Gasconnection        73 non-null     float64\n",
      " 30  AC                   73 non-null     float64\n",
      " 31  Wifi                 73 non-null     float64\n",
      " 32  Children'splayarea   73 non-null     float64\n",
      " 33  LiftAvailable        73 non-null     float64\n",
      " 34  BED                  73 non-null     float64\n",
      " 35  VaastuCompliant      73 non-null     float64\n",
      " 36  Microwave            73 non-null     float64\n",
      " 37  GolfCourse           73 non-null     float64\n",
      " 38  TV                   73 non-null     float64\n",
      " 39  DiningTable          73 non-null     float64\n",
      " 40  Sofa                 73 non-null     float64\n",
      " 41  Wardrobe             73 non-null     float64\n",
      " 42  Refrigerator         73 non-null     float64\n",
      "dtypes: float64(39), int64(3), object(1)\n",
      "memory usage: 25.1+ KB\n"
     ]
    }
   ],
   "source": [
    "Kolkata_dataset.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Int64Index: 2000 entries, 0 to 2000\n",
      "Data columns (total 43 columns):\n",
      " #   Column               Non-Null Count  Dtype  \n",
      "---  ------               --------------  -----  \n",
      " 0   Unnamed: 0           2000 non-null   float64\n",
      " 1   Unnamed: 0.1         2000 non-null   int64  \n",
      " 2   Unnamed: 0.1.1       2000 non-null   float64\n",
      " 3   Price                2000 non-null   float64\n",
      " 4   Area                 2000 non-null   int64  \n",
      " 5   Location             2000 non-null   object \n",
      " 6   No. of Bedrooms      2000 non-null   int64  \n",
      " 7   Resale               2000 non-null   int64  \n",
      " 8   MaintenanceStaff     2000 non-null   float64\n",
      " 9   Gymnasium            2000 non-null   float64\n",
      " 10  SwimmingPool         2000 non-null   float64\n",
      " 11  LandscapedGardens    2000 non-null   float64\n",
      " 12  JoggingTrack         2000 non-null   float64\n",
      " 13  RainWaterHarvesting  2000 non-null   float64\n",
      " 14  IndoorGames          2000 non-null   float64\n",
      " 15  ShoppingMall         2000 non-null   float64\n",
      " 16  Intercom             2000 non-null   float64\n",
      " 17  SportsFacility       2000 non-null   float64\n",
      " 18  ATM                  2000 non-null   float64\n",
      " 19  ClubHouse            2000 non-null   float64\n",
      " 20  School               2000 non-null   float64\n",
      " 21  24X7Security         2000 non-null   float64\n",
      " 22  PowerBackup          2000 non-null   float64\n",
      " 23  CarParking           2000 non-null   float64\n",
      " 24  StaffQuarter         2000 non-null   float64\n",
      " 25  Cafeteria            2000 non-null   float64\n",
      " 26  MultipurposeRoom     2000 non-null   float64\n",
      " 27  Hospital             2000 non-null   float64\n",
      " 28  WashingMachine       2000 non-null   float64\n",
      " 29  Gasconnection        2000 non-null   float64\n",
      " 30  AC                   2000 non-null   float64\n",
      " 31  Wifi                 2000 non-null   float64\n",
      " 32  Children'splayarea   2000 non-null   float64\n",
      " 33  LiftAvailable        2000 non-null   float64\n",
      " 34  BED                  2000 non-null   float64\n",
      " 35  VaastuCompliant      2000 non-null   float64\n",
      " 36  Microwave            2000 non-null   float64\n",
      " 37  GolfCourse           2000 non-null   float64\n",
      " 38  TV                   2000 non-null   float64\n",
      " 39  DiningTable          2000 non-null   float64\n",
      " 40  Sofa                 2000 non-null   float64\n",
      " 41  Wardrobe             2000 non-null   float64\n",
      " 42  Refrigerator         2000 non-null   float64\n",
      "dtypes: float64(38), int64(4), object(1)\n",
      "memory usage: 687.5+ KB\n"
     ]
    }
   ],
   "source": [
    "Delhi_dataset.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "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>Unnamed: 0.1</th>\n",
       "      <th>Unnamed: 0.1.1</th>\n",
       "      <th>Price</th>\n",
       "      <th>Area</th>\n",
       "      <th>No. of Bedrooms</th>\n",
       "      <th>Resale</th>\n",
       "      <th>MaintenanceStaff</th>\n",
       "      <th>Gymnasium</th>\n",
       "      <th>SwimmingPool</th>\n",
       "      <th>...</th>\n",
       "      <th>LiftAvailable</th>\n",
       "      <th>BED</th>\n",
       "      <th>VaastuCompliant</th>\n",
       "      <th>Microwave</th>\n",
       "      <th>GolfCourse</th>\n",
       "      <th>TV</th>\n",
       "      <th>DiningTable</th>\n",
       "      <th>Sofa</th>\n",
       "      <th>Wardrobe</th>\n",
