Intuit Challenge.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib as mpl\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline\n",
    "import seaborn as sns\n",
    "sns.set_style('whitegrid')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "df= pd.read_csv(r\"C:\\Users\\welcome\\Desktop\\Intuit\\ML_Challenge_Intuit_Last_Date_5_FEB_2018\\ML_Challenge_Intuit_Last_Date_5_FEB_2018\\ship_data.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Passenger ID</th>\n",
       "      <th>Class</th>\n",
       "      <th>Name</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Age</th>\n",
       "      <th>Siblings Count</th>\n",
       "      <th>Parents Count</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>Survived</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Alexander Harris</td>\n",
       "      <td>male</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7250.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>Frank Parsons</td>\n",
       "      <td>female</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71283.3</td>\n",
       "      <td>Los Angeles</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>Anthony Churchill</td>\n",
       "      <td>female</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7925.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>Alexandra Hughes</td>\n",
       "      <td>female</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53100.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>3</td>\n",
       "      <td>Joan Fraser</td>\n",
       "      <td>male</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8050.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>6</td>\n",
       "      <td>3</td>\n",
       "      <td>Megan Clarkson</td>\n",
       "      <td>male</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8458.3</td>\n",
       "      <td>Chicago</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>7</td>\n",
       "      <td>1</td>\n",
       "      <td>Molly Bower</td>\n",
       "      <td>male</td>\n",
       "      <td>54.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>51862.5</td>\n",
       "      <td>New York</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>8</td>\n",
       "      <td>3</td>\n",
       "      <td>Steven Jones</td>\n",
       "      <td>male</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>21075.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>9</td>\n",
       "      <td>3</td>\n",
       "      <td>Bernadette Vance</td>\n",
       "      <td>female</td>\n",
       "      <td>27.0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>11133.3</td>\n",
       "      <td>New York</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>Irene Chapman</td>\n",
       "      <td>female</td>\n",
       "      <td>-20.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>30070.8</td>\n",
       "      <td>Los Angeles</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Passenger ID  Class               Name  Gender   Age  Siblings Count  \\\n",
       "0             1      3   Alexander Harris    male  22.0               1   \n",
       "1             2      1      Frank Parsons  female  38.0               1   \n",
       "2             3      3  Anthony Churchill  female  26.0               0   \n",
       "3             4      1   Alexandra Hughes  female  35.0               1   \n",
       "4             5      3        Joan Fraser    male  35.0               0   \n",
       "5             6      3     Megan Clarkson    male   NaN               0   \n",
       "6             7      1        Molly Bower    male  54.0               0   \n",
       "7             8      3       Steven Jones    male   2.0               3   \n",
       "8             9      3   Bernadette Vance  female  27.0               0   \n",
       "9            10      2      Irene Chapman  female -20.0               1   \n",
       "\n",
       "   Parents Count     Fare     Embarked  Survived  \n",
       "0              0   7250.0     New York         0  \n",
       "1              0  71283.3  Los Angeles         1  \n",
       "2              0   7925.0     New York         1  \n",
       "3              0  53100.0     New York         1  \n",
       "4              0   8050.0     New York         0  \n",
       "5              0   8458.3      Chicago         0  \n",
       "6              0  51862.5     New York         0  \n",
       "7              1  21075.0     New York         0  \n",
       "8              2  11133.3     New York         1  \n",
       "9              0  30070.8  Los Angeles         1  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 891 entries, 0 to 890\n",
      "Data columns (total 10 columns):\n",
      "Passenger ID      891 non-null int64\n",
      "Class             891 non-null int64\n",
      "Name              891 non-null object\n",
      "Gender            891 non-null object\n",
      "Age               714 non-null float64\n",
      "Siblings Count    891 non-null int64\n",
      "Parents Count     891 non-null int64\n",
      "Fare              891 non-null float64\n",
      "Embarked          889 non-null object\n",
      "Survived          891 non-null int64\n",
      "dtypes: float64(2), int64(5), object(3)\n",
      "memory usage: 69.7+ KB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "177"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Age'].isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Embarked'].isnull().sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 5) Replace all NULL and NAN values in the dataset programatically:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Passenger ID</th>\n",
       "      <th>Class</th>\n",
       "      <th>Name</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Age</th>\n",
       "      <th>Siblings Count</th>\n",
       "      <th>Parents Count</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>Survived</th>\n",
       "      <th>AgeFill</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Alexander Harris</td>\n",
       "      <td>male</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7250.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>0</td>\n",
       "      <td>22.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>Frank Parsons</td>\n",
       "      <td>female</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71283.3</td>\n",
       "      <td>Los Angeles</td>\n",
       "      <td>1</td>\n",
       "      <td>38.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>Anthony Churchill</td>\n",
       "      <td>female</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7925.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>1</td>\n",
       "      <td>26.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>Alexandra Hughes</td>\n",
       "      <td>female</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53100.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>1</td>\n",
       "      <td>35.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>3</td>\n",
       "      <td>Joan Fraser</td>\n",
       "      <td>male</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8050.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>0</td>\n",
       "      <td>35.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Passenger ID  Class               Name  Gender   Age  Siblings Count  \\\n",
       "0             1      3   Alexander Harris    male  22.0               1   \n",
       "1             2      1      Frank Parsons  female  38.0               1   \n",
       "2             3      3  Anthony Churchill  female  26.0               0   \n",
       "3             4      1   Alexandra Hughes  female  35.0               1   \n",
       "4             5      3        Joan Fraser    male  35.0               0   \n",
       "\n",
       "   Parents Count     Fare     Embarked  Survived  AgeFill  \n",
       "0              0   7250.0     New York         0     22.0  \n",
       "1              0  71283.3  Los Angeles         1     38.0  \n",
       "2              0   7925.0     New York         1     26.0  \n",
       "3              0  53100.0     New York         1     35.0  \n",
       "4              0   8050.0     New York         0     35.0  "
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#for Age column:\n",
    "# fill in the missing ages:\n",
    "df['AgeFill'] = df['Age']\n",
    "\n",
    "# Populate AgeFill\n",
    "df['AgeFill'] = df['AgeFill'].groupby([df['Class'], df['Gender']]).apply(lambda x: x.fillna(x.median()))\n",
    "df.head()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Passenger ID</th>\n",
       "      <th>Class</th>\n",
       "      <th>Name</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Siblings Count</th>\n",
       "      <th>Parents Count</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>Survived</th>\n",
       "      <th>AgeFill</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Alexander Harris</td>\n",
       "      <td>male</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7250.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>0</td>\n",
       "      <td>22.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>Frank Parsons</td>\n",
       "      <td>female</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71283.3</td>\n",
       "      <td>Los Angeles</td>\n",
       "      <td>1</td>\n",
       "      <td>38.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>Anthony Churchill</td>\n",
       "      <td>female</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7925.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>1</td>\n",
       "      <td>26.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>Alexandra Hughes</td>\n",
       "      <td>female</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53100.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>1</td>\n",
       "      <td>35.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>3</td>\n",
       "      <td>Joan Fraser</td>\n",
       "      <td>male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8050.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>0</td>\n",
       "      <td>35.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Passenger ID  Class               Name  Gender  Siblings Count  \\\n",
       "0             1      3   Alexander Harris    male               1   \n",
