ML1.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "%matplotlib inline\n",
    "import warnings\n",
    "warnings.filterwarnings('ignore')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "train = pd.read_csv(\"C:/Users/DELL/Desktop/pandas/titanic/train.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "test = pd.read_csv(\"C:/Users/DELL/Desktop/pandas/titanic/test.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "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>count</th>\n",
       "      <td>891.000000</td>\n",
       "      <td>891.000000</td>\n",
       "      <td>891.000000</td>\n",
       "      <td>891</td>\n",
       "      <td>891</td>\n",
       "      <td>714.000000</td>\n",
       "      <td>891.000000</td>\n",
       "      <td>891.000000</td>\n",
       "      <td>891</td>\n",
       "      <td>891.000000</td>\n",
       "      <td>204</td>\n",
       "      <td>889</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>unique</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>891</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>681</td>\n",
       "      <td>NaN</td>\n",
       "      <td>147</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>top</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Johansson, Mr. Karl Johan</td>\n",
       "      <td>male</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>347082</td>\n",
       "      <td>NaN</td>\n",
       "      <td>B96 B98</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>freq</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "      <td>577</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>7</td>\n",
       "      <td>NaN</td>\n",
       "      <td>4</td>\n",
       "      <td>644</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>446.000000</td>\n",
       "      <td>0.383838</td>\n",
       "      <td>2.308642</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>29.699118</td>\n",
       "      <td>0.523008</td>\n",
       "      <td>0.381594</td>\n",
       "      <td>NaN</td>\n",
       "      <td>32.204208</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>257.353842</td>\n",
       "      <td>0.486592</td>\n",
       "      <td>0.836071</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>14.526497</td>\n",
       "      <td>1.102743</td>\n",
       "      <td>0.806057</td>\n",
       "      <td>NaN</td>\n",
       "      <td>49.693429</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.420000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>223.500000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>20.125000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>7.910400</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>446.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>28.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>14.454200</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>668.500000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>38.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>31.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>891.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>80.000000</td>\n",
       "      <td>8.000000</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>512.329200</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        PassengerId    Survived      Pclass                       Name   Sex  \\\n",
       "count    891.000000  891.000000  891.000000                        891   891   \n",
       "unique          NaN         NaN         NaN                        891     2   \n",
       "top             NaN         NaN         NaN  Johansson, Mr. Karl Johan  male   \n",
       "freq            NaN         NaN         NaN                          1   577   \n",
       "mean     446.000000    0.383838    2.308642                        NaN   NaN   \n",
       "std      257.353842    0.486592    0.836071                        NaN   NaN   \n",
       "min        1.000000    0.000000    1.000000                        NaN   NaN   \n",
       "25%      223.500000    0.000000    2.000000                        NaN   NaN   \n",
       "50%      446.000000    0.000000    3.000000                        NaN   NaN   \n",
       "75%      668.500000    1.000000    3.000000                        NaN   NaN   \n",
       "max      891.000000    1.000000    3.000000                        NaN   NaN   \n",
       "\n",
       "               Age       SibSp       Parch  Ticket        Fare    Cabin  \\\n",
       "count   714.000000  891.000000  891.000000     891  891.000000      204   \n",
       "unique         NaN         NaN         NaN     681         NaN      147   \n",
       "top            NaN         NaN         NaN  347082         NaN  B96 B98   \n",
       "freq           NaN         NaN         NaN       7         NaN        4   \n",
       "mean     29.699118    0.523008    0.381594     NaN   32.204208      NaN   \n",
       "std      14.526497    1.102743    0.806057     NaN   49.693429      NaN   \n",
       "min       0.420000    0.000000    0.000000     NaN    0.000000      NaN   \n",
       "25%      20.125000    0.000000    0.000000     NaN    7.910400      NaN   \n",
       "50%      28.000000    0.000000    0.000000     NaN   14.454200      NaN   \n",
       "75%      38.000000    1.000000    0.000000     NaN   31.000000      NaN   \n",
       "max      80.000000    8.000000    6.000000     NaN  512.329200      NaN   \n",
       "\n",
       "       Embarked  \n",
       "count       889  \n",
       "unique        3  \n",
       "top           S  \n",
       "freq        644  \n",
       "mean        NaN  \n",
       "std         NaN  \n",
       "min         NaN  \n",
       "25%         NaN  \n",
       "50%         NaN  \n",
       "75%         NaN  \n",
       "max         NaN  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train.describe(include='all')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>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",
       "    </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",
       "    </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",
       "    </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",
       "    </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",
       "    </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",
       "    </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  \n",
       "0  34.5      0      0   330911   7.8292   NaN        Q  \n",
       "1  47.0      1      0   363272   7.0000   NaN        S  \n",
       "2  62.0      0      0   240276   9.6875   NaN        Q  \n",
       "3  27.0      0      0   315154   8.6625   NaN        S  \n",
       "4  22.0      1      1  3101298  12.2875   NaN        S  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "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": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Index(['PassengerId', 'Survived', 'Pclass', 'Name', 'Sex', 'Age', 'SibSp',\n",
      "       'Parch', 'Ticket', 'Fare', 'Cabin', 'Embarked'],\n",
      "      dtype='object')\n"
     ]
    }
   ],
   "source": [
    "print(train.columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "PassengerId      0\n",
      "Survived         0\n",
      "Pclass           0\n",
      "Name             0\n",
      "Sex              0\n",
      "Age            177\n",
      "SibSp            0\n",
      "Parch            0\n",
      "Ticket           0\n",
      "Fare             0\n",
      "Cabin          687\n",
      "Embarked         2\n",
      "dtype: int64\n"
     ]
    }
   ],
   "source": [
    "print(pd.isnull(train).sum())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Total</th>\n",
       "      <th>%</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Cabin</th>\n",
       "      <td>687</td>\n",
       "      <td>77.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Age</th>\n",
       "      <td>177</td>\n",
       "      <td>19.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Embarked</th>\n",
       "      <td>2</td>\n",
       "      <td>0.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Fare</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Ticket</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          Total     %\n",
       "Cabin       687  77.1\n",
       "Age         177  19.9\n",
       "Embarked      2   0.2\n",
       "Fare          0   0.0\n",
       "Ticket        0   0.0"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "total = train.isnull().sum().sort_values(ascending=False)\n",
    "percent_1 = train.isnull().sum()/train.isnull().count()*100\n",
    "percent_2 = (round(percent_1, 1)).sort_values(ascending=False)\n",
    "missing_data = pd.concat([total, percent_2], axis=1, keys=['Total', '%'])\n",
    "missing_data.head(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "train = train.drop(['Cabin'], axis = 1)\n",
    "test = test.drop(['Cabin'], axis = 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "train = train.drop(['Ticket'], axis = 1)\n",
    "test = test.drop(['Ticket'], axis = 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>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>Fare</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>7.2500</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>71.2833</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>7.9250</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>53.1000</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>8.0500</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     Fare Embarked  \n",
       "0      0   7.2500        S  \n",
       "1      0  71.2833        C  \n",
       "2      0   7.9250        S  \n",
       "3      0  53.1000        S  \n",
       "4      0   8.0500        S  "
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='Sex', ylabel='Survived'>"
      ]
     },
     "execution_count": 13,
     "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": [
    "sns.barplot(x=\"Sex\", y=\"Survived\", data=train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "#females were more likely to survive"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "891"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train.shape[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='Pclass', ylabel='Survived'>"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEGCAYAAABo25JHAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8vihELAAAACXBIWXMAAAsTAAALEwEAmpwYAAATCUlEQVR4nO3dfZBdd33f8ffHazTEjikxVkeMJGMFRKhJjZNsRDtOAyFxIpN2BM2TiRtKC9GoU0PyBwinU1weynSQM0wLmKhqorrJpLhpTYOaKjgpEJuah0gmtrFszKhysFb2xjKu8UM9lSV/+8ce0+urq90rec9erX/v18wd3fM7v3v2s3Nn9qNz7j3npKqQJLXrjEkHkCRNlkUgSY2zCCSpcRaBJDXOIpCkxp056QAn67zzzqsLLrhg0jEkaVm59dZbH6qqlaPWLbsiuOCCC9i7d++kY0jSspLkWyda56EhSWqcRSBJjbMIJKlxFoEkNa7XIkiyMck9SfYnuWrE+vckua173JnkWJJz+8wkSXq23oogyRRwLXAZcCHwliQXDs6pqmuq6uKquhj4DeCmqnq4r0ySpOP1uUewAdhfVQeq6ghwPbBpnvlvAT7VYx5J0gh9FsFq4ODA8kw3dpwkZwEbgRtOsH5zkr1J9h4+fHjRg0pSy/o8oSwjxk5084O/B9xyosNCVbUD2AEwPT39vL2BwtatW5mdnWXVqlVs27Zt0nEkNaLPIpgB1g4srwHuP8Hcy/GwELOzsxw6dGjSMSQ1ps9DQ3uA9UnWJVnB3B/7XcOTkvw14HXAZ3rMIkk6gd72CKrqaJIrgRuBKWBnVe1LsqVbv72b+mbgT6rqib6ySJJOrNeLzlXVbmD30Nj2oeXrgOv6zCFJOjHPLJakxlkEktQ4i0CSGmcRSFLjLAJJapxFIEmNswgkqXEWgSQ1ziKQpMZZBJLUOItAkhpnEUhS4ywCSWqcRSBJjbMIJKlxvd6PYNJ+5D2/O+kIJ+Wchx5jCrjvoceWVfZbr3nrpCNIeg7cI5CkxlkEktQ4i0CSGmcRSFLjLAJJalyvRZBkY5J7kuxPctUJ5rw+yW1J9iW5qc88kqTj9fb10SRTwLXApcAMsCfJrqq6a2DOi4FPAhur6r4kf72vPJKk0frcI9gA7K+qA1V1BLge2DQ055eBT1fVfQBV9WCPeSRJI/RZBKuBgwPLM93YoFcC35fkz5LcmmTkmUlJNifZm2Tv4cOHe4orSW3qswgyYqyGls8EfgT4WeBngPcleeVxL6raUVXTVTW9cuXKxU8qSQ3r8xITM8DageU1wP0j5jxUVU8ATyS5GXgN8M0ec0mSBvS5R7AHWJ9kXZIVwOXArqE5nwH+TpIzk5wFvBa4u8dMkqQhve0RVNXRJFcCNwJTwM6q2pdkS7d+e1XdneSzwB3A08BvV9WdfWWSJB2v16uPVtVuYPfQ2Pah5WuAa/rMIUk6Mc8slqTGWQSS1DiLQJIaZxFIUuMsAklq3PP6nsXLzdMrzn7Wv5K0FCyC08gT63960hEkNchDQ5LUOItAkhpnEUhS4/yMQFokW7duZXZ2llWrVrFt27ZJx5HGZhFIi2R2dpZDhw5NOoZ00jw0JEmNswgkqXEWgSQ1ziKQpMZZBJLUOItAkhpnEUhS4ywCSWqcRSBJjeu1CJJsTHJPkv1Jrhqx/vVJvpPktu5xdZ95JEnH6+