       "      <th>Refrigerator</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>1396.000000</td>\n",
       "      <td>1396.000000</td>\n",
       "      <td>1396.000000</td>\n",
       "      <td>1.396000e+03</td>\n",
       "      <td>1396.000000</td>\n",
       "      <td>1396.000000</td>\n",
       "      <td>1396.000000</td>\n",
       "      <td>1396.000000</td>\n",
       "      <td>1396.000000</td>\n",
       "      <td>1396.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>1396.000000</td>\n",
       "      <td>1396.000000</td>\n",
       "      <td>1396.000000</td>\n",
       "      <td>1396.000000</td>\n",
       "      <td>1396.000000</td>\n",
       "      <td>1396.000000</td>\n",
       "      <td>1396.000000</td>\n",
       "      <td>1396.000000</td>\n",
       "      <td>1396.000000</td>\n",
       "      <td>1396.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>698.493553</td>\n",
       "      <td>699.487106</td>\n",
       "      <td>699.487106</td>\n",
       "      <td>1.542958e-08</td>\n",
       "      <td>1074.368911</td>\n",
       "      <td>1.957736</td>\n",
       "      <td>0.767908</td>\n",
       "      <td>0.711318</td>\n",
       "      <td>0.573066</td>\n",
       "      <td>0.373926</td>\n",
       "      <td>...</td>\n",
       "      <td>0.818768</td>\n",
       "      <td>0.265043</td>\n",
       "      <td>0.467049</td>\n",
       "      <td>0.011461</td>\n",
       "      <td>0.053725</td>\n",
       "      <td>0.050143</td>\n",
       "      <td>0.020057</td>\n",
       "      <td>0.025072</td>\n",
       "      <td>0.077364</td>\n",
       "      <td>0.026504</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>403.145906</td>\n",
       "      <td>403.157028</td>\n",
       "      <td>403.157028</td>\n",
       "      <td>2.531016e-08</td>\n",
       "      <td>591.049782</td>\n",
       "      <td>0.871083</td>\n",
       "      <td>0.422318</td>\n",
       "      <td>0.453312</td>\n",
       "      <td>0.494810</td>\n",
       "      <td>0.484018</td>\n",
       "      <td>...</td>\n",
       "      <td>0.385348</td>\n",
       "      <td>0.441514</td>\n",
       "      <td>0.499092</td>\n",
       "      <td>0.106480</td>\n",
       "      <td>0.225555</td>\n",
       "      <td>0.218319</td>\n",
       "      <td>0.140247</td>\n",
       "      <td>0.156399</td>\n",
       "      <td>0.267264</td>\n",
       "      <td>0.160687</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2.000000e-09</td>\n",
       "      <td>245.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>349.750000</td>\n",
       "      <td>350.750000</td>\n",
       "      <td>350.750000</td>\n",
       "      <td>5.500000e-09</td>\n",
       "      <td>650.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>698.500000</td>\n",
       "      <td>699.500000</td>\n",
       "      <td>699.500000</td>\n",
       "      <td>9.950000e-09</td>\n",
       "      <td>1011.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>1047.250000</td>\n",
       "      <td>1048.250000</td>\n",
       "      <td>1048.250000</td>\n",
       "      <td>1.685000e-08</td>\n",
       "      <td>1310.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>1396.000000</td>\n",
       "      <td>1397.000000</td>\n",
       "      <td>1397.000000</td>\n",
       "      <td>4.000000e-07</td>\n",
       "      <td>7000.000000</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>8 rows × 42 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        Unnamed: 0  Unnamed: 0.1  Unnamed: 0.1.1         Price         Area  \\\n",
       "count  1396.000000   1396.000000     1396.000000  1.396000e+03  1396.000000   \n",
       "mean    698.493553    699.487106      699.487106  1.542958e-08  1074.368911   \n",
       "std     403.145906    403.157028      403.157028  2.531016e-08   591.049782   \n",
       "min       0.000000      0.000000        0.000000  2.000000e-09   245.000000   \n",
       "25%     349.750000    350.750000      350.750000  5.500000e-09   650.000000   \n",
       "50%     698.500000    699.500000      699.500000  9.950000e-09  1011.000000   \n",
       "75%    1047.250000   1048.250000     1048.250000  1.685000e-08  1310.000000   \n",
       "max    1396.000000   1397.000000     1397.000000  4.000000e-07  7000.000000   \n",
       "\n",
       "       No. of Bedrooms       Resale  MaintenanceStaff    Gymnasium  \\\n",
       "count      1396.000000  1396.000000       1396.000000  1396.000000   \n",
       "mean          1.957736     0.767908          0.711318     0.573066   \n",
       "std           0.871083     0.422318          0.453312     0.494810   \n",
       "min           1.000000     0.000000          0.000000     0.000000   \n",
       "25%           1.000000     1.000000          0.000000     0.000000   \n",
