simple_imputation_cars.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Practicing imputation with cars dataset "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Importing the classics\n",
    "import pandas as pd \n",
    "import numpy as np \n",
    "\n",
    "#Importing sklearn tools\n",
    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
    "from sklearn.model_selection import KFold\n",
    "from sklearn.model_selection import cross_val_score\n",
    "\n",
    "from sklearn.impute import SimpleImputer, MissingIndicator"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1000, 3)"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv('Mock_CAR_GENDER_MAKE_PRICE.csv', header = 0, index_col = 0)\n",
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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>gender</th>\n",
       "      <th>carmake</th>\n",
       "      <th>price</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>id</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Male</td>\n",
       "      <td>Honda</td>\n",
       "      <td>16907.46</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Female</td>\n",
       "      <td>Chevrolet</td>\n",
       "      <td>25298.09</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Female</td>\n",
       "      <td>Mazda</td>\n",
       "      <td>21812.35</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Male</td>\n",
       "      <td>Honda</td>\n",
       "      <td>22583.60</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Female</td>\n",
       "      <td>Aston Martin</td>\n",
       "      <td>28987.44</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Male</td>\n",
       "      <td>Mercury</td>\n",
       "      <td>24213.82</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Male</td>\n",
       "      <td>Chevrolet</td>\n",
       "      <td>29778.91</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Female</td>\n",
       "      <td>Chevrolet</td>\n",
       "      <td>28993.37</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>Female</td>\n",
       "      <td>Nissan</td>\n",
       "      <td>21563.51</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>Male</td>\n",
       "      <td>Mercury</td>\n",
       "      <td>23162.97</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>Male</td>\n",
       "      <td>Honda</td>\n",
       "      <td>24967.98</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>Female</td>\n",
       "      <td>Infiniti</td>\n",
       "      <td>12506.23</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>Female</td>\n",
       "      <td>Lexus</td>\n",
       "      <td>14185.59</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>Male</td>\n",
       "      <td>Hyundai</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>Male</td>\n",
       "      <td>Chevrolet</td>\n",
       "      <td>22116.19</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    gender       carmake     price\n",
       "id                                \n",
       "1     Male         Honda  16907.46\n",
       "2   Female     Chevrolet  25298.09\n",
       "3   Female         Mazda  21812.35\n",
       "4     Male         Honda  22583.60\n",
       "5   Female  Aston Martin  28987.44\n",
       "6     Male       Mercury  24213.82\n",
       "7     Male     Chevrolet  29778.91\n",
       "8   Female     Chevrolet  28993.37\n",
       "9   Female        Nissan  21563.51\n",
       "10    Male       Mercury  23162.97\n",
       "11    Male         Honda  24967.98\n",
       "12  Female      Infiniti  12506.23\n",
       "13  Female         Lexus  14185.59\n",
       "14    Male       Hyundai       NaN\n",
       "15    Male     Chevrolet  22116.19"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head(15)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Lets replace the ID with zero index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.reset_index(drop = True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>gender</th>\n",
       "      <th>carmake</th>\n",
       "      <th>price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Male</td>\n",
       "      <td>Honda</td>\n",
       "      <td>16907.46</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Female</td>\n",
       "      <td>Chevrolet</td>\n",
       "      <td>25298.09</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Female</td>\n",
       "      <td>Mazda</td>\n",
       "      <td>21812.35</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Male</td>\n",
       "      <td>Honda</td>\n",
       "      <td>22583.60</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Female</td>\n",
       "      <td>Aston Martin</td>\n",
       "      <td>28987.44</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   gender       carmake     price\n",
       "0    Male         Honda  16907.46\n",
       "1  Female     Chevrolet  25298.09\n",
       "2  Female         Mazda  21812.35\n",
       "3    Male         Honda  22583.60\n",
       "4  Female  Aston Martin  28987.44"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Replacing the carmake labels to omit spaces and all lower case e.g. 'Aston Martin' -> 'astonmartin'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.carmake = df.carmake.replace('\\s+', '',regex=True)\n",
    "df.carmake = df.carmake.str.lower()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Replacing gender column to be female true column"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>gender</th>\n",
       "      <th>carmake</th>\n",
       "      <th>price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.0</td>\n",
       "      <td>honda</td>\n",
