Preprocessing - Encoding Categorical Variables into Numerical Using Pandas & Scikit Learn.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "3a739601",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np \n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "6af6174f",
   "metadata": {},
   "outputs": [],
   "source": [
    "df1 = sns.load_dataset('titanic')\n",
    "#Lets start off with Loading Titanic dataset from seaborn"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "fd683eb8",
   "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>survived</th>\n",
       "      <th>pclass</th>\n",
       "      <th>sex</th>\n",
       "      <th>age</th>\n",
       "      <th>sibsp</th>\n",
       "      <th>parch</th>\n",
       "      <th>fare</th>\n",
       "      <th>embarked</th>\n",
       "      <th>class</th>\n",
       "      <th>who</th>\n",
       "      <th>adult_male</th>\n",
       "      <th>deck</th>\n",
       "      <th>embark_town</th>\n",
       "      <th>alive</th>\n",
       "      <th>alone</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>S</td>\n",
       "      <td>Third</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>no</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>female</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>C</td>\n",
       "      <td>First</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>C</td>\n",
       "      <td>Cherbourg</td>\n",
       "      <td>yes</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>female</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>S</td>\n",
       "      <td>Third</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>yes</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>female</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>S</td>\n",
       "      <td>First</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>C</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>yes</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>S</td>\n",
       "      <td>Third</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>no</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   survived  pclass     sex   age  sibsp  parch     fare embarked  class  \\\n",
       "0         0       3    male  22.0      1      0   7.2500        S  Third   \n",
       "1         1       1  female  38.0      1      0  71.2833        C  First   \n",
       "2         1       3  female  26.0      0      0   7.9250        S  Third   \n",
       "3         1       1  female  35.0      1      0  53.1000        S  First   \n",
       "4         0       3    male  35.0      0      0   8.0500        S  Third   \n",
       "\n",
       "     who  adult_male deck  embark_town alive  alone  \n",
       "0    man        True  NaN  Southampton    no  False  \n",
       "1  woman       False    C    Cherbourg   yes  False  \n",
       "2  woman       False  NaN  Southampton   yes   True  \n",
       "3  woman       False    C  Southampton   yes  False  \n",
       "4    man        True  NaN  Southampton    no   True  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "6cb0942e",
   "metadata": {},
   "outputs": [],
   "source": [
    "df2 = df1.copy(deep=True)\n",
    "df3 = df2.copy(deep=True)\n",
    "#Create a copy of our dataframe "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3a3315b0",
   "metadata": {},
   "source": [
    "## Encoding Using Pandas"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "83e64248",
   "metadata": {},
   "source": [
    "### Encoding Features embark_town & class Using Dummies "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "bde452c0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "survived         0\n",
       "pclass           0\n",
       "sex              0\n",
       "age            177\n",
       "sibsp            0\n",
       "parch            0\n",
       "fare             0\n",
       "embarked         2\n",
       "class            0\n",
       "who              0\n",
       "adult_male       0\n",
       "deck           688\n",
       "embark_town      2\n",
       "alive            0\n",
       "alone            0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1.isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "58047ef7",
   "metadata": {},
   "outputs": [],
   "source": [
    "dummy_encoded = pd.get_dummies(df1, columns = [\"embark_town\",\"class\"], prefix = [\"town\",\"class\"])\n",
    "#by default get_dummies handles na or missing values. If data requires a separte column for missing values pass If dummy_na = True"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "f7d3a6c0",
   "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>survived</th>\n",
       "      <th>pclass</th>\n",
       "      <th>sex</th>\n",
       "      <th>age</th>\n",
       "      <th>sibsp</th>\n",
       "      <th>parch</th>\n",
       "      <th>fare</th>\n",
       "      <th>embarked</th>\n",
       "      <th>who</th>\n",
       "      <th>adult_male</th>\n",
       "      <th>deck</th>\n",
       "      <th>alive</th>\n",
       "      <th>alone</th>\n",
       "      <th>town_Cherbourg</th>\n",
       "      <th>town_Queenstown</th>\n",
       "      <th>town_Southampton</th>\n",
       "      <th>class_First</th>\n",
       "      <th>class_Second</th>\n",
       "      <th>class_Third</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>S</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>no</td>\n",
       "      <td>False</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>female</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>C</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>C</td>\n",
       "      <td>yes</td>\n",
       "      <td>False</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>female</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>S</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>yes</td>\n",
       "      <td>True</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>female</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>S</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>C</td>\n",
       "      <td>yes</td>\n",
       "      <td>False</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>S</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>no</td>\n",
       "      <td>True</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   survived  pclass     sex   age  sibsp  parch     fare embarked    who  \\\n",
       "0         0       3    male  22.0      1      0   7.2500        S    man   \n",
       "1         1       1  female  38.0      1      0  71.2833        C  woman   \n",
       "2         1       3  female  26.0      0      0   7.9250        S  woman   \n",
       "3         1       1  female  35.0      1      0  53.1000        S  woman   \n",
       "4         0       3    male  35.0      0      0   8.0500        S    man   \n",
       "\n",
       "   adult_male deck alive  alone  town_Cherbourg  town_Queenstown  \\\n",
       "0        True  NaN    no  False               0                0   \n",
       "1       False    C   yes  False               1                0   \n",
       "2       False  NaN   yes   True               0                0   \n",
       "3       False    C   yes  False               0                0   \n",
       "4        True  NaN    no   True               0                0   \n",
       "\n",
       "   town_Southampton  class_First  class_Second  class_Third  \n",
       "0                 1            0             0            1  \n",
       "1                 0            1             0            0  \n",
       "2                 1            0             0            1  \n",
       "3                 1            1             0            0  \n",
       "4                 1            0             0            1  "
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dummy_encoded.head()\n",
    "#output our Dataframe"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b1d7c788",
   "metadata": {},
   "source": [
    "### Label Encoding using Pandas\n",
    "Label encoding is also known as integer encoding. Integer encoding replaces categorical values with numeric values. Here, the unique values in variables are replaced with a sequence of integer values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "e3925638",
   "metadata": {},
   "outputs": [],
   "source": [
    "class_map = {'class':{'Third':1, 'Second':2, 'First':3},\n",
    "            'sex':{'male':0, 'female':1}}\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "a3a9eebe",
   "metadata": {},
   "outputs": [],
   "source": [
    "df1 = df1.replace(class_map)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "5c01861b",
