ML.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 271,
   "id": "36aaa9b0",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import os\n",
    "import pandas as pd\n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 272,
   "id": "f2de8818",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Car_Name</th>\n",
       "      <th>Year</th>\n",
       "      <th>Selling_Price</th>\n",
       "      <th>Present_Price</th>\n",
       "      <th>Kms_Driven</th>\n",
       "      <th>Fuel_Type</th>\n",
       "      <th>Seller_Type</th>\n",
       "      <th>Transmission</th>\n",
       "      <th>Owner</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>ritz</td>\n",
       "      <td>2014</td>\n",
       "      <td>3.35</td>\n",
       "      <td>5.59</td>\n",
       "      <td>27000</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>sx4</td>\n",
       "      <td>2013</td>\n",
       "      <td>4.75</td>\n",
       "      <td>9.54</td>\n",
       "      <td>43000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>ciaz</td>\n",
       "      <td>2017</td>\n",
       "      <td>7.25</td>\n",
       "      <td>9.85</td>\n",
       "      <td>6900</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>wagon r</td>\n",
       "      <td>2011</td>\n",
       "      <td>2.85</td>\n",
       "      <td>4.15</td>\n",
       "      <td>5200</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>swift</td>\n",
       "      <td>2014</td>\n",
       "      <td>4.60</td>\n",
       "      <td>6.87</td>\n",
       "      <td>42450</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>296</th>\n",
       "      <td>city</td>\n",
       "      <td>2016</td>\n",
       "      <td>9.50</td>\n",
       "      <td>11.60</td>\n",
       "      <td>33988</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>297</th>\n",
       "      <td>brio</td>\n",
       "      <td>2015</td>\n",
       "      <td>4.00</td>\n",
       "      <td>5.90</td>\n",
       "      <td>60000</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>298</th>\n",
       "      <td>city</td>\n",
       "      <td>2009</td>\n",
       "      <td>3.35</td>\n",
       "      <td>11.00</td>\n",
       "      <td>87934</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>299</th>\n",
       "      <td>city</td>\n",
       "      <td>2017</td>\n",
       "      <td>11.50</td>\n",
       "      <td>12.50</td>\n",
       "      <td>9000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>300</th>\n",
       "      <td>brio</td>\n",
       "      <td>2016</td>\n",
       "      <td>5.30</td>\n",
       "      <td>5.90</td>\n",
       "      <td>5464</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>301 rows × 9 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Car_Name  Year  Selling_Price  Present_Price  Kms_Driven Fuel_Type  \\\n",
       "0       ritz  2014           3.35           5.59       27000    Petrol   \n",
       "1        sx4  2013           4.75           9.54       43000    Diesel   \n",
       "2       ciaz  2017           7.25           9.85        6900    Petrol   \n",
       "3    wagon r  2011           2.85           4.15        5200    Petrol   \n",
       "4      swift  2014           4.60           6.87       42450    Diesel   \n",
       "..       ...   ...            ...            ...         ...       ...   \n",
       "296     city  2016           9.50          11.60       33988    Diesel   \n",
       "297     brio  2015           4.00           5.90       60000    Petrol   \n",
       "298     city  2009           3.35          11.00       87934    Petrol   \n",
       "299     city  2017          11.50          12.50        9000    Diesel   \n",
       "300     brio  2016           5.30           5.90        5464    Petrol   \n",
       "\n",
       "    Seller_Type Transmission  Owner  \n",
       "0        Dealer       Manual      0  \n",
       "1        Dealer       Manual      0  \n",
       "2        Dealer       Manual      0  \n",
       "3        Dealer       Manual      0  \n",
       "4        Dealer       Manual      0  \n",
       "..          ...          ...    ...  \n",
       "296      Dealer       Manual      0  \n",
       "297      Dealer       Manual      0  \n",
       "298      Dealer       Manual      0  \n",
       "299      Dealer       Manual      0  \n",
       "300      Dealer       Manual      0  \n",
       "\n",
       "[301 rows x 9 columns]"
      ]
     },
     "execution_count": 272,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv(\"car data.csv\")\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 332,
   "id": "e1752cbc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 1, 3], dtype=int64)"
      ]
     },
     "execution_count": 332,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Owner'].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 273,
   "id": "0184fd4a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Year</th>\n",
       "      <th>Selling_Price</th>\n",
       "      <th>Present_Price</th>\n",
       "      <th>Kms_Driven</th>\n",
       "      <th>Owner</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>301.000000</td>\n",
       "      <td>301.000000</td>\n",
       "      <td>301.000000</td>\n",
       "      <td>301.000000</td>\n",
       "      <td>301.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>2013.627907</td>\n",
       "      <td>4.661296</td>\n",
       "      <td>7.628472</td>\n",
       "      <td>36947.205980</td>\n",
       "      <td>0.043189</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>2.891554</td>\n",
       "      <td>5.082812</td>\n",
       "      <td>8.644115</td>\n",
       "      <td>38886.883882</td>\n",
       "      <td>0.247915</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>2003.000000</td>\n",
       "      <td>0.100000</td>\n",
       "      <td>0.320000</td>\n",
       "      <td>500.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>2012.000000</td>\n",
       "      <td>0.900000</td>\n",
       "      <td>1.200000</td>\n",
       "      <td>15000.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>2014.000000</td>\n",
       "      <td>3.600000</td>\n",
       "      <td>6.400000</td>\n",
       "      <td>32000.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>2016.000000</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>9.900000</td>\n",
       "      <td>48767.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>2018.000000</td>\n",
       "      <td>35.000000</td>\n",
       "      <td>92.600000</td>\n",
       "      <td>500000.000000</td>\n",
       "      <td>3.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              Year  Selling_Price  Present_Price     Kms_Driven       Owner\n",
       "count   301.000000     301.000000     301.000000     301.000000  301.000000\n",
       "mean   2013.627907       4.661296       7.628472   36947.205980    0.043189\n",
       "std       2.891554       5.082812       8.644115   38886.883882    0.247915\n",
       "min    2003.000000       0.100000       0.320000     500.000000    0.000000\n",
       "25%    2012.000000       0.900000       1.200000   15000.000000    0.000000\n",
       "50%    2014.000000       3.600000       6.400000   32000.000000    0.000000\n",
       "75%    2016.000000       6.000000       9.900000   48767.000000    0.000000\n",
       "max    2018.000000      35.000000      92.600000  500000.000000    3.000000"
      ]
     },
     "execution_count": 273,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Describe the Dataset\n",
    "df.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 274,
   "id": "ab708d2e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Car_Name</th>\n",
       "      <th>Year</th>\n",
       "      <th>Selling_Price</th>\n",
       "      <th>Present_Price</th>\n",
       "      <th>Kms_Driven</th>\n",
       "      <th>Fuel_Type</th>\n",
       "      <th>Seller_Type</th>\n",
       "      <th>Transmission</th>\n",
       "      <th>Owner</th>\n",
       "      <th>current_year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>ritz</td>\n",
       "      <td>2014</td>\n",
       "      <td>3.35</td>\n",
       "      <td>5.59</td>\n",
       "      <td>27000</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2021</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>sx4</td>\n",
       "      <td>2013</td>\n",
       "      <td>4.75</td>\n",
       "      <td>9.54</td>\n",
       "      <td>43000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2021</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>ciaz</td>\n",
       "      <td>2017</td>\n",
       "      <td>7.25</td>\n",
       "      <td>9.85</td>\n",
       "      <td>6900</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2021</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>wagon r</td>\n",
       "      <td>2011</td>\n",
       "      <td>2.85</td>\n",
       "      <td>4.15</td>\n",
       "      <td>5200</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2021</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>swift</td>\n",
       "      <td>2014</td>\n",
       "      <td>4.60</td>\n",
       "      <td>6.87</td>\n",
       "      <td>42450</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2021</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Car_Name  Year  Selling_Price  Present_Price  Kms_Driven Fuel_Type  \\\n",
       "0     ritz  2014           3.35           5.59       27000    Petrol   \n",
       "1      sx4  2013           4.75           9.54       43000    Diesel   \n",
       "2     ciaz  2017           7.25           9.85        6900    Petrol   \n",
       "3  wagon r  2011           2.85           4.15        5200    Petrol   \n",
       "4    swift  2014           4.60           6.87       42450    Diesel   \n",
       "\n",
       "  Seller_Type Transmission  Owner  current_year  \n",
       "0      Dealer       Manual      0          2021  \n",
       "1      Dealer       Manual      0          2021  \n",
       "2      Dealer       Manual      0          2021  \n",
       "3      Dealer       Manual      0          2021  \n",
       "4      Dealer       Manual      0          2021  "
      ]
     },
     "execution_count": 274,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#DataPreprocessing\n",
    "#adding another column\n",
    "df['current_year']=2021\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 275,
   "id": "824cb7bc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Car_Name</th>\n",
       "      <th>Year</th>\n",
       "      <th>Selling_Price</th>\n",
       "      <th>Present_Price</th>\n",
       "      <th>Kms_Driven</th>\n",
       "      <th>Fuel_Type</th>\n",
       "      <th>Seller_Type</th>\n",
       "      <th>Transmission</th>\n",
       "      <th>Owner</th>\n",
       "      <th>current_year</th>\n",
       "      <th>no_of_years</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>ritz</td>\n",
       "      <td>2014</td>\n",
       "      <td>3.35</td>\n",
       "      <td>5.59</td>\n",
       "      <td>27000</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2021</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>sx4</td>\n",
       "      <td>2013</td>\n",
       "      <td>4.75</td>\n",
       "      <td>9.54</td>\n",
