day29-sklearn-pipelines/titanic-without-using-pipeline.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.impute import SimpleImputer\n",
    "from sklearn.preprocessing import OneHotEncoder\n",
    "from sklearn.preprocessing import MinMaxScaler\n",
    "from sklearn.tree import DecisionTreeClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv('train.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "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": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.drop(columns=['PassengerId','Name','Ticket','Cabin'],inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Survived</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>female</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>female</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>female</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Survived  Pclass     Sex   Age  SibSp  Parch     Fare Embarked\n",
       "0         0       3    male  22.0      1      0   7.2500        S\n",
       "1         1       1  female  38.0      1      0  71.2833        C\n",
       "2         1       3  female  26.0      0      0   7.9250        S\n",
       "3         1       1  female  35.0      1      0  53.1000        S\n",
       "4         0       3    male  35.0      0      0   8.0500        S"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Step 1 -> train/test/split\n",
    "X_train,X_test,y_train,y_test = train_test_split(df.drop(columns=['Survived']),\n",
    "                                                 df['Survived'],\n",
    "                                                 test_size=0.2,\n",
    "                                                random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "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>Pclass</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>331</th>\n",
       "      <td>1</td>\n",
       "      <td>male</td>\n",
       "      <td>45.5</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>28.5</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>733</th>\n",
       "      <td>2</td>\n",
       "      <td>male</td>\n",
       "      <td>23.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>13.0</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Pclass   Sex   Age  SibSp  Parch  Fare Embarked\n",
       "331       1  male  45.5      0      0  28.5        S\n",
       "733       2  male  23.0      0      0  13.0        S"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train.head(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "331    0\n",
       "733    0\n",
       "382    0\n",
       "704    0\n",
       "813    0\n",
       "Name: Survived, dtype: int64"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Survived      0\n",
       "Pclass        0\n",
       "Sex           0\n",
       "Age         177\n",
       "SibSp         0\n",
       "Parch         0\n",
       "Fare          0\n",
       "Embarked      2\n",
       "dtype: int64"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Applying imputation\n",
    "\n",
    "si_age = SimpleImputer()\n",
    "si_embarked = SimpleImputer(strategy='most_frequent')\n",
    "\n",
    "X_train_age = si_age.fit_transform(X_train[['Age']])\n",
    "X_train_embarked = si_embarked.fit_transform(X_train[['Embarked']])\n",
    "\n",
    "X_test_age = si_age.transform(X_test[['Age']])\n",
    "X_test_embarked = si_embarked.transform(X_test[['Embarked']])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {
    "collapsed": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['Q'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['C'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['C'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['C'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['C'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['C'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['C'],\n",
       "       ['C'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['Q'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['C'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['Q'],\n",
       "       ['Q'],\n",
       "       ['C'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['C'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['Q'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['Q'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['C'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['C'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['Q'],\n",
       "       ['Q'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['C'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S'],\n",
       "       ['S']], dtype=object)"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train_embarked"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [],
   "source": [
    "# one hot encoding Sex and Embarked\n",
    "\n",
    "ohe_sex = OneHotEncoder(sparse=False,handle_unknown='ignore')\n",
    "ohe_embarked = OneHotEncoder(sparse=False,handle_unknown='ignore')\n",
    "\n",
    "X_train_sex = ohe_sex.fit_transform(X_train[['Sex']])\n",
    "X_train_embarked = ohe_embarked.fit_transform(X_train_embarked)\n",
    "\n",
    "X_test_sex = ohe_sex.transform(X_test[['Sex']])\n",
    "X_test_embarked = ohe_embarked.transform(X_test_embarked)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0., 0., 1.],\n",
       "       [0., 0., 1.],\n",
       "       [0., 0., 1.],\n",
       "       ...,\n",
       "       [0., 0., 1.],\n",
       "       [0., 0., 1.],\n",
       "       [0., 0., 1.]])"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train_embarked"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "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>Pclass</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>331</th>\n",
       "      <td>1</td>\n",
       "      <td>male</td>\n",
       "      <td>45.5</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>28.5</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>733</th>\n",
       "      <td>2</td>\n",
       "      <td>male</td>\n",
       "      <td>23.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>13.0</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Pclass   Sex   Age  SibSp  Parch  Fare Embarked\n",
       "331       1  male  45.5      0      0  28.5        S\n",
       "733       2  male  23.0      0      0  13.0        S"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train.head(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train_rem = X_train.drop(columns=['Sex','Age','Embarked'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_test_rem = X_test.drop(columns=['Sex','Age','Embarked'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train_transformed = np.concatenate((X_train_rem,X_train_age,X_train_sex,X_train_embarked),axis=1)\n",
    "X_test_transformed = np.concatenate((X_test_rem,X_test_age,X_test_sex,X_test_embarked),axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(179, 10)"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_test_transformed.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DecisionTreeClassifier()"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "clf = DecisionTreeClassifier()\n",
    "clf.fit(X_train_transformed,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 1, 0, 1, 1, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0,\n",
       "       0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 1, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0,\n",
       "       0, 0, 0, 0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 0, 1, 0, 1, 1, 1, 0, 0, 1,\n",
       "       0, 0, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 0, 1, 1, 0, 0, 0, 1, 1,\n",
       "       0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 1, 0, 0, 1, 1, 0, 0, 0,\n",
       "       1, 0, 1, 1, 0, 0, 0, 0, 1, 0, 0, 1, 1, 1, 0, 0, 1, 1, 0, 0, 1, 0,\n",
       "       0, 1, 1, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 1, 1, 0, 0, 1, 0, 0,\n",
       "       0, 0, 0, 1, 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0, 0, 0,\n",
       "       0, 1, 1], dtype=int64)"
      ]
     },
     "execution_count": 54,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_pred = clf.predict(X_test_transformed)\n",
    "y_pred"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.7932960893854749"
      ]
     },
     "execution_count": 55,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.metrics import accuracy_score\n",
    "accuracy_score(y_test,y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [],
   "source": [
    "pickle.dump(ohe_sex,open('models/ohe_sex.pkl','wb'))\n",
    "pickle.dump(ohe_embarked,open('models/ohe_embarked.pkl','wb'))\n",
    "pickle.dump(clf,open('models/clf.pkl','wb'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "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": "3.8.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}