0SE0mmgGuBS4EZYE+SXVV119DUL1bV3+0rhyRpfn3uEWwA9lfVgao6AlwPbOrx50mSTkGfRbAaODiwPNONDfvbSW5P8sdJXj1qQ0k2J9mbZO/hw4f7yCpJzeqzCDJirIaWvwa8rKpeA3wc+MNRG6qqHVU1XVXTK1euXNyUktS4PotgBlg7sLwGuH9wQlU9WlWPd893Ay9Icl6PmSRJQ/osgj3A+iTrkqwALgd2DU5IsipJuucbujzf7jGTJGlIb98aqqqjSa4EbgSmgJ1VtS/Jlm79duDngX+S5CjwJHB5VQ0fPpIk9ajXO5R1h3t2D41tH3j+CeATfWaQJM3PM4slqXEWgSQ1zpvX67R13wf/5qQjnJSjD58LnMnRh7+1bLKff/XXJx1BpwH3CCSpcRaBJDXOIpCkxlkEktQ4i0CSGmcRSFLjLAJJapxFIEmNswgkqXEWgSQ1ziKQpMZZBJLUOItAkho379VHkzzG8Tec/66qetGiJ5IkLal5i6CqzgFI8kFgFvg9IMAVwDm9p5Mk9W7cQ0M/U1WfrKrHqurRqvot4Of6DCZJWhrjFsGxJFckmUpyRpIrgGN9BpMkLY1xi+CXgV8E/qp7/EI3Nq8kG5Pck2R/kqvmmfejSY4l+fkx80iSFslYt6qsqr8ENp3MhpNMAdcClwIzwJ4ku6rqrhHzPgLceDLblyQtjrH2CJK8MsnnktzZLV+U5J8v8LINwP6qOlBVR4DrGV0m7wRuAB48idySpEUy7qGhfwf8BvAUQFXdAVy+wGtWAwcHlme6se9Kshp4M7B9zBySpEU21qEh4Kyq+vMkg2NHF3hNRowNn5Pwr4H3VtWxoW0/e0PJZmAzwPnnn79gWGkSznvh08DR7l9p+Ri3CB5K8nK6P+Tdh7oPLPCaGWDtwPIa4P6hOdPA9V0JnAe8McnRqvrDwUlVtQPYATA9PX3CE9ykSXr3RY9MOoJ0SsYtgn/K3B/iVyU5BNzL3Ell89kDrE+yDjjE3KGkZ33TqKrWPfM8yXXAHw2XgCSpX+MWwbeq6qeSnA2cUVWPLfSCqjqa5Ermvg00Beysqn1JtnTr/VxAkk4D4xbBvUk+C/wn4PPjbryqdgO7h8ZGFkBVvW3c7UqSFs+43xr6AeB/MHeI6N4kn0jyY/3FkiQtlbGKoKqerKo/qKq/D/wQ8CLgpl6TSZKWxNj3I0jyuiSfBL4GvJC5S05Ikpa5sT4jSHIvcBvwB8B7quqJPkNJkpbOuB8Wv6aqHu01iSRpIha6Q9nWqtoGfDjJcSdyVdW7eksmSVoSC+0R3N39u7fvIJKkyVjoVpX/rXt6R1X9xRLkkSQtsXG/NfTRJN9I8qEkr+41kSRpSY17HsFPAK8HDgM7knx9jPsRSJKWgbHPI6iq2ar6GLCFua+SXt1XKEnS0hn3DmV/I8n7uzuUfQL4EnOXlZYkLXPjnkfw74FPAT9dVcP3FJAkLWMLFkF3c/n/VVX/ZgnySJKW2IKHhqrqGPCSJCuWII8kaYmNfWMa4JYku4DvXmeoqj7aSypJ0pIZtwju7x5nAOf0F0eStNTGKoKq+kDfQSRJkzHuZai/AIy66NwbFj2RJGlJjXto6N0Dz18I/BxwdPHjSJKW2riHhm4dGrolibeqlKTngXHPLD534HFeko3AqjFetzHJPUn2J7lqxPpNSe5IcluSvUl+7BR+B0nSczDuoaFb+f+fERwF/hJ4+3wv6E5Euxa4FJgB9iTZVVV3DUz7HLCrqirJRczdCvNV48eXJD1X8+4RJPnRJKuqal1VfT/wAeAb3eOu+V4LbAD2V9WBqjoCXA9sGpxQVY9X1TMFczYjPpCWJPVroUND/xY4ApDkx4F/BfwH4DvAjgVeuxo4OLA80409S5I3J/kG8N+BfzxqQ0k2d4eO9h4+fHiBHytJOhkLFcFUVT3cPf8lYEdV3VBV7wNescBrM2Js1FdQ/2tVvQp4E/ChURuqqh1VNV1V0ytXrlzgx0qSTsaCRZDkmc8RfhL4/MC6hT5fmAHWDiyvYe7s5JGq6mbg5UnOW2C7kqRFtFARfAq4KclngCeBLwIkeQVzh4fmswdYn2Rdd8G6y4FdgxOSvCJJuuc/DKwAvn3Sv4Uk6ZQtdPP6Dyf5HPBS4E8GPtg9A3jnAq89muRK4EZgCthZVfuSbOnWb2fuxLS3JnmKuaL5pYGfIUlaAgt+fbSqvjJi7JvjbLyqdgO7h8a2Dzz/CPCRcbYlSX3ZunUrs7OzrFq1im3btk06zpIb9zwCSXremp2d5dChQ5OOMTFj37xekvT8ZBFIUuMsAklqnEUgSY2zCCSpcRaBJDXOIpCkxlkEktQ4i0CSGmcRSFLjLAJJapzXGpLUi0s+fsmkI4xtxSMrOIMzOPjIwWWV+5Z33rIo23GPQJIaZxFIUuMsAklqnEUgSY2zCCSpcRaBJDXOIpCkxlkEktS4XosgycYk9yTZn+SqEeuvSHJH9/hSktf0mUeSdLzeiiDJFHAtcBlwIfCWJBcOTbsXeF1VXQR8CNjRVx5J0mh97hFsAPZX1YGqOgJcD2wanFBVX6qq/90tfgVY02MeSRqpziqePvtp6qyadJSJ6PNaQ6uBgwPLM8Br55n/duCPR61IshnYDHD++ecvVj5JAuCpS56adISJ6nOPICPGRtZtkp9grgjeO2p9Ve2oqumqml65cuUiRpQk9blHMAOsHVheA9w/PCnJRcBvA5dV1bd7zCNJGqHPPYI9wPok65KsAC4Hdg1OSHI+8GngV6rqmz1mkSSdQG97BFV1NMmVwI3AFLCzqvYl2dKt3w5cDbwE+GQSgKNVNd1XJknS8Xq9MU1V7QZ2D41tH3j+DuAdfWaQJM3PM4slqXEWgSQ1ziKQpMZZBJLUOItAkhpnEUhS4ywCSWqcRSBJjbMIJKlxFoEkNc4ikKTGWQSS1DiLQJIaZxFIUuMsAklqnEUgSY2zCCSpcRaBJDXOIpCkxlkEktQ4i0CSGtdrESTZmOSeJPuTXDVi/auSfDnJ/03y7j6zSJJGO7OvDSeZAq4FLgVmgD1JdlXVXQPTHgbeBbyprxySpPn1uUewAdhfVQeq6ghwPbBpcEJVPVhVe4CneswhSZpHn0WwGjg4sDzTjZ20JJuT7E2y9/Dhw4sSTpI0p88iyIixOpUNVdWOqpququmVK1c+x1iSpEF9FsEMsHZgeQ1wf48/T5J0Cvosgj3A+iTrkqwALgd29fjzJEmnoLdvDVXV0SRXAjcCU8DOqtqXZEu3fnuSVcBe4EXA00l+Hbiwqh7tK5ck6dl6KwKAqtoN7B4a2z7wfJa5Q0aSpAnxzGJJapxFIEmNswgkqXEWgSQ1ziKQpMZZBJLUOItAkhpnEUhS4ywCSWqcRSBJjbMIJKlxFoEkNc4ikKTGWQSS1DiLQJIaZxFIUuMsAklqnEUgSY2zCCSpcRaBJDXOIpCkxvVaBEk2Jrknyf4kV41YnyQf69bfkeSH+8wjSTpeb0WQZAq4FrgMuBB4S5ILh6ZdBqzvHpuB3+orjyRptD73CDYA+6vqQFUdAa4HNg3N2QT8bs35CvDiJC/tMZMkaciZPW57NXBwYHkGeO0Yc1YDDwxOSrKZuT0GgMeT3LO4UU8r5wEPTTrEychv/sNJRzidLK/3719k0glOJ8vrvQPyrpN6/152ohV9FsGohHUKc6iqHcCOxQh1ukuyt6qmJ51Dp8b3b/lq+b3r89DQDLB2YHkNcP8pzJEk9ajPItgDrE+yLskK4HJg19CcXcBbu28P/S3gO1X1wPCGJEn96e3QUFUdTXIlcCMwBeysqn1JtnTrtwO7gTcC+4H/A/yjvvIsI00cAnse8/1bvpp971J13CF5SVJDPLNYkhpnEUhS4yyC00SSnUkeTHLnpLPo5CRZm+QLSe5Osi/Jr006k8aX5IVJ/jzJ7d3794FJZ1pqfkZwmkjy48DjzJ1p/YOTzqPxdWfDv7SqvpbkHOBW4E1VddeEo2kMSQKcXVWPJ3kB8D+BX+uudtAE9whOE1V1M/DwpHPo5FXVA1X1te75Y8DdzJ0hr2Wgu8TN493iC7pHU/9DtgikRZTkAuCHgK9OOIpOQpKpJLcBDwJ/WlVNvX8WgbRIknwvcAPw61X16KTzaHxVdayqLmbu6gYbkjR1eNYikBZBd2z5BuD3q+rTk86jU1NVjwB/BmycbJKlZRFIz1H3YePvAHdX1UcnnUcnJ8nKJC/unn8P8FPANyYaaolZBKeJJJ8Cvgz8QJKZJG+fdCaN7RLgV4A3JLmte7xx0qE0tpcCX0hyB3PXSPvTqvqjCWdaUn59VJIa5x6BJDXOIpCkxlkEktQ4i0CSGmcRSFLjLAJpSJJj3VdA70zyn5OcNc/c9yd591LmkxabRSAd78mquri7CuwRYMukA0l9sgik+X0ReAVAkrcmuaO7bv3vDU9M8qtJ9nTrb3hmTyLJL3R7F7cnubkbe3V3Dfzbum2uX9LfShrgCWXSkCSPV9X3JjmTuesHfRa4Gfg0cElVPZTk3Kp6OMn7gcer6jeTvKSqvt1t418Cf1VVH0/ydWBjVR1K8uKqeiTJx4GvVNXvJ1kBTFXVkxP5hdU89wik431Pd0nivcB9zF1H6A3Af6mqhwCqatS9I34wyRe7P/xXAK/uxm8Brkvyq8BUN/Zl4J8leS/wMktAk3TmpANIp6Enu0sSf1d3YbmFdp+vY+7OZLcneRvweoCq2pLktcDPArclubiq/mOSr3ZjNyZ5R1V9fnF/DWk87hFI4/kc8ItJXgKQ5NwRc84BHuguSX3FM4NJXl5VX62qq4GHgLVJvh84UFUfA3YBF/X+G0gn4B6BNIaq2pfkw8BNSY4BfwG8bWja+5i7M9m3gK8zVwwA13QfBoe5QrkduAr4B0meAmaBD/b+S0gn4IfFktQ4Dw1JUuMsAklqnEUgSY2zCCSpcRaBJDXOIpCkxlkEktS4/wcl5kql14zKswAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.barplot(x=\"Pclass\", y=\"Survived\", data=train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "#people of higher socioeconomic class were more likely to survive"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='SibSp', ylabel='Survived'>"
      ]
     },
     "execution_count": 18,
     "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": [
    "sns.barplot(x=\"SibSp\", y=\"Survived\", data=train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    " #people with lesser siblings or spouses were more likely to survive"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='Parch', ylabel='Survived'>"
      ]
     },
     "execution_count": 20,
     "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": [
    "sns.barplot(x=\"Parch\", y=\"Survived\", data=train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "#people with less than 4 children or parents were more likely to survive"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "#cleaning nan values from agegroup to represent in a bargraph\n",
    "train[\"Age\"] = train[\"Age\"].fillna(-0.5)\n",
    "test[\"Age\"] = test[\"Age\"].fillna(-0.5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>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>Fare</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>7.2500</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>71.2833</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>7.9250</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>53.1000</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>8.0500</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>886</th>\n",
       "      <td>887</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>Montvila, Rev. Juozas</td>\n",
       "      <td>male</td>\n",
       "      <td>27.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>13.0000</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>887</th>\n",
       "      <td>888</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Graham, Miss. Margaret Edith</td>\n",
       "      <td>female</td>\n",
       "      <td>19.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>30.0000</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>888</th>\n",
       "      <td>889</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Johnston, Miss. Catherine Helen \"Carrie\"</td>\n",
       "      <td>female</td>\n",
       "      <td>-0.5</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>23.4500</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>889</th>\n",
       "      <td>890</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Behr, Mr. Karl Howell</td>\n",
       "      <td>male</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>30.0000</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>890</th>\n",
       "      <td>891</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Dooley, Mr. Patrick</td>\n",
       "      <td>male</td>\n",
       "      <td>32.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.7500</td>\n",
       "      <td>Q</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>891 rows × 10 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",
       "886          887         0       2   \n",
       "887          888         1       1   \n",
       "888          889         0       3   \n",
       "889          890         1       1   \n",
       "890          891         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",
       "886                              Montvila, Rev. Juozas    male  27.0      0   \n",
       "887                       Graham, Miss. Margaret Edith  female  19.0      0   \n",
       "888           Johnston, Miss. Catherine Helen \"Carrie\"  female  -0.5      1   \n",
       "889                              Behr, Mr. Karl Howell    male  26.0      0   \n",
       "890                                Dooley, Mr. Patrick    male  32.0      0   \n",
       "\n",
       "     Parch     Fare Embarked  \n",
       "0        0   7.2500        S  \n",
       "1        0  71.2833        C  \n",
       "2        0   7.9250        S  \n",
       "3        0  53.1000        S  \n",
       "4        0   8.0500        S  \n",
       "..     ...      ...      ...  \n",
       "886      0  13.0000        S  \n",
       "887      0  30.0000        S  \n",
       "888      2  23.4500        S  \n",
       "889      0  30.0000        C  \n",
       "890      0   7.7500        Q  \n",
       "\n",
       "[891 rows x 10 columns]"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 891 entries, 0 to 890\n",
      "Data columns (total 10 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   Fare         891 non-null    float64\n",
      " 9   Embarked     889 non-null    object \n",
      "dtypes: float64(2), int64(5), object(3)\n",
      "memory usage: 69.7+ KB\n"
     ]
    }
   ],
   "source": [
    "train.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "#sorting ages into groups"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "bins = [-1, 0, 5, 12, 18, 24, 35, 60, np.inf]\n",
    "labels = ['Unknown', 'Baby', 'Child', 'Teenager', 'Student', 'Young Adult', 'Adult', 'Senior']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "train['AgeGroup'] = pd.cut(train[\"Age\"], bins, labels = labels)\n",
    "test['AgeGroup'] = pd.cut(test[\"Age\"], bins, labels = labels)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "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>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>AgeGroup</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>418.000000</td>\n",
       "      <td>418.000000</td>\n",
       "      <td>418</td>\n",
       "      <td>418</td>\n",
       "      <td>418.000000</td>\n",
       "      <td>418.000000</td>\n",
       "      <td>418.000000</td>\n",
       "      <td>417.000000</td>\n",
       "      <td>418</td>\n",
       "      <td>418</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>unique</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>418</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>top</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Clark, Mr. Walter Miller</td>\n",
       "      <td>male</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>Young Adult</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>freq</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "      <td>266</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>270</td>\n",
       "      <td>96</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>1100.500000</td>\n",
       "      <td>2.265550</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>23.941388</td>\n",
       "      <td>0.447368</td>\n",
       "      <td>0.392344</td>\n",
       "      <td>35.627188</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>120.810458</td>\n",
       "      <td>0.841838</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>17.741080</td>\n",
       "      <td>0.896760</td>\n",
       "      <td>0.981429</td>\n",