       "      <td>16907.46</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1.0</td>\n",
       "      <td>chevrolet</td>\n",
       "      <td>25298.09</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.0</td>\n",
       "      <td>mazda</td>\n",
       "      <td>21812.35</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.0</td>\n",
       "      <td>honda</td>\n",
       "      <td>22583.60</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1.0</td>\n",
       "      <td>astonmartin</td>\n",
       "      <td>28987.44</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0.0</td>\n",
       "      <td>mercury</td>\n",
       "      <td>24213.82</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0.0</td>\n",
       "      <td>chevrolet</td>\n",
       "      <td>29778.91</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>1.0</td>\n",
       "      <td>chevrolet</td>\n",
       "      <td>28993.37</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>1.0</td>\n",
       "      <td>nissan</td>\n",
       "      <td>21563.51</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>0.0</td>\n",
       "      <td>mercury</td>\n",
       "      <td>23162.97</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>0.0</td>\n",
       "      <td>honda</td>\n",
       "      <td>24967.98</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>1.0</td>\n",
       "      <td>infiniti</td>\n",
       "      <td>12506.23</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>1.0</td>\n",
       "      <td>lexus</td>\n",
       "      <td>14185.59</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>0.0</td>\n",
       "      <td>hyundai</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>0.0</td>\n",
       "      <td>chevrolet</td>\n",
       "      <td>22116.19</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    gender      carmake     price\n",
       "0      0.0        honda  16907.46\n",
       "1      1.0    chevrolet  25298.09\n",
       "2      1.0        mazda  21812.35\n",
       "3      0.0        honda  22583.60\n",
       "4      1.0  astonmartin  28987.44\n",
       "5      0.0      mercury  24213.82\n",
       "6      0.0    chevrolet  29778.91\n",
       "7      1.0    chevrolet  28993.37\n",
       "8      1.0       nissan  21563.51\n",
       "9      0.0      mercury  23162.97\n",
       "10     0.0        honda  24967.98\n",
       "11     1.0     infiniti  12506.23\n",
       "12     1.0        lexus  14185.59\n",
       "13     0.0      hyundai       NaN\n",
       "14     0.0    chevrolet  22116.19"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Relabel sex\n",
    "df[['gender']] = df[['gender']].replace({'Female':1.,  'Male':0.})\n",
    "df.head(15)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>gender</th>\n",
       "      <th>price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>1000.000000</td>\n",
       "      <td>801.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>0.481000</td>\n",
       "      <td>20027.687478</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>0.499889</td>\n",
       "      <td>5689.499086</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>10031.760000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>15360.720000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>20161.840000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>24977.690000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>29917.250000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            gender         price\n",
       "count  1000.000000    801.000000\n",
       "mean      0.481000  20027.687478\n",
       "std       0.499889   5689.499086\n",
       "min       0.000000  10031.760000\n",
       "25%       0.000000  15360.720000\n",
       "50%       0.000000  20161.840000\n",
       "75%       1.000000  24977.690000\n",
       "max       1.000000  29917.250000"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Removing all nan values "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "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>gender</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>199.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>0.517588</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>0.500951</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           gender\n",
       "count  199.000000\n",
       "mean     0.517588\n",
       "std      0.500951\n",
       "min      0.000000\n",
       "25%      0.000000\n",
       "50%      1.000000\n",
       "75%      1.000000\n",
       "max      1.000000"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1 = df.dropna(inplace=False)\n",
    "df_inter = df.fillna(0)\n",
    "df_nan = df_inter[df_inter['price'] == 0]\n",
    "\n",
    "df_nan = df_nan.drop('price', axis = 1)\n",
    "df_nan = df_nan.reset_index(drop = True)\n",
    "df_nan.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sum(df1['carmake'].str.contains('smart'))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Notice that the training data will not contain any smart cars... "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>gender</th>\n",
       "      <th>carmake</th>\n",
       "      <th>price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.0</td>\n",
       "      <td>honda</td>\n",
       "      <td>16907.46</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1.0</td>\n",
       "      <td>chevrolet</td>\n",
       "      <td>25298.09</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.0</td>\n",
       "      <td>mazda</td>\n",
       "      <td>21812.35</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.0</td>\n",
       "      <td>honda</td>\n",
       "      <td>22583.60</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1.0</td>\n",