       "1             2      1      Frank Parsons  female               1   \n",
       "2             3      3  Anthony Churchill  female               0   \n",
       "3             4      1   Alexandra Hughes  female               1   \n",
       "4             5      3        Joan Fraser    male               0   \n",
       "\n",
       "   Parents Count     Fare     Embarked  Survived  AgeFill  \n",
       "0              0   7250.0     New York         0     22.0  \n",
       "1              0  71283.3  Los Angeles         1     38.0  \n",
       "2              0   7925.0     New York         1     26.0  \n",
       "3              0  53100.0     New York         1     35.0  \n",
       "4              0   8050.0     New York         0     35.0  "
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.drop(['Age'], axis=1, inplace=True)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "New York       644\n",
      "Los Angeles    168\n",
      "Chicago         77\n",
      "Name: Embarked, dtype: int64\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\welcome\\Anaconda2\\lib\\site-packages\\seaborn\\categorical.py:1460: FutureWarning: remove_na is deprecated and is a private function. Do not use.\n",
      "  stat_data = remove_na(group_data)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.FacetGrid at 0x14063c88>"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAASUAAAEYCAYAAAAag+AEAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nkogYRVESEaMoSiJiFEVJRIyiKImIUf4PFjm1zwrSkgQAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x140634e0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#for embarked:\n",
    "print df['Embarked'].value_counts()\n",
    "sns.factorplot('Embarked', data=df, kind='count')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Passenger ID</th>\n",
       "      <th>Class</th>\n",
       "      <th>Name</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Siblings Count</th>\n",
       "      <th>Parents Count</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>Survived</th>\n",
       "      <th>AgeFill</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Alexander Harris</td>\n",
       "      <td>male</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7250.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>0</td>\n",
       "      <td>22.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>Frank Parsons</td>\n",
       "      <td>female</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71283.3</td>\n",
       "      <td>Los Angeles</td>\n",
       "      <td>1</td>\n",
       "      <td>38.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>Anthony Churchill</td>\n",
       "      <td>female</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7925.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>1</td>\n",
       "      <td>26.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>Alexandra Hughes</td>\n",
       "      <td>female</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53100.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>1</td>\n",
       "      <td>35.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>3</td>\n",
       "      <td>Joan Fraser</td>\n",
       "      <td>male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8050.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>0</td>\n",
       "      <td>35.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>6</td>\n",
       "      <td>3</td>\n",
       "      <td>Megan Clarkson</td>\n",
       "      <td>male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8458.3</td>\n",
       "      <td>Chicago</td>\n",
       "      <td>0</td>\n",
       "      <td>25.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>7</td>\n",
       "      <td>1</td>\n",
       "      <td>Molly Bower</td>\n",
       "      <td>male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>51862.5</td>\n",
       "      <td>New York</td>\n",
       "      <td>0</td>\n",
       "      <td>54.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>8</td>\n",
       "      <td>3</td>\n",
       "      <td>Steven Jones</td>\n",
       "      <td>male</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>21075.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>0</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>9</td>\n",
       "      <td>3</td>\n",
       "      <td>Bernadette Vance</td>\n",
       "      <td>female</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>11133.3</td>\n",
       "      <td>New York</td>\n",
       "      <td>1</td>\n",
       "      <td>27.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>Irene Chapman</td>\n",
       "      <td>female</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>30070.8</td>\n",
       "      <td>Los Angeles</td>\n",
       "      <td>1</td>\n",
       "      <td>-20.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Passenger ID  Class               Name  Gender  Siblings Count  \\\n",
       "0             1      3   Alexander Harris    male               1   \n",
       "1             2      1      Frank Parsons  female               1   \n",
       "2             3      3  Anthony Churchill  female               0   \n",
       "3             4      1   Alexandra Hughes  female               1   \n",
       "4             5      3        Joan Fraser    male               0   \n",
       "5             6      3     Megan Clarkson    male               0   \n",
       "6             7      1        Molly Bower    male               0   \n",
       "7             8      3       Steven Jones    male               3   \n",
       "8             9      3   Bernadette Vance  female               0   \n",
       "9            10      2      Irene Chapman  female               1   \n",
       "\n",
       "   Parents Count     Fare     Embarked  Survived  AgeFill  \n",
       "0              0   7250.0     New York         0     22.0  \n",
       "1              0  71283.3  Los Angeles         1     38.0  \n",
       "2              0   7925.0     New York         1     26.0  \n",
       "3              0  53100.0     New York         1     35.0  \n",
       "4              0   8050.0     New York         0     35.0  \n",
       "5              0   8458.3      Chicago         0     25.0  \n",
       "6              0  51862.5     New York         0     54.0  \n",
       "7              1  21075.0     New York         0      2.0  \n",
       "8              2  11133.3     New York         1     27.0  \n",
       "9              0  30070.8  Los Angeles         1    -20.0  "
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#most of the values of Embarked are 'New York', so i replace the NaN values with 'New York':\n",
    "df['Embarked'].fillna('New York', inplace= True)\n",
    "df.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "New York       646\n",
      "Los Angeles    168\n",
      "Chicago         77\n",
      "Name: Embarked, dtype: int64\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.FacetGrid at 0x1411ff60>"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAASUAAAEYCAYAAAAag+AEAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x14312588>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "print df['Embarked'].value_counts()\n",
    "sns.factorplot('Embarked', data=df, kind='count')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 891 entries, 0 to 890\n",
      "Data columns (total 10 columns):\n",
      "Passenger ID      891 non-null int64\n",
      "Class             891 non-null int64\n",
      "Name              891 non-null object\n",
      "Gender            891 non-null object\n",
      "Siblings Count    891 non-null int64\n",
      "Parents Count     891 non-null int64\n",
      "Fare              891 non-null float64\n",
      "Embarked          891 non-null object\n",
      "Survived          891 non-null int64\n",
      "AgeFill           891 non-null float64\n",
      "dtypes: float64(2), int64(5), object(3)\n",
      "memory usage: 69.7+ KB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 6) Find the number of passengers who were alone and who were with family:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Passenger ID</th>\n",
       "      <th>Class</th>\n",
       "      <th>Name</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Siblings Count</th>\n",
       "      <th>Parents Count</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>Survived</th>\n",
       "      <th>AgeFill</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Alexander Harris</td>\n",
       "      <td>male</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7250.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>0</td>\n",
       "      <td>22.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>Frank Parsons</td>\n",
       "      <td>female</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71283.3</td>\n",
       "      <td>Los Angeles</td>\n",
       "      <td>1</td>\n",
       "      <td>38.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>Anthony Churchill</td>\n",
       "      <td>female</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7925.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>1</td>\n",
       "      <td>26.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>Alexandra Hughes</td>\n",
       "      <td>female</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53100.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>1</td>\n",
       "      <td>35.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>3</td>\n",
       "      <td>Joan Fraser</td>\n",
       "      <td>male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8050.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>0</td>\n",
       "      <td>35.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Passenger ID  Class               Name  Gender  Siblings Count  \\\n",
       "0             1      3   Alexander Harris    male               1   \n",
       "1             2      1      Frank Parsons  female               1   \n",
       "2             3      3  Anthony Churchill  female               0   \n",
       "3             4      1   Alexandra Hughes  female               1   \n",
       "4             5      3        Joan Fraser    male               0   \n",
       "\n",
       "   Parents Count     Fare     Embarked  Survived  AgeFill  \n",