       "      <td>43000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2021</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>ciaz</td>\n",
       "      <td>2017</td>\n",
       "      <td>7.25</td>\n",
       "      <td>9.85</td>\n",
       "      <td>6900</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2021</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>wagon r</td>\n",
       "      <td>2011</td>\n",
       "      <td>2.85</td>\n",
       "      <td>4.15</td>\n",
       "      <td>5200</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2021</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>swift</td>\n",
       "      <td>2014</td>\n",
       "      <td>4.60</td>\n",
       "      <td>6.87</td>\n",
       "      <td>42450</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2021</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Car_Name  Year  Selling_Price  Present_Price  Kms_Driven Fuel_Type  \\\n",
       "0     ritz  2014           3.35           5.59       27000    Petrol   \n",
       "1      sx4  2013           4.75           9.54       43000    Diesel   \n",
       "2     ciaz  2017           7.25           9.85        6900    Petrol   \n",
       "3  wagon r  2011           2.85           4.15        5200    Petrol   \n",
       "4    swift  2014           4.60           6.87       42450    Diesel   \n",
       "\n",
       "  Seller_Type Transmission  Owner  current_year  no_of_years  \n",
       "0      Dealer       Manual      0          2021            7  \n",
       "1      Dealer       Manual      0          2021            8  \n",
       "2      Dealer       Manual      0          2021            4  \n",
       "3      Dealer       Manual      0          2021           10  \n",
       "4      Dealer       Manual      0          2021            7  "
      ]
     },
     "execution_count": 275,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['no_of_years']=df['current_year']-df['Year']\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 276,
   "id": "6cd7ad4c",
   "metadata": {},
   "outputs": [],
   "source": [
    "#Dropping Year columns because it is irrelevant and doesnt' make any difference\n",
    "df.drop('Year',axis=1,inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 277,
   "id": "fb75334e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Car_Name</th>\n",
       "      <th>Selling_Price</th>\n",
       "      <th>Present_Price</th>\n",
       "      <th>Kms_Driven</th>\n",
       "      <th>Fuel_Type</th>\n",
       "      <th>Seller_Type</th>\n",
       "      <th>Transmission</th>\n",
       "      <th>Owner</th>\n",
       "      <th>current_year</th>\n",
       "      <th>no_of_years</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>ritz</td>\n",
       "      <td>3.35</td>\n",
       "      <td>5.59</td>\n",
       "      <td>27000</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2021</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>sx4</td>\n",
       "      <td>4.75</td>\n",
       "      <td>9.54</td>\n",
       "      <td>43000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2021</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>ciaz</td>\n",
       "      <td>7.25</td>\n",
       "      <td>9.85</td>\n",
       "      <td>6900</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2021</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>wagon r</td>\n",
       "      <td>2.85</td>\n",
       "      <td>4.15</td>\n",
       "      <td>5200</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2021</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>swift</td>\n",
       "      <td>4.60</td>\n",
       "      <td>6.87</td>\n",
       "      <td>42450</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2021</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Car_Name  Selling_Price  Present_Price  Kms_Driven Fuel_Type Seller_Type  \\\n",
       "0     ritz           3.35           5.59       27000    Petrol      Dealer   \n",
       "1      sx4           4.75           9.54       43000    Diesel      Dealer   \n",
       "2     ciaz           7.25           9.85        6900    Petrol      Dealer   \n",
       "3  wagon r           2.85           4.15        5200    Petrol      Dealer   \n",
       "4    swift           4.60           6.87       42450    Diesel      Dealer   \n",
       "\n",
       "  Transmission  Owner  current_year  no_of_years  \n",
       "0       Manual      0          2021            7  \n",
       "1       Manual      0          2021            8  \n",
       "2       Manual      0          2021            4  \n",
       "3       Manual      0          2021           10  \n",
       "4       Manual      0          2021            7  "
      ]
     },
     "execution_count": 277,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 278,
   "id": "9771053c",
   "metadata": {},
   "outputs": [],
   "source": [
    "#Convert the values\n",
    "df['selling usd'] = df['Selling_Price'] # * 100000)/83"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 279,
   "id": "0469f030",
   "metadata": {},
   "outputs": [],
   "source": [
    "df['Present usd'] = df['Present_Price'] #* 100000)/83"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 280,
   "id": "7dec9f3f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Car_Name</th>\n",
       "      <th>Selling_Price</th>\n",
       "      <th>Present_Price</th>\n",
       "      <th>Kms_Driven</th>\n",
       "      <th>Fuel_Type</th>\n",
       "      <th>Seller_Type</th>\n",
       "      <th>Transmission</th>\n",
       "      <th>Owner</th>\n",
       "      <th>current_year</th>\n",
       "      <th>no_of_years</th>\n",
       "      <th>selling usd</th>\n",
       "      <th>Present usd</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>ritz</td>\n",
       "      <td>3.35</td>\n",
       "      <td>5.59</td>\n",
       "      <td>27000</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2021</td>\n",
       "      <td>7</td>\n",
       "      <td>3.35</td>\n",
       "      <td>5.59</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>sx4</td>\n",
       "      <td>4.75</td>\n",
       "      <td>9.54</td>\n",
       "      <td>43000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2021</td>\n",
       "      <td>8</td>\n",
       "      <td>4.75</td>\n",
       "      <td>9.54</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>ciaz</td>\n",
       "      <td>7.25</td>\n",
       "      <td>9.85</td>\n",
       "      <td>6900</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2021</td>\n",
       "      <td>4</td>\n",
       "      <td>7.25</td>\n",
       "      <td>9.85</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>wagon r</td>\n",
       "      <td>2.85</td>\n",
       "      <td>4.15</td>\n",
       "      <td>5200</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2021</td>\n",
       "      <td>10</td>\n",
       "      <td>2.85</td>\n",
       "      <td>4.15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>swift</td>\n",
       "      <td>4.60</td>\n",
       "      <td>6.87</td>\n",
       "      <td>42450</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2021</td>\n",
       "      <td>7</td>\n",
       "      <td>4.60</td>\n",
       "      <td>6.87</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>296</th>\n",
       "      <td>city</td>\n",
       "      <td>9.50</td>\n",
       "      <td>11.60</td>\n",
       "      <td>33988</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2021</td>\n",
       "      <td>5</td>\n",
       "      <td>9.50</td>\n",
       "      <td>11.60</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>297</th>\n",
       "      <td>brio</td>\n",
       "      <td>4.00</td>\n",
       "      <td>5.90</td>\n",
       "      <td>60000</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2021</td>\n",
       "      <td>6</td>\n",
       "      <td>4.00</td>\n",
       "      <td>5.90</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>298</th>\n",
       "      <td>city</td>\n",
       "      <td>3.35</td>\n",
       "      <td>11.00</td>\n",
       "      <td>87934</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2021</td>\n",
       "      <td>12</td>\n",
       "      <td>3.35</td>\n",
       "      <td>11.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>299</th>\n",
       "      <td>city</td>\n",
       "      <td>11.50</td>\n",
       "      <td>12.50</td>\n",
       "      <td>9000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2021</td>\n",
       "      <td>4</td>\n",
       "      <td>11.50</td>\n",
       "      <td>12.50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>300</th>\n",
       "      <td>brio</td>\n",
       "      <td>5.30</td>\n",
       "      <td>5.90</td>\n",
       "      <td>5464</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>2021</td>\n",
       "      <td>5</td>\n",
       "      <td>5.30</td>\n",
       "      <td>5.90</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>301 rows × 12 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Car_Name  Selling_Price  Present_Price  Kms_Driven Fuel_Type Seller_Type  \\\n",
       "0       ritz           3.35           5.59       27000    Petrol      Dealer   \n",
       "1        sx4           4.75           9.54       43000    Diesel      Dealer   \n",
       "2       ciaz           7.25           9.85        6900    Petrol      Dealer   \n",
       "3    wagon r           2.85           4.15        5200    Petrol      Dealer   \n",
       "4      swift           4.60           6.87       42450    Diesel      Dealer   \n",
       "..       ...            ...            ...         ...       ...         ...   \n",
       "296     city           9.50          11.60       33988    Diesel      Dealer   \n",
       "297     brio           4.00           5.90       60000    Petrol      Dealer   \n",
       "298     city           3.35          11.00       87934    Petrol      Dealer   \n",
       "299     city          11.50          12.50        9000    Diesel      Dealer   \n",
       "300     brio           5.30           5.90        5464    Petrol      Dealer   \n",
       "\n",
       "    Transmission  Owner  current_year  no_of_years  selling usd  Present usd  \n",
       "0         Manual      0          2021            7         3.35         5.59  \n",
       "1         Manual      0          2021            8         4.75         9.54  \n",
       "2         Manual      0          2021            4         7.25         9.85  \n",
       "3         Manual      0          2021           10         2.85         4.15  \n",
       "4         Manual      0          2021            7         4.60         6.87  \n",
       "..           ...    ...           ...          ...          ...          ...  \n",
       "296       Manual      0          2021            5         9.50        11.60  \n",
       "297       Manual      0          2021            6         4.00         5.90  \n",
       "298       Manual      0          2021           12         3.35        11.00  \n",
       "299       Manual      0          2021            4        11.50        12.50  \n",
       "300       Manual      0          2021            5         5.30         5.90  \n",
       "\n",
       "[301 rows x 12 columns]"
      ]
     },
