{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This notebook was prepared by [Donne Martin](http://donnemartin.com). Source and license info is on [GitHub](https://github.com/donnemartin/data-science-ipython-notebooks)."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Kaggle Machine Learning Competition: Predicting Titanic Survivors"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* Competition Site\n",
    "* Description\n",
    "* Evaluation\n",
    "* Data Set\n",
    "* Setup Imports and Variables\n",
    "* Explore the Data\n",
    "* Feature: Passenger Classes\n",
    "* Feature: Sex\n",
    "* Feature: Embarked\n",
    "* Feature: Age\n",
    "* Feature: Family Size\n",
    "* Final Data Preparation for Machine Learning\n",
    "* Data Wrangling Summary\n",
    "* Random Forest: Training\n",
    "* Random Forest: Predicting\n",
    "* Random Forest: Prepare for Kaggle Submission\n",
    "* Support Vector Machine: Training\n",
    "* Support Vector Machine: Predicting"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Competition Site"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Description, Evaluation, and Data Set taken from the [competition site](https://www.kaggle.com/c/titanic-gettingStarted)."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Description"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "![alt text](http://upload.wikimedia.org/wikipedia/commons/6/6e/St%C3%B6wer_Titanic.jpg)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The sinking of the RMS Titanic is one of the most infamous shipwrecks in history.  On April 15, 1912, during her maiden voyage, the Titanic sank after colliding with an iceberg, killing 1502 out of 2224 passengers and crew. This sensational tragedy shocked the international community and led to better safety regulations for ships.\n",
    "\n",
    "One of the reasons that the shipwreck led to such loss of life was that there were not enough lifeboats for the passengers and crew. Although there was some element of luck involved in surviving the sinking, some groups of people were more likely to survive than others, such as women, children, and the upper-class.\n",
    "\n",
    "In this challenge, we ask you to complete the analysis of what sorts of people were likely to survive. In particular, we ask you to apply the tools of machine learning to predict which passengers survived the tragedy."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Evaluation"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The historical data has been split into two groups, a 'training set' and a 'test set'.  For the training set, we provide the outcome ( 'ground truth' ) for each passenger.  You will use this set to build your model to generate predictions for the test set.\n",
    "\n",
    "For each passenger in the test set, you must predict whether or not they survived the sinking ( 0 for deceased, 1 for survived ).  Your score is the percentage of passengers you correctly predict.\n",
    "\n",
    " The Kaggle leaderboard has a public and private component.  50% of your predictions for the test set have been randomly assigned to the public leaderboard ( the same 50% for all users ).  Your score on this public portion is what will appear on the leaderboard.  At the end of the contest, we will reveal your score on the private 50% of the data, which will determine the final winner.  This method prevents users from 'overfitting' to the leaderboard."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Data Set"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "| File Name        | Available Formats |\n",
    "|------------------|-------------------|\n",
    "| train            | .csv (59.76 kb)   |\n",
    "| gendermodel      | .csv (3.18 kb)    |\n",
    "| genderclassmodel | .csv (3.18 kb)    |\n",
    "| test             | .csv (27.96 kb)   |\n",
    "| gendermodel      | .py (3.58 kb)     |\n",
    "| genderclassmodel | .py (5.63 kb)     |\n",
    "| myfirstforest    | .py (3.99 kb)     |"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<pre>\n",
    "VARIABLE DESCRIPTIONS:\n",
    "survival        Survival\n",
    "                (0 = No; 1 = Yes)\n",
    "pclass          Passenger Class\n",
    "                (1 = 1st; 2 = 2nd; 3 = 3rd)\n",
    "name            Name\n",
    "sex             Sex\n",
    "age             Age\n",
    "sibsp           Number of Siblings/Spouses Aboard\n",
    "parch           Number of Parents/Children Aboard\n",
    "ticket          Ticket Number\n",
    "fare            Passenger Fare\n",
    "cabin           Cabin\n",
    "embarked        Port of Embarkation\n",
    "                (C = Cherbourg; Q = Queenstown; S = Southampton)\n",
    "\n",
    "SPECIAL NOTES:\n",
    "Pclass is a proxy for socio-economic status (SES)\n",
    " 1st ~ Upper; 2nd ~ Middle; 3rd ~ Lower\n",
    "\n",
    "Age is in Years; Fractional if Age less than One (1)\n",
    " If the Age is Estimated, it is in the form xx.5\n",
    "\n",
    "With respect to the family relation variables (i.e. sibsp and parch)\n",
    "some relations were ignored.  The following are the definitions used\n",
    "for sibsp and parch.\n",
    "\n",
    "Sibling:  Brother, Sister, Stepbrother, or Stepsister of Passenger Aboard Titanic\n",
    "Spouse:   Husband or Wife of Passenger Aboard Titanic (Mistresses and Fiances Ignored)\n",
    "Parent:   Mother or Father of Passenger Aboard Titanic\n",
    "Child:    Son, Daughter, Stepson, or Stepdaughter of Passenger Aboard Titanic\n",
    "\n",
    "Other family relatives excluded from this study include cousins,\n",
    "nephews/nieces, aunts/uncles, and in-laws.  Some children travelled\n",
    "only with a nanny, therefore parch=0 for them.  As well, some\n",
    "travelled with very close friends or neighbors in a village, however,\n",
    "the definitions do not support such relations.\n",
    "</pre>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Setup Imports and Variables"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import pylab as plt\n",
    "\n",
    "# Set the global default size of matplotlib figures\n",
    "plt.rc('figure', figsize=(10, 5))\n",
    "\n",
    "# Size of matplotlib figures that contain subplots\n",
    "fizsize_with_subplots = (10, 10)\n",
    "\n",
    "# Size of matplotlib histogram bins\n",
    "bin_size = 10"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Explore the Data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Read the data:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\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</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</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</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</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</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      1   \n",
       "1  Cumings, Mrs. John Bradley (Florence Briggs Th...  female   38      1   \n",
       "2                             Heikkinen, Miss. Laina  female   26      0   \n",
       "3       Futrelle, Mrs. Jacques Heath (Lily May Peel)  female   35      1   \n",
       "4                           Allen, Mr. William Henry    male   35      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": [
    "df_train = pd.read_csv('../data/titanic/train.csv')\n",
    "df_train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\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>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</td>\n",
       "      <td> 0</td>\n",
       "      <td> 0</td>\n",
       "      <td>     211536</td>\n",
       "      <td> 13.00</td>\n",
       "      <td>  NaN</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</td>\n",
       "      <td> 0</td>\n",
       "      <td> 0</td>\n",
       "      <td>     112053</td>\n",
       "      <td> 30.00</td>\n",
       "      <td>  B42</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>NaN</td>\n",
       "      <td> 1</td>\n",
       "      <td> 2</td>\n",
       "      <td> W./C. 6607</td>\n",
       "      <td> 23.45</td>\n",
       "      <td>  NaN</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</td>\n",
       "      <td> 0</td>\n",
       "      <td> 0</td>\n",
       "      <td>     111369</td>\n",
       "      <td> 30.00</td>\n",
       "      <td> C148</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</td>\n",
       "      <td> 0</td>\n",
       "      <td> 0</td>\n",
       "      <td>     370376</td>\n",
       "      <td>  7.75</td>\n",
       "      <td>  NaN</td>\n",
       "      <td> Q</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     PassengerId  Survived  Pclass                                      Name  \\\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      Ticket   Fare Cabin Embarked  \n",
       "886    male   27      0      0      211536  13.00   NaN        S  \n",
       "887  female   19      0      0      112053  30.00   B42        S  \n",
       "888  female  NaN      1      2  W./C. 6607  23.45   NaN        S  \n",
       "889    male   26      0      0      111369  30.00  C148        C  \n",
       "890    male   32      0      0      370376   7.75   NaN        Q  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train.tail()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "View the data types of each column:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "PassengerId      int64\n",
       "Survived         int64\n",
       "Pclass           int64\n",
       "Name            object\n",
       "Sex             object\n",
