Titanic_RF.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "a2d5da36",
   "metadata": {},
   "source": [
    "# Import libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "8fe04dc2",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2786b4f0",
   "metadata": {},
   "source": [
    "# Read Datasets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "f2964910",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_train = pd.read_csv('../DataSets/Titanic_train.csv')\n",
    "df_test = pd.read_csv('../DataSets/Titanic_test.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "9f4fbc7e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "((891, 12), (418, 11))"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train.shape, df_test.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "9c3bbf7a",
   "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>PassengerId</th>\n",
       "      <th>Survived</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Name</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>Embarked</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Braund, Mr. Owen Harris</td>\n",
       "      <td>male</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>A/5 21171</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
       "      <td>female</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>PC 17599</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>C85</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Heikkinen, Miss. Laina</td>\n",
       "      <td>female</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>STON/O2. 3101282</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n",
       "      <td>female</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>113803</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>C123</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Allen, Mr. William Henry</td>\n",
       "      <td>male</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>373450</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   PassengerId  Survived  Pclass  \\\n",
       "0            1         0       3   \n",
       "1            2         1       1   \n",
       "2            3         1       3   \n",
       "3            4         1       1   \n",
       "4            5         0       3   \n",
       "\n",
       "                                                Name     Sex   Age  SibSp  \\\n",
       "0                            Braund, Mr. Owen Harris    male  22.0      1   \n",
       "1  Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0      1   \n",
       "2                             Heikkinen, Miss. Laina  female  26.0      0   \n",
       "3       Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0      1   \n",
       "4                           Allen, Mr. William Henry    male  35.0      0   \n",
       "\n",
       "   Parch            Ticket     Fare Cabin Embarked  \n",
       "0      0         A/5 21171   7.2500   NaN        S  \n",
       "1      0          PC 17599  71.2833   C85        C  \n",
       "2      0  STON/O2. 3101282   7.9250   NaN        S  \n",
       "3      0            113803  53.1000  C123        S  \n",
       "4      0            373450   8.0500   NaN        S  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "834bbd8a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 891 entries, 0 to 890\n",
      "Data columns (total 12 columns):\n",
      " #   Column       Non-Null Count  Dtype  \n",
      "---  ------       --------------  -----  \n",
      " 0   PassengerId  891 non-null    int64  \n",
      " 1   Survived     891 non-null    int64  \n",
      " 2   Pclass       891 non-null    int64  \n",
      " 3   Name         891 non-null    object \n",
      " 4   Sex          891 non-null    object \n",
      " 5   Age          714 non-null    float64\n",
      " 6   SibSp        891 non-null    int64  \n",
      " 7   Parch        891 non-null    int64  \n",
      " 8   Ticket       891 non-null    object \n",
      " 9   Fare         891 non-null    float64\n",
      " 10  Cabin        204 non-null    object \n",
      " 11  Embarked     889 non-null    object \n",
      "dtypes: float64(2), int64(5), object(5)\n",
      "memory usage: 83.7+ KB\n"
     ]
    }
   ],
   "source": [
    "df_train.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "19ecfba4",
   "metadata": {},
   "source": [
    "# Imputation - handelling missing data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "d0530941",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['PassengerId', 'Survived', 'Pclass', 'Name', 'Sex', 'Age', 'SibSp',\n",
       "       'Parch', 'Ticket', 'Fare', 'Cabin', 'Embarked'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "a6ec35ca",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['PassengerId', 'Survived', 'Pclass', 'Name', 'Sex', 'Age', 'SibSp',\n",
       "       'Parch', 'Ticket', 'Fare', 'Cabin', 'Embarked'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "6f3abcb1",
   "metadata": {},
   "outputs": [],
   "source": [
    "selected_columns = list(df_train.columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "221db529",
   "metadata": {},
   "outputs": [],
   "source": [
    "selected_columns.remove('PassengerId')\n",
    "selected_columns.remove('Name')\n",
    "selected_columns.remove('Ticket')\n",
    "selected_columns.remove('Cabin')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "514edfb2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['Survived', 'Pclass', 'Sex', 'Age', 'SibSp', 'Parch', 'Fare', 'Embarked']"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "selected_columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "a7dc459b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 891 entries, 0 to 890\n",
      "Data columns (total 8 columns):\n",
      " #   Column    Non-Null Count  Dtype  \n",
      "---  ------    --------------  -----  \n",
      " 0   Survived  891 non-null    int64  \n",
      " 1   Pclass    891 non-null    int64  \n",
      " 2   Sex       891 non-null    object \n",
      " 3   Age       714 non-null    float64\n",
      " 4   SibSp     891 non-null    int64  \n",
      " 5   Parch     891 non-null    int64  \n",
      " 6   Fare      891 non-null    float64\n",
      " 7   Embarked  889 non-null    object \n",
      "dtypes: float64(2), int64(4), object(2)\n",
      "memory usage: 55.8+ KB\n"
     ]
    }
   ],
   "source": [
    "df_train[selected_columns].info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "792d9659",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# check histogram for the columns if missing data is there\n",
    "\n",
    "df_train['Age'].hist(bins=20)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "d8314792",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(29.69911764705882, 28.0)"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# here outliers are there in \"Age\" column, so use median to replace missing data\n",
    "\n",
    "df_train['Age'].mean(), df_train['Age'].median()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "748ea275",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(177, 86)"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# check missing values for 'Age' column in train and test data\n",
    "\n",
    "df_train['Age'].isna().sum(), df_test['Age'].isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "dfc87221",
   "metadata": {},
   "outputs": [],
   "source": [
    "# fill missing values permenantly of 'Age' column by median of 'Age' column of train \n",
    "\n",
    "df_train['Age'].fillna(df_train['Age'].median(), inplace = True)\n",
    "df_test['Age'].fillna(df_train['Age'].median(), inplace = True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "5661d7b2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "S    644\n",
       "C    168\n",
       "Q     77\n",
       "Name: Embarked, dtype: int64"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# if classes are there for some column with missing values, then use .value_counts(),  don't use histograms\n",
    "\n",
    "df_train['Embarked'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "bb45be60",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(2, 0)"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train['Embarked'].isna().sum(), df_test['Embarked'].isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "f7e52c56",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'S'"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# fill missing values permenantly, if classes are there in column by mode of the same column from train data \n",
    "\n",
    "df_train['Embarked'].mode().iloc[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "4252cbbe",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_train['Embarked'].fillna(df_train['Embarked'].mode().iloc[0], inplace = True)\n",
    "df_test['Embarked'].fillna(df_train['Embarked'].mode().iloc[0], inplace = True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "fa53d667",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 891 entries, 0 to 890\n",
      "Data columns (total 8 columns):\n",
      " #   Column    Non-Null Count  Dtype  \n",
      "---  ------    --------------  -----  \n",
      " 0   Survived  891 non-null    int64  \n",
      " 1   Pclass    891 non-null    int64  \n",
      " 2   Sex       891 non-null    object \n",
      " 3   Age       891 non-null    float64\n",
      " 4   SibSp     891 non-null    int64  \n",
      " 5   Parch     891 non-null    int64  \n",
      " 6   Fare      891 non-null    float64\n",
      " 7   Embarked  891 non-null    object \n",
      "dtypes: float64(2), int64(4), object(2)\n",
      "memory usage: 55.8+ KB\n"
     ]
    }
   ],
   "source": [
    "df_train[selected_columns].info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "9db2c64e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "PassengerId      0\n",
       "Pclass           0\n",
       "Name             0\n",
       "Sex              0\n",
       "Age              0\n",
       "SibSp            0\n",
       "Parch            0\n",
       "Ticket           0\n",
       "Fare             1\n",
       "Cabin          327\n",
       "Embarked         0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_test.isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "82c5b514",
   "metadata": {},
   "outputs": [],
   "source": [
    "# handle missing values of test data also"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "31c71698",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "df_train['Fare'].hist(bins=20)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "de30168c",
   "metadata": {},
   "outputs": [],
   "source": [
    "# here outliers are there, so use median to replace missing values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "2bed6a95",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(32.2042079685746, 14.4542)"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train['Fare'].mean(), df_train['Fare'].median()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "ef25022a",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_test['Fare'].fillna(df_train['Fare'].median(), inplace = True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "078af4d6",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 418 entries, 0 to 417\n",
      "Data columns (total 11 columns):\n",
      " #   Column       Non-Null Count  Dtype  \n",
      "---  ------       --------------  -----  \n",
      " 0   PassengerId  418 non-null    int64  \n",
      " 1   Pclass       418 non-null    int64  \n",
      " 2   Name         418 non-null    object \n",
      " 3   Sex          418 non-null    object \n",
      " 4   Age          418 non-null    float64\n",
      " 5   SibSp        418 non-null    int64  \n",
      " 6   Parch        418 non-null    int64  \n",
      " 7   Ticket       418 non-null    object \n",
      " 8   Fare         418 non-null    float64\n",
      " 9   Cabin        91 non-null     object \n",
      " 10  Embarked     418 non-null    object \n",
      "dtypes: float64(2), int64(4), object(5)\n",
      "memory usage: 36.0+ KB\n"
     ]
    }
   ],
   "source": [
    "df_test.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "20e743ae",
   "metadata": {},
   "source": [
    "# Feature Encoding"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "15324a55",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 891 entries, 0 to 890\n",
      "Data columns (total 8 columns):\n",
      " #   Column    Non-Null Count  Dtype  \n",