       "50%           2.000000     1.000000          1.000000     1.000000   \n",
       "75%           3.000000     1.000000          1.000000     1.000000   \n",
       "max           6.000000     1.000000          1.000000     1.000000   \n",
       "\n",
       "       SwimmingPool  ...  LiftAvailable          BED  VaastuCompliant  \\\n",
       "count   1396.000000  ...    1396.000000  1396.000000      1396.000000   \n",
       "mean       0.373926  ...       0.818768     0.265043         0.467049   \n",
       "std        0.484018  ...       0.385348     0.441514         0.499092   \n",
       "min        0.000000  ...       0.000000     0.000000         0.000000   \n",
       "25%        0.000000  ...       1.000000     0.000000         0.000000   \n",
       "50%        0.000000  ...       1.000000     0.000000         0.000000   \n",
       "75%        1.000000  ...       1.000000     1.000000         1.000000   \n",
       "max        1.000000  ...       1.000000     1.000000         1.000000   \n",
       "\n",
       "         Microwave   GolfCourse           TV  DiningTable         Sofa  \\\n",
       "count  1396.000000  1396.000000  1396.000000  1396.000000  1396.000000   \n",
       "mean      0.011461     0.053725     0.050143     0.020057     0.025072   \n",
       "std       0.106480     0.225555     0.218319     0.140247     0.156399   \n",
       "min       0.000000     0.000000     0.000000     0.000000     0.000000   \n",
       "25%       0.000000     0.000000     0.000000     0.000000     0.000000   \n",
       "50%       0.000000     0.000000     0.000000     0.000000     0.000000   \n",
       "75%       0.000000     0.000000     0.000000     0.000000     0.000000   \n",
       "max       1.000000     1.000000     1.000000     1.000000     1.000000   \n",
       "\n",
       "          Wardrobe  Refrigerator  \n",
       "count  1396.000000   1396.000000  \n",
       "mean      0.077364      0.026504  \n",
       "std       0.267264      0.160687  \n",
       "min       0.000000      0.000000  \n",
       "25%       0.000000      0.000000  \n",
       "50%       0.000000      0.000000  \n",
       "75%       0.000000      0.000000  \n",
       "max       1.000000      1.000000  \n",
       "\n",
       "[8 rows x 42 columns]"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Mumbai_dataset.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "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>Unnamed: 0.1</th>\n",
       "      <th>Unnamed: 0.1.1</th>\n",
       "      <th>Price</th>\n",
       "      <th>Area</th>\n",
       "      <th>No. of Bedrooms</th>\n",
       "      <th>Resale</th>\n",
       "      <th>MaintenanceStaff</th>\n",
       "      <th>Gymnasium</th>\n",
       "      <th>SwimmingPool</th>\n",
       "      <th>...</th>\n",
       "      <th>LiftAvailable</th>\n",
       "      <th>BED</th>\n",
       "      <th>VaastuCompliant</th>\n",
       "      <th>Microwave</th>\n",
       "      <th>GolfCourse</th>\n",
       "      <th>TV</th>\n",
       "      <th>DiningTable</th>\n",
       "      <th>Sofa</th>\n",
       "      <th>Wardrobe</th>\n",
       "      <th>Refrigerator</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>73.000000</td>\n",
       "      <td>73.000000</td>\n",
       "      <td>73.000000</td>\n",
       "      <td>7.300000e+01</td>\n",
       "      <td>73.000000</td>\n",
       "      <td>73.000000</td>\n",
       "      <td>73.000000</td>\n",
       "      <td>73.000000</td>\n",
       "      <td>73.000000</td>\n",
       "      <td>73.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>73.000000</td>\n",
       "      <td>73.000000</td>\n",
       "      <td>73.000000</td>\n",
       "      <td>73.000000</td>\n",
       "      <td>73.000000</td>\n",
       "      <td>73.000000</td>\n",
       "      <td>73.000000</td>\n",
       "      <td>73.000000</td>\n",
       "      <td>73.0</td>\n",
       "      <td>73.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>36.876712</td>\n",
       "      <td>37.753425</td>\n",
       "      <td>37.753425</td>\n",
       "      <td>6.663712e-09</td>\n",
       "      <td>1281.095890</td>\n",
       "      <td>2.561644</td>\n",
       "      <td>0.356164</td>\n",
       "      <td>0.232877</td>\n",
       "      <td>0.575342</td>\n",
       "      <td>0.452055</td>\n",
       "      <td>...</td>\n",
       "      <td>0.753425</td>\n",
       "      <td>0.068493</td>\n",
       "      <td>0.246575</td>\n",
       "      <td>0.068493</td>\n",
       "      <td>0.041096</td>\n",
       "      <td>0.041096</td>\n",
       "      <td>0.054795</td>\n",
       "      <td>0.068493</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.068493</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>21.407388</td>\n",
