titanic-survival-model.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "02af92c4",
   "metadata": {
    "_cell_guid": "b1076dfc-b9ad-4769-8c92-a6c4dae69d19",
    "_uuid": "8f2839f25d086af736a60e9eeb907d3b93b6e0e5",
    "execution": {
     "iopub.execute_input": "2022-03-03T06:26:42.135405Z",
     "iopub.status.busy": "2022-03-03T06:26:42.134496Z",
     "iopub.status.idle": "2022-03-03T06:26:42.142660Z",
     "shell.execute_reply": "2022-03-03T06:26:42.141833Z",
     "shell.execute_reply.started": "2022-03-03T06:24:03.861683Z"
    },
    "papermill": {
     "duration": 0.039669,
     "end_time": "2022-03-03T06:26:42.142886",
     "exception": false,
     "start_time": "2022-03-03T06:26:42.103217",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "/kaggle/input/titanic/train.csv\n",
      "/kaggle/input/titanic/test.csv\n",
      "/kaggle/input/titanic/gender_submission.csv\n"
     ]
    }
   ],
   "source": [
    "# This Python 3 environment comes with many helpful analytics libraries installed\n",
    "# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n",
    "# For example, here's several helpful packages to load\n",
    "\n",
    "import numpy as np # linear algebra\n",
    "import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n",
    "\n",
    "# Input data files are available in the read-only \"../input/\" directory\n",
    "# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n",
    "\n",
    "import os\n",
    "for dirname, _, filenames in os.walk('/kaggle/input'):\n",
    "    for filename in filenames:\n",
    "        print(os.path.join(dirname, filename))\n",
    "\n",
    "# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n",
    "# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5dd02c99",
   "metadata": {
    "papermill": {
     "duration": 0.020919,
     "end_time": "2022-03-03T06:26:42.185627",
     "exception": false,
     "start_time": "2022-03-03T06:26:42.164708",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# Import Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "e9711c36",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-03-03T06:26:42.231144Z",
     "iopub.status.busy": "2022-03-03T06:26:42.230159Z",
     "iopub.status.idle": "2022-03-03T06:26:42.266550Z",
     "shell.execute_reply": "2022-03-03T06:26:42.267502Z",
     "shell.execute_reply.started": "2022-03-03T06:24:03.875521Z"
    },
    "papermill": {
     "duration": 0.062152,
     "end_time": "2022-03-03T06:26:42.267756",
     "exception": false,
     "start_time": "2022-03-03T06:26:42.205604",
     "status": "completed"
    },
    "tags": []
   },
   "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": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# training data (has survived)\n",
    "train_data = pd.read_csv('/kaggle/input/titanic/train.csv')\n",
    "train_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "e6828ded",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-03-03T06:26:42.320525Z",
     "iopub.status.busy": "2022-03-03T06:26:42.319911Z",
     "iopub.status.idle": "2022-03-03T06:26:42.339009Z",
     "shell.execute_reply": "2022-03-03T06:26:42.339705Z",
     "shell.execute_reply.started": "2022-03-03T06:24:03.904241Z"
    },
    "papermill": {
     "duration": 0.045838,
     "end_time": "2022-03-03T06:26:42.339948",
     "exception": false,
     "start_time": "2022-03-03T06:26:42.294110",
     "status": "completed"
    },
    "tags": []
   },
   "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": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# test data\n",
    "test_data = pd.read_csv('/kaggle/input/titanic/test.csv')\n",
    "test_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "48b9b954",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-03-03T06:26:42.394861Z",
     "iopub.status.busy": "2022-03-03T06:26:42.394216Z",
     "iopub.status.idle": "2022-03-03T06:26:42.415916Z",
     "shell.execute_reply": "2022-03-03T06:26:42.415405Z",
     "shell.execute_reply.started": "2022-03-03T06:24:03.927596Z"
    },
    "papermill": {
     "duration": 0.051613,
     "end_time": "2022-03-03T06:26:42.416071",
     "exception": false,
     "start_time": "2022-03-03T06:26:42.364458",
     "status": "completed"
    },
    "tags": []
   },
   "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></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 rowspan=\"5\" valign=\"top\">train</th>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0.0</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>1.0</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>1.0</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>1.0</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>0.0</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",
       "train 0            1       0.0       3   \n",
       "      1            2       1.0       1   \n",
       "      2            3       1.0       3   \n",
       "      3            4       1.0       1   \n",
       "      4            5       0.0       3   \n",
       "\n",
       "                                                      Name     Sex   Age  \\\n",
       "train 0                            Braund, Mr. Owen Harris    male  22.0   \n",
       "      1  Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0   \n",
       "      2                             Heikkinen, Miss. Laina  female  26.0   \n",
       "      3       Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0   \n",
       "      4                           Allen, Mr. William Henry    male  35.0   \n",
       "\n",
       "         SibSp  Parch            Ticket     Fare Cabin Embarked  \n",
