{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 96,
   "id": "52e4d5b0-5142-488c-afe8-da951cce0ec5",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import warnings\n",
    "warnings.filterwarnings('ignore')\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "e6eee592-2f01-482a-bf99-2140ba125d70",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'2.3.2'"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.__version__"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "id": "40099d81-2fd2-41cd-ae18-093e7174f8fb",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(\"car_fuel_efficiency.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "id": "d7432f7f-c628-428e-b7ba-f932f85c0469",
   "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>engine_displacement</th>\n",
       "      <th>num_cylinders</th>\n",
       "      <th>horsepower</th>\n",
       "      <th>vehicle_weight</th>\n",
       "      <th>acceleration</th>\n",
       "      <th>model_year</th>\n",
       "      <th>origin</th>\n",
       "      <th>fuel_type</th>\n",
       "      <th>drivetrain</th>\n",
       "      <th>num_doors</th>\n",
       "      <th>fuel_efficiency_mpg</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>170</td>\n",
       "      <td>3.0</td>\n",
       "      <td>159.0</td>\n",
       "      <td>3413.433759</td>\n",
       "      <td>17.7</td>\n",
       "      <td>2003</td>\n",
       "      <td>Europe</td>\n",
       "      <td>Gasoline</td>\n",
       "      <td>All-wheel drive</td>\n",
       "      <td>0.0</td>\n",
       "      <td>13.231729</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>130</td>\n",
       "      <td>5.0</td>\n",
       "      <td>97.0</td>\n",
       "      <td>3149.664934</td>\n",
       "      <td>17.8</td>\n",
       "      <td>2007</td>\n",
       "      <td>USA</td>\n",
       "      <td>Gasoline</td>\n",
       "      <td>Front-wheel drive</td>\n",
       "      <td>0.0</td>\n",
       "      <td>13.688217</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>170</td>\n",
       "      <td>NaN</td>\n",
       "      <td>78.0</td>\n",
       "      <td>3079.038997</td>\n",
       "      <td>15.1</td>\n",
       "      <td>2018</td>\n",
       "      <td>Europe</td>\n",
       "      <td>Gasoline</td>\n",
       "      <td>Front-wheel drive</td>\n",
       "      <td>0.0</td>\n",
       "      <td>14.246341</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>220</td>\n",
       "      <td>4.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2542.392402</td>\n",
       "      <td>20.2</td>\n",
       "      <td>2009</td>\n",
       "      <td>USA</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>All-wheel drive</td>\n",
       "      <td>2.0</td>\n",
       "      <td>16.912736</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>210</td>\n",
       "      <td>1.0</td>\n",
       "      <td>140.0</td>\n",
       "      <td>3460.870990</td>\n",
       "      <td>14.4</td>\n",
       "      <td>2009</td>\n",
       "      <td>Europe</td>\n",
       "      <td>Gasoline</td>\n",
       "      <td>All-wheel drive</td>\n",
       "      <td>2.0</td>\n",
       "      <td>12.488369</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   engine_displacement  num_cylinders  horsepower  vehicle_weight  \\\n",
       "0                  170            3.0       159.0     3413.433759   \n",
       "1                  130            5.0        97.0     3149.664934   \n",
       "2                  170            NaN        78.0     3079.038997   \n",
       "3                  220            4.0         NaN     2542.392402   \n",
       "4                  210            1.0       140.0     3460.870990   \n",
       "\n",
       "   acceleration  model_year  origin fuel_type         drivetrain  num_doors  \\\n",
       "0          17.7        2003  Europe  Gasoline    All-wheel drive        0.0   \n",
       "1          17.8        2007     USA  Gasoline  Front-wheel drive        0.0   \n",
       "2          15.1        2018  Europe  Gasoline  Front-wheel drive        0.0   \n",
       "3          20.2        2009     USA    Diesel    All-wheel drive        2.0   \n",
       "4          14.4        2009  Europe  Gasoline    All-wheel drive        2.0   \n",
       "\n",
       "   fuel_efficiency_mpg  \n",
       "0            13.231729  \n",
       "1            13.688217  \n",
       "2            14.246341  \n",
       "3            16.912736  \n",
       "4            12.488369  "
      ]
     },
     "execution_count": 56,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2b12116a-060a-48a5-afe9-fdde99e53fce",