       "      <td>astonmartin</td>\n",
       "      <td>28987.44</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   gender      carmake     price\n",
       "0     0.0        honda  16907.46\n",
       "1     1.0    chevrolet  25298.09\n",
       "2     1.0        mazda  21812.35\n",
       "3     0.0        honda  22583.60\n",
       "4     1.0  astonmartin  28987.44"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "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>gender</th>\n",
       "      <th>carmake</th>\n",
       "      <th>price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>993</th>\n",
       "      <td>0.0</td>\n",
       "      <td>audi</td>\n",
       "      <td>29742.98</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>994</th>\n",
       "      <td>1.0</td>\n",
       "      <td>oldsmobile</td>\n",
       "      <td>19087.81</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>995</th>\n",
       "      <td>0.0</td>\n",
       "      <td>chevrolet</td>\n",
       "      <td>14743.35</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>996</th>\n",
       "      <td>1.0</td>\n",
       "      <td>ford</td>\n",
       "      <td>13630.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>998</th>\n",
       "      <td>0.0</td>\n",
       "      <td>lotus</td>\n",
       "      <td>15388.68</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     gender     carmake     price\n",
       "993     0.0        audi  29742.98\n",
       "994     1.0  oldsmobile  19087.81\n",
       "995     0.0   chevrolet  14743.35\n",
       "996     1.0        ford  13630.00\n",
       "998     0.0       lotus  15388.68"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>gender</th>\n",
       "      <th>carmake</th>\n",
       "      <th>price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>801.000000</td>\n",
       "      <td>801</td>\n",
       "      <td>801.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>unique</th>\n",
       "      <td>NaN</td>\n",
       "      <td>54</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>top</th>\n",
       "      <td>NaN</td>\n",
       "      <td>ford</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>freq</th>\n",
       "      <td>NaN</td>\n",
       "      <td>78</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>0.471910</td>\n",
       "      <td>NaN</td>\n",
       "      <td>20027.687478</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>0.499522</td>\n",
       "      <td>NaN</td>\n",
       "      <td>5689.499086</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>10031.760000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>15360.720000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>20161.840000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>24977.690000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>29917.250000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            gender carmake         price\n",
       "count   801.000000     801    801.000000\n",
       "unique         NaN      54           NaN\n",
       "top            NaN    ford           NaN\n",
       "freq           NaN      78           NaN\n",
       "mean      0.471910     NaN  20027.687478\n",
       "std       0.499522     NaN   5689.499086\n",
       "min       0.000000     NaN  10031.760000\n",
       "25%       0.000000     NaN  15360.720000\n",
       "50%       0.000000     NaN  20161.840000\n",
       "75%       1.000000     NaN  24977.690000\n",
       "max       1.000000     NaN  29917.250000"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1.describe(include = 'all')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Very simple imputation method: Replace missing values with mean of entire comumn "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We ignore the gategorical data here, just replacing every missing value with the overall mean, we dont distingush between car type or gender. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create an imputer that fills missing values with mean column values - could just as well have chosen, median, mode, or just some hand selected value such as 0. using replace(np.nan, 0)\n",
    "imputer = SimpleImputer(strategy='mean')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "# split dataset into inputs and outputs\n",
    "df_values = df.values\n",
    "X = df_values[:,0:2]\n",
    "y = df_values[:,2]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1000,)"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1000, 1)"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_reshape = y.reshape(-1, 1)\n",
    "y_reshape.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "transformed_y = imputer.fit_transform(y_reshape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "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>female</th>\n",
       "      <th>make</th>\n",
       "      <th>price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>honda</td>\n",
       "      <td>16907.460000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>chevrolet</td>\n",
       "      <td>25298.090000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>mazda</td>\n",
       "      <td>21812.350000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>honda</td>\n",
       "      <td>22583.600000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>astonmartin</td>\n",
       "      <td>28987.440000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0</td>\n",
       "      <td>mercury</td>\n",
       "      <td>24213.820000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0</td>\n",
       "      <td>chevrolet</td>\n",