       "0              0   7250.0     New York         0     22.0  \n",
       "1              0  71283.3  Los Angeles         1     38.0  \n",
       "2              0   7925.0     New York         1     26.0  \n",
       "3              0  53100.0     New York         1     35.0  \n",
       "4              0   8050.0     New York         0     35.0  "
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Passenger ID</th>\n",
       "      <th>Class</th>\n",
       "      <th>Name</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Siblings Count</th>\n",
       "      <th>Parents Count</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>Survived</th>\n",
       "      <th>AgeFill</th>\n",
       "      <th>Family_members</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Alexander Harris</td>\n",
       "      <td>male</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7250.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>Frank Parsons</td>\n",
       "      <td>female</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71283.3</td>\n",
       "      <td>Los Angeles</td>\n",
       "      <td>1</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>Anthony Churchill</td>\n",
       "      <td>female</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7925.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>1</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>Alexandra Hughes</td>\n",
       "      <td>female</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53100.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>1</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>3</td>\n",
       "      <td>Joan Fraser</td>\n",
       "      <td>male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8050.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>0</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Passenger ID  Class               Name  Gender  Siblings Count  \\\n",
       "0             1      3   Alexander Harris    male               1   \n",
       "1             2      1      Frank Parsons  female               1   \n",
       "2             3      3  Anthony Churchill  female               0   \n",
       "3             4      1   Alexandra Hughes  female               1   \n",
       "4             5      3        Joan Fraser    male               0   \n",
       "\n",
       "   Parents Count     Fare     Embarked  Survived  AgeFill  Family_members  \n",
       "0              0   7250.0     New York         0     22.0               1  \n",
       "1              0  71283.3  Los Angeles         1     38.0               1  \n",
       "2              0   7925.0     New York         1     26.0               0  \n",
       "3              0  53100.0     New York         1     35.0               1  \n",
       "4              0   8050.0     New York         0     35.0               0  "
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Family_members'] = df['Siblings Count']+ df['Parents Count']\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Passenger ID</th>\n",
       "      <th>Class</th>\n",
       "      <th>Name</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Siblings Count</th>\n",
       "      <th>Parents Count</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>Survived</th>\n",
       "      <th>AgeFill</th>\n",
       "      <th>Family_members</th>\n",
       "      <th>Alone/With Family</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Alexander Harris</td>\n",
       "      <td>male</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7250.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>Frank Parsons</td>\n",
       "      <td>female</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71283.3</td>\n",
       "      <td>Los Angeles</td>\n",
       "      <td>1</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>Anthony Churchill</td>\n",
       "      <td>female</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7925.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>1</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>Alexandra Hughes</td>\n",
       "      <td>female</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53100.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>1</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>3</td>\n",
       "      <td>Joan Fraser</td>\n",
       "      <td>male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8050.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>0</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Passenger ID  Class               Name  Gender  Siblings Count  \\\n",
       "0             1      3   Alexander Harris    male               1   \n",
       "1             2      1      Frank Parsons  female               1   \n",
       "2             3      3  Anthony Churchill  female               0   \n",
       "3             4      1   Alexandra Hughes  female               1   \n",
       "4             5      3        Joan Fraser    male               0   \n",
       "\n",
       "   Parents Count     Fare     Embarked  Survived  AgeFill  Family_members  \\\n",
       "0              0   7250.0     New York         0     22.0               1   \n",
       "1              0  71283.3  Los Angeles         1     38.0               1   \n",
       "2              0   7925.0     New York         1     26.0               0   \n",
       "3              0  53100.0     New York         1     35.0               1   \n",
       "4              0   8050.0     New York         0     35.0               0   \n",
       "\n",
       "   Alone/With Family  \n",
       "0                  1  \n",
       "1                  1  \n",
       "2                  0  \n",
       "3                  1  \n",
       "4                  0  "
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Alone/With Family'] = df['Family_members']\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\welcome\\Anaconda2\\lib\\site-packages\\pandas\\core\\indexing.py:194: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame\n",
      "\n",
      "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
      "  self._setitem_with_indexer(indexer, value)\n"
     ]
    }
   ],
   "source": [
    "df['Alone/With Family'].loc[df['Family_members'] >0] = 'With Family'\n",
    "df['Alone/With Family'].loc[df['Family_members'] == 0] = 'Alone'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Passenger ID</th>\n",
       "      <th>Class</th>\n",
       "      <th>Name</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Siblings Count</th>\n",
       "      <th>Parents Count</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>Survived</th>\n",
       "      <th>AgeFill</th>\n",
       "      <th>Family_members</th>\n",
       "      <th>Alone/With Family</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Alexander Harris</td>\n",
       "      <td>male</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7250.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>With Family</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>Frank Parsons</td>\n",
       "      <td>female</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71283.3</td>\n",
       "      <td>Los Angeles</td>\n",
       "      <td>1</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>With Family</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>Anthony Churchill</td>\n",
       "      <td>female</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7925.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>1</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>Alone</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>Alexandra Hughes</td>\n",
       "      <td>female</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53100.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>1</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>With Family</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>3</td>\n",
       "      <td>Joan Fraser</td>\n",
       "      <td>male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8050.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>0</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>Alone</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Passenger ID  Class               Name  Gender  Siblings Count  \\\n",
       "0             1      3   Alexander Harris    male               1   \n",
       "1             2      1      Frank Parsons  female               1   \n",
       "2             3      3  Anthony Churchill  female               0   \n",
       "3             4      1   Alexandra Hughes  female               1   \n",
       "4             5      3        Joan Fraser    male               0   \n",
       "\n",
       "   Parents Count     Fare     Embarked  Survived  AgeFill  Family_members  \\\n",
       "0              0   7250.0     New York         0     22.0               1   \n",
       "1              0  71283.3  Los Angeles         1     38.0               1   \n",
       "2              0   7925.0     New York         1     26.0               0   \n",
       "3              0  53100.0     New York         1     35.0               1   \n",
       "4              0   8050.0     New York         0     35.0               0   \n",
       "\n",
       "  Alone/With Family  \n",
       "0       With Family  \n",
       "1       With Family  \n",
       "2             Alone  \n",
       "3       With Family  \n",
       "4             Alone  "
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Alone          537\n",
       "With Family    354\n",
       "Name: Alone/With Family, dtype: int64"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Alone/With Family'].value_counts()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 7) What percentage of passengers survived in each Class:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\welcome\\Anaconda2\\lib\\site-packages\\seaborn\\categorical.py:1508: FutureWarning: remove_na is deprecated and is a private function. Do not use.\n",