   "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>survived</th>\n",
       "      <th>pclass</th>\n",
       "      <th>sex</th>\n",
       "      <th>age</th>\n",
       "      <th>sibsp</th>\n",
       "      <th>parch</th>\n",
       "      <th>fare</th>\n",
       "      <th>embarked</th>\n",
       "      <th>class</th>\n",
       "      <th>who</th>\n",
       "      <th>adult_male</th>\n",
       "      <th>deck</th>\n",
       "      <th>embark_town</th>\n",
       "      <th>alive</th>\n",
       "      <th>alone</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>S</td>\n",
       "      <td>1</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>no</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>C</td>\n",
       "      <td>3</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>C</td>\n",
       "      <td>Cherbourg</td>\n",
       "      <td>yes</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>S</td>\n",
       "      <td>1</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>yes</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>S</td>\n",
       "      <td>3</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>C</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>yes</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>S</td>\n",
       "      <td>1</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>no</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   survived  pclass  sex   age  sibsp  parch     fare embarked class    who  \\\n",
       "0         0       3    0  22.0      1      0   7.2500        S     1    man   \n",
       "1         1       1    1  38.0      1      0  71.2833        C     3  woman   \n",
       "2         1       3    1  26.0      0      0   7.9250        S     1  woman   \n",
       "3         1       1    1  35.0      1      0  53.1000        S     3  woman   \n",
       "4         0       3    0  35.0      0      0   8.0500        S     1    man   \n",
       "\n",
       "   adult_male deck  embark_town alive  alone  \n",
       "0        True  NaN  Southampton    no  False  \n",
       "1       False    C    Cherbourg   yes  False  \n",
       "2       False  NaN  Southampton   yes   True  \n",
       "3       False    C  Southampton   yes  False  \n",
       "4        True  NaN  Southampton    no   True  "
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2ad596b3",
   "metadata": {},
   "source": [
    "### Ordinal Encoding using Pandas \n",
    "Ordinal encoding is similar to label encoding, except there's an order to the encoding. Ordinal data has ranking. We can define the order of the values as a list and pass it to the category parameter. Lets encode Class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "b295b29e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "survived          int64\n",
       "pclass            int64\n",
       "sex               int64\n",
       "age             float64\n",
       "sibsp             int64\n",
       "parch             int64\n",
       "fare            float64\n",
       "embarked         object\n",
       "class          category\n",
       "who              object\n",
       "adult_male         bool\n",
       "deck           category\n",
       "embark_town      object\n",
       "alive            object\n",
       "alone              bool\n",
       "dtype: object"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "69cff759",
   "metadata": {},
   "outputs": [],
   "source": [
    "df1['embark_town'] = df1['embark_town'].astype('category')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "8b5e2365",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "survived          int64\n",
       "pclass            int64\n",
       "sex               int64\n",
       "age             float64\n",
       "sibsp             int64\n",
       "parch             int64\n",
       "fare            float64\n",
       "embarked         object\n",
       "class          category\n",
       "who              object\n",
       "adult_male         bool\n",
       "deck           category\n",
       "embark_town    category\n",
       "alive            object\n",
       "alone              bool\n",
       "dtype: object"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "3d7a4826",
   "metadata": {},
   "outputs": [],
   "source": [
    "df1['embark_town'] = df1['embark_town'].cat.codes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "35dfd883",
   "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>survived</th>\n",
       "      <th>pclass</th>\n",
       "      <th>sex</th>\n",
       "      <th>age</th>\n",
       "      <th>sibsp</th>\n",
       "      <th>parch</th>\n",
       "      <th>fare</th>\n",
       "      <th>embarked</th>\n",
       "      <th>class</th>\n",
       "      <th>who</th>\n",
       "      <th>adult_male</th>\n",
       "      <th>deck</th>\n",
       "      <th>embark_town</th>\n",
       "      <th>alive</th>\n",
       "      <th>alone</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>S</td>\n",
       "      <td>1</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2</td>\n",
       "      <td>no</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>C</td>\n",
       "      <td>3</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>C</td>\n",
       "      <td>0</td>\n",
       "      <td>yes</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>S</td>\n",
       "      <td>1</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2</td>\n",
       "      <td>yes</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>S</td>\n",
       "      <td>3</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>C</td>\n",
       "      <td>2</td>\n",
       "      <td>yes</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>S</td>\n",
       "      <td>1</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2</td>\n",
       "      <td>no</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   survived  pclass  sex   age  sibsp  parch     fare embarked class    who  \\\n",
       "0         0       3    0  22.0      1      0   7.2500        S     1    man   \n",
       "1         1       1    1  38.0      1      0  71.2833        C     3  woman   \n",
       "2         1       3    1  26.0      0      0   7.9250        S     1  woman   \n",
       "3         1       1    1  35.0      1      0  53.1000        S     3  woman   \n",
       "4         0       3    0  35.0      0      0   8.0500        S     1    man   \n",
       "\n",
       "   adult_male deck  embark_town alive  alone  \n",
       "0        True  NaN            2    no  False  \n",
       "1       False    C            0   yes  False  \n",
       "2       False  NaN            2   yes   True  \n",
       "3       False    C            2   yes  False  \n",
       "4        True  NaN            2    no   True  "
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "aba0b1a1",
   "metadata": {},
   "source": [
    "# Encoding Using Scikit Learn"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "42f756cd",
   "metadata": {},
   "source": [
    "### Label Encoding with Sckit Learn"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "a84d8ece",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import LabelEncoder, OneHotEncoder"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "ff9ec32f",
   "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>survived</th>\n",
       "      <th>pclass</th>\n",
       "      <th>sex</th>\n",
       "      <th>age</th>\n",
       "      <th>sibsp</th>\n",
       "      <th>parch</th>\n",
       "      <th>fare</th>\n",
       "      <th>embarked</th>\n",
       "      <th>class</th>\n",
       "      <th>who</th>\n",
       "      <th>adult_male</th>\n",
       "      <th>deck</th>\n",
       "      <th>embark_town</th>\n",
       "      <th>alive</th>\n",
       "      <th>alone</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>S</td>\n",
       "      <td>Third</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>no</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>female</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>C</td>\n",
       "      <td>First</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>C</td>\n",
       "      <td>Cherbourg</td>\n",
       "      <td>yes</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>female</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>S</td>\n",
       "      <td>Third</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>yes</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>female</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>S</td>\n",