       "      <td>29778.910000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>1</td>\n",
       "      <td>chevrolet</td>\n",
       "      <td>28993.370000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>1</td>\n",
       "      <td>nissan</td>\n",
       "      <td>21563.510000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>0</td>\n",
       "      <td>mercury</td>\n",
       "      <td>23162.970000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>0</td>\n",
       "      <td>honda</td>\n",
       "      <td>24967.980000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>1</td>\n",
       "      <td>infiniti</td>\n",
       "      <td>12506.230000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>1</td>\n",
       "      <td>lexus</td>\n",
       "      <td>14185.590000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>0</td>\n",
       "      <td>hyundai</td>\n",
       "      <td>20027.687478</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>0</td>\n",
       "      <td>chevrolet</td>\n",
       "      <td>22116.190000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   female         make         price\n",
       "0       0        honda  16907.460000\n",
       "1       1    chevrolet  25298.090000\n",
       "2       1        mazda  21812.350000\n",
       "3       0        honda  22583.600000\n",
       "4       1  astonmartin  28987.440000\n",
       "5       0      mercury  24213.820000\n",
       "6       0    chevrolet  29778.910000\n",
       "7       1    chevrolet  28993.370000\n",
       "8       1       nissan  21563.510000\n",
       "9       0      mercury  23162.970000\n",
       "10      0        honda  24967.980000\n",
       "11      1     infiniti  12506.230000\n",
       "12      1        lexus  14185.590000\n",
       "13      0      hyundai  20027.687478\n",
       "14      0    chevrolet  22116.190000"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df2part1 = pd.DataFrame(X, columns = ['female', 'make'])\n",
    "df2part2 = pd.DataFrame(transformed_y, columns = ['price'])\n",
    "df2 = df2part1.join(df2part2)\n",
    "df2.head(15)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "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>female</th>\n",
       "      <th>make</th>\n",
       "      <th>price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>1000.0</td>\n",
       "      <td>1000</td>\n",
       "      <td>1000.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>unique</th>\n",
       "      <td>2.0</td>\n",
       "      <td>55</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>top</th>\n",
       "      <td>0.0</td>\n",
       "      <td>ford</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>freq</th>\n",
       "      <td>519.0</td>\n",
       "      <td>100</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>20027.687478</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>5091.389017</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>10031.760000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>16359.345000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>20027.687478</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>23689.645000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>29917.250000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        female  make         price\n",
       "count   1000.0  1000   1000.000000\n",
       "unique     2.0    55           NaN\n",
       "top        0.0  ford           NaN\n",
       "freq     519.0   100           NaN\n",
       "mean       NaN   NaN  20027.687478\n",
       "std        NaN   NaN   5091.389017\n",
       "min        NaN   NaN  10031.760000\n",
       "25%        NaN   NaN  16359.345000\n",
       "50%        NaN   NaN  20027.687478\n",
       "75%        NaN   NaN  23689.645000\n",
       "max        NaN   NaN  29917.250000"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df2.describe(include = 'all')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Less simple imputation method: replacing price values based on the categorical data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Idea: lets sepearate the dataframe. One dataframe with no missing values and the other will contain all the missing values. \n",
    "\n",
    "We have already created the first one: df1. lets rename it: df_train. \n",
    "This would not be the best method if multiple columns had missing values, nor if we did not have sufficient number of rows without missing columns. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Adding dummy variables to our categorical data i.e. carmake. We use TF-IDF."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "#carmake \n",
    "tfidf = TfidfVectorizer()\n",
    "make_values = tfidf.fit_transform(df.carmake).toarray()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "col_names = tfidf.get_feature_names()\n",
    "make_values_total_df = pd.DataFrame(data = make_values, columns = col_names) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "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>acura</th>\n",
       "      <th>astonmartin</th>\n",
       "      <th>audi</th>\n",
       "      <th>bentley</th>\n",
       "      <th>benz</th>\n",
       "      <th>bmw</th>\n",
       "      <th>buick</th>\n",
       "      <th>cadillac</th>\n",
       "      <th>chevrolet</th>\n",
       "      <th>chrysler</th>\n",
       "      <th>...</th>\n",
       "      <th>saab</th>\n",
       "      <th>saturn</th>\n",
       "      <th>scion</th>\n",
       "      <th>smart</th>\n",
       "      <th>subaru</th>\n",
       "      <th>suzuki</th>\n",
       "      <th>tesla</th>\n",
       "      <th>toyota</th>\n",
       "      <th>volkswagen</th>\n",