       "      <td>21.601042</td>\n",
       "      <td>21.601042</td>\n",
       "      <td>7.611397e-09</td>\n",
       "      <td>793.350545</td>\n",
       "      <td>0.645202</td>\n",
       "      <td>0.482179</td>\n",
       "      <td>0.425589</td>\n",
       "      <td>0.497712</td>\n",
       "      <td>0.501140</td>\n",
       "      <td>...</td>\n",
       "      <td>0.434000</td>\n",
       "      <td>0.254338</td>\n",
       "      <td>0.434000</td>\n",
       "      <td>0.254338</td>\n",
       "      <td>0.199886</td>\n",
       "      <td>0.199886</td>\n",
       "      <td>0.229154</td>\n",
       "      <td>0.254338</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.254338</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2.099000e-09</td>\n",
       "      <td>350.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>19.000000</td>\n",
       "      <td>20.000000</td>\n",
       "      <td>20.000000</td>\n",
       "      <td>3.200000e-09</td>\n",
       "      <td>875.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>37.000000</td>\n",
       "      <td>38.000000</td>\n",
       "      <td>38.000000</td>\n",
       "      <td>3.774000e-09</td>\n",
       "      <td>1107.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>55.000000</td>\n",
       "      <td>56.000000</td>\n",
       "      <td>56.000000</td>\n",
       "      <td>7.936000e-09</td>\n",
       "      <td>1319.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>73.000000</td>\n",
       "      <td>74.000000</td>\n",
       "      <td>74.000000</td>\n",
       "      <td>4.500000e-08</td>\n",
       "      <td>5000.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>8 rows × 42 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       Unnamed: 0  Unnamed: 0.1  Unnamed: 0.1.1         Price         Area  \\\n",
       "count   73.000000     73.000000       73.000000  7.300000e+01    73.000000   \n",
       "mean    36.876712     37.753425       37.753425  6.663712e-09  1281.095890   \n",
       "std     21.407388     21.601042       21.601042  7.611397e-09   793.350545   \n",
       "min      0.000000      0.000000        0.000000  2.099000e-09   350.000000   \n",
       "25%     19.000000     20.000000       20.000000  3.200000e-09   875.000000   \n",
       "50%     37.000000     38.000000       38.000000  3.774000e-09  1107.000000   \n",
       "75%     55.000000     56.000000       56.000000  7.936000e-09  1319.000000   \n",
       "max     73.000000     74.000000       74.000000  4.500000e-08  5000.000000   \n",
       "\n",
       "       No. of Bedrooms     Resale  MaintenanceStaff  Gymnasium  SwimmingPool  \\\n",
       "count        73.000000  73.000000         73.000000  73.000000     73.000000   \n",
       "mean          2.561644   0.356164          0.232877   0.575342      0.452055   \n",
       "std           0.645202   0.482179          0.425589   0.497712      0.501140   \n",
       "min           1.000000   0.000000          0.000000   0.000000      0.000000   \n",
       "25%           2.000000   0.000000          0.000000   0.000000      0.000000   \n",
       "50%           3.000000   0.000000          0.000000   1.000000      0.000000   \n",
       "75%           3.000000   1.000000          0.000000   1.000000      1.000000   \n",
       "max           4.000000   1.000000          1.000000   1.000000      1.000000   \n",
       "\n",
       "       ...  LiftAvailable        BED  VaastuCompliant  Microwave  GolfCourse  \\\n",
       "count  ...      73.000000  73.000000        73.000000  73.000000   73.000000   \n",
       "mean   ...       0.753425   0.068493         0.246575   0.068493    0.041096   \n",
       "std    ...       0.434000   0.254338         0.434000   0.254338    0.199886   \n",
       "min    ...       0.000000   0.000000         0.000000   0.000000    0.000000   \n",
       "25%    ...       1.000000   0.000000         0.000000   0.000000    0.000000   \n",
       "50%    ...       1.000000   0.000000         0.000000   0.000000    0.000000   \n",
       "75%    ...       1.000000   0.000000         0.000000   0.000000    0.000000   \n",
       "max    ...       1.000000   1.000000         1.000000   1.000000    1.000000   \n",
       "\n",
       "              TV  DiningTable       Sofa  Wardrobe  Refrigerator  \n",
       "count  73.000000    73.000000  73.000000      73.0     73.000000  \n",
       "mean    0.041096     0.054795   0.068493       0.0      0.068493  \n",
       "std     0.199886     0.229154   0.254338       0.0      0.254338  \n",
       "min     0.000000     0.000000   0.000000       0.0      0.000000  \n",
       "25%     0.000000     0.000000   0.000000       0.0      0.000000  \n",