   "metadata": {},
   "source": [
    "## 1. No. of Records"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "id": "515593f3-b510-48c2-9067-d9f8ffec3062",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(9704, 11)"
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2a91bf5f-4be4-49b1-bf26-299b71da934a",
   "metadata": {},
   "source": [
    "## 2. Distinct fuel types"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "id": "28148b46-460f-4dc0-895e-9b445b2c5cca",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    Gasoline\n",
       "1    Gasoline\n",
       "2    Gasoline\n",
       "3      Diesel\n",
       "4    Gasoline\n",
       "Name: fuel_type, dtype: object"
      ]
     },
     "execution_count": 58,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fuels = df['fuel_type']\n",
    "fuels.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "id": "a94560b0-3240-45c0-b075-28873370b87f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2"
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fuels.nunique()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "48bb4b87-2a21-408e-866c-8d4bacc57caa",
   "metadata": {},
   "source": [
    "## 3. Null Values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "id": "7f2d85e3-672f-4e09-a48c-1f26a5627c2d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "engine_displacement      0\n",
       "num_cylinders          482\n",
       "horsepower             708\n",
       "vehicle_weight           0\n",
       "acceleration           930\n",
       "model_year               0\n",
       "origin                   0\n",
       "fuel_type                0\n",
       "drivetrain               0\n",
       "num_doors              502\n",
       "fuel_efficiency_mpg      0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 60,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "98f06e86-38d3-4441-bafe-22f9089f6ee2",
   "metadata": {},
   "source": [
    "Clearly, in fuel types there is no missing values"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f052a64b-db12-4342-96d0-3f5ca215cca0",
   "metadata": {},
   "source": [
    "## 4. Max fuel efficiency "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "id": "de01f839-411a-4ed1-bc49-f479174cd8b3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['engine_displacement', 'num_cylinders', 'horsepower', 'vehicle_weight',\n",
       "       'acceleration', 'model_year', 'origin', 'fuel_type', 'drivetrain',\n",
       "       'num_doors', 'fuel_efficiency_mpg'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 61,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "id": "98a48cd5-38df-4736-b873-1d78c1546bde",
   "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>engine_displacement</th>\n",
       "      <th>num_cylinders</th>\n",
       "      <th>horsepower</th>\n",
       "      <th>vehicle_weight</th>\n",
       "      <th>acceleration</th>\n",
       "      <th>model_year</th>\n",
       "      <th>origin</th>\n",
       "      <th>fuel_type</th>\n",
       "      <th>drivetrain</th>\n",
       "      <th>num_doors</th>\n",
       "      <th>fuel_efficiency_mpg</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>170</td>\n",
       "      <td>3.0</td>\n",
       "      <td>159.0</td>\n",
       "      <td>3413.433759</td>\n",
       "      <td>17.7</td>\n",
       "      <td>2003</td>\n",
       "      <td>Europe</td>\n",
       "      <td>Gasoline</td>\n",
       "      <td>All-wheel drive</td>\n",
       "      <td>0.0</td>\n",
       "      <td>13.231729</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>130</td>\n",
       "      <td>5.0</td>\n",
       "      <td>97.0</td>\n",
       "      <td>3149.664934</td>\n",
       "      <td>17.8</td>\n",
       "      <td>2007</td>\n",
       "      <td>USA</td>\n",
       "      <td>Gasoline</td>\n",
       "      <td>Front-wheel drive</td>\n",
       "      <td>0.0</td>\n",
       "      <td>13.688217</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>170</td>\n",
       "      <td>NaN</td>\n",
       "      <td>78.0</td>\n",
       "      <td>3079.038997</td>\n",
       "      <td>15.1</td>\n",
       "      <td>2018</td>\n",
       "      <td>Europe</td>\n",
       "      <td>Gasoline</td>\n",
       "      <td>Front-wheel drive</td>\n",
       "      <td>0.0</td>\n",
       "      <td>14.246341</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>220</td>\n",
       "      <td>4.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2542.392402</td>\n",
       "      <td>20.2</td>\n",
       "      <td>2009</td>\n",