     "execution_count": 280,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 281,
   "id": "0b3fdab7",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 301 entries, 0 to 300\n",
      "Data columns (total 12 columns):\n",
      " #   Column         Non-Null Count  Dtype  \n",
      "---  ------         --------------  -----  \n",
      " 0   Car_Name       301 non-null    object \n",
      " 1   Selling_Price  301 non-null    float64\n",
      " 2   Present_Price  301 non-null    float64\n",
      " 3   Kms_Driven     301 non-null    int64  \n",
      " 4   Fuel_Type      301 non-null    object \n",
      " 5   Seller_Type    301 non-null    object \n",
      " 6   Transmission   301 non-null    object \n",
      " 7   Owner          301 non-null    int64  \n",
      " 8   current_year   301 non-null    int64  \n",
      " 9   no_of_years    301 non-null    int64  \n",
      " 10  selling usd    301 non-null    float64\n",
      " 11  Present usd    301 non-null    float64\n",
      "dtypes: float64(4), int64(4), object(4)\n",
      "memory usage: 28.3+ KB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 282,
   "id": "54d2a9c7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['Petrol', 'Diesel', 'CNG'], dtype=object)"
      ]
     },
     "execution_count": 282,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Checking Unique Values\n",
    "df['Fuel_Type'].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 283,
   "id": "3390aed0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['Dealer', 'Individual'], dtype=object)"
      ]
     },
     "execution_count": 283,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Seller_Type'].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 284,
   "id": "be8eea11",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['Manual', 'Automatic'], dtype=object)"
      ]
     },
     "execution_count": 284,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Transmission'].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 285,
   "id": "a17ec121",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['ritz', 'sx4', 'ciaz', 'wagon r', 'swift', 'vitara brezza',\n",
       "       's cross', 'alto 800', 'ertiga', 'dzire', 'alto k10', 'ignis',\n",
       "       '800', 'baleno', 'omni', 'fortuner', 'innova', 'corolla altis',\n",
       "       'etios cross', 'etios g', 'etios liva', 'corolla', 'etios gd',\n",
       "       'camry', 'land cruiser', 'Royal Enfield Thunder 500',\n",
       "       'UM Renegade Mojave', 'KTM RC200', 'Bajaj Dominar 400',\n",
       "       'Royal Enfield Classic 350', 'KTM RC390', 'Hyosung GT250R',\n",
       "       'Royal Enfield Thunder 350', 'KTM 390 Duke ',\n",
       "       'Mahindra Mojo XT300', 'Bajaj Pulsar RS200',\n",
       "       'Royal Enfield Bullet 350', 'Royal Enfield Classic 500',\n",
       "       'Bajaj Avenger 220', 'Bajaj Avenger 150', 'Honda CB Hornet 160R',\n",
       "       'Yamaha FZ S V 2.0', 'Yamaha FZ 16', 'TVS Apache RTR 160',\n",
       "       'Bajaj Pulsar 150', 'Honda CBR 150', 'Hero Extreme',\n",
       "       'Bajaj Avenger 220 dtsi', 'Bajaj Avenger 150 street',\n",
       "       'Yamaha FZ  v 2.0', 'Bajaj Pulsar  NS 200', 'Bajaj Pulsar 220 F',\n",
       "       'TVS Apache RTR 180', 'Hero Passion X pro', 'Bajaj Pulsar NS 200',\n",
       "       'Yamaha Fazer ', 'Honda Activa 4G', 'TVS Sport ',\n",
       "       'Honda Dream Yuga ', 'Bajaj Avenger Street 220',\n",
       "       'Hero Splender iSmart', 'Activa 3g', 'Hero Passion Pro',\n",
       "       'Honda CB Trigger', 'Yamaha FZ S ', 'Bajaj Pulsar 135 LS',\n",
       "       'Activa 4g', 'Honda CB Unicorn', 'Hero Honda CBZ extreme',\n",
       "       'Honda Karizma', 'Honda Activa 125', 'TVS Jupyter',\n",
       "       'Hero Honda Passion Pro', 'Hero Splender Plus', 'Honda CB Shine',\n",
       "       'Bajaj Discover 100', 'Suzuki Access 125', 'TVS Wego',\n",
       "       'Honda CB twister', 'Hero Glamour', 'Hero Super Splendor',\n",
       "       'Bajaj Discover 125', 'Hero Hunk', 'Hero  Ignitor Disc',\n",
       "       'Hero  CBZ Xtreme', 'Bajaj  ct 100', 'i20', 'grand i10', 'i10',\n",
       "       'eon', 'xcent', 'elantra', 'creta', 'verna', 'city', 'brio',\n",
       "       'amaze', 'jazz'], dtype=object)"
      ]
     },
     "execution_count": 285,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Car_Name'].unique()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "45946b4f",
   "metadata": {},
   "source": [
    "Car_Name doesn't matter since, it doesn't provide any information. Howeveer we can consider them as \"Hidden Variables\". Since, car type or brand value matter for many people and which is highly subjective. And for this course we are not considering hidden variable. One appropriate way to interpret hidden variables is fuzzy-logic."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 286,
   "id": "97403401",
   "metadata": {},
   "outputs": [],
   "source": [
    "#Here our selling price would be our target variable\n",
    "y = df[['selling usd']]\n",
    "X = df[['Present usd', 'Kms_Driven','Fuel_Type','Seller_Type','Transmission','Owner','no_of_years']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 287,
   "id": "0b18ef5b",
   "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>Present usd</th>\n",
       "      <th>Kms_Driven</th>\n",
       "      <th>Fuel_Type</th>\n",
       "      <th>Seller_Type</th>\n",
       "      <th>Transmission</th>\n",
       "      <th>Owner</th>\n",
       "      <th>no_of_years</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>5.59</td>\n",
       "      <td>27000</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>9.54</td>\n",
       "      <td>43000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>9.85</td>\n",
       "      <td>6900</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4.15</td>\n",
       "      <td>5200</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>6.87</td>\n",
       "      <td>42450</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>296</th>\n",
       "      <td>11.60</td>\n",
       "      <td>33988</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>297</th>\n",
       "      <td>5.90</td>\n",
       "      <td>60000</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>298</th>\n",
       "      <td>11.00</td>\n",
       "      <td>87934</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>299</th>\n",
       "      <td>12.50</td>\n",
       "      <td>9000</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>300</th>\n",
       "      <td>5.90</td>\n",
       "      <td>5464</td>\n",
       "      <td>Petrol</td>\n",
       "      <td>Dealer</td>\n",
       "      <td>Manual</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>301 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Present usd  Kms_Driven Fuel_Type Seller_Type Transmission  Owner  \\\n",
       "0           5.59       27000    Petrol      Dealer       Manual      0   \n",
       "1           9.54       43000    Diesel      Dealer       Manual      0   \n",
       "2           9.85        6900    Petrol      Dealer       Manual      0   \n",
       "3           4.15        5200    Petrol      Dealer       Manual      0   \n",
       "4           6.87       42450    Diesel      Dealer       Manual      0   \n",
       "..           ...         ...       ...         ...          ...    ...   \n",
       "296        11.60       33988    Diesel      Dealer       Manual      0   \n",
       "297         5.90       60000    Petrol      Dealer       Manual      0   \n",
       "298        11.00       87934    Petrol      Dealer       Manual      0   \n",
       "299        12.50        9000    Diesel      Dealer       Manual      0   \n",
       "300         5.90        5464    Petrol      Dealer       Manual      0   \n",
       "\n",
       "     no_of_years  \n",
       "0              7  \n",
       "1              8  \n",
       "2              4  \n",
       "3             10  \n",
       "4              7  \n",
       "..           ...  \n",
       "296            5  \n",
       "297            6  \n",
       "298           12  \n",
       "299            4  \n",
       "300            5  \n",
       "\n",
       "[301 rows x 7 columns]"
      ]
     },
     "execution_count": 287,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 288,
   "id": "b0d075db",
   "metadata": {},
   "outputs": [],
   "source": [
    "#One Hot encoding\n",
    "X1 = pd.get_dummies(X,drop_first=True)\n",
    "#X2 = pd.get_dummies(X,drop_first=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 289,
   "id": "24695184",
   "metadata": {
    "scrolled": true
   },
   "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>Present usd</th>\n",
       "      <th>Kms_Driven</th>\n",
       "      <th>Owner</th>\n",
       "      <th>no_of_years</th>\n",
       "      <th>Fuel_Type_Diesel</th>\n",
       "      <th>Fuel_Type_Petrol</th>\n",
       "      <th>Seller_Type_Individual</th>\n",
       "      <th>Transmission_Manual</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>5.59</td>\n",
       "      <td>27000</td>\n",
       "      <td>0</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>9.54</td>\n",
       "      <td>43000</td>\n",
       "      <td>0</td>\n",
       "      <td>8</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>9.85</td>\n",
       "      <td>6900</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4.15</td>\n",
       "      <td>5200</td>\n",
       "      <td>0</td>\n",
       "      <td>10</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>6.87</td>\n",
       "      <td>42450</td>\n",
       "      <td>0</td>\n",
       "      <td>7</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>296</th>\n",
       "      <td>11.60</td>\n",
       "      <td>33988</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>297</th>\n",
       "      <td>5.90</td>\n",
       "      <td>60000</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>298</th>\n",
       "      <td>11.00</td>\n",
       "      <td>87934</td>\n",
       "      <td>0</td>\n",
       "      <td>12</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>299</th>\n",
       "      <td>12.50</td>\n",
       "      <td>9000</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>300</th>\n",
       "      <td>5.90</td>\n",
       "      <td>5464</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>301 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Present usd  Kms_Driven  Owner  no_of_years  Fuel_Type_Diesel  \\\n",
       "0           5.59       27000      0            7                 0   \n",
       "1           9.54       43000      0            8                 1   \n",
       "2           9.85        6900      0            4                 0   \n",
       "3           4.15        5200      0           10                 0   \n",
       "4           6.87       42450      0            7                 1   \n",
       "..           ...         ...    ...          ...               ...   \n",
       "296        11.60       33988      0            5                 1   \n",
       "297         5.90       60000      0            6                 0   \n",
       "298        11.00       87934      0           12                 0   \n",
       "299        12.50        9000      0            4                 1   \n",