       "50%     0.000000     0.000000   0.000000       0.0      0.000000  \n",
       "75%     0.000000     0.000000   0.000000       0.0      0.000000  \n",
       "max     1.000000     1.000000   1.000000       0.0      1.000000  \n",
       "\n",
       "[8 rows x 42 columns]"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Kolkata_dataset.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Unnamed: 0</th>\n",
       "      <th>Unnamed: 0.1</th>\n",
       "      <th>Unnamed: 0.1.1</th>\n",
       "      <th>Price</th>\n",
       "      <th>Area</th>\n",
       "      <th>No. of Bedrooms</th>\n",
       "      <th>Resale</th>\n",
       "      <th>MaintenanceStaff</th>\n",
       "      <th>Gymnasium</th>\n",
       "      <th>SwimmingPool</th>\n",
       "      <th>...</th>\n",
       "      <th>LiftAvailable</th>\n",
       "      <th>BED</th>\n",
       "      <th>VaastuCompliant</th>\n",
       "      <th>Microwave</th>\n",
       "      <th>GolfCourse</th>\n",
       "      <th>TV</th>\n",
       "      <th>DiningTable</th>\n",
       "      <th>Sofa</th>\n",
       "      <th>Wardrobe</th>\n",
       "      <th>Refrigerator</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>2000.000000</td>\n",
       "      <td>2000.000000</td>\n",
       "      <td>2000.000000</td>\n",
       "      <td>2.000000e+03</td>\n",
       "      <td>2000.00000</td>\n",
       "      <td>2000.000000</td>\n",
       "      <td>2000.000000</td>\n",
       "      <td>2000.000000</td>\n",
       "      <td>2000.000000</td>\n",
       "      <td>2000.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>2000.000000</td>\n",
       "      <td>2000.000000</td>\n",
       "      <td>2000.000000</td>\n",
       "      <td>2000.00000</td>\n",
       "      <td>2000.0</td>\n",
       "      <td>2000.000000</td>\n",
       "      <td>2000.000000</td>\n",
       "      <td>2000.000000</td>\n",
       "      <td>2000.0</td>\n",
       "      <td>2000.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>1000.495500</td>\n",
       "      <td>1001.491000</td>\n",
       "      <td>1001.491000</td>\n",
       "      <td>1.029326e-08</td>\n",
       "      <td>1200.19150</td>\n",
       "      <td>2.689000</td>\n",
       "      <td>0.701000</td>\n",
       "      <td>0.072000</td>\n",
       "      <td>0.194000</td>\n",
       "      <td>0.052500</td>\n",
       "      <td>...</td>\n",
       "      <td>0.651000</td>\n",
       "      <td>0.053500</td>\n",
       "      <td>0.154500</td>\n",
       "      <td>0.04550</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.051500</td>\n",
       "      <td>0.034500</td>\n",
       "      <td>0.045000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.041500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>577.502354</td>\n",
       "      <td>577.510126</td>\n",
       "      <td>577.510126</td>\n",
       "      <td>9.124262e-09</td>\n",
       "      <td>614.62765</td>\n",
       "      <td>0.729757</td>\n",
       "      <td>0.457934</td>\n",
       "      <td>0.258553</td>\n",
       "      <td>0.395528</td>\n",
       "      <td>0.223089</td>\n",
       "      <td>...</td>\n",
       "      <td>0.476773</td>\n",
       "      <td>0.225085</td>\n",
       "      <td>0.361518</td>\n",
       "      <td>0.20845</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.221071</td>\n",
       "      <td>0.182555</td>\n",
       "      <td>0.207356</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.199493</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2.000000e-09</td>\n",
       "      <td>200.00000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>500.750000</td>\n",
       "      <td>501.750000</td>\n",
       "      <td>501.750000</td>\n",
       "      <td>3.600000e-09</td>\n",
       "      <td>720.00000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>1000.500000</td>\n",
       "      <td>1001.500000</td>\n",
       "      <td>1001.500000</td>\n",
       "      <td>7.000000e-09</td>\n",
       "      <td>1000.00000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>1500.250000</td>\n",
       "      <td>1501.250000</td>\n",
       "      <td>1501.250000</td>\n",
       "      <td>1.550000e-08</td>\n",
       "      <td>1700.00000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>2000.000000</td>\n",
       "      <td>2001.000000</td>\n",
       "      <td>2001.000000</td>\n",
       "      <td>1.625000e-07</td>\n",
       "      <td>6400.00000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.00000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>8 rows × 42 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        Unnamed: 0  Unnamed: 0.1  Unnamed: 0.1.1         Price        Area  \\\n",
       "count  2000.000000   2000.000000     2000.000000  2.000000e+03  2000.00000   \n",