       "      <td>USA</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>All-wheel drive</td>\n",
       "      <td>2.0</td>\n",
       "      <td>16.912736</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>210</td>\n",
       "      <td>1.0</td>\n",
       "      <td>140.0</td>\n",
       "      <td>3460.870990</td>\n",
       "      <td>14.4</td>\n",
       "      <td>2009</td>\n",
       "      <td>Europe</td>\n",
       "      <td>Gasoline</td>\n",
       "      <td>All-wheel drive</td>\n",
       "      <td>2.0</td>\n",
       "      <td>12.488369</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   engine_displacement  num_cylinders  horsepower  vehicle_weight  \\\n",
       "0                  170            3.0       159.0     3413.433759   \n",
       "1                  130            5.0        97.0     3149.664934   \n",
       "2                  170            NaN        78.0     3079.038997   \n",
       "3                  220            4.0         NaN     2542.392402   \n",
       "4                  210            1.0       140.0     3460.870990   \n",
       "\n",
       "   acceleration  model_year  origin fuel_type         drivetrain  num_doors  \\\n",
       "0          17.7        2003  Europe  Gasoline    All-wheel drive        0.0   \n",
       "1          17.8        2007     USA  Gasoline  Front-wheel drive        0.0   \n",
       "2          15.1        2018  Europe  Gasoline  Front-wheel drive        0.0   \n",
       "3          20.2        2009     USA    Diesel    All-wheel drive        2.0   \n",
       "4          14.4        2009  Europe  Gasoline    All-wheel drive        2.0   \n",
       "\n",
       "   fuel_efficiency_mpg  \n",
       "0            13.231729  \n",
       "1            13.688217  \n",
       "2            14.246341  \n",
       "3            16.912736  \n",
       "4            12.488369  "
      ]
     },
     "execution_count": 62,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "id": "25faf234-3f06-4f9b-bd07-0f25de03ee1c",
   "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>engine_displacement</th>\n",
       "      <th>num_cylinders</th>\n",
       "      <th>horsepower</th>\n",
       "      <th>vehicle_weight</th>\n",
       "      <th>acceleration</th>\n",
       "      <th>model_year</th>\n",
       "      <th>origin</th>\n",
       "      <th>fuel_type</th>\n",
       "      <th>drivetrain</th>\n",
       "      <th>num_doors</th>\n",
       "      <th>fuel_efficiency_mpg</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>250</td>\n",
       "      <td>1.0</td>\n",
       "      <td>174.0</td>\n",
       "      <td>2714.219310</td>\n",
       "      <td>10.3</td>\n",
       "      <td>2016</td>\n",
       "      <td>Asia</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>Front-wheel drive</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>16.823554</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>320</td>\n",
       "      <td>5.0</td>\n",
       "      <td>145.0</td>\n",
       "      <td>2783.868974</td>\n",
       "      <td>15.1</td>\n",
       "      <td>2010</td>\n",
       "      <td>Asia</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>All-wheel drive</td>\n",
       "      <td>1.0</td>\n",
       "      <td>16.175820</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>200</td>\n",
       "      <td>6.0</td>\n",
       "      <td>160.0</td>\n",
       "      <td>3582.687368</td>\n",
       "      <td>14.9</td>\n",
       "      <td>2007</td>\n",
       "      <td>Asia</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>All-wheel drive</td>\n",
       "      <td>0.0</td>\n",
       "      <td>11.871091</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>150</td>\n",
       "      <td>3.0</td>\n",
       "      <td>197.0</td>\n",
       "      <td>2231.808142</td>\n",
       "      <td>18.7</td>\n",
       "      <td>2011</td>\n",
       "      <td>Asia</td>\n",
       "      <td>Gasoline</td>\n",
       "      <td>Front-wheel drive</td>\n",
       "      <td>1.0</td>\n",
       "      <td>18.889083</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>160</td>\n",
       "      <td>4.0</td>\n",
       "      <td>133.0</td>\n",
       "      <td>2659.431451</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2016</td>\n",
       "      <td>Asia</td>\n",
       "      <td>Gasoline</td>\n",
       "      <td>Front-wheel drive</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>16.077730</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    engine_displacement  num_cylinders  horsepower  vehicle_weight  \\\n",
       "8                   250            1.0       174.0     2714.219310   \n",