       "train 0      1      0         A/5 21171   7.2500   NaN        S  \n",
       "      1      1      0          PC 17599  71.2833   C85        C  \n",
       "      2      0      0  STON/O2. 3101282   7.9250   NaN        S  \n",
       "      3      1      0            113803  53.1000  C123        S  \n",
       "      4      0      0            373450   8.0500   NaN        S  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# combined data (for imputing missing values)\n",
    "comb_data = pd.concat([train_data,test_data],keys=['train', 'test'])\n",
    "comb_data.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "471515fd",
   "metadata": {
    "papermill": {
     "duration": 0.021455,
     "end_time": "2022-03-03T06:26:42.459891",
     "exception": false,
     "start_time": "2022-03-03T06:26:42.438436",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# Check for missing values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "ddd8bb82",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-03-03T06:26:42.510964Z",
     "iopub.status.busy": "2022-03-03T06:26:42.510355Z",
     "iopub.status.idle": "2022-03-03T06:26:42.520710Z",
     "shell.execute_reply": "2022-03-03T06:26:42.520188Z",
     "shell.execute_reply.started": "2022-03-03T06:24:03.951265Z"
    },
    "papermill": {
     "duration": 0.039855,
     "end_time": "2022-03-03T06:26:42.520851",
     "exception": false,
     "start_time": "2022-03-03T06:26:42.480996",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Survived     418\n",
      "Age          263\n",
      "Fare           1\n",
      "Cabin       1014\n",
      "Embarked       2\n",
      "dtype: int64\n"
     ]
    }
   ],
   "source": [
    "cols = [col for col in comb_data.columns if comb_data[col].isna().any()]\n",
    "print(comb_data[cols].isna().sum())"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5ee63607",
   "metadata": {
    "papermill": {
     "duration": 0.023122,
     "end_time": "2022-03-03T06:26:42.565925",
     "exception": false,
     "start_time": "2022-03-03T06:26:42.542803",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# Features\n",
    "1. Calculate family size, isAlone\n",
    "2. Extract titles and bin\n",
    "3. Normalize fare \n",
    "4. Extract deck from cabin information\n",
    "5. Fill missing fare (mean, given other information)\n",
    "6. Fill missing ages (median, from other information), bin ages\n",
    "7. Fill missing cabin (create seperate catergory for unknown cabin)\n",
    "8. Fill missing embarked (mode, given other information?)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7f30ca44",
   "metadata": {
    "papermill": {
     "duration": 0.022284,
     "end_time": "2022-03-03T06:26:42.611419",
     "exception": false,
     "start_time": "2022-03-03T06:26:42.589135",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "**1. Family size**\n",
    "\n",
    "The fields *Parch* and *Sibsp* allow us to create a 'family size' feature and 'alone' feature. Later: We may also be able to extract a 'party size' feature from ticket and cabin info. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "7fd5acb6",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-03-03T06:26:42.682503Z",
     "iopub.status.busy": "2022-03-03T06:26:42.656661Z",
     "iopub.status.idle": "2022-03-03T06:26:42.690070Z",
     "shell.execute_reply": "2022-03-03T06:26:42.690593Z",
     "shell.execute_reply.started": "2022-03-03T06:24:03.967669Z"
    },
    "papermill": {
     "duration": 0.057929,
     "end_time": "2022-03-03T06:26:42.690785",
     "exception": false,
     "start_time": "2022-03-03T06:26:42.632856",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "FamilySize  Pclass\n",
      "1           1         0.532110\n",
      "            2         0.346154\n",
      "            3         0.212963\n",
      "2           1         0.728571\n",
      "            2         0.529412\n",
      "            3         0.350877\n",
      "3           1         0.750000\n",
      "            2         0.677419\n",
      "            3         0.425532\n",
      "4           1         0.714286\n",
      "            2         0.769231\n",
      "            3         0.666667\n",
      "5           1         1.000000\n",
      "            2         1.000000\n",
      "            3         0.000000\n",
      "6           1         0.500000\n",
      "            2         1.000000\n",
      "            3         0.000000\n",
      "7           3         0.333333\n",
      "8           3         0.000000\n",
      "11          3         0.000000\n",
      "Name: Survived, dtype: float64\n"
     ]
    }
   ],
   "source": [
    "def family_size(row):\n",
    "    family_size = int(row['Parch']) + int(row['SibSp']) + 1\n",
    "    isAlone = (family_size == 1)\n",
    "    return family_size\n",
    "\n",
    "comb_data['FamilySize'] = comb_data.apply(lambda row: family_size(row), axis=1)\n",
    "\n",
    "family_map = {1: 'Alone', 2: 'Couple', 3: 'Small', 4: 'Small', 5: 'Large', 6: 'Large', 7: 'Large', 8: 'Large', 11: 'Large'}\n",
    "\n",
    "comb_data['FamilySizeMap'] = comb_data['FamilySize'].map(lambda x: family_map[x])\n",
    "\n",
    "print(comb_data.groupby(['FamilySize','Pclass'])['Survived'].mean())"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "677bb144",
   "metadata": {
    "papermill": {
     "duration": 0.023106,
     "end_time": "2022-03-03T06:26:42.737034",
     "exception": false,
     "start_time": "2022-03-03T06:26:42.713928",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "**2. Extract titles and bin**\n",
    "\n",