       "      <td>55.907576</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>892.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-0.500000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>996.250000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>9.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>7.895800</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>1100.500000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>24.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>14.454200</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>1204.750000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>35.750000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>31.500000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>1309.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>76.000000</td>\n",
       "      <td>8.000000</td>\n",
       "      <td>9.000000</td>\n",
       "      <td>512.329200</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        PassengerId      Pclass                      Name   Sex         Age  \\\n",
       "count    418.000000  418.000000                       418   418  418.000000   \n",
       "unique          NaN         NaN                       418     2         NaN   \n",
       "top             NaN         NaN  Clark, Mr. Walter Miller  male         NaN   \n",
       "freq            NaN         NaN                         1   266         NaN   \n",
       "mean    1100.500000    2.265550                       NaN   NaN   23.941388   \n",
       "std      120.810458    0.841838                       NaN   NaN   17.741080   \n",
       "min      892.000000    1.000000                       NaN   NaN   -0.500000   \n",
       "25%      996.250000    1.000000                       NaN   NaN    9.000000   \n",
       "50%     1100.500000    3.000000                       NaN   NaN   24.000000   \n",
       "75%     1204.750000    3.000000                       NaN   NaN   35.750000   \n",
       "max     1309.000000    3.000000                       NaN   NaN   76.000000   \n",
       "\n",
       "             SibSp       Parch        Fare Embarked     AgeGroup  \n",
       "count   418.000000  418.000000  417.000000      418          418  \n",
       "unique         NaN         NaN         NaN        3            8  \n",
       "top            NaN         NaN         NaN        S  Young Adult  \n",
       "freq           NaN         NaN         NaN      270           96  \n",
       "mean      0.447368    0.392344   35.627188      NaN          NaN  \n",
       "std       0.896760    0.981429   55.907576      NaN          NaN  \n",
       "min       0.000000    0.000000    0.000000      NaN          NaN  \n",
       "25%       0.000000    0.000000    7.895800      NaN          NaN  \n",
       "50%       0.000000    0.000000   14.454200      NaN          NaN  \n",
       "75%       1.000000    0.000000   31.500000      NaN          NaN  \n",
       "max       8.000000    9.000000  512.329200      NaN          NaN  "
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test.describe(include='all')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "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>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>AgeGroup</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>891.000000</td>\n",
       "      <td>891.000000</td>\n",
       "      <td>891.000000</td>\n",
       "      <td>891</td>\n",
       "      <td>891</td>\n",
       "      <td>891.000000</td>\n",
       "      <td>891.000000</td>\n",
       "      <td>891.000000</td>\n",
       "      <td>891.000000</td>\n",
       "      <td>889</td>\n",
       "      <td>891</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>unique</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>891</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>top</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Johansson, Mr. Karl Johan</td>\n",
       "      <td>male</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>Young Adult</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>freq</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "      <td>577</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>644</td>\n",
       "      <td>220</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>446.000000</td>\n",
       "      <td>0.383838</td>\n",
       "      <td>2.308642</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>23.699966</td>\n",
       "      <td>0.523008</td>\n",
       "      <td>0.381594</td>\n",
       "      <td>32.204208</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>257.353842</td>\n",
       "      <td>0.486592</td>\n",
       "      <td>0.836071</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>17.731181</td>\n",
       "      <td>1.102743</td>\n",
       "      <td>0.806057</td>\n",
       "      <td>49.693429</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-0.500000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>223.500000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>7.910400</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>446.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>24.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>14.454200</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>668.500000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>35.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>31.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>891.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>80.000000</td>\n",
       "      <td>8.000000</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>512.329200</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        PassengerId    Survived      Pclass                       Name   Sex  \\\n",
       "count    891.000000  891.000000  891.000000                        891   891   \n",
       "unique          NaN         NaN         NaN                        891     2   \n",
       "top             NaN         NaN         NaN  Johansson, Mr. Karl Johan  male   \n",
       "freq            NaN         NaN         NaN                          1   577   \n",
       "mean     446.000000    0.383838    2.308642                        NaN   NaN   \n",
       "std      257.353842    0.486592    0.836071                        NaN   NaN   \n",
       "min        1.000000    0.000000    1.000000                        NaN   NaN   \n",
       "25%      223.500000    0.000000    2.000000                        NaN   NaN   \n",
       "50%      446.000000    0.000000    3.000000                        NaN   NaN   \n",
       "75%      668.500000    1.000000    3.000000                        NaN   NaN   \n",
       "max      891.000000    1.000000    3.000000                        NaN   NaN   \n",
       "\n",
       "               Age       SibSp       Parch        Fare Embarked     AgeGroup  \n",
       "count   891.000000  891.000000  891.000000  891.000000      889          891  \n",
       "unique         NaN         NaN         NaN         NaN        3            8  \n",
       "top            NaN         NaN         NaN         NaN        S  Young Adult  \n",
       "freq           NaN         NaN         NaN         NaN      644          220  \n",
       "mean     23.699966    0.523008    0.381594   32.204208      NaN          NaN  \n",
       "std      17.731181    1.102743    0.806057   49.693429      NaN          NaN  \n",
       "min      -0.500000    0.000000    0.000000    0.000000      NaN          NaN  \n",
       "25%       6.000000    0.000000    0.000000    7.910400      NaN          NaN  \n",
       "50%      24.000000    0.000000    0.000000   14.454200      NaN          NaN  \n",
       "75%      35.000000    1.000000    0.000000   31.000000      NaN          NaN  \n",
       "max      80.000000    8.000000    6.000000  512.329200      NaN          NaN  "
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train.describe(include='all')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='AgeGroup', ylabel='Survived'>"
      ]
     },
     "execution_count": 30,
     "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": [
    "sns.barplot(x=\"AgeGroup\", y=\"Survived\", data=train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    " #babies were more likely to survive"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "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>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>AgeGroup</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>891.000000</td>\n",
       "      <td>891.000000</td>\n",
       "      <td>891.000000</td>\n",
       "      <td>891</td>\n",
       "      <td>891</td>\n",
       "      <td>891.000000</td>\n",
       "      <td>891.000000</td>\n",
       "      <td>891.000000</td>\n",
       "      <td>891.000000</td>\n",
       "      <td>889</td>\n",
       "      <td>891</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>unique</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>891</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>top</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Johansson, Mr. Karl Johan</td>\n",
       "      <td>male</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>Young Adult</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>freq</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "      <td>577</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>644</td>\n",
       "      <td>220</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>446.000000</td>\n",
       "      <td>0.383838</td>\n",
       "      <td>2.308642</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>23.699966</td>\n",
       "      <td>0.523008</td>\n",
       "      <td>0.381594</td>\n",
       "      <td>32.204208</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>257.353842</td>\n",
       "      <td>0.486592</td>\n",
       "      <td>0.836071</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>17.731181</td>\n",
       "      <td>1.102743</td>\n",
       "      <td>0.806057</td>\n",
       "      <td>49.693429</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-0.500000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>223.500000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>7.910400</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>446.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>24.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>14.454200</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>668.500000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>35.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>31.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>891.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>80.000000</td>\n",
       "      <td>8.000000</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>512.329200</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        PassengerId    Survived      Pclass                       Name   Sex  \\\n",
       "count    891.000000  891.000000  891.000000                        891   891   \n",
       "unique          NaN         NaN         NaN                        891     2   \n",
       "top             NaN         NaN         NaN  Johansson, Mr. Karl Johan  male   \n",
       "freq            NaN         NaN         NaN                          1   577   \n",
       "mean     446.000000    0.383838    2.308642                        NaN   NaN   \n",
       "std      257.353842    0.486592    0.836071                        NaN   NaN   \n",
       "min        1.000000    0.000000    1.000000                        NaN   NaN   \n",
       "25%      223.500000    0.000000    2.000000                        NaN   NaN   \n",
       "50%      446.000000    0.000000    3.000000                        NaN   NaN   \n",
       "75%      668.500000    1.000000    3.000000                        NaN   NaN   \n",
       "max      891.000000    1.000000    3.000000                        NaN   NaN   \n",
       "\n",