       "12                  320            5.0       145.0     2783.868974   \n",
       "14                  200            6.0       160.0     3582.687368   \n",
       "20                  150            3.0       197.0     2231.808142   \n",
       "21                  160            4.0       133.0     2659.431451   \n",
       "\n",
       "    acceleration  model_year origin fuel_type         drivetrain  num_doors  \\\n",
       "8           10.3        2016   Asia    Diesel  Front-wheel drive       -1.0   \n",
       "12          15.1        2010   Asia    Diesel    All-wheel drive        1.0   \n",
       "14          14.9        2007   Asia    Diesel    All-wheel drive        0.0   \n",
       "20          18.7        2011   Asia  Gasoline  Front-wheel drive        1.0   \n",
       "21           NaN        2016   Asia  Gasoline  Front-wheel drive       -1.0   \n",
       "\n",
       "    fuel_efficiency_mpg  \n",
       "8             16.823554  \n",
       "12            16.175820  \n",
       "14            11.871091  \n",
       "20            18.889083  \n",
       "21            16.077730  "
      ]
     },
     "execution_count": 63,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mask_asia = df['origin'] == 'Asia'\n",
    "eff = df[mask_asia]\n",
    "eff.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "id": "5d1f7efd-77f9-4568-a012-5cd1ba753fd6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "23.759122836520497"
      ]
     },
     "execution_count": 64,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "max_eff = max(eff['fuel_efficiency_mpg'])\n",
    "max_eff"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cda34c7c-f2c0-497d-b419-dae670db022b",
   "metadata": {},
   "source": [
    "## 5. Median value of horsepower"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "id": "e8328da7-f04f-41bd-94f5-b534aa00f2c1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "engine_displacement      0\n",
       "num_cylinders          482\n",
       "horsepower             708\n",
       "vehicle_weight           0\n",
       "acceleration           930\n",
       "model_year               0\n",
       "origin                   0\n",
       "fuel_type                0\n",
       "drivetrain               0\n",
       "num_doors              502\n",
       "fuel_efficiency_mpg      0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 65,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "id": "6eaafaf8-6674-443d-b26c-6d8212d91754",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "149.0"
      ]
     },
     "execution_count": 66,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# median of the horsepower col\n",
    "df['horsepower'].median()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "id": "9b785320-6b9a-41c0-bb27-c0f126145177",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "horsepower\n",
       "152.0    142\n",
       "145.0    141\n",
       "151.0    134\n",
       "148.0    130\n",
       "141.0    130\n",
       "        ... \n",
       "40.0       1\n",
       "57.0       1\n",
       "245.0      1\n",
       "252.0      1\n",
       "61.0       1\n",
       "Name: count, Length: 192, dtype: int64"
      ]
     },
     "execution_count": 67,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# most frequent value here\n",
    "df['horsepower'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "id": "126b6df6-515f-463e-83f3-10abbf2c25e2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "np.float64(152.0)"
      ]
     },
     "execution_count": 74,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# alternatively mode gives the max freq count\n",
    "mode_horsepower = df['horsepower'].mode()[0]\n",
    "mode_horsepower"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "id": "bd17e63f-c5c1-4d8a-8ba5-1b8e106175fc",
   "metadata": {},
   "outputs": [],
   "source": [
    "# fill the missing values in the col with mode\n",
    "df['horsepower'].fillna(mode_horsepower, inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "id": "e7dc6b1a-323a-4f88-b475-f76059759e66",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "engine_displacement      0\n",
       "num_cylinders          482\n",
       "horsepower               0\n",
       "vehicle_weight           0\n",
       "acceleration           930\n",
       "model_year               0\n",
       "origin                   0\n",
       "fuel_type                0\n",
       "drivetrain               0\n",
       "num_doors              502\n",