       "      <td>First</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>C</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>yes</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>S</td>\n",
       "      <td>Third</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>no</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   survived  pclass     sex   age  sibsp  parch     fare embarked  class  \\\n",
       "0         0       3    male  22.0      1      0   7.2500        S  Third   \n",
       "1         1       1  female  38.0      1      0  71.2833        C  First   \n",
       "2         1       3  female  26.0      0      0   7.9250        S  Third   \n",
       "3         1       1  female  35.0      1      0  53.1000        S  First   \n",
       "4         0       3    male  35.0      0      0   8.0500        S  Third   \n",
       "\n",
       "     who  adult_male deck  embark_town alive  alone  \n",
       "0    man        True  NaN  Southampton    no  False  \n",
       "1  woman       False    C    Cherbourg   yes  False  \n",
       "2  woman       False  NaN  Southampton   yes   True  \n",
       "3  woman       False    C  Southampton   yes  False  \n",
       "4    man        True  NaN  Southampton    no   True  "
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df2.head(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "bd02138d",
   "metadata": {},
   "outputs": [],
   "source": [
    "labelencoder = LabelEncoder()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "bf87b092",
   "metadata": {},
   "outputs": [],
   "source": [
    "df2['embarked'] = labelencoder.fit_transform(df2['embarked'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "fa04f7c4",
   "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>survived</th>\n",
       "      <th>pclass</th>\n",
       "      <th>sex</th>\n",
       "      <th>age</th>\n",
       "      <th>sibsp</th>\n",
       "      <th>parch</th>\n",
       "      <th>fare</th>\n",
       "      <th>embarked</th>\n",
       "      <th>class</th>\n",
       "      <th>who</th>\n",
       "      <th>adult_male</th>\n",
       "      <th>deck</th>\n",
       "      <th>embark_town</th>\n",
       "      <th>alive</th>\n",
       "      <th>alone</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>2</td>\n",
       "      <td>Third</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>no</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>female</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>0</td>\n",
       "      <td>First</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>C</td>\n",
       "      <td>Cherbourg</td>\n",
       "      <td>yes</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>female</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>2</td>\n",
       "      <td>Third</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>yes</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>female</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>2</td>\n",
       "      <td>First</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>C</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>yes</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>2</td>\n",
       "      <td>Third</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>no</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   survived  pclass     sex   age  sibsp  parch     fare  embarked  class  \\\n",
       "0         0       3    male  22.0      1      0   7.2500         2  Third   \n",
       "1         1       1  female  38.0      1      0  71.2833         0  First   \n",
       "2         1       3  female  26.0      0      0   7.9250         2  Third   \n",
       "3         1       1  female  35.0      1      0  53.1000         2  First   \n",
       "4         0       3    male  35.0      0      0   8.0500         2  Third   \n",
       "\n",
       "     who  adult_male deck  embark_town alive  alone  \n",
       "0    man        True  NaN  Southampton    no  False  \n",
       "1  woman       False    C    Cherbourg   yes  False  \n",
       "2  woman       False  NaN  Southampton   yes   True  \n",
       "3  woman       False    C  Southampton   yes  False  \n",
       "4    man        True  NaN  Southampton    no   True  "
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df2.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d8b300ec",
   "metadata": {},
   "source": [
    "### Onehotencoder with Sklearn with Feature Names "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "6308048b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "survived          int64\n",
       "pclass            int64\n",
       "sex              object\n",
       "age             float64\n",
       "sibsp             int64\n",
       "parch             int64\n",
       "fare            float64\n",
       "embarked          int64\n",
       "class          category\n",
       "who              object\n",
       "adult_male         bool\n",
       "deck           category\n",
       "embark_town      object\n",
       "alive            object\n",
       "alone              bool\n",
       "dtype: object"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df2.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "0485991a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "survived         0\n",
       "pclass           0\n",
       "sex              0\n",
       "age            177\n",
       "sibsp            0\n",
       "parch            0\n",
       "fare             0\n",
       "embarked         0\n",
       "class            0\n",
       "who              0\n",
       "adult_male       0\n",
       "deck           688\n",
       "embark_town      2\n",
       "alive            0\n",
       "alone            0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df2.isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "699fed87",
   "metadata": {},
   "outputs": [],
   "source": [
    "df2['embark_town'] = df2['embark_town'].fillna(df2['embark_town'].mode()[0])\n",
    "#we fill missing values in 'embark_town' with most common town where travellers boarded Titanic"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "48b9049d",
   "metadata": {},
   "outputs": [],
   "source": [
    "on_hot = OneHotEncoder(sparse=False)\n",
    "#with sparse = False we make sure that sckit learn returns dense matrix "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "421d3e5a",
   "metadata": {},
   "outputs": [],
   "source": [
    "hot_encoded = on_hot.fit_transform(df2[['embark_town']])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "335034b6",
   "metadata": {},
   "outputs": [],
   "source": [
    "column_names = on_hot.get_feature_names_out(['embark_town'])\n",
    "#we are able to conveniently access feature names from get_feature_names_out "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "e2f9bb46",
   "metadata": {},
   "outputs": [],
   "source": [
    "encoded_df = pd.DataFrame(hot_encoded, columns=column_names)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "00239d17",
   "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>survived</th>\n",
       "      <th>pclass</th>\n",
       "      <th>sex</th>\n",
       "      <th>age</th>\n",
       "      <th>sibsp</th>\n",
       "      <th>parch</th>\n",
       "      <th>fare</th>\n",
       "      <th>embarked</th>\n",
       "      <th>class</th>\n",
       "      <th>who</th>\n",
       "      <th>adult_male</th>\n",
       "      <th>deck</th>\n",
       "      <th>embark_town</th>\n",
       "      <th>alive</th>\n",
       "      <th>alone</th>\n",
       "      <th>embark_town_Cherbourg</th>\n",
       "      <th>embark_town_Queenstown</th>\n",
       "      <th>embark_town_Southampton</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>2</td>\n",
       "      <td>Third</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>no</td>\n",
       "      <td>False</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>female</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>0</td>\n",
       "      <td>First</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>C</td>\n",
       "      <td>Cherbourg</td>\n",
       "      <td>yes</td>\n",
       "      <td>False</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>female</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>2</td>\n",
       "      <td>Third</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>yes</td>\n",
       "      <td>True</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>female</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>2</td>\n",
       "      <td>First</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>C</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>yes</td>\n",