      "  stat_data = remove_na(group_data[hue_mask])\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.FacetGrid at 0x14685fd0>"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAVUAAAEYCAYAAADsymWcAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nUQUAg/4/QDZJWxGeF9kAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x14413fd0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.factorplot('Class',  hue='Survived',  data=df, kind='count')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr:last-of-type th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th colspan=\"8\" halign=\"left\">AgeFill</th>\n",
       "      <th colspan=\"2\" halign=\"left\">Family_members</th>\n",
       "      <th>...</th>\n",
       "      <th colspan=\"2\" halign=\"left\">Passenger ID</th>\n",
       "      <th colspan=\"8\" halign=\"left\">Siblings Count</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>...</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Class</th>\n",
       "      <th>Survived</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">1</th>\n",
       "      <th>0</th>\n",
       "      <td>80.0</td>\n",
       "      <td>42.956250</td>\n",
       "      <td>13.729805</td>\n",
       "      <td>2.00</td>\n",
       "      <td>36.75</td>\n",
       "      <td>40.0</td>\n",
       "      <td>51.25</td>\n",
       "      <td>71.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>0.587500</td>\n",
       "      <td>...</td>\n",
       "      <td>608.75</td>\n",
       "      <td>873.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>0.287500</td>\n",
       "      <td>0.555610</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.25</td>\n",
       "      <td>3.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>136.0</td>\n",
       "      <td>35.271471</td>\n",
       "      <td>13.496892</td>\n",
       "      <td>-5.00</td>\n",
       "      <td>25.75</td>\n",
       "      <td>35.0</td>\n",
       "      <td>43.25</td>\n",
       "      <td>80.0</td>\n",
       "      <td>136.0</td>\n",
       "      <td>0.882353</td>\n",
       "      <td>...</td>\n",
       "      <td>693.50</td>\n",
       "      <td>890.0</td>\n",
       "      <td>136.0</td>\n",
       "      <td>0.492647</td>\n",
       "      <td>0.632412</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.00</td>\n",
       "      <td>3.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">2</th>\n",
       "      <th>0</th>\n",
       "      <td>97.0</td>\n",
       "      <td>33.288660</td>\n",
       "      <td>11.736436</td>\n",
       "      <td>16.00</td>\n",
       "      <td>25.00</td>\n",
       "      <td>30.0</td>\n",
       "      <td>38.00</td>\n",
       "      <td>70.0</td>\n",
       "      <td>97.0</td>\n",
       "      <td>0.463918</td>\n",
       "      <td>...</td>\n",
       "      <td>686.00</td>\n",
       "      <td>887.0</td>\n",
       "      <td>97.0</td>\n",
       "      <td>0.319588</td>\n",
       "      <td>0.550500</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.00</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>87.0</td>\n",
       "      <td>25.653218</td>\n",
       "      <td>15.270984</td>\n",
       "      <td>-20.00</td>\n",
       "      <td>18.00</td>\n",
       "      <td>28.0</td>\n",
       "      <td>34.00</td>\n",
       "      <td>62.0</td>\n",
       "      <td>87.0</td>\n",
       "      <td>1.137931</td>\n",
       "      <td>...</td>\n",
       "      <td>612.50</td>\n",
       "      <td>881.0</td>\n",
       "      <td>87.0</td>\n",
       "      <td>0.494253</td>\n",
       "      <td>0.644720</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.00</td>\n",
       "      <td>3.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">3</th>\n",
       "      <th>0</th>\n",
       "      <td>372.0</td>\n",
       "      <td>26.436828</td>\n",
       "      <td>13.896592</td>\n",
       "      <td>1.00</td>\n",
       "      <td>21.00</td>\n",
       "      <td>25.0</td>\n",
       "      <td>30.00</td>\n",
       "      <td>200.0</td>\n",
       "      <td>372.0</td>\n",
       "      <td>1.056452</td>\n",
       "      <td>...</td>\n",
       "      <td>679.50</td>\n",
       "      <td>891.0</td>\n",
       "      <td>372.0</td>\n",
       "      <td>0.672043</td>\n",
       "      <td>1.504700</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.00</td>\n",
       "      <td>8.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>119.0</td>\n",
       "      <td>22.146387</td>\n",
       "      <td>15.571193</td>\n",
       "      <td>0.42</td>\n",
       "      <td>18.00</td>\n",
       "      <td>21.5</td>\n",
       "      <td>26.00</td>\n",
       "      <td>150.0</td>\n",
       "      <td>119.0</td>\n",
       "      <td>0.857143</td>\n",
       "      <td>...</td>\n",
       "      <td>633.50</td>\n",
       "      <td>876.0</td>\n",
       "      <td>119.0</td>\n",
       "      <td>0.436975</td>\n",
       "      <td>0.829934</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.00</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>6 rows × 48 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "               AgeFill                                                   \\\n",
       "                 count       mean        std    min    25%   50%    75%   \n",
       "Class Survived                                                            \n",
       "1     0           80.0  42.956250  13.729805   2.00  36.75  40.0  51.25   \n",
       "      1          136.0  35.271471  13.496892  -5.00  25.75  35.0  43.25   \n",
       "2     0           97.0  33.288660  11.736436  16.00  25.00  30.0  38.00   \n",
       "      1           87.0  25.653218  15.270984 -20.00  18.00  28.0  34.00   \n",
       "3     0          372.0  26.436828  13.896592   1.00  21.00  25.0  30.00   \n",
       "      1          119.0  22.146387  15.571193   0.42  18.00  21.5  26.00   \n",
       "\n",
       "                      Family_members           ...  Passenger ID         \\\n",
       "                  max          count      mean ...           75%    max   \n",
       "Class Survived                                 ...                        \n",
       "1     0          71.0           80.0  0.587500 ...        608.75  873.0   \n",
       "      1          80.0          136.0  0.882353 ...        693.50  890.0   \n",
       "2     0          70.0           97.0  0.463918 ...        686.00  887.0   \n",
       "      1          62.0           87.0  1.137931 ...        612.50  881.0   \n",
       "3     0         200.0          372.0  1.056452 ...        679.50  891.0   \n",
       "      1         150.0          119.0  0.857143 ...        633.50  876.0   \n",
       "\n",
       "               Siblings Count                                                \n",
       "                        count      mean       std  min  25%  50%   75%  max  \n",
       "Class Survived                                                               \n",
       "1     0                  80.0  0.287500  0.555610  0.0  0.0  0.0  0.25  3.0  \n",
       "      1                 136.0  0.492647  0.632412  0.0  0.0  0.0  1.00  3.0  \n",
       "2     0                  97.0  0.319588  0.550500  0.0  0.0  0.0  1.00  2.0  \n",
       "      1                  87.0  0.494253  0.644720  0.0  0.0  0.0  1.00  3.0  \n",
       "3     0                 372.0  0.672043  1.504700  0.0  0.0  0.0  1.00  8.0  \n",
       "      1                 119.0  0.436975  0.829934  0.0  0.0  0.0  1.00  4.0  \n",
       "\n",
       "[6 rows x 48 columns]"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby([df['Class'], df['Survived']]).describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'%Survived:\\n   Class 1: (136/(136+80))*100 = 62.9\\n   Class 2: (87/(87+97))*100 = 47.3\\n   Class 3: (119/(119+372))*100 = 24.2'"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "'''%Survived:\n",
    "   Class 1: (136/(136+80))*100 = 62.9\n",
    "   Class 2: (87/(87+97))*100 = 47.3\n",
    "   Class 3: (119/(119+372))*100 = 24.2'''"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 8) Find the percentage of passengers who survived, based on Gender:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.FacetGrid at 0x1433f550>"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAVUAAAEYCAYAAADsymWcAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nYBBRBQCD/g98CXMH6irtKwAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x1433ff60>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.factorplot('Gender',  hue='Survived',  data=df, kind='count')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr:last-of-type th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th colspan=\"8\" halign=\"left\">AgeFill</th>\n",
       "      <th colspan=\"2\" halign=\"left\">Class</th>\n",
       "      <th>...</th>\n",
       "      <th colspan=\"2\" halign=\"left\">Passenger ID</th>\n",
       "      <th colspan=\"8\" halign=\"left\">Siblings Count</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>...</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Gender</th>\n",
       "      <th>Survived</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">female</th>\n",
       "      <th>0</th>\n",
       "      <td>81.0</td>\n",
       "      <td>24.302469</td>\n",
       "      <td>12.172376</td>\n",
       "      <td>2.0</td>\n",
       "      <td>18.0</td>\n",
       "      <td>21.5</td>\n",
       "      <td>30.0</td>\n",
       "      <td>57.0</td>\n",
       "      <td>81.0</td>\n",
       "      <td>2.851852</td>\n",
       "      <td>...</td>\n",
       "      <td>643.0</td>\n",
       "      <td>889.0</td>\n",
       "      <td>81.0</td>\n",
       "      <td>1.209877</td>\n",
       "      <td>1.814635</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>8.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>233.0</td>\n",
       "      <td>28.143777</td>\n",
       "      <td>13.633884</td>\n",
       "      <td>-20.0</td>\n",
       "      <td>21.5</td>\n",
       "      <td>27.0</td>\n",
       "      <td>35.0</td>\n",
       "      <td>63.0</td>\n",
       "      <td>233.0</td>\n",
       "      <td>1.918455</td>\n",
       "      <td>...</td>\n",
       "      <td>636.0</td>\n",
       "      <td>888.0</td>\n",
       "      <td>233.0</td>\n",
       "      <td>0.515021</td>\n",
       "      <td>0.737533</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">male</th>\n",
       "      <th>0</th>\n",
       "      <td>468.0</td>\n",
       "      <td>31.050214</td>\n",
       "      <td>14.920458</td>\n",
       "      <td>1.0</td>\n",
       "      <td>24.0</td>\n",