       "Age            float64\n",
       "SibSp            int64\n",
       "Parch            int64\n",
       "Ticket          object\n",
       "Fare           float64\n",
       "Cabin           object\n",
       "Embarked        object\n",
       "dtype: object"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train.dtypes"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Type 'object' is a string for pandas, which poses problems with machine learning algorithms.  If we want to use these as features, we'll need to convert these to number representations."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Get some basic information on the DataFrame:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Int64Index: 891 entries, 0 to 890\n",
      "Data columns (total 12 columns):\n",
      "PassengerId    891 non-null int64\n",
      "Survived       891 non-null int64\n",
      "Pclass         891 non-null int64\n",
      "Name           891 non-null object\n",
      "Sex            891 non-null object\n",
      "Age            714 non-null float64\n",
      "SibSp          891 non-null int64\n",
      "Parch          891 non-null int64\n",
      "Ticket         891 non-null object\n",
      "Fare           891 non-null float64\n",
      "Cabin          204 non-null object\n",
      "Embarked       889 non-null object\n",
      "dtypes: float64(2), int64(5), object(5)"
     ]
    }
   ],
   "source": [
    "df_train.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Age, Cabin, and Embarked are missing values.  Cabin has too many missing values, whereas we might be able to infer values for Age and Embarked."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Generate various descriptive statistics on the DataFrame:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\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>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Fare</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> 714.000000</td>\n",
       "      <td> 891.000000</td>\n",
       "      <td> 891.000000</td>\n",
       "      <td> 891.000000</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>  29.699118</td>\n",
       "      <td>   0.523008</td>\n",
       "      <td>   0.381594</td>\n",
       "      <td>  32.204208</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>  14.526497</td>\n",
       "      <td>   1.102743</td>\n",
       "      <td>   0.806057</td>\n",
       "      <td>  49.693429</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>   0.420000</td>\n",
       "      <td>   0.000000</td>\n",
       "      <td>   0.000000</td>\n",
       "      <td>   0.000000</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>  20.125000</td>\n",
       "      <td>   0.000000</td>\n",
       "      <td>   0.000000</td>\n",
       "      <td>   7.910400</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>  28.000000</td>\n",
       "      <td>   0.000000</td>\n",
       "      <td>   0.000000</td>\n",
       "      <td>  14.454200</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>  38.000000</td>\n",
       "      <td>   1.000000</td>\n",
       "      <td>   0.000000</td>\n",
       "      <td>  31.000000</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>  80.000000</td>\n",
       "      <td>   8.000000</td>\n",
       "      <td>   6.000000</td>\n",
       "      <td> 512.329200</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       PassengerId    Survived      Pclass         Age       SibSp  \\\n",
       "count   891.000000  891.000000  891.000000  714.000000  891.000000   \n",
       "mean    446.000000    0.383838    2.308642   29.699118    0.523008   \n",
       "std     257.353842    0.486592    0.836071   14.526497    1.102743   \n",
       "min       1.000000    0.000000    1.000000    0.420000    0.000000   \n",
       "25%     223.500000    0.000000    2.000000   20.125000    0.000000   \n",
       "50%     446.000000    0.000000    3.000000   28.000000    0.000000   \n",
       "75%     668.500000    1.000000    3.000000   38.000000    1.000000   \n",
       "max     891.000000    1.000000    3.000000   80.000000    8.000000   \n",
       "\n",
       "            Parch        Fare  \n",
       "count  891.000000  891.000000  \n",
       "mean     0.381594   32.204208  \n",
       "std      0.806057   49.693429  \n",
       "min      0.000000    0.000000  \n",
       "25%      0.000000    7.910400  \n",
       "50%      0.000000   14.454200  \n",
       "75%      0.000000   31.000000  \n",
       "max      6.000000  512.329200  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now that we have a general idea of the data set contents, we can dive deeper into each column.  We'll be doing exploratory data analysis and cleaning data to setup 'features' we'll be using in our machine learning algorithms.\n",
    "\n",
    "Plot a few features to get a better idea of each:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.text.Text at 0x10af2a5d0>"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAlIAAAJZCAYAAABiGNuwAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nbkiZmZmZdckNKTMzM7Mu/X+AP0780h2GHQAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x10a9ede50>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Set up a grid of plots\n",
    "fig = plt.figure(figsize=fizsize_with_subplots) \n",
    "fig_dims = (3, 2)\n",
    "\n",
    "# Plot death and survival counts\n",
    "plt.subplot2grid(fig_dims, (0, 0))\n",
    "df_train['Survived'].value_counts().plot(kind='bar', \n",
    "                                         title='Death and Survival Counts')\n",
    "\n",
    "# Plot Pclass counts\n",
    "plt.subplot2grid(fig_dims, (0, 1))\n",
    "df_train['Pclass'].value_counts().plot(kind='bar', \n",
    "                                       title='Passenger Class Counts')\n",
    "\n",
    "# Plot Sex counts\n",
    "plt.subplot2grid(fig_dims, (1, 0))\n",
    "df_train['Sex'].value_counts().plot(kind='bar', \n",
    "                                    title='Gender Counts')\n",
    "plt.xticks(rotation=0)\n",
    "\n",
    "# Plot Embarked counts\n",
    "plt.subplot2grid(fig_dims, (1, 1))\n",
    "df_train['Embarked'].value_counts().plot(kind='bar', \n",
    "                                         title='Ports of Embarkation Counts')\n",
    "\n",
    "# Plot the Age histogram\n",
    "plt.subplot2grid(fig_dims, (2, 0))\n",
    "df_train['Age'].hist()\n",
    "plt.title('Age Histogram')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Next we'll explore various features to view their impact on survival rates."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Feature: Passenger Classes"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "From our exploratory data analysis in the previous section, we see there are three passenger classes: First, Second, and Third class.  We'll determine which proportion of passengers survived based on their passenger class."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Generate a cross tab of Pclass and Survived:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>Survived</th>\n",
       "      <th>0</th>\n",
       "      <th>1</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Pclass</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>  80</td>\n",
       "      <td> 136</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>  97</td>\n",
       "      <td>  87</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td> 372</td>\n",
       "      <td> 119</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Survived    0    1\n",
       "Pclass            \n",
       "1          80  136\n",
       "2          97   87\n",
       "3         372  119"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pclass_xt = pd.crosstab(df_train['Pclass'], df_train['Survived'])\n",
    "pclass_xt"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Plot the cross tab:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.text.Text at 0x10a9eda10>"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAl4AAAFMCAYAAAAa17KLAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nnk7w9PBiAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x10a9abf90>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Normalize the cross tab to sum to 1:\n",
    "pclass_xt_pct = pclass_xt.div(pclass_xt.sum(1).astype(float), axis=0)\n",
    "\n",
    "pclass_xt_pct.plot(kind='bar', \n",
    "                   stacked=True, \n",
    "                   title='Survival Rate by Passenger Classes')\n",
    "plt.xlabel('Passenger Class')\n",
    "plt.ylabel('Survival Rate')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can see that passenger class seems to have a significant impact on whether a passenger survived.  Those in First Class the highest chance for survival."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Feature: Sex"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Gender might have also played a role in determining a passenger's survival rate.  We'll need to map Sex from a string to a number to prepare it for machine learning algorithms."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Generate a mapping of Sex from a string to a number representation:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'female': 0, 'male': 1}"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sexes = sort(df_train['Sex'].unique())\n",
    "genders_mapping = dict(zip(sexes, range(0, len(sexes) + 1)))\n",
    "genders_mapping"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Transform Sex from a string to a number representation:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>PassengerId</th>\n",