       "      <td>False</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>2</td>\n",
       "      <td>Third</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>no</td>\n",
       "      <td>True</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>886</th>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>male</td>\n",
       "      <td>27.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>13.0000</td>\n",
       "      <td>2</td>\n",
       "      <td>Second</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>no</td>\n",
       "      <td>True</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>887</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>female</td>\n",
       "      <td>19.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>30.0000</td>\n",
       "      <td>2</td>\n",
       "      <td>First</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>B</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>yes</td>\n",
       "      <td>True</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>888</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>female</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>23.4500</td>\n",
       "      <td>2</td>\n",
       "      <td>Third</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>no</td>\n",
       "      <td>False</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>889</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>male</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>30.0000</td>\n",
       "      <td>0</td>\n",
       "      <td>First</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>C</td>\n",
       "      <td>Cherbourg</td>\n",
       "      <td>yes</td>\n",
       "      <td>True</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>890</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>32.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.7500</td>\n",
       "      <td>1</td>\n",
       "      <td>Third</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Queenstown</td>\n",
       "      <td>no</td>\n",
       "      <td>True</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>891 rows × 18 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     survived  pclass     sex   age  sibsp  parch     fare  embarked   class  \\\n",
       "0           0       3    male  22.0      1      0   7.2500         2   Third   \n",
       "1           1       1  female  38.0      1      0  71.2833         0   First   \n",
       "2           1       3  female  26.0      0      0   7.9250         2   Third   \n",
       "3           1       1  female  35.0      1      0  53.1000         2   First   \n",
       "4           0       3    male  35.0      0      0   8.0500         2   Third   \n",
       "..        ...     ...     ...   ...    ...    ...      ...       ...     ...   \n",
       "886         0       2    male  27.0      0      0  13.0000         2  Second   \n",
       "887         1       1  female  19.0      0      0  30.0000         2   First   \n",
       "888         0       3  female   NaN      1      2  23.4500         2   Third   \n",
       "889         1       1    male  26.0      0      0  30.0000         0   First   \n",
       "890         0       3    male  32.0      0      0   7.7500         1   Third   \n",
       "\n",
       "       who  adult_male deck  embark_town alive  alone  embark_town_Cherbourg  \\\n",
       "0      man        True  NaN  Southampton    no  False                    0.0   \n",
       "1    woman       False    C    Cherbourg   yes  False                    1.0   \n",
       "2    woman       False  NaN  Southampton   yes   True                    0.0   \n",
       "3    woman       False    C  Southampton   yes  False                    0.0   \n",
       "4      man        True  NaN  Southampton    no   True                    0.0   \n",
       "..     ...         ...  ...          ...   ...    ...                    ...   \n",
       "886    man        True  NaN  Southampton    no   True                    0.0   \n",
       "887  woman       False    B  Southampton   yes   True                    0.0   \n",
       "888  woman       False  NaN  Southampton    no  False                    0.0   \n",
       "889    man        True    C    Cherbourg   yes   True                    1.0   \n",
       "890    man        True  NaN   Queenstown    no   True                    0.0   \n",
       "\n",
       "     embark_town_Queenstown  embark_town_Southampton  \n",
       "0                       0.0                      1.0  \n",
       "1                       0.0                      0.0  \n",
       "2                       0.0                      1.0  \n",
       "3                       0.0                      1.0  \n",
       "4                       0.0                      1.0  \n",
       "..                      ...                      ...  \n",
       "886                     0.0                      1.0  \n",
       "887                     0.0                      1.0  \n",
       "888                     0.0                      1.0  \n",
       "889                     0.0                      0.0  \n",
       "890                     1.0                      0.0  \n",
       "\n",
       "[891 rows x 18 columns]"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df2.join(encoded_df)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "99a7152b",
   "metadata": {},
   "source": [
    "## Ordinal Encoder with Scikit "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9ba58b2b",
   "metadata": {},
   "source": [
    "### Encoding with Scikit default values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "ce076f77",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import OrdinalEncoder"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "0755e4ba",
   "metadata": {},
   "outputs": [],
   "source": [
    "Ordinal_encoded = OrdinalEncoder()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "9779b0ba",
   "metadata": {},
   "outputs": [],
   "source": [
    "df2[['class']] = Ordinal_encoded.fit_transform(df2[['class']])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "f83ea6d3",
   "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>survived</th>\n",
       "      <th>pclass</th>\n",
       "      <th>sex</th>\n",
       "      <th>age</th>\n",
       "      <th>sibsp</th>\n",
       "      <th>parch</th>\n",
       "      <th>fare</th>\n",
       "      <th>embarked</th>\n",
       "      <th>class</th>\n",
       "      <th>who</th>\n",
       "      <th>adult_male</th>\n",
       "      <th>deck</th>\n",
       "      <th>embark_town</th>\n",
       "      <th>alive</th>\n",
       "      <th>alone</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>2</td>\n",
       "      <td>2.0</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>no</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>female</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>C</td>\n",
       "      <td>Cherbourg</td>\n",
       "      <td>yes</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>female</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>2</td>\n",
       "      <td>2.0</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>yes</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>female</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>2</td>\n",
       "      <td>0.0</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>C</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>yes</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>2</td>\n",
       "      <td>2.0</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>no</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   survived  pclass     sex   age  sibsp  parch     fare  embarked  class  \\\n",
       "0         0       3    male  22.0      1      0   7.2500         2    2.0   \n",
       "1         1       1  female  38.0      1      0  71.2833         0    0.0   \n",
       "2         1       3  female  26.0      0      0   7.9250         2    2.0   \n",
       "3         1       1  female  35.0      1      0  53.1000         2    0.0   \n",
       "4         0       3    male  35.0      0      0   8.0500         2    2.0   \n",
       "\n",
       "     who  adult_male deck  embark_town alive  alone  \n",
       "0    man        True  NaN  Southampton    no  False  \n",
       "1  woman       False    C    Cherbourg   yes  False  \n",
       "2  woman       False  NaN  Southampton   yes   True  \n",
       "3  woman       False    C  Southampton   yes  False  \n",
       "4    man        True  NaN  Southampton    no   True  "