       "      <td>26.0</td>\n",
       "      <td>38.0</td>\n",
       "      <td>200.0</td>\n",
       "      <td>468.0</td>\n",
       "      <td>2.476496</td>\n",
       "      <td>...</td>\n",
       "      <td>678.5</td>\n",
       "      <td>891.0</td>\n",
       "      <td>468.0</td>\n",
       "      <td>0.440171</td>\n",
       "      <td>1.138507</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>8.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>109.0</td>\n",
       "      <td>28.501560</td>\n",
       "      <td>19.684763</td>\n",
       "      <td>-5.0</td>\n",
       "      <td>20.0</td>\n",
       "      <td>27.0</td>\n",
       "      <td>37.0</td>\n",
       "      <td>150.0</td>\n",
       "      <td>109.0</td>\n",
       "      <td>2.018349</td>\n",
       "      <td>...</td>\n",
       "      <td>680.0</td>\n",
       "      <td>890.0</td>\n",
       "      <td>109.0</td>\n",
       "      <td>0.385321</td>\n",
       "      <td>0.636952</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4 rows × 56 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                AgeFill                                                       \\\n",
       "                  count       mean        std   min   25%   50%   75%    max   \n",
       "Gender Survived                                                                \n",
       "female 0           81.0  24.302469  12.172376   2.0  18.0  21.5  30.0   57.0   \n",
       "       1          233.0  28.143777  13.633884 -20.0  21.5  27.0  35.0   63.0   \n",
       "male   0          468.0  31.050214  14.920458   1.0  24.0  26.0  38.0  200.0   \n",
       "       1          109.0  28.501560  19.684763  -5.0  20.0  27.0  37.0  150.0   \n",
       "\n",
       "                 Class           ...  Passenger ID        Siblings Count  \\\n",
       "                 count      mean ...           75%    max          count   \n",
       "Gender Survived                  ...                                       \n",
       "female 0          81.0  2.851852 ...         643.0  889.0           81.0   \n",
       "       1         233.0  1.918455 ...         636.0  888.0          233.0   \n",
       "male   0         468.0  2.476496 ...         678.5  891.0          468.0   \n",
       "       1         109.0  2.018349 ...         680.0  890.0          109.0   \n",
       "\n",
       "                                                              \n",
       "                     mean       std  min  25%  50%  75%  max  \n",
       "Gender Survived                                               \n",
       "female 0         1.209877  1.814635  0.0  0.0  1.0  1.0  8.0  \n",
       "       1         0.515021  0.737533  0.0  0.0  0.0  1.0  4.0  \n",
       "male   0         0.440171  1.138507  0.0  0.0  0.0  0.0  8.0  \n",
       "       1         0.385321  0.636952  0.0  0.0  0.0  1.0  4.0  \n",
       "\n",
       "[4 rows x 56 columns]"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby([df['Gender'], df['Survived']]).describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'%Survived:\\n   Male: (109/(109+468))*100= 18.9\\n   Female: (233/(233+81))*100= 74.2'"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "'''%Survived:\n",
    "   Male: (109/(109+468))*100= 18.9\n",
    "   Female: (233/(233+81))*100= 74.2'''"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 9) Did having a family member increased the chances of survival:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.FacetGrid at 0x146c7b38>"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAVUAAAEYCAYAAADsymWcAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x17787198>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.factorplot('Alone/With Family',  hue='Survived',  data=df, kind='count')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr:last-of-type th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th colspan=\"8\" halign=\"left\">AgeFill</th>\n",
       "      <th colspan=\"2\" halign=\"left\">Class</th>\n",
       "      <th>...</th>\n",
       "      <th colspan=\"2\" halign=\"left\">Passenger ID</th>\n",
       "      <th colspan=\"8\" halign=\"left\">Siblings Count</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>...</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Alone/With Family</th>\n",
       "      <th>Survived</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">Alone</th>\n",
       "      <th>0</th>\n",
       "      <td>374.0</td>\n",
       "      <td>31.110963</td>\n",
       "      <td>11.975080</td>\n",
       "      <td>11.0</td>\n",
       "      <td>24.0</td>\n",
       "      <td>25.5</td>\n",
       "      <td>38.00</td>\n",
       "      <td>74.0</td>\n",
       "      <td>374.0</td>\n",
       "      <td>2.545455</td>\n",
       "      <td>...</td>\n",
       "      <td>694.75</td>\n",
       "      <td>891.0</td>\n",
       "      <td>374.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>163.0</td>\n",
       "      <td>31.291411</td>\n",
       "      <td>14.932029</td>\n",
       "      <td>-5.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>29.0</td>\n",
       "      <td>36.00</td>\n",
       "      <td>150.0</td>\n",
       "      <td>163.0</td>\n",
       "      <td>2.067485</td>\n",
       "      <td>...</td>\n",
       "      <td>646.00</td>\n",
       "      <td>890.0</td>\n",
       "      <td>163.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">With Family</th>\n",
       "      <th>0</th>\n",
       "      <td>175.0</td>\n",
       "      <td>27.797143</td>\n",
       "      <td>19.202872</td>\n",
       "      <td>1.0</td>\n",
       "      <td>18.0</td>\n",
       "      <td>25.0</td>\n",
       "      <td>36.25</td>\n",
       "      <td>200.0</td>\n",
       "      <td>175.0</td>\n",
       "      <td>2.502857</td>\n",
       "      <td>...</td>\n",
       "      <td>638.50</td>\n",
       "      <td>889.0</td>\n",
       "      <td>175.0</td>\n",
       "      <td>1.737143</td>\n",
       "      <td>1.777750</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>8.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>179.0</td>\n",
       "      <td>25.495363</td>\n",
       "      <td>16.075105</td>\n",
       "      <td>-20.0</td>\n",
       "      <td>15.5</td>\n",
       "      <td>24.0</td>\n",
       "      <td>36.00</td>\n",
       "      <td>63.0</td>\n",
       "      <td>179.0</td>\n",
       "      <td>1.843575</td>\n",
       "      <td>...</td>\n",
       "      <td>663.00</td>\n",
       "      <td>881.0</td>\n",
       "      <td>179.0</td>\n",
       "      <td>0.905028</td>\n",
       "      <td>0.754706</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4 rows × 56 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                           AgeFill                                          \\\n",
       "                             count       mean        std   min   25%   50%   \n",
       "Alone/With Family Survived                                                   \n",
       "Alone             0          374.0  31.110963  11.975080  11.0  24.0  25.5   \n",
       "                  1          163.0  31.291411  14.932029  -5.0  22.0  29.0   \n",
       "With Family       0          175.0  27.797143  19.202872   1.0  18.0  25.0   \n",
       "                  1          179.0  25.495363  16.075105 -20.0  15.5  24.0   \n",
       "\n",
       "                                          Class           ...  Passenger ID  \\\n",
       "                              75%    max  count      mean ...           75%   \n",
       "Alone/With Family Survived                                ...                 \n",
       "Alone             0         38.00   74.0  374.0  2.545455 ...        694.75   \n",
       "                  1         36.00  150.0  163.0  2.067485 ...        646.00   \n",
       "With Family       0         36.25  200.0  175.0  2.502857 ...        638.50   \n",
       "                  1         36.00   63.0  179.0  1.843575 ...        663.00   \n",
       "\n",
       "                                  Siblings Count                           \\\n",
       "                              max          count      mean       std  min   \n",
       "Alone/With Family Survived                                                  \n",
       "Alone             0         891.0          374.0  0.000000  0.000000  0.0   \n",
       "                  1         890.0          163.0  0.000000  0.000000  0.0   \n",
       "With Family       0         889.0          175.0  1.737143  1.777750  0.0   \n",
       "                  1         881.0          179.0  0.905028  0.754706  0.0   \n",
       "\n",
       "                                                \n",
       "                            25%  50%  75%  max  \n",
       "Alone/With Family Survived                      \n",
       "Alone             0         0.0  0.0  0.0  0.0  \n",
       "                  1         0.0  0.0  0.0  0.0  \n",
       "With Family       0         1.0  1.0  2.0  8.0  \n",
       "                  1         0.0  1.0  1.0  4.0  \n",
       "\n",
       "[4 rows x 56 columns]"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby([df['Alone/With Family'], df['Survived']]).describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'% Survived:\\n    Alone: (163/(163+374))*100 = 30.4\\n    With Family: (179/(179+175)) = 50.6'"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "'''% Survived:\n",
    "    Alone: (163/(163+374))*100 = 30.4\n",
    "    With Family: (179/(179+175)) = 50.6'''"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Yes, from the above analysis, we can say that having a family member increased the chances of survival '"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "'''Yes, from the above analysis, we can say that having a family member increased the chances of survival '''"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 1) Count the number of passengers on the ship based on Gender:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "male      577\n",
       "female    314\n",