       "      <th>Survived</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Name</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>Sex_Val</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</td>\n",
       "      <td> 1</td>\n",
       "      <td> 0</td>\n",
       "      <td>        A/5 21171</td>\n",
       "      <td>  7.2500</td>\n",
       "      <td>  NaN</td>\n",
       "      <td> S</td>\n",
       "      <td> 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</td>\n",
       "      <td> 1</td>\n",
       "      <td> 0</td>\n",
       "      <td>         PC 17599</td>\n",
       "      <td> 71.2833</td>\n",
       "      <td>  C85</td>\n",
       "      <td> C</td>\n",
       "      <td> 0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td> 3</td>\n",
       "      <td> 1</td>\n",
       "      <td> 3</td>\n",
       "      <td>                            Heikkinen, Miss. Laina</td>\n",
       "      <td> female</td>\n",
       "      <td> 26</td>\n",
       "      <td> 0</td>\n",
       "      <td> 0</td>\n",
       "      <td> STON/O2. 3101282</td>\n",
       "      <td>  7.9250</td>\n",
       "      <td>  NaN</td>\n",
       "      <td> S</td>\n",
       "      <td> 0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td> 4</td>\n",
       "      <td> 1</td>\n",
       "      <td> 1</td>\n",
       "      <td>      Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n",
       "      <td> female</td>\n",
       "      <td> 35</td>\n",
       "      <td> 1</td>\n",
       "      <td> 0</td>\n",
       "      <td>           113803</td>\n",
       "      <td> 53.1000</td>\n",
       "      <td> C123</td>\n",
       "      <td> S</td>\n",
       "      <td> 0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td> 5</td>\n",
       "      <td> 0</td>\n",
       "      <td> 3</td>\n",
       "      <td>                          Allen, Mr. William Henry</td>\n",
       "      <td>   male</td>\n",
       "      <td> 35</td>\n",
       "      <td> 0</td>\n",
       "      <td> 0</td>\n",
       "      <td>           373450</td>\n",
       "      <td>  8.0500</td>\n",
       "      <td>  NaN</td>\n",
       "      <td> S</td>\n",
       "      <td> 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      1   \n",
       "1  Cumings, Mrs. John Bradley (Florence Briggs Th...  female   38      1   \n",
       "2                             Heikkinen, Miss. Laina  female   26      0   \n",
       "3       Futrelle, Mrs. Jacques Heath (Lily May Peel)  female   35      1   \n",
       "4                           Allen, Mr. William Henry    male   35      0   \n",
       "\n",
       "   Parch            Ticket     Fare Cabin Embarked  Sex_Val  \n",
       "0      0         A/5 21171   7.2500   NaN        S        1  \n",
       "1      0          PC 17599  71.2833   C85        C        0  \n",
       "2      0  STON/O2. 3101282   7.9250   NaN        S        0  \n",
       "3      0            113803  53.1000  C123        S        0  \n",
       "4      0            373450   8.0500   NaN        S        1  "
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train['Sex_Val'] = df_train['Sex'].map(genders_mapping).astype(int)\n",
    "df_train.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Plot a normalized cross tab for Sex_Val and Survived:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x10a9ddd50>"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAk8AAAFNCAYAAAAZ54v4AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x10adb6d90>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sex_val_xt = pd.crosstab(df_train['Sex_Val'], df_train['Survived'])\n",
    "sex_val_xt_pct = sex_val_xt.div(sex_val_xt.sum(1).astype(float), axis=0)\n",
    "sex_val_xt_pct.plot(kind='bar', stacked=True, title='Survival Rate by Gender')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The majority of females survived, whereas the majority of males did not."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Next we'll determine whether we can gain any insights on survival rate by looking at both Sex and Pclass."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Count males and females in each Pclass:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "M:  1 122\n",
      "F:  1 94\n",
      "M:  2 108\n",
      "F:  2 76\n",
      "M:  3 347\n",
      "F:  3 144\n"
     ]
    }
   ],
   "source": [
    "# Get the unique values of Pclass:\n",
    "passenger_classes = sort(df_train['Pclass'].unique())\n",
    "\n",
    "for p_class in passenger_classes:\n",
    "    print 'M: ', p_class, len(df_train[(df_train['Sex'] == 'male') & \n",
    "                             (df_train['Pclass'] == p_class)])\n",
    "    print 'F: ', p_class, len(df_train[(df_train['Sex'] == 'female') & \n",
    "                             (df_train['Pclass'] == p_class)])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Plot survival rate by Sex and Pclass:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.text.Text at 0x10b610e50>"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAl4AAAFVCAYAAAA+DuHYAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nggAuJN4AAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x10b0c3710>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAl4AAAFVCAYAAAA+DuHYAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAABJRU5ErkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x10b5b5b50>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Plot survival rate by Sex\n",
    "females_df = df_train[df_train['Sex'] == 'female']\n",
    "females_xt = pd.crosstab(females_df['Pclass'], df_train['Survived'])\n",
    "females_xt_pct = females_xt.div(females_xt.sum(1).astype(float), axis=0)\n",
    "females_xt_pct.plot(kind='bar', \n",
    "                    stacked=True, \n",
    "                    title='Female Survival Rate by Passenger Class')\n",
    "plt.xlabel('Passenger Class')\n",
    "plt.ylabel('Survival Rate')\n",
    "\n",
    "# Plot survival rate by Pclass\n",
    "males_df = df_train[df_train['Sex'] == 'male']\n",
    "males_xt = pd.crosstab(males_df['Pclass'], df_train['Survived'])\n",
    "males_xt_pct = males_xt.div(males_xt.sum(1).astype(float), axis=0)\n",
    "males_xt_pct.plot(kind='bar', \n",
    "                  stacked=True, \n",
    "                  title='Male Survival Rate by Passenger Class')\n",
    "plt.xlabel('Passenger Class')\n",
    "plt.ylabel('Survival Rate')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The vast majority of females in First and Second class survived.  Males in First class had the highest chance for survival."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Feature: Embarked"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The Embarked column might be an important feature but it is missing a couple data points which might pose a problem for machine learning algorithms:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>PassengerId</th>\n",
       "      <th>Survived</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Name</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>Sex_Val</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>61 </th>\n",
       "      <td>  62</td>\n",
       "      <td> 1</td>\n",
       "      <td> 1</td>\n",
       "      <td>                       Icard, Miss. Amelie</td>\n",
       "      <td> female</td>\n",
       "      <td> 38</td>\n",
       "      <td> 0</td>\n",
       "      <td> 0</td>\n",
       "      <td> 113572</td>\n",
       "      <td> 80</td>\n",
       "      <td> B28</td>\n",
       "      <td> NaN</td>\n",
       "      <td> 0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>829</th>\n",
       "      <td> 830</td>\n",
       "      <td> 1</td>\n",
       "      <td> 1</td>\n",
       "      <td> Stone, Mrs. George Nelson (Martha Evelyn)</td>\n",
       "      <td> female</td>\n",
       "      <td> 62</td>\n",
       "      <td> 0</td>\n",
       "      <td> 0</td>\n",
       "      <td> 113572</td>\n",
       "      <td> 80</td>\n",
       "      <td> B28</td>\n",
       "      <td> NaN</td>\n",
       "      <td> 0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     PassengerId  Survived  Pclass                                       Name  \\\n",
       "61            62         1       1                        Icard, Miss. Amelie   \n",
       "829          830         1       1  Stone, Mrs. George Nelson (Martha Evelyn)   \n",
       "\n",
       "        Sex  Age  SibSp  Parch  Ticket  Fare Cabin Embarked  Sex_Val  \n",
       "61   female   38      0      0  113572    80   B28      NaN        0  \n",
       "829  female   62      0      0  113572    80   B28      NaN        0  "
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train[df_train['Embarked'].isnull()]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Prepare to map Embarked from a string to a number representation:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{nan: 0, 'C': 1, 'Q': 2, 'S': 3}"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Get the unique values of Embarked\n",
    "embarked_locs = sort(df_train['Embarked'].unique())\n",
    "\n",
    "embarked_locs_mapping = dict(zip(embarked_locs, \n",
    "                                 range(0, len(embarked_locs) + 1)))\n",
    "embarked_locs_mapping"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Transform Embarked from a string to a number representation to prepare it for machine learning algorithms:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>PassengerId</th>\n",