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df2.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "92c5e3a3",
   "metadata": {},
   "outputs": [],
   "source": [
    "#In the above example we have encoded data with sckit learns default assigning of ordinal code to the class variable. \n",
    "#It has encoded class 3 as 2, Class 1 as 0, and class 3 as 3 since 3 > 2 > 1 which in ordinal data makes class 3 as more significant than class 1"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3ee99512",
   "metadata": {},
   "source": [
    "### Encoding by assigning explicit Ordinal Values "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "d7d19589",
   "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>survived</th>\n",
       "      <th>pclass</th>\n",
       "      <th>sex</th>\n",
       "      <th>age</th>\n",
       "      <th>sibsp</th>\n",
       "      <th>parch</th>\n",
       "      <th>fare</th>\n",
       "      <th>embarked</th>\n",
       "      <th>class</th>\n",
       "      <th>who</th>\n",
       "      <th>adult_male</th>\n",
       "      <th>deck</th>\n",
       "      <th>embark_town</th>\n",
       "      <th>alive</th>\n",
       "      <th>alone</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>S</td>\n",
       "      <td>Third</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>no</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>female</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>C</td>\n",
       "      <td>First</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>C</td>\n",
       "      <td>Cherbourg</td>\n",
       "      <td>yes</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>female</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>S</td>\n",
       "      <td>Third</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>yes</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>female</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>S</td>\n",
       "      <td>First</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>C</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>yes</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>S</td>\n",
       "      <td>Third</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>no</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   survived  pclass     sex   age  sibsp  parch     fare embarked  class  \\\n",
       "0         0       3    male  22.0      1      0   7.2500        S  Third   \n",
       "1         1       1  female  38.0      1      0  71.2833        C  First   \n",
       "2         1       3  female  26.0      0      0   7.9250        S  Third   \n",
       "3         1       1  female  35.0      1      0  53.1000        S  First   \n",
       "4         0       3    male  35.0      0      0   8.0500        S  Third   \n",
       "\n",
       "     who  adult_male deck  embark_town alive  alone  \n",
       "0    man        True  NaN  Southampton    no  False  \n",
       "1  woman       False    C    Cherbourg   yes  False  \n",
       "2  woman       False  NaN  Southampton   yes   True  \n",
       "3  woman       False    C  Southampton   yes  False  \n",
       "4    man        True  NaN  Southampton    no   True  "
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df3.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "f9c9534d",
   "metadata": {},
   "outputs": [],
   "source": [
    "ratings_order = ['Third','Second','First'] #Now First class has a higher order than Third Class\n",
    "oe = OrdinalEncoder(categories = [ratings_order], dtype = int)\n",
    "rating_order = oe.fit_transform(df3[['class']])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "7b3127c0",
   "metadata": {},
   "outputs": [],
   "source": [
    "df3 = df3.assign(class_encoded = rating_order)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "id": "2c2fc655",
   "metadata": {},
   "outputs": [],
   "source": [
    "def highlight_cols(s):\n",
    "    color = 'yellow'\n",
    "    return 'background-color: %s' % color"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "id": "2806c567",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style type=\"text/css\">\n",
       "#T_8583a_row0_col8, #T_8583a_row0_col15, #T_8583a_row1_col8, #T_8583a_row1_col15, #T_8583a_row2_col8, #T_8583a_row2_col15, #T_8583a_row3_col8, #T_8583a_row3_col15, #T_8583a_row4_col8, #T_8583a_row4_col15 {\n",
       "  background-color: yellow;\n",
       "}\n",
       "</style>\n",
       "<table id=\"T_8583a\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th class=\"blank level0\" >&nbsp;</th>\n",
       "      <th id=\"T_8583a_level0_col0\" class=\"col_heading level0 col0\" >survived</th>\n",
       "      <th id=\"T_8583a_level0_col1\" class=\"col_heading level0 col1\" >pclass</th>\n",
       "      <th id=\"T_8583a_level0_col2\" class=\"col_heading level0 col2\" >sex</th>\n",
       "      <th id=\"T_8583a_level0_col3\" class=\"col_heading level0 col3\" >age</th>\n",
       "      <th id=\"T_8583a_level0_col4\" class=\"col_heading level0 col4\" >sibsp</th>\n",
       "      <th id=\"T_8583a_level0_col5\" class=\"col_heading level0 col5\" >parch</th>\n",
       "      <th id=\"T_8583a_level0_col6\" class=\"col_heading level0 col6\" >fare</th>\n",
       "      <th id=\"T_8583a_level0_col7\" class=\"col_heading level0 col7\" >embarked</th>\n",
       "      <th id=\"T_8583a_level0_col8\" class=\"col_heading level0 col8\" >class</th>\n",
       "      <th id=\"T_8583a_level0_col9\" class=\"col_heading level0 col9\" >who</th>\n",
       "      <th id=\"T_8583a_level0_col10\" class=\"col_heading level0 col10\" >adult_male</th>\n",
       "      <th id=\"T_8583a_level0_col11\" class=\"col_heading level0 col11\" >deck</th>\n",
       "      <th id=\"T_8583a_level0_col12\" class=\"col_heading level0 col12\" >embark_town</th>\n",
       "      <th id=\"T_8583a_level0_col13\" class=\"col_heading level0 col13\" >alive</th>\n",
       "      <th id=\"T_8583a_level0_col14\" class=\"col_heading level0 col14\" >alone</th>\n",
       "      <th id=\"T_8583a_level0_col15\" class=\"col_heading level0 col15\" >class_encoded</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th id=\"T_8583a_level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
       "      <td id=\"T_8583a_row0_col0\" class=\"data row0 col0\" >0</td>\n",
       "      <td id=\"T_8583a_row0_col1\" class=\"data row0 col1\" >3</td>\n",
       "      <td id=\"T_8583a_row0_col2\" class=\"data row0 col2\" >male</td>\n",
       "      <td id=\"T_8583a_row0_col3\" class=\"data row0 col3\" >22.000000</td>\n",
       "      <td id=\"T_8583a_row0_col4\" class=\"data row0 col4\" >1</td>\n",
       "      <td id=\"T_8583a_row0_col5\" class=\"data row0 col5\" >0</td>\n",
       "      <td id=\"T_8583a_row0_col6\" class=\"data row0 col6\" >7.250000</td>\n",
       "      <td id=\"T_8583a_row0_col7\" class=\"data row0 col7\" >S</td>\n",
       "      <td id=\"T_8583a_row0_col8\" class=\"data row0 col8\" >Third</td>\n",
       "      <td id=\"T_8583a_row0_col9\" class=\"data row0 col9\" >man</td>\n",
       "      <td id=\"T_8583a_row0_col10\" class=\"data row0 col10\" >True</td>\n",
       "      <td id=\"T_8583a_row0_col11\" class=\"data row0 col11\" >nan</td>\n",
       "      <td id=\"T_8583a_row0_col12\" class=\"data row0 col12\" >Southampton</td>\n",
       "      <td id=\"T_8583a_row0_col13\" class=\"data row0 col13\" >no</td>\n",
       "      <td id=\"T_8583a_row0_col14\" class=\"data row0 col14\" >False</td>\n",
       "      <td id=\"T_8583a_row0_col15\" class=\"data row0 col15\" >0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_8583a_level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
       "      <td id=\"T_8583a_row1_col0\" class=\"data row1 col0\" >1</td>\n",
       "      <td id=\"T_8583a_row1_col1\" class=\"data row1 col1\" >1</td>\n",
       "      <td id=\"T_8583a_row1_col2\" class=\"data row1 col2\" >female</td>\n",
       "      <td id=\"T_8583a_row1_col3\" class=\"data row1 col3\" >38.000000</td>\n",
       "      <td id=\"T_8583a_row1_col4\" class=\"data row1 col4\" >1</td>\n",
       "      <td id=\"T_8583a_row1_col5\" class=\"data row1 col5\" >0</td>\n",
       "      <td id=\"T_8583a_row1_col6\" class=\"data row1 col6\" >71.283300</td>\n",
       "      <td id=\"T_8583a_row1_col7\" class=\"data row1 col7\" >C</td>\n",
       "      <td id=\"T_8583a_row1_col8\" class=\"data row1 col8\" >First</td>\n",
       "      <td id=\"T_8583a_row1_col9\" class=\"data row1 col9\" >woman</td>\n",
       "      <td id=\"T_8583a_row1_col10\" class=\"data row1 col10\" >False</td>\n",
       "      <td id=\"T_8583a_row1_col11\" class=\"data row1 col11\" >C</td>\n",