      "---  ------    --------------  -----  \n",
      " 0   Survived  891 non-null    int64  \n",
      " 1   Pclass    891 non-null    int64  \n",
      " 2   Sex       891 non-null    object \n",
      " 3   Age       891 non-null    float64\n",
      " 4   SibSp     891 non-null    int64  \n",
      " 5   Parch     891 non-null    int64  \n",
      " 6   Fare      891 non-null    float64\n",
      " 7   Embarked  891 non-null    object \n",
      "dtypes: float64(2), int64(4), object(2)\n",
      "memory usage: 55.8+ KB\n"
     ]
    }
   ],
   "source": [
    "df_train[selected_columns].info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "d32eb0cc",
   "metadata": {},
   "outputs": [],
   "source": [
    "# do encoding for train and test data also\n",
    "\n",
    "# do encoding for the columns with datatype as object"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "c039b218",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Encoding of 'Age' column"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "26f912c2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "male      577\n",
       "female    314\n",
       "Name: Sex, dtype: int64"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train['Sex'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "72950c0a",
   "metadata": {},
   "outputs": [],
   "source": [
    "# As in 'Sex' coulmn only 2 classes are there, so we can do direct encoding"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "3e454d3c",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_train['Encod_Sex'] = df_train['Sex'].apply(lambda X:0 if X=='male' else 1)\n",
    "df_test['Encod_Sex'] = df_test['Sex'].apply(lambda X:0 if X=='male' else 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "9396725c",
   "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>PassengerId</th>\n",
       "      <th>Survived</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Name</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>Encod_Sex</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Braund, Mr. Owen Harris</td>\n",
       "      <td>male</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>A/5 21171</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
       "      <td>female</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>PC 17599</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>C85</td>\n",
       "      <td>C</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Heikkinen, Miss. Laina</td>\n",
       "      <td>female</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>STON/O2. 3101282</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n",
       "      <td>female</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>113803</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>C123</td>\n",
       "      <td>S</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Allen, Mr. William Henry</td>\n",
       "      <td>male</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>373450</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   PassengerId  Survived  Pclass  \\\n",
       "0            1         0       3   \n",
       "1            2         1       1   \n",
       "2            3         1       3   \n",
       "3            4         1       1   \n",
       "4            5         0       3   \n",
       "\n",
       "                                                Name     Sex   Age  SibSp  \\\n",
       "0                            Braund, Mr. Owen Harris    male  22.0      1   \n",
       "1  Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0      1   \n",
       "2                             Heikkinen, Miss. Laina  female  26.0      0   \n",
       "3       Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0      1   \n",
       "4                           Allen, Mr. William Henry    male  35.0      0   \n",
       "\n",
       "   Parch            Ticket     Fare Cabin Embarked  Encod_Sex  \n",
       "0      0         A/5 21171   7.2500   NaN        S          0  \n",
       "1      0          PC 17599  71.2833   C85        C          1  \n",
       "2      0  STON/O2. 3101282   7.9250   NaN        S          1  \n",
       "3      0            113803  53.1000  C123        S          1  \n",
       "4      0            373450   8.0500   NaN        S          0  "
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "912bd1e2",
   "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>PassengerId</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Name</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>Encod_Sex</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>892</td>\n",
       "      <td>3</td>\n",
       "      <td>Kelly, Mr. James</td>\n",
       "      <td>male</td>\n",
       "      <td>34.5</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>330911</td>\n",
       "      <td>7.8292</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Q</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>893</td>\n",
       "      <td>3</td>\n",
       "      <td>Wilkes, Mrs. James (Ellen Needs)</td>\n",
       "      <td>female</td>\n",
       "      <td>47.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>363272</td>\n",
       "      <td>7.0000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>894</td>\n",
       "      <td>2</td>\n",
       "      <td>Myles, Mr. Thomas Francis</td>\n",
       "      <td>male</td>\n",
       "      <td>62.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>240276</td>\n",
       "      <td>9.6875</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Q</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>895</td>\n",
       "      <td>3</td>\n",
       "      <td>Wirz, Mr. Albert</td>\n",
       "      <td>male</td>\n",
       "      <td>27.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>315154</td>\n",
       "      <td>8.6625</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>896</td>\n",
       "      <td>3</td>\n",
       "      <td>Hirvonen, Mrs. Alexander (Helga E Lindqvist)</td>\n",
       "      <td>female</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3101298</td>\n",
       "      <td>12.2875</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   PassengerId  Pclass                                          Name     Sex  \\\n",
       "0          892       3                              Kelly, Mr. James    male   \n",
       "1          893       3              Wilkes, Mrs. James (Ellen Needs)  female   \n",
       "2          894       2                     Myles, Mr. Thomas Francis    male   \n",
       "3          895       3                              Wirz, Mr. Albert    male   \n",
       "4          896       3  Hirvonen, Mrs. Alexander (Helga E Lindqvist)  female   \n",
       "\n",
       "    Age  SibSp  Parch   Ticket     Fare Cabin Embarked  Encod_Sex  \n",
       "0  34.5      0      0   330911   7.8292   NaN        Q          0  \n",
       "1  47.0      1      0   363272   7.0000   NaN        S          1  \n",
       "2  62.0      0      0   240276   9.6875   NaN        Q          0  \n",
       "3  27.0      0      0   315154   8.6625   NaN        S          0  \n",
       "4  22.0      1      1  3101298  12.2875   NaN        S          1  "
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_test.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "deeb70e5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['Survived', 'Pclass', 'Sex', 'Age', 'SibSp', 'Parch', 'Fare', 'Embarked']"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "selected_columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "75e55ac2",
   "metadata": {},
   "outputs": [],
   "source": [
    "selected_columns.append('Encod_Sex')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "09702144",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['Survived',\n",
       " 'Pclass',\n",
       " 'Sex',\n",
       " 'Age',\n",
       " 'SibSp',\n",
       " 'Parch',\n",
       " 'Fare',\n",
       " 'Embarked',\n",
       " 'Encod_Sex']"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "selected_columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "423d6789",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Encoding of 'Embarked' column"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "2208e207",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "S    646\n",
       "C    168\n",
       "Q     77\n",
       "Name: Embarked, dtype: int64"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train['Embarked'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "ca001972",
   "metadata": {},
   "outputs": [],
   "source": [
    "# need to do one-hot encoding, as number of classes are more than 2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "e1e0a2cd",
   "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>C</th>\n",
       "      <th>Q</th>\n",
       "      <th>S</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\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>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>886</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>887</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>888</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>889</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>890</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>891 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     C  Q  S\n",
       "0    0  0  1\n",
       "1    1  0  0\n",
       "2    0  0  1\n",
       "3    0  0  1\n",
       "4    0  0  1\n",
       "..  .. .. ..\n",
       "886  0  0  1\n",
       "887  0  0  1\n",
       "888  0  0  1\n",
       "889  1  0  0\n",
       "890  0  1  0\n",
       "\n",
       "[891 rows x 3 columns]"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.get_dummies(df_train['Embarked'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "8bb97bd4",
   "metadata": {},
   "outputs": [],
   "source": [
    "temp = pd.get_dummies(df_train['Embarked'])\n",
    "\n",
    "df_train = pd.concat([df_train, temp], axis=1)\n",
    "\n",
    "temp1 = pd.get_dummies(df_test['Embarked'])\n",
    "df_test = pd.concat([df_test, temp1], axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "d395534d",
   "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>PassengerId</th>\n",
       "      <th>Survived</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Name</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>Encod_Sex</th>\n",
       "      <th>C</th>\n",
       "      <th>Q</th>\n",
       "      <th>S</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Braund, Mr. Owen Harris</td>\n",
       "      <td>male</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>A/5 21171</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
       "      <td>female</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>PC 17599</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>C85</td>\n",
       "      <td>C</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Heikkinen, Miss. Laina</td>\n",
       "      <td>female</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>STON/O2. 3101282</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</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>4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n",
       "      <td>female</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>113803</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>C123</td>\n",
       "      <td>S</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Allen, Mr. William Henry</td>\n",
       "      <td>male</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>373450</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   PassengerId  Survived  Pclass  \\\n",
       "0            1         0       3   \n",
       "1            2         1       1   \n",
       "2            3         1       3   \n",
       "3            4         1       1   \n",
       "4            5         0       3   \n",
       "\n",
       "                                                Name     Sex   Age  SibSp  \\\n",
       "0                            Braund, Mr. Owen Harris    male  22.0      1   \n",
       "1  Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0      1   \n",
       "2                             Heikkinen, Miss. Laina  female  26.0      0   \n",
       "3       Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0      1   \n",
       "4                           Allen, Mr. William Henry    male  35.0      0   \n",
       "\n",
       "   Parch            Ticket     Fare Cabin Embarked  Encod_Sex  C  Q  S  \n",