       "      <th>Survived</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Name</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>Sex_Val</th>\n",
       "      <th>Embarked_Val</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</td>\n",
       "      <td> 1</td>\n",
       "      <td> 0</td>\n",
       "      <td>        A/5 21171</td>\n",
       "      <td>  7.2500</td>\n",
       "      <td>  NaN</td>\n",
       "      <td> S</td>\n",
       "      <td> 1</td>\n",
       "      <td> 3</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</td>\n",
       "      <td> 1</td>\n",
       "      <td> 0</td>\n",
       "      <td>         PC 17599</td>\n",
       "      <td> 71.2833</td>\n",
       "      <td>  C85</td>\n",
       "      <td> C</td>\n",
       "      <td> 0</td>\n",
       "      <td> 1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td> 3</td>\n",
       "      <td> 1</td>\n",
       "      <td> 3</td>\n",
       "      <td>                            Heikkinen, Miss. Laina</td>\n",
       "      <td> female</td>\n",
       "      <td> 26</td>\n",
       "      <td> 0</td>\n",
       "      <td> 0</td>\n",
       "      <td> STON/O2. 3101282</td>\n",
       "      <td>  7.9250</td>\n",
       "      <td>  NaN</td>\n",
       "      <td> S</td>\n",
       "      <td> 0</td>\n",
       "      <td> 3</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</td>\n",
       "      <td> 1</td>\n",
       "      <td> 0</td>\n",
       "      <td>           113803</td>\n",
       "      <td> 53.1000</td>\n",
       "      <td> C123</td>\n",
       "      <td> S</td>\n",
       "      <td> 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</td>\n",
       "      <td> 0</td>\n",
       "      <td> 0</td>\n",
       "      <td>           373450</td>\n",
       "      <td>  8.0500</td>\n",
       "      <td>  NaN</td>\n",
       "      <td> S</td>\n",
       "      <td> 1</td>\n",
       "      <td> 3</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      1   \n",
       "1  Cumings, Mrs. John Bradley (Florence Briggs Th...  female   38      1   \n",
       "2                             Heikkinen, Miss. Laina  female   26      0   \n",
       "3       Futrelle, Mrs. Jacques Heath (Lily May Peel)  female   35      1   \n",
       "4                           Allen, Mr. William Henry    male   35      0   \n",
       "\n",
       "   Parch            Ticket     Fare Cabin Embarked  Sex_Val  Embarked_Val  \n",
       "0      0         A/5 21171   7.2500   NaN        S        1             3  \n",
       "1      0          PC 17599  71.2833   C85        C        0             1  \n",
       "2      0  STON/O2. 3101282   7.9250   NaN        S        0             3  \n",
       "3      0            113803  53.1000  C123        S        0             3  \n",
       "4      0            373450   8.0500   NaN        S        1             3  "
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train['Embarked_Val'] = df_train['Embarked'] \\\n",
    "                               .map(embarked_locs_mapping) \\\n",
    "                               .astype(int)\n",
    "df_train.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Plot the histogram for Embarked_Val:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAmgAAAFRCAYAAADAclGxAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzt3X28bnVd5//XGxBvgQNShxvRY6OM0qQHFTRvco+po5Zg\nM5M3Ncaxxl+/McemyRKaJrAmBOpnM+bUVKMNWmBoDkF5w41cilPgGGyxjgiUpzwgxxtATaxAPr8/\nrrU9F9t9zrWuc/a11tp7v56Px/U4a61r3Xz2Zy8uPvu7PmtdqSokSZI0HAf0HYAkSZLuzwJNkiRp\nYCzQJEmSBsYCTZIkaWAs0CRJkgbGAk2SJGlgLNAktZLkGUluTvLVJKfM+Vj/K8kvreL+zkryzlXa\n1xlJfmc19rUPx/7hJB/s49iSumWBJg1Ykh1J7m6KotuT/G6Sh+7Hvp6zH+H8IvCWqjqkqi6ZEuvS\n6y37eKxqXqtln/aVZCHJZ++3o6o3VdWrVyes+x1rW5KrV1i+I8n3Nsf+/ar6Fy32taoFrqTuWaBJ\nw1bA91fVIcCTgKcAPz/LDpIcNLGv7EcsjwS27+X9b8Y68Xrdfhxvf2LdvZPdP/9atdrF6n5ZB/mU\n1gQLNGmNqKrbgA8A/wwgySlJ/jLJnUmuSvK4pXWbUZefTfIJ4O+SXMC4wLq0Gdl6/UrHSPLq5jLm\nl5L8UZKjm+V/BXxHs/1Xkjxgltib0aH/k+TNTby3JHl6klcl+dsku5L8yLLNjkxyWXO8UZJHTuzv\nvzXbfTnJx5M8c+K9s5K8J8k7k3wZOG1ZLA9IcmGSdzfTr0qyvTnOXyX5f5r1Hgq8HzimydlXkhy9\n/HJpi9/DTyf5RJK7krwryQNnyd0Keby6mU6SX2ty9+UkNyT5zib+HwJ+ton7j5r1H9/k8c4kf5Hk\nxRP7fXiSS5v9fCzJf5kczUtyX5LXJLkZ+HTL38G7m9/BV5rYHpvx5eFdSf4myfP2NQ/SRmCBJg1f\nAJIcB7wQuC7J8cAFwOuAI4H3MS6eJkc3Xg68CDisqn4I+Ft2j3D96rccZHz582zgB4Gjgb8B3gVQ\nVf9kYvtDq+qevcW6BycDnwCOAC4ELmI8KvhPgH8DvDXJQyb288OML6seCSwCvz+xr48BTwQOb/Lw\n7iQHT7x/CvDuqjpscrskDwIuBr4OvLT5OXYB31dVhwKvAn4tyYlV9TXgBcBtTc4OrarPMTGa1eL3\nUE0+/wXwaOAJwLa95GgWzweeBTy2+Tl/EPhSVf128zOf28R9alNQX8q4wP824N8Dv9/ED/Dfga8C\nmxkXtD/Ct47anQqcBJzQzE/7HXw/8I7m/euBy5vlxwC/BPzWfmdAWscs0KRhC3BxkjuBq4ER8Cbg\nZcAfV9WVVfUN4FeBBwNPb7Yrxv1it1bVP7Q81g8Db6uqxar6R+AM4LsnR67axjrx+rGJ9z9TVefX\n+AuAL2L8P+pfrKp7qupy4B+Bx0ys/8dV9dEmlv/UxHIsfLMX686quq+q3gw8EPinE9v+6VKfXFX9\nfbPsUOCDwM1V9aNNHFTV+6rqM830R4DLGBc+Sz/TSj/nkmm/Bxj/Hm6vqjsZF0lb95LDpy3L352M\nRz5Xcg9wCPD4JAdU1aer6vY9xPk04KFVdU5V3VtVVwF/DLwiyYHAvwTOrKq/r6pPAeev8LO/qaru\nWjqfWvwOPlJVlzd5eQ/wcOCcZv4PgC1JDt1LLqQNzQJNGrYCTq2qw6tqS1W9tik4jmY8ojVeaVxs\nfBY4dmLbzzKbpVGzpX1+DfjSsn22jXXp9baJ93dNTH+9OcYXli172MS+di6L5Q7GRR1JXt9clryr\nKWIOYzyCtWQn9xfGRco/A8693xvJC5Nck/Fl3TsZjzo+vOXPfAzTfw+TRdPkz7iSa5bl7/DJ/U+q\nqg8Bb2U8+rUryW8lOWQvcS4/H/6mWX4kcNCy95fnj+Xbt/gdfH5i+uvAF5eK4mYe9p4LaUOzQJPW\nptuARy3NJAlwHHDrxDrLL1FNazS/Ddgysc+HMi5Ubt3TBnO09PMsxfIwxpdGb0vyLOBngB+sqk1N\nEfNl7j/is9LPfhlwDnBlkm9v9vtA4A+B84Bvb/b1vol9TcvZrUz/PSyPY9VU1a9X1VMYX3Y8nnFe\nVjrObcBxTXxLHtXE+QXgXibyvWz6m4dbmmj5O5C0HyzQpLXpIuD7kjyn6S/6aeDvgT/dyza7GPd7\n7cmFwKuSPLEpXM5mPKKz4gjOHqzm/6BflPGz1w5m3LP0Z1V1K+PLevcCX0xycJJfYHz5cmpcVfUr\njPulrkzycODg5vVF4L4kL2Tc27VkF/DwvVyKezez/R5WLT9JnpLkqc1x726O+42JuL9jYvVrmnV+\nNuMbIxYY94i9q6ruA94LnJXkwc1NDq9k78XkvvwOJM3AAk1ag6rqJsaN9b/OeATk+4AXV9W9e9ns\nTcDPN71N/3GFfV4J/GfGI0q3MW5qf/mMoS3dJbr0+sOl3TPbiF4xbnQ/k/Fl1hMZ/7wwbnT/AHAT\nsIPx5bK/XbbtSsda6jn7L4xvFLiC8aW91zEueO8AXgH80Tc3qrqRceH610nuyPiu1sl9fZrZfg97\ne2RGm8dpTK5zKPDbTdw7GBeZv9K89zbghOZ3/d7mZogXM77J5AuML42+sjmPAF7L+BLl7Yz7zy5k\n3BM4edxJ+/o72Nu8pAnZ3RIwh50n/5TmLrDGdzD+H8DvMW4SfRTj/7hfWlV3NducAfwo478EX1dV\nl80tQEnSt0hyLuNLvq/qOxZpo5prgXa/AyUHMO53OJnxLd5frKrzkrwBOLyqTk9yAuPLDycxbrK9\nAji+GYKXJM1B88f0A4FPMv78/RPgx1b6xghJ3ejyEudzgVuq6rOMn1F0frP8fOAlzfSpwIXNbfc7\ngFsYF3SSpPk5hPGl7b9jfNXjVy3OpH51+ZUdL2fc1wCwuaqWbrnfxfjhiDC+5fuaiW120v4Wf0nS\nPqiqjwOP7TsOSbt1MoLW3IX1YsZ3PN1P81ycac3CkiRJG0ZXI2gvBP584qGUu5IcVVW3N3dFLT3Q\n8Fbu//ydR7DseUJJLNgkSdKaUVUzP2Knqx60V7D78ibAJez+AuPTGN/yvrT85c1zdR7NeMj9Y8t3\nVlW+OnydeeaZvcew0V7m3JxvhJc5N+cb4bWv5j6C1jyN/LnAqycWnwNc1HxP3w7gpQBVtT3JRcB2\nxg9BfE3tz0+nVbFjx46+Q9hwzHn3zHn3zHn3zPnaMfcCrcbfoXfksmV3MC7aVlr/bMZPMJckSdqQ\n/CYBTbVt27a+Q9hwzHn3zHn3zHn3zPna0dmDaldLEq96SpKkNSEJNeCbBLSGjUajvkPYcMx598x5\n98x598z52mGBJkmSNDBe4pQkSZoTL3FKkiStExZomsqehe6Z8+6Z8+6Z8+6Z87XDAk2SJGlg7EGT\nJEmaE3vQJEmS1gkLNE1lz0L3zHn3zHn3zHn3zPnaYYEmSZI0MPagSZIkzYk9aJIkSeuEBZqmsmeh\ne+a8e+a8e+a8e+Z87bBAkyRJGhh70CRJkubEHjRJkqR1wgJNU9mz0D1z3j1z3r21nPMkvny1eu2r\ng1bxfJUkaQNZi+02I2Ch5xg2mn0r0uxBkyRpRuOREf9fpDbsQZMkSVoXLNA01VruE1mrzHn3zHn3\nzHkfRn0HoJYs0CRJkgbGHjRJkmZkD5raswdNkiRpXbBA01T2iXTPnHfPnHfPnPdh1HcAaskCTZIk\naWDsQZMkaUb2oKk9e9AkSZLWBQs0TWWfSPfMeffMeffMeR9GfQegluZeoCXZlOQ9ST6VZHuSpyY5\nIsnlSW5KclmSTRPrn5Hk5iQ3Jnn+vOOTJEkamrn3oCU5H/hwVb09yUHAQ4H/BHyxqs5L8gbg8Ko6\nPckJwAXAScCxwBXA8VV138T+7EGTJPXKHjS1N8AetCSHAc+qqrcDVNW9VfVl4BTg/Ga184GXNNOn\nAhdW1T1VtQO4BTh5njFKkiQNzbwvcT4a+EKS301yXZLfSfJQYHNV7WrW2QVsbqaPAXZObL+T8Uia\nemSfSPfMeffMeffMeR9GfQegluZdoB0EPAn4jap6EvA14PTJFZrrlXsbJ3YMWZIkbSgHzXn/O4Gd\nVfV/m/n3AGcAtyc5qqpuT3I08Pnm/VuB4ya2f0Sz7H62bdvGli1bANi0aRNbt25lYWEB2P0XmfOr\nO79kKPE47/xqzy8sLAwqno0wv7RsKPHMHv+o+XetzTPlfef3b35pegf7o4ubBD4C/NuquinJWcBD\nmre+VFXnJjkd2LTsJoGT2X2TwGMm7wrwJgFJUt+8SUDtDfAmgca/B34/ySeAJwC/DJwDPC/JTcBz\nmnmqajtwEbAdeD/wGqux/i391ajumPPumfPumfM+jPoOQC3N+xInVfUJxo/NWO65e1j/bODsuQYl\nSZI0YH4XpyRJM/ISp9ob7iVOSZIkzcACTVPZJ9I9c949c949c96HUd8BqCULNEmSpIGxB02SpBnZ\ng6b27EGTJElaFyzQNJV9It0z590z590z530Y9R2AWrJAkyRJGhh70CRJmpE9aGrPHjRJkqR1wQJN\nU9kn0j1z3j1z3j1z3odR3wGoJQs0SZKkgbEHTZKkGdmDpvbsQZMkSVoXLNA0lX0i3TPn3TPn3TPn\nfRj1HYBaskCTJEkaGHvQJEmakT1oas8eNEmSpHXBAk1T2SfSPXPePXPePXPeh1HfAaglCzRJkqSB\nsQdNkqQZ2YOm9uxBkyRJWhcs0DSVfSLdM+fdM+fdM+d9GPUdgFqyQJMkSRoYe9AkSZqRPWhqzx40\nSZKkdcECTVPZJ9I9c949c949c96HUd8BqCULNEmSpIGxB02SpBnZg6b27EGTJElaFyzQNJV9It0z\n590z590z530Y9R2AWpp7gZZkR5Ibklyf5GPNsiOSXJ7kpiSXJdk0sf4ZSW5OcmOS5887PkmSpKGZ\new9aks8AT66qOyaWnQd8sarOS/IG4PCqOj3JCcAFwEnAscAVwPFVdd/EtvagSZJ6ZQ+a2ht2D9ry\nwE4Bzm+mzwde0kyfClxYVfdU1Q7gFuDkTiKUJEkaiC4KtAKuSPLxJK9ulm2uql3N9C5gczN9DLBz\nYtudjEfS1CP7RLpnzrtnzrtnzvsw6jsAtXRQB8d4RlV9Lsm3AZcnuXHyzaqqJHsbJ3YMWZIkbShz\nL9Cq6nPNv19I8r8ZX7LcleSoqro9ydHA55vVbwWOm9j8Ec2y+9m2bRtbtmwBYNOmTWzdupWFhQVg\n919kzq/u/JKhxOO886s9v7CwMKh4NsL80rKhxDN7/KPm37U2z5T3nd+/+aXpHeyPud4kkOQhwIFV\n9dUkDwUuA94IPBf4UlWdm+R0YNOymwROZvdNAo+ZvCvAmwQkSX3zJgG1N8ybBDYDVydZBK4F/riq\nLgPOAZ6X5CbgOc08VbUduAjYDrwfeI3VWP+W/mpUd8x598x598x5H0Z9B6CW5nqJs6o+A2xdYfkd\njEfRVtrmbODsecYlSZI0ZH4XpyRJM/ISp9ob5iVOSZIkzcgCTVPZJ9I9c949c949c96HUd8BqCUL\nNEmSpIGxB02SpBnZg6b27EGTJElaFyzQNJV9It0z590z590z530Y9R2AWrJAkyRJGhh70CRJmpE9\naGrPHjRJkqR1wQJNU9kn0j1z3j1z3j1z3odR3wGoJQs0SZKkgbEHTZKkGdmDpvbsQZMkSVoXLNA0\nlX0i3TPn3TPn3TPnfRj1HYBaskCTJEkaGHvQJEmakT1oas8eNEmSpHXBAk1T2SfSPXPePXPePXPe\nh1HfAaglCzRJkqSBsQdNkqQZ2YOm9uxBkyRJWhcs0DSVfSLdM+fdM+fdM+d9GPUdgFqyQJMkSRoY\ne9AkSZqRPWhqzx40SZKkdcECTVPZJ9I9c949c949c96HUd8BqCULNEmSpIGxB02SpBnZg6b27EGT\nJElaFyzQNJV9It0z590z590z530Y9R2AWpp7gZbkwCTXJ7m0mT8iyeVJbkpyWZJNE+uekeTmJDcm\nef68Y5MkSRqiufegJfmPwJOBQ6rqlCTnAV+sqvOSvAE4vKpOT3ICcAFwEnAscAVwfFXdt2x/9qBJ\nknplD5raG2APWpJHAC8C/iewFNwpwPnN9PnAS5rpU4ELq+qeqtoB3AKcPM/4JEmShmjelzh/DfgZ\nYHIUbHNV7WqmdwGbm+ljgJ0T6+1kPJKmntkn0j1z3j1z3j1z3odR3wGopYPmteMk3w98vqquT7Kw\n0jpVVUn2Nka84nvbtm1jy5YtAGzatImtW7eysDA+xNJ/8M6v3vzi4uKg4tkI80uGEo/zzs9jfnFx\ncVDxzDq/u9hZS/OLA4tnPc4vTe9gf8ytBy3J2cArgXuBBwGHAu9l3GO2UFW3JzkauKqqHpfkdICq\nOqfZ/gPAmVV17bL92oMmSeqVPWhqb2A9aFX1c1V1XFU9Gng58KGqeiVwCXBas9ppwMXN9CXAy5Mc\nnOTRwGOBj80rPkmSpKGaW4G2gqU/Nc4BnpfkJuA5zTxVtR24CNgOvB94jUNlw7D8spvmz5x3z5x3\nz5z3YdR3AGppbj1ok6rqw8CHm+k7gOfuYb2zgbO7iEmSJGmo/C5OSZJmZA+a2htYD5okSZL2zdQC\nLckzV1j2jPmEoyGyT6R75rx75rx75rwPo74DUEttRtB+fYVlb13tQCRJkjS2xx60JN8NPB34KeDN\n7P6qpkOAH6iqJ3YS4bfGZQ+aJKlX9qCpvX3rQdvbXZwHMy7GDmz+XfIV4F/PeiBJkiS1s8dLnFX1\n4ao6C/juqnrjxOvNVXVzdyGqb/aJdM+cd8+cd8+c92HUdwBqqc1z0B6Y5HeALRPrV1U9Z25RSZIk\nbWBTn4OW5AbgN4HrgG80i6uq/nzOse0pHnvQJEm9sgdN7a1+D9qSe6rqN/chIkmSJO2DNo/ZuDTJ\nTyQ5OskRS6+5R6bBsE+ke+a8e+a8e+a8D6O+A1BLbUbQtjEex339suWPXvVoJEmS5HdxSpI0K3vQ\n1N6cetCSnMYKZ2FVvWPWg0mSJGm6Nj1oJ028vgc4CzhljjFpYOwT6Z457545754578Oo7wDU0tQR\ntKp67eR8kk3AH8wtIkmSpA1u5h60JAcDf1FVx88npKnHtwdNktQre9DU3vx60C6dmD0AOAG4aNYD\nSZIkqZ02PWj/X/P6VeBs4Huq6g1zjUqDYp9I98x598x598x5H0Z9B6CWphZoVTUCbgQOBQ4H/mHO\nMUmSJG1obb6L86XArwAfbhZ9D/AzVfXuOce2p3jsQZMk9coeNLW3bz1obb8s/blV9flm/tuAK6vq\nCfsU536yQJMk9c0CTe3tW4HWpgctwBcm5r/ULNMGYZ9I98x598x598x5H0Z9B6CW2nwX5weADya5\ngHFh9jLg/XONSpIkaQPb4yXOJI8FNlfVR5P8K+AZzVt3ARdU1S0dxbg8Li9xSpJ65SVOtbfKPWhJ\n/gQ4o6puWLb8CcAvV9WL9ynO/WSBJknqmwWa2lv9HrTNy4szgGbZo2c9kNYu+0S6Z867Z867Z877\nMOo7ALW0twJt017ee9BqByJJkqSxvV3ifBfwoar67WXLX834sRsv6yC+leLyEqckqVde4lR7q9+D\ndhTwv4F/BP68Wfxk4IHAD1TV5/Yx0v1igSZJ6psFmtpb5R60qrodeDrwRmAH8BngjVX1tL6KM/XD\nPpHumfPumfPumfM+jPoOQC3t9TlozVDVh5rXTJI8iPHXQz0QOBj4o6o6I8kRwB8Aj2Jc+L20qu5q\ntjkD+FHgG8DrquqyWY8rSZK01k39qqf92nnykKq6O8lBwEeB1wOnAF+sqvOSvAE4vKpOT3ICcAFw\nEnAscAVwfFXdt2yfXuKUJPXKS5xqb35f9bTPquruZvJg4EDgTsYF2vnN8vOBlzTTpwIXVtU9VbUD\nuAU4eZ7xSZIkDdFcC7QkByRZBHYBV1XVXzJ+vtquZpVdwOZm+hhg58TmOxmPpKln9ol0z5x3z5x3\nz5z3YdR3AGqpzXdx7rPm8uTWJIcx/j7Pf77s/UqytzHiFd/btm0bW7ZsAWDTpk1s3bqVhYUFYPd/\n8M6v3vzi4uKg4tkI80uGEo/zzs9jfnFxcVDxzDq/u9hZS/OLA4tnPc4vTe9gf8y1B+1+B0r+M/B1\n4N8CC1V1e5KjGY+sPS7J6QBVdU6z/geAM6vq2mX7sQdNktQre9DU3sB60JIcmWRTM/1g4HnA9cAl\nwGnNaqcBFzfTlwAvT3JwkkcDjwU+Nq/4JEmShmpuBRpwNPChpgftWuDSqroSOAd4XpKbgOc081TV\nduAiYDvwfuA1DpUNw/LLbpo/c949c949c96HUd8BqKW59aBV1SeBJ62w/A7guXvY5mzg7HnFJEmS\ntBZ01oO2WuxBkyT1zR40tTewHjRJkiTtGws0TWWfSPfMeffMeffMeR9GfQeglizQJEmSBsYeNEmS\nZmQPmtqzB02SJGldsEDTVPaJdM+cd8+cd8+c92HUdwBqyQJNkiRpYOxBkyRpRvagqT170CRJktYF\nCzRNZZ9I98x598x598x5H0Z9B6CWLNAkSZIGxh40SZJmZA+a2rMHTZIkaV2wQNNU9ol0z5x3z5x3\nz5z3YdR3AGrJAk2SJGlg7EGTJGlG9qCpPXvQJEmS1gULNE1ln0j3zHn3zHn3zHkfRn0HoJYs0CRJ\nkgbGHjRJkmZkD5raswdNkiRpXbBA01T2iXTPnHfPnHfPnPdh1HcAaskCTZIkaWDsQZMkaUb2oKk9\ne9AkSZLWBQs0TWWfSPfMeffMeffMeR9GfQeglizQJEmSBsYeNEmSZmQPmtqzB02SJGldmGuBluS4\nJFcl+cskf5Hkdc3yI5JcnuSmJJcl2TSxzRlJbk5yY5LnzzM+tWOfSPfMeffMeffMeR9GfQegluY9\ngnYP8FNV9Z3A04CfSPJ44HTg8qo6HriymSfJCcDLgBOAFwC/kcRRPkmStKF02oOW5GLgrc3r2VW1\nK8lRwKiqHpfkDOC+qjq3Wf8DwFlVdc3EPuxBkyT1yh40tTfwHrQkW4ATgWuBzVW1q3lrF7C5mT4G\n2Dmx2U7g2I5ClCRJGoROCrQkDwP+EPjJqvrq5HvNcNje/gzxT5Se2SfSPXPePXPePXPeh1HfAail\ng+Z9gCQPYFycvbOqLm4W70pyVFXdnuRo4PPN8luB4yY2f0Sz7H62bdvGli1bANi0aRNbt25lYWEB\n2P0fvPOrN7+4uDioeDbC/JKhxOO88/OYX1xcHFQ8s87vLnbW0vziwOJZj/NL0zvYH3PtQcv4Iv35\nwJeq6qcmlp/XLDs3yenApqo6vblJ4ALgZMaXNq8AHjPZdGYPmiSpb/agqb1960Gbd4H2TOAjwA3s\nPpPPAD4GXAQ8knGJ+dKquqvZ5ueAHwXuZXxJ9IPL9mmBJknqlQWa2hvgTQJV9dGqOqCqtlbVic3r\nA1V1R1U9t6qOr6rnLxVnzTZnV9Vjqupxy4sz9WP5ZTfNnznvnjnvnjnvw6jvANTSXAs0SZIkzc7v\n4pQkaUZe4lR7A7zEKUmSpNlZoGkq+0S6Z867Z867Z877MOo7ALVkgSZJkjQw9qBJkjQje9DUnj1o\nkiRJ64IFmqayT6R75rx75rx75rwPo74DUEsWaJIkSQNjD5rWtXGfiNSOny1qyx40tbdvPWgHzSMU\naVj8EFUbFvOShsNLnJrKPpE+jPoOQJo7P1v6MOo7ALVkgSZJkjQw9qBpXbNPRO3FHjS15meL2vM5\naJIkSeuCBZqmsk+kD6O+A5Dmzs+WPoz6DkAtWaBJkiQNjD1oWtfsE1F79qCpPT9b1J49aJIkSeuC\nBZqmsk+kD6O+A5Dmzs+WPoz6DkAtWaBJkiQNjD1oWtfsE1F79qCpPT9b1J49aJIkSeuCBZqmsk+k\nD6O+A5Dmzs+WPoz6DkAtWaBJkiQNjD1oWtfsE1F79qCpPT9b1J49aJIkSeuCBZqmsk+kD6O+A5Dm\nzs+WPoz6DkAtWaBJkiQNjD1oWtfsE1F79qCpPT9b1J49aJIkSevCXAu0JG9PsivJJyeWHZHk8iQ3\nJbksyaaJ985IcnOSG5M8f56xqT37RPow6jsAae78bOnDqO8A1NK8R9B+F3jBsmWnA5dX1fHAlc08\nSU4AXgac0GzzG0kc4ZMkSRvO3HvQkmwBLq2q72rmbwSeXVW7khwFjKrqcUnOAO6rqnOb9T4AnFVV\n1yzbnz1oas0+EbVnD5ra87NF7a2dHrTNVbWrmd4FbG6mjwF2Tqy3Ezi2y8AkSZKGoNdLiM1Q2N7+\nBPHPkwGwT6QPo74DkObOz5Y+jPoOQC0d1MMxdyU5qqpuT3I08Plm+a3AcRPrPaJZ9i22bdvGli1b\nANi0aRNbt25lYWEB2P0fvPOrN7+4uDioeGaZHxsBCxPTrIF5przv/Dzm+z5fN9r84uLioOKZ/fNl\n1Py7luYXBxbPepxfmt7B/uijB+084EtVdW6S04FNVXV6c5PABcDJjC9tXgE8ZnnDmT1omoV9ImrP\nHjS152eL2tu3HrS5jqAluRB4NnBkks8CvwCcA1yU5McYl5cvBaiq7UkuArYD9wKvsRKTJEkbkd8k\noKlGo9GyS4Zrx9r9K3fE7mFzdcMRtK752dKHEX62dG3t3MUpSZKkvXAETeva2v0rV91zBE3t+dmi\n9hxBkyRJWhcs0DTV0q3l6tKo7wCkufOzpQ+jvgNQSxZokiRJA2MPmtY1+0TU3swtItrw/GxRGwN8\nDpokrS3+D1dtWdBrvrzEqansE+nDqO8ApA6M+g5gAxr1HYBaskCTJEkaGHvQtK7Zg6b2PFc0C88X\nteVz0CRJktYFCzRNZQ9aH0Z9ByB1YNR3ABvQqO8A1JIFmiRJ0sDYg6Z1zR40tee5oll4vqgte9Ak\nSZLWBQs0TWUPWh9GfQcgdWDUdwAb0KjvANSSBZokSdLA2IOmdc0eNLXnuaJZeL6oLXvQJEmS1gUL\nNE1lD1ofRn0HIHVg1HcAG9Co7wDUkgWaJEnSwNiDpnXNHjS157miWXi+qC170CRJktYFCzRNZQ9a\nH0Z9ByCAMcGsAAAIkUlEQVR1YNR3ABvQqO8A1JIFmiRJ0sDYg6Z1zR40tee5oll4vqgte9AkSZLW\nBQs0TWUPWh9GfQcgdWDUdwAb0KjvANSSBZokSdLA2IOmdc0eNLXnuaJZeL6oLXvQJEmS1oXBFWhJ\nXpDkxiQ3J3lD3/HIHrR+jPoOQOrAqO8ANqBR3wGopUEVaEkOBN4KvAA4AXhFksf3G5UWFxf7DmED\nMufaCDzPu2fO14pBFWjAycAtVbWjqu4B3gWc2nNMG95dd93VdwgbkDnXRuB53j1zvlYc1HcAyxwL\nfHZififw1OUrvfGNb+wsII0vcZpzSZK6M7QCrdUtMWedddacw9ByH/7wh/sOYYPZ0XcAUgd29B3A\nBrSj7wDU0tAKtFuB4ybmj2M8iibth5nvbh6I8/sOYANaq+fKWraWz/O1er6s5ZxvHIN6DlqSg4BP\nA98L3AZ8DHhFVX2q18AkSZI6NKgRtKq6N8lrgQ8CBwJvsziTJEkbzaBG0CRJkjS8x2x8U5sH1iZ5\nS/P+J5Kc2HWM6820nCdZSPLlJNc3r5/vI871Isnbk+xK8sm9rOM5voqm5dxzfPUlOS7JVUn+Mslf\nJHndHtbzXF8lbXLuub66kjwoybVJFpNsT/KmPazX/jyvqsG9GF/evAXYAjyA8ZP1Hr9snRcB72um\nnwpc03fca/nVMucLwCV9x7peXsCzgBOBT+7hfc/x7nPuOb76OT8K2NpMP4xxn7Gf5/3n3HN99fP+\nkObfg4BrgGcue3+m83yoI2htHlh7Cs2tKFV1LbApyeZuw1xX2j4keK3etjQ4VXU1cOdeVvEcX2Ut\ncg6e46uqqm6vqsVm+u+ATwHHLFvNc30Vtcw5eK6vqqq6u5k8mPGgxx3LVpnpPB9qgbbSA2uPbbHO\nI+Yc13rWJucFPL0Zmn1fkhM6i25j8hzvnuf4HCXZwngE89plb3muz8lecu65vsqSHJBkEdgFXFVV\n25etMtN5Pqi7OCe0vXNhefXvHQ/7rk3urgOOq6q7k7wQuBg4fr5hbXie493yHJ+TJA8D3gP8ZDOq\n8y2rLJv3XN9PU3Luub7Kquo+YGuSw4APJlmoqtGy1Vqf50MdQWvzwNrl6zyiWaZ9MzXnVfXVpSHc\nqno/8IAkR3QX4objOd4xz/H5SPIA4A+B36uqi1dYxXN9lU3Luef6/FTVl4E/AZ6y7K2ZzvOhFmgf\nBx6bZEuSg4GXAZcsW+cS4EcAkjwNuKuqdnUb5royNedJNidJM30y48e0LL/GrtXjOd4xz/HV1+Tz\nbcD2qvqve1jNc30Vtcm55/rqSnJkkk3N9IOB5wHXL1ttpvN8kJc4aw8PrE3y4837v1VV70vyoiS3\nAF8DXtVjyGtem5wD/xr4d0nuBe4GXt5bwOtAkguBZwNHJvkscCbjO2g9x+dkWs7xHJ+HZwD/Brgh\nydL/sH4OeCR4rs/J1Jzjub7ajgbOT3IA48Gvd1bVlftTt/igWkmSpIEZ6iVOSZKkDcsCTZIkaWAs\n0CRJkgbGAk2SJGlgLNAkSZIGxgJNkiRpYCzQJK2KJN9Icn2STya5qHlYY9ttn9h83cysx7yw+S7B\nn1y2/KwkO5t4ll6HzbDfUZInzxrPxPYLSS6dYf1nJ/nuifkfT/LKfT2+pLVvkA+qlbQm3V1VJwIk\n+T3g/wV+bdpGSQ5i/GXOTwbe3/ZgSY4CnlJVj13h7QLeXFVvbru/FbbfJ83PM6t/DnwV+DP45oNE\nJW1gjqBJmoePAo9JcniSi5tRrj9L8l3wzRGudyb5KPAO4I3Ay5qRrh+c3FGSByX53SQ3JLkuyULz\n1mXAsc02z1whhuVfSkySbU08lyX5TJLXJnl9s98/S3L4xOqvnBgRPKnZ/uQkf9qs/3+SHD+x30uS\nXAlcwUSBl+SkZv3vSPLiJNc085cn+fYkW4AfB35q6Wdp8vPTzfZbm20+keS9E18nM0pyTpJrk3x6\nDzmQtEZZoElaVc0I0guAG4BfBP68qp7I+Ktm3jGx6uOA762qHwJ+AXhXVZ1YVe9etsufAL5RVU8A\nXsH461QOBl4M/FWzzUeXh8Huguf6pnBa8p3ADwAnAb8MfKWqnsR49OpHJrZ/cDMi+Brg7c3yTwHP\natY/Ezh7Yr8nAv+qqhaa7UnydOA3gVOq6q+Bq6vqac32fwD8bFXtAP4H4xG/pZ+l2F3kvQP4mSaH\nn2yOS/P+gVX1VOA/TCyXtA54iVPSannwxPf+fYRxUXMt8C8BquqqJA9Pcgjj4uKSqvqHZv2wwohX\n4xnAW5p9fDrJ3wDHA3+3l1j2dImzgKuq6mvA15LcBSz1in0SeMLEehc2x7w6yaFJDgUOA96R5DHN\nOpOfoZdV1V0T848Hfgt4XlXd3iw7LslFwFHAwcBfT6y/0ojfocBhVXV1s+h8YLKAfW/z73XAlhUz\nIWlNcgRN0mr5ejMCdGJV/WRV3dMs31PhdffE9LSerz3tY1+2+YeJ6fsm5u9j+h+tvwRcWVXfxXgE\nb/JGiOU/z+eArwNPmlj+68BbmtHAH1+2fRvLf6al2L+Bf3BL64oFmqR5uhr4YRjf2Qh8oaq+yrcW\nGl8FDmmxj+OBRwKf3sd49lboZdn0y5pjPhO4q6q+AhwK3Nas86op+7oL+H7gTUme3Syf3H7bxPor\n/fxpjnnnRH/ZK4HRXo4raZ2wQJO0WlYaBTsLeHKSTzDu1zptYt3J9a8CTljpJgHgN4ADktwAvAs4\nbWJ0bm8jb5M9aNcledQKx10+XRPTf5/kuub4P9YsP49xwXUdcOCy9b9lX1X1ecZF2n9vbjQ4C3h3\nko8DX5jY5lLgB5o4nzmxDxjn7FeaHD6BcV/fSvb5zlNJw5Mq/5uWJEkaEkfQJEmSBsYCTZIkaWAs\n0CRJkgbGAk2SJGlgLNAkSZIGxgJNkiRpYCzQJEmSBsYCTZIkaWD+f2wjJrUnu986AAAAAElFTkSu\nQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x10b0c3dd0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "df_train['Embarked_Val'].hist(bins=len(embarked_locs), range=(0, 3))\n",
    "plt.title('Port of Embarkation Histogram')\n",
    "plt.xlabel('Port of Embarkation')\n",
    "plt.ylabel('Count')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Since the vast majority of passengers embarked in 'S': 3, we assign the missing values in Embarked to 'S': "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "if len(df_train[df_train['Embarked'].isnull()] > 0):\n",
    "    df_train.replace({'Embarked_Val' : \n",
    "                   { embarked_locs_mapping[nan] : embarked_locs_mapping['S'] \n",
    "                   }\n",
    "               }, \n",
    "               inplace=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Verify we do not have any more NaNs for Embarked_Val:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1, 2, 3])"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "embarked_locs = sort(df_train['Embarked_Val'].unique())\n",
    "embarked_locs"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Plot a normalized cross tab for Embarked_Val and Survived:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.text.Text at 0x10b7e28d0>"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAl4AAAFMCAYAAAAa17KLAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\newAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x10ba3e790>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "embarked_val_xt = pd.crosstab(df_train['Embarked_Val'], df_train['Survived'])\n",
    "embarked_val_xt_pct = \\\n",
    "    embarked_val_xt.div(embarked_val_xt.sum(1).astype(float), axis=0)\n",