    "We can see the names are impeccably formatted to {Last Name}, {Title}. {Given Names} ({Actual name, if female and married}). So, there's a couple of bits of info to pull: title, and martial status"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "6bd6216b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-03-03T06:26:42.791466Z",
     "iopub.status.busy": "2022-03-03T06:26:42.790829Z",
     "iopub.status.idle": "2022-03-03T06:26:42.820088Z",
     "shell.execute_reply": "2022-03-03T06:26:42.819368Z",
     "shell.execute_reply.started": "2022-03-03T06:24:04.003413Z"
    },
    "papermill": {
     "duration": 0.057526,
     "end_time": "2022-03-03T06:26:42.820248",
     "exception": false,
     "start_time": "2022-03-03T06:26:42.762722",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Mr Mr\n",
      "Mrs Mrs\n",
      "Miss Miss\n",
      "Master Master\n",
      "Don Noble\n",
      "Rev Occupation\n",
      "Dr Occupation\n",
      "Mme Mrs\n",
      "Ms Miss\n",
      "Major Occupation\n",
      "Lady Noble\n",
      "Sir Noble\n",
      "Mlle Miss\n",
      "Col Occupation\n",
      "Capt Occupation\n",
      "the Countess Noble\n",
      "Jonkheer Noble\n",
      "Dona Noble\n",
      "[('Mr', 757), ('Miss', 264), ('Mrs', 198), ('Master', 61), ('Occupation', 23), ('Noble', 6)]\n"
     ]
    }
   ],
   "source": [
    "import re  # regex\n",
    "\n",
    "def title_from_name(name):\n",
    "    result = re.search(',\\s(.*?)\\.',name) # find characters between comma and space, and period. Non-greedy.\n",
    "    return result.group(1)\n",
    "\n",
    "title_freq = {}\n",
    "\n",
    "for n in comb_data['Name']:\n",
    "    if type(n) == str:\n",
    "        t = title_from_name(n)\n",
    "        if t:\n",
    "            title_freq[t] = 1 + title_freq.get(t,0)\n",
    "\n",
    "#print(title_freq.keys())          \n",
    "#print([(k,title_freq[k]) for k in sorted(title_freq,key=title_freq.get,reverse=True)])\n",
    "\n",
    "# from inspection\n",
    "title_map = {\n",
    "    'Mr': 'Mr', \n",
    "    'Mrs': 'Mrs', \n",
    "    'Miss': 'Miss', \n",
    "    'Master': 'Master', \n",
    "    'Don': 'Noble', \n",
    "    'Rev': 'Occupation', \n",
    "    'Dr': 'Occupation', \n",
    "    'Mme': 'Mrs', \n",
    "    'Ms': 'Miss', \n",
    "    'Major': 'Occupation', \n",
    "    'Lady': 'Noble', \n",
    "    'Sir': 'Noble', \n",
    "    'Mlle': 'Miss', \n",
    "    'Col': 'Occupation', \n",
    "    'Capt': 'Occupation',\n",
    "    'the Countess': 'Noble', \n",
    "    'Jonkheer': 'Noble', \n",
    "    'Dona': 'Noble'\n",
    "}\n",
    "\n",
    "title_map_freq = {}\n",
    "for k,v in title_map.items():\n",
    "    print(k,v)\n",
    "    title_map_freq[v] = title_freq[k] + title_map_freq.get(v,0)\n",
    "    \n",
    "print([(k,title_map_freq[k]) for k in sorted(title_map_freq,key=title_map_freq.get,reverse=True)])\n",
    "\n",
    "comb_data['Title'] = comb_data['Name'].map(lambda x: title_from_name(x))\n",
    "comb_data['TitleMap'] = comb_data['Name'].map(lambda x: title_map[title_from_name(x)])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8e2038f2",
   "metadata": {
    "papermill": {
     "duration": 0.021866,
     "end_time": "2022-03-03T06:26:42.868095",
     "exception": false,
     "start_time": "2022-03-03T06:26:42.846229",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "**3. Normalise fare**\n",
    "\n",
    "Use log transformation. Could use "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "1951f32d",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-03-03T06:26:42.921385Z",
     "iopub.status.busy": "2022-03-03T06:26:42.916456Z",
     "iopub.status.idle": "2022-03-03T06:26:44.443452Z",
     "shell.execute_reply": "2022-03-03T06:26:44.443925Z",
     "shell.execute_reply.started": "2022-03-03T06:24:04.029478Z"
    },
    "papermill": {
     "duration": 1.552672,
     "end_time": "2022-03-03T06:26:44.444116",
     "exception": false,
     "start_time": "2022-03-03T06:26:42.891444",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Pclass  TitleMap    Sex   \n",
      "1       Master      male      14.400000\n",
      "        Miss        female    13.467742\n",
      "        Mr          male      11.447368\n",
      "        Mrs         female    12.717949\n",
      "        Noble       female    12.666667\n",
      "                    male      11.000000\n",
      "        Occupation  female     9.000000\n",
      "                    male      11.416667\n",
      "2       Master      male       9.272727\n",
      "        Miss        female     8.529412\n",
      "        Mr          male       8.090278\n",
      "        Mrs         female     8.872727\n",
      "        Occupation  male       7.800000\n",
      "3       Master      male       9.136364\n",
      "        Miss        female     7.145695\n",
      "        Mr          male       6.607710\n",
      "        Mrs         female     8.046154\n",
      "Name: LogFare, dtype: float64\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1584x576 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "import math\n",
    "\n",
    "def log_fare(x):\n",
    "    try:\n",
    "        norm = int(3*math.log(x+1))\n",
    "        if norm < 6:\n",
    "            return np.nan\n",
    "        else:\n",
    "            return norm\n",
    "    except:\n",
    "        return np.nan\n",
    "\n",
    "comb_data['LogFare'] = comb_data['Fare'].map(lambda x: log_fare(x))\n",
    "\n",
    "print(comb_data.groupby(['Pclass','TitleMap','Sex'])['LogFare'].mean())\n",
    "\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "fig, axes = plt.subplots(figsize=(22,8), nrows = 1, ncols = 2)\n",