       "      <th>volvo</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 57 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   acura  astonmartin  audi  bentley  benz  bmw  buick  cadillac  chevrolet  \\\n",
       "0    0.0          0.0   0.0      0.0   0.0  0.0    0.0       0.0        0.0   \n",
       "1    0.0          0.0   0.0      0.0   0.0  0.0    0.0       0.0        1.0   \n",
       "2    0.0          0.0   0.0      0.0   0.0  0.0    0.0       0.0        0.0   \n",
       "3    0.0          0.0   0.0      0.0   0.0  0.0    0.0       0.0        0.0   \n",
       "4    0.0          1.0   0.0      0.0   0.0  0.0    0.0       0.0        0.0   \n",
       "\n",
       "   chrysler  ...    saab  saturn  scion  smart  subaru  suzuki  tesla  toyota  \\\n",
       "0       0.0  ...     0.0     0.0    0.0    0.0     0.0     0.0    0.0     0.0   \n",
       "1       0.0  ...     0.0     0.0    0.0    0.0     0.0     0.0    0.0     0.0   \n",
       "2       0.0  ...     0.0     0.0    0.0    0.0     0.0     0.0    0.0     0.0   \n",
       "3       0.0  ...     0.0     0.0    0.0    0.0     0.0     0.0    0.0     0.0   \n",
       "4       0.0  ...     0.0     0.0    0.0    0.0     0.0     0.0    0.0     0.0   \n",
       "\n",
       "   volkswagen  volvo  \n",
       "0         0.0    0.0  \n",
       "1         0.0    0.0  \n",
       "2         0.0    0.0  \n",
       "3         0.0    0.0  \n",
       "4         0.0    0.0  \n",
       "\n",
       "[5 rows x 57 columns]"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "make_values_total_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "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>gender</th>\n",
       "      <th>acura</th>\n",
       "      <th>astonmartin</th>\n",
       "      <th>audi</th>\n",
       "      <th>bentley</th>\n",
       "      <th>benz</th>\n",
       "      <th>bmw</th>\n",
       "      <th>buick</th>\n",
       "      <th>cadillac</th>\n",
       "      <th>chevrolet</th>\n",
       "      <th>...</th>\n",
       "      <th>saturn</th>\n",
       "      <th>scion</th>\n",
       "      <th>smart</th>\n",
       "      <th>subaru</th>\n",
       "      <th>suzuki</th>\n",
       "      <th>tesla</th>\n",
       "      <th>toyota</th>\n",
       "      <th>volkswagen</th>\n",
       "      <th>volvo</th>\n",
       "      <th>price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>16907.46</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>25298.09</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>21812.35</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>22583.60</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>28987.44</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 59 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   gender  acura  astonmartin  audi  bentley  benz  bmw  buick  cadillac  \\\n",
       "0     0.0    0.0          0.0   0.0      0.0   0.0  0.0    0.0       0.0   \n",
       "1     1.0    0.0          0.0   0.0      0.0   0.0  0.0    0.0       0.0   \n",
       "2     1.0    0.0          0.0   0.0      0.0   0.0  0.0    0.0       0.0   \n",
       "3     0.0    0.0          0.0   0.0      0.0   0.0  0.0    0.0       0.0   \n",
       "4     1.0    0.0          1.0   0.0      0.0   0.0  0.0    0.0       0.0   \n",
       "\n",
       "   chevrolet    ...     saturn  scion  smart  subaru  suzuki  tesla  toyota  \\\n",
       "0        0.0    ...        0.0    0.0    0.0     0.0     0.0    0.0     0.0   \n",
       "1        1.0    ...        0.0    0.0    0.0     0.0     0.0    0.0     0.0   \n",
       "2        0.0    ...        0.0    0.0    0.0     0.0     0.0    0.0     0.0   \n",
       "3        0.0    ...        0.0    0.0    0.0     0.0     0.0    0.0     0.0   \n",
       "4        0.0    ...        0.0    0.0    0.0     0.0     0.0    0.0     0.0   \n",
       "\n",
       "   volkswagen  volvo     price  \n",
       "0         0.0    0.0  16907.46  \n",
       "1         0.0    0.0  25298.09  \n",
       "2         0.0    0.0  21812.35  \n",
       "3         0.0    0.0  22583.60  \n",
       "4         0.0    0.0  28987.44  \n",
       "\n",
       "[5 rows x 59 columns]"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_tfidf = df.join(make_values_total_df)\n",
    "df_tfidf = df_tfidf.drop('carmake', axis = 1)\n",
    "df_tfidf = df_tfidf[[c for c in df_tfidf if c not in ['price']] + ['price']]\n",
    "df_tfidf.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Creating the training dataset "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "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>gender</th>\n",
       "      <th>acura</th>\n",
       "      <th>astonmartin</th>\n",
       "      <th>audi</th>\n",
       "      <th>bentley</th>\n",
       "      <th>benz</th>\n",
       "      <th>bmw</th>\n",
       "      <th>buick</th>\n",
       "      <th>cadillac</th>\n",
       "      <th>chevrolet</th>\n",
       "      <th>...</th>\n",
       "      <th>saturn</th>\n",
       "      <th>scion</th>\n",
       "      <th>smart</th>\n",
       "      <th>subaru</th>\n",
       "      <th>suzuki</th>\n",
       "      <th>tesla</th>\n",
       "      <th>toyota</th>\n",
       "      <th>volkswagen</th>\n",
       "      <th>volvo</th>\n",
       "      <th>price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.0</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>0.471910</td>\n",
       "      <td>0.011236</td>\n",
       "      <td>0.002497</td>\n",
       "      <td>0.019975</td>\n",
       "      <td>0.008739</td>\n",
       "      <td>0.026483</td>\n",
       "      <td>0.022472</td>\n",
       "      <td>0.024969</td>\n",
       "      <td>0.024969</td>\n",
       "      <td>0.069913</td>\n",