    "embarked_val_xt_pct.plot(kind='bar', stacked=True)\n",
    "plt.title('Survival Rate by Port of Embarkation')\n",
    "plt.xlabel('Port of Embarkation')\n",
    "plt.ylabel('Survival Rate')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "It appears those that embarked in location 'C': 1 had the highest rate of survival.  We'll dig in some more to see why this might be the case.  Below we plot a graphs to determine gender and passenger class makeup for each port:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAlEAAAJKCAYAAAAMbRCGAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nRU5ErkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x10b30de50>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Set up a grid of plots\n",
    "fig = plt.figure(figsize=fizsize_with_subplots) \n",
    "\n",
    "rows = 2\n",
    "cols = 3\n",
    "col_names = ('Sex_Val', 'Pclass')\n",
    "\n",
    "for portIdx in embarked_locs:\n",
    "    for colIdx in range(0, len(col_names)):\n",
    "        plt.subplot2grid((rows, cols), (colIdx, portIdx - 1))\n",
    "        df_train[df_train['Embarked_Val'] == portIdx][col_names[colIdx]] \\\n",
    "            .value_counts().plot(kind='bar')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Leaving Embarked as integers implies ordering in the values, which does not exist.  Another way to represent Embarked without ordering is to create dummy variables:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "df_train = pd.concat([df_train, pd.get_dummies(df_train['Embarked_Val'], prefix='Embarked_Val')], axis=1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Feature: Age"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The Age column seems like an important feature--unfortunately it is missing many values.  We'll need to fill in the missing values like we did with Embarked."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Filter to view missing Age values:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Sex</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Age</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>5 </th>\n",
       "      <td>   male</td>\n",
       "      <td> 3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>   male</td>\n",
       "      <td> 2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td> female</td>\n",
       "      <td> 3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>   male</td>\n",
       "      <td> 3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td> female</td>\n",
       "      <td> 3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       Sex  Pclass  Age\n",
       "5     male       3  NaN\n",
       "17    male       2  NaN\n",
       "19  female       3  NaN\n",
       "26    male       3  NaN\n",
       "28  female       3  NaN"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train[df_train['Age'].isnull()][['Sex', 'Pclass', 'Age']].head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Determine the Age typical for each passenger class by Sex_Val.  We'll use the median instead of the mean because the Age histogram seems to be right skewed."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "# To keep Age in tact, make a copy of it called AgeFill \n",
    "# that we will use to fill in the missing ages:\n",
    "df_train['AgeFill'] = df_train['Age']\n",
    "\n",
    "# Populate AgeFill\n",
    "df_train['AgeFill'] = df_train['AgeFill'] \\\n",
    "                        .groupby([df_train['Sex_Val'], df_train['Pclass']]) \\\n",
    "                        .apply(lambda x: x.fillna(x.median()))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Ensure AgeFill does not contain any missing values:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(df_train[df_train['AgeFill'].isnull()])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Plot a normalized cross tab for AgeFill and Survived:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.text.Text at 0x10c4125d0>"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAmcAAAJoCAYAAAAj5EbEAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x10c054390>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Set up a grid of plots\n",
    "fig, axes = plt.subplots(2, 1, figsize=fizsize_with_subplots)\n",
    "\n",
    "# Histogram of AgeFill segmented by Survived\n",
    "df1 = df_train[df_train['Survived'] == 0]['Age']\n",
    "df2 = df_train[df_train['Survived'] == 1]['Age']\n",
    "max_age = max(df_train['AgeFill'])\n",
    "axes[0].hist([df1, df2], \n",
    "             bins=max_age / bin_size, \n",
    "             range=(1, max_age), \n",
    "             stacked=True)\n",
    "axes[0].legend(('Died', 'Survived'), loc='best')\n",
    "axes[0].set_title('Survivors by Age Groups Histogram')\n",
    "axes[0].set_xlabel('Age')\n",
    "axes[0].set_ylabel('Count')\n",
    "\n",
    "# Scatter plot Survived and AgeFill\n",
    "axes[1].scatter(df_train['Survived'], df_train['AgeFill'])\n",
    "axes[1].set_title('Survivors by Age Plot')\n",
    "axes[1].set_xlabel('Survived')\n",
    "axes[1].set_ylabel('Age')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Unfortunately, the graphs above do not seem to clearly show any insights.  We'll keep digging further."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Plot AgeFill density by Pclass:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.legend.Legend at 0x10be093d0>"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAm0AAAFRCAYAAAAmW5r1AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x10b6d4b50>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "for pclass in passenger_classes:\n",
    "    df_train.AgeFill[df_train.Pclass == pclass].plot(kind='kde')\n",
    "plt.title('Age Density Plot by Passenger Class')\n",
    "plt.xlabel('Age')\n",
    "plt.legend(('1st Class', '2nd Class', '3rd Class'), loc='best')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "When looking at AgeFill density by Pclass, we see the first class passengers were generally older then second class passengers, which in turn were older than third class passengers.  We've determined that first class passengers had a higher survival rate than second class passengers, which in turn had a higher survival rate than third class passengers."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x10d6c22d0>"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAlcAAAJPCAYAAABRvvFyAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x10d3a5290>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Set up a grid of plots\n",
    "fig = plt.figure(figsize=fizsize_with_subplots) \n",
    "fig_dims = (3, 1)\n",
    "\n",
    "# Plot the AgeFill histogram for Survivors\n",
    "plt.subplot2grid(fig_dims, (0, 0))\n",
    "survived_df = df_train[df_train['Survived'] == 1]\n",
    "survived_df['AgeFill'].hist(bins=max_age / bin_size, range=(1, max_age))\n",
    "\n",
    "# Plot the AgeFill histogram for Females\n",
    "plt.subplot2grid(fig_dims, (1, 0))\n",
    "females_df = df_train[(df_train['Sex_Val'] == 0) & (df_train['Survived'] == 1)]\n",
    "females_df['AgeFill'].hist(bins=max_age / bin_size, range=(1, max_age))\n",
    "\n",
    "# Plot the AgeFill histogram for first class passengers\n",
    "plt.subplot2grid(fig_dims, (2, 0))\n",
    "class1_df = df_train[(df_train['Pclass'] == 1) & (df_train['Survived'] == 1)]\n",
    "class1_df['AgeFill'].hist(bins=max_age / bin_size, range=(1, max_age))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In the first graph, we see that most survivors come from the 20's to 30's age ranges and might be explained by the following two graphs.  The second graph shows most females are within their 20's.  The third graph shows most first class passengers are within their 30's."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Feature: Family Size"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Feature enginering involves creating new features or modifying existing features which might be advantageous to a machine learning algorithm.\n",
    "\n",
    "Define a new feature FamilySize that is the sum of Parch (number of parents or children on board) and SibSp (number of siblings or spouses):"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>PassengerId</th>\n",
       "      <th>Survived</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Name</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>Sex_Val</th>\n",
       "      <th>Embarked_Val</th>\n",
       "      <th>Embarked_Val_1</th>\n",
       "      <th>Embarked_Val_2</th>\n",
       "      <th>Embarked_Val_3</th>\n",
       "      <th>AgeFill</th>\n",
       "      <th>FamilySize</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</td>\n",
       "      <td> 1</td>\n",
       "      <td> 0</td>\n",
       "      <td>        A/5 21171</td>\n",
       "      <td>  7.2500</td>\n",
       "      <td>  NaN</td>\n",
       "      <td> S</td>\n",
       "      <td> 1</td>\n",
       "      <td> 3</td>\n",
       "      <td> 0</td>\n",
       "      <td> 0</td>\n",
       "      <td> 1</td>\n",
       "      <td> 22</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</td>\n",
       "      <td> 1</td>\n",
       "      <td> 0</td>\n",
       "      <td>         PC 17599</td>\n",
       "      <td> 71.2833</td>\n",
       "      <td>  C85</td>\n",
       "      <td> C</td>\n",
       "      <td> 0</td>\n",
       "      <td> 1</td>\n",
       "      <td> 1</td>\n",
       "      <td> 0</td>\n",
       "      <td> 0</td>\n",
       "      <td> 38</td>\n",
       "      <td> 1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td> 3</td>\n",