       "300         5.90        5464      0            5                 0   \n",
       "\n",
       "     Fuel_Type_Petrol  Seller_Type_Individual  Transmission_Manual  \n",
       "0                   1                       0                    1  \n",
       "1                   0                       0                    1  \n",
       "2                   1                       0                    1  \n",
       "3                   1                       0                    1  \n",
       "4                   0                       0                    1  \n",
       "..                ...                     ...                  ...  \n",
       "296                 0                       0                    1  \n",
       "297                 1                       0                    1  \n",
       "298                 1                       0                    1  \n",
       "299                 0                       0                    1  \n",
       "300                 1                       0                    1  \n",
       "\n",
       "[301 rows x 8 columns]"
      ]
     },
     "execution_count": 289,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 330,
   "id": "bc7bda1b",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 2000x2000 with 72 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.pairplot(X1)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 331,
   "id": "4c3b1e26",
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.heatmap(X1.corr().round(2), annot=True)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1ec7adc6",
   "metadata": {},
   "source": [
    "### Features and Target Variables"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 292,
   "id": "8c007d94",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "X_train,X_test,y_train,y_test = train_test_split(X1,y,test_size=0.25,random_state=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 293,
   "id": "b1a3e369",
   "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>Present usd</th>\n",
       "      <th>Kms_Driven</th>\n",
       "      <th>Owner</th>\n",
       "      <th>no_of_years</th>\n",
       "      <th>Fuel_Type_Diesel</th>\n",
       "      <th>Fuel_Type_Petrol</th>\n",
       "      <th>Seller_Type_Individual</th>\n",
       "      <th>Transmission_Manual</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>146</th>\n",
       "      <td>0.787</td>\n",
       "      <td>15000</td>\n",
       "      <td>0</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>260</th>\n",
       "      <td>13.600</td>\n",
       "      <td>29223</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>37</th>\n",
       "      <td>2.280</td>\n",
       "      <td>127000</td>\n",
       "      <td>0</td>\n",
       "      <td>18</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>273</th>\n",
       "      <td>7.500</td>\n",
       "      <td>61203</td>\n",
       "      <td>0</td>\n",
       "      <td>11</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>164</th>\n",
       "      <td>0.540</td>\n",
       "      <td>14000</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Present usd  Kms_Driven  Owner  no_of_years  Fuel_Type_Diesel  \\\n",
       "146        0.787       15000      0            7                 0   \n",
       "260       13.600       29223      0            5                 0   \n",
       "37         2.280      127000      0           18                 0   \n",
       "273        7.500       61203      0           11                 0   \n",
       "164        0.540       14000      0            5                 0   \n",
       "\n",
       "     Fuel_Type_Petrol  Seller_Type_Individual  Transmission_Manual  \n",
       "146                 1                       1                    1  \n",
       "260                 1                       0                    1  \n",
       "37                  1                       1                    1  \n",
       "273                 1                       0                    1  \n",
       "164                 1                       1                    1  "
      ]
     },
     "execution_count": 293,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Taking 225 Samples for Training and 76 for testing\n",
    "X_train.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "058e8e9b",
   "metadata": {},
   "source": [
    "#Fitting different models to check their performance\n",
    "1. Multivariate Linear Regression\n",
    "2. Decision Tree\n",
    "3. Random Forest Regressor\n",
    "4. Neural Network\n",
    "5. KNN\n",
    "#Dimintionality Reduction\n",
    "1. PCA\n",
    "#Scaling\n",
    "Minmax"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d4866eb1",
   "metadata": {},
   "source": [
    "### 1. Linear Regression Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 294,
   "id": "4f6a0959",
   "metadata": {},
   "outputs": [],
   "source": [
    "MAE = []\n",
    "MSE = []\n",
    "RMSE = []\n",
    "r2 = []"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 295,
   "id": "d988e9ae",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MAE: 1.1969864403009076\n",
      "MSE: 4.349378132257332\n",
      "RMSE: 2.085516274752449\n",
      "R2: 0.8639362504421002\n"
     ]
    }
   ],
   "source": [
    "from sklearn.linear_model import LinearRegression\n",
    "reg = LinearRegression()\n",
    "reg.fit(X_train, y_train)\n",
    "y_pred = reg.predict(X_test)\n",
    "#print errors\n",
    "from sklearn import metrics\n",
    "print('MAE:', metrics.mean_absolute_error(y_test, y_pred))\n",
    "MAE.append(metrics.mean_absolute_error(y_test, y_pred))\n",
    "print('MSE:', metrics.mean_squared_error(y_test, y_pred))\n",
    "MSE.append(metrics.mean_squared_error(y_test, y_pred))\n",
    "print('RMSE:', np.sqrt(metrics.mean_squared_error(y_test, y_pred)))\n",
    "RMSE.append(np.sqrt(metrics.mean_squared_error(y_test, y_pred)))\n",
    "R2 = metrics.r2_score(y_test,y_pred)\n",
    "print('R2:',R2)\n",
    "r2.append(R2)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d4d50d23",
   "metadata": {},
   "source": [
    "### 2. Decision Tree model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 296,
   "id": "a4da4d34",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MAE: 0.8796052631578949\n",
      "MSE: 2.8957749999999995\n",
      "RMSE: 1.7016976817284555\n",
      "R2: 0.9094100369306046\n"
     ]
    }
   ],
   "source": [
    "from sklearn.tree import DecisionTreeRegressor\n",
    "\n",
    "#creating object for Decision tree\n",
    "tree = DecisionTreeRegressor()\n",
    "\n",
    "#fitting the decision tree model\n",
    "tree.fit(X_train,y_train)\n",
    "\n",
    "# Predict on the test data: y_pred\n",
    "y_pred = tree.predict(X_test)\n",
    "\n",
    "from sklearn import metrics\n",
    "print('MAE:', metrics.mean_absolute_error(y_test, y_pred))\n",
    "MAE.append(metrics.mean_absolute_error(y_test, y_pred))\n",
    "print('MSE:', metrics.mean_squared_error(y_test, y_pred))\n",
    "MSE.append(metrics.mean_squared_error(y_test, y_pred))\n",
    "print('RMSE:', np.sqrt(metrics.mean_squared_error(y_test, y_pred)))\n",
    "RMSE.append(np.sqrt(metrics.mean_squared_error(y_test, y_pred)))\n",
    "R2 = metrics.r2_score(y_test,y_pred)\n",
    "print('R2:',R2)\n",
    "r2.append(R2)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0ce92771",
   "metadata": {},
   "source": [
    "### 3. Random Forest"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 297,
   "id": "acc3f143",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MAE: 0.7727513157894738\n",
      "MSE: 2.642217535921052\n",
      "RMSE: 1.6254899371946454\n",
      "R2: 0.9173422006197316\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\18562\\AppData\\Local\\Temp\\ipykernel_25852\\2059104574.py:7: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().\n",
      "  rf.fit(X_train,y_train)\n"
     ]
    }
   ],
   "source": [
    "from sklearn.ensemble import RandomForestRegressor\n",
    "\n",
    "#creating object for Random forest regressor\n",
    "rf = RandomForestRegressor(n_estimators = 100, random_state = 42)\n",
    "\n",
    "#fitting the rf model\n",
    "rf.fit(X_train,y_train)\n",
    "\n",
    "# Predict on the test data: y_pred\n",
    "y_pred = rf.predict(X_test)\n",
    "\n",
    "#print errors\n",
    "from sklearn import metrics\n",
    "print('MAE:', metrics.mean_absolute_error(y_test, y_pred))\n",
    "MAE.append(metrics.mean_absolute_error(y_test, y_pred))\n",
    "print('MSE:', metrics.mean_squared_error(y_test, y_pred))\n",
    "MSE.append(metrics.mean_squared_error(y_test, y_pred))\n",
    "print('RMSE:', np.sqrt(metrics.mean_squared_error(y_test, y_pred)))\n",
    "RMSE.append(np.sqrt(metrics.mean_squared_error(y_test, y_pred)))\n",
    "R2 = metrics.r2_score(y_test,y_pred)\n",
    "print('R2:',R2)\n",
    "r2.append(R2)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ccf18ec2",
   "metadata": {},
   "source": [
    "### 4. SVR"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 298,
   "id": "4104067b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MAE: 3.4733767817967647\n",
      "MSE: 37.359024978589375\n",
      "RMSE: 6.112202956266208\n",
      "R2: -0.16872087545442205\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\softwares\\anaconda\\lib\\site-packages\\sklearn\\utils\\validation.py:993: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
      "  y = column_or_1d(y, warn=True)\n"
     ]
    }
   ],
   "source": [
    "from sklearn.svm import SVR\n",
    "regr = SVR()\n",
    "regr.fit(X_train,y_train)\n",
    "y_pred = regr.predict(X_test)\n",
    "#print errors\n",
    "from sklearn import metrics\n",
    "print('MAE:', metrics.mean_absolute_error(y_test, y_pred))\n",
    "MAE.append(metrics.mean_absolute_error(y_test, y_pred))\n",
    "print('MSE:', metrics.mean_squared_error(y_test, y_pred))\n",
    "MSE.append(metrics.mean_squared_error(y_test, y_pred))\n",
    "print('RMSE:', np.sqrt(metrics.mean_squared_error(y_test, y_pred)))\n",
    "RMSE.append(np.sqrt(metrics.mean_squared_error(y_test, y_pred)))\n",
    "R2 = metrics.r2_score(y_test,y_pred)\n",
    "print('R2:',R2)\n",
    "r2.append(R2)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6e7ee64e",
   "metadata": {},
   "source": [
    "### 5. Neural Network"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 299,
   "id": "3a5c2b61",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\softwares\\anaconda\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:1599: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
      "  y = column_or_1d(y, warn=True)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "-0.6979514789947614"
      ]
     },
     "execution_count": 299,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.neural_network import MLPRegressor\n",
    "from sklearn.datasets import make_regression\n",
    "from sklearn.model_selection import train_test_split\n",
    "regr = MLPRegressor(random_state=1, max_iter=500).fit(X_train, y_train)\n",
    "regr.predict(X_test)\n",
    "regr.score(X_test, y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 300,
   "id": "3296a475",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MAE: 4.926577241340418\n",
      "MSE: 54.27627164743997\n",
      "RMSE: 7.367243151100686\n",