    "ax = sns.countplot(x ='LogFare', hue='Pclass', data = comb_data, ax = axes[0])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a773a0b4",
   "metadata": {
    "papermill": {
     "duration": 0.023006,
     "end_time": "2022-03-03T06:26:44.490600",
     "exception": false,
     "start_time": "2022-03-03T06:26:44.467594",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "**4. Extract deck from cabin info**\n",
    "\n",
    "First letter is the deck"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "ca80f30c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-03-03T06:26:44.547864Z",
     "iopub.status.busy": "2022-03-03T06:26:44.546885Z",
     "iopub.status.idle": "2022-03-03T06:26:44.550819Z",
     "shell.execute_reply": "2022-03-03T06:26:44.551362Z",
     "shell.execute_reply.started": "2022-03-03T06:24:04.537360Z"
    },
    "papermill": {
     "duration": 0.037375,
     "end_time": "2022-03-03T06:26:44.551525",
     "exception": false,
     "start_time": "2022-03-03T06:26:44.514150",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "# first letter is the deck\n",
    "def extract_deck(s):\n",
    "    try:\n",
    "        return s[0]\n",
    "    except:\n",
    "        return ''\n",
    "\n",
    "comb_data['Deck'] = comb_data['Cabin'].map(lambda x: extract_deck(x))\n",
    "\n",
    "deck_map = {'A': 'ABC','B': 'ABC','C': 'ABC','D': 'D', 'E': 'E', 'F':'F', 'G':'GT', 'T':'GT'}\n",
    "\n",
    "def map_deck(s):\n",
    "    if s:\n",
    "        return deck_map[s]\n",
    "    else:\n",
    "        return 'unknown'\n",
    "    \n",
    "comb_data['DeckMap'] = comb_data['Deck'].map(lambda x: map_deck(x))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "23ac1bad",
   "metadata": {
    "papermill": {
     "duration": 0.023269,
     "end_time": "2022-03-03T06:26:44.598152",
     "exception": false,
     "start_time": "2022-03-03T06:26:44.574883",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "**5. Fill missing fare**\n",
    "\n",
    "Details: 3rd class, alone, male, 60 years old, embarked at S... The most significant of those is the class, so value should probably be around the mean for 3rd Class fares. Check the difference with the other info."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "18f12a62",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-03-03T06:26:44.648864Z",
     "iopub.status.busy": "2022-03-03T06:26:44.647942Z",
     "iopub.status.idle": "2022-03-03T06:26:44.675576Z",
     "shell.execute_reply": "2022-03-03T06:26:44.675007Z",
     "shell.execute_reply.started": "2022-03-03T06:24:04.548410Z"
    },
    "papermill": {
     "duration": 0.053969,
     "end_time": "2022-03-03T06:26:44.675739",
     "exception": false,
     "start_time": "2022-03-03T06:26:44.621770",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "comb_data['LogFare'] = comb_data.groupby(['Pclass','Sex','TitleMap','FamilySizeMap'])['LogFare'].apply(lambda x: x.fillna(x.median()))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "79d27756",
   "metadata": {
    "papermill": {
     "duration": 0.023192,
     "end_time": "2022-03-03T06:26:44.722577",
     "exception": false,
     "start_time": "2022-03-03T06:26:44.699385",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "**6. Fill missing ages**\n",
    "\n",
    "Based it on class, gender, title, family size"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "d1e6f657",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-03-03T06:26:44.773149Z",
     "iopub.status.busy": "2022-03-03T06:26:44.772571Z",
     "iopub.status.idle": "2022-03-03T06:26:44.825877Z",
     "shell.execute_reply": "2022-03-03T06:26:44.826325Z",
     "shell.execute_reply.started": "2022-03-03T06:24:04.590050Z"
    },
    "papermill": {
     "duration": 0.080558,
     "end_time": "2022-03-03T06:26:44.826498",
     "exception": false,
     "start_time": "2022-03-03T06:26:44.745940",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Pclass  Sex     TitleMap    FamilySizeMap\n",
      "1       female  Miss        Alone            32.00\n",
      "                            Couple           22.00\n",
      "                            Large            23.00\n",
      "                            Small            20.50\n",
      "                Mrs         Alone            54.00\n",
      "                            Couple           41.00\n",
      "                            Large            54.00\n",
      "                            Small            47.50\n",
      "                Noble       Alone            36.00\n",
      "                            Couple           48.00\n",
      "                Occupation  Alone            49.00\n",
      "        male    Master      Large            13.00\n",
      "                            Small             5.00\n",
      "                Mr          Alone            42.00\n",
      "                            Couple           38.00\n",
      "                            Large            61.00\n",
      "                            Small            47.00\n",
      "                Noble       Alone            39.00\n",
      "                            Couple           49.00\n",
      "                Occupation  Alone            52.50\n",
      "                            Couple           47.00\n",
      "                            Small            51.50\n",
      "2       female  Miss        Alone            28.00\n",
      "                            Couple           20.00\n",
      "                            Small             8.00\n",
      "                Mrs         Alone            32.00\n",
      "                            Couple           29.00\n",