       "      <td id=\"T_8583a_row1_col12\" class=\"data row1 col12\" >Cherbourg</td>\n",
       "      <td id=\"T_8583a_row1_col13\" class=\"data row1 col13\" >yes</td>\n",
       "      <td id=\"T_8583a_row1_col14\" class=\"data row1 col14\" >False</td>\n",
       "      <td id=\"T_8583a_row1_col15\" class=\"data row1 col15\" >2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_8583a_level0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
       "      <td id=\"T_8583a_row2_col0\" class=\"data row2 col0\" >1</td>\n",
       "      <td id=\"T_8583a_row2_col1\" class=\"data row2 col1\" >3</td>\n",
       "      <td id=\"T_8583a_row2_col2\" class=\"data row2 col2\" >female</td>\n",
       "      <td id=\"T_8583a_row2_col3\" class=\"data row2 col3\" >26.000000</td>\n",
       "      <td id=\"T_8583a_row2_col4\" class=\"data row2 col4\" >0</td>\n",
       "      <td id=\"T_8583a_row2_col5\" class=\"data row2 col5\" >0</td>\n",
       "      <td id=\"T_8583a_row2_col6\" class=\"data row2 col6\" >7.925000</td>\n",
       "      <td id=\"T_8583a_row2_col7\" class=\"data row2 col7\" >S</td>\n",
       "      <td id=\"T_8583a_row2_col8\" class=\"data row2 col8\" >Third</td>\n",
       "      <td id=\"T_8583a_row2_col9\" class=\"data row2 col9\" >woman</td>\n",
       "      <td id=\"T_8583a_row2_col10\" class=\"data row2 col10\" >False</td>\n",
       "      <td id=\"T_8583a_row2_col11\" class=\"data row2 col11\" >nan</td>\n",
       "      <td id=\"T_8583a_row2_col12\" class=\"data row2 col12\" >Southampton</td>\n",
       "      <td id=\"T_8583a_row2_col13\" class=\"data row2 col13\" >yes</td>\n",
       "      <td id=\"T_8583a_row2_col14\" class=\"data row2 col14\" >True</td>\n",
       "      <td id=\"T_8583a_row2_col15\" class=\"data row2 col15\" >0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_8583a_level0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
       "      <td id=\"T_8583a_row3_col0\" class=\"data row3 col0\" >1</td>\n",
       "      <td id=\"T_8583a_row3_col1\" class=\"data row3 col1\" >1</td>\n",
       "      <td id=\"T_8583a_row3_col2\" class=\"data row3 col2\" >female</td>\n",
       "      <td id=\"T_8583a_row3_col3\" class=\"data row3 col3\" >35.000000</td>\n",
       "      <td id=\"T_8583a_row3_col4\" class=\"data row3 col4\" >1</td>\n",
       "      <td id=\"T_8583a_row3_col5\" class=\"data row3 col5\" >0</td>\n",
       "      <td id=\"T_8583a_row3_col6\" class=\"data row3 col6\" >53.100000</td>\n",
       "      <td id=\"T_8583a_row3_col7\" class=\"data row3 col7\" >S</td>\n",
       "      <td id=\"T_8583a_row3_col8\" class=\"data row3 col8\" >First</td>\n",
       "      <td id=\"T_8583a_row3_col9\" class=\"data row3 col9\" >woman</td>\n",
       "      <td id=\"T_8583a_row3_col10\" class=\"data row3 col10\" >False</td>\n",
       "      <td id=\"T_8583a_row3_col11\" class=\"data row3 col11\" >C</td>\n",
       "      <td id=\"T_8583a_row3_col12\" class=\"data row3 col12\" >Southampton</td>\n",
       "      <td id=\"T_8583a_row3_col13\" class=\"data row3 col13\" >yes</td>\n",
       "      <td id=\"T_8583a_row3_col14\" class=\"data row3 col14\" >False</td>\n",
       "      <td id=\"T_8583a_row3_col15\" class=\"data row3 col15\" >2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_8583a_level0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
       "      <td id=\"T_8583a_row4_col0\" class=\"data row4 col0\" >0</td>\n",
       "      <td id=\"T_8583a_row4_col1\" class=\"data row4 col1\" >3</td>\n",
       "      <td id=\"T_8583a_row4_col2\" class=\"data row4 col2\" >male</td>\n",
       "      <td id=\"T_8583a_row4_col3\" class=\"data row4 col3\" >35.000000</td>\n",
       "      <td id=\"T_8583a_row4_col4\" class=\"data row4 col4\" >0</td>\n",
       "      <td id=\"T_8583a_row4_col5\" class=\"data row4 col5\" >0</td>\n",
       "      <td id=\"T_8583a_row4_col6\" class=\"data row4 col6\" >8.050000</td>\n",
       "      <td id=\"T_8583a_row4_col7\" class=\"data row4 col7\" >S</td>\n",
       "      <td id=\"T_8583a_row4_col8\" class=\"data row4 col8\" >Third</td>\n",
       "      <td id=\"T_8583a_row4_col9\" class=\"data row4 col9\" >man</td>\n",
       "      <td id=\"T_8583a_row4_col10\" class=\"data row4 col10\" >True</td>\n",
       "      <td id=\"T_8583a_row4_col11\" class=\"data row4 col11\" >nan</td>\n",
       "      <td id=\"T_8583a_row4_col12\" class=\"data row4 col12\" >Southampton</td>\n",
       "      <td id=\"T_8583a_row4_col13\" class=\"data row4 col13\" >no</td>\n",
       "      <td id=\"T_8583a_row4_col14\" class=\"data row4 col14\" >True</td>\n",
       "      <td id=\"T_8583a_row4_col15\" class=\"data row4 col15\" >0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n"
      ],
      "text/plain": [
       "<pandas.io.formats.style.Styler at 0x12224baf0>"
      ]
     },
     "execution_count": 54,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df3.head().style.applymap(highlight_cols, subset=pd.IndexSlice[:, ['class', 'class_encoded']])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "774c9f93",
   "metadata": {},
   "source": [
    "## Encoding with Scikit column transformer "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b7503a34",
   "metadata": {},
   "source": [
    "Preserve Column Order after Sckit Column Transformer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "98d1df97",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.compose import ColumnTransformer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "39060faf",
   "metadata": {},
   "outputs": [],
   "source": [
    "col_transformer = ColumnTransformer([\n",
    "    ('ohe', OneHotEncoder(handle_unknown=\"ignore\"), ['embark_town','who'])],\n",
    "    remainder='passthrough',n_jobs=-1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "ab9d59f2",
   "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>ohe__embark_town_Cherbourg</th>\n",
       "      <th>ohe__embark_town_Queenstown</th>\n",
       "      <th>ohe__embark_town_Southampton</th>\n",
       "      <th>ohe__who_child</th>\n",
       "      <th>ohe__who_man</th>\n",
       "      <th>ohe__who_woman</th>\n",
       "      <th>remainder__survived</th>\n",
       "      <th>remainder__pclass</th>\n",
       "      <th>remainder__sex</th>\n",
       "      <th>remainder__age</th>\n",
       "      <th>remainder__sibsp</th>\n",
       "      <th>remainder__parch</th>\n",
       "      <th>remainder__fare</th>\n",
       "      <th>remainder__embarked</th>\n",
       "      <th>remainder__class</th>\n",
       "      <th>remainder__adult_male</th>\n",
       "      <th>remainder__deck</th>\n",
       "      <th>remainder__alive</th>\n",
       "      <th>remainder__alone</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>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7.25</td>\n",
       "      <td>2</td>\n",
       "      <td>2.0</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>no</td>\n",
       "      <td>False</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>1.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>female</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>False</td>\n",
       "      <td>C</td>\n",
       "      <td>yes</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\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>1.0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>female</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.925</td>\n",
       "      <td>2</td>\n",
       "      <td>2.0</td>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>yes</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\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>1.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>female</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53.1</td>\n",
       "      <td>2</td>\n",
       "      <td>0.0</td>\n",
       "      <td>False</td>\n",
       "      <td>C</td>\n",
       "      <td>yes</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.05</td>\n",
       "      <td>2</td>\n",
       "      <td>2.0</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>no</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  ohe__embark_town_Cherbourg ohe__embark_town_Queenstown  \\\n",
       "0                        0.0                         0.0   \n",
       "1                        1.0                         0.0   \n",
       "2                        0.0                         0.0   \n",
       "3                        0.0                         0.0   \n",
       "4                        0.0                         0.0   \n",
       "\n",
       "  ohe__embark_town_Southampton ohe__who_child ohe__who_man ohe__who_woman  \\\n",