       "               Age       SibSp       Parch        Fare Embarked     AgeGroup  \n",
       "count   891.000000  891.000000  891.000000  891.000000      889          891  \n",
       "unique         NaN         NaN         NaN         NaN        3            8  \n",
       "top            NaN         NaN         NaN         NaN        S  Young Adult  \n",
       "freq           NaN         NaN         NaN         NaN      644          220  \n",
       "mean     23.699966    0.523008    0.381594   32.204208      NaN          NaN  \n",
       "std      17.731181    1.102743    0.806057   49.693429      NaN          NaN  \n",
       "min      -0.500000    0.000000    0.000000    0.000000      NaN          NaN  \n",
       "25%       6.000000    0.000000    0.000000    7.910400      NaN          NaN  \n",
       "50%      24.000000    0.000000    0.000000   14.454200      NaN          NaN  \n",
       "75%      35.000000    1.000000    0.000000   31.000000      NaN          NaN  \n",
       "max      80.000000    8.000000    6.000000  512.329200      NaN          NaN  "
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train.describe(include='all')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Index(['PassengerId', 'Pclass', 'Name', 'Sex', 'Age', 'SibSp', 'Parch', 'Fare',\n",
      "       'Embarked', 'AgeGroup'],\n",
      "      dtype='object')\n"
     ]
    }
   ],
   "source": [
    "print(test.columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Index(['PassengerId', 'Survived', 'Pclass', 'Name', 'Sex', 'Age', 'SibSp',\n",
      "       'Parch', 'Fare', 'Embarked', 'AgeGroup'],\n",
      "      dtype='object')\n"
     ]
    }
   ],
   "source": [
    "print(train.columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "644"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "southampton_count=train[train[\"Embarked\"] == \"S\"].shape[0]\n",
    "southampton_count"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "168"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cherbourg_count = train[train[\"Embarked\"] == \"C\"].shape[0]\n",
    "cherbourg_count"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "77"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "queenstown_count = train[train[\"Embarked\"] == \"Q\"].shape[0]\n",
    "queenstown_count"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "PassengerId    0\n",
      "Survived       0\n",
      "Pclass         0\n",
      "Name           0\n",
      "Sex            0\n",
      "Age            0\n",
      "SibSp          0\n",
      "Parch          0\n",
      "Fare           0\n",
      "Embarked       2\n",
      "AgeGroup       0\n",
      "dtype: int64\n"
     ]
    }
   ],
   "source": [
    "print(pd.isnull(train).sum())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Clearly most people were from southampton\n",
    "#So, we fill in missing values with S. i.e Southampton\n",
    "train = train.fillna({\"Embarked\": \"S\"})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "PassengerId    0\n",
      "Survived       0\n",
      "Pclass         0\n",
      "Name           0\n",
      "Sex            0\n",
      "Age            0\n",
      "SibSp          0\n",
      "Parch          0\n",
      "Fare           0\n",
      "Embarked       0\n",
      "AgeGroup       0\n",
      "dtype: int64\n"
     ]
    }
   ],
   "source": [
    "print(pd.isnull(train).sum())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [],
   "source": [
    "combine=[train,test]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "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",
       " 886          887         0       2   \n",
       " 887          888         1       1   \n",
       " 888          889         0       3   \n",
       " 889          890         1       1   \n",
       " 890          891         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",
       " 886                              Montvila, Rev. Juozas    male  27.0      0   \n",
       " 887                       Graham, Miss. Margaret Edith  female  19.0      0   \n",
       " 888           Johnston, Miss. Catherine Helen \"Carrie\"  female  -0.5      1   \n",
       " 889                              Behr, Mr. Karl Howell    male  26.0      0   \n",
       " 890                                Dooley, Mr. Patrick    male  32.0      0   \n",
       " \n",
       "      Parch     Fare Embarked     AgeGroup  \n",
       " 0        0   7.2500        S      Student  \n",
       " 1        0  71.2833        C        Adult  \n",
       " 2        0   7.9250        S  Young Adult  \n",
       " 3        0  53.1000        S  Young Adult  \n",
       " 4        0   8.0500        S  Young Adult  \n",
       " ..     ...      ...      ...          ...  \n",
       " 886      0  13.0000        S  Young Adult  \n",
       " 887      0  30.0000        S      Student  \n",
       " 888      2  23.4500        S      Unknown  \n",
       " 889      0  30.0000        C  Young Adult  \n",
       " 890      0   7.7500        Q  Young Adult  \n",
       " \n",
       " [891 rows x 11 columns],\n",
       "      PassengerId  Pclass                                          Name  \\\n",
       " 0            892       3                              Kelly, Mr. James   \n",
       " 1            893       3              Wilkes, Mrs. James (Ellen Needs)   \n",
       " 2            894       2                     Myles, Mr. Thomas Francis   \n",
       " 3            895       3                              Wirz, Mr. Albert   \n",
       " 4            896       3  Hirvonen, Mrs. Alexander (Helga E Lindqvist)   \n",
       " ..           ...     ...                                           ...   \n",
       " 413         1305       3                            Spector, Mr. Woolf   \n",
       " 414         1306       1                  Oliva y Ocana, Dona. Fermina   \n",
       " 415         1307       3                  Saether, Mr. Simon Sivertsen   \n",
       " 416         1308       3                           Ware, Mr. Frederick   \n",
       " 417         1309       3                      Peter, Master. Michael J   \n",
       " \n",
       "         Sex   Age  SibSp  Parch      Fare Embarked     AgeGroup  \n",
       " 0      male  34.5      0      0    7.8292        Q  Young Adult  \n",
       " 1    female  47.0      1      0    7.0000        S        Adult  \n",
       " 2      male  62.0      0      0    9.6875        Q       Senior  \n",
       " 3      male  27.0      0      0    8.6625        S  Young Adult  \n",
       " 4    female  22.0      1      1   12.2875        S      Student  \n",
       " ..      ...   ...    ...    ...       ...      ...          ...  \n",
       " 413    male  -0.5      0      0    8.0500        S      Unknown  \n",
       " 414  female  39.0      0      0  108.9000        C        Adult  \n",
       " 415    male  38.5      0      0    7.2500        S        Adult  \n",
       " 416    male  -0.5      0      0    8.0500        S      Unknown  \n",
       " 417    male  -0.5      1      1   22.3583        C      Unknown  \n",
       " \n",
       " [418 rows x 10 columns]]"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "combine"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [],
   "source": [
    "for dataset in combine:\n",
    "    dataset['Title'] = dataset.Name.str.extract(' ([A-Za-z]+)\\.',expand= False)\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "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>Sex</th>\n",
       "      <th>female</th>\n",
       "      <th>male</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Title</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Capt</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Col</th>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Countess</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Don</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Dr</th>\n",
       "      <td>1</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Jonkheer</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Lady</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Major</th>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Master</th>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Miss</th>\n",
       "      <td>182</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Mlle</th>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Mme</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Mr</th>\n",
       "      <td>0</td>\n",
       "      <td>517</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Mrs</th>\n",
       "      <td>125</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Ms</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Rev</th>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Sir</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Sex       female  male\n",
       "Title                 \n",
       "Capt           0     1\n",
       "Col            0     2\n",
       "Countess       1     0\n",
       "Don            0     1\n",
       "Dr             1     6\n",
       "Jonkheer       0     1\n",
       "Lady           1     0\n",
       "Major          0     2\n",
       "Master         0    40\n",
       "Miss         182     0\n",
       "Mlle           2     0\n",
       "Mme            1     0\n",
       "Mr             0   517\n",
       "Mrs          125     0\n",
       "Ms             1     0\n",
       "Rev            0     6\n",
       "Sir            0     1"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.crosstab(train['Title'], train['Sex'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [],
   "source": [
    "for dataset in combine:\n",
    "    dataset['Title'] = dataset['Title'].replace(['Capt', 'Col', 'Don', 'Dr', 'Major', 'Rev', 'Jonkheer', 'Dona'], 'Rare')\n",
    "    dataset['Title'] = dataset['Title'].replace(['Lady', 'Countess','Sir'], 'Royal')\n",
    "    dataset['Title'] = dataset['Title'].replace(['Ms', 'Mme','Mlle'], 'Mrs')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "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>Sex</th>\n",
       "      <th>female</th>\n",
       "      <th>male</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Title</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Master</th>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Miss</th>\n",
       "      <td>182</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Mr</th>\n",
       "      <td>0</td>\n",
       "      <td>517</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Mrs</th>\n",
       "      <td>129</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Rare</th>\n",
       "      <td>1</td>\n",
       "      <td>19</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Royal</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Sex     female  male\n",
       "Title               \n",
       "Master       0    40\n",
       "Miss       182     0\n",
       "Mr           0   517\n",
       "Mrs        129     0\n",
       "Rare         1    19\n",
       "Royal        2     1"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.crosstab(train['Title'], train['Sex'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [],
   "source": [
    " #map each of the title groups to a numerical value\n",
    "title_mapping = {\"Mr\": 1, \"Miss\": 2, \"Mrs\": 3, \"Master\": 4, \"Royal\": 5, \"Rare\": 6}\n",
    "for dataset in combine:\n",
    "    dataset['Title'] = dataset['Title'].map(title_mapping)\n",
    "    dataset['Title'] = dataset['Title'].fillna(0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "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>Title</th>\n",
       "      <th>Survived</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0.156673</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>0.697802</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>0.798450</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>0.575000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>6</td>\n",