       "Name: Gender, dtype: int64"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Gender'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.FacetGrid at 0x177ae080>"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAASUAAAEYCAYAAAAag+AEAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x17868fd0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.factorplot( 'Gender',  data=df, kind='count')\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 2) Count the number of passengers on the ship based on Class:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "3    491\n",
       "1    216\n",
       "2    184\n",
       "Name: Class, dtype: int64"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Class'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.FacetGrid at 0x178f2f98>"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAASUAAAEYCAYAAAAag+AEAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMS4wLCBo\ndHRwOi8vbWF0cGxvdGxpYi5vcmcvpW3flQAAEs5JREFUeJzt3X9s1PXhx/HX5+4A8Xq1NsgfF2gt\n/qxORtpb+weljsxZEmOYSbUFAjPgZphWq5MVOlrkO0ZbO7vFEsRhjAoasIKOLFk224G1VVt3GaCl\nOLegIO02tTB6J1J6n8/3D2M3BrIT+uHzPvt8/MV9yl1ebdpnPvejV8txHEcAYAif1wMA4D8RJQBG\nIUoAjEKUABiFKAEwivFRikajXk8AcAEZHyUAYwtRAmAUogTAKEQJgFECbt3w9773PYVCIUnSlClT\nVFZWpp///Ofy+/0qKirSvffeK9u29fDDD+vdd9/V+PHjtWbNGmVnZ7s1CUAKcCVKJ06ckCRt2rRp\n5NjcuXPV3NysqVOn6oc//KF6enp0+PBhDQ0NaevWrdq9e7fq6+v1+OOPuzEJQIpwJUr79+/X8ePH\ntXjxYg0PD6uiokJDQ0PKysqSJBUVFemNN97QRx99pFmzZkmSZsyYoXfeeceNOQBSiCtRuuiii7Rk\nyRLdfvvtev/99/WDH/xA6enpIx8PBoM6dOiQYrGY0tLSRo77/X4NDw8rEDh1Vm9vrxszAXgoNzf3\njMddiVJOTo6ys7NlWZZycnIUCoV09OjRkY/H43Glp6frs88+UzweHzlu2/ZpQZK+fDyArx9Xnn17\n8cUXVV9fL0n6xz/+oePHj+viiy/WwYMH5TiOOjo6FIlElJeXp/b2dknS7t27dfXVV7sxB0AKceVM\nqbS0VCtWrNC8efNkWZbWrl0rn8+nhx56SIlEQkVFRfrmN7+pG264QZ2dnSovL5fjOFq7dq0bcwCk\nEMv0d56MRqPKz8/3egaQtJnNM72e4LnOis5zvi4vngRgFKIEwChECYBRiBIAoxAlAEYhSgCMQpQA\nGIUoATAKUQJgFKIEwChECYBRiBIAoxAlAEYhSgCMQpQAGIUoATAKUQJgFKIEwChECYBRiBIAoxAl\nAEYhSgCMQpQAGIUoATAKUQJgFKIEwChECYBRiBIAoxAlAEYhSgCMQpQAGIUoATAKUQJgFKIEwChE\nCYBRiBIAoxAlAEYhSgCMQpQAGMW1KH3yySe68cYb9be//U0ffPCB5s2bp/nz52vVqlWybVuStG7d\nOpWWlqq8vFx79+51awqAFOJKlE6ePKna2lpddNFFkqS6ujpVVlbq+eefl+M4amtrU09Pj7q7u9XS\n0qKmpiatXr3ajSkAUkzAjRttaGhQeXm5fv3rX0uSenp6VFBQIEkqLi5WZ2encnJyVFRUJMuyFA6H\nlUgkNDAwoMzMzNNur7e3142ZAFySzM9sbm7uGY+PepS2b9+uzMxMzZo1ayRKjuPIsixJUjAY1ODg\noGKxmDIyMkau98XxM0Xpy8YDRmr1eoD3zudndtSjtG3bNlmWpTfeeEO9vb2qqqrSwMDAyMfj8bjS\n09OVlpameDx+yvFQKDTacwCkmFF/TOm5557T5s2btWnTJuXm5qqhoUHFxcXq6uqSJLW3tysSiSgv\nL08dHR2ybVt9fX2ybfuMZ0kAxhZXHlP6b1VVVaqpqVFTU5OmTZumkpIS+f1+RSIRlZWVybZt1dbW\nXogpAAxnOY7jeD3ibKLRqPLz872eASRtZvNMryd4rrOi85yvy4snARiFKAEwClECYBSiBMAoRAmA\nUYgSAKMQJQBGIUoAjEKUABiFKAEwClECYBSiBMAoRAmAUYgSAKMQJQBGIUoAjEKUABiFKAEwClEC\nYBSiBMAoRAmAUYgSAKMQJQBGIUoAjEKUABiFKAEwClECYBSiBMAoRAmAUYgSAKMQJQBGIUoAjEKU\nABiFKAEwClECYBSiBMAoRAmAUYgSAKME3LjRRCKhlStX6sCBA/L7/aqrq5PjOFq+fLksy9JVV12l\nVatWyefzad26ddq1a5cCgYCqq6s1ffp0NyYBSBGuRGnnzp2SpC1btqirq2skSpWVlSosLFRtba3a\n2toUDofV3d2tlpYW9ff3q6KiQtu2bXNjEoAU4UqUbrrpJn3729+WJPX19WnSpEnatWuXCgoKJEnF\nxcXq7OxUTk6OioqKZFmWwuGwEomEBgYGlJmZ6cYsACnAlShJUiAQUFVVlV555RU99thj2rlzpyzL\nkiQFg0ENDg4qFospIyNj5DpfHP/vKPX29ro1E4ALkvmZzc3NPeNx16IkSQ0NDXrooYd0xx136MSJ\nEyPH4/G40tPTlZaWpng8fsrxUCh02u182XjASK1eD/De+fzMuvLs28svv6wnnnhCkjRx4kRZlqVv\nfOMb6urqkiS1t7crEokoLy9PHR0dsm1bfX19sm2bu27AGOfKmdLNN9+sFStWaMGCBRoeHlZ1dbWu\nuOIK1dTUqKmpSdOmTVNJSYn8fr8ikYjKyspk27Zqa2vdmAMghViO4zhejzibaDSq/Px8r2cASZvZ\nPNPrCZ7rrOg85+vy4kkARiFKAIxClAAYhSgBMApRAmCUpKLU0tJyyuVnn33WlTEAcNbXKf32t7/V\nH//4R3V1denNN9+U9Pk7ALz33ntatGjRBRkIYGw5a5RmzZqlyy67TEePHlVZWZkkyefzaerUqRdk\nHICx56xRuuSSS1RYWKjCwkJ98sknI7+/lkgkLsg4AGNPUr9msnr1ar366quaPHmyHMeRZVnasmWL\n29sAjEFJRWnPnj1qbW2Vz8eTdQDclVRlsrOzT3nrEQBwS1JnSv39/Zo9e7ays7MlibtvAFyTVJQe\nffRRt3cAgKQko/TSSy+dduzee+8d9TEAkFSUJk2aJElyHEf79u2TbduujgIwdiUVpfLy8lMu33XX\nXa6MAYCkonTgwIGRf3/00Ufq7+93bRCAsS2pKP3ne2dPmDBBP/nJT1wbBGBsSypKmzZt0pEjR3To\n0CFNmTKFvzgCwDVJvXjyd7/7ncrLy7VhwwaVlZXpN7/5jdu7AIxRSZ0pPf3009q+fbuCwaBisZi+\n//3va+7cuW5vAzAGJXWmZFmWgsGgJCktLU0TJkxwdRSAsSupM6WsrCzV19crEokoGo0qKyvL7V0A\nxqikzpTuuOMOXXLJJXr99de1fft2LViwwO1dAMaopKJUX1+v7373u6qtrdWLL76o+vp6t3cBGKOS\nilIgENCVV14pSZo6dSrvqwTANUk9phQOh9XU1KQZM2Zo7969mjx5stu7AIxRSZ3y1NXVKTMzU6++\n+qoyMzNVV1fn9i4AY1RSZ0oTJkzQnXfe6fIUAOAv5AIwDFECYBSiBMAoRAmAUZJ6oNt0+cue9XqC\n56KNi7yeAIwKzpQAGIUoATAKUQJgFKIEwCij/kD3yZMnVV1drcOHD2toaEhLly7VlVdeqeXLl8uy\nLF111VVatWqVfD6f1q1bp127dikQCKi6ulrTp08f7TkAUsyoR2nHjh3KyMhQY2Ojjhw5ottuu03X\nXnutKisrVVhYqNraWrW1tSkcDqu7u1stLS3q7+9XRUWFtm3bNtpzAKSYUY/SnDlzVFJSMnLZ7/er\np6dHBQUFkqTi4mJ1dnYqJydHRUVFsixL4XBYiURCAwMD/KUUYIwb9Sh98V7esVhM9913nyorK9XQ\n0CDLskY+Pjg4qFgspoyMjFOuNzg4eMYo9fb2jvbMrx2+RjBJMt+Pubm5Zzzuyosn+/v7dc8992j+\n/Pm69dZb1djYOPKxeDyu9PR0paWlKR6Pn3I8FAqd8fa+bPy/vTUas1Pa//4a4YJp9XqA987n+3HU\nn337+OOPtXjxYi1btkylpaWSpOuuu05dXV2SpPb2dkUiEeXl5amjo0O2bauvr0+2bXPXDcDonylt\n2LBBx44d0/r167V+/XpJ0k9/+lOtWbNGTU1NmjZtmkpKSuT3+xWJRFRWVibbtk/50+AAxi7LcRzH\n6xFnE41GlZ+ff9b/w+++8btvJpnZPNPrCZ7rrOg85+vy4kkARiFKAIzytXjrEoyOg/93g9cTPJdV\n+7bXE8Y8zpQAGIUoATAKUQJgFKIEwChECYBRiBIAoxAlAEYhSgCMQpQAGIUoATAKUQJgFKIEwChE\nCYBRiBIAoxAlAEYhSgCMQpQAGIUoATAKUQJgFKIEwChECYBRiBIAoxAlAEYhSgCMQpQAGIUoATAK\nUQJgFKIEwChECYBRiBIAoxAlAEYhSgCMQpQAGIUoATAKUQJgFKIEwCiuRWnPnj1auHChJOmDDz7Q\nvHnzNH/+fK1atUq2bUuS1q1bp9LSUpWXl2vv3r1uTQGQQlyJ0saNG7Vy5UqdOHFCklRXV6fKyko9\n//zzchxHbW1t6unpUXd3t1paWtTU1KTVq1e7MQVAinElSllZWWpubh653NPTo4KCAklScXGxXn/9\ndUWjURUVFcmyLIXDYSUSCQ0MDLgxB0AKCbhxoyUlJfrwww9HLjuOI8uyJEnBYFCDg4OKxWLKyMgY\n+T9fHM/MzDzt9np7e92Y+bUyGl+j4CjsSHV8r42OZL6Oubm5ZzzuSpT+m8/37xOyeDyu9PR0paWl\nKR6Pn3I8FAqd8fpfNv7f3hqNmSntf3+N/reDo7Aj1Y3G11Gt538Tqe58vo4X5Nm36667Tl1dXZKk\n9vZ2RSIR5eXlqaOjQ7Ztq6+vT7Ztn/EsCcDYckHOlKqqqlRTU6OmpiZNmzZNJSUl8vv9ikQiKisr\nk23bqq2tvRBTABjOtShNmTJFL7zwgiQpJydHmzdvPu3/VFRUqKKiwq0JAFIQL54EYBSiBMAoRAmA\nUYgSAKMQJQBGIUoAjEKUABiFKAEwClECYBSiBMAoRAmAUYgSAKMQJQBGIUoAjEKUABiFKAEwClEC\nYBSiBMAoRAmAUYgSAKMQJQBGIUoAjEKUABiFKAEwClECYBSiBMAoRAmAUYgSAKMQJQBGIUoAjEKU\nABiFKAEwClECYBSiBMAoRAmAUYgSAKMQJQBGIUoAjEKUABgl4PUA27b18MMP691339X48eO1Zs0a\nZWdnez0LgEc8P1NqbW3V0NCQtm7dqh//+Meqr6/3ehIAD1mO4zheDqirq9P06dN1yy23SJJmzZql\n1157beTj0WjUq2kAXJafn3/aMc/vvsViMaWlpY1c9vv9Gh4eViDw+bQzjQbw9eX53be0tDTF4/GR\ny7ZtjwQJwNjjeZTy8vLU3t4uSdq9e7euvvpqjxcB8JLnjyl98ezbX/7yFzmOo7Vr1+qKK67wchIA\nD3kepa+DPXv26Be/+IU2bdrk9ZSUdPLkSVVXV+vw4cMaGhrS0qVL9Z3vfMfrWSknkUho5cqVOnDg\ngPx+v+rq6pSVleX1rK+MB2/O08aNG7Vjxw5NnDjR6ykpa8eOHcrIyFBjY6OOHDmi2267jSidg507\nd0qStmzZoq6uLtXV1enxxx/3eNVX5/ljSqkuKytLzc3NXs9IaXPmzNH9998/ctnv93u4JnXddNNN\n+tnPfiZJ6uvr06RJkzxedG44UzpPJSUl+vDDD72ekdKCwaCkz18ect9996mystLjRakrEAioqqpK\nr7zyih577DGv55wTzpRghP7+fi1atEhz587Vrbfe6vWclNbQ0KDf//73qqmp0aeffur1nK+MKMFz\nH3/8sRYvXqxly5aptLTU6zkp6+WXX9YTTzwhSZo4caIsy0rJu8JECZ7bsGGDjh07pvXr12vhwoVa\nuHChPvvsM69npZybb75Z+/bt04IFC7RkyRJVV1drwoQJXs/6ynhJAACjcKYEwChECYBRiBIAoxAl\nAEYhSgCMwiu64ar33ntPjY2NOn78uD799FPdeOONKigo0NatW/XLX/7S63kwEFGCa44dO6YHH3xQ\nzc3Nuvzyy5VIJHT//ffrsssu83oaDEaU4Jq2tjYVFhbq8ssvl/T5L9o2NDToz3/+s7q7uyVJmzdv\n1h/+8AcNDw8rFAqpublZhw8f1ooVKxQIBOT3+/XII49o3LhxqqyslOM4OnnypFavXq1rrrnGw88O\nbiFKcM0///lPTZ069ZRjwWBQ48aNk/T5G/wdPXpUTz/9tHw+n5YsWaK3335b+/fv1/XXX6/ly5fr\nT3/6k/71r3+pr69PoVBIjz76qP76178qFot58SnhAiBKcE04HNa+fftOOXbo0CG99dZbkiSfz6dx\n48bpwQcf1MUXX6y///3vGh4eVmlpqTZu3Ki77rpLoVBIDzzwgIqLi/X+++/rRz/6kQKBgJYuXerF\np4QLgGff4JrZs2frtdde08GDByV9/g6T9fX1uvTSSyVJ+/fvV2trq371q1+ppqZGtm3LcRy1tbUp\nPz9fzzzzjObMmaMnn3xSXV1dmjx5sp566iktXbpUTU1NXn5qcBG/+wZXvfPOO3rkkUfkOI7i8bhm\nz56tb33rW9q6davWrl2ru+++W7FYTOPHj9f48eNVWlqqGTNmaNmyZfL7/fL5fFqxYoXC4bAeeOAB\nHT9+XD6fT/fcc4+Kioq8/vTgAqIEwCjcfQNgFKIEwChECYBRiBIAoxAlAEYhSgCMQpQAGOX/AWZk\nHCVMHxW/AAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x177a4eb8>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.factorplot( 'Class',  data=df, kind='count')\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 3) Count the number of passengers on the ship who are children (Age less than 16 years):"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Passenger ID</th>\n",
       "      <th>Class</th>\n",
       "      <th>Name</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Siblings Count</th>\n",
       "      <th>Parents Count</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>Survived</th>\n",
       "      <th>AgeFill</th>\n",
       "      <th>Family_members</th>\n",
       "      <th>Alone/With Family</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Alexander Harris</td>\n",
       "      <td>male</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7250.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>With Family</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>Frank Parsons</td>\n",
       "      <td>female</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71283.3</td>\n",
       "      <td>Los Angeles</td>\n",
       "      <td>1</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>With Family</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>Anthony Churchill</td>\n",
       "      <td>female</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7925.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>1</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>Alone</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>Alexandra Hughes</td>\n",
       "      <td>female</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53100.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>1</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>With Family</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>3</td>\n",
       "      <td>Joan Fraser</td>\n",
       "      <td>male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8050.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>0</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>Alone</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Passenger ID  Class               Name  Gender  Siblings Count  \\\n",
       "0             1      3   Alexander Harris    male               1   \n",
       "1             2      1      Frank Parsons  female               1   \n",
       "2             3      3  Anthony Churchill  female               0   \n",
       "3             4      1   Alexandra Hughes  female               1   \n",
       "4             5      3        Joan Fraser    male               0   \n",
       "\n",
       "   Parents Count     Fare     Embarked  Survived  AgeFill  Family_members  \\\n",
       "0              0   7250.0     New York         0     22.0               1   \n",
       "1              0  71283.3  Los Angeles         1     38.0               1   \n",
       "2              0   7925.0     New York         1     26.0               0   \n",