       "0      0         A/5 21171   7.2500   NaN        S          0  0  0  1  \n",
       "1      0          PC 17599  71.2833   C85        C          1  1  0  0  \n",
       "2      0  STON/O2. 3101282   7.9250   NaN        S          1  0  0  1  \n",
       "3      0            113803  53.1000  C123        S          1  0  0  1  \n",
       "4      0            373450   8.0500   NaN        S          0  0  0  1  "
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "e40a5fd1",
   "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>PassengerId</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Name</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>Encod_Sex</th>\n",
       "      <th>C</th>\n",
       "      <th>Q</th>\n",
       "      <th>S</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>892</td>\n",
       "      <td>3</td>\n",
       "      <td>Kelly, Mr. James</td>\n",
       "      <td>male</td>\n",
       "      <td>34.5</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>330911</td>\n",
       "      <td>7.8292</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Q</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>893</td>\n",
       "      <td>3</td>\n",
       "      <td>Wilkes, Mrs. James (Ellen Needs)</td>\n",
       "      <td>female</td>\n",
       "      <td>47.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>363272</td>\n",
       "      <td>7.0000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>894</td>\n",
       "      <td>2</td>\n",
       "      <td>Myles, Mr. Thomas Francis</td>\n",
       "      <td>male</td>\n",
       "      <td>62.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>240276</td>\n",
       "      <td>9.6875</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Q</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>895</td>\n",
       "      <td>3</td>\n",
       "      <td>Wirz, Mr. Albert</td>\n",
       "      <td>male</td>\n",
       "      <td>27.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>315154</td>\n",
       "      <td>8.6625</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>896</td>\n",
       "      <td>3</td>\n",
       "      <td>Hirvonen, Mrs. Alexander (Helga E Lindqvist)</td>\n",
       "      <td>female</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3101298</td>\n",
       "      <td>12.2875</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</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": [
       "   PassengerId  Pclass                                          Name     Sex  \\\n",
       "0          892       3                              Kelly, Mr. James    male   \n",
       "1          893       3              Wilkes, Mrs. James (Ellen Needs)  female   \n",
       "2          894       2                     Myles, Mr. Thomas Francis    male   \n",
       "3          895       3                              Wirz, Mr. Albert    male   \n",
       "4          896       3  Hirvonen, Mrs. Alexander (Helga E Lindqvist)  female   \n",
       "\n",
       "    Age  SibSp  Parch   Ticket     Fare Cabin Embarked  Encod_Sex  C  Q  S  \n",
       "0  34.5      0      0   330911   7.8292   NaN        Q          0  0  1  0  \n",
       "1  47.0      1      0   363272   7.0000   NaN        S          1  0  0  1  \n",
       "2  62.0      0      0   240276   9.6875   NaN        Q          0  0  1  0  \n",
       "3  27.0      0      0   315154   8.6625   NaN        S          0  0  0  1  \n",
       "4  22.0      1      1  3101298  12.2875   NaN        S          1  0  0  1  "
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_test.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "5c931fe6",
   "metadata": {},
   "outputs": [],
   "source": [
    "selected_columns.extend(temp.columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "f560b882",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['Survived',\n",
       " 'Pclass',\n",
       " 'Sex',\n",
       " 'Age',\n",
       " 'SibSp',\n",
       " 'Parch',\n",
       " 'Fare',\n",
       " 'Embarked',\n",
       " 'Encod_Sex',\n",
       " 'C',\n",
       " 'Q',\n",
       " 'S']"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "selected_columns"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d2d3ccea",
   "metadata": {},
   "source": [
    "# Feature Selection"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "3c5a20ae",
   "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>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Encod_Sex</th>\n",
       "      <th>C</th>\n",
       "      <th>Q</th>\n",
       "      <th>S</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Survived</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.338481</td>\n",
       "      <td>-0.064910</td>\n",
       "      <td>-0.035322</td>\n",
       "      <td>0.081629</td>\n",
       "      <td>0.257307</td>\n",
       "      <td>0.543351</td>\n",
       "      <td>0.168240</td>\n",
       "      <td>0.003650</td>\n",
       "      <td>-0.149683</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Pclass</th>\n",
       "      <td>-0.338481</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.339898</td>\n",
       "      <td>0.083081</td>\n",
       "      <td>0.018443</td>\n",
       "      <td>-0.549500</td>\n",
       "      <td>-0.131900</td>\n",
       "      <td>-0.243292</td>\n",
       "      <td>0.221009</td>\n",
       "      <td>0.074053</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Age</th>\n",
       "      <td>-0.064910</td>\n",
       "      <td>-0.339898</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.233296</td>\n",
       "      <td>-0.172482</td>\n",
       "      <td>0.096688</td>\n",
       "      <td>-0.081163</td>\n",
       "      <td>0.030248</td>\n",
       "      <td>-0.031415</td>\n",
       "      <td>-0.006729</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>SibSp</th>\n",
       "      <td>-0.035322</td>\n",
       "      <td>0.083081</td>\n",
       "      <td>-0.233296</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.414838</td>\n",
       "      <td>0.159651</td>\n",
       "      <td>0.114631</td>\n",
       "      <td>-0.059528</td>\n",
       "      <td>-0.026354</td>\n",
       "      <td>0.068734</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Parch</th>\n",
       "      <td>0.081629</td>\n",
       "      <td>0.018443</td>\n",
       "      <td>-0.172482</td>\n",
       "      <td>0.414838</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.216225</td>\n",
       "      <td>0.245489</td>\n",
       "      <td>-0.011069</td>\n",
       "      <td>-0.081228</td>\n",
       "      <td>0.060814</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Fare</th>\n",
       "      <td>0.257307</td>\n",
       "      <td>-0.549500</td>\n",
       "      <td>0.096688</td>\n",
       "      <td>0.159651</td>\n",
       "      <td>0.216225</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.182333</td>\n",
       "      <td>0.269335</td>\n",
       "      <td>-0.117216</td>\n",
       "      <td>-0.162184</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Encod_Sex</th>\n",
       "      <td>0.543351</td>\n",
       "      <td>-0.131900</td>\n",
       "      <td>-0.081163</td>\n",
       "      <td>0.114631</td>\n",
       "      <td>0.245489</td>\n",
       "      <td>0.182333</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.082853</td>\n",
       "      <td>0.074115</td>\n",
       "      <td>-0.119224</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>C</th>\n",
       "      <td>0.168240</td>\n",
       "      <td>-0.243292</td>\n",
       "      <td>0.030248</td>\n",
       "      <td>-0.059528</td>\n",
       "      <td>-0.011069</td>\n",
       "      <td>0.269335</td>\n",
       "      <td>0.082853</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.148258</td>\n",
       "      <td>-0.782742</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Q</th>\n",
       "      <td>0.003650</td>\n",
       "      <td>0.221009</td>\n",
       "      <td>-0.031415</td>\n",
       "      <td>-0.026354</td>\n",
       "      <td>-0.081228</td>\n",
       "      <td>-0.117216</td>\n",
       "      <td>0.074115</td>\n",
       "      <td>-0.148258</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.499421</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>S</th>\n",
       "      <td>-0.149683</td>\n",
       "      <td>0.074053</td>\n",
       "      <td>-0.006729</td>\n",
       "      <td>0.068734</td>\n",
       "      <td>0.060814</td>\n",
       "      <td>-0.162184</td>\n",
       "      <td>-0.119224</td>\n",
       "      <td>-0.782742</td>\n",
       "      <td>-0.499421</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           Survived    Pclass       Age     SibSp     Parch      Fare  \\\n",
       "Survived   1.000000 -0.338481 -0.064910 -0.035322  0.081629  0.257307   \n",
       "Pclass    -0.338481  1.000000 -0.339898  0.083081  0.018443 -0.549500   \n",
       "Age       -0.064910 -0.339898  1.000000 -0.233296 -0.172482  0.096688   \n",
       "SibSp     -0.035322  0.083081 -0.233296  1.000000  0.414838  0.159651   \n",
       "Parch      0.081629  0.018443 -0.172482  0.414838  1.000000  0.216225   \n",
       "Fare       0.257307 -0.549500  0.096688  0.159651  0.216225  1.000000   \n",
       "Encod_Sex  0.543351 -0.131900 -0.081163  0.114631  0.245489  0.182333   \n",
       "C          0.168240 -0.243292  0.030248 -0.059528 -0.011069  0.269335   \n",
       "Q          0.003650  0.221009 -0.031415 -0.026354 -0.081228 -0.117216   \n",
       "S         -0.149683  0.074053 -0.006729  0.068734  0.060814 -0.162184   \n",
       "\n",
       "           Encod_Sex         C         Q         S  \n",
       "Survived    0.543351  0.168240  0.003650 -0.149683  \n",
       "Pclass     -0.131900 -0.243292  0.221009  0.074053  \n",
       "Age        -0.081163  0.030248 -0.031415 -0.006729  \n",
       "SibSp       0.114631 -0.059528 -0.026354  0.068734  \n",
       "Parch       0.245489 -0.011069 -0.081228  0.060814  \n",
       "Fare        0.182333  0.269335 -0.117216 -0.162184  \n",
       "Encod_Sex   1.000000  0.082853  0.074115 -0.119224  \n",
       "C           0.082853  1.000000 -0.148258 -0.782742  \n",
       "Q           0.074115 -0.148258  1.000000 -0.499421  \n",
       "S          -0.119224 -0.782742 -0.499421  1.000000  "
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train[selected_columns].corr()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "96357d31",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Survived     1.000000\n",
       "Pclass      -0.338481\n",
       "Age         -0.064910\n",
       "SibSp       -0.035322\n",
       "Parch        0.081629\n",
       "Fare         0.257307\n",
       "Encod_Sex    0.543351\n",
       "C            0.168240\n",
       "Q            0.003650\n",
       "S           -0.149683\n",
       "Name: Survived, dtype: float64"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train[selected_columns].corr()['Survived']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "086acb8e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# if number of columns are in 100's, then column may be delete/drop whoes correlation is very less (<0.1)\n",
    "\n",
    "# here number of columns are very less so all columns we will selecte"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "id": "09f108ba",
   "metadata": {},
   "outputs": [],
   "source": [
    "selected_columns.remove('Survived')\n",
    "selected_columns.remove('Sex')\n",
    "selected_columns.remove('Embarked')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "id": "9f1458af",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['Pclass', 'Age', 'SibSp', 'Parch', 'Fare', 'Encod_Sex', 'C', 'Q', 'S']"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "selected_columns"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e81484cc",
   "metadata": {},
   "source": [
    "# import algorithm - RF"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "b0d42282",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.ensemble import RandomForestClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "id": "017914e0",
   "metadata": {},
   "outputs": [],
   "source": [
    "model = RandomForestClassifier(random_state=66)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "id": "df3f2421",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RandomForestClassifier(random_state=66)"
      ]
     },