       "      <td>0.250000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Title  Survived\n",
       "0      1  0.156673\n",
       "1      2  0.697802\n",
       "2      3  0.798450\n",
       "3      4  0.575000\n",
       "4      5  1.000000\n",
       "5      6  0.250000"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train[['Title', 'Survived']].groupby(['Title'], as_index=False).mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "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>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>AgeGroup</th>\n",
       "      <th>Title</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>7.2500</td>\n",
       "      <td>S</td>\n",
       "      <td>Student</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>71.2833</td>\n",
       "      <td>C</td>\n",
       "      <td>Adult</td>\n",
       "      <td>3</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>7.9250</td>\n",
       "      <td>S</td>\n",
       "      <td>Young Adult</td>\n",
       "      <td>2</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>53.1000</td>\n",
       "      <td>S</td>\n",
       "      <td>Young Adult</td>\n",
       "      <td>3</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>8.0500</td>\n",
       "      <td>S</td>\n",
       "      <td>Young Adult</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     Fare Embarked     AgeGroup  Title  \n",
       "0      0   7.2500        S      Student      1  \n",
       "1      0  71.2833        C        Adult      3  \n",
       "2      0   7.9250        S  Young Adult      2  \n",
       "3      0  53.1000        S  Young Adult      3  \n",
       "4      0   8.0500        S  Young Adult      1  "
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "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>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>AgeGroup</th>\n",
       "      <th>Title</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>881</th>\n",
       "      <td>882</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Markun, Mr. Johann</td>\n",
       "      <td>male</td>\n",
       "      <td>33.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.8958</td>\n",
       "      <td>S</td>\n",
       "      <td>Young Adult</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>882</th>\n",
       "      <td>883</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Dahlberg, Miss. Gerda Ulrika</td>\n",
       "      <td>female</td>\n",
       "      <td>22.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>10.5167</td>\n",
       "      <td>S</td>\n",
       "      <td>Student</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>883</th>\n",
       "      <td>884</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>Banfield, Mr. Frederick James</td>\n",
       "      <td>male</td>\n",
       "      <td>28.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>10.5000</td>\n",
       "      <td>S</td>\n",
       "      <td>Young Adult</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>884</th>\n",
       "      <td>885</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Sutehall, Mr. Henry Jr</td>\n",
       "      <td>male</td>\n",
       "      <td>25.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.0500</td>\n",
       "      <td>S</td>\n",
       "      <td>Young Adult</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>885</th>\n",
       "      <td>886</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Rice, Mrs. William (Margaret Norton)</td>\n",
       "      <td>female</td>\n",
       "      <td>39.0</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "      <td>29.1250</td>\n",
       "      <td>Q</td>\n",
       "      <td>Adult</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>886</th>\n",
       "      <td>887</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>Montvila, Rev. Juozas</td>\n",
       "      <td>male</td>\n",
       "      <td>27.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>13.0000</td>\n",
       "      <td>S</td>\n",
       "      <td>Young Adult</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>887</th>\n",
       "      <td>888</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Graham, Miss. Margaret Edith</td>\n",
       "      <td>female</td>\n",
       "      <td>19.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>30.0000</td>\n",
       "      <td>S</td>\n",
       "      <td>Student</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>888</th>\n",
       "      <td>889</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Johnston, Miss. Catherine Helen \"Carrie\"</td>\n",
       "      <td>female</td>\n",
       "      <td>-0.5</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>23.4500</td>\n",
       "      <td>S</td>\n",
       "      <td>Unknown</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>889</th>\n",
       "      <td>890</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Behr, Mr. Karl Howell</td>\n",
       "      <td>male</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>30.0000</td>\n",
       "      <td>C</td>\n",
       "      <td>Young Adult</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>890</th>\n",
       "      <td>891</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Dooley, Mr. Patrick</td>\n",
       "      <td>male</td>\n",
       "      <td>32.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.7500</td>\n",
       "      <td>Q</td>\n",
       "      <td>Young Adult</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     PassengerId  Survived  Pclass                                      Name  \\\n",
       "881          882         0       3                        Markun, Mr. Johann   \n",
       "882          883         0       3              Dahlberg, Miss. Gerda Ulrika   \n",
       "883          884         0       2             Banfield, Mr. Frederick James   \n",
       "884          885         0       3                    Sutehall, Mr. Henry Jr   \n",
       "885          886         0       3      Rice, Mrs. William (Margaret Norton)   \n",
       "886          887         0       2                     Montvila, Rev. Juozas   \n",
       "887          888         1       1              Graham, Miss. Margaret Edith   \n",
       "888          889         0       3  Johnston, Miss. Catherine Helen \"Carrie\"   \n",
       "889          890         1       1                     Behr, Mr. Karl Howell   \n",
       "890          891         0       3                       Dooley, Mr. Patrick   \n",
       "\n",
       "        Sex   Age  SibSp  Parch     Fare Embarked     AgeGroup  Title  \n",
       "881    male  33.0      0      0   7.8958        S  Young Adult      1  \n",
       "882  female  22.0      0      0  10.5167        S      Student      2  \n",
       "883    male  28.0      0      0  10.5000        S  Young Adult      1  \n",
       "884    male  25.0      0      0   7.0500        S  Young Adult      1  \n",
       "885  female  39.0      0      5  29.1250        Q        Adult      3  \n",
       "886    male  27.0      0      0  13.0000        S  Young Adult      6  \n",
       "887  female  19.0      0      0  30.0000        S      Student      2  \n",
       "888  female  -0.5      1      2  23.4500        S      Unknown      2  \n",
       "889    male  26.0      0      0  30.0000        C  Young Adult      1  \n",
       "890    male  32.0      0      0   7.7500        Q  Young Adult      1  "
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train.tail(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [],
   "source": [
    "mr_age = train[train[\"Title\"] == 1][\"AgeGroup\"].mode()#Young Adult"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    Young Adult\n",
       "Name: AgeGroup, dtype: category\n",
       "Categories (8, object): ['Unknown' < 'Baby' < 'Child' < 'Teenager' < 'Student' < 'Young Adult' < 'Adult' < 'Senior']"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mr_age"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    Unknown\n",
       "Name: AgeGroup, dtype: category\n",
       "Categories (8, object): ['Unknown' < 'Baby' < 'Child' < 'Teenager' < 'Student' < 'Young Adult' < 'Adult' < 'Senior']"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "miss_age = train[train[\"Title\"] == 2][\"AgeGroup\"].mode() #Student\n",
    "mrs_age = train[train[\"Title\"] == 3][\"AgeGroup\"].mode() #Adult\n",
    "master_age = train[train[\"Title\"] == 4][\"AgeGroup\"].mode() #Baby\n",
    "royal_age = train[train[\"Title\"] == 5][\"AgeGroup\"].mode() #Adult\n",
    "rare_age = train[train[\"Title\"] == 6][\"AgeGroup\"].mode() #Adult\n",
    "miss_age"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    Adult\n",
       "Name: AgeGroup, dtype: category\n",
       "Categories (8, object): ['Unknown' < 'Baby' < 'Child' < 'Teenager' < 'Student' < 'Young Adult' < 'Adult' < 'Senior']"
      ]
     },
     "execution_count": 54,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mrs_age"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    Baby\n",
       "Name: AgeGroup, dtype: category\n",
       "Categories (8, object): ['Unknown' < 'Baby' < 'Child' < 'Teenager' < 'Student' < 'Young Adult' < 'Adult' < 'Senior']"
      ]
     },
     "execution_count": 55,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "master_age"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    Adult\n",
       "Name: AgeGroup, dtype: category\n",
       "Categories (8, object): ['Unknown' < 'Baby' < 'Child' < 'Teenager' < 'Student' < 'Young Adult' < 'Adult' < 'Senior']"
      ]
     },
     "execution_count": 56,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "royal_age"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    Adult\n",
       "Name: AgeGroup, dtype: category\n",
       "Categories (8, object): ['Unknown' < 'Baby' < 'Child' < 'Teenager' < 'Student' < 'Young Adult' < 'Adult' < 'Senior']"
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rare_age"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [],
   "source": [
    " age_title_mapping = {1: \"Young Adult\", 2:\"Student\", 3:\"Adult\"\n",
    "                    , 4:\"Baby\", 5:\"Adult\", 6:\"Adult\"}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [],
   "source": [
    "#filling in missing agegroups\n",
    "#train = train.fillna({\"Age\": train[\"Title\"].map(age_title_mapping)})\n",
    "#test = test.fillna({\"Age\": test[\"Title\"].map(age_title_mapping)})\n",
    "for x in range(len(train[\"AgeGroup\"])):\n",
    "    if train[\"AgeGroup\"][x] == \"Unknown\":\n",
    "        train[\"AgeGroup\"][x] == age_title_mapping[train[\"Title\"][x]]\n",
    "for x in range(len(test[\"AgeGroup\"])):\n",
    "    if train[\"AgeGroup\"][x] == \"Unknown\":\n",
    "        train[\"AgeGroup\"][x] == age_title_mapping[train[\"Title\"][x]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "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>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>AgeGroup</th>\n",
       "      <th>Title</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>7.2500</td>\n",
       "      <td>S</td>\n",
       "      <td>Student</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>71.2833</td>\n",
       "      <td>C</td>\n",
       "      <td>Adult</td>\n",
       "      <td>3</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>7.9250</td>\n",
       "      <td>S</td>\n",
       "      <td>Young Adult</td>\n",
       "      <td>2</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>53.1000</td>\n",
       "      <td>S</td>\n",
       "      <td>Young Adult</td>\n",
       "      <td>3</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>8.0500</td>\n",
       "      <td>S</td>\n",
       "      <td>Young Adult</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>6</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Moran, Mr. James</td>\n",
       "      <td>male</td>\n",
       "      <td>-0.5</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.4583</td>\n",