       "      <td>...</td>\n",
       "      <td>0.007491</td>\n",
       "      <td>0.002497</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.013733</td>\n",
       "      <td>0.011236</td>\n",
       "      <td>0.001248</td>\n",
       "      <td>0.041199</td>\n",
       "      <td>0.037453</td>\n",
       "      <td>0.012484</td>\n",
       "      <td>20027.687478</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>0.499522</td>\n",
       "      <td>0.105468</td>\n",
       "      <td>0.049938</td>\n",
       "      <td>0.140002</td>\n",
       "      <td>0.093132</td>\n",
       "      <td>0.134342</td>\n",
       "      <td>0.148305</td>\n",
       "      <td>0.156127</td>\n",
       "      <td>0.156127</td>\n",
       "      <td>0.255159</td>\n",
       "      <td>...</td>\n",
       "      <td>0.086278</td>\n",
       "      <td>0.049938</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.116452</td>\n",
       "      <td>0.105468</td>\n",
       "      <td>0.035333</td>\n",
       "      <td>0.198873</td>\n",
       "      <td>0.189988</td>\n",
       "      <td>0.111103</td>\n",
       "      <td>5689.499086</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>10031.760000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>15360.720000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>20161.840000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>24977.690000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.707107</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>29917.250000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>8 rows × 59 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "           gender       acura  astonmartin        audi     bentley  \\\n",
       "count  801.000000  801.000000   801.000000  801.000000  801.000000   \n",
       "mean     0.471910    0.011236     0.002497    0.019975    0.008739   \n",
       "std      0.499522    0.105468     0.049938    0.140002    0.093132   \n",
       "min      0.000000    0.000000     0.000000    0.000000    0.000000   \n",
       "25%      0.000000    0.000000     0.000000    0.000000    0.000000   \n",
       "50%      0.000000    0.000000     0.000000    0.000000    0.000000   \n",
       "75%      1.000000    0.000000     0.000000    0.000000    0.000000   \n",
       "max      1.000000    1.000000     1.000000    1.000000    1.000000   \n",
       "\n",
       "             benz         bmw       buick    cadillac   chevrolet  \\\n",
       "count  801.000000  801.000000  801.000000  801.000000  801.000000   \n",
       "mean     0.026483    0.022472    0.024969    0.024969    0.069913   \n",
       "std      0.134342    0.148305    0.156127    0.156127    0.255159   \n",
       "min      0.000000    0.000000    0.000000    0.000000    0.000000   \n",
       "25%      0.000000    0.000000    0.000000    0.000000    0.000000   \n",
       "50%      0.000000    0.000000    0.000000    0.000000    0.000000   \n",
       "75%      0.000000    0.000000    0.000000    0.000000    0.000000   \n",
       "max      0.707107    1.000000    1.000000    1.000000    1.000000   \n",
       "\n",
       "           ...           saturn       scion  smart      subaru      suzuki  \\\n",
       "count      ...       801.000000  801.000000  801.0  801.000000  801.000000   \n",
       "mean       ...         0.007491    0.002497    0.0    0.013733    0.011236   \n",
       "std        ...         0.086278    0.049938    0.0    0.116452    0.105468   \n",
       "min        ...         0.000000    0.000000    0.0    0.000000    0.000000   \n",
       "25%        ...         0.000000    0.000000    0.0    0.000000    0.000000   \n",
       "50%        ...         0.000000    0.000000    0.0    0.000000    0.000000   \n",
       "75%        ...         0.000000    0.000000    0.0    0.000000    0.000000   \n",
       "max        ...         1.000000    1.000000    0.0    1.000000    1.000000   \n",
       "\n",
       "            tesla      toyota  volkswagen       volvo         price  \n",
       "count  801.000000  801.000000  801.000000  801.000000    801.000000  \n",
       "mean     0.001248    0.041199    0.037453    0.012484  20027.687478  \n",
       "std      0.035333    0.198873    0.189988    0.111103   5689.499086  \n",
       "min      0.000000    0.000000    0.000000    0.000000  10031.760000  \n",
       "25%      0.000000    0.000000    0.000000    0.000000  15360.720000  \n",
       "50%      0.000000    0.000000    0.000000    0.000000  20161.840000  \n",
       "75%      0.000000    0.000000    0.000000    0.000000  24977.690000  \n",
       "max      1.000000    1.000000    1.000000    1.000000  29917.250000  \n",
       "\n",
       "[8 rows x 59 columns]"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train = df_tfidf.dropna(inplace=False)\n",
    "df_train = df_train.reset_index(drop = True)\n",
    "df_train.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "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>gender</th>\n",
       "      <th>acura</th>\n",
       "      <th>astonmartin</th>\n",
       "      <th>audi</th>\n",
       "      <th>bentley</th>\n",
       "      <th>benz</th>\n",
       "      <th>bmw</th>\n",
       "      <th>buick</th>\n",
       "      <th>cadillac</th>\n",
       "      <th>chevrolet</th>\n",
       "      <th>...</th>\n",
       "      <th>saturn</th>\n",
       "      <th>scion</th>\n",
       "      <th>smart</th>\n",
       "      <th>subaru</th>\n",
       "      <th>suzuki</th>\n",
       "      <th>tesla</th>\n",
       "      <th>toyota</th>\n",
       "      <th>volkswagen</th>\n",
       "      <th>volvo</th>\n",