       "3              0  53100.0     New York         1     35.0               1   \n",
       "4              0   8050.0     New York         0     35.0               0   \n",
       "\n",
       "  Alone/With Family  \n",
       "0       With Family  \n",
       "1       With Family  \n",
       "2             Alone  \n",
       "3       With Family  \n",
       "4             Alone  "
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Passenger ID</th>\n",
       "      <th>Class</th>\n",
       "      <th>Name</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Siblings Count</th>\n",
       "      <th>Parents Count</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>Survived</th>\n",
       "      <th>AgeFill</th>\n",
       "      <th>Family_members</th>\n",
       "      <th>Alone/With Family</th>\n",
       "      <th>Person</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Alexander Harris</td>\n",
       "      <td>male</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7250.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>With Family</td>\n",
       "      <td>male</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>Frank Parsons</td>\n",
       "      <td>female</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71283.3</td>\n",
       "      <td>Los Angeles</td>\n",
       "      <td>1</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>With Family</td>\n",
       "      <td>female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>Anthony Churchill</td>\n",
       "      <td>female</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7925.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>1</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>Alone</td>\n",
       "      <td>female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>Alexandra Hughes</td>\n",
       "      <td>female</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53100.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>1</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>With Family</td>\n",
       "      <td>female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>3</td>\n",
       "      <td>Joan Fraser</td>\n",
       "      <td>male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8050.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>0</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>Alone</td>\n",
       "      <td>male</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Passenger ID  Class               Name  Gender  Siblings Count  \\\n",
       "0             1      3   Alexander Harris    male               1   \n",
       "1             2      1      Frank Parsons  female               1   \n",
       "2             3      3  Anthony Churchill  female               0   \n",
       "3             4      1   Alexandra Hughes  female               1   \n",
       "4             5      3        Joan Fraser    male               0   \n",
       "\n",
       "   Parents Count     Fare     Embarked  Survived  AgeFill  Family_members  \\\n",
       "0              0   7250.0     New York         0     22.0               1   \n",
       "1              0  71283.3  Los Angeles         1     38.0               1   \n",
       "2              0   7925.0     New York         1     26.0               0   \n",
       "3              0  53100.0     New York         1     35.0               1   \n",
       "4              0   8050.0     New York         0     35.0               0   \n",
       "\n",
       "  Alone/With Family  Person  \n",
       "0       With Family    male  \n",
       "1       With Family  female  \n",
       "2             Alone  female  \n",
       "3       With Family  female  \n",
       "4             Alone    male  "
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Person'] = df['Gender']\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [],
   "source": [
    "df['Person'].loc[df['AgeFill'] <16] = 'Child'\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Passenger ID</th>\n",
       "      <th>Class</th>\n",
       "      <th>Name</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Siblings Count</th>\n",
       "      <th>Parents Count</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>Survived</th>\n",
       "      <th>AgeFill</th>\n",
       "      <th>Family_members</th>\n",
       "      <th>Alone/With Family</th>\n",
       "      <th>Person</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Alexander Harris</td>\n",
       "      <td>male</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7250.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>With Family</td>\n",
       "      <td>male</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>Frank Parsons</td>\n",
       "      <td>female</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71283.3</td>\n",
       "      <td>Los Angeles</td>\n",
       "      <td>1</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>With Family</td>\n",
       "      <td>female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>Anthony Churchill</td>\n",
       "      <td>female</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7925.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>1</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>Alone</td>\n",
       "      <td>female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>Alexandra Hughes</td>\n",
       "      <td>female</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53100.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>1</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>With Family</td>\n",
       "      <td>female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>3</td>\n",
       "      <td>Joan Fraser</td>\n",
       "      <td>male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8050.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>0</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>Alone</td>\n",
       "      <td>male</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>6</td>\n",
       "      <td>3</td>\n",
       "      <td>Megan Clarkson</td>\n",
       "      <td>male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8458.3</td>\n",
       "      <td>Chicago</td>\n",
       "      <td>0</td>\n",
       "      <td>25.0</td>\n",
       "      <td>0</td>\n",
       "      <td>Alone</td>\n",
       "      <td>male</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>7</td>\n",
       "      <td>1</td>\n",
       "      <td>Molly Bower</td>\n",
       "      <td>male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>51862.5</td>\n",
       "      <td>New York</td>\n",
       "      <td>0</td>\n",
       "      <td>54.0</td>\n",
       "      <td>0</td>\n",
       "      <td>Alone</td>\n",
       "      <td>male</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>8</td>\n",
       "      <td>3</td>\n",
       "      <td>Steven Jones</td>\n",
       "      <td>male</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>21075.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>4</td>\n",
       "      <td>With Family</td>\n",
       "      <td>Child</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>9</td>\n",
       "      <td>3</td>\n",
       "      <td>Bernadette Vance</td>\n",
       "      <td>female</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>11133.3</td>\n",
       "      <td>New York</td>\n",
       "      <td>1</td>\n",
       "      <td>27.0</td>\n",
       "      <td>2</td>\n",
       "      <td>With Family</td>\n",
       "      <td>female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>Irene Chapman</td>\n",
       "      <td>female</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>30070.8</td>\n",
       "      <td>Los Angeles</td>\n",
       "      <td>1</td>\n",
       "      <td>-20.0</td>\n",
       "      <td>1</td>\n",
       "      <td>With Family</td>\n",
       "      <td>Child</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Passenger ID  Class               Name  Gender  Siblings Count  \\\n",
       "0             1      3   Alexander Harris    male               1   \n",
       "1             2      1      Frank Parsons  female               1   \n",
       "2             3      3  Anthony Churchill  female               0   \n",
       "3             4      1   Alexandra Hughes  female               1   \n",
       "4             5      3        Joan Fraser    male               0   \n",
       "5             6      3     Megan Clarkson    male               0   \n",
       "6             7      1        Molly Bower    male               0   \n",
       "7             8      3       Steven Jones    male               3   \n",
       "8             9      3   Bernadette Vance  female               0   \n",
       "9            10      2      Irene Chapman  female               1   \n",
       "\n",
       "   Parents Count     Fare     Embarked  Survived  AgeFill  Family_members  \\\n",
       "0              0   7250.0     New York         0     22.0               1   \n",
       "1              0  71283.3  Los Angeles         1     38.0               1   \n",
       "2              0   7925.0     New York         1     26.0               0   \n",
       "3              0  53100.0     New York         1     35.0               1   \n",
       "4              0   8050.0     New York         0     35.0               0   \n",
       "5              0   8458.3      Chicago         0     25.0               0   \n",
       "6              0  51862.5     New York         0     54.0               0   \n",
       "7              1  21075.0     New York         0      2.0               4   \n",
       "8              2  11133.3     New York         1     27.0               2   \n",
       "9              0  30070.8  Los Angeles         1    -20.0               1   \n",
       "\n",
       "  Alone/With Family  Person  \n",
       "0       With Family    male  \n",
       "1       With Family  female  \n",
       "2             Alone  female  \n",
       "3       With Family  female  \n",
       "4             Alone    male  \n",
       "5             Alone    male  \n",
       "6             Alone    male  \n",
       "7       With Family   Child  \n",
       "8       With Family  female  \n",
       "9       With Family   Child  "
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "male      536\n",
      "female    271\n",