       "      <td>Q</td>\n",
       "      <td>Unknown</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>McCarthy, Mr. Timothy J</td>\n",
       "      <td>male</td>\n",
       "      <td>54.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>51.8625</td>\n",
       "      <td>S</td>\n",
       "      <td>Adult</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>8</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Palsson, Master. Gosta Leonard</td>\n",
       "      <td>male</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>21.0750</td>\n",
       "      <td>S</td>\n",
       "      <td>Baby</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>9</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)</td>\n",
       "      <td>female</td>\n",
       "      <td>27.0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>11.1333</td>\n",
       "      <td>S</td>\n",
       "      <td>Young Adult</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>10</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>Nasser, Mrs. Nicholas (Adele Achem)</td>\n",
       "      <td>female</td>\n",
       "      <td>14.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>30.0708</td>\n",
       "      <td>C</td>\n",
       "      <td>Teenager</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>11</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Sandstrom, Miss. Marguerite Rut</td>\n",
       "      <td>female</td>\n",
       "      <td>4.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>16.7000</td>\n",
       "      <td>S</td>\n",
       "      <td>Baby</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>12</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Bonnell, Miss. Elizabeth</td>\n",
       "      <td>female</td>\n",
       "      <td>58.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>26.5500</td>\n",
       "      <td>S</td>\n",
       "      <td>Adult</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>13</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Saundercock, Mr. William Henry</td>\n",
       "      <td>male</td>\n",
       "      <td>20.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>S</td>\n",
       "      <td>Student</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>14</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Andersson, Mr. Anders Johan</td>\n",
       "      <td>male</td>\n",
       "      <td>39.0</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>31.2750</td>\n",
       "      <td>S</td>\n",
       "      <td>Adult</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>15</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Vestrom, Miss. Hulda Amanda Adolfina</td>\n",
       "      <td>female</td>\n",
       "      <td>14.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.8542</td>\n",
       "      <td>S</td>\n",
       "      <td>Teenager</td>\n",
       "      <td>2</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",
       "5             6         0       3   \n",
       "6             7         0       1   \n",
       "7             8         0       3   \n",
       "8             9         1       3   \n",
       "9            10         1       2   \n",
       "10           11         1       3   \n",
       "11           12         1       1   \n",
       "12           13         0       3   \n",
       "13           14         0       3   \n",
       "14           15         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",
       "5                                    Moran, Mr. James    male  -0.5      0   \n",
       "6                             McCarthy, Mr. Timothy J    male  54.0      0   \n",
       "7                      Palsson, Master. Gosta Leonard    male   2.0      3   \n",
       "8   Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)  female  27.0      0   \n",
       "9                 Nasser, Mrs. Nicholas (Adele Achem)  female  14.0      1   \n",
       "10                    Sandstrom, Miss. Marguerite Rut  female   4.0      1   \n",
       "11                           Bonnell, Miss. Elizabeth  female  58.0      0   \n",
       "12                     Saundercock, Mr. William Henry    male  20.0      0   \n",
       "13                        Andersson, Mr. Anders Johan    male  39.0      1   \n",
       "14               Vestrom, Miss. Hulda Amanda Adolfina  female  14.0      0   \n",
       "\n",
       "    Parch     Fare Embarked     AgeGroup  Title  \n",
       "0       0   7.2500        S      Student      1  \n",
       "1       0  71.2833        C        Adult      3  \n",
       "2       0   7.9250        S  Young Adult      2  \n",
       "3       0  53.1000        S  Young Adult      3  \n",
       "4       0   8.0500        S  Young Adult      1  \n",
       "5       0   8.4583        Q      Unknown      1  \n",
       "6       0  51.8625        S        Adult      1  \n",
       "7       1  21.0750        S         Baby      4  \n",
       "8       2  11.1333        S  Young Adult      3  \n",
       "9       0  30.0708        C     Teenager      3  \n",
       "10      1  16.7000        S         Baby      2  \n",
       "11      0  26.5500        S        Adult      2  \n",
       "12      0   8.0500        S      Student      1  \n",
       "13      5  31.2750        S        Adult      1  \n",
       "14      0   7.8542        S     Teenager      2  "
      ]
     },
     "execution_count": 60,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train.head(15)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "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>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>AgeGroup</th>\n",
       "      <th>Title</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>7.2500</td>\n",
       "      <td>S</td>\n",
       "      <td>4.0</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>71.2833</td>\n",
       "      <td>C</td>\n",
       "      <td>6.0</td>\n",
       "      <td>3</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>7.9250</td>\n",
       "      <td>S</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2</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>53.1000</td>\n",
       "      <td>S</td>\n",
       "      <td>5.0</td>\n",
       "      <td>3</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>8.0500</td>\n",
       "      <td>S</td>\n",
       "      <td>5.0</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     Fare Embarked  AgeGroup  Title  \n",
       "0      0   7.2500        S       4.0      1  \n",
       "1      0  71.2833        C       6.0      3  \n",
       "2      0   7.9250        S       5.0      2  \n",
       "3      0  53.1000        S       5.0      3  \n",
       "4      0   8.0500        S       5.0      1  "
      ]
     },
     "execution_count": 61,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#map each Age value to a numerical value\n",
    "age_mapping = {'Baby': 1, 'Child': 2, 'Teenager': 3, 'Student': 4, 'Young Adult': 5, 'Adult': 6, 'Senior': 7}\n",
    "train['AgeGroup'] = train['AgeGroup'].map(age_mapping)\n",
    "test['AgeGroup'] = test['AgeGroup'].map(age_mapping)\n",
    "\n",
    "train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {},
   "outputs": [],
   "source": [
    "#remove Age column\n",
    "train = train.drop(['Age'], axis = 1)\n",
    "test = test.drop(['Age'], axis = 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {},
   "outputs": [],
   "source": [
    "#map Sex column to a numerical value"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [],
   "source": [
    "sex_mapping = {\"male\":0, \"female\":1}\n",
    "train['Sex'] = train['Sex'].map(sex_mapping)\n",
    "test['Sex'] = test['Sex'].map(sex_mapping)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {
    "scrolled": false
   },
   "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>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>AgeGroup</th>\n",
       "      <th>Title</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>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>S</td>\n",
       "      <td>4.0</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>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>C</td>\n",
       "      <td>6.0</td>\n",
       "      <td>3</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>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>S</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2</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>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>S</td>\n",
       "      <td>5.0</td>\n",
       "      <td>3</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>S</td>\n",
       "      <td>5.0</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  SibSp  Parch  \\\n",
       "0                            Braund, Mr. Owen Harris    0      1      0   \n",
       "1  Cumings, Mrs. John Bradley (Florence Briggs Th...    1      1      0   \n",
       "2                             Heikkinen, Miss. Laina    1      0      0   \n",
       "3       Futrelle, Mrs. Jacques Heath (Lily May Peel)    1      1      0   \n",
       "4                           Allen, Mr. William Henry    0      0      0   \n",
       "\n",
       "      Fare Embarked  AgeGroup  Title  \n",
       "0   7.2500        S       4.0      1  \n",
       "1  71.2833        C       6.0      3  \n",
       "2   7.9250        S       5.0      2  \n",
       "3  53.1000        S       5.0      3  \n",
       "4   8.0500        S       5.0      1  "
      ]
     },
     "execution_count": 65,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "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>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>AgeGroup</th>\n",
       "      <th>Title</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>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>1</td>\n",
       "      <td>4.0</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>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>2</td>\n",
       "      <td>6.0</td>\n",
       "      <td>3</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>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>1</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2</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>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>1</td>\n",
       "      <td>5.0</td>\n",
       "      <td>3</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>1</td>\n",
       "      <td>5.0</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  SibSp  Parch  \\\n",
       "0                            Braund, Mr. Owen Harris    0      1      0   \n",
       "1  Cumings, Mrs. John Bradley (Florence Briggs Th...    1      1      0   \n",
       "2                             Heikkinen, Miss. Laina    1      0      0   \n",
       "3       Futrelle, Mrs. Jacques Heath (Lily May Peel)    1      1      0   \n",
       "4                           Allen, Mr. William Henry    0      0      0   \n",
       "\n",
       "      Fare  Embarked  AgeGroup  Title  \n",
       "0   7.2500         1       4.0      1  \n",
       "1  71.2833         2       6.0      3  \n",
       "2   7.9250         1       5.0      2  \n",
       "3  53.1000         1       5.0      3  \n",
       "4   8.0500         1       5.0      1  "
      ]
     },
     "execution_count": 66,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#map each Embarked value to a numerical value\n",
    "embarked_mapping = {\"S\": 1, \"C\": 2, \"Q\": 3}\n",
    "train['Embarked'] = train['Embarked'].map(embarked_mapping)\n",
    "test['Embarked'] = test['Embarked'].map(embarked_mapping)\n",
    "\n",
    "train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [],
   "source": [
    "#fill in missing fare values based on mean fare for that Pclass\n",
    "for x in range(len(test[\"Fare\"])):\n",
    "    if pd.isnull(test[\"Fare\"][x]):\n",
    "        pclass = test[\"Pclass\"][x]\n",