     "execution_count": 55,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.fit(df_train[selected_columns], df_train['Survived'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "id": "f9b83e3f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9797979797979798"
      ]
     },
     "execution_count": 56,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.score(df_train[selected_columns], df_train['Survived'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "id": "1d63f041",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_pred = model.predict(df_test[selected_columns])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "id": "f0cfba56",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 1, 1, 0, 1, 0, 1, 1, 1,\n",
       "       1, 0, 1, 0, 1, 1, 1, 0, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 1,\n",
       "       1, 0, 0, 0, 1, 1, 1, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 1,\n",
       "       1, 0, 0, 1, 1, 0, 0, 0, 1, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0,\n",
       "       1, 1, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0,\n",
       "       0, 1, 1, 1, 1, 0, 0, 1, 0, 1, 1, 0, 1, 0, 0, 1, 0, 1, 0, 0, 1, 0,\n",
       "       0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 1, 0, 1, 0, 0, 1,\n",
       "       0, 0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1,\n",
       "       1, 1, 1, 1, 0, 0, 1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0,\n",
       "       0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0,\n",
       "       1, 0, 1, 1, 1, 0, 0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 1, 1, 1, 1, 1, 1,\n",
       "       0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1,\n",
       "       0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0,\n",
       "       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1,\n",
       "       0, 0, 0, 1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0,\n",
       "       1, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 1, 0,\n",
       "       0, 0, 1, 0, 1, 0, 0, 1, 0, 1, 1, 1, 1, 0, 0, 0, 1, 1, 0, 1, 0, 0,\n",
       "       1, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1,\n",
       "       0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 1, 0, 0, 1],\n",
       "      dtype=int64)"
      ]
     },
     "execution_count": 58,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_pred"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "id": "107c7dbd",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_test['Survived'] = y_pred"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "id": "2218dcf5",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_test[['PassengerId', 'Survived']].to_csv('../DataSets/Titanic_gender_submission1.csv', index = False)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "12810436",
   "metadata": {},
   "source": [
    "# Hyperparameter tuning "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "id": "8827d646",
   "metadata": {},
   "outputs": [],
   "source": [
    "# using GridSearchCV"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "id": "78f02a48",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import GridSearchCV"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "id": "f88577f7",
   "metadata": {},
   "outputs": [],
   "source": [
    "dict1 = {'criterion':[\"gini\", \"entropy\"],\n",
    "         'n_estimators':[20, 40, 60, 80, 100],\n",
    "         'max_depth':[2,3,4,5,6],\n",
    "         'min_samples_split':[3,4,5,6,7],\n",
    "         'min_samples_leaf':[2,3,4,5,6],\n",
    "        }"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "id": "eb4daa5f",
   "metadata": {},
   "outputs": [],
   "source": [
    "grid_cv = GridSearchCV(RandomForestClassifier(), dict1, cv=5, n_jobs=-1, verbose=3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "id": "988c7d3c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Fitting 5 folds for each of 1250 candidates, totalling 6250 fits\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "GridSearchCV(cv=5, estimator=RandomForestClassifier(), n_jobs=-1,\n",
       "             param_grid={'criterion': ['gini', 'entropy'],\n",
       "                         'max_depth': [2, 3, 4, 5, 6],\n",
       "                         'min_samples_leaf': [2, 3, 4, 5, 6],\n",
       "                         'min_samples_split': [3, 4, 5, 6, 7],\n",
       "                         'n_estimators': [20, 40, 60, 80, 100]},\n",
       "             verbose=3)"
      ]
     },
     "execution_count": 65,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grid_cv.fit(df_train[selected_columns], df_train['Survived'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "id": "5d86435d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RandomForestClassifier(criterion='entropy', max_depth=4, min_samples_leaf=6,\n",
       "                       min_samples_split=3, n_estimators=80)"
      ]
     },
     "execution_count": 66,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grid_cv.best_estimator_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "id": "bc790c9c",
   "metadata": {},
   "outputs": [],
   "source": [
    "model_1 = RandomForestClassifier(criterion='entropy', max_depth=4, min_samples_leaf=6, min_samples_split=3, n_estimators=80, random_state=66)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "id": "63d843e7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RandomForestClassifier(criterion='entropy', max_depth=4, min_samples_leaf=6,\n",
       "                       min_samples_split=3, n_estimators=80, random_state=66)"
      ]
     },
     "execution_count": 69,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model_1.fit(df_train[selected_columns], df_train['Survived'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "id": "e4579b2c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8439955106621774"
      ]
     },
     "execution_count": 70,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model_1.score(df_train[selected_columns], df_train['Survived'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "id": "176cce5b",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_pred = model_1.predict(df_test[selected_columns])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "id": "802efa04",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0,\n",
       "       1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1,\n",
       "       1, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 1,\n",
       "       1, 0, 0, 1, 1, 0, 0, 0, 1, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0,\n",
       "       1, 1, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0,\n",
       "       0, 1, 1, 1, 1, 0, 0, 1, 0, 1, 1, 0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 0,\n",
       "       0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0,\n",
       "       0, 0, 1, 1, 0, 0, 1, 1, 1, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1,\n",
       "       1, 0, 1, 1, 0, 0, 1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0,\n",
       "       0, 0, 1, 1, 0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 0, 1, 0, 0, 1, 0, 1, 0,\n",
       "       1, 0, 1, 0, 1, 1, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1,\n",
       "       0, 0, 0, 0, 1, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1,\n",
       "       0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 0,\n",
       "       0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0,\n",
       "       0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0,\n",
       "       1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 1, 0,\n",
       "       0, 0, 1, 0, 1, 0, 0, 1, 0, 1, 1, 0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0,\n",
       "       1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1,\n",
       "       0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 1, 0, 0, 0],\n",
       "      dtype=int64)"
      ]
     },
     "execution_count": 72,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_pred"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "id": "be2e732d",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_test['Survived'] = y_pred"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "id": "18c53bf2",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_test[['PassengerId', 'Survived']].to_csv('../DataSets/Titanic_gender_submission2.csv', index = False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "id": "789ff819",
   "metadata": {},
   "outputs": [],
   "source": [
    "# RandomizedSearchCV"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "id": "9478156b",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import RandomizedSearchCV"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "id": "b9c6af4f",
   "metadata": {},
   "outputs": [],
   "source": [
    "randser_cv = RandomizedSearchCV(RandomForestClassifier(), dict1, cv=5, n_jobs=-1, verbose=3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "id": "491be292",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Fitting 5 folds for each of 10 candidates, totalling 50 fits\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "RandomizedSearchCV(cv=5, estimator=RandomForestClassifier(), n_jobs=-1,\n",
       "                   param_distributions={'criterion': ['gini', 'entropy'],\n",
       "                                        'max_depth': [2, 3, 4, 5, 6],\n",
       "                                        'min_samples_leaf': [2, 3, 4, 5, 6],\n",
       "                                        'min_samples_split': [3, 4, 5, 6, 7],\n",
       "                                        'n_estimators': [20, 40, 60, 80, 100]},\n",
       "                   verbose=3)"
      ]
     },
     "execution_count": 78,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "randser_cv.fit(df_train[selected_columns], df_train['Survived'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "id": "9a031be2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RandomForestClassifier(max_depth=5, min_samples_leaf=4, min_samples_split=7,\n",
       "                       n_estimators=80)"
      ]
     },
     "execution_count": 79,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "randser_cv.best_estimator_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "id": "b5ab4f31",
   "metadata": {},
   "outputs": [],
   "source": [
    "model_2 = RandomForestClassifier(max_depth=5, min_samples_leaf=4, min_samples_split=7, n_estimators=80, random_state=66)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "id": "036b4d63",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RandomForestClassifier(max_depth=5, min_samples_leaf=4, min_samples_split=7,\n",
       "                       n_estimators=80, random_state=66)"
      ]
     },
     "execution_count": 81,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model_2.fit(df_train[selected_columns], df_train['Survived'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "id": "28b987ce",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8518518518518519"
      ]
     },
     "execution_count": 82,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model_2.score(df_train[selected_columns], df_train['Survived'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "id": "61187099",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_pred = model_2.predict(df_test[selected_columns])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "id": "dadc7caa",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0,\n",
       "       1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1,\n",
       "       1, 0, 0, 0, 1, 1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 1,\n",
       "       1, 0, 0, 1, 1, 0, 0, 0, 1, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0,\n",
       "       1, 1, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0,\n",
       "       0, 1, 1, 1, 1, 0, 0, 1, 0, 1, 1, 0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 0,\n",
       "       0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1,\n",
       "       0, 0, 1, 0, 0, 1, 1, 1, 1, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1,\n",
       "       1, 0, 1, 1, 0, 0, 1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 1,\n",
       "       0, 0, 1, 1, 0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 0, 1, 0, 0, 1, 0, 1, 0,\n",
       "       1, 0, 1, 0, 1, 1, 0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 1, 1, 1, 1,\n",
       "       0, 0, 0, 0, 1, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1,\n",
       "       0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 0,\n",