       "mean   1000.495500   1001.491000     1001.491000  1.029326e-08  1200.19150   \n",
       "std     577.502354    577.510126      577.510126  9.124262e-09   614.62765   \n",
       "min       0.000000      0.000000        0.000000  2.000000e-09   200.00000   \n",
       "25%     500.750000    501.750000      501.750000  3.600000e-09   720.00000   \n",
       "50%    1000.500000   1001.500000     1001.500000  7.000000e-09  1000.00000   \n",
       "75%    1500.250000   1501.250000     1501.250000  1.550000e-08  1700.00000   \n",
       "max    2000.000000   2001.000000     2001.000000  1.625000e-07  6400.00000   \n",
       "\n",
       "       No. of Bedrooms       Resale  MaintenanceStaff    Gymnasium  \\\n",
       "count      2000.000000  2000.000000       2000.000000  2000.000000   \n",
       "mean          2.689000     0.701000          0.072000     0.194000   \n",
       "std           0.729757     0.457934          0.258553     0.395528   \n",
       "min           1.000000     0.000000          0.000000     0.000000   \n",
       "25%           2.000000     0.000000          0.000000     0.000000   \n",
       "50%           3.000000     1.000000          0.000000     0.000000   \n",
       "75%           3.000000     1.000000          0.000000     0.000000   \n",
       "max           5.000000     1.000000          1.000000     1.000000   \n",
       "\n",
       "       SwimmingPool  ...  LiftAvailable          BED  VaastuCompliant  \\\n",
       "count   2000.000000  ...    2000.000000  2000.000000      2000.000000   \n",
       "mean       0.052500  ...       0.651000     0.053500         0.154500   \n",
       "std        0.223089  ...       0.476773     0.225085         0.361518   \n",
       "min        0.000000  ...       0.000000     0.000000         0.000000   \n",
       "25%        0.000000  ...       0.000000     0.000000         0.000000   \n",
       "50%        0.000000  ...       1.000000     0.000000         0.000000   \n",
       "75%        0.000000  ...       1.000000     0.000000         0.000000   \n",
       "max        1.000000  ...       1.000000     1.000000         1.000000   \n",
       "\n",
       "        Microwave  GolfCourse           TV  DiningTable         Sofa  \\\n",
       "count  2000.00000      2000.0  2000.000000  2000.000000  2000.000000   \n",
       "mean      0.04550         0.0     0.051500     0.034500     0.045000   \n",
       "std       0.20845         0.0     0.221071     0.182555     0.207356   \n",
       "min       0.00000         0.0     0.000000     0.000000     0.000000   \n",
       "25%       0.00000         0.0     0.000000     0.000000     0.000000   \n",
       "50%       0.00000         0.0     0.000000     0.000000     0.000000   \n",
       "75%       0.00000         0.0     0.000000     0.000000     0.000000   \n",
       "max       1.00000         0.0     1.000000     1.000000     1.000000   \n",
       "\n",
       "       Wardrobe  Refrigerator  \n",
       "count    2000.0   2000.000000  \n",
       "mean        0.0      0.041500  \n",
       "std         0.0      0.199493  \n",
       "min         0.0      0.000000  \n",
       "25%         0.0      0.000000  \n",
       "50%         0.0      0.000000  \n",
       "75%         0.0      0.000000  \n",
       "max         0.0      1.000000  \n",
       "\n",
       "[8 rows x 42 columns]"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Delhi_dataset.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##Modifying the Prices"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "banglore_dataset['Price'] = banglore_dataset['Price']/100000\n",
    "Mumbai_dataset['Price'] = Mumbai_dataset['Price']/100000\n",
    "Kolkata_dataset['Price'] = Kolkata_dataset['Price']/100000\n",
    "Delhi_dataset['Price'] = Delhi_dataset['Price']/100000"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Feature Generation-Latitude and Longitude"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "from geopy.geocoders import Nominatim"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "geolocator = Nominatim(user_agent=\"OpenStreetMap Nominatim\")\n",
    "\n",
    "def feature_generation(df):\n",
    "    lat=[]\n",
    "    long=[]\n",
    "    a=0\n",
    "    for i in df['Location']: \n",
    "        location = geolocator.geocode(i)\n",
    "        try:\n",
    "            lat.append(location.latitude)\n",
    "            long.append(location.longitude)\n",
    "            print(a)\n",
    "        except:\n",
    "            lat.append(\"NA\")\n",
    "            long.append(\"NA\")\n",
    "        a=a+1\n",
    "    df['Latitude'] = lat\n",
    "    df['Longitude'] = long"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0\n",
      "3\n",
      "4\n",
      "5\n",
      "6\n",