       "fuel_efficiency_mpg      0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 81,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# check if null values are removed or not\n",
    "df.isnull().sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3eaf5439-3f99-4506-bdd8-ca35e03c18bf",
   "metadata": {},
   "source": [
    "Clearly the null values have been imputed"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "id": "94dc61c5-bbcb-47f4-9370-f3238c26e2a2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "152.0"
      ]
     },
     "execution_count": 82,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# now recalculate the median\n",
    "df['horsepower'].median()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "32337e0a-dbfc-4e96-9fab-15723b3a5166",
   "metadata": {},
   "source": [
    "## 6. Model building"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "id": "a28d7bfb-3f4d-4018-8881-b39bf43d4089",
   "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>engine_displacement</th>\n",
       "      <th>num_cylinders</th>\n",
       "      <th>horsepower</th>\n",
       "      <th>vehicle_weight</th>\n",
       "      <th>acceleration</th>\n",
       "      <th>model_year</th>\n",
       "      <th>origin</th>\n",
       "      <th>fuel_type</th>\n",
       "      <th>drivetrain</th>\n",
       "      <th>num_doors</th>\n",
       "      <th>fuel_efficiency_mpg</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>170</td>\n",
       "      <td>3.0</td>\n",
       "      <td>159.0</td>\n",
       "      <td>3413.433759</td>\n",
       "      <td>17.7</td>\n",
       "      <td>2003</td>\n",
       "      <td>Europe</td>\n",
       "      <td>Gasoline</td>\n",
       "      <td>All-wheel drive</td>\n",
       "      <td>0.0</td>\n",
       "      <td>13.231729</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>130</td>\n",
       "      <td>5.0</td>\n",
       "      <td>97.0</td>\n",
       "      <td>3149.664934</td>\n",
       "      <td>17.8</td>\n",
       "      <td>2007</td>\n",
       "      <td>USA</td>\n",
       "      <td>Gasoline</td>\n",
       "      <td>Front-wheel drive</td>\n",
       "      <td>0.0</td>\n",
       "      <td>13.688217</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>170</td>\n",
       "      <td>NaN</td>\n",
       "      <td>78.0</td>\n",
       "      <td>3079.038997</td>\n",
       "      <td>15.1</td>\n",
       "      <td>2018</td>\n",
       "      <td>Europe</td>\n",
       "      <td>Gasoline</td>\n",
       "      <td>Front-wheel drive</td>\n",
       "      <td>0.0</td>\n",
       "      <td>14.246341</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>220</td>\n",
       "      <td>4.0</td>\n",
       "      <td>152.0</td>\n",
       "      <td>2542.392402</td>\n",
       "      <td>20.2</td>\n",
       "      <td>2009</td>\n",
       "      <td>USA</td>\n",
       "      <td>Diesel</td>\n",
       "      <td>All-wheel drive</td>\n",
       "      <td>2.0</td>\n",
       "      <td>16.912736</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>210</td>\n",
       "      <td>1.0</td>\n",
       "      <td>140.0</td>\n",
       "      <td>3460.870990</td>\n",
       "      <td>14.4</td>\n",
       "      <td>2009</td>\n",
       "      <td>Europe</td>\n",
       "      <td>Gasoline</td>\n",
       "      <td>All-wheel drive</td>\n",
       "      <td>2.0</td>\n",
       "      <td>12.488369</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   engine_displacement  num_cylinders  horsepower  vehicle_weight  \\\n",
       "0                  170            3.0       159.0     3413.433759   \n",
       "1                  130            5.0        97.0     3149.664934   \n",
       "2                  170            NaN        78.0     3079.038997   \n",
       "3                  220            4.0       152.0     2542.392402   \n",
       "4                  210            1.0       140.0     3460.870990   \n",
       "\n",
       "   acceleration  model_year  origin fuel_type         drivetrain  num_doors  \\\n",
       "0          17.7        2003  Europe  Gasoline    All-wheel drive        0.0   \n",
       "1          17.8        2007     USA  Gasoline  Front-wheel drive        0.0   \n",
       "2          15.1        2018  Europe  Gasoline  Front-wheel drive        0.0   \n",
       "3          20.2        2009     USA    Diesel    All-wheel drive        2.0   \n",
       "4          14.4        2009  Europe  Gasoline    All-wheel drive        2.0   \n",
       "\n",
       "   fuel_efficiency_mpg  \n",
       "0            13.231729  \n",
       "1            13.688217  \n",
       "2            14.246341  \n",
       "3            16.912736  \n",