       "       0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1,\n",
       "       0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0,\n",
       "       1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 1, 1, 0,\n",
       "       0, 0, 1, 0, 1, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0,\n",
       "       1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1,\n",
       "       0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 1, 0, 0, 0],\n",
       "      dtype=int64)"
      ]
     },
     "execution_count": 84,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_pred"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "id": "f2c82f6d",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_test['Survived'] = y_pred"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "id": "60fdb7b6",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_test[['PassengerId', 'Survived']].to_csv('../DataSets/Titanic_gender_submission3.csv', index=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "661e1245",
   "metadata": {},
   "source": [
    "# Feature Creation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "id": "9ecc1bce",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0                                Braund, Mr. Owen Harris\n",
       "1      Cumings, Mrs. John Bradley (Florence Briggs Th...\n",
       "2                                 Heikkinen, Miss. Laina\n",
       "3           Futrelle, Mrs. Jacques Heath (Lily May Peel)\n",
       "4                               Allen, Mr. William Henry\n",
       "                             ...                        \n",
       "886                                Montvila, Rev. Juozas\n",
       "887                         Graham, Miss. Margaret Edith\n",
       "888             Johnston, Miss. Catherine Helen \"Carrie\"\n",
       "889                                Behr, Mr. Karl Howell\n",
       "890                                  Dooley, Mr. Patrick\n",
       "Name: Name, Length: 891, dtype: object"
      ]
     },
     "execution_count": 87,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# feature creation of 'Name' column\n",
    "\n",
    "df_train['Name']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "id": "c5f2dd15",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0        Mr\n",
       "1       Mrs\n",
       "2      Miss\n",
       "3       Mrs\n",
       "4        Mr\n",
       "       ... \n",
       "886     Rev\n",
       "887    Miss\n",
       "888    Miss\n",
       "889      Mr\n",
       "890      Mr\n",
       "Name: Name, Length: 891, dtype: object"
      ]
     },
     "execution_count": 88,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# str1 = 'Braund, Mr. Own Harris'\n",
    "# str1.split(',')[1].split('.')[0].lstrip()\n",
    "\n",
    "df_train['Name'].apply(lambda X: X.split(',')[1].split('.')[0].lstrip())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "id": "adafcd95",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0          Mr\n",
       "1         Mrs\n",
       "2          Mr\n",
       "3          Mr\n",
       "4         Mrs\n",
       "        ...  \n",
       "413        Mr\n",
       "414      Dona\n",
       "415        Mr\n",
       "416        Mr\n",
       "417    Master\n",
       "Name: Name, Length: 418, dtype: object"
      ]
     },
     "execution_count": 89,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_test['Name'].apply(lambda X: X.split(',')[1].split('.')[0].lstrip())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "id": "6633ddb4",
   "metadata": {},
   "outputs": [],
   "source": [
    "name_titles = df_train['Name'].apply(lambda X: X.split(',')[1].split('.')[0].lstrip())\n",
    "name_titles_1 = df_test['Name'].apply(lambda X: X.split(',')[1].split('.')[0].lstrip())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "id": "e9c6422f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Mr              517\n",
       "Miss            182\n",
       "Mrs             125\n",
       "Master           40\n",
       "Dr                7\n",
       "Rev               6\n",
       "Mlle              2\n",
       "Major             2\n",
       "Col               2\n",
       "Don               1\n",
       "Sir               1\n",
       "Jonkheer          1\n",
       "the Countess      1\n",
       "Mme               1\n",
       "Lady              1\n",
       "Capt              1\n",
       "Ms                1\n",
       "Name: Name, dtype: int64"
      ]
     },
     "execution_count": 91,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "name_titles.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "id": "a64bc172",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Mr        240\n",
       "Miss       78\n",
       "Mrs        72\n",
       "Master     21\n",
       "Col         2\n",
       "Rev         2\n",
       "Dona        1\n",
       "Dr          1\n",
       "Ms          1\n",
       "Name: Name, dtype: int64"
      ]
     },
     "execution_count": 92,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "name_titles_1.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "id": "5aae70f5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Mr        517\n",
       "Miss      182\n",
       "Mrs       125\n",
       "Master     40\n",
       "Name: Name, dtype: int64"
      ]
     },
     "execution_count": 93,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "name_titles.value_counts()[:4]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "id": "2ad42e22",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Mr        240\n",
       "Miss       78\n",
       "Mrs        72\n",
       "Master     21\n",
       "Name: Name, dtype: int64"
      ]
     },
     "execution_count": 94,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "name_titles_1.value_counts()[:4]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "id": "0cde3f03",
   "metadata": {},
   "outputs": [],
   "source": [
    "titles = list(name_titles.value_counts()[:4].index)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "id": "ee492e6c",
   "metadata": {},
   "outputs": [],
   "source": [
    "titles_1 = list(name_titles_1.value_counts()[:4].index)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "id": "cc585a33",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_train['Title'] = ['other' if not title in titles else title for title in name_titles]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 98,
   "id": "408329e5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Mr        517\n",
       "Miss      182\n",
       "Mrs       125\n",
       "Master     40\n",
       "other      27\n",
       "Name: Title, dtype: int64"
      ]
     },
     "execution_count": 98,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train['Title'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 99,
   "id": "b1df5e31",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_test['Title'] = ['other' if not title in titles_1 else title for title in name_titles_1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "id": "b1a264f8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Mr        240\n",
       "Miss       78\n",
       "Mrs        72\n",
       "Master     21\n",
       "other       7\n",
       "Name: Title, dtype: int64"
      ]
     },
     "execution_count": 100,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_test['Title'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 101,
   "id": "09f08e0c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Title\n",
       "Master    0.575000\n",
       "Miss      0.697802\n",
       "Mr        0.156673\n",
       "Mrs       0.792000\n",
       "other     0.444444\n",
       "Name: Survived, dtype: float64"
      ]
     },
     "execution_count": 101,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train.groupby('Title').mean()['Survived']\n",
    "\n",
    "# here judge the data which gives more information"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 102,
   "id": "abd332f6",
   "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>Master</th>\n",
       "      <th>Miss</th>\n",
       "      <th>Mr</th>\n",
       "      <th>Mrs</th>\n",
       "      <th>other</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\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>1</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\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>...</th>\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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>887</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>888</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>889</th>\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>890</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>891 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Master  Miss  Mr  Mrs  other\n",
       "0         0     0   1    0      0\n",
       "1         0     0   0    1      0\n",
       "2         0     1   0    0      0\n",
       "3         0     0   0    1      0\n",
       "4         0     0   1    0      0\n",
       "..      ...   ...  ..  ...    ...\n",
       "886       0     0   0    0      1\n",
       "887       0     1   0    0      0\n",
       "888       0     1   0    0      0\n",
       "889       0     0   1    0      0\n",
       "890       0     0   1    0      0\n",
       "\n",
       "[891 rows x 5 columns]"
      ]
     },
     "execution_count": 102,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.get_dummies(df_train['Title'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "id": "9ba6027d",
   "metadata": {},
   "outputs": [],
   "source": [
    "temp = pd.get_dummies(df_train['Title'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 104,
   "id": "d619c566",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_train = pd.concat([df_train, temp], axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "id": "6afd7aa2",
   "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>PassengerId</th>\n",
       "      <th>Survived</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Name</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>...</th>\n",
       "      <th>Encod_Sex</th>\n",
       "      <th>C</th>\n",
       "      <th>Q</th>\n",
       "      <th>S</th>\n",
       "      <th>Title</th>\n",
       "      <th>Master</th>\n",
       "      <th>Miss</th>\n",
       "      <th>Mr</th>\n",
       "      <th>Mrs</th>\n",
       "      <th>other</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Braund, Mr. Owen Harris</td>\n",
       "      <td>male</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>A/5 21171</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>Mr</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>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
       "      <td>female</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>PC 17599</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Mrs</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Heikkinen, Miss. Laina</td>\n",
       "      <td>female</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>STON/O2. 3101282</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>Miss</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n",
       "      <td>female</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>113803</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>Mrs</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Allen, Mr. William Henry</td>\n",
       "      <td>male</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>373450</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>Mr</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 22 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   PassengerId  Survived  Pclass  \\\n",
       "0            1         0       3   \n",
       "1            2         1       1   \n",
       "2            3         1       3   \n",
       "3            4         1       1   \n",
       "4            5         0       3   \n",
       "\n",
       "                                                Name     Sex   Age  SibSp  \\\n",
       "0                            Braund, Mr. Owen Harris    male  22.0      1   \n",
       "1  Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0      1   \n",
       "2                             Heikkinen, Miss. Laina  female  26.0      0   \n",
       "3       Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0      1   \n",