       "0                          1.0            0.0          1.0            0.0   \n",
       "1                          0.0            0.0          0.0            1.0   \n",
       "2                          1.0            0.0          0.0            1.0   \n",
       "3                          1.0            0.0          0.0            1.0   \n",
       "4                          1.0            0.0          1.0            0.0   \n",
       "\n",
       "  remainder__survived remainder__pclass remainder__sex remainder__age  \\\n",
       "0                   0                 3           male           22.0   \n",
       "1                   1                 1         female           38.0   \n",
       "2                   1                 3         female           26.0   \n",
       "3                   1                 1         female           35.0   \n",
       "4                   0                 3           male           35.0   \n",
       "\n",
       "  remainder__sibsp remainder__parch remainder__fare remainder__embarked  \\\n",
       "0                1                0            7.25                   2   \n",
       "1                1                0         71.2833                   0   \n",
       "2                0                0           7.925                   2   \n",
       "3                1                0            53.1                   2   \n",
       "4                0                0            8.05                   2   \n",
       "\n",
       "  remainder__class remainder__adult_male remainder__deck remainder__alive  \\\n",
       "0              2.0                  True             NaN               no   \n",
       "1              0.0                 False               C              yes   \n",
       "2              2.0                 False             NaN              yes   \n",
       "3              0.0                 False               C              yes   \n",
       "4              2.0                  True             NaN               no   \n",
       "\n",
       "  remainder__alone  \n",
       "0            False  \n",
       "1            False  \n",
       "2             True  \n",
       "3            False  \n",
       "4             True  "
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.DataFrame(col_transformer.fit_transform(df2), columns=col_transformer.get_feature_names_out()).head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "edb6a2c2",
   "metadata": {},
   "source": [
    "## MakeColumnTransformer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "760b882f",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.compose import make_column_transformer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "4587f6ff",
   "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>survived</th>\n",
       "      <th>pclass</th>\n",
       "      <th>sex</th>\n",
       "      <th>age</th>\n",
       "      <th>sibsp</th>\n",
       "      <th>parch</th>\n",
       "      <th>fare</th>\n",
       "      <th>embarked</th>\n",
       "      <th>class</th>\n",
       "      <th>who</th>\n",
       "      <th>adult_male</th>\n",
       "      <th>deck</th>\n",
       "      <th>embark_town</th>\n",
       "      <th>alive</th>\n",
       "      <th>alone</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>2</td>\n",
       "      <td>2.0</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>no</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>female</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>C</td>\n",
       "      <td>Cherbourg</td>\n",
       "      <td>yes</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>female</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>2</td>\n",
       "      <td>2.0</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>yes</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>female</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>2</td>\n",
       "      <td>0.0</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>C</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>yes</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>2</td>\n",
       "      <td>2.0</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>no</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   survived  pclass     sex   age  sibsp  parch     fare  embarked  class  \\\n",
       "0         0       3    male  22.0      1      0   7.2500         2    2.0   \n",
       "1         1       1  female  38.0      1      0  71.2833         0    0.0   \n",
       "2         1       3  female  26.0      0      0   7.9250         2    2.0   \n",
       "3         1       1  female  35.0      1      0  53.1000         2    0.0   \n",
       "4         0       3    male  35.0      0      0   8.0500         2    2.0   \n",
       "\n",
       "     who  adult_male deck  embark_town alive  alone  \n",
       "0    man        True  NaN  Southampton    no  False  \n",
       "1  woman       False    C    Cherbourg   yes  False  \n",
       "2  woman       False  NaN  Southampton   yes   True  \n",
       "3  woman       False    C  Southampton   yes  False  \n",
       "4    man        True  NaN  Southampton    no   True  "
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df2.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "d00f4f71",
   "metadata": {},
   "outputs": [],
   "source": [
    "transformer = make_column_transformer(\n",
    "    (OneHotEncoder(handle_unknown = 'ignore'),['sex','embark_town']),\n",
    "    remainder = 'passthrough',n_jobs=-1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "8542807d",
   "metadata": {},
   "outputs": [],
   "source": [
    "transformed = transformer.fit_transform(df2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "f5e1b4ec",
   "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>onehotencoder__sex_female</th>\n",
       "      <th>onehotencoder__sex_male</th>\n",
       "      <th>onehotencoder__embark_town_Cherbourg</th>\n",
       "      <th>onehotencoder__embark_town_Queenstown</th>\n",
       "      <th>onehotencoder__embark_town_Southampton</th>\n",
       "      <th>remainder__survived</th>\n",
       "      <th>remainder__pclass</th>\n",
       "      <th>remainder__age</th>\n",
       "      <th>remainder__sibsp</th>\n",
       "      <th>remainder__parch</th>\n",
       "      <th>remainder__fare</th>\n",
       "      <th>remainder__embarked</th>\n",
       "      <th>remainder__class</th>\n",
       "      <th>remainder__who</th>\n",
       "      <th>remainder__adult_male</th>\n",
       "      <th>remainder__deck</th>\n",
       "      <th>remainder__alive</th>\n",
       "      <th>remainder__alone</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7.25</td>\n",
       "      <td>2</td>\n",
       "      <td>2.0</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>no</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</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>1</td>\n",
       "      <td>1</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>C</td>\n",
       "      <td>yes</td>\n",
       "      <td>False</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>1.0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.925</td>\n",
       "      <td>2</td>\n",
       "      <td>2.0</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>yes</td>\n",
       "      <td>True</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>1.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53.1</td>\n",
       "      <td>2</td>\n",
       "      <td>0.0</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>C</td>\n",
       "      <td>yes</td>\n",
       "      <td>False</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>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.05</td>\n",
       "      <td>2</td>\n",
       "      <td>2.0</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>no</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>886</th>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>27.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>13.0</td>\n",
       "      <td>2</td>\n",
       "      <td>1.0</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>no</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>887</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>19.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>30.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0.0</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>B</td>\n",
       "      <td>yes</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>888</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>23.45</td>\n",