      "R2: -0.6979514789947614\n"
     ]
    }
   ],
   "source": [
    "y_pred = regr.predict(X_test)\n",
    "from sklearn import metrics\n",
    "print('MAE:', metrics.mean_absolute_error(y_test, y_pred))\n",
    "MAE.append(metrics.mean_absolute_error(y_test, y_pred))\n",
    "print('MSE:', metrics.mean_squared_error(y_test, y_pred))\n",
    "MSE.append(metrics.mean_squared_error(y_test, y_pred))\n",
    "print('RMSE:', np.sqrt(metrics.mean_squared_error(y_test, y_pred)))\n",
    "RMSE.append(np.sqrt(metrics.mean_squared_error(y_test, y_pred)))\n",
    "R2 = metrics.r2_score(y_test,y_pred)\n",
    "print('R2:',R2)\n",
    "r2.append(R2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 301,
   "id": "57fc5ab7",
   "metadata": {},
   "outputs": [],
   "source": [
    "#Repeating With Scaled Dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 302,
   "id": "72d7a41a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "MinMaxScaler()"
      ]
     },
     "execution_count": 302,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.preprocessing import MinMaxScaler\n",
    "scaler = MinMaxScaler()\n",
    "scaler.fit(X_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 303,
   "id": "147e50c0",
   "metadata": {},
   "outputs": [],
   "source": [
    "column_names = []\n",
    "for c in X1.columns:\n",
    "    column_names.append(c)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 304,
   "id": "cb7a55a2",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['Present usd', 'Kms_Driven', 'Owner', 'no_of_years', 'Fuel_Type_Diesel', 'Fuel_Type_Petrol', 'Seller_Type_Individual', 'Transmission_Manual']\n"
     ]
    }
   ],
   "source": [
    "print(column_names)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 305,
   "id": "3d1faec6",
   "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>Present usd</th>\n",
       "      <th>Kms_Driven</th>\n",
       "      <th>Owner</th>\n",
       "      <th>no_of_years</th>\n",
       "      <th>Fuel_Type_Diesel</th>\n",
       "      <th>Fuel_Type_Petrol</th>\n",
       "      <th>Seller_Type_Individual</th>\n",
       "      <th>Transmission_Manual</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-0.236215</td>\n",
       "      <td>-0.256224</td>\n",
       "      <td>-0.174501</td>\n",
       "      <td>-0.128897</td>\n",
       "      <td>-0.498962</td>\n",
       "      <td>0.509327</td>\n",
       "      <td>-0.737285</td>\n",
       "      <td>0.39148</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.221505</td>\n",
       "      <td>0.155911</td>\n",
       "      <td>-0.174501</td>\n",
       "      <td>0.217514</td>\n",
       "      <td>2.004162</td>\n",
       "      <td>-1.963374</td>\n",
       "      <td>-0.737285</td>\n",
       "      <td>0.39148</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.257427</td>\n",
       "      <td>-0.773969</td>\n",
       "      <td>-0.174501</td>\n",
       "      <td>-1.168129</td>\n",
       "      <td>-0.498962</td>\n",
       "      <td>0.509327</td>\n",
       "      <td>-0.737285</td>\n",
       "      <td>0.39148</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>-0.403079</td>\n",
       "      <td>-0.817758</td>\n",
       "      <td>-0.174501</td>\n",
       "      <td>0.910335</td>\n",
       "      <td>-0.498962</td>\n",
       "      <td>0.509327</td>\n",
       "      <td>-0.737285</td>\n",
       "      <td>0.39148</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>-0.087890</td>\n",
       "      <td>0.141743</td>\n",
       "      <td>-0.174501</td>\n",
       "      <td>-0.128897</td>\n",
       "      <td>2.004162</td>\n",
       "      <td>-1.963374</td>\n",
       "      <td>-0.737285</td>\n",
       "      <td>0.39148</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Present usd  Kms_Driven     Owner  no_of_years  Fuel_Type_Diesel  \\\n",
       "0    -0.236215   -0.256224 -0.174501    -0.128897         -0.498962   \n",
       "1     0.221505    0.155911 -0.174501     0.217514          2.004162   \n",
       "2     0.257427   -0.773969 -0.174501    -1.168129         -0.498962   \n",
       "3    -0.403079   -0.817758 -0.174501     0.910335         -0.498962   \n",
       "4    -0.087890    0.141743 -0.174501    -0.128897          2.004162   \n",
       "\n",
       "   Fuel_Type_Petrol  Seller_Type_Individual  Transmission_Manual  \n",
       "0          0.509327               -0.737285              0.39148  \n",
       "1         -1.963374               -0.737285              0.39148  \n",
       "2          0.509327               -0.737285              0.39148  \n",
       "3          0.509327               -0.737285              0.39148  \n",
       "4         -1.963374               -0.737285              0.39148  "
      ]
     },
     "execution_count": 305,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.preprocessing import StandardScaler#features# Separating out the features\n",
    "X1 = StandardScaler().fit_transform(X1)\n",
    "X1 = pd.DataFrame(X1, columns =column_names)\n",
    "X1.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 306,
   "id": "f096adc5",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train,X_test,y_train,y_test = train_test_split(X1,y,test_size=0.25,random_state=0)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a5a5929e",
   "metadata": {},
   "source": [
    "1. Linear Regression after Scaling"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 307,
   "id": "37d68e1f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MAE: 1.196986440300909\n",
      "MSE: 4.349378132257337\n",
      "RMSE: 2.0855162747524503\n",
      "R2: 0.8639362504421\n"
     ]
    }
   ],
   "source": [
    "from sklearn.linear_model import LinearRegression\n",
    "reg = LinearRegression()\n",
    "reg.fit(X_train, y_train)\n",
    "y_pred = reg.predict(X_test)\n",
    "#print errors\n",
    "from sklearn import metrics\n",
    "print('MAE:', metrics.mean_absolute_error(y_test, y_pred))\n",
    "print('MSE:', metrics.mean_squared_error(y_test, y_pred))\n",
    "print('RMSE:', np.sqrt(metrics.mean_squared_error(y_test, y_pred)))\n",
    "R2 = metrics.r2_score(y_test,y_pred)\n",
    "print('R2:',R2)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0e39d669",
   "metadata": {},
   "source": [
    "2. Decision Tree model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 308,
   "id": "a036b0fd",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MAE: 0.8421052631578947\n",
      "MSE: 2.4629236842105264\n",
      "RMSE: 1.5693704738558472\n",
      "R2: 0.922951138954038\n"
     ]
    }
   ],
   "source": [
    "from sklearn.tree import DecisionTreeRegressor\n",
    "\n",
    "#creating object for Decision tree\n",
    "tree = DecisionTreeRegressor()\n",
    "\n",
    "#fitting the decision tree model\n",
    "tree.fit(X_train,y_train)\n",
    "\n",
    "# Predict on the test data: y_pred\n",
    "y_pred = tree.predict(X_test)\n",
    "\n",
    "#print errors\n",
    "from sklearn import metrics\n",
    "print('MAE:', metrics.mean_absolute_error(y_test, y_pred))\n",
    "print('MSE:', metrics.mean_squared_error(y_test, y_pred))\n",
    "print('RMSE:', np.sqrt(metrics.mean_squared_error(y_test, y_pred)))\n",
    "R2 = metrics.r2_score(y_test,y_pred)\n",
    "print('R2:',R2)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "486a8b59",
   "metadata": {},
   "source": [
    "3. Random Forest - Scaler"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 309,
   "id": "8ef55058",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MAE: 0.7618026315789475\n",
      "MSE: 2.6213776447368415\n",
      "RMSE: 1.6190669055776667\n",
      "R2: 0.9179941452538098\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\18562\\AppData\\Local\\Temp\\ipykernel_25852\\531649128.py:7: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().\n",
      "  rf.fit(X_train,y_train)\n"
     ]
    }
   ],
   "source": [
    "from sklearn.ensemble import RandomForestRegressor\n",
    "\n",
    "#creating object for Random forest regressor\n",
    "rf = RandomForestRegressor(n_estimators = 100, random_state = 42)\n",
    "\n",
    "#fitting the rf model\n",
    "rf.fit(X_train,y_train)\n",
    "\n",
    "# Predict on the test data: y_pred\n",
    "y_pred = rf.predict(X_test)\n",
    "\n",
    "#print errors\n",
    "from sklearn import metrics\n",
    "print('MAE:', metrics.mean_absolute_error(y_test, y_pred))\n",
    "print('MSE:', metrics.mean_squared_error(y_test, y_pred))\n",
    "print('RMSE:', np.sqrt(metrics.mean_squared_error(y_test, y_pred)))\n",
    "R2 = metrics.r2_score(y_test,y_pred)\n",
    "print('R2:',R2)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "16c1157e",
   "metadata": {},
   "source": [
    "4. SVR scaled Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 310,
   "id": "f21ee4a9",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MAE: 1.516915708790308\n",
      "MSE: 13.976464519523276\n",
      "RMSE: 3.7385110029961495\n",
      "R2: 0.56276734046522\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\softwares\\anaconda\\lib\\site-packages\\sklearn\\utils\\validation.py:993: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
      "  y = column_or_1d(y, warn=True)\n"
     ]
    }
   ],
   "source": [
    "from sklearn.svm import SVR\n",
    "regr = SVR()\n",
    "regr.fit(X_train,y_train)\n",
    "y_pred = regr.predict(X_test)\n",
    "#print errors\n",
    "from sklearn import metrics\n",
    "print('MAE:', metrics.mean_absolute_error(y_test, y_pred))\n",
    "print('MSE:', metrics.mean_squared_error(y_test, y_pred))\n",
    "print('RMSE:', np.sqrt(metrics.mean_squared_error(y_test, y_pred)))\n",
    "R2 = metrics.r2_score(y_test,y_pred)\n",
    "print('R2:',R2)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "67e40561",
   "metadata": {},
   "source": [
    "5. Neural Network"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 311,
   "id": "0a008a1c",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\softwares\\anaconda\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:1599: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
      "  y = column_or_1d(y, warn=True)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MAE: 1.516915708790308\n",
      "MSE: 13.976464519523276\n",
      "RMSE: 3.7385110029961495\n",
      "R2: 0.56276734046522\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\softwares\\anaconda\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:692: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "from sklearn.neural_network import MLPRegressor\n",
    "from sklearn.datasets import make_regression\n",
    "from sklearn.model_selection import train_test_split\n",
    "regr = MLPRegressor(random_state=1, max_iter=500).fit(X_train, y_train)\n",
    "regr.predict(X_test[:2])\n",
    "regr.score(X_test, y_test)\n",
    "from sklearn import metrics\n",
    "print('MAE:', metrics.mean_absolute_error(y_test, y_pred))\n",
    "print('MSE:', metrics.mean_squared_error(y_test, y_pred))\n",
    "print('RMSE:', np.sqrt(metrics.mean_squared_error(y_test, y_pred)))\n",
    "R2 = metrics.r2_score(y_test,y_pred)\n",
    "print('R2:',R2)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cf9702b4",
   "metadata": {},
   "source": [
    "### After PCA"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 312,