       "      <th>price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>796</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>29742.98</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>797</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>19087.81</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>798</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>14743.35</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>799</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>13630.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>800</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>15388.68</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 59 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     gender  acura  astonmartin  audi  bentley  benz  bmw  buick  cadillac  \\\n",
       "796     0.0    0.0          0.0   1.0      0.0   0.0  0.0    0.0       0.0   \n",
       "797     1.0    0.0          0.0   0.0      0.0   0.0  0.0    0.0       0.0   \n",
       "798     0.0    0.0          0.0   0.0      0.0   0.0  0.0    0.0       0.0   \n",
       "799     1.0    0.0          0.0   0.0      0.0   0.0  0.0    0.0       0.0   \n",
       "800     0.0    0.0          0.0   0.0      0.0   0.0  0.0    0.0       0.0   \n",
       "\n",
       "     chevrolet    ...     saturn  scion  smart  subaru  suzuki  tesla  toyota  \\\n",
       "796        0.0    ...        0.0    0.0    0.0     0.0     0.0    0.0     0.0   \n",
       "797        0.0    ...        0.0    0.0    0.0     0.0     0.0    0.0     0.0   \n",
       "798        1.0    ...        0.0    0.0    0.0     0.0     0.0    0.0     0.0   \n",
       "799        0.0    ...        0.0    0.0    0.0     0.0     0.0    0.0     0.0   \n",
       "800        0.0    ...        0.0    0.0    0.0     0.0     0.0    0.0     0.0   \n",
       "\n",
       "     volkswagen  volvo     price  \n",
       "796         0.0    0.0  29742.98  \n",
       "797         0.0    0.0  19087.81  \n",
       "798         0.0    0.0  14743.35  \n",
       "799         0.0    0.0  13630.00  \n",
       "800         0.0    0.0  15388.68  \n",
       "\n",
       "[5 rows x 59 columns]"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "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>gender</th>\n",
       "      <th>acura</th>\n",
       "      <th>astonmartin</th>\n",
       "      <th>audi</th>\n",
       "      <th>bentley</th>\n",
       "      <th>benz</th>\n",
       "      <th>bmw</th>\n",
       "      <th>buick</th>\n",
       "      <th>cadillac</th>\n",
       "      <th>chevrolet</th>\n",
       "      <th>...</th>\n",
       "      <th>saab</th>\n",
       "      <th>saturn</th>\n",
       "      <th>scion</th>\n",
       "      <th>smart</th>\n",
       "      <th>subaru</th>\n",
       "      <th>suzuki</th>\n",
       "      <th>tesla</th>\n",
       "      <th>toyota</th>\n",
       "      <th>volkswagen</th>\n",
       "      <th>volvo</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 58 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   gender  acura  astonmartin  audi  bentley  benz  bmw  buick  cadillac  \\\n",
       "0     0.0    0.0          0.0   0.0      0.0   0.0  0.0    0.0       0.0   \n",
       "1     0.0    0.0          0.0   0.0      0.0   0.0  0.0    0.0       0.0   \n",
       "2     0.0    0.0          0.0   0.0      0.0   0.0  0.0    0.0       0.0   \n",
       "3     1.0    0.0          0.0   0.0      0.0   0.0  0.0    0.0       0.0   \n",
       "4     1.0    0.0          0.0   0.0      0.0   0.0  0.0    0.0       0.0   \n",
       "\n",
       "   chevrolet  ...    saab  saturn  scion  smart  subaru  suzuki  tesla  \\\n",
       "0        0.0  ...     0.0     0.0    0.0    0.0     0.0     0.0    0.0   \n",
       "1        0.0  ...     0.0     0.0    0.0    0.0     0.0     0.0    0.0   \n",
       "2        0.0  ...     0.0     0.0    0.0    0.0     0.0     0.0    0.0   \n",
       "3        0.0  ...     0.0     0.0    0.0    0.0     0.0     0.0    0.0   \n",
       "4        0.0  ...     0.0     0.0    0.0    0.0     0.0     0.0    0.0   \n",
       "\n",
       "   toyota  volkswagen  volvo  \n",
       "0     0.0         0.0    0.0  \n",
       "1     0.0         0.0    0.0  \n",
       "2     0.0         0.0    0.0  \n",
       "3     0.0         0.0    0.0  \n",
       "4     0.0         0.0    0.0  \n",
       "\n",
       "[5 rows x 58 columns]"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_tfidf[['price']] = df_tfidf[['price']].replace(np.NaN, 0)\n",
    "df_test = df_tfidf[df_tfidf.price == 0.]\n",
    "df_test = df_test.drop('price', axis = 1)\n",
    "df_test = df_test.reset_index(drop = True)\n",
    "df_test.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Now that we have created the training and test set we can create our pipeline "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train = df_train.iloc[:,df_train.columns!='price'].values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [],
   "source": [
    "y_train = df_train['price'].values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_test = df_test.values\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.linear_model import LinearRegression\n",
    "from sklearn.model_selection import GridSearchCV"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "LinearRegression(copy_X=True, fit_intercept=True, n_jobs=None,\n",
       "         normalize=False)"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "linreg = LinearRegression()\n",
    "linreg.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'copy_X': True, 'fit_intercept': True, 'n_jobs': None, 'normalize': False}"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "linreg.get_params()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.076893384964142"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "linreg.score(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [],