       "4                           Allen, Mr. William Henry    male  35.0      0   \n",
       "\n",
       "   Parch            Ticket     Fare  ... Encod_Sex  C  Q  S  Title  Master  \\\n",
       "0      0         A/5 21171   7.2500  ...         0  0  0  1     Mr       0   \n",
       "1      0          PC 17599  71.2833  ...         1  1  0  0    Mrs       0   \n",
       "2      0  STON/O2. 3101282   7.9250  ...         1  0  0  1   Miss       0   \n",
       "3      0            113803  53.1000  ...         1  0  0  1    Mrs       0   \n",
       "4      0            373450   8.0500  ...         0  0  0  1     Mr       0   \n",
       "\n",
       "  Miss  Mr  Mrs  other  \n",
       "0    0   1    0      0  \n",
       "1    0   0    1      0  \n",
       "2    1   0    0      0  \n",
       "3    0   0    1      0  \n",
       "4    0   1    0      0  \n",
       "\n",
       "[5 rows x 22 columns]"
      ]
     },
     "execution_count": 105,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 106,
   "id": "cf4ff3f6",
   "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>Master</th>\n",
       "      <th>Miss</th>\n",
       "      <th>Mr</th>\n",
       "      <th>Mrs</th>\n",
       "      <th>other</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\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>1</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\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>3</th>\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>4</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>413</th>\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>414</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>415</th>\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>416</th>\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>417</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>418 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Master  Miss  Mr  Mrs  other\n",
       "0         0     0   1    0      0\n",
       "1         0     0   0    1      0\n",
       "2         0     0   1    0      0\n",
       "3         0     0   1    0      0\n",
       "4         0     0   0    1      0\n",
       "..      ...   ...  ..  ...    ...\n",
       "413       0     0   1    0      0\n",
       "414       0     0   0    0      1\n",
       "415       0     0   1    0      0\n",
       "416       0     0   1    0      0\n",
       "417       1     0   0    0      0\n",
       "\n",
       "[418 rows x 5 columns]"
      ]
     },
     "execution_count": 106,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.get_dummies(df_test['Title'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 107,
   "id": "4f08c895",
   "metadata": {},
   "outputs": [],
   "source": [
    "temp1 = pd.get_dummies(df_test['Title'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 108,
   "id": "64386351",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_test = pd.concat([df_test, temp1], axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 109,
   "id": "b047c7cc",
   "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>PassengerId</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Name</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>...</th>\n",
       "      <th>C</th>\n",
       "      <th>Q</th>\n",
       "      <th>S</th>\n",
       "      <th>Survived</th>\n",
       "      <th>Title</th>\n",
       "      <th>Master</th>\n",
       "      <th>Miss</th>\n",
       "      <th>Mr</th>\n",
       "      <th>Mrs</th>\n",
       "      <th>other</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>892</td>\n",
       "      <td>3</td>\n",
       "      <td>Kelly, Mr. James</td>\n",
       "      <td>male</td>\n",
       "      <td>34.5</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>330911</td>\n",
       "      <td>7.8292</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Mr</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>1</th>\n",
       "      <td>893</td>\n",
       "      <td>3</td>\n",
       "      <td>Wilkes, Mrs. James (Ellen Needs)</td>\n",
       "      <td>female</td>\n",
       "      <td>47.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>363272</td>\n",
       "      <td>7.0000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Mrs</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>894</td>\n",
       "      <td>2</td>\n",
       "      <td>Myles, Mr. Thomas Francis</td>\n",
       "      <td>male</td>\n",
       "      <td>62.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>240276</td>\n",
       "      <td>9.6875</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Mr</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>3</th>\n",
       "      <td>895</td>\n",
       "      <td>3</td>\n",
       "      <td>Wirz, Mr. Albert</td>\n",
       "      <td>male</td>\n",
       "      <td>27.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>315154</td>\n",
       "      <td>8.6625</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Mr</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>4</th>\n",
       "      <td>896</td>\n",
       "      <td>3</td>\n",
       "      <td>Hirvonen, Mrs. Alexander (Helga E Lindqvist)</td>\n",
       "      <td>female</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3101298</td>\n",
       "      <td>12.2875</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Mrs</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 22 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   PassengerId  Pclass                                          Name     Sex  \\\n",
       "0          892       3                              Kelly, Mr. James    male   \n",
       "1          893       3              Wilkes, Mrs. James (Ellen Needs)  female   \n",
       "2          894       2                     Myles, Mr. Thomas Francis    male   \n",
       "3          895       3                              Wirz, Mr. Albert    male   \n",
       "4          896       3  Hirvonen, Mrs. Alexander (Helga E Lindqvist)  female   \n",
       "\n",
       "    Age  SibSp  Parch   Ticket     Fare Cabin  ...  C  Q  S  Survived  Title  \\\n",
       "0  34.5      0      0   330911   7.8292   NaN  ...  0  1  0         0     Mr   \n",
       "1  47.0      1      0   363272   7.0000   NaN  ...  0  0  1         0    Mrs   \n",
       "2  62.0      0      0   240276   9.6875   NaN  ...  0  1  0         0     Mr   \n",
       "3  27.0      0      0   315154   8.6625   NaN  ...  0  0  1         0     Mr   \n",
       "4  22.0      1      1  3101298  12.2875   NaN  ...  0  0  1         1    Mrs   \n",
       "\n",
       "   Master Miss  Mr  Mrs  other  \n",
       "0       0    0   1    0      0  \n",
       "1       0    0   0    1      0  \n",
       "2       0    0   1    0      0  \n",
       "3       0    0   1    0      0  \n",
       "4       0    0   0    1      0  \n",
       "\n",
       "[5 rows x 22 columns]"
      ]
     },
     "execution_count": 109,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_test.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 110,
   "id": "ec54d62b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 891 entries, 0 to 890\n",
      "Data columns (total 22 columns):\n",
      " #   Column       Non-Null Count  Dtype  \n",
      "---  ------       --------------  -----  \n",
      " 0   PassengerId  891 non-null    int64  \n",
      " 1   Survived     891 non-null    int64  \n",
      " 2   Pclass       891 non-null    int64  \n",
      " 3   Name         891 non-null    object \n",
      " 4   Sex          891 non-null    object \n",
      " 5   Age          891 non-null    float64\n",
      " 6   SibSp        891 non-null    int64  \n",
      " 7   Parch        891 non-null    int64  \n",
      " 8   Ticket       891 non-null    object \n",
      " 9   Fare         891 non-null    float64\n",
      " 10  Cabin        204 non-null    object \n",
      " 11  Embarked     891 non-null    object \n",
      " 12  Encod_Sex    891 non-null    int64  \n",
      " 13  C            891 non-null    uint8  \n",
      " 14  Q            891 non-null    uint8  \n",
      " 15  S            891 non-null    uint8  \n",
      " 16  Title        891 non-null    object \n",
      " 17  Master       891 non-null    uint8  \n",
      " 18  Miss         891 non-null    uint8  \n",
      " 19  Mr           891 non-null    uint8  \n",
      " 20  Mrs          891 non-null    uint8  \n",
      " 21  other        891 non-null    uint8  \n",
      "dtypes: float64(2), int64(6), object(6), uint8(8)\n",
      "memory usage: 104.5+ KB\n"
     ]
    }
   ],
   "source": [
    "df_train.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 111,
   "id": "22e194be",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 418 entries, 0 to 417\n",
      "Data columns (total 22 columns):\n",
      " #   Column       Non-Null Count  Dtype  \n",
      "---  ------       --------------  -----  \n",
      " 0   PassengerId  418 non-null    int64  \n",
      " 1   Pclass       418 non-null    int64  \n",
      " 2   Name         418 non-null    object \n",
      " 3   Sex          418 non-null    object \n",
      " 4   Age          418 non-null    float64\n",
      " 5   SibSp        418 non-null    int64  \n",
      " 6   Parch        418 non-null    int64  \n",
      " 7   Ticket       418 non-null    object \n",
      " 8   Fare         418 non-null    float64\n",
      " 9   Cabin        91 non-null     object \n",
      " 10  Embarked     418 non-null    object \n",
      " 11  Encod_Sex    418 non-null    int64  \n",
      " 12  C            418 non-null    uint8  \n",
      " 13  Q            418 non-null    uint8  \n",
      " 14  S            418 non-null    uint8  \n",
      " 15  Survived     418 non-null    int64  \n",
      " 16  Title        418 non-null    object \n",
      " 17  Master       418 non-null    uint8  \n",
      " 18  Miss         418 non-null    uint8  \n",
      " 19  Mr           418 non-null    uint8  \n",
      " 20  Mrs          418 non-null    uint8  \n",
      " 21  other        418 non-null    uint8  \n",
      "dtypes: float64(2), int64(6), object(6), uint8(8)\n",
      "memory usage: 49.1+ KB\n"
     ]
    }
   ],
   "source": [
    "df_test.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 112,
   "id": "bf009952",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['Pclass', 'Age', 'SibSp', 'Parch', 'Fare', 'Encod_Sex', 'C', 'Q', 'S']"
      ]
     },
     "execution_count": 112,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "selected_columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 113,
   "id": "00c89085",
   "metadata": {},
   "outputs": [],
   "source": [
    "selected_columns.extend(temp.columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 114,
   "id": "f4341718",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['Pclass',\n",
       " 'Age',\n",
       " 'SibSp',\n",
       " 'Parch',\n",
       " 'Fare',\n",
       " 'Encod_Sex',\n",
       " 'C',\n",
       " 'Q',\n",
       " 'S',\n",
       " 'Master',\n",
       " 'Miss',\n",
       " 'Mr',\n",
       " 'Mrs',\n",
       " 'other']"
      ]
     },
     "execution_count": 114,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "selected_columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 115,
   "id": "b250f88c",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Feature creation of 'Age' column\n",
    "\n",
    "df_train['Age_Group'] = ['child' if i<25 else 'young' if i<55 else 'old' for i in df_train['Age']]\n",
    "df_test['Age_Group'] = ['child' if i<25 else 'young' if i<55 else 'old' for i in df_test['Age']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 116,
   "id": "520771f6",
   "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>Age</th>\n",
       "      <th>Age_Group</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>22.0</td>\n",
       "      <td>child</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>38.0</td>\n",
       "      <td>young</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>26.0</td>\n",
       "      <td>young</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>35.0</td>\n",
       "      <td>young</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>35.0</td>\n",
       "      <td>young</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>886</th>\n",
       "      <td>27.0</td>\n",
       "      <td>young</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>887</th>\n",
       "      <td>19.0</td>\n",
       "      <td>child</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>888</th>\n",