       "4            12.488369  "
      ]
     },
     "execution_count": 84,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "id": "30057fab-fad4-44ae-9b9b-2aae11614f84",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    False\n",
       "1    False\n",
       "2    False\n",
       "3    False\n",
       "4    False\n",
       "Name: origin, dtype: bool"
      ]
     },
     "execution_count": 83,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mask_asia.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "id": "dbaa1132-9a2f-411a-9668-b5110109e3aa",
   "metadata": {},
   "outputs": [],
   "source": [
    "columns_to_keep = ['vehicle_weight', 'model_year']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "id": "c37eb7f0-4e38-4a8d-b5a0-f54ba43ef6c7",
   "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>vehicle_weight</th>\n",
       "      <th>model_year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>2714.219310</td>\n",
       "      <td>2016</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>2783.868974</td>\n",
       "      <td>2010</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>3582.687368</td>\n",
       "      <td>2007</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>2231.808142</td>\n",
       "      <td>2011</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>2659.431451</td>\n",
       "      <td>2016</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>34</th>\n",
       "      <td>2844.227534</td>\n",
       "      <td>2014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>38</th>\n",
       "      <td>3761.994038</td>\n",
       "      <td>2019</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    vehicle_weight  model_year\n",
       "8      2714.219310        2016\n",
       "12     2783.868974        2010\n",
       "14     3582.687368        2007\n",
       "20     2231.808142        2011\n",
       "21     2659.431451        2016\n",
       "34     2844.227534        2014\n",
       "38     3761.994038        2019"
      ]
     },
     "execution_count": 94,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# subset the asian data\n",
    "df_asia = df[mask_asia]\n",
    "df_asia_final = df_asia[columns_to_keep].head(7)\n",
    "df_asia_final"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "id": "89abd22c-7cc2-49b9-8afd-4e824f4360c7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(7, 2)"
      ]
     },
     "execution_count": 100,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# get the underlying numpy array\n",
    "X = np.array(df_asia_final)\n",
    "X.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 110,
   "id": "252a6e2f-c7f9-4c30-b74a-8b4e1ea876ab",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(2, 2)"
      ]
     },
     "execution_count": 110,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# take the dot product with the traspose (7,2).(2,7) -> (7,7)\n",
    "XTX = X.T @ X\n",
    "XTX.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 111,
   "id": "63342692-a307-48cd-a6cf-bdfc8e1985c1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(2, 2)"
      ]
     },
     "execution_count": 111,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "XTX_inv = np.linalg.inv(XTX)\n",
    "XTX_inv.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 112,
   "id": "e4b0a33e-ee66-48d3-82d4-7953e0a64461",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1100, 1300,  800,  900, 1000, 1100, 1200])"
      ]
     },
     "execution_count": 112,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Create an array y with values \n",
    "y = np.array([1100, 1300, 800, 900, 1000, 1100, 1200])\n",
    "y "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 114,
   "id": "e5b0bf7e-9e5d-46c8-9d47-4555f05bfc6f",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Multiply the inverse of XTX with the transpose of X, and then multiply the result by y. Call the result w\n",
    "step = XTX_inv @ X.T\n",
    "w = step @ y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 115,
   "id": "1ddb3d1f-b877-4c66-9245-098cd63b850a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "np.float64(0.5187709081074016)"
      ]
     },
     "execution_count": 115,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# sum of all the elements of the result / weights\n",
    "np.sum(w)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5cad1468-2329-4fa3-9b91-0dc30dffafbc",
   "metadata": {},
   "source": [
    "## End of Week 1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2bbec182-f585-43fa-9960-ca979139c0e2",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}