    "        test[\"Fare\"][x] = round(train[train[\"Pclass\"] == pclass][\"Fare\"].mean(), 4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 891 entries, 0 to 890\n",
      "Data columns (total 11 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    int64  \n",
      " 5   SibSp        891 non-null    int64  \n",
      " 6   Parch        891 non-null    int64  \n",
      " 7   Fare         891 non-null    float64\n",
      " 8   Embarked     891 non-null    int64  \n",
      " 9   AgeGroup     714 non-null    float64\n",
      " 10  Title        891 non-null    int64  \n",
      "dtypes: float64(2), int64(8), object(1)\n",
      "memory usage: 76.7+ KB\n"
     ]
    }
   ],
   "source": [
    "train.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [],
   "source": [
    " #seperate fare into logical groups\n",
    "train['FareBand'] = pd.qcut(train['Fare'], 4, labels = [1, 2, 3, 4])\n",
    "test['FareBand'] = pd.qcut(test['Fare'], 4, labels = [1, 2, 3, 4])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {},
   "outputs": [],
   "source": [
    "#drop Fare values\n",
    "train = train.drop(['Fare'], axis = 1)\n",
    "test = test.drop(['Fare'], axis = 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {},
   "outputs": [],
   "source": [
    "#drop Name values because no more info can be extracted from it\n",
    "train = train.drop(['Name'], axis = 1)\n",
    "test = test.drop(['Name'], axis = 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "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>Sex</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>AgeGroup</th>\n",
       "      <th>Title</th>\n",
       "      <th>FareBand</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>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>4.0</td>\n",
       "      <td>1</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>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>6.0</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>5.0</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>886</th>\n",
       "      <td>887</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>5.0</td>\n",
       "      <td>6</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>887</th>\n",
       "      <td>888</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>4.0</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>888</th>\n",
       "      <td>889</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>889</th>\n",
       "      <td>890</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>890</th>\n",
       "      <td>891</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>891 rows × 10 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     PassengerId  Survived  Pclass  Sex  SibSp  Parch  Embarked  AgeGroup  \\\n",
       "0              1         0       3    0      1      0         1       4.0   \n",
       "1              2         1       1    1      1      0         2       6.0   \n",
       "2              3         1       3    1      0      0         1       5.0   \n",
       "3              4         1       1    1      1      0         1       5.0   \n",
       "4              5         0       3    0      0      0         1       5.0   \n",
       "..           ...       ...     ...  ...    ...    ...       ...       ...   \n",
       "886          887         0       2    0      0      0         1       5.0   \n",
       "887          888         1       1    1      0      0         1       4.0   \n",
       "888          889         0       3    1      1      2         1       NaN   \n",
       "889          890         1       1    0      0      0         2       5.0   \n",
       "890          891         0       3    0      0      0         3       5.0   \n",
       "\n",
       "     Title FareBand  \n",
       "0        1        1  \n",
       "1        3        4  \n",
       "2        2        2  \n",
       "3        3        4  \n",
       "4        1        2  \n",
       "..     ...      ...  \n",
       "886      6        2  \n",
       "887      2        3  \n",
       "888      2        3  \n",
       "889      1        3  \n",
       "890      1        1  \n",
       "\n",
       "[891 rows x 10 columns]"
      ]
     },
     "execution_count": 72,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "metadata": {},
   "outputs": [],
   "source": [
    "#assume missing agegroups to be adult for no reason(self)\n",
    "train[\"AgeGroup\"] = train[\"AgeGroup\"].fillna(6)\n",
    "test[\"AgeGroup\"] = test[\"AgeGroup\"].fillna(6)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "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>Sex</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>AgeGroup</th>\n",
       "      <th>Title</th>\n",
       "      <th>FareBand</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>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>4.0</td>\n",
       "      <td>1</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>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>6.0</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>5.0</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>886</th>\n",
       "      <td>887</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>5.0</td>\n",
       "      <td>6</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>887</th>\n",
       "      <td>888</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>4.0</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>888</th>\n",
       "      <td>889</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>6.0</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>889</th>\n",
       "      <td>890</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>890</th>\n",
       "      <td>891</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>891 rows × 10 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     PassengerId  Survived  Pclass  Sex  SibSp  Parch  Embarked  AgeGroup  \\\n",
       "0              1         0       3    0      1      0         1       4.0   \n",
       "1              2         1       1    1      1      0         2       6.0   \n",
       "2              3         1       3    1      0      0         1       5.0   \n",
       "3              4         1       1    1      1      0         1       5.0   \n",
       "4              5         0       3    0      0      0         1       5.0   \n",
       "..           ...       ...     ...  ...    ...    ...       ...       ...   \n",
       "886          887         0       2    0      0      0         1       5.0   \n",
       "887          888         1       1    1      0      0         1       4.0   \n",
       "888          889         0       3    1      1      2         1       6.0   \n",
       "889          890         1       1    0      0      0         2       5.0   \n",
       "890          891         0       3    0      0      0         3       5.0   \n",
       "\n",
       "     Title FareBand  \n",
       "0        1        1  \n",
       "1        3        4  \n",
       "2        2        2  \n",
       "3        3        4  \n",
       "4        1        2  \n",
       "..     ...      ...  \n",
       "886      6        2  \n",
       "887      2        3  \n",
       "888      2        3  \n",
       "889      1        3  \n",
       "890      1        1  \n",
       "\n",
       "[891 rows x 10 columns]"
      ]
     },
     "execution_count": 74,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "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>Sex</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>AgeGroup</th>\n",
       "      <th>Title</th>\n",
       "      <th>FareBand</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>892</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>893</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>6.0</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>894</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>7.0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>895</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>896</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>4.0</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>413</th>\n",
       "      <td>1305</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>6.0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>414</th>\n",
       "      <td>1306</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>6.0</td>\n",
       "      <td>6</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>415</th>\n",
       "      <td>1307</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>6.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>416</th>\n",
       "      <td>1308</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>6.0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>417</th>\n",
       "      <td>1309</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>6.0</td>\n",
       "      <td>4</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>418 rows × 9 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     PassengerId  Pclass  Sex  SibSp  Parch  Embarked  AgeGroup  Title  \\\n",
       "0            892       3    0      0      0         3       5.0      1   \n",
       "1            893       3    1      1      0         1       6.0      3   \n",
       "2            894       2    0      0      0         3       7.0      1   \n",
       "3            895       3    0      0      0         1       5.0      1   \n",
       "4            896       3    1      1      1         1       4.0      3   \n",
       "..           ...     ...  ...    ...    ...       ...       ...    ...   \n",
       "413         1305       3    0      0      0         1       6.0      1   \n",
       "414         1306       1    1      0      0         2       6.0      6   \n",
       "415         1307       3    0      0      0         1       6.0      1   \n",
       "416         1308       3    0      0      0         1       6.0      1   \n",
       "417         1309       3    0      1      1         2       6.0      4   \n",
       "\n",
       "    FareBand  \n",
       "0          1  \n",
       "1          1  \n",
       "2          2  \n",
       "3          2  \n",
       "4          2  \n",
       "..       ...  \n",
       "413        2  \n",
       "414        4  \n",
       "415        1  \n",
       "416        2  \n",
       "417        3  \n",
       "\n",
       "[418 rows x 9 columns]"
      ]
     },
     "execution_count": 75,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "x_train:       Pclass  Sex  SibSp  Parch  Embarked  AgeGroup  Title FareBand\n",
      "172       3    1      1      1         1       1.0      2        2\n",
      "447       1    0      0      0         1       5.0      1        3\n",
      "597       3    0      0      0         1       6.0      1        1\n",
      "204       3    0      0      0         1       3.0      1        2\n",
      "240       3    1      1      0         2       6.0      2        2\n",
      "..      ...  ...    ...    ...       ...       ...    ...      ...\n",
      "835       1    1      1      1         2       6.0      2        4\n",
      "192       3    1      1      0         1       4.0      2        1\n",
      "629       3    0      0      0         3       6.0      1        1\n",
      "559       3    1      1      0         1       6.0      3        3\n",
      "684       2    0      1      1         1       6.0      1        4\n",
      "\n",
      "[694 rows x 8 columns]\n",
      "y_train:  172    1\n",
      "447    1\n",
      "597    0\n",
      "204    1\n",
      "240    0\n",
      "      ..\n",
      "835    1\n",
      "192    1\n",
      "629    0\n",
      "559    1\n",
      "684    0\n",
      "Name: Survived, Length: 694, dtype: int64\n",
      "x_test:       Pclass  Sex  SibSp  Parch  Embarked  AgeGroup  Title FareBand\n",
      "495       3    0      0      0         2       6.0      1        3\n",