   "source": [
    "#grid_search= GridSearchCV(estimator=linreg, cv=5, n_jobs=-1)\n",
    "#grid_search=grid_search.fit(X,y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [],
   "source": [
    "#best_accuracy=grid_search.best_score_\n",
    "#best_parameters=grid_search.best_params_\n",
    "#print (best_accuracy)\n",
    "#print (best_parameters)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([2.08290000e+04, 2.00720000e+04, 2.01980000e+04, 1.96000000e+04,\n",
       "       1.83720000e+04, 2.05180000e+04, 2.08680000e+04, 1.88510000e+04,\n",
       "       2.09920000e+04, 2.00720000e+04, 2.00260000e+04, 2.08280000e+04,\n",
       "       1.73250000e+04, 2.21400000e+04, 2.21400000e+04, 2.16680000e+04,\n",
       "       2.00260000e+04, 1.86040000e+04, 2.08280000e+04, 1.95540000e+04,\n",
       "       2.23620000e+04, 1.81450000e+04, 1.86170000e+04, 2.00720000e+04,\n",
       "       2.12120000e+04, 1.90080000e+04, 1.49410000e+04, 1.77970000e+04,\n",
       "       2.06620000e+04, 2.08680000e+04, 2.21400000e+04, 1.83720000e+04,\n",
       "       1.81320000e+04, 2.01980000e+04, 5.30991112e+15, 2.12120000e+04,\n",
       "       2.09900000e+04, 2.09900000e+04, 1.95860000e+04, 2.05180000e+04,\n",
       "       1.96000000e+04, 1.81320000e+04, 2.19390000e+04, 2.08680000e+04,\n",
       "       2.01980000e+04, 2.08680000e+04, 2.00260000e+04, 2.10710000e+04,\n",
       "       2.08280000e+04, 1.77970000e+04, 2.05990000e+04, 1.83720000e+04,\n",
       "       2.11100000e+04, 1.87600000e+04, 1.93230000e+04, 2.09920000e+04,\n",
       "       2.01980000e+04, 2.16840000e+04, 1.83700000e+04, 1.80710000e+04,\n",
       "       1.77970000e+04, 2.00620000e+04, 1.95540000e+04, 2.00260000e+04,\n",
       "       2.08680000e+04, 1.88510000e+04, 2.23620000e+04, 2.00620000e+04,\n",
       "       1.80710000e+04, 2.01980000e+04, 2.09920000e+04, 2.09920000e+04,\n",
       "       1.81320000e+04, 2.01980000e+04, 1.81320000e+04, 1.97260000e+04,\n",
       "       1.97810000e+04, 2.08680000e+04, 1.62980000e+04, 1.86170000e+04,\n",
       "       1.95900000e+04, 1.88510000e+04, 1.86040000e+04, 1.77970000e+04,\n",
       "       1.87600000e+04, 2.19390000e+04, 2.00620000e+04, 1.91140000e+04,\n",
       "       1.94800000e+04, 2.09240000e+04, 2.01980000e+04, 2.12120000e+04,\n",
       "       2.00720000e+04, 1.88440000e+04, 2.08290000e+04, 1.97810000e+04,\n",
       "       2.19390000e+04, 2.14640000e+04, 2.19390000e+04, 1.95860000e+04,\n",
       "       2.00620000e+04, 2.09900000e+04, 2.05990000e+04, 1.97260000e+04,\n",
       "       2.12120000e+04, 2.21400000e+04, 1.81450000e+04, 2.16840000e+04,\n",
       "       1.90080000e+04, 2.09900000e+04, 2.08290000e+04, 1.86170000e+04,\n",
       "       1.80710000e+04, 1.81320000e+04, 1.86040000e+04, 2.21400000e+04,\n",
       "       2.01980000e+04, 2.09900000e+04, 2.08280000e+04, 1.87600000e+04,\n",
       "       1.96000000e+04, 1.88440000e+04, 2.16840000e+04, 2.16680000e+04,\n",
       "       2.09920000e+04, 2.14640000e+04, 1.95860000e+04, 1.87600000e+04,\n",
       "       2.12120000e+04, 2.13400000e+04, 2.05180000e+04, 2.21400000e+04,\n",
       "       2.01980000e+04, 2.00720000e+04, 2.01980000e+04, 2.10710000e+04,\n",
       "       2.15820000e+04, 1.96000000e+04, 1.85430000e+04, 1.73250000e+04,\n",
       "       2.01980000e+04, 2.00260000e+04, 1.86040000e+04, 1.97260000e+04,\n",
       "       1.86040000e+04, 1.95860000e+04, 1.97260000e+04, 1.97260000e+04,\n",
       "       2.09900000e+04, 1.58260000e+04, 2.10710000e+04, 1.92320000e+04,\n",
       "       1.96000000e+04, 2.01980000e+04, 2.09920000e+04, 2.13400000e+04,\n",
       "       2.21940000e+04, 2.16680000e+04, 2.09920000e+04, 2.14640000e+04,\n",
       "       1.91140000e+04, 2.16680000e+04, 2.11100000e+04, 1.95540000e+04,\n",
       "       1.83720000e+04, 2.00260000e+04, 2.09920000e+04, 1.54130000e+04,\n",
       "       2.16840000e+04, 2.16840000e+04, 2.08280000e+04, 2.21400000e+04,\n",
       "       1.69960000e+04, 2.11100000e+04, 1.97260000e+04, 2.09920000e+04,\n",
       "       1.95540000e+04, 2.24110000e+04, 1.81320000e+04, 2.13400000e+04,\n",
       "       1.95900000e+04, 1.96000000e+04, 2.11340000e+04, 2.01980000e+04,\n",
       "       1.97260000e+04, 2.09920000e+04, 2.81320000e+04, 1.97260000e+04,\n",
       "       2.09240000e+04, 1.95860000e+04, 1.73250000e+04, 2.14640000e+04,\n",
       "       1.91140000e+04, 2.01980000e+04, 2.13960000e+04, 1.85170000e+04,\n",
       "       2.00720000e+04, 2.05180000e+04, 1.81450000e+04])"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "linreg.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_y_pred = pd.DataFrame(linreg.predict(X_test), columns = ['price'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_pred = df_nan.join(df_y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_pred.head(35)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_pred.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Something has gone really wrong here, the mean and standard deviation for price are huge, they must contain very large velues - the smart car is super expensive for example... I dont know why this has happened "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_pred_cleaned = df_pred[df_pred.carmake != 'smart']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_pred_cleaned.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Much more realistic - maybe it is because there are no smart cars in the training data? doesnt explain the super high value completly. "
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}