   "id": "137b1b8e",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.decomposition import PCA\n",
    "pca = PCA(n_components=2)\n",
    "#pca.fit(X1)\n",
    "X1_ = pca.fit_transform(X1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 313,
   "id": "e10d6668",
   "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>PC1</th>\n",
       "      <th>PC2</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-0.490285</td>\n",
       "      <td>-0.322115</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2.468345</td>\n",
       "      <td>-0.488686</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-0.393046</td>\n",
       "      <td>-1.291685</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>-0.657654</td>\n",
       "      <td>0.021169</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2.314750</td>\n",
       "      <td>-0.745471</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        PC1       PC2\n",
       "0 -0.490285 -0.322115\n",
       "1  2.468345 -0.488686\n",
       "2 -0.393046 -1.291685\n",
       "3 -0.657654  0.021169\n",
       "4  2.314750 -0.745471"
      ]
     },
     "execution_count": 313,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X2 = pd.DataFrame(X1_, columns =['PC1','PC2'])\n",
    "X2.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 314,
   "id": "59e52512",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train,X_test,y_train,y_test = train_test_split(X2,y,test_size=0.25,random_state=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 315,
   "id": "52fb1369",
   "metadata": {},
   "outputs": [],
   "source": [
    "MAEp = []\n",
    "MSEp = []\n",
    "RMSEp = []\n",
    "r2P = []"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 316,
   "id": "954a7723",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MAE: 2.1243399435719694\n",
      "MSE: 12.419527310235592\n",
      "RMSE: 3.5241349733282905\n",
      "R2: 0.6114737780478148\n"
     ]
    }
   ],
   "source": [
    "#Linear Regreesion\n",
    "from sklearn.linear_model import LinearRegression\n",
    "\n",
    "regp = LinearRegression()\n",
    "regp.fit(X_train,y_train)\n",
    "y_pred = regp.predict(X_test)\n",
    "\n",
    "y_pred = regp.predict(X_test)\n",
    "from sklearn import metrics\n",
    "print('MAE:', metrics.mean_absolute_error(y_test, y_pred))\n",
    "MAEp.append(metrics.mean_absolute_error(y_test, y_pred))\n",
    "print('MSE:', metrics.mean_squared_error(y_test, y_pred))\n",
    "MSEp.append(metrics.mean_squared_error(y_test, y_pred))\n",
    "print('RMSE:', np.sqrt(metrics.mean_squared_error(y_test, y_pred)))\n",
    "RMSEp.append(np.sqrt(metrics.mean_squared_error(y_test, y_pred)))\n",
    "R2 = metrics.r2_score(y_test,y_pred)\n",
    "print('R2:',R2)\n",
    "r2P.append(R2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 317,
   "id": "5b85417f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MAE: 1.4268421052631577\n",
      "MSE: 8.873378947368419\n",
      "RMSE: 2.9788217380985422\n",
      "R2: 0.7224096930380105\n"
     ]
    }
   ],
   "source": [
    "#Decision Tree\n",
    "treep = DecisionTreeRegressor()\n",
    "treep.fit(X_train,y_train)\n",
    "\n",
    "y_pred = treep.predict(X_test)\n",
    "\n",
    "#print errors\n",
    "y_pred = treep.predict(X_test)\n",
    "from sklearn import metrics\n",
    "print('MAE:', metrics.mean_absolute_error(y_test, y_pred))\n",
    "MAEp.append(metrics.mean_absolute_error(y_test, y_pred))\n",
    "print('MSE:', metrics.mean_squared_error(y_test, y_pred))\n",
    "MSEp.append(metrics.mean_squared_error(y_test, y_pred))\n",
    "print('RMSE:', np.sqrt(metrics.mean_squared_error(y_test, y_pred)))\n",
    "RMSEp.append(np.sqrt(metrics.mean_squared_error(y_test, y_pred)))\n",
    "R2 = metrics.r2_score(y_test,y_pred)\n",
    "print('R2:',R2)\n",
    "r2P.append(R2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 318,
   "id": "71573f67",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[2.1243399435719694, 1.4268421052631577]"
      ]
     },
     "execution_count": 318,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "MAEp"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 319,
   "id": "933c73a9",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\18562\\AppData\\Local\\Temp\\ipykernel_25852\\3313338163.py:2: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().\n",
      "  rfp.fit(X_train,y_train)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MAE: 1.157207894736843\n",
      "MSE: 5.637789766315791\n",
      "RMSE: 2.3744030336730515\n",
      "R2: 0.8236302313806969\n"
     ]
    }
   ],
   "source": [
    "#Random Forest\n",
    "rfp = RandomForestRegressor(n_estimators = 100, random_state = 42)\n",
    "rfp.fit(X_train,y_train)\n",
    "\n",
    "y_pred = rfp.predict(X_test)\n",
    "\n",
    "#print errors\n",
    "y_pred = rfp.predict(X_test)\n",
    "from sklearn import metrics\n",
    "print('MAE:', metrics.mean_absolute_error(y_test, y_pred))\n",
    "MAEp.append(metrics.mean_absolute_error(y_test, y_pred))\n",
    "print('MSE:', metrics.mean_squared_error(y_test, y_pred))\n",
    "MSEp.append(metrics.mean_squared_error(y_test, y_pred))\n",
    "print('RMSE:', np.sqrt(metrics.mean_squared_error(y_test, y_pred)))\n",
    "RMSEp.append(np.sqrt(metrics.mean_squared_error(y_test, y_pred)))\n",
    "R2 = metrics.r2_score(y_test,y_pred)\n",
    "print('R2:',R2)\n",
    "r2P.append(R2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 320,
   "id": "b6ec2366",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MAE: 1.7270775486546663\n",
      "MSE: 15.686290308415844\n",
      "RMSE: 3.9605921663831842\n",
      "R2: 0.509278013749271\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\softwares\\anaconda\\lib\\site-packages\\sklearn\\utils\\validation.py:993: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
      "  y = column_or_1d(y, warn=True)\n"
     ]
    }
   ],
   "source": [
    "#Support Vector Regressor\n",
    "regr_svr = SVR()\n",
    "regr_svr.fit(X_train,y_train)\n",
    "\n",
    "y_pred = regr_svr.predict(X_test)\n",
    "\n",
    "#print errors\n",
    "y_pred = regr_svr.predict(X_test)\n",
    "from sklearn import metrics\n",
    "print('MAE:', metrics.mean_absolute_error(y_test, y_pred))\n",
    "MAEp.append(metrics.mean_absolute_error(y_test, y_pred))\n",
    "print('MSE:', metrics.mean_squared_error(y_test, y_pred))\n",
    "MSEp.append(metrics.mean_squared_error(y_test, y_pred))\n",
    "print('RMSE:', np.sqrt(metrics.mean_squared_error(y_test, y_pred)))\n",
    "RMSEp.append(np.sqrt(metrics.mean_squared_error(y_test, y_pred)))\n",
    "R2 = metrics.r2_score(y_test,y_pred)\n",
    "print('R2:',R2)\n",
    "r2P.append(R2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 321,
   "id": "ee1c5873",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\softwares\\anaconda\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:1599: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
      "  y = column_or_1d(y, warn=True)\n",
      "C:\\softwares\\anaconda\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:692: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n",
      "C:\\softwares\\anaconda\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:1599: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
      "  y = column_or_1d(y, warn=True)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MAE: 1.7342790347659058\n",
      "MSE: 10.317498866343374\n",
      "RMSE: 3.212086372802477\n",
      "R2: 0.6772325746059088\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\softwares\\anaconda\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:692: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "#Neural Network\n",
    "regr_ml = MLPRegressor(random_state=1, max_iter=500).fit(X_train, y_train)\n",
    "regr_ml.fit(X_train,y_train)\n",
    "\n",
    "\n",
    "y_pred = regr_ml.predict(X_test)\n",
    "\n",
    "from sklearn import metrics\n",
    "print('MAE:', metrics.mean_absolute_error(y_test, y_pred))\n",
    "MAEp.append(metrics.mean_absolute_error(y_test, y_pred))\n",
    "print('MSE:', metrics.mean_squared_error(y_test, y_pred))\n",
    "MSEp.append(metrics.mean_squared_error(y_test, y_pred))\n",
    "print('RMSE:', np.sqrt(metrics.mean_squared_error(y_test, y_pred)))\n",
    "RMSEp.append(np.sqrt(metrics.mean_squared_error(y_test, y_pred)))\n",
    "R2 = metrics.r2_score(y_test,y_pred)\n",
    "print('R2:',R2)\n",
    "r2P.append(R2)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9d6f2257",
   "metadata": {},
   "source": [
    "### Comparing models"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 322,
   "id": "29038393",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "A=[1,2,3,4,5]\n",
    "plt.bar(A,MAE,tick_label=['Regression','DecisionTree','RandomForest','KNN','MLP'],color=['red','green','blue','purple', 'yellow'])\n",
    "plt.xlabel('Algorithms')\n",
    "plt.ylabel('values')\n",
    "plt.title('MAE')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 323,
   "id": "d32ea5f7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "A=[1,2,3,4,5]\n",
    "plt.bar(A,MSE,tick_label=['Regression','DecisionTree','RandomForest','KNN','MLP'],color=['red','green','blue','purple', 'yellow'])\n",
    "plt.xlabel('Algorithms')\n",
    "plt.ylabel('values')\n",
    "plt.title('MSE')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 324,
   "id": "2b5fa1a2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "A=[1,2,3,4,5]\n",
    "plt.bar(A,RMSE,tick_label=['Regression','DecisionTree','RandomForest','KNN','MLP'],color=['red','green','blue','purple', 'yellow'])\n",
    "plt.xlabel('Algorithms')\n",
    "plt.ylabel('values')\n",
    "plt.title('RMSE')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 325,
   "id": "62fccec1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "A=[1,2,3,4,5]\n",
    "plt.bar(A,r2,tick_label=['Regression','DecisionTree','RandomForest','KNN','MLP'],color=['red','green','blue','purple', 'yellow'])\n",
    "plt.xlabel('Algorithms')\n",
    "plt.ylabel('values')\n",
    "plt.title('R2')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 326,
   "id": "f0a17ed7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "A=[1,2,3,4,5]\n",
    "plt.bar(A,MAEp,tick_label=['Regression','DecisionTree','RandomForest','KNN','MLP'],color=['red','green','blue','purple', 'yellow'])\n",
    "plt.xlabel('Algorithms')\n",
    "plt.ylabel('values')\n",
    "plt.title('MAE-PCA')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 327,
   "id": "87e9cd99",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "A=[1,2,3,4,5]\n",
    "plt.bar(A,MSEp,tick_label=['Regression','DecisionTree','RandomForest','KNN','MLP'],color=['red','green','blue','purple', 'yellow'])\n",
    "plt.xlabel('Algorithms')\n",
    "plt.ylabel('values')\n",
    "plt.title('MSE-PCA')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 328,