      "648       3    0      0      0         1       6.0      1        1\n",
      "278       3    0      4      1         3       2.0      4        3\n",
      "31        1    1      1      0         2       6.0      3        4\n",
      "255       3    1      0      2         2       5.0      3        3\n",
      "..      ...  ...    ...    ...       ...       ...    ...      ...\n",
      "875       3    1      0      0         2       3.0      2        1\n",
      "727       3    1      0      0         3       6.0      2        1\n",
      "428       3    0      0      0         3       6.0      1        1\n",
      "54        1    0      0      1         2       7.0      1        4\n",
      "45        3    0      0      0         1       6.0      1        2\n",
      "\n",
      "[197 rows x 8 columns]\n",
      "y_test:  495    0\n",
      "648    0\n",
      "278    0\n",
      "31     1\n",
      "255    1\n",
      "      ..\n",
      "875    1\n",
      "727    1\n",
      "428    0\n",
      "54     0\n",
      "45     0\n",
      "Name: Survived, Length: 197, dtype: int64\n"
     ]
    }
   ],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "predictors = train.drop(['Survived', 'PassengerId'], axis=1)\n",
    "target = train[\"Survived\"]\n",
    "x_train, x_val, y_train, y_val = train_test_split(predictors, target, test_size = 0.22, random_state = 0)\n",
    "print (\"x_train: \", x_train)\n",
    "print (\"y_train: \", y_train)\n",
    "print(\"x_test: \", x_val)\n",
    "print (\"y_test: \", y_val)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "79.19\n"
     ]
    }
   ],
   "source": [
    "# Logistic Regression\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.metrics import accuracy_score\n",
    "logreg = LogisticRegression()\n",
    "logreg.fit(x_train, y_train)\n",
    "y_pred = logreg.predict(x_val)\n",
    "acc_logreg = round(accuracy_score(y_pred, y_val) * 100, 2)\n",
    "print(acc_logreg)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "78.68\n"
     ]
    }
   ],
   "source": [
    "# Gaussian Naive Bayes\n",
    "from sklearn.naive_bayes import GaussianNB\n",
    "gaussian = GaussianNB()\n",
    "gaussian.fit(x_train, y_train)\n",
    "y_pred = gaussian.predict(x_val)\n",
    "acc_gaussian = round(accuracy_score(y_pred, y_val) * 100, 2)\n",
    "print(acc_gaussian)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "82.74\n"
     ]
    }
   ],
   "source": [
    "# Support Vector Machines\n",
    "from sklearn.svm import SVC\n",
    "\n",
    "svc = SVC()\n",
    "svc.fit(x_train, y_train)\n",
    "y_pred = svc.predict(x_val)\n",
    "acc_svc = round(accuracy_score(y_pred, y_val) * 100, 2)\n",
    "print(acc_svc)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "78.17\n"
     ]
    }
   ],
   "source": [
    "# Linear SVC\n",
    "from sklearn.svm import LinearSVC\n",
    "\n",
    "linear_svc = LinearSVC()\n",
    "linear_svc.fit(x_train, y_train)\n",
    "y_pred = linear_svc.predict(x_val)\n",
    "acc_linear_svc = round(accuracy_score(y_pred, y_val) * 100, 2)\n",
    "print(acc_linear_svc)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "76.65\n"
     ]
    }
   ],
   "source": [
    "# Perceptron\n",
    "from sklearn.linear_model import Perceptron\n",
    "\n",
    "perceptron = Perceptron()\n",
    "perceptron.fit(x_train, y_train)\n",
    "y_pred = perceptron.predict(x_val)\n",
    "acc_perceptron = round(accuracy_score(y_pred, y_val) * 100, 2)\n",
    "print(acc_perceptron)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "82.74\n"
     ]
    }
   ],
   "source": [
    "#Decision Tree\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "\n",
    "decisiontree = DecisionTreeClassifier()\n",
    "decisiontree.fit(x_train, y_train)\n",
    "y_pred = decisiontree.predict(x_val)\n",
    "acc_decisiontree = round(accuracy_score(y_pred, y_val) * 100, 2)\n",
    "print(acc_decisiontree)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "84.77\n"
     ]
    }
   ],
   "source": [
    "# Random Forest\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "\n",
    "randomforest = RandomForestClassifier()\n",
    "randomforest.fit(x_train, y_train)\n",
    "y_pred = randomforest.predict(x_val)\n",
    "acc_randomforest = round(accuracy_score(y_pred, y_val) * 100, 2)\n",
    "print(acc_randomforest)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "81.22\n"
     ]
    }
   ],
   "source": [
    "# KNN or k-Nearest Neighbors\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "\n",
    "knn = KNeighborsClassifier()\n",
    "knn.fit(x_train, y_train)\n",
    "y_pred = knn.predict(x_val)\n",
    "acc_knn = round(accuracy_score(y_pred, y_val) * 100, 2)\n",
    "print(acc_knn)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "71.07\n"
     ]
    }
   ],
   "source": [
    "# Stochastic Gradient Descent\n",
    "from sklearn.linear_model import SGDClassifier\n",
    "\n",
    "sgd = SGDClassifier()\n",
    "sgd.fit(x_train, y_train)\n",
    "y_pred = sgd.predict(x_val)\n",
    "acc_sgd = round(accuracy_score(y_pred, y_val) * 100, 2)\n",
    "print(acc_sgd)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "84.77\n"
     ]
    }
   ],
   "source": [
    "# Gradient Boosting Classifier\n",
    "from sklearn.ensemble import GradientBoostingClassifier\n",
    "\n",
    "gbk = GradientBoostingClassifier()\n",
    "gbk.fit(x_train, y_train)\n",
    "y_pred = gbk.predict(x_val)\n",
    "acc_gbk = round(accuracy_score(y_pred, y_val) * 100, 2)\n",
    "print(acc_gbk)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "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>Model</th>\n",
       "      <th>Score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Random Forest</td>\n",
       "      <td>84.77</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>Gradient Boosting Classifier</td>\n",
       "      <td>84.77</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Support Vector Machines</td>\n",
       "      <td>82.74</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Decision Tree</td>\n",
       "      <td>82.74</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>KNN</td>\n",
       "      <td>81.22</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Logistic Regression</td>\n",
       "      <td>79.19</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Naive Bayes</td>\n",
       "      <td>78.68</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Linear SVC</td>\n",
       "      <td>78.17</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Perceptron</td>\n",
       "      <td>76.65</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Stochastic Gradient Descent</td>\n",
       "      <td>71.07</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                          Model  Score\n",
       "3                 Random Forest  84.77\n",
       "9  Gradient Boosting Classifier  84.77\n",
       "0       Support Vector Machines  82.74\n",
       "7                 Decision Tree  82.74\n",
       "1                           KNN  81.22\n",
       "2           Logistic Regression  79.19\n",
       "4                   Naive Bayes  78.68\n",
       "6                    Linear SVC  78.17\n",
       "5                    Perceptron  76.65\n",
       "8   Stochastic Gradient Descent  71.07"
      ]
     },
     "execution_count": 87,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "models = pd.DataFrame({\n",
    "    'Model': ['Support Vector Machines', 'KNN', 'Logistic Regression', \n",
    "              'Random Forest', 'Naive Bayes', 'Perceptron', 'Linear SVC', \n",
    "              'Decision Tree', 'Stochastic Gradient Descent', 'Gradient Boosting Classifier'],\n",
    "    'Score': [acc_svc, acc_knn, acc_logreg, \n",
    "              acc_randomforest, acc_gaussian, acc_perceptron,acc_linear_svc, acc_decisiontree,\n",
    "              acc_sgd, acc_gbk]})\n",
    "models.sort_values(by='Score', ascending=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 418 entries, 0 to 417\n",
      "Data columns (total 9 columns):\n",
      " #   Column       Non-Null Count  Dtype   \n",
      "---  ------       --------------  -----   \n",
      " 0   PassengerId  418 non-null    int64   \n",
      " 1   Pclass       418 non-null    int64   \n",
      " 2   Sex          418 non-null    int64   \n",
      " 3   SibSp        418 non-null    int64   \n",
      " 4   Parch        418 non-null    int64   \n",
      " 5   Embarked     418 non-null    int64   \n",
      " 6   AgeGroup     418 non-null    float64 \n",
      " 7   Title        418 non-null    int64   \n",
      " 8   FareBand     418 non-null    category\n",
      "dtypes: category(1), float64(1), int64(7)\n",
      "memory usage: 26.8 KB\n"
     ]
    }
   ],
   "source": [
    "test.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0 0 0 0 0 0 0 0 1 0 0 1 1 0 1 1 0 0 0 1 1 1 1 0 1 0 1 0 1 0 0 0 1 0 1 0 0\n",
      " 0 0 0 0 1 0 1 1 0 0 0 1 0 0 0 1 1 0 0 0 0 0 1 0 0 0 1 1 1 1 0 1 1 1 0 1 1\n",
      " 1 1 0 1 0 1 1 0 1 0 0 0 0 1 1 1 0 0 0 0 1 0 1 0 1 0 1 0 0 0 1 0 0 0 0 0 0\n",
      " 1 1 1 1 0 0 1 0 1 1 0 1 0 0 0 0 1 0 0 0 1 0 0 0 0 0 0 0 0 0 1 0 0 1 0 0 0\n",
      " 1 0 1 0 0 0 0 0 1 1 1 1 1 1 1 0 0 1 0 0 1 0 0 0 1 0 0 1 1 1 1 1 0 0 1 0 1\n",
      " 0 1 0 0 0 0 1 1 0 1 0 1 1 0 0 1 1 1 1 0 0 0 0 1 0 0 0 0 1 0 0 1 1 1 0 1 0\n",
      " 1 0 1 1 0 1 0 0 0 1 0 0 1 0 0 0 1 1 1 1 0 0 1 0 1 0 1 0 1 0 1 0 0 0 0 0 1\n",
      " 0 0 0 1 1 0 0 0 0 0 0 0 0 1 1 0 1 0 0 0 0 0 1 1 0 1 0 0 0 0 0 0 0 0 1 0 0\n",
      " 1 0 0 0 0 0 0 0 1 1 0 1 1 0 0 0 0 1 1 1 1 0 0 0 0 0 0 1 1 0 1 0 0 0 1 0 0\n",
      " 1 0 1 0 0 0 1 0 0 0 1 1 1 0 1 0 1 1 0 0 0 1 1 1 0 0 0 0 1 1 0 1 0 0 0 1 0\n",
      " 0 1 0 0 1 1 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 1 1 0 0 1 0 1 0 0 1 0 1 0 0 0 0\n",
      " 0 1 1 1 1 0 0 1 0 0 1]\n"
     ]
    }
   ],
   "source": [
    "#set ids as PassengerId and predict survival zids = test['PassengerId']\n",
    "ids = test['PassengerId']\n",
    "predictions = randomforest.predict(test.drop('PassengerId', axis=1))\n",
    "print(predictions)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "metadata": {},
   "outputs": [],
   "source": [
    "#set the output as a dataframe and convert to csv file named submission.csv\n",
    "output = pd.DataFrame({ 'PassengerId' : ids, 'Survived': predictions })\n",
    "output.to_csv('submission.csv', index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "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",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>892</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>893</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>894</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>895</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>896</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>413</th>\n",
       "      <td>1305</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>414</th>\n",
       "      <td>1306</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>415</th>\n",
       "      <td>1307</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>416</th>\n",
       "      <td>1308</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>417</th>\n",
       "      <td>1309</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>418 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     PassengerId  Survived\n",
       "0            892         0\n",
       "1            893         0\n",
       "2            894         0\n",
       "3            895         0\n",
       "4            896         0\n",
       "..           ...       ...\n",
       "413         1305         0\n",
       "414         1306         1\n",
       "415         1307         0\n",
       "416         1308         0\n",
       "417         1309         1\n",
       "\n",
       "[418 rows x 2 columns]"
      ]
     },
     "execution_count": 91,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "output"
   ]
  },
  {
   "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": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}