       "      <td>28.0</td>\n",
       "      <td>young</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>889</th>\n",
       "      <td>26.0</td>\n",
       "      <td>young</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>890</th>\n",
       "      <td>32.0</td>\n",
       "      <td>young</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>891 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      Age Age_Group\n",
       "0    22.0     child\n",
       "1    38.0     young\n",
       "2    26.0     young\n",
       "3    35.0     young\n",
       "4    35.0     young\n",
       "..    ...       ...\n",
       "886  27.0     young\n",
       "887  19.0     child\n",
       "888  28.0     young\n",
       "889  26.0     young\n",
       "890  32.0     young\n",
       "\n",
       "[891 rows x 2 columns]"
      ]
     },
     "execution_count": 116,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train[['Age', 'Age_Group']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 117,
   "id": "fc6abc09",
   "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>Age</th>\n",
       "      <th>Age_Group</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>34.5</td>\n",
       "      <td>young</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>47.0</td>\n",
       "      <td>young</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>62.0</td>\n",
       "      <td>old</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>27.0</td>\n",
       "      <td>young</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>22.0</td>\n",
       "      <td>child</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>413</th>\n",
       "      <td>28.0</td>\n",
       "      <td>young</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>414</th>\n",
       "      <td>39.0</td>\n",
       "      <td>young</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>415</th>\n",
       "      <td>38.5</td>\n",
       "      <td>young</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>416</th>\n",
       "      <td>28.0</td>\n",
       "      <td>young</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>417</th>\n",
       "      <td>28.0</td>\n",
       "      <td>young</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>418 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      Age Age_Group\n",
       "0    34.5     young\n",
       "1    47.0     young\n",
       "2    62.0       old\n",
       "3    27.0     young\n",
       "4    22.0     child\n",
       "..    ...       ...\n",
       "413  28.0     young\n",
       "414  39.0     young\n",
       "415  38.5     young\n",
       "416  28.0     young\n",
       "417  28.0     young\n",
       "\n",
       "[418 rows x 2 columns]"
      ]
     },
     "execution_count": 117,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_test[['Age', 'Age_Group']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 118,
   "id": "cff3ddc8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Age_Group\n",
       "child    0.424460\n",
       "old      0.309524\n",
       "young    0.369527\n",
       "Name: Survived, dtype: float64"
      ]
     },
     "execution_count": 118,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train.groupby('Age_Group').mean()['Survived']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 119,
   "id": "db5ee250",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Age_Group\n",
       "child    0.404580\n",
       "old      0.480000\n",
       "young    0.263359\n",
       "Name: Survived, dtype: float64"
      ]
     },
     "execution_count": 119,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_test.groupby('Age_Group').mean()['Survived']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 120,
   "id": "4e33bd52",
   "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>child</th>\n",
       "      <th>old</th>\n",
       "      <th>young</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>886</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>887</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>888</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>889</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>890</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>891 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     child  old  young\n",
       "0        1    0      0\n",
       "1        0    0      1\n",
       "2        0    0      1\n",
       "3        0    0      1\n",
       "4        0    0      1\n",
       "..     ...  ...    ...\n",
       "886      0    0      1\n",
       "887      1    0      0\n",
       "888      0    0      1\n",
       "889      0    0      1\n",
       "890      0    0      1\n",
       "\n",
       "[891 rows x 3 columns]"
      ]
     },
     "execution_count": 120,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.get_dummies(df_train['Age_Group'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 121,
   "id": "67e1db63",
   "metadata": {},
   "outputs": [],
   "source": [
    "temp = pd.get_dummies(df_train['Age_Group'])\n",
    "\n",
    "df_train = pd.concat([df_train, temp], axis=1)\n",
    "\n",
    "temp1 = pd.get_dummies(df_test['Age_Group'])\n",
    "df_test = pd.concat([df_test, temp1], axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 122,
   "id": "a04475fa",
   "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>PassengerId</th>\n",
       "      <th>Survived</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Name</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>...</th>\n",
       "      <th>Title</th>\n",
       "      <th>Master</th>\n",
       "      <th>Miss</th>\n",
       "      <th>Mr</th>\n",
       "      <th>Mrs</th>\n",
       "      <th>other</th>\n",
       "      <th>Age_Group</th>\n",
       "      <th>child</th>\n",
       "      <th>old</th>\n",
       "      <th>young</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Braund, Mr. Owen Harris</td>\n",
       "      <td>male</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>A/5 21171</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>...</td>\n",
       "      <td>Mr</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>child</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
       "      <td>female</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>PC 17599</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>...</td>\n",
       "      <td>Mrs</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>young</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Heikkinen, Miss. Laina</td>\n",
       "      <td>female</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>STON/O2. 3101282</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>...</td>\n",
       "      <td>Miss</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>young</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n",
       "      <td>female</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>113803</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>...</td>\n",
       "      <td>Mrs</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>young</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Allen, Mr. William Henry</td>\n",
       "      <td>male</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>373450</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>...</td>\n",
       "      <td>Mr</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>young</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 26 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   PassengerId  Survived  Pclass  \\\n",
       "0            1         0       3   \n",
       "1            2         1       1   \n",
       "2            3         1       3   \n",
       "3            4         1       1   \n",
       "4            5         0       3   \n",
       "\n",
       "                                                Name     Sex   Age  SibSp  \\\n",
       "0                            Braund, Mr. Owen Harris    male  22.0      1   \n",
       "1  Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0      1   \n",
       "2                             Heikkinen, Miss. Laina  female  26.0      0   \n",
       "3       Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0      1   \n",
       "4                           Allen, Mr. William Henry    male  35.0      0   \n",
       "\n",
       "   Parch            Ticket     Fare  ... Title Master  Miss  Mr  Mrs  other  \\\n",
       "0      0         A/5 21171   7.2500  ...    Mr      0     0   1    0      0   \n",
       "1      0          PC 17599  71.2833  ...   Mrs      0     0   0    1      0   \n",
       "2      0  STON/O2. 3101282   7.9250  ...  Miss      0     1   0    0      0   \n",
       "3      0            113803  53.1000  ...   Mrs      0     0   0    1      0   \n",
       "4      0            373450   8.0500  ...    Mr      0     0   1    0      0   \n",
       "\n",
       "  Age_Group  child  old  young  \n",
       "0     child      1    0      0  \n",
       "1     young      0    0      1  \n",
       "2     young      0    0      1  \n",
       "3     young      0    0      1  \n",
       "4     young      0    0      1  \n",
       "\n",
       "[5 rows x 26 columns]"
      ]
     },
     "execution_count": 122,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 123,
   "id": "cba8e517",
   "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>PassengerId</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Name</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>...</th>\n",
       "      <th>Title</th>\n",
       "      <th>Master</th>\n",
       "      <th>Miss</th>\n",
       "      <th>Mr</th>\n",
       "      <th>Mrs</th>\n",
       "      <th>other</th>\n",
       "      <th>Age_Group</th>\n",
       "      <th>child</th>\n",
       "      <th>old</th>\n",
       "      <th>young</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>892</td>\n",
       "      <td>3</td>\n",
       "      <td>Kelly, Mr. James</td>\n",
       "      <td>male</td>\n",
       "      <td>34.5</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>330911</td>\n",
       "      <td>7.8292</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>Mr</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>young</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>893</td>\n",
       "      <td>3</td>\n",
       "      <td>Wilkes, Mrs. James (Ellen Needs)</td>\n",
       "      <td>female</td>\n",
       "      <td>47.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>363272</td>\n",
       "      <td>7.0000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>Mrs</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>young</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>894</td>\n",
       "      <td>2</td>\n",
       "      <td>Myles, Mr. Thomas Francis</td>\n",
       "      <td>male</td>\n",
       "      <td>62.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>240276</td>\n",
       "      <td>9.6875</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>Mr</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>old</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>895</td>\n",
       "      <td>3</td>\n",
       "      <td>Wirz, Mr. Albert</td>\n",
       "      <td>male</td>\n",
       "      <td>27.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>315154</td>\n",
       "      <td>8.6625</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>Mr</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>young</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>896</td>\n",
       "      <td>3</td>\n",
       "      <td>Hirvonen, Mrs. Alexander (Helga E Lindqvist)</td>\n",
       "      <td>female</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3101298</td>\n",
       "      <td>12.2875</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>Mrs</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>child</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 26 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   PassengerId  Pclass                                          Name     Sex  \\\n",
       "0          892       3                              Kelly, Mr. James    male   \n",
       "1          893       3              Wilkes, Mrs. James (Ellen Needs)  female   \n",
       "2          894       2                     Myles, Mr. Thomas Francis    male   \n",
       "3          895       3                              Wirz, Mr. Albert    male   \n",
       "4          896       3  Hirvonen, Mrs. Alexander (Helga E Lindqvist)  female   \n",