       "      <td>2</td>\n",
       "      <td>2.0</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>no</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>889</th>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>30.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>C</td>\n",
       "      <td>yes</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>890</th>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>32.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.75</td>\n",
       "      <td>1</td>\n",
       "      <td>2.0</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>no</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>891 rows × 18 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    onehotencoder__sex_female onehotencoder__sex_male  \\\n",
       "0                         0.0                     1.0   \n",
       "1                         1.0                     0.0   \n",
       "2                         1.0                     0.0   \n",
       "3                         1.0                     0.0   \n",
       "4                         0.0                     1.0   \n",
       "..                        ...                     ...   \n",
       "886                       0.0                     1.0   \n",
       "887                       1.0                     0.0   \n",
       "888                       1.0                     0.0   \n",
       "889                       0.0                     1.0   \n",
       "890                       0.0                     1.0   \n",
       "\n",
       "    onehotencoder__embark_town_Cherbourg  \\\n",
       "0                                    0.0   \n",
       "1                                    1.0   \n",
       "2                                    0.0   \n",
       "3                                    0.0   \n",
       "4                                    0.0   \n",
       "..                                   ...   \n",
       "886                                  0.0   \n",
       "887                                  0.0   \n",
       "888                                  0.0   \n",
       "889                                  1.0   \n",
       "890                                  0.0   \n",
       "\n",
       "    onehotencoder__embark_town_Queenstown  \\\n",
       "0                                     0.0   \n",
       "1                                     0.0   \n",
       "2                                     0.0   \n",
       "3                                     0.0   \n",
       "4                                     0.0   \n",
       "..                                    ...   \n",
       "886                                   0.0   \n",
       "887                                   0.0   \n",
       "888                                   0.0   \n",
       "889                                   0.0   \n",
       "890                                   1.0   \n",
       "\n",
       "    onehotencoder__embark_town_Southampton remainder__survived  \\\n",
       "0                                      1.0                   0   \n",
       "1                                      0.0                   1   \n",
       "2                                      1.0                   1   \n",
       "3                                      1.0                   1   \n",
       "4                                      1.0                   0   \n",
       "..                                     ...                 ...   \n",
       "886                                    1.0                   0   \n",
       "887                                    1.0                   1   \n",
       "888                                    1.0                   0   \n",
       "889                                    0.0                   1   \n",
       "890                                    0.0                   0   \n",
       "\n",
       "    remainder__pclass remainder__age remainder__sibsp remainder__parch  \\\n",
       "0                   3           22.0                1                0   \n",
       "1                   1           38.0                1                0   \n",
       "2                   3           26.0                0                0   \n",
       "3                   1           35.0                1                0   \n",
       "4                   3           35.0                0                0   \n",
       "..                ...            ...              ...              ...   \n",
       "886                 2           27.0                0                0   \n",
       "887                 1           19.0                0                0   \n",
       "888                 3            NaN                1                2   \n",
       "889                 1           26.0                0                0   \n",
       "890                 3           32.0                0                0   \n",
       "\n",
       "    remainder__fare remainder__embarked remainder__class remainder__who  \\\n",
       "0              7.25                   2              2.0            man   \n",
       "1           71.2833                   0              0.0          woman   \n",
       "2             7.925                   2              2.0          woman   \n",
       "3              53.1                   2              0.0          woman   \n",
       "4              8.05                   2              2.0            man   \n",
       "..              ...                 ...              ...            ...   \n",
       "886            13.0                   2              1.0            man   \n",
       "887            30.0                   2              0.0          woman   \n",
       "888           23.45                   2              2.0          woman   \n",
       "889            30.0                   0              0.0            man   \n",
       "890            7.75                   1              2.0            man   \n",
       "\n",
       "    remainder__adult_male remainder__deck remainder__alive remainder__alone  \n",
       "0                    True             NaN               no            False  \n",
       "1                   False               C              yes            False  \n",
       "2                   False             NaN              yes             True  \n",
       "3                   False               C              yes            False  \n",
       "4                    True             NaN               no             True  \n",
       "..                    ...             ...              ...              ...  \n",
       "886                  True             NaN               no             True  \n",
       "887                 False               B              yes             True  \n",
       "888                 False             NaN               no            False  \n",
       "889                  True               C              yes             True  \n",
       "890                  True             NaN               no             True  \n",
       "\n",
       "[891 rows x 18 columns]"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.DataFrame(transformed, columns = transformer.get_feature_names_out())"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fe51d426",
   "metadata": {},
   "source": [
    "References: \n",
    "    \n",
    "1. https://stackoverflow.com/questions/68874492/preserve-column-order-after-applying-sklearn-compose-columntransformer/70526434#70526434\n",
    "2. https://towardsdatascience.com/using-columntransformer-to-combine-data-processing-steps-af383f7d5260\n",
    "3. https://pbpython.com/categorical-encoding.html\n",
    "4. https://scikit-learn.ru/example/column-transformer-with-mixed-types/\n",
    "5. https://towardsdatascience.com/categorical-feature-encoding-547707acf4e5\n",
    "6. https://sparkbyexamples.com/pandas/pandas-concat-dataframes-explained/\n",
    "7. https://stackoverflow.com/questions/54570947/feature-names-from-onehotencoder\n",
    "8. https://stackoverflow.com/questions/56338847/how-to-give-column-names-after-one-hot-encoding-with-sklearn\n",
    "9. https://stackoverflow.com/questions/56502864/using-ordinalencoder-to-transform-categorical-values\n",
    "10.https://inria.github.io/scikit-learn-mooc/python_scripts/03_categorical_pipeline.html\n",
    "11.https://towardsdatascience.com/using-columntransformer-to-combine-data-processing-steps-af383f7d5260\n",
    "12.https://bait509-ubc.github.io/BAIT509/lectures/lecture5.html\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f23e8baf",
   "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": "3.9.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}