      "7\n",
      "8\n",
      "9\n",
      "10\n",
      "11\n",
      "12\n",
      "13\n",
      "14\n",
      "15\n",
      "16\n",
      "19\n",
      "20\n",
      "21\n",
      "22\n",
      "23\n",
      "24\n",
      "25\n",
      "26\n",
      "27\n",
      "28\n",
      "29\n",
      "30\n",
      "31\n",
      "32\n",
      "33\n",
      "34\n",
      "35\n",
      "36\n",
      "39\n",
      "40\n",
      "41\n",
      "42\n",
      "43\n",
      "44\n",
      "45\n",
      "46\n",
      "47\n",
      "48\n",
      "49\n",
      "50\n",
      "51\n",
      "52\n",
      "53\n",
      "54\n",
      "55\n",
      "56\n",
      "58\n",
      "59\n",
      "60\n",
      "61\n",
      "62\n",
      "63\n",
      "64\n",
      "65\n",
      "66\n",
      "67\n",
      "68\n",
      "69\n",
      "70\n",
      "71\n",
      "72\n",
      "73\n",
      "74\n",
      "75\n",
      "76\n",
      "77\n",
      "78\n",
      "80\n",
      "81\n",
      "82\n",
      "83\n",
      "85\n",
      "86\n",
      "87\n",
      "88\n",
      "89\n",
      "90\n",
      "91\n",
      "92\n",
      "93\n",
      "94\n",
      "95\n",
      "96\n",
      "97\n",
      "98\n",
      "99\n",
      "100\n",
      "102\n",
      "103\n",
      "104\n",
      "105\n",
      "106\n",
      "107\n",
      "108\n",
      "109\n",
      "110\n",
      "111\n",
      "112\n",
      "113\n",
      "114\n",
      "115\n",
      "116\n",
      "117\n",
      "119\n",
      "120\n",
      "121\n",
      "123\n",
      "125\n",
      "126\n",
      "127\n",
      "129\n",
      "130\n",
      "132\n",
      "133\n",
      "134\n",
      "136\n",
      "137\n",
      "138\n",
      "139\n",
      "143\n",
      "144\n",
      "145\n",
      "146\n",
      "147\n",
      "148\n",
      "149\n",
      "150\n",
      "154\n",
      "155\n",
      "156\n",
      "157\n",
      "158\n",
      "159\n",
      "160\n",
      "161\n",
      "162\n",
      "163\n",
      "164\n",
      "165\n",
      "166\n",
      "167\n",
      "168\n",
      "169\n",
      "170\n",
      "171\n",
      "172\n",
      "173\n",
      "174\n",
      "175\n",
      "176\n",
      "177\n",
      "178\n",
      "179\n",
      "180\n",
      "181\n",
      "182\n",
      "183\n",
      "184\n",
      "185\n",
      "186\n",
      "187\n",
      "188\n",
      "189\n",
      "190\n",
      "191\n",
      "192\n",
      "193\n",
      "194\n",
      "195\n",
      "196\n",
      "197\n",
      "198\n",
      "199\n",
      "200\n",
      "201\n",
      "202\n",
      "203\n",
      "204\n",
      "205\n",
      "206\n",
      "207\n",
      "208\n",
      "209\n",
      "210\n",
      "211\n",
      "212\n",
      "213\n",
      "214\n",
      "215\n",
      "216\n",
      "217\n",
      "218\n",
      "219\n",
      "220\n",
      "221\n",
      "222\n",
      "223\n",
      "224\n",
      "225\n",
      "226\n",
      "227\n",
      "228\n",
      "229\n",
      "230\n",
      "231\n",
      "232\n",
      "233\n",
      "234\n",
      "235\n",
      "236\n",
      "237\n",
      "238\n",
      "239\n",
      "240\n",
      "241\n",
      "242\n",
      "243\n",
      "244\n",
      "245\n",
      "246\n",
      "247\n",
      "248\n",
      "249\n",
      "250\n",
      "251\n",
      "252\n",
      "253\n",
      "254\n",
      "255\n",
      "256\n",
      "257\n",
      "258\n",
      "259\n",
      "260\n",
      "261\n",
      "262\n",
      "263\n",
      "264\n",
      "265\n",
      "266\n",
      "267\n",
      "268\n",
      "269\n",
      "270\n",
      "271\n",
      "272\n",
      "273\n",
      "274\n",
      "275\n",
      "276\n",
      "277\n",
      "278\n",
      "279\n",
      "280\n",
      "282\n",
      "283\n",
      "284\n",
      "285\n",
      "286\n",
      "287\n",
      "288\n",
      "289\n",
      "290\n",
      "291\n",
      "292\n",
      "293\n",
      "294\n",
      "295\n",
      "296\n",
      "297\n",
      "298\n",
      "299\n",
      "300\n",
      "305\n",
      "306\n",
      "307\n",
      "308\n",
      "309\n",
      "310\n",
      "311\n",
      "312\n",
      "313\n",
      "314\n",
      "315\n",
      "317\n",
      "318\n",
      "319\n",
      "321\n",
      "322\n",
      "323\n",
      "324\n",
      "325\n",
      "326\n",
      "327\n",
      "328\n",
      "329\n",
      "330\n",
      "331\n",
      "332\n",
      "333\n"
     ]
    }
   ],
   "source": [
    "feature_generation(banglore_dataset)\n",
    "feature_generation(Mumbai_dataset)\n",
    "feature_generation(Kolkata_dataset)\n",
    "feature_generation(Delhi_dataset)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "banglore_dataset.to_csv('Bangalore.csv')\n",
    "Mumbai_dataset.to_csv('Mumbai.csv')\n",
    "Kolkata_dataset.to_csv('Kolkata.csv')\n",