       "\n",
       "    Age  SibSp  Parch   Ticket     Fare Cabin  ... Title  Master  Miss  Mr  \\\n",
       "0  34.5      0      0   330911   7.8292   NaN  ...    Mr       0     0   1   \n",
       "1  47.0      1      0   363272   7.0000   NaN  ...   Mrs       0     0   0   \n",
       "2  62.0      0      0   240276   9.6875   NaN  ...    Mr       0     0   1   \n",
       "3  27.0      0      0   315154   8.6625   NaN  ...    Mr       0     0   1   \n",
       "4  22.0      1      1  3101298  12.2875   NaN  ...   Mrs       0     0   0   \n",
       "\n",
       "   Mrs  other Age_Group  child  old  young  \n",
       "0    0      0     young      0    0      1  \n",
       "1    1      0     young      0    0      1  \n",
       "2    0      0       old      0    1      0  \n",
       "3    0      0     young      0    0      1  \n",
       "4    1      0     child      1    0      0  \n",
       "\n",
       "[5 rows x 26 columns]"
      ]
     },
     "execution_count": 123,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_test.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 124,
   "id": "697a0d3b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['Pclass',\n",
       " 'Age',\n",
       " 'SibSp',\n",
       " 'Parch',\n",
       " 'Fare',\n",
       " 'Encod_Sex',\n",
       " 'C',\n",
       " 'Q',\n",
       " 'S',\n",
       " 'Master',\n",
       " 'Miss',\n",
       " 'Mr',\n",
       " 'Mrs',\n",
       " 'other']"
      ]
     },
     "execution_count": 124,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "selected_columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 125,
   "id": "8c0c9633",
   "metadata": {},
   "outputs": [],
   "source": [
    "selected_columns.extend(temp.columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 126,
   "id": "161e7271",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['Pclass',\n",
       " 'Age',\n",
       " 'SibSp',\n",
       " 'Parch',\n",
       " 'Fare',\n",
       " 'Encod_Sex',\n",
       " 'C',\n",
       " 'Q',\n",
       " 'S',\n",
       " 'Master',\n",
       " 'Miss',\n",
       " 'Mr',\n",
       " 'Mrs',\n",
       " 'other',\n",
       " 'child',\n",
       " 'old',\n",
       " 'young']"
      ]
     },
     "execution_count": 126,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "selected_columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b31f69c4",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "id": "fa0ec888",
   "metadata": {},
   "source": [
    "# Hyperparameter tuning_1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 127,
   "id": "5baefdeb",
   "metadata": {},
   "outputs": [],
   "source": [
    "# using GridSearchCV"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 128,
   "id": "df052450",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import GridSearchCV"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 129,
   "id": "cf4d0755",
   "metadata": {},
   "outputs": [],
   "source": [
    "grid_cv = GridSearchCV(RandomForestClassifier(), dict1, cv=5, n_jobs=-1, verbose=3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 130,
   "id": "f05dc64a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Fitting 5 folds for each of 1250 candidates, totalling 6250 fits\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "GridSearchCV(cv=5, estimator=RandomForestClassifier(), n_jobs=-1,\n",
       "             param_grid={'criterion': ['gini', 'entropy'],\n",
       "                         'max_depth': [2, 3, 4, 5, 6],\n",
       "                         'min_samples_leaf': [2, 3, 4, 5, 6],\n",
       "                         'min_samples_split': [3, 4, 5, 6, 7],\n",
       "                         'n_estimators': [20, 40, 60, 80, 100]},\n",
       "             verbose=3)"
      ]
     },
     "execution_count": 130,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grid_cv.fit(df_train[selected_columns], df_train['Survived'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 131,
   "id": "742275aa",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RandomForestClassifier(max_depth=6, min_samples_leaf=2, min_samples_split=4,\n",
       "                       n_estimators=40)"
      ]
     },
     "execution_count": 131,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grid_cv.best_estimator_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 132,
   "id": "6247c4a0",
   "metadata": {},
   "outputs": [],
   "source": [
    "model_1 = RandomForestClassifier(max_depth=6, min_samples_leaf=2, min_samples_split=4, n_estimators=40, random_state=66)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 133,
   "id": "ec102c20",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RandomForestClassifier(max_depth=6, min_samples_leaf=2, min_samples_split=4,\n",
       "                       n_estimators=40, random_state=66)"
      ]
     },
     "execution_count": 133,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model_1.fit(df_train[selected_columns], df_train['Survived'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 134,
   "id": "99f589dc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.867564534231201"
      ]
     },
     "execution_count": 134,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model_1.score(df_train[selected_columns], df_train['Survived'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 135,
   "id": "9b9b9c1b",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_pred = model_1.predict(df_test[selected_columns])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 136,
   "id": "bdfb779a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 0, 0, 1, 0, 1, 1, 0, 0, 0, 1, 0, 1,\n",
       "       1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1,\n",
       "       1, 0, 0, 0, 1, 1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 1,\n",
       "       1, 0, 0, 1, 1, 0, 0, 0, 1, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 1, 1,\n",
       "       1, 1, 1, 0, 1, 0, 0, 0, 1, 0, 1, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0,\n",
       "       0, 1, 1, 1, 1, 0, 0, 1, 0, 1, 1, 0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 0,\n",
       "       0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1,\n",
       "       0, 0, 1, 1, 0, 1, 1, 1, 1, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1,\n",
       "       1, 0, 1, 1, 0, 0, 1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 1,\n",
       "       0, 1, 1, 1, 1, 1, 0, 0, 1, 0, 1, 0, 0, 0, 0, 1, 0, 0, 1, 0, 1, 0,\n",
       "       1, 0, 1, 0, 1, 1, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1,\n",
       "       0, 0, 1, 0, 1, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1,\n",
       "       0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 0,\n",
       "       0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1,\n",
       "       0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0,\n",
       "       1, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 1, 0, 1, 0, 1, 1, 0,\n",
       "       0, 0, 1, 0, 1, 0, 0, 1, 0, 1, 1, 0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0,\n",
       "       1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1,\n",
       "       0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 1, 0, 0, 1],\n",
       "      dtype=int64)"
      ]
     },
     "execution_count": 136,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_pred"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 137,
   "id": "a21df55e",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_test['Survived'] = y_pred"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 138,
   "id": "efd8dcac",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_test[['PassengerId', 'Survived']].to_csv('../DataSets/Titanic_gender_submission4.csv', index = False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 139,
   "id": "b9ac695a",
   "metadata": {},
   "outputs": [],
   "source": [
    "# using RandomizedSearchCV"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 140,
   "id": "a0c3d3d6",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import RandomizedSearchCV"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 141,
   "id": "369a9d6d",
   "metadata": {},
   "outputs": [],
   "source": [
    "randsearch_cv = RandomizedSearchCV(RandomForestClassifier(), dict1, cv=5, n_jobs=-1, verbose=3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 142,
   "id": "97eb906a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Fitting 5 folds for each of 10 candidates, totalling 50 fits\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "RandomizedSearchCV(cv=5, estimator=RandomForestClassifier(), n_jobs=-1,\n",
       "                   param_distributions={'criterion': ['gini', 'entropy'],\n",
       "                                        'max_depth': [2, 3, 4, 5, 6],\n",
       "                                        'min_samples_leaf': [2, 3, 4, 5, 6],\n",
       "                                        'min_samples_split': [3, 4, 5, 6, 7],\n",
       "                                        'n_estimators': [20, 40, 60, 80, 100]},\n",
       "                   verbose=3)"
      ]
     },
     "execution_count": 142,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "randsearch_cv.fit(df_train[selected_columns], df_train['Survived'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 143,
   "id": "5f051b54",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RandomForestClassifier(max_depth=6, min_samples_leaf=2, min_samples_split=4,\n",
       "                       n_estimators=40)"
      ]
     },
     "execution_count": 143,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "randsearch_cv.best_estimator_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 144,
   "id": "18f92dac",
   "metadata": {},
   "outputs": [],
   "source": [
    "model_2 = RandomForestClassifier(max_depth=6, min_samples_leaf=2, min_samples_split=4, n_estimators=40, random_state=66)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 145,
   "id": "360ca494",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_pred = model_2.predict(df_test[selected_columns])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 146,
   "id": "506a030d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 0, 0, 1, 0, 1, 1, 0, 0, 0, 1, 0, 1,\n",
       "       1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1,\n",
       "       1, 0, 0, 0, 1, 1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 1,\n",
       "       1, 0, 0, 1, 1, 0, 0, 0, 1, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 1, 1,\n",
       "       1, 1, 1, 0, 1, 0, 0, 0, 1, 0, 1, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0,\n",
       "       0, 1, 1, 1, 1, 0, 0, 1, 0, 1, 1, 0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 0,\n",
       "       0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1,\n",
       "       0, 0, 1, 1, 0, 1, 1, 1, 1, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1,\n",
       "       1, 0, 1, 1, 0, 0, 1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 1,\n",
       "       0, 1, 1, 1, 1, 1, 0, 0, 1, 0, 1, 0, 0, 0, 0, 1, 0, 0, 1, 0, 1, 0,\n",
       "       1, 0, 1, 0, 1, 1, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1,\n",
       "       0, 0, 1, 0, 1, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1,\n",
       "       0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 0,\n",
       "       0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1,\n",
       "       0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0,\n",
       "       1, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 1, 0, 1, 0, 1, 1, 0,\n",
       "       0, 0, 1, 0, 1, 0, 0, 1, 0, 1, 1, 0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0,\n",
       "       1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1,\n",
       "       0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 1, 0, 0, 1],\n",
       "      dtype=int64)"
      ]
     },
     "execution_count": 146,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_pred"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 147,
   "id": "f3979a60",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_test['Survived'] = y_pred"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 148,
   "id": "3a8a98ba",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_test[['PassengerId', 'Survived']].to_csv('../DataSets/Titanic_gender_submission5.csv', index = False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a5fd270f",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}