      "                            Large            39.00\n",
      "                            Small            32.00\n",
      "        male    Master      Small             2.00\n",
      "                Mr          Alone            29.00\n",
      "                            Couple           33.25\n",
      "                            Small            31.00\n",
      "                Occupation  Alone            42.00\n",
      "                            Couple           41.00\n",
      "                            Small            30.00\n",
      "3       female  Miss        Alone            22.00\n",
      "                            Couple           17.50\n",
      "                            Large             9.00\n",
      "                            Small             3.00\n",
      "                Mrs         Alone            38.00\n",
      "                            Couple           28.50\n",
      "                            Large            40.00\n",
      "                            Small            29.00\n",
      "        male    Master      Alone              NaN\n",
      "                            Couple            6.00\n",
      "                            Large             6.00\n",
      "                            Small             6.00\n",
      "                Mr          Alone            26.00\n",
      "                            Couple           26.00\n",
      "                            Large            23.50\n",
      "                            Small            26.00\n",
      "Name: Age, dtype: float64\n",
      "False\n"
     ]
    }
   ],
   "source": [
    "print(comb_data.groupby(['Pclass','Sex','TitleMap','FamilySizeMap'])['Age'].median())\n",
    "comb_data['Age'] = comb_data.groupby(['Pclass','Sex','TitleMap','FamilySizeMap'])['Age'].apply(lambda x: x.fillna(x.median()))\n",
    "\n",
    "if comb_data['Age'].isna().any():\n",
    "    comb_data['Age'] = comb_data.groupby(['Pclass','Sex','TitleMap'])['Age'].apply(lambda x: x.fillna(x.median()))\n",
    "    \n",
    "print(comb_data['Age'].isna().any())\n",
    "\n",
    "comb_data['AgeBin'] = pd.cut(comb_data['Age'], bins=7, labels=None)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a94dcada",
   "metadata": {
    "papermill": {
     "duration": 0.024231,
     "end_time": "2022-03-03T06:26:44.874612",
     "exception": false,
     "start_time": "2022-03-03T06:26:44.850381",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "**8. Fill missing embarked (mode, given other information?)**\n",
    "\n",
    "Use mode..."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "fadaf7e8",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-03-03T06:26:44.930169Z",
     "iopub.status.busy": "2022-03-03T06:26:44.929530Z",
     "iopub.status.idle": "2022-03-03T06:26:44.947226Z",
     "shell.execute_reply": "2022-03-03T06:26:44.947672Z",
     "shell.execute_reply.started": "2022-03-03T06:24:04.642790Z"
    },
    "papermill": {
     "duration": 0.048439,
     "end_time": "2022-03-03T06:26:44.947879",
     "exception": false,
     "start_time": "2022-03-03T06:26:44.899440",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "comb_data['Embarked'] = comb_data.groupby(['Pclass','Sex','TitleMap'])['Embarked'].apply(lambda x: x.fillna(x.mode()[0]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "7bd96471",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-03-03T06:26:45.008435Z",
     "iopub.status.busy": "2022-03-03T06:26:45.007582Z",
     "iopub.status.idle": "2022-03-03T06:26:45.015342Z",
     "shell.execute_reply": "2022-03-03T06:26:45.014886Z",
     "shell.execute_reply.started": "2022-03-03T06:24:04.665688Z"
    },
    "papermill": {
     "duration": 0.043603,
     "end_time": "2022-03-03T06:26:45.015480",
     "exception": false,
     "start_time": "2022-03-03T06:26:44.971877",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Survived     418\n",
      "Fare           1\n",
      "Cabin       1014\n",
      "dtype: int64\n"
     ]
    }
   ],
   "source": [
    "cols = [col for col in comb_data.columns if comb_data[col].isna().any()]\n",
    "print(comb_data[cols].isna().sum())"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dadaea08",
   "metadata": {
    "papermill": {
     "duration": 0.024606,
     "end_time": "2022-03-03T06:26:45.064284",
     "exception": false,
     "start_time": "2022-03-03T06:26:45.039678",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# Encoding\n",
    "\n",
    "Convert categorical fields to using one hot-encoding"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "4b66f603",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-03-03T06:26:45.124606Z",
     "iopub.status.busy": "2022-03-03T06:26:45.123734Z",
     "iopub.status.idle": "2022-03-03T06:26:45.159070Z",
     "shell.execute_reply": "2022-03-03T06:26:45.158549Z",
     "shell.execute_reply.started": "2022-03-03T06:24:36.410620Z"
    },
    "papermill": {
     "duration": 0.06988,
     "end_time": "2022-03-03T06:26:45.159206",
     "exception": false,
     "start_time": "2022-03-03T06:26:45.089326",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['Sex', 'TitleMap', 'FamilySizeMap', 'Embarked', 'DeckMap', 'AgeBin']\n"
     ]
    },
    {
     "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></th>\n",
       "      <th>PassengerId</th>\n",
       "      <th>Survived</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>LogFare</th>\n",
       "      <th>Parch</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Sex_female</th>\n",
       "      <th>Sex_male</th>\n",
       "      <th>TitleMap_Master</th>\n",
       "      <th>TitleMap_Miss</th>\n",
       "      <th>...</th>\n",