       "      <td> 1</td>\n",
       "      <td> 3</td>\n",
       "      <td>                            Heikkinen, Miss. Laina</td>\n",
       "      <td> female</td>\n",
       "      <td> 26</td>\n",
       "      <td> 0</td>\n",
       "      <td> 0</td>\n",
       "      <td> STON/O2. 3101282</td>\n",
       "      <td>  7.9250</td>\n",
       "      <td>  NaN</td>\n",
       "      <td> S</td>\n",
       "      <td> 0</td>\n",
       "      <td> 3</td>\n",
       "      <td> 0</td>\n",
       "      <td> 0</td>\n",
       "      <td> 1</td>\n",
       "      <td> 26</td>\n",
       "      <td> 0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td> 4</td>\n",
       "      <td> 1</td>\n",
       "      <td> 1</td>\n",
       "      <td>      Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n",
       "      <td> female</td>\n",
       "      <td> 35</td>\n",
       "      <td> 1</td>\n",
       "      <td> 0</td>\n",
       "      <td>           113803</td>\n",
       "      <td> 53.1000</td>\n",
       "      <td> C123</td>\n",
       "      <td> S</td>\n",
       "      <td> 0</td>\n",
       "      <td> 3</td>\n",
       "      <td> 0</td>\n",
       "      <td> 0</td>\n",
       "      <td> 1</td>\n",
       "      <td> 35</td>\n",
       "      <td> 1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td> 5</td>\n",
       "      <td> 0</td>\n",
       "      <td> 3</td>\n",
       "      <td>                          Allen, Mr. William Henry</td>\n",
       "      <td>   male</td>\n",
       "      <td> 35</td>\n",
       "      <td> 0</td>\n",
       "      <td> 0</td>\n",
       "      <td>           373450</td>\n",
       "      <td>  8.0500</td>\n",
       "      <td>  NaN</td>\n",
       "      <td> S</td>\n",
       "      <td> 1</td>\n",
       "      <td> 3</td>\n",
       "      <td> 0</td>\n",
       "      <td> 0</td>\n",
       "      <td> 1</td>\n",
       "      <td> 35</td>\n",
       "      <td> 0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   PassengerId  Survived  Pclass  \\\n",
       "0            1         0       3   \n",
       "1            2         1       1   \n",
       "2            3         1       3   \n",
       "3            4         1       1   \n",
       "4            5         0       3   \n",
       "\n",
       "                                                Name     Sex  Age  SibSp  \\\n",
       "0                            Braund, Mr. Owen Harris    male   22      1   \n",
       "1  Cumings, Mrs. John Bradley (Florence Briggs Th...  female   38      1   \n",
       "2                             Heikkinen, Miss. Laina  female   26      0   \n",
       "3       Futrelle, Mrs. Jacques Heath (Lily May Peel)  female   35      1   \n",
       "4                           Allen, Mr. William Henry    male   35      0   \n",
       "\n",
       "   Parch            Ticket     Fare Cabin Embarked  Sex_Val  Embarked_Val  \\\n",
       "0      0         A/5 21171   7.2500   NaN        S        1             3   \n",
       "1      0          PC 17599  71.2833   C85        C        0             1   \n",
       "2      0  STON/O2. 3101282   7.9250   NaN        S        0             3   \n",
       "3      0            113803  53.1000  C123        S        0             3   \n",
       "4      0            373450   8.0500   NaN        S        1             3   \n",
       "\n",
       "   Embarked_Val_1  Embarked_Val_2  Embarked_Val_3  AgeFill  FamilySize  \n",
       "0               0               0               1       22           1  \n",
       "1               1               0               0       38           1  \n",
       "2               0               0               1       26           0  \n",
       "3               0               0               1       35           1  \n",
       "4               0               0               1       35           0  "
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train['FamilySize'] = df_train['SibSp'] + df_train['Parch']\n",
    "df_train.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Plot a histogram of FamilySize:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.text.Text at 0x10db78590>"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAlcAAAFCCAYAAADcyPgxAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x10be12450>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "df_train['FamilySize'].hist()\n",
    "plt.title('Family Size Histogram')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Plot a histogram of AgeFill segmented by Survived:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.text.Text at 0x10dd85bd0>"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAlcAAAFCCAYAAADcyPgxAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nQn26Z51/swAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x10c473890>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Get the unique values of Embarked and its maximum\n",
    "family_sizes = sort(df_train['FamilySize'].unique())\n",
    "family_size_max = max(family_sizes)\n",
    "\n",
    "df1 = df_train[df_train['Survived'] == 0]['FamilySize']\n",
    "df2 = df_train[df_train['Survived'] == 1]['FamilySize']\n",
    "plt.hist([df1, df2], \n",
    "         bins=family_size_max + 1, \n",
    "         range=(0, family_size_max), \n",
    "         stacked=True)\n",
    "plt.legend(('Died', 'Survived'), loc='best')\n",
    "plt.title('Survivors by Family Size')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Based on the histograms, it is not immediately obvious what impact FamilySize has on survival.  The machine learning algorithms might benefit from this feature.\n",
    "\n",
    "Additional features we might want to engineer might be related to the Name column, for example honorrary or pedestrian titles might give clues and better predictive power for a male's survival."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Final Data Preparation for Machine Learning"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Many machine learning algorithms do not work on strings and they usually require the data to be in an array, not a DataFrame.\n",
    "\n",
    "Show only the columns of type 'object' (strings):"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Name        object\n",
       "Sex         object\n",
       "Ticket      object\n",
       "Cabin       object\n",
       "Embarked    object\n",
       "dtype: object"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train.dtypes[df_train.dtypes.map(lambda x: x == 'object')]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Drop the columns we won't use:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "df_train = df_train.drop(['Name', 'Sex', 'Ticket', 'Cabin', 'Embarked'], \n",
    "                         axis=1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Drop the following columns:\n",
    "* The Age column since we will be using the AgeFill column instead.\n",
    "* The SibSp and Parch columns since we will be using FamilySize instead.\n",
    "* The PassengerId column since it won't be used as a feature.\n",
    "* The Embarked_Val as we decided to use dummy variables instead."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Survived            int64\n",
       "Pclass              int64\n",
       "Fare              float64\n",
       "Sex_Val             int64\n",
       "Embarked_Val_1    float64\n",
       "Embarked_Val_2    float64\n",
       "Embarked_Val_3    float64\n",
       "AgeFill           float64\n",
       "FamilySize          int64\n",
       "dtype: object"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train = df_train.drop(['Age', 'SibSp', 'Parch', 'PassengerId', 'Embarked_Val'], axis=1)\n",
    "df_train.dtypes"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Convert the DataFrame to a numpy array:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[  0.    ,   3.    ,   7.25  , ...,   1.    ,  22.    ,   1.    ],\n",
       "       [  1.    ,   1.    ,  71.2833, ...,   0.    ,  38.    ,   1.    ],\n",
       "       [  1.    ,   3.    ,   7.925 , ...,   1.    ,  26.    ,   0.    ],\n",
       "       ..., \n",
       "       [  0.    ,   3.    ,  23.45  , ...,   1.    ,  21.5   ,   3.    ],\n",
       "       [  1.    ,   1.    ,  30.    , ...,   0.    ,  26.    ,   0.    ],\n",
       "       [  0.    ,   3.    ,   7.75  , ...,   0.    ,  32.    ,   0.    ]])"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_data = df_train.values\n",
    "train_data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Data Wrangling Summary"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Below is a summary of the data wrangling we performed on our training data set.  We encapsulate this in a function since we'll need to do the same operations to our test set later."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "def clean_data(df, drop_passenger_id):\n",
    "    \n",
    "    # Get the unique values of Sex\n",
    "    sexes = sort(df['Sex'].unique())\n",
    "    \n",
    "    # Generate a mapping of Sex from a string to a number representation    \n",
    "    genders_mapping = dict(zip(sexes, range(0, len(sexes) + 1)))\n",
    "\n",
    "    # Transform Sex from a string to a number representation\n",
    "    df['Sex_Val'] = df['Sex'].map(genders_mapping).astype(int)\n",
    "    \n",
    "    # Get the unique values of Embarked\n",
    "    embarked_locs = sort(df['Embarked'].unique())\n",
    "\n",
    "    # Generate a mapping of Embarked from a string to a number representation        \n",