   "id": "6b39de2d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAjcAAAHFCAYAAAAOmtghAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8qNh9FAAAACXBIWXMAAA9hAAAPYQGoP6dpAABBaElEQVR4nO3deVwV9f7H8fdRFFAWzQUxUVwKEXMDSzS3KEnNNM30XiuX1CzT0rTC7tW0BUsz8la4hJC2WIla5p6JZi5XFG7eJDID4RpktoCaouD390cPzs8jqKDgwen1fDzm8Wi+853vfGYY483MnDM2Y4wRAACARVRydgEAAABliXADAAAshXADAAAshXADAAAshXADAAAshXADAAAshXADAAAshXADAAAshXADAAAshXADoMTi4uJks9nsk4uLi3x9fTV48GAdOHDAoW+3bt1ks9nUpEkTFfdF6Fu3brWPExcX57Bs165duueee9SwYUO5urrKx8dHoaGhevLJJ4vdRnGTv7//JfcnPT3dYZ1KlSqpVq1a6tWrl3bs2FGkf25url588UWFhITIy8tLrq6u8vf314gRI7R3795itzF37lzZbDa1bNnykvUAKBsuzi4AwLUnNjZWzZs316lTp/TVV1/pxRdf1ObNm/Xtt9+qZs2a9n6enp5KS0vTF198obCwMIcxFi1aJC8vL+Xm5jq0r169Wnfffbe6deumV155Rb6+vsrKylJiYqKWLl2qV1991aF/kyZN9N577xWp0dXVtcT7M27cOP39739XQUGBvvnmG02fPl3du3fXjh071LZtW0nSwYMH1aNHDx05ckRjxozR9OnT5eHhofT0dH300UcKDg7W77//Lm9v7yL7KUnffPONdu3apVtuuaXEdQG4TAYASig2NtZIMrt373Zonz59upFkFi1aZG/r2rWrCQoKMh06dDB///vfHfrn5uaaatWqmVGjRhlJJjY21r6sS5cupmnTpubMmTNFtl9QUOAwX7iNy5WWlmYkmVmzZjm0b9q0yUgyI0eONMYYk5+fb2666Sbj5eVl9u3bV+xYa9asMSdOnHBo2717t5FkevfubSSZUaNGXXatAEqO21IArlhISIgk6aeffiqybMSIEVq+fLl+//13e9vSpUslSYMHDy7S/5dfflHt2rXl4lL0wnKlSlfnf1kdOnSQJB06dEiStHLlSu3bt08REREXvL3Us2dPVatWzaEtJiZGkjRz5kx17NhRS5cu1R9//FGOlQOQeOYGQBlIS0uTJN14441Flg0ePFiVK1fWBx98YG+LiYnRvffeKy8vryL9Q0NDtWvXLo0fP167du3SmTNnLrn9/Pz8ItPZs2cve3++//57SVKdOnUkSRs2bJAk9evXr8RjnDx5Uh988IHat2+vli1basSIETp27Jg+/vjjy64LQMkQbgCUWkFBgfLz83X8+HGtX79eL7zwgrp06aK77767SF9PT0/de++99mdP9u/fr127dmnEiBHFjj1z5kzdeuut+te//qUOHTqoevXq6tSpk2bOnKnjx48X6f/NN9+oSpUqRabRo0eXeH/Onj2r/Px85eXlae/evRo5cqQkaciQIZKkjIwMSVLjxo1LPOayZcuUk5Ojhx56SJI0aNAgeXh42K/mACg/PFAMoNQKb9sUCgwM1CeffFLsrSTpz1tTXbt21b59+xQXF6emTZuqS5cu2rNnT5G+tWrV0pdffqnExERt2rRJiYmJSkhIUEREhObPn6/du3erdu3a9v5Nmza13+Y6V+FVF+nPKzvnqly5smw2m33+6aef1tNPP22f9/Hx0fz589WrV69LHIkLi4mJkbu7u/3Wm4eHhwYOHKjY2FgdOHBAN9xww2WPDeDiuHIDoNQWL16s3bt364svvtDDDz+slJQU/e1vf7tg/y5duuiGG27Q/PnztWTJEo0YMcIhXBQnJCRETz/9tD7++GP9+OOPmjBhgtLT0/XKK6849HNzc1NISEiRqVGjRvY+51/VeeeddxzGePzxx7V7927t2bNHBw8eVFZWlsOVn4YNG0r6/9tvl/L9999r69at6t27t4wx+v333/X777/r3nvvlfT/n6ACUD4INwBKLTAwUCEhIerevbvmzZunkSNHat26dVq2bNkF1xk+fLiio6P166+/aujQoaXaXpUqVTRt2jRJ0n//+99S17t7926HqU+fPg7LGzRooJCQELVr105NmjQpErzCw8Ml/flgcUksWrRIxhgtW7ZMNWvWtE+9e/eWJL3zzjsqKCgo9X4AKBluSwG4Yq+88ori4+M1depU9e/fv9hPNQ0dOlS7du1SYGCgrr/++guOlZWVJV9f3yLtKSkpkqT69euXur7CT3Ndrr59++qmm25SZGSk7rrrrmI/MbV+/Xp17txZrq6ueuedd9S0aVO9/fbbRfp99tlnevXVV7V27VrdddddV1QXgOIRbgBcsZo1ayoiIkJPPfWU3n//fd1///1F+tSvX79EVz7Cw8PVoEED9enTR82bN9fZs2eVnJysV199VR4eHnr88ccd+p88eVI7d+4sdqzznw26XJUrV9aKFSvUo0cPhYaG6pFHHlH37t1VvXp1HTp0SMuWLdOqVav022+/6YsvvtCPP/6ol19+Wd26dSsyVsuWLfXGG28oJiaGcAOUE8INgDIxbtw4vfHGG5oxY8ZFn7+5lH/84x/65JNP9NprrykrK0t5eXny9fXV7bffroiICAUGBjr0/+GHHxQaGlrsWGfOnLngQ86l1bRpU+3du1f/+te/tGLFCkVHR9tr69Kli7Zt2yZvb2/FxMSoatWqGj58eLHj1K5dW/fcc4+WLVumn376ST4+PmVSH4D/ZzOmmJe+AAAAXKN4oBgAAFgK4QYAAFgK4QYAAFgK4QYAAFgK4QYAAFgK4QYAAFjKX+57bs6ePasff/xRnp6el3y3DQAAqBiMMTp27Jjq169f7Legn+svF25+/PFH+fn5ObsMAABwGTIzM9WgQYOL9vnLhRtPT09Jfx4cLy8vJ1cDAABKIjc3V35+fvbf4xfzlws3hbeivLy8CDcAAFxjSvJICQ8UAwAASyHcAAAASyHcAAAASyHcAAAASyHcAAAASyHcAAAASyHcAAAAS6kw4SYyMlI2m01PPPHERftt2bJFwcHBcnNzU5MmTTRv3ryrUyAAALgmVIhws3v3bi1YsECtWrW6aL+0tDT16tVLnTt3VlJSkqZMmaLx48crPj7+KlUKAAAqOqeHm+PHj2vIkCFauHChatasedG+8+bNU8OGDRUVFaXAwECNHDlSI0aM0OzZs69StQAAoKJzergZO3asevfurdtvv/2SfXfs2KEePXo4tIWHhysxMVFnzpwpdp28vDzl5uY6TAAAwLqcGm6WLl2qPXv2KDIyskT9s7Oz5ePj49Dm4+Oj/Px8HT16tNh1IiMj5e3tbZ94IzgAANbmtHCTmZmpxx9/XO+9957c3NxKvN75L8wyxhTbXigiIkI5OTn2KTMz8/KLBgAAFZ7T3gq+Z88eHTlyRMHBwfa2goICbd26VW+88Yby8vJUuXJlh3Xq1aun7Oxsh7YjR47IxcVFtWrVKnY7rq6ucnV1LfsdAAAAFZLTwk1YWJj27dvn0DZ8+HA1b95cTz/9dJFgI0mhoaFatWqVQ9uGDRsUEhKiKlWqlGu9AADg2uC0cOPp6amWLVs6tFWvXl21atWyt0dEROjw4cNavHixJGnMmDF64403NHHiRI0aNUo7duxQTEyMPvjgg6tePwA4y3TbdGeXcM2YZqY5uwQ4gdM/LXUxWVlZysjIsM83btxYa9asUUJCgtq0aaPnn39ec+fO1YABA5xYJQAAqEicduWmOAkJCQ7zcXFxRfp07dpVe/fuvToFAQCAa06FvnIDAABQWoQbAABgKYQbAABgKYQbAABgKYQbAABgKYQbAABgKYQbAABgKYQbAABgKYQbAABgKYQbAABgKYQbAABgKYQbAABgKYQbAABgKYQbAABgKYQbAABgKYQbAABgKYQbAABgKYQbAABgKYQbAABgKYQbAABgKYQbAABgKYQbAABgKYQbAABgKYQbAABgKYQbAABgKYQbAABgKYQbAABgKYQbAABgKYQbAABgKYQbAABgKYQbAABgKYQbAABgKYQbAABgKU4NN9HR0WrVqpW8vLzk5eWl0NBQrV279oL9ExISZLPZikzffvvtVawaAABUZC7O3HiDBg00c+ZMNWvWTJL0zjvvqG/fvkpKSlJQUNAF10tNTZWXl5d9vk6dOuVeKwAAuDY4Ndz06dPHYf7FF19UdHS0du7cedFwU7duXdWoUaOcqwMAANeiCvPMTUFBgZYuXaoTJ04oNDT0on3btm0rX19fhYWFafPmzVepwhKy2ZhKOgEAUA6ceuVGkvbt26fQ0FCdOnVKHh4eWrFihVq0aFFsX19fXy1YsEDBwcHKy8vTkiVLFBYWpoSEBHXp0qXYdfLy8pSXl2efz83NLZf9AAAAFYPTw01AQICSk5P1+++/Kz4+XkOHDtWWLVuKDTgBAQEKCAiwz4eGhiozM1OzZ8++YLiJjIzU9OnTy61+AABQsTj9tlTVqlXVrFkzhYSEKDIyUq1bt9brr79e4vU7dOigAwcOXHB5RESEcnJy7FNmZmZZlA0AACoop1+5OZ8xxuE20qUkJSXJ19f3gstdXV3l6upaFqUBAIBrgFPDzZQpU9SzZ0/5+fnp2LFjWrp0qRISErRu3TpJf151OXz4sBYvXixJioqKkr+/v4KCgnT69Gm9++67io+PV3x8vDN3AwAAVCBODTc//fSTHnjgAWVlZcnb21utWrXSunXrdMcdd0iSsrKylJGRYe9/+vRpTZo0SYcPH5a7u7uCgoK0evVq9erVy1m7AAAAKhibMcY4u4irKTc3V97e3srJyXH4IsAyw0ecS+6vdeoBZWa6jQ9JlNQ0M83ZJaCMlOb3t9MfKAYAAChLhBsAAGAphBsAAGAphBsAAGAphBsAAGAphBsAAGAphBsAAGAphBsAAGAphBsAAGAphBsAAGAphBsAAGAphBsAAGAphBsAAGAphBsAAGAphBsAAGAphBsAAGAphBsAAGAphBsAAGAphBsAAGApLs4uAACAa4PN2QVcQ4xTt86VGwAAYCmEGwAAYCmEGwAAYCmEGwAAYCmEGwAAYCmEGwAAYCmEGwAAYCmEGwAAYCmEGwAAYCmEGwAAYCmEGwAAYCmEGwAAYCmEGwAAYCmEGwAAYClODTfR0dFq1aqVvLy85OXlpdDQUK1du/ai62zZskXBwcFyc3NTkyZNNG/evKtULQAAuBY4Ndw0aNBAM2fOVGJiohITE3Xbbbepb9+++uabb4rtn5aWpl69eqlz585KSkrSlClTNH78eMXHx1/lygEAQEXl4syN9+nTx2H+xRdfVHR0tHbu3KmgoKAi/efNm6eGDRsqKipKkhQYGKjExETNnj1bAwYMuBolAwCACq7CPHNTUFCgpUuX6sSJEwoNDS22z44dO9SjRw+HtvDwcCUmJurMmTPFrpOXl6fc3FyHCQAAWJfTw82+ffvk4eEhV1dXjRkzRitWrFCLFi2K7ZudnS0fHx+HNh8fH+Xn5+vo0aPFrhMZGSlvb2/75OfnV+b7AAAAKg6nh5uAgAAlJydr586deuSRRzR06FDt37//gv1tNpvDvDGm2PZCERERysnJsU+ZmZllVzwAAKhwnPrMjSRVrVpVzZo1kySFhIRo9+7dev311zV//vwifevVq6fs7GyHtiNHjsjFxUW1atUqdnxXV1e5urqWfeGoUGzTiw+3KMpMM84uAQDKldOv3JzPGKO8vLxil4WGhmrjxo0ObRs2bFBISIiqVKlyNcoDAAAVnFPDzZQpU/Tll18qPT1d+/bt07PPPquEhAQNGTJE0p+3lB588EF7/zFjxujQoUOaOHGiUlJStGjRIsXExGjSpEnO2gUAAFDBOPW21E8//aQHHnhAWVlZ8vb2VqtWrbRu3TrdcccdkqSsrCxlZGTY+zdu3Fhr1qzRhAkT9Oabb6p+/fqaO3cuHwMHAAB2Tg03MTExF10eFxdXpK1r167au3dvOVUEAACudRXumRsAAIArQbgBAACWQrgBAACWQrgBAACWQrgBAACWQrgBAACWQrgBAACWQrgBAACWQrgBAACWQrgBAACWQrgBAACWQrgBAACWQrgBAACWQrgBAACWQrgBAACWQrgBAACWQrgBAACWQrgBAACWQrgBAACWQrgBAACWQrgBAACWQrgBAACWQrgBAACWQrgBAACWQrgBAACWQrgBAACWQrgBAACWQrgBAACWQrgBAACWQrgBAACWQrgBAACWQrgBAACWQrgBAACW4tRwExkZqfbt28vT01N169ZVv379lJqaetF1EhISZLPZikzffvvtVaoaAABUZE4NN1u2bNHYsWO1c+dObdy4Ufn5+erRo4dOnDhxyXVTU1OVlZVln2644YarUDEAAKjoXJy58XXr1jnMx8bGqm7dutqzZ4+6dOly0XXr1q2rGjVqlGN1AADgWlShnrnJycmRJF133XWX7Nu2bVv5+voqLCxMmzdvLu/SAADANcKpV27OZYzRxIkTdeutt6ply5YX7Ofr66sFCxYoODhYeXl5WrJkicLCwpSQkFDs1Z68vDzl5eXZ53Nzc8ulfgAAUDFUmHDz2GOP6euvv9a2bdsu2i8gIEABAQH2+dDQUGVmZmr27NnFhpvIyEhNnz69zOsFAAAVU4W4LTVu3Dh9+umn2rx5sxo0aFDq9Tt06KADBw4UuywiIkI5OTn2KTMz80rLBQAAFZhTr9wYYzRu3DitWLFCCQkJaty48WWNk5SUJF9f32KXubq6ytXV9UrKBAAA1xCnhpuxY8fq/fff1yeffCJPT09lZ2dLkry9veXu7i7pzysvhw8f1uLFiyVJUVFR8vf3V1BQkE6fPq13331X8fHxio+Pd9p+AACAisOp4SY6OlqS1K1bN4f22NhYDRs2TJKUlZWljIwM+7LTp09r0qRJOnz4sNzd3RUUFKTVq1erV69eV6tsAABQgTn9ttSlxMXFOcw/9dRTeuqpp8qpIgAAcK2rEA8UAwAAlBXCDQAAsBTCDQAAsBTCDQAAsBTCDQAAsJQK8/oFANcem83ZFVw7SvDhUABlhCs3AADAUgg3AADAUgg3AADAUgg3AADAUgg3AADAUkodbk6ePKk//vjDPn/o0CFFRUVpw4YNZVoYAADA5Sh1uOnbt68WL14sSfr99991yy236NVXX1Xfvn3tb/kGAABwllKHm71796pz586SpGXLlsnHx0eHDh3S4sWLNXfu3DIvEAAAoDRKHW7++OMPeXp6SpI2bNig/v37q1KlSurQoYMOHTpU5gUCAACURqnDTbNmzbRy5UplZmZq/fr16tGjhyTpyJEj8vLyKvMCAQAASqPU4Wbq1KmaNGmS/P39dfPNNys0NFTSn1dx2rZtW+YFAgAAlEap3y1177336tZbb1VWVpZat25tbw8LC9M999xTpsUBAACU1mV9z029evXk6empjRs36uTJk5Kk9u3bq3nz5mVaHAAAQGmVOtz88ssvCgsL04033qhevXopKytLkjRy5Eg9+eSTZV4gAABAaZQ63EyYMEFVqlRRRkaGqlWrZm8fNGiQ1q1bV6bFAQAAlFapn7nZsGGD1q9frwYNGji033DDDXwUHAAAOF2pr9ycOHHC4YpNoaNHj8rV1bVMigIAALhcpQ43Xbp0sb9+QZJsNpvOnj2rWbNmqXv37mVaHAAAQGmV+rbUrFmz1K1bNyUmJur06dN66qmn9M033+jXX3/VV199VR41AgAAlFipr9y0aNFCX3/9tW6++WbdcccdOnHihPr376+kpCQ1bdq0PGoEAAAosVJfuZH+/J6b6dOnl3UtAAAAV6zU4Wbr1q0XXd6lS5fLLgYAAOBKlTrcdOvWrUibzWaz/3dBQcEVFQQAAHAlSv3MzW+//eYwHTlyROvWrVP79u21YcOG8qgRAACgxEp95cbb27tI2x133CFXV1dNmDBBe/bsKZPCAAAALsdlvTizOHXq1FFqampZDQcAAHBZSn3l5uuvv3aYN8YoKytLM2fOVOvWrcusMAAAgMtR6nDTpk0b2Ww2GWMc2jt06KBFixaVWWEAAACXo9S3pdLS0vTDDz8oLS1NaWlpOnTokP744w9t375dzZs3L9VYkZGRat++vTw9PVW3bl3169evRLe2tmzZouDgYLm5ualJkyaaN29eaXcDAABYVKnDTaNGjRwmPz8/ubm5XdbGt2zZorFjx2rnzp3auHGj8vPz1aNHD504ceKC66SlpalXr17q3LmzkpKSNGXKFI0fP17x8fGXVQMAALCWEt2Wmjt3bokHHD9+fIn7rlu3zmE+NjZWdevW1Z49ey74ZYDz5s1Tw4YNFRUVJUkKDAxUYmKiZs+erQEDBpR42wAAwJpKFG5ee+21Eg1ms9lKFW7Ol5OTI0m67rrrLthnx44d6tGjh0NbeHi4YmJidObMGVWpUsVhWV5envLy8uzzubm5l10fAACo+EoUbtLS0sq7DhljNHHiRN16661q2bLlBftlZ2fLx8fHoc3Hx0f5+fk6evSofH19HZZFRkbyHiwAAP5Cyux7bq7UY489pq+//loffPDBJfue+7oHSfZPbp3fLkkRERHKycmxT5mZmWVTMAAAqJAu663g//vf//Tpp58qIyNDp0+fdlg2Z86cUo83btw4ffrpp9q6dasaNGhw0b716tVTdna2Q9uRI0fk4uKiWrVqFenv6uoqV1fXUtcEAACuTaUON5s2bdLdd9+txo0bKzU1VS1btlR6erqMMWrXrl2pxjLGaNy4cVqxYoUSEhLUuHHjS64TGhqqVatWObRt2LBBISEhRZ63AQAAfz2lvi0VERGhJ598Uv/973/l5uam+Ph4ZWZmqmvXrho4cGCpxho7dqzeffddvf/++/L09FR2drays7N18uRJh+09+OCD9vkxY8bo0KFDmjhxolJSUrRo0SLFxMRo0qRJpd0VAABgQaUONykpKRo6dKgkycXFRSdPnpSHh4dmzJihl19+uVRjRUdHKycnR926dZOvr699+vDDD+19srKylJGRYZ9v3Lix1qxZo4SEBLVp00bPP/+85s6dy8fAAQCApMu4LVW9enX7R6vr16+vgwcPKigoSJJ09OjRUo11/iscihMXF1ekrWvXrtq7d2+ptgUAAP4aSh1uOnTooK+++kotWrRQ79699eSTT2rfvn1avny5OnToUB41AgAAlFipw82cOXN0/PhxSdJzzz2n48eP68MPP1SzZs1K/GV/AAAA5aXU4eb555/X/fffL2OMqlWrprfeeqs86gIAALgspX6g+JdfflHv3r3VoEEDPfnkk0pOTi6HsgAAAC5PqcPNp59+quzsbE2bNk179uxRcHCwWrRooZdeeknp6enlUCIAAEDJXdbrF2rUqKHRo0crISFBhw4d0vDhw7VkyRI1a9asrOsDAAAolSt6t9SZM2eUmJioXbt2KT09vcgLLQEAAK62ywo3mzdv1qhRo+Tj46OhQ4fK09NTq1at4qWUAADA6Ur9aakGDRrol19+UXh4uObPn68+ffrIzc2tPGoDAAAotVKHm6lTp2rgwIGqWbNmedQDAABwRUodbkaPHl0edQAAAJSJK3qgGAAAoKIh3AAAAEsh3AAAAEsh3AAAAEsh3AAAAEsh3AAAAEsh3AAAAEsh3AAAAEsh3AAAAEsh3AAAAEsh3AAAAEsh3AAAAEsh3AAAAEsh3AAAAEsh3AAAAEsh3AAAAEsh3AAAAEsh3AAAAEsh3AAAAEsh3AAAAEsh3AAAAEsh3AAAAEtxarjZunWr+vTpo/r168tms2nlypUX7Z+QkCCbzVZk+vbbb69OwQAAoMJzcebGT5w4odatW2v48OEaMGBAiddLTU2Vl5eXfb5OnTrlUR4AALgGOTXc9OzZUz179iz1enXr1lWNGjXKviAAAHDNuyafuWnbtq18fX0VFhamzZs3X7RvXl6ecnNzHSYAAGBd11S48fX11YIFCxQfH6/ly5crICBAYWFh2rp16wXXiYyMlLe3t33y8/O7ihUDAICrzam3pUorICBAAQEB9vnQ0FBlZmZq9uzZ6tKlS7HrREREaOLEifb53NxcAg4AABZ2TV25KU6HDh104MCBCy53dXWVl5eXwwQAAKzrmg83SUlJ8vX1dXYZAACggnDqbanjx4/r+++/t8+npaUpOTlZ1113nRo2bKiIiAgdPnxYixcvliRFRUXJ399fQUFBOn36tN59913Fx8crPj7eWbsAAAAqGKeGm8TERHXv3t0+X/hszNChQxUXF6esrCxlZGTYl58+fVqTJk3S4cOH5e7urqCgIK1evVq9evW66rUDAICKyWaMMc4u4mrKzc2Vt7e3cnJyyuf5G5ut7Me0qjI89WzTOe4lZaaV4XHnsJdYWf6fdrptetkNZnHTzLQyHI0TvuTKPlqU5vf3Nf/MDQAAwLkINwAAwFIINwAAwFIINwAAwFIINwAAwFIINwAAwFIINwAAwFIINwAAwFIINwAAwFIINwAAwFIINwAAwFIINwAAwFIINwAAwFIINwAAwFIINwAAwFIINwAAwFIINwAAwFIINwAAwFIINwAAwFIINwAAwFIINwAAwFIINwAAwFIINwAAwFIINwAAwFIINwAAwFIINwAAwFIINwAAwFIINwAAwFIINwAAwFIINwAAwFIINwAAwFIINwAAwFIINwAAwFIINwAAwFKcGm62bt2qPn36qH79+rLZbFq5cuUl19myZYuCg4Pl5uamJk2aaN68eeVfKAAAuGY4NdycOHFCrVu31htvvFGi/mlpaerVq5c6d+6spKQkTZkyRePHj1d8fHw5VwoAAK4VLs7ceM+ePdWzZ88S9583b54aNmyoqKgoSVJgYKASExM1e/ZsDRgwoJyqBAAA15Jr6pmbHTt2qEePHg5t4eHhSkxM1JkzZ4pdJy8vT7m5uQ4TAACwrmsq3GRnZ8vHx8ehzcfHR/n5+Tp69Gix60RGRsrb29s++fn5XY1SAQCAk1xT4UaSbDabw7wxptj2QhEREcrJybFPmZmZ5V4jAABwHqc+c1Na9erVU3Z2tkPbkSNH5OLiolq1ahW7jqurq1xdXa9GeQAAoAK4pq7chIaGauPGjQ5tGzZsUEhIiKpUqeKkqgAAQEXi1HBz/PhxJScnKzk5WdKfH/VOTk5WRkaGpD9vKT344IP2/mPGjNGhQ4c0ceJEpaSkaNGiRYqJidGkSZOcUT4AAKiAnHpbKjExUd27d7fPT5w4UZI0dOhQxcXFKSsryx50JKlx48Zas2aNJkyYoDfffFP169fX3Llz+Rg4AACwc2q46datm/2B4OLExcUVaevatav27t1bjlUBAIBr2TX1zA0AAMClEG4AAIClEG4AAIClEG4AAIClEG4AAIClEG4AAIClEG4AAIClEG4AAIClEG4AAIClEG4AAIClEG4AAIClEG4AAIClEG4AAIClEG4AAIClEG4AAIClEG4AAIClEG4AAIClEG4AAIClEG4AAIClEG4AAIClEG4AAIClEG4AAIClEG4AAIClEG4AAIClEG4AAIClEG4AAIClEG4AAIClEG4AAIClEG4AAIClEG4AAIClEG4AAIClEG4AAIClEG4AAIClOD3cvPXWW2rcuLHc3NwUHBysL7/88oJ9ExISZLPZikzffvvtVawYAABUZE4NNx9++KGeeOIJPfvss0pKSlLnzp3Vs2dPZWRkXHS91NRUZWVl2acbbrjhKlUMAAAqOqeGmzlz5uihhx7SyJEjFRgYqKioKPn5+Sk6Ovqi69WtW1f16tWzT5UrV75KFQMAgIrOaeHm9OnT2rNnj3r06OHQ3qNHD23fvv2i67Zt21a+vr4KCwvT5s2bL9o3Ly9Pubm5DhMAALAup4Wbo0ePqqCgQD4+Pg7tPj4+ys7OLnYdX19fLViwQPHx8Vq+fLkCAgIUFhamrVu3XnA7kZGR8vb2tk9+fn5luh8AAKBicXF2ATabzWHeGFOkrVBAQIACAgLs86GhocrMzNTs2bPVpUuXYteJiIjQxIkT7fO5ubkEHAAALMxpV25q166typUrF7lKc+TIkSJXcy6mQ4cOOnDgwAWXu7q6ysvLy2ECAADW5bRwU7VqVQUHB2vjxo0O7Rs3blTHjh1LPE5SUpJ8fX3LujwAAHCNcuptqYkTJ+qBBx5QSEiIQkNDtWDBAmVkZGjMmDGS/ryldPjwYS1evFiSFBUVJX9/fwUFBen06dN69913FR8fr/j4eGfuBgAAqECcGm4GDRqkX375RTNmzFBWVpZatmypNWvWqFGjRpKkrKwsh++8OX36tCZNmqTDhw/L3d1dQUFBWr16tXr16uWsXQAAABWMzRhjnF3E1ZSbmytvb2/l5OSUz/M3F3gYGsUow1PPNp3jXlJmWhkedw57iZXl/2mn26aX3WAWN81MK8PROOFLruyjRWl+fzv99QsAAABliXADAAAshXADAAAshXADAAAshXADAAAshXADAAAshXADAAAshXADAAAshXADAAAshXADAAAshXADAAAshXADAAAshXADAAAshXADAAAshXADAAAshXADAAAshXADAAAshXADAAAshXADAAAshXADAAAshXADAAAshXADAAAshXADAAAshXADAAAshXADAAAshXADAAAshXADAAAshXADAAAshXADAAAshXADAAAshXADAAAshXADAAAshXADAAAsxenh5q233lLjxo3l5uam4OBgffnllxftv2XLFgUHB8vNzU1NmjTRvHnzrlKlAADgWuDUcPPhhx/qiSee0LPPPqukpCR17txZPXv2VEZGRrH909LS1KtXL3Xu3FlJSUmaMmWKxo8fr/j4+KtcOQAAqKicGm7mzJmjhx56SCNHjlRgYKCioqLk5+en6OjoYvvPmzdPDRs2VFRUlAIDAzVy5EiNGDFCs2fPvsqVAwCAispp4eb06dPas2ePevTo4dDeo0cPbd++vdh1duzYUaR/eHi4EhMTdebMmXKrFQAAXDtcnLXho0ePqqCgQD4+Pg7tPj4+ys7OLnad7OzsYvvn5+fr6NGj8vX1LbJOXl6e8vLy7PM5OTmSpNzc3CvdBVypsvwZnCq7oayOc985yvZ054QvKc53Zyn74174szTGXLKv08JNIZvN5jBvjCnSdqn+xbUXioyM1PTp04u0+/n5lbZUlDVvb2dX8JfkPZPj7gyc7s4x03ums0v4iyq/E/7YsWPyvsQ/KKeFm9q1a6ty5cpFrtIcOXKkyNWZQvXq1Su2v4uLi2rVqlXsOhEREZo4caJ9/uzZs/r1119Vq1ati4YoK8nNzZWfn58yMzPl5eXl7HL+EjjmzsFxdw6Ou3P81Y67MUbHjh1T/fr1L9nXaeGmatWqCg4O1saNG3XPPffY2zdu3Ki+ffsWu05oaKhWrVrl0LZhwwaFhISoSpUqxa7j6uoqV1dXh7YaNWpcWfHXKC8vr7/EP4CKhGPuHBx35+C4O8df6bhf6opNIad+WmrixIl6++23tWjRIqWkpGjChAnKyMjQmDFjJP151eXBBx+09x8zZowOHTqkiRMnKiUlRYsWLVJMTIwmTZrkrF0AAAAVjFOfuRk0aJB++eUXzZgxQ1lZWWrZsqXWrFmjRo0aSZKysrIcvvOmcePGWrNmjSZMmKA333xT9evX19y5czVgwABn7QIAAKhgnP5A8aOPPqpHH3202GVxcXFF2rp27aq9e/eWc1XW4urqqmnTphW5PYfywzF3Do67c3DcnYPjfmE2U5LPVAEAAFwjnP5uKQAAgLJEuAEAAJZCuAEAAJZCuEGJ2Ww2rVy50tllXDX+/v6Kiooq8764MI4jgLJAuCkHw4YNk81mk81mk4uLixo2bKhHHnlEv/32m7NLuyJZWVnq2bOns8twOL5VqlSRj4+P7rjjDi1atEhnz54ts+3s3r1bo0ePLvO+JVG4fxeahg0bVmbbOp9Vz99z+fv7FzmmDRo0cHpNFSXYDRs2TP369XNoW7Zsmdzc3PTKK6/oueeek81ms38nWaHk5GTZbDalp6dLktLT02Wz2VS3bl0dO3bMoW+bNm303HPPleNeXJsK//2df2ylPz9dfO6//+J+Tuc69zyvVq2aWrZsqfnz55dT5RUL4aac3HnnncrKylJ6errefvttrVq16oIfeS8Lxhjl5+eX2/jSn6+/qCgfOTz3+K5du1bdu3fX448/rrvuuqvMjkOdOnVUrVq1Mu9bEllZWfYpKipKXl5eDm2vv/66Q/8zZ86U2balq3/+OkPh92sVTklJSZc9Vlkf/4rm7bff1pAhQ/TGG2/oqaeekiS5ubkpJiZG33333SXXP3bsmGbPnl3eZVqGn5+fli5dqpMnT9rbTp06pQ8++EANGzYs1ViF5/nXX3+tfv36acyYMfrwww/LuuQKh3BTTlxdXVWvXj01aNBAPXr00KBBg7Rhwwb78tjYWAUGBsrNzU3NmzfXW2+95bD+9u3b1aZNG7m5uSkkJEQrV66UzWZTcnKyJCkhIUE2m03r169XSEiIXF1d9eWXX8oYo1deeUVNmjSRu7u7WrdurWXLltnH/e233zRkyBDVqVNH7u7uuuGGGxQbGytJOn36tB577DH5+vrKzc1N/v7+ioyMtK97/m2pffv26bbbbpO7u7tq1aql0aNH6/jx4/blhX9VzJ49W76+vqpVq5bGjh1bJr8ICo/v9ddfr3bt2mnKlCn65JNPtHbtWvv3I+Xk5Gj06NGqW7euvLy8dNttt+k///mPwziffvqpQkJC5Obmptq1a6t///72Zef/Jf3cc8+pYcOGcnV1Vf369TV+/PgL9s3IyFDfvn3l4eEhLy8v3Xffffrpp58cxmrTpo2WLFkif39/eXt7a/Dgwfa/buvVq2efvL29ZbPZ7POnTp1SjRo19NFHH6lbt25yc3PTu+++K+nS59Xhw4c1aNAg1axZU7Vq1VLfvn3tf2UXd3yLO38LCgr00EMPqXHjxnJ3d1dAQECRsFWSn/2RI0fUp08fubu7q3HjxnrvvfeK1FHS47ho0SI1bNhQHh4eeuSRR1RQUKBXXnlF9erVU926dfXiiy8WGdvT09PhONepU8e+LDo6Wk2bNlXVqlUVEBCgJUuWOKxrs9k0b9489e3bV9WrV9cLL7wgSVq1apWCg4Pl5uamJk2aaPr06Q5h+0LnULdu3XTo0CFNmDDB/pd2RfHKK6/oscce0/vvv6+RI0fa2wMCAtS9e3f94x//uOQY48aN05w5c3TkyJHyLNUy2rVrp4YNG2r58uX2tuXLl8vPz09t27Yt1ViF53mzZs30wgsv6IYbbvhLPF5AuLkKfvjhB61bt87+/quFCxfq2Wef1YsvvqiUlBS99NJL+uc//6l33nlH0p9/5fTp00c33XST9u7dq+eff15PP/10sWM/9dRTioyMVEpKilq1aqV//OMfio2NVXR0tL755htNmDBB999/v7Zs2SJJ+uc//6n9+/dr7dq1SklJUXR0tGrXri1Jmjt3rj799FN99NFHSk1N1bvvvit/f/9it/vHH3/ozjvvVM2aNbV79259/PHH+vzzz/XYY4859Nu8ebMOHjyozZs365133lFcXFyxX85YFm677Ta1bt1ay5cvlzFGvXv3VnZ2ttasWaM9e/aoXbt2CgsL06+//ipJWr16tfr376/evXsrKSlJmzZtUkhISLFjL1u2TK+99prmz5+vAwcOaOXKlbrpppuK7WuMUb9+/fTrr79qy5Yt2rhxow4ePKhBgwY59Dt48KBWrlypzz77TJ999pm2bNmimTNL/gbjp59+WuPHj1dKSorCw8MveV798ccf6t69uzw8PLR161Zt27ZNHh4euvPOO3X69OkLbuf88/fs2bNq0KCBPvroI+3fv19Tp07VlClT9NFHHzmsd6mf/bBhw5Senq4vvvhCy5Yt01tvveXwy680x3Ht2rVat26dPvjgAy1atEi9e/fW//73P23ZskUvv/yy/vGPf2jnzp0lOq4rVqzQ448/rieffFL//e9/9fDDD2v48OHavHmzQ79p06apb9++2rdvn0aMGKH169fr/vvv1/jx47V//37Nnz9fcXFx9mB1sXNo+fLlatCggcPVpIrgmWee0fPPP6/PPvus2G+CnzlzpuLj47V79+6LjvO3v/1NzZo104wZM8qrVMsZPny4/Q9PSVq0aJFGjBhxxeO6ublZ/kqjJMmgzA0dOtRUrlzZVK9e3bi5uRlJRpKZM2eOMcYYPz8/8/777zus8/zzz5vQ0FBjjDHR0dGmVq1a5uTJk/blCxcuNJJMUlKSMcaYzZs3G0lm5cqV9j7Hjx83bm5uZvv27Q5jP/TQQ+Zvf/ubMcaYPn36mOHDhxdb97hx48xtt91mzp49W+xySWbFihXGGGMWLFhgatasaY4fP25fvnr1alOpUiWTnZ1tPw6NGjUy+fn59j4DBw40gwYNKv7AldDQoUNN3759i102aNAgExgYaDZt2mS8vLzMqVOnHJY3bdrUzJ8/3xhjTGhoqBkyZMgFt9OoUSPz2muvGWOMefXVV82NN95oTp8+fcm+GzZsMJUrVzYZGRn25d98842RZP79738bY4yZNm2aqVatmsnNzbX3mTx5srnllluKjB0bG2u8vb3t82lpaUaSiYqKcuh3qfMqJibGBAQEOPx88/LyjLu7u1m/fr297VLnb3EeffRRM2DAAIcxLvazT01NNZLMzp077ctTUlKMpCs+juHh4cbf398UFBTY2wICAkxkZKR9vlGjRqZq1aqmevXq9un11183xhjTsWNHM2rUKIf9GzhwoOnVq5d9XpJ54oknHPp07tzZvPTSSw5tS5YsMb6+vsaY0p1DzjZ06FBTtWpVI8ls2rSpyPJp06aZ1q1bG2OMGTx4sLntttuMMcYkJSUZSSYtLc0Y8//nalJSklm3bp2pUqWK+f77740xxrRu3dpMmzbtauzONaXw/28///yzcXV1NWlpaSY9Pd24ubmZn3/+2fTt29cMHTrUoe+FnHtOnTlzxsTGxhpJ5q233ir/HXEyrtyUk+7duys5OVm7du3SuHHjFB4ernHjxunnn39WZmamHnroIXl4eNinF154QQcPHpQkpaamqlWrVnJzc7OPd/PNNxe7nXOvNOzfv1+nTp3SHXfc4TD24sWL7WM/8sgjWrp0qdq0aaOnnnpK27dvt68/bNgwJScnKyAgQOPHj3e4jXa+lJQUtW7dWtWrV7e3derUSWfPnlVqaqq9LSgoSJUrV7bP+/r6luulaWOMbDab9uzZo+PHj6tWrVoOxyItLc1+LJKTkxUWFlaicQcOHKiTJ0+qSZMmGjVqlFasWHHBZ3tSUlLk5+cnPz8/e1uLFi1Uo0YNpaSk2Nv8/f3l6elpny/tsTn3Z1+S82rPnj36/vvv5enpaV9+3XXX6dSpU/Y+hS50/haaN2+eQkJCVKdOHXl4eGjhwoUO74GTLv6zT0lJkYuLi8M+NG/eXDVq1Lji4+jj46MWLVqoUqVKDm3nH9vJkycrOTnZPhW+pDclJUWdOnVy6NupUyeHbZ5//KU/j++MGTMcjv+oUaOUlZWlP/74o1TnUEXQqlUr+fv7a+rUqUUeBj7XCy+8oC+//PKi/7+QpPDwcN1666365z//WdalWlLt2rXVu3dvvfPOO4qNjVXv3r3tV9lL4+mnn5aHh4fc3d01duxYTZ48WQ8//HA5VFyxOP3dUlZVvXp1NWvWTNKft3u6d++u6dOn22/bLFy4ULfccovDOoW/CAp/QZ/LXOAtGeeGi8JPCq1evVrXX3+9Q7/CB4F79uypQ4cOafXq1fr8888VFhamsWPHavbs2WrXrp3S0tK0du1aff7557rvvvt0++23Ozyzc249F3ou4Nz2wlsZ5y4ry080nS8lJUWNGzfW2bNn5evrq4SEhCJ9Cn+Buru7l3hcPz8/paamauPGjfr888/16KOPatasWdqyZUuRfbzQsTm//UqPTXE/+4udV2fPnlVwcHCxz7ac+7xJ4djFnb/PP/+8PvroI02YMEGvvvqqQkND5enpqVmzZmnXrl0OY1xs/wrP54s9W3Ilx7Ekx7Z27dr2fTxfcf/+zm879/hLfx7f6dOnOzy3VcjNza1U51BFcP311ys+Pl7du3fXnXfeqXXr1jmEyEJNmzbVqFGj9MwzzygmJuaiY86cOVOhoaGaPHlyeZVtKSNGjLD/znjzzTcva4zJkydr2LBhqlatmnx9fSvU81zliSs3V8m0adM0e/ZsFRQU6Prrr9cPP/ygZs2aOUyNGzeW9OdfsF9//bXy8vLs6ycmJl5yGy1atJCrq6syMjKKjH3uX7916tTRsGHD9O677yoqKkoLFiywL/Py8tKgQYO0cOFCffjhh4qPj7c/o3L+tpKTk3XixAl721dffaVKlSrpxhtvvKxjdKW++OIL7du3TwMGDFC7du2UnZ0tFxeXIsei8K+fVq1aadOmTSUe393dXXfffbfmzp2rhIQE7dixQ/v27SvSr0WLFsrIyFBmZqa9bf/+/crJyVFgYOCV72gxfHx8LnletWvXTgcOHFDdunWL9PH29r7o+IXn748//qgvv/xSHTt21KOPPqq2bduqWbNmRa78XEpgYKDy8/MdzuvU1FT9/vvv9nlnHMfC2rZt2+bQtn379ktus127dkpNTS1ybJs1a2a/inSxc6hq1aoqKCgon526TA0bNtSWLVt05MgR9ejRQ7m5ucX2mzp1qr777jstXbr0ouPdfPPN6t+/v5555pnyKNdyCp+HO336tMLDwy9rjMIQX79+/b9MsJG4cnPVdOvWTUFBQXrppZf03HPPafz48fLy8lLPnj2Vl5enxMRE/fbbb5o4caL+/ve/69lnn9Xo0aP1zDPPKCMjw/4xyoudnJ6enpo0aZImTJigs2fP6tZbb1Vubq62b98uDw8PDR06VFOnTlVwcLCCgoKUl5enzz77zP4/7ddee02+vr5q06aNKlWqpI8//lj16tVzuFVQaMiQIZo2bZqGDh2q5557Tj///LPGjRunBx54QD4+PuVyDM+Vl5en7OxsFRQU6KefftK6desUGRmpu+66Sw8++KAqVaqk0NBQ9evXTy+//LICAgL0448/as2aNerXr59CQkI0bdo0hYWFqWnTpho8eLDy8/O1du1a+0ddzxUXF6eCggLdcsstqlatmpYsWSJ3d3c1atSoSN/bb79drVq10pAhQxQVFaX8/Hw9+uij6tq16wUfWC4LlzqvhgwZolmzZqlv376aMWOGGjRooIyMDC1fvlyTJ0++6Pe8nHv+3nDDDVq8eLHWr1+vxo0ba8mSJdq9e7c9RJVEQECA7rzzTo0aNUoLFiyQi4uLnnjiCYerac46jpMnT9Z9991nfwB91apVWr58uT7//POLrjd16lTddddd8vPz08CBA1WpUiV9/fXX2rdvn1544YVLnkP+/v7aunWrBg8eLFdX18u6BVEeGjRooISEBHXv3l09evTQ+vXri/Tx8fHRxIkTNWvWrEuO9+KLLyooKEguLvz6uZTKlSvbb4eee4v3XDk5OfZP0Ra67rrrSv2Rcavhys1VNHHiRC1cuFDh4eF6++23FRcXp5tuukldu3ZVXFyc/ZeDl5eXVq1apeTkZLVp00bPPvuspk6dKkkOz+EU5/nnn9fUqVMVGRmpwMBAhYeHa9WqVfaxq1atqoiICLVq1UpdunRR5cqV7X9teXh46OWXX1ZISIjat2+v9PR0rVmzxuHZhULVqlXT+vXr9euvv6p9+/a69957FRYWpjfeeKMsD9kFrVu3Tr6+vvL399edd96pzZs3a+7cufrkk09UuXJl2Ww2rVmzRl26dNGIESN04403avDgwUpPT7eHr27duunjjz/Wp59+qjZt2ui2224rcmulUI0aNbRw4UJ16tTJfsVn1apVqlWrVpG+hR+Zr1mzprp06aLbb79dTZo0Kffvlhg5cuRFz6tq1app69atatiwofr376/AwECNGDFCJ0+elJeX1yXHLzx/+/Xrp/79+2vQoEG65ZZb9Msvv1zWd+DExsbKz89PXbt2Vf/+/e0f2y/krOPYr18/vf7665o1a5aCgoI0f/58xcbGqlu3bhddLzw8XJ999pk2btyo9u3bq0OHDpozZ449vFzqHJoxY4bS09PVtGnTIrcJne3666/Xli1b9Pvvv+uOO+5wuMJWaPLkyfLw8LjkWDfeeKNGjBihU6dOlUOl1uPl5XXRf58JCQlq27atw1T4++KvzGYu9DAHKpT33ntPw4cPV05OTqmeFQEA4K+G64IV1OLFi9WkSRNdf/31+s9//qOnn35a9913H8EGAIBLINxUUNnZ2Zo6daqys7Pl6+urgQMHFvstqwAAwBG3pQAAgKXwQDEAALAUwg0AALAUwg0AALAUwg0AALAUwg2AcpWQkCCbzVbsF785a1v+/v6Kiooq93oAOAfhBkCZ2L59uypXrqw777zTaTV07NhRWVlZ9ndlxcXFFfv6EADWRrgBUCYWLVqkcePGadu2bcrIyLjq2z9z5oyqVq2qevXq/aVeEAigKMINgCt24sQJffTRR3rkkUd01113KS4u7qL9Fy5cKD8/P1WrVk333HOP5syZU+QKS3R0tJo2baqqVasqICBAS5YscVhus9k0b9489e3bV9WrV9cLL7zgcFsqISHB/soSm80mm82m5557zr7+H3/8oREjRsjT01MNGzbUggUL7MvS09Nls9n00UcfqXPnznJ3d1f79u313Xffaffu3QoJCZGHh4fuvPNO/fzzz/b1EhISdPPNN6t69eqqUaOGOnXqpEOHDl32cQVwmQwAXKGYmBgTEhJijDFm1apVxt/f35w9e9YYY8zmzZuNJPPbb78ZY4zZtm2bqVSpkpk1a5ZJTU01b775prnuuuuMt7e3fbzly5ebKlWqmDfffNOkpqaaV1991VSuXNl88cUX9j6STN26dU1MTIw5ePCgSU9Pd9hWXl6eiYqKMl5eXiYrK8tkZWWZY8eOGWOMadSokbnuuuvMm2++aQ4cOGAiIyNNpUqVTEpKijHGmLS0NCPJNG/e3Kxbt87s37/fdOjQwbRr185069bNbNu2zezdu9c0a9bMjBkzxhhjzJkzZ4y3t7eZNGmS+f77783+/ftNXFycOXToUHkffgDnIdwAuGIdO3Y0UVFRxpg/f8nXrl3bbNy40RhTNNwMGjTI9O7d22H9IUOGOISbjh07mlGjRjn0GThwoOnVq5d9XpJ54oknHPqcv63Y2FiHcQs1atTI3H///fb5s2fPmrp165ro6GhjzP+Hm7ffftve54MPPjCSzKZNm+xtkZGRJiAgwBhjzC+//GIkmYSEhAseJwBXB7elAFyR1NRU/fvf/9bgwYMlSS4uLho0aJAWLVp0wf4333yzQ9v58ykpKerUqZNDW6dOnZSSkuLQFhISctl1t2rVyv7fNptN9erV05EjRy7Yx8fHR5J00003ObQVrnPddddp2LBhCg8PV58+ffT6668rKyvrsusDcPkINwCuSExMjPLz83X99dfLxcVFLi4uio6O1vLly/Xbb78V6W+MKfLArynmFXfF9Tm/rXr16pddd5UqVYps7+zZsxfsU7jt89vOXSc2NlY7duxQx44d9eGHH+rGG2/Uzp07L7tGAJeHcAPgsuXn52vx4sV69dVXlZycbJ/+85//qFGjRnrvvfeKrNO8eXP9+9//dmhLTEx0mA8MDNS2bdsc2rZv367AwMBS1Ve1alUVFBSUap0r1bZtW0VERGj79u1q2bKl3n///au6fQCSi7MLAHDt+uyzz/Tbb7/poYcesn+3TKF7771XMTExeu211xzax40bpy5dumjOnDnq06ePvvjiC61du9bhqszkyZN13333qV27dgoLC9OqVau0fPlyff7556Wqz9/fX8ePH9emTZvUunVrVatWTdWqVbv8Hb6ItLQ0LViwQHfffbfq16+v1NRUfffdd3rwwQfLZXsALowrNwAuW0xMjG6//fYiwUaSBgwYoOTkZO3du9ehvVOnTpo3b57mzJmj1q1ba926dZowYYLc3Nzsffr166fXX39ds2bNUlBQkObPn6/Y2Fh169atVPV17NhRY8aM0aBBg1SnTh298sorl7WfJVGtWjV9++23GjBggG688UaNHj1ajz32mB5++OFy2yaA4tlMcTe7AeAqGjVqlL799lt9+eWXzi4FgAVwWwrAVTd79mzdcccdql69utauXat33nlHb731lrPLAmARXLkBcNXdd999SkhI0LFjx9SkSRONGzdOY8aMcXZZACyCcAMAACyFB4oBAIClEG4AAIClEG4AAIClEG4AAIClEG4AAIClEG4AAIClEG4AAIClEG4AAIClEG4AAICl/B/84Cad+tkvEwAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "A=[1,2,3,4,5]\n",
    "plt.bar(A,RMSEp,tick_label=['Regression','DecisionTree','RandomForest','KNN','MLP'],color=['red','green','blue','purple', 'yellow'])\n",
    "plt.xlabel('Algorithms')\n",
    "plt.ylabel('values')\n",
    "plt.title('RMSE-PCA')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 329,
   "id": "9a368ee0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "A=[1,2,3,4,5]\n",
    "plt.bar(A,r2P,tick_label=['Regression','DecisionTree','RandomForest','KNN','MLP'],color=['red','green','blue','purple', 'yellow'])\n",
    "plt.xlabel('Algorithms')\n",
    "plt.ylabel('values')\n",
    "plt.title('r2-PCA')\n",
    "plt.show()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}