       "      <th>DeckMap_F</th>\n",
       "      <th>DeckMap_GT</th>\n",
       "      <th>DeckMap_unknown</th>\n",
       "      <th>AgeBin_(0.0902, 11.574]</th>\n",
       "      <th>AgeBin_(11.574, 22.979]</th>\n",
       "      <th>AgeBin_(22.979, 34.383]</th>\n",
       "      <th>AgeBin_(34.383, 45.787]</th>\n",
       "      <th>AgeBin_(45.787, 57.191]</th>\n",
       "      <th>AgeBin_(57.191, 68.596]</th>\n",
       "      <th>AgeBin_(68.596, 80.0]</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"5\" valign=\"top\">train</th>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3</td>\n",
       "      <td>6.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "      <td>12.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3</td>\n",
       "      <td>6.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "      <td>11.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3</td>\n",
       "      <td>6.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 34 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "         PassengerId  Survived  Pclass  LogFare  Parch  SibSp  Sex_female  \\\n",
       "train 0            1       0.0       3      6.0      0      1           0   \n",
       "      1            2       1.0       1     12.0      0      1           1   \n",
       "      2            3       1.0       3      6.0      0      0           1   \n",
       "      3            4       1.0       1     11.0      0      1           1   \n",
       "      4            5       0.0       3      6.0      0      0           0   \n",
       "\n",
       "         Sex_male  TitleMap_Master  TitleMap_Miss  ...  DeckMap_F  DeckMap_GT  \\\n",
       "train 0         1                0              0  ...          0           0   \n",
       "      1         0                0              0  ...          0           0   \n",
       "      2         0                0              1  ...          0           0   \n",
       "      3         0                0              0  ...          0           0   \n",
       "      4         1                0              0  ...          0           0   \n",
       "\n",
       "         DeckMap_unknown  AgeBin_(0.0902, 11.574]  AgeBin_(11.574, 22.979]  \\\n",
       "train 0                1                        0                        1   \n",
       "      1                0                        0                        0   \n",
       "      2                1                        0                        0   \n",
       "      3                0                        0                        0   \n",
       "      4                1                        0                        0   \n",
       "\n",
       "         AgeBin_(22.979, 34.383]  AgeBin_(34.383, 45.787]  \\\n",
       "train 0                        0                        0   \n",
       "      1                        0                        1   \n",
       "      2                        1                        0   \n",
       "      3                        0                        1   \n",
       "      4                        0                        1   \n",
       "\n",
       "         AgeBin_(45.787, 57.191]  AgeBin_(57.191, 68.596]  \\\n",
       "train 0                        0                        0   \n",
       "      1                        0                        0   \n",
       "      2                        0                        0   \n",
       "      3                        0                        0   \n",
       "      4                        0                        0   \n",
       "\n",
       "         AgeBin_(68.596, 80.0]  \n",
       "train 0                      0  \n",
       "      1                      0  \n",
       "      2                      0  \n",
       "      3                      0  \n",
       "      4                      0  \n",
       "\n",
       "[5 rows x 34 columns]"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data = comb_data[['PassengerId','Survived','Pclass','Sex','LogFare','TitleMap','FamilySizeMap','Embarked','DeckMap','Parch','SibSp','AgeBin']]\n",
    "category_cols = [col for col in data.columns if data[col].dtype == object] + ['AgeBin']\n",
    "print(category_cols)\n",
    "encoded_columns = pd.get_dummies(data[category_cols],prefix=category_cols,columns=category_cols)\n",
    "data = data.join(encoded_columns).drop(category_cols, axis=1)\n",
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "58823876",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-03-03T06:26:45.214869Z",
     "iopub.status.busy": "2022-03-03T06:26:45.214253Z",
     "iopub.status.idle": "2022-03-03T06:26:45.217645Z",
     "shell.execute_reply": "2022-03-03T06:26:45.217179Z",
     "shell.execute_reply.started": "2022-03-03T06:25:40.414567Z"
    },
    "papermill": {
     "duration": 0.033515,
     "end_time": "2022-03-03T06:26:45.217795",
     "exception": false,
     "start_time": "2022-03-03T06:26:45.184280",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "train_data = data.loc['train',:]\n",
    "test_data = data.loc['test',:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "1e004bf6",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-03-03T06:26:45.286493Z",
     "iopub.status.busy": "2022-03-03T06:26:45.285856Z",
     "iopub.status.idle": "2022-03-03T06:26:45.289459Z",
     "shell.execute_reply": "2022-03-03T06:26:45.288884Z",
     "shell.execute_reply.started": "2022-03-03T06:24:04.728854Z"
    },
    "papermill": {
     "duration": 0.046789,
     "end_time": "2022-03-03T06:26:45.289590",
     "exception": false,
     "start_time": "2022-03-03T06:26:45.242801",