    "    embarked_locs_mapping = dict(zip(embarked_locs, \n",
    "                                     range(0, len(embarked_locs) + 1)))\n",
    "    \n",
    "    # Transform Embarked from a string to dummy variables\n",
    "    df = pd.concat([df, pd.get_dummies(df['Embarked'], prefix='Embarked_Val')], axis=1)\n",
    "    \n",
    "    # Fill in missing values of Embarked\n",
    "    # Since the vast majority of passengers embarked in 'S': 3, \n",
    "    # we assign the missing values in Embarked to 'S':\n",
    "    if len(df[df['Embarked'].isnull()] > 0):\n",
    "        df.replace({'Embarked_Val' : \n",
    "                       { embarked_locs_mapping[nan] : embarked_locs_mapping['S'] \n",
    "                       }\n",
    "                   }, \n",
    "                   inplace=True)\n",
    "    \n",
    "    # Fill in missing values of Fare with the average Fare\n",
    "    if len(df[df['Fare'].isnull()] > 0):\n",
    "        avg_fare = df['Fare'].mean()\n",
    "        df.replace({ None: avg_fare }, inplace=True)\n",
    "    \n",
    "    # To keep Age in tact, make a copy of it called AgeFill \n",
    "    # that we will use to fill in the missing ages:\n",
    "    df['AgeFill'] = df['Age']\n",
    "\n",
    "    # Determine the Age typical for each passenger class by Sex_Val.  \n",
    "    # We'll use the median instead of the mean because the Age \n",
    "    # histogram seems to be right skewed.\n",
    "    df['AgeFill'] = df['AgeFill'] \\\n",
    "                        .groupby([df['Sex_Val'], df['Pclass']]) \\\n",
    "                        .apply(lambda x: x.fillna(x.median()))\n",
    "            \n",
    "    # Define a new feature FamilySize that is the sum of \n",
    "    # Parch (number of parents or children on board) and \n",
    "    # SibSp (number of siblings or spouses):\n",
    "    df['FamilySize'] = df['SibSp'] + df['Parch']\n",
    "    \n",
    "    # Drop the columns we won't use:\n",
    "    df = df.drop(['Name', 'Sex', 'Ticket', 'Cabin', 'Embarked'], axis=1)\n",
    "    \n",
    "    # Drop the Age column since we will be using the AgeFill column instead.\n",
    "    # Drop the SibSp and Parch columns since we will be using FamilySize.\n",
    "    # Drop the PassengerId column since it won't be used as a feature.\n",
    "    df = df.drop(['Age', 'SibSp', 'Parch'], axis=1)\n",
    "    \n",
    "    if drop_passenger_id:\n",
    "        df = df.drop(['PassengerId'], axis=1)\n",
    "    \n",
    "    return df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Random Forest: Training"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Create the random forest object:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "from sklearn.ensemble import RandomForestClassifier\n",
    "\n",
    "clf = RandomForestClassifier(n_estimators=100)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Fit the training data and create the decision trees:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Mean accuracy of Random Forest: 0.980920314254'"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Training data features, skip the first column 'Survived'\n",
    "train_features = train_data[:, 1:]\n",
    "\n",
    "# 'Survived' column values\n",
    "train_target = train_data[:, 0]\n",
    "\n",
    "# Fit the model to our training data\n",
    "clf = clf.fit(train_features, train_target)\n",
    "score = clf.score(train_features, train_target)\n",
    "\"Mean accuracy of Random Forest: {0}\".format(score)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Random Forest: Predicting"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Read the test data:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\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": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_test = pd.read_csv('../data/titanic/test.csv')\n",
    "df_test.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Note the test data does not contain the column 'Survived', we'll use our trained model to predict these values."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "# Data wrangle the test set and convert it to a numpy array\n",
    "df_test = clean_data(df_test, drop_passenger_id=False)\n",
    "test_data = df_test.values"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Take the decision trees and run it on the test data:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "# Get the test data features, skipping the first column 'PassengerId'\n",
    "test_x = test_data[:, 1:]\n",
    "\n",
    "# Predict the Survival values for the test data\n",
    "test_y = clf.predict(test_x)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Random Forest: Prepare for Kaggle Submission\n",
    "\n",
    "Create a DataFrame by combining the index from the test data with the output of predictions, then write the results to the output:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "df_test['Survived'] = test_y\n",
    "df_test[['PassengerId', 'Survived']] \\\n",
    "    .to_csv('../data/titanic/results-rf.csv', index=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Evaluate Model Accuracy"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Submitting to Kaggle will give you an accuracy score.  It would be helpful to get an idea of accuracy without submitting to Kaggle.\n",
    "\n",
    "We'll split our training data, 80% will go to \"train\" and 20% will go to \"test\":"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "((891, 8), (891,))\n",
      "((712, 8), (712,))\n",
      "((179, 8), (179,))\n"
     ]
    }
   ],
   "source": [
    "from sklearn import metrics\n",
    "from sklearn.cross_validation import train_test_split\n",
    "\n",
    "# Split 80-20 train vs test data\n",
    "train_x, test_x, train_y, test_y = train_test_split(train_features, \n",
    "                                                    train_target, \n",
    "                                                    test_size=0.20, \n",
    "                                                    random_state=0)\n",
    "print (train_features.shape, train_target.shape)\n",
    "print (train_x.shape, train_y.shape)\n",
    "print (test_x.shape, test_y.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Use the new training data to fit the model, predict, and get the accuracy score:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy = 0.83\n"
     ]
    }
   ],
   "source": [
    "clf = clf.fit(train_x, train_y)\n",
    "predict_y = clf.predict(test_x)\n",
    "\n",
    "from sklearn.metrics import accuracy_score\n",
    "print (\"Accuracy = %.2f\" % (accuracy_score(test_y, predict_y)))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "View the Confusion Matrix:"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "|      | condition True | condition false|\n",
    "|------|----------------|---------------|\n",
    "|prediction true|True Positive|False positive|\n",
    "|Prediction False|False Negative|True Negative|"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAlgAAAE/CAYAAACaf72jAAAEJGlDQ1BJQ0MgUHJvZmlsZQAAOBGF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\nYII=\n",
      "text/plain": [
       "<IPython.core.display.Image at 0x10e2207d0>"
      ]
     },
     "execution_count": 46,
     "metadata": {
      "image/png": {
       "width": 800
      }
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from IPython.core.display import Image \n",
    "Image(filename='../data/confusion_matrix.png', width=800)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Get the model score and confusion matrix:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model Score 0.83 \n",
      "\n",
      "('Confusion Matrix ', array([[98, 12],\n",
      "       [19, 50]]))\n",
      "          Predicted\n",
      "         |  0  |  1  |\n",
      "         |-----|-----|\n",
      "       0 |  98 |  12 |\n",
      "Actual   |-----|-----|\n",
      "       1 |  19 |  50 |\n",
      "         |-----|-----|\n"
     ]
    }
   ],
   "source": [
    "model_score = clf.score(test_x, test_y)\n",
    "print (\"Model Score %.2f \\n\" % (model_score))\n",
    "\n",
    "confusion_matrix = metrics.confusion_matrix(test_y, predict_y)\n",
    "print (\"Confusion Matrix \", confusion_matrix)\n",
    "\n",
    "print (\"          Predicted\")\n",
    "print (\"         |  0  |  1  |\")\n",
    "print (\"         |-----|-----|\")\n",
    "print (\"       0 | %3d | %3d |\" % (confusion_matrix[0, 0],\n",
    "                                   confusion_matrix[0, 1]))\n",
    "print (\"Actual   |-----|-----|\")\n",
    "print (\"       1 | %3d | %3d |\" % (confusion_matrix[1, 0],\n",
    "                                   confusion_matrix[1, 1]))\n",
    "print (\"         |-----|-----|\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Display the classification report:"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "$$Precision = \\frac{TP}{TP + FP}$$ \n",
    "\n",
    "$$Recall = \\frac{TP}{TP + FN}$$ \n",
    "\n",
    "$$F1 = \\frac{2TP}{2TP + FP + FN}$$ "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "Not Survived       0.84      0.89      0.86       110\n",
      "    Survived       0.81      0.72      0.76        69\n",
      "\n",
      " avg / total       0.83      0.83      0.82       179\n",
      "\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import classification_report\n",
    "print(classification_report(test_y, \n",
    "                            predict_y, \n",
    "                            target_names=['Not Survived', 'Survived']))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}