    "Delhi_dataset.to_csv('Delhi.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "banglore = pd.read_csv('Bangalore.csv')\n",
    "Mumbai =pd.read_csv('Mumbai.csv')\n",
    "Kolkata = pd.read_csv('Kolkata.csv')\n",
    "Delhi = pd.read_csv('Delhi.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "banglore_dataset.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##Custom color palette"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "custom_colors = [\"#4e89ae\", \"#c56183\",\"#ed6663\",\"#ffa372\"]\n",
    "customPalette = sns.set_palette(sns.color_palette(custom_colors))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "sns.set_style(\"whitegrid\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def triple_plot(x, title,c):\n",
    "    fig, ax = plt.subplots(3,1,figsize=(20,10),sharex=True)\n",
    "    sns.distplot(x, ax=ax[0],color=c)\n",
    "    ax[0].set(xlabel=None)\n",
    "    ax[0].set_title('Histogram + KDE')\n",
    "    sns.boxplot(x, ax=ax[1],color=c)\n",
    "    ax[1].set(xlabel=None)\n",
    "    ax[1].set_title('Boxplot')\n",
    "    sns.violinplot(x, ax=ax[2],color=c)\n",
    "    ax[2].set(xlabel=None)\n",
    "    ax[2].set_title('Violin plot')\n",
    "    fig.suptitle(title, fontsize=16)\n",
    "    plt.tight_layout(pad=3.0)\n",
    "    plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "triple_plot(banglore_dataset['Price'],'Distribution of Price(in lakhs) in Bangalore',custom_colors[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "triple_plot(Mumbai_dataset['Price'],'Distribution of Price(in lakhs) in Mumbai',custom_colors[1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "triple_plot(Kolkata_dataset['Price'],'Distribution of Price(in lakhs) in Kolkata',custom_colors[2])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "triple_plot(Delhi_dataset['Price'],'Distribution of Price(in lakhs) in Delhi',custom_colors[3])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def count_plot(data,title):\n",
    "    df5=data[data['Resale']==0]\n",
    "    df6=data[data['Resale']==1]\n",
    "    fig,ax = plt.subplots(1,2,figsize=(15,10))\n",
    "    ax[0] = sns.countplot(y='Location',data=df5,order=df5.Location.value_counts().index[:10],ax=ax[0])\n",
    "    ax[0].set_title('No. of new properties')\n",
    "    ax[1] = sns.countplot(y='Location',data=df6,order=df6.Location.value_counts().index[:10],ax=ax[1])\n",
    "    ax[1].set_title('No. of old properties')\n",
    "    fig.suptitle(title,fontsize=16)\n",
    "    plt.tight_layout(pad=3.0)\n",
    "    plt.show()\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "count_plot(banglore_dataset,'New and Resale Properties in Bangalore')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "count_plot(Mumbai_dataset,'New and Resale Properties in Mumbai')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "count_plot(Kolkata_dataset,'New and Resale Properties in kolkata')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "count_plot(Delhi_dataset,'New and Resale Properties in Delhi')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def cat_plot(data,title):\n",
    "    sns.catplot(x='No. of Bedrooms',y='Price',data=data)\n",
    "    plt.title('No.of Bedrooms Vs Price in'+title,size=16)\n",
    "    plt.gcf().set_size_inches(6,8)\n",
    "    plt.show"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cat_plot(banglore_dataset,'Bangalore')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cat_plot(Mumbai_dataset,'Mumbai')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cat_plot(Kolkata_dataset,'Kolkata')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cat_plot(Delhi_dataset,'Delhi')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def scatter_plot(data,title,c):\n",
    "    sns.scatterplot(x='Area',y='Price',data=data,color=c)\n",
    "    plt.title('Area in Square feet Vs Price'+title,size=16)\n",
    "    plt.gcf().set_size_inches(6,8)\n",
    "    plt.show"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "scatter_plot(banglore_dataset,'Bangalore',custom_colors[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "scatter_plot(Mumbai_dataset,'Mumbai',custom_colors[1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "scatter_plot(Kolkata_dataset,'Kolkata',custom_colors[2])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "scatter_plot(Delhi_dataset,'Delhi',custom_colors[3])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "frames = [banglore_dataset,Mumbai_dataset,Kolkata_dataset,Delhi_dataset]\n",
    "merged = pd.concat(frames)\n",
    "merged = merged.loc[:, ~merged.columns.str.contains('^Unnamed')]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "merged.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "merged.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}