     "status": "completed"
    },
    "tags": []
   },
   "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>LogFare</th>\n",
       "      <th>Parch</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Sex_female</th>\n",
       "      <th>Sex_male</th>\n",
       "      <th>TitleMap_Master</th>\n",
       "      <th>TitleMap_Miss</th>\n",
       "      <th>...</th>\n",
       "      <th>DeckMap_F</th>\n",
       "      <th>DeckMap_GT</th>\n",
       "      <th>DeckMap_unknown</th>\n",
       "      <th>AgeBin_(0.0902, 11.574]</th>\n",
       "      <th>AgeBin_(11.574, 22.979]</th>\n",
       "      <th>AgeBin_(22.979, 34.383]</th>\n",
       "      <th>AgeBin_(34.383, 45.787]</th>\n",
       "      <th>AgeBin_(45.787, 57.191]</th>\n",
       "      <th>AgeBin_(57.191, 68.596]</th>\n",
       "      <th>AgeBin_(68.596, 80.0]</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>892</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3</td>\n",
       "      <td>6.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>893</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3</td>\n",
       "      <td>6.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>894</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2</td>\n",
       "      <td>7.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>895</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3</td>\n",
       "      <td>6.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>896</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3</td>\n",
       "      <td>7.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 34 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   PassengerId  Survived  Pclass  LogFare  Parch  SibSp  Sex_female  Sex_male  \\\n",
       "0          892       NaN       3      6.0      0      0           0         1   \n",
       "1          893       NaN       3      6.0      0      1           1         0   \n",
       "2          894       NaN       2      7.0      0      0           0         1   \n",
       "3          895       NaN       3      6.0      0      0           0         1   \n",
       "4          896       NaN       3      7.0      1      1           1         0   \n",
       "\n",
       "   TitleMap_Master  TitleMap_Miss  ...  DeckMap_F  DeckMap_GT  \\\n",
       "0                0              0  ...          0           0   \n",
       "1                0              0  ...          0           0   \n",
       "2                0              0  ...          0           0   \n",
       "3                0              0  ...          0           0   \n",
       "4                0              0  ...          0           0   \n",
       "\n",
       "   DeckMap_unknown  AgeBin_(0.0902, 11.574]  AgeBin_(11.574, 22.979]  \\\n",
       "0                1                        0                        0   \n",
       "1                1                        0                        0   \n",
       "2                1                        0                        0   \n",
       "3                1                        0                        0   \n",
       "4                1                        0                        1   \n",
       "\n",
       "   AgeBin_(22.979, 34.383]  AgeBin_(34.383, 45.787]  AgeBin_(45.787, 57.191]  \\\n",
       "0                        0                        1                        0   \n",
       "1                        0                        0                        1   \n",
       "2                        0                        0                        0   \n",
       "3                        1                        0                        0   \n",
       "4                        0                        0                        0   \n",
       "\n",
       "   AgeBin_(57.191, 68.596]  AgeBin_(68.596, 80.0]  \n",
       "0                        0                      0  \n",
       "1                        0                      0  \n",
       "2                        1                      0  \n",
       "3                        0                      0  \n",
       "4                        0                      0  \n",
       "\n",
       "[5 rows x 34 columns]"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_data.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f7d4802c",
   "metadata": {
    "papermill": {
     "duration": 0.025291,
     "end_time": "2022-03-03T06:26:45.340303",
     "exception": false,
     "start_time": "2022-03-03T06:26:45.315012",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# Random Forest Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "6ff0a6a3",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-03-03T06:26:45.398975Z",
     "iopub.status.busy": "2022-03-03T06:26:45.398326Z",
     "iopub.status.idle": "2022-03-03T06:26:45.409110Z",
     "shell.execute_reply": "2022-03-03T06:26:45.408470Z",
     "shell.execute_reply.started": "2022-03-03T06:25:44.129356Z"
    },
    "papermill": {
     "duration": 0.043672,
     "end_time": "2022-03-03T06:26:45.409248",
     "exception": false,
     "start_time": "2022-03-03T06:26:45.365576",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "AgeBin_(0.0902, 11.574] AgeBin_(0.0902, 11.574]\n",
      "AgeBin_(11.574, 22.979] AgeBin_(11.574, 22.979]\n",
      "AgeBin_(22.979, 34.383] AgeBin_(22.979, 34.383]\n",
      "AgeBin_(34.383, 45.787] AgeBin_(34.383, 45.787]\n",
      "AgeBin_(45.787, 57.191] AgeBin_(45.787, 57.191]\n",
      "AgeBin_(57.191, 68.596] AgeBin_(57.191, 68.596]\n",
      "AgeBin_(68.596, 80.0] AgeBin_(68.596, 80.0]\n",
      "DeckMap_ABC DeckMap_ABC\n",
      "DeckMap_D DeckMap_D\n",
      "DeckMap_E DeckMap_E\n",
      "DeckMap_F DeckMap_F\n",
      "DeckMap_GT DeckMap_GT\n",
      "DeckMap_unknown DeckMap_unknown\n",
      "Embarked_C Embarked_C\n",
      "Embarked_Q Embarked_Q\n",
      "Embarked_S Embarked_S\n",
      "FamilySizeMap_Alone FamilySizeMap_Alone\n",
      "FamilySizeMap_Couple FamilySizeMap_Couple\n",
      "FamilySizeMap_Large FamilySizeMap_Large\n",
      "FamilySizeMap_Small FamilySizeMap_Small\n",
      "LogFare LogFare\n",
      "Parch Parch\n",
      "PassengerId PassengerId\n",
      "Pclass Pclass\n",
      "Sex_female Sex_female\n",
      "Sex_male Sex_male\n",
      "SibSp SibSp\n",
      "Survived Survived\n",
      "TitleMap_Master TitleMap_Master\n",
      "TitleMap_Miss TitleMap_Miss\n",
      "TitleMap_Mr TitleMap_Mr\n",
      "TitleMap_Mrs TitleMap_Mrs\n",
      "TitleMap_Noble TitleMap_Noble\n",
      "TitleMap_Occupation TitleMap_Occupation\n",
      "['Pclass', 'LogFare', 'Sex_female', 'Sex_male', 'TitleMap_Master', 'TitleMap_Miss', 'TitleMap_Mr', 'TitleMap_Mrs', 'TitleMap_Noble', 'TitleMap_Occupation', 'FamilySizeMap_Alone', 'FamilySizeMap_Couple', 'FamilySizeMap_Large', 'FamilySizeMap_Small', 'Embarked_C', 'Embarked_Q', 'Embarked_S', 'DeckMap_ABC', 'DeckMap_D', 'DeckMap_E', 'DeckMap_F', 'DeckMap_GT', 'DeckMap_unknown', 'AgeBin_(0.0902, 11.574]', 'AgeBin_(11.574, 22.979]', 'AgeBin_(22.979, 34.383]', 'AgeBin_(34.383, 45.787]', 'AgeBin_(45.787, 57.191]', 'AgeBin_(57.191, 68.596]', 'AgeBin_(68.596, 80.0]']\n"
     ]
    }
   ],
   "source": [
    "# features, not features\n",
    "not_features = ['SibSp','Parch','Survived','PassengerId']\n",
    "features = [col for col in train_data.columns if (not col in not_features) and (not train_data[col].dtype == object)]\n",
    "columns = train_data.columns\n",
    "\n",
    "for x,y in zip(sorted(features + not_features),sorted(columns)):\n",
    "    print(x,y)\n",
    "    \n",
    "print(features)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "9f844938",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-03-03T06:26:45.468231Z",
     "iopub.status.busy": "2022-03-03T06:26:45.467487Z",
     "iopub.status.idle": "2022-03-03T06:26:50.651866Z",
     "shell.execute_reply": "2022-03-03T06:26:50.651181Z",
     "shell.execute_reply.started": "2022-03-03T06:24:04.778337Z"
    },
    "papermill": {
     "duration": 5.216987,
     "end_time": "2022-03-03T06:26:50.652049",
     "exception": false,
     "start_time": "2022-03-03T06:26:45.435062",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=-1)]: Using backend ThreadingBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=-1)]: Done  42 tasks      | elapsed:    0.1s\n",
      "[Parallel(n_jobs=-1)]: Done 192 tasks      | elapsed:    0.3s\n",
      "[Parallel(n_jobs=-1)]: Done 442 tasks      | elapsed:    0.8s\n",
      "[Parallel(n_jobs=-1)]: Done 792 tasks      | elapsed:    1.4s\n",
      "[Parallel(n_jobs=-1)]: Done 1242 tasks      | elapsed:    2.1s\n",
      "[Parallel(n_jobs=-1)]: Done 1750 out of 1750 | elapsed:    2.9s finished\n",
      "[Parallel(n_jobs=4)]: Using backend ThreadingBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=4)]: Done  42 tasks      | elapsed:    0.0s\n",
      "[Parallel(n_jobs=4)]: Done 192 tasks      | elapsed:    0.0s\n",
      "[Parallel(n_jobs=4)]: Done 442 tasks      | elapsed:    0.1s\n",
      "[Parallel(n_jobs=4)]: Done 792 tasks      | elapsed:    0.2s\n",
      "[Parallel(n_jobs=4)]: Done 1242 tasks      | elapsed:    0.3s\n",
      "[Parallel(n_jobs=4)]: Done 1750 out of 1750 | elapsed:    0.4s finished\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Your submission was succesfully saved!\n"
     ]
    }
   ],
   "source": [
    "from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier, GradientBoostingClassifier, ExtraTreesClassifier, VotingClassifier\n",
    "from sklearn.model_selection import GridSearchCV, cross_val_score, StratifiedKFold, learning_curve\n",
    "#from xgboost import XGBClassifier\n",
    "\n",
    "y = train_data['Survived']\n",
    "\n",
    "X = train_data[features] # pd.get_dummies(train_data[features])\n",
    "X_test = test_data[features] # pd.get_dummies(test_data[features])\n",
    "\n",
    "# fit model no training data\n",
    "rfc_single = RandomForestClassifier(criterion='gini',\n",
    "                                           n_estimators=1750,\n",
    "                                           max_depth=7,\n",
    "                                           min_samples_split=6,\n",
    "                                           min_samples_leaf=6,\n",
    "                                           max_features='auto',\n",
    "                                           oob_score=True,\n",
    "                                           random_state=42,\n",
    "                                           n_jobs=-1,\n",
    "                                           verbose=1) \n",
    "rfc_single.fit(X, y)\n",
    "\n",
    "predictions = rfc_single.predict(X_test).astype(int)\n",
    "\n",
    "output = pd.DataFrame({'PassengerId': test_data.PassengerId, 'Survived': predictions})\n",
    "output.to_csv('submission.csv', index=False)\n",
    "print('Your submission was succesfully saved!')"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.12"
  },
  "papermill": {
   "default_parameters": {},
   "duration": 18.040727,
   "end_time": "2022-03-03T06:26:51.390612",
   "environment_variables": {},
   "exception": null,
   "input_path": "__notebook__.ipynb",
   "output_path": "__notebook__.ipynb",
   "parameters": {},
   "start_time": "2022-03-03T06:26:33.349885",
   "version": "2.3.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}