      "Child      84\n",
      "Name: Person, dtype: int64\n",
      "('number of childrens are:', 84)\n"
     ]
    }
   ],
   "source": [
    "#number of childrens\n",
    "counts = df['Person'].value_counts()\n",
    "print counts\n",
    "print (\"number of childrens are:\", counts['Child'])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.FacetGrid at 0x145a4860>"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAASUAAAEYCAYAAAAag+AEAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMS4wLCBo\ndHRwOi8vbWF0cGxvdGxpYi5vcmcvpW3flQAAFgBJREFUeJzt3XtwVPXdx/HPyYZrrk2B2h0JJoAS\nR6hN0kBLiDDVximDVAdIggUpWHuR2BSRyCUBCuQy0e1UGEpbp0PFohBJb1rbSgqmRAl0p4gNkYtF\noISbgCVZMZfd8/zBsJrHAFF3s78l79df7Nk9x+85MO85u3vOatm2bQsADBER6gEA4KOIEgCjECUA\nRiFKAIxClAAYxfgoud3uUI8AoBsZHyUAPQtRAmAUogTAKEQJgFGIEgCjECUARiFKAIxClAAYhSgB\nMApRAmAUogTAKJGhHiAQ0h57JtQjhJy7YmaoRwACgjMlAEYhSgCMQpQAGIUoATAKUQJgFKIEwChE\nCYBRiBIAoxAlAEYhSgCMQpQAGIUoATBK0G7I/da3vqWYmBhJ0o033qicnBytWrVKDodDmZmZmjt3\nrnw+n5YtW6b9+/erd+/eWrlypYYMGRKskQCEgaBEqaWlRZK0YcMG/7LJkydr9erVGjx4sB566CHV\n19fr+PHjam1t1aZNm7Rnzx6VlZXp5z//eTBGAhAmghKlt956SxcvXtTs2bPV3t6u/Px8tba2KjEx\nUZKUmZmp119/XWfOnNG4ceMkSbfffrv+/e9/d7q9hoaGYIx5XeEYIdykpKR0ujwoUerbt6/mzJmj\nqVOn6p133tF3v/tdxcbG+p+PiorSsWPH1NzcrOjoaP9yh8Oh9vZ2RUZ2HOtKw39odyDHD0vXPkZA\neAhKlJKSkjRkyBBZlqWkpCTFxMTovffe8z/v8XgUGxurDz74QB6Px7/c5/N9LEgAepagfPv2wgsv\nqKysTJJ06tQpXbx4Uf3799fRo0dl27Z27Nih9PR0paamqqamRpK0Z88e3XzzzcEYB0AYCcppyZQp\nU7Rw4ULl5eXJsiyVlJQoIiJC8+fPl9frVWZmpr70pS9p5MiRqq2tVW5urmzbVklJSTDGARBGLNu2\n7VAPcTVut1tpaWlXfQ2/0c1vdOP6wcWTAIxClAAYhSgBMApRAmAUogTAKEQJgFGIEgCjECUARiFK\nAIxClAAYhSgBMApRAmAUogTAKEQJgFGIEgCjECUARiFKAIxClAAYhSgBMApRAmAUogTAKEQJgFGI\nEgCjECUARiFKAIxClAAYhSgBMApRAmAUogTAKEQJgFGIEgCjECUARiFKAIxClAAYJWhROnv2rO64\n4w69/fbbOnLkiPLy8jR9+nQtXbpUPp9PkrRmzRpNmTJFubm52rt3b7BGARBGghKltrY2FRcXq2/f\nvpKk0tJSFRQUaOPGjbJtW9XV1aqvr9euXbtUWVkpl8ul5cuXB2MUAGEmKFEqLy9Xbm6uBg0aJEmq\nr69XRkaGJCkrK0uvvfaa3G63MjMzZVmWnE6nvF6vzp07F4xxAISRyEBvsKqqSgkJCRo3bpx++ctf\nSpJs25ZlWZKkqKgoNTU1qbm5WfHx8f71Li9PSEj42DYbGhoCPeZ1h2OEcJOSktLp8oBHacuWLbIs\nS6+//roaGhpUWFjY4QzI4/EoNjZW0dHR8ng8HZbHxMR0us0rDf+h3YEYPaxd+xgB4SHgb99++9vf\n6tlnn9WGDRuUkpKi8vJyZWVlqa6uTpJUU1Oj9PR0paamaseOHfL5fGpsbJTP5+v0LAlAzxLwM6XO\nFBYWqqioSC6XS8nJycrOzpbD4VB6erpycnLk8/lUXFzcHaMAMJxl27Yd6iGuxu12Ky0t7aqvSXvs\nmW6axlzuipmhHgEICC6eBGAUogTAKEQJgFGIEgCjECUARiFKAIxClAAYhSgBMApRAmAUogTAKEQJ\ngFGIEgCjECUARiFKAIxClAAYhSgBMApRAmAUogTAKEQJgFGIEgCjECUARiFKAIxClAAYhSgBMApR\nAmAUogTAKEQJgFGIEgCjECUARiFKAIxClAAYhSgBMApRAmAUogTAKEQJgFEig7FRr9erJUuW6PDh\nw3I4HCotLZVt23r88cdlWZaGDx+upUuXKiIiQmvWrNH27dsVGRmpRYsWadSoUcEYCUCY6NKZUmVl\nZYfHzzzzzFVfv23bNknS888/r0ceeUSlpaUqLS1VQUGBNm7cKNu2VV1drfr6eu3atUuVlZVyuVxa\nvnz5p9wNANeLq54pvfjii/r73/+uuro67dy5U9Kls6CDBw9q5syZV1zvzjvv1Pjx4yVJjY2NGjBg\ngLZv366MjAxJUlZWlmpra5WUlKTMzExZliWn0ymv16tz584pISEhQLsHINxcNUrjxo3TwIED9d57\n7yknJ0eSFBERocGDB197w5GRKiws1CuvvKKnnnpK27Ztk2VZkqSoqCg1NTWpublZ8fHx/nUuL///\nUWpoaPjEO9bTcIwQblJSUjpdftUoxcXFafTo0Ro9erTOnj2rlpYWSZfOlrqivLxc8+fP17Rp0/zr\nSpLH41FsbKyio6Pl8Xg6LI+Jieny8B/a3aV5rmfXPkZAeOjSB93Lly/Xq6++qkGDBsm2bVmWpeef\nf/6Kr//973+vU6dO6Xvf+5769esny7J02223qa6uTqNHj1ZNTY3GjBmjxMREVVRUaM6cOTp58qR8\nPh9v3YAerktReuONN7R161ZFRHTtCoJvfOMbWrhwoe6//361t7dr0aJFGjp0qIqKiuRyuZScnKzs\n7Gw5HA6lp6crJydHPp9PxcXFn2lnAIS/LkVpyJAhamlpUb9+/bq00f79++tnP/vZx5Y/++yzH1uW\nn5+v/Pz8Lm0XwPWvS1E6ceKEJkyYoCFDhkjSNd++AcCn1aUoPfnkk8GeAwAkdTFKv/vd7z62bO7c\nuQEfBgC6FKUBAwZIkmzb1r59++Tz+YI6FICeq0tRys3N7fD4wQcfDMowANClKB0+fNj/5zNnzujE\niRNBGwhAz9alKH30+qE+ffpowYIFQRsIQM/WpSht2LBB58+f17Fjx3TjjTdy1fV16uhPRoZ6hJBL\nLH4z1CP0eF26RPvll19Wbm6u1q1bp5ycHP3hD38I9lwAeqgunSmtX79eVVVVioqKUnNzsx544AFN\nnjw52LMB6IG6dKZkWZaioqIkSdHR0erTp09QhwLQc3XpTCkxMVFlZWVKT0+X2+1WYmJisOcC0EN1\n6Uxp2rRpiouL02uvvaaqqirdf//9wZ4LQA/VpSiVlZXprrvuUnFxsV544QWVlZUFey4APVSXohQZ\nGalhw4ZJkgYPHtzl31UCgE+qS58pOZ1OuVwu3X777dq7d68GDRoU7LkA9FBdOuUpLS1VQkKCXn31\nVSUkJKi0tDTYcwHoobp0ptSnTx/NmjUryKMAAP/bbgCGIUoAjEKUABiFKAEwClECYBSiBMAoRAmA\nUYgSAKMQJQBGIUoAjEKUABiFKAEwClECYBSiBMAoRAmAUYgSAKMQJQBG6dIvT34SbW1tWrRokY4f\nP67W1lb94Ac/0LBhw/T444/LsiwNHz5cS5cuVUREhNasWaPt27crMjJSixYt0qhRowI9DoAwE/Ao\n/fGPf1R8fLwqKip0/vx53XvvvRoxYoQKCgo0evRoFRcXq7q6Wk6nU7t27VJlZaVOnDih/Px8bdmy\nJdDjAAgzAY/S3XffrezsbP9jh8Oh+vp6ZWRkSJKysrJUW1urpKQkZWZmyrIsOZ1Oeb1enTt3TgkJ\nCYEeCUAYCXiUoqKiJEnNzc165JFHVFBQoPLyclmW5X++qalJzc3Nio+P77BeU1NTp1FqaGgI9JjX\nnUAco6gAzBHu+LfWfVJSUjpdHvAoSdKJEyf08MMPa/r06Zo0aZIqKir8z3k8HsXGxio6Oloej6fD\n8piYmE63d6XhP7Q7EGOHtWsfo2s7GoA5wl0gjiM+m4B/+/buu+9q9uzZeuyxxzRlyhRJ0q233qq6\nujpJUk1NjdLT05WamqodO3bI5/OpsbFRPp+Pt24AAn+mtG7dOl24cEFr167V2rVrJUmLFy/WypUr\n5XK5lJycrOzsbDkcDqWnpysnJ0c+n0/FxcWBHgVAGLJs27ZDPcTVuN1upaWlXfU1aY89003TmMtd\nMfMzb+PoT0YGYJLwllj8ZqhH6PG4eBKAUYgSAKMQJQBGIUoAjEKUABiFKAEwClECYBSiBMAoRAmA\nUYgSAKMQJQBGIUoAjEKUABiFKAEwClECYBSiBMAoRAmAUYgSAKMQJQBGIUoAjEKUABiFKAEwClEC\nYBSiBMAoRAmAUYgSAKMQJQBGIUoAjEKUABiFKAEwClECYBSiBMAoRAmAUYgSAKMQJQBGCVqU3njj\nDc2YMUOSdOTIEeXl5Wn69OlaunSpfD6fJGnNmjWaMmWKcnNztXfv3mCNAiCMBCVKv/rVr7RkyRK1\ntLRIkkpLS1VQUKCNGzfKtm1VV1ervr5eu3btUmVlpVwul5YvXx6MUQCEmchgbDQxMVGrV6/WggUL\nJEn19fXKyMiQJGVlZam2tlZJSUnKzMyUZVlyOp3yer06d+6cEhISPra9hoaGYIx5XQnEMYoKwBzh\njn9r3SclJaXT5UGJUnZ2tv773//6H9u2LcuyJElRUVFqampSc3Oz4uPj/a+5vLyzKF1p+A/tDsjc\n4ezax+jajgZgjnAXiOOIz6ZbPuiOiPjwP+PxeBQbG6vo6Gh5PJ4Oy2NiYrpjHAAG65Yo3Xrrraqr\nq5Mk1dTUKD09XampqdqxY4d8Pp8aGxvl8/k6PUsC0LME5e3b/1dYWKiioiK5XC4lJycrOztbDodD\n6enpysnJkc/nU3FxcXeMAsBwlm3bdqiHuBq32620tLSrvibtsWe6aRpzuStmfuZtHP3JyABMEt4S\ni98M9Qg9HhdPAjBKt7x9A3qSsavHhnqEkKvNr/3U63KmBMAoRAmAUYgSAKMQJQBGIUoAjEKUABiF\nKAEwClECYBSiBMAoRAmAUYgSAKMQJQBGIUoAjEKUABiFKAEwClECYBSiBMAoRAmAUYgSAKMQJQBG\nIUoAjEKUABiFKAEwClECYBSiBMAoRAmAUYgSAKMQJQBGIUoAjEKUABiFKAEwClECYBSiBMAokaEe\nwOfzadmyZdq/f7969+6tlStXasiQIaEeC0CIhPxMaevWrWptbdWmTZv06KOPqqysLNQjAQghy7Zt\nO5QDlJaWatSoUZo4caIkady4cfrHP/7hf97tdodqNABBlpaW9rFlIX/71tzcrOjoaP9jh8Oh9vZ2\nRUZeGq2zoQFcv0L+9i06Oloej8f/2Ofz+YMEoOcJeZRSU1NVU1MjSdqzZ49uvvnmEE8EIJRC/pnS\n5W/fDhw4INu2VVJSoqFDh4ZyJAAhFPIoXW+qqqr0n//8R/Pnzw/1KCHh9Xr10EMP6f3339e6desU\nFxcXkO2OHTtWtbW1AdlWODt48KAqKip08eJFvf/++7rjjjuUkZGhTZs26ac//WmH165atUrf+c53\ntGXLFg0YMEB5eXkdnjf1mPLhDQLqzJkzOn/+vKqqqkI9ynXnwoULmjdvnlavXq2bbrpJXq9XP/rR\njzRw4MBOX7948eJunjAwiNJVVFVVadu2bfrggw905swZzZw5U9XV1Tp48KAWLFigkydP6m9/+5va\n29sVExOj1atXd1h/w4YNevHFF2VZlr75zW9q5syZIdqT7lNUVKR33nlHCxculMfj0fnz5yVJS5Ys\n0S233KK77rpLX/7yl3XkyBGNGTNGTU1N2rt3r5KSklRRUaEDBw6orKxMPp9PFy5c0JIlS5Samurf\n/v79+7Vy5UpJUnx8vEpKShQTExOSfe1u1dXVGj16tG666SZJl76pLi8v17/+9S9VVlbqwQcf1Llz\n5zRhwgTl5+drxowZWrZsmX99r9eroqIiHTp0SIMHD1Zra2toduQaiNI1eDwe/frXv9ZLL72k9evX\na/Pmzaqrq9P69et12223af369YqIiNCcOXP05ptv+tc7dOiQ/vznP2vjxo2yLEuzZs1SZmamkpOT\nQ7g3wbd06VLNmzdPCQkJGjlypKZPn+6P1HPPPafjx4/rN7/5jQYOHKiMjAxVVlaqqKhIX//613Xh\nwgUdOnRIhYWFuuWWW/SnP/1JVVVVHaJUVFSkkpISDRs2TJWVlXr66af14x//OIR73H1Onz6twYMH\nd1gWFRWlXr16qaWlRWvXrpXX69X48eOVn5//sfVramrU0tKizZs3q7GxUX/961+7a/RPhChdQ0pK\niiQpJiZGQ4cOlWVZiouLU1tbm3r16qV58+apf//+OnnypNrb2/3rHThwQI2NjZo1a5Yk6X//+5+O\nHj163UfpsgMHDmjnzp16+eWXJV166yFdOrtxOp2SpP79+2vYsGGSLh3flpYWDRo0SGvXrlXfvn3l\n8Xg6XMMmSW+//baWL18uSWpra1NSUlJ37VLIOZ1O7du3r8OyY8eOaffu3Ro+fLh69+4tSVe8pObg\nwYMaNWqUf1tf/OIXgzvwp0SUrsGyrE6Xt7W1aevWraqsrNTFixd133336aPfGSQnJ2vYsGF6+umn\nZVmW1q9f36Mud0hOTtY999yjSZMm6ezZs6qsrJR05eN52apVq/TEE09o6NCheuqpp3T8+PEOzycl\nJam8vFxOp1Nut1tnzpwJ2j6YZsKECfrFL36hvLw8JSYmqq2tTWVlZfra1752zeMqXfo7eemll/TA\nAw/o1KlTOnXqVDdM/ckRpU8pMjJS/fr103333afevXtr4MCBOn36tP/5ESNG6Ktf/ary8vLU2tqq\nUaNG6Qtf+EIIJ+5e3//+97V48WJt3rxZzc3Nmjt3bpfWu+eee/TDH/5Qn//853XDDTf4P5O6bNmy\nZSosLJTX65V0KWI9RXR0tMrKyrRkyRLZti2Px6MJEyZo6NCh+uc//3nN9e+880653W5NnTpVTqdT\nn/vc57ph6k+OSwIAGCXkV3QDwEcRJQBGIUoAjEKUABiFKAEwCpcEIKDq6upUUFDgvyiypaVFkyZN\n0owZM0I8GcIFUULAjRkzxn/Hemtrq+6++25NnjxZsbGxIZ4M4YAoIaiam5sVERGhEydO6OGHH5b0\n4Y20+/bt0xNPPKFevXpp2rRpOnz4sHbu3Cmfz6eJEydq1qxZ2rdvn1asWCGHw6E+ffpoxYoV8vl8\nevTRR3XDDTfo2LFjGjlypP/WE1wHbCCAdu7caY8ZM8b+9re/bc+YMcOePXu2vX37dnvq1Kn2wYMH\nbdu27c2bN9sul8veuXOnPWnSJP+6WVlZ9tGjR+2Wlhb7ueees23btu+991573759tm3b9iuvvGLn\n5+fbx44dszMyMuympia7vb3dHj9+vH369Onu31kEBWdKCLiPvn27bN68eZ3eSPvRG2pdLpdcLpfe\nffddjRs3TtKlO+Mv3xT9la98RU8++aQkKTEx0X+z7sCBA9XS0hLcnUK3IUroFle6kTYi4tIXwK2t\nrfrLX/4il8sl27Y1ceJETZw4UYMGDdJbb72lESNGaPfu3f7fEurKDagIT0QJ3aKzG2k/egNz7969\nFRcXp8mTJysuLk5jx46V0+nUypUrtWLFCtm2LYfDoZKSklDtAroJN+QCMAoXTwIwClECYBSiBMAo\nRAmAUYgSAKMQJQBGIUoAjPJ/Hp+LG+tvl+oAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x1483f2e8>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.factorplot( 'Person',  data=df, kind='count')\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 4) Find the number of children in the various classes:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr:last-of-type th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th colspan=\"8\" halign=\"left\">AgeFill</th>\n",
       "      <th colspan=\"2\" halign=\"left\">Family_members</th>\n",
       "      <th>...</th>\n",
       "      <th colspan=\"2\" halign=\"left\">Siblings Count</th>\n",
       "      <th colspan=\"8\" halign=\"left\">Survived</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>...</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Class</th>\n",
       "      <th>Person</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"3\" valign=\"top\">1</th>\n",
       "      <th>Child</th>\n",
       "      <td>7.0</td>\n",
       "      <td>5.988571</td>\n",
       "      <td>7.492279</td>\n",
       "      <td>-5.00</td>\n",
       "      <td>1.46</td>\n",
       "      <td>4.0</td>\n",
       "      <td>12.50</td>\n",
       "      <td>15.0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>2.142857</td>\n",
       "      <td>...</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>0.857143</td>\n",
       "      <td>0.377964</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>female</th>\n",
       "      <td>91.0</td>\n",
       "      <td>35.450549</td>\n",
       "      <td>12.305612</td>\n",
       "      <td>16.00</td>\n",
       "      <td>24.00</td>\n",
       "      <td>35.0</td>\n",
       "      <td>43.50</td>\n",
       "      <td>63.0</td>\n",
       "      <td>91.0</td>\n",
       "      <td>0.967033</td>\n",
       "      <td>...</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>91.0</td>\n",
       "      <td>0.978022</td>\n",
       "      <td>0.147424</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>male</th>\n",
       "      <td>118.0</td>\n",
       "      <td>42.080508</td>\n",
       "      <td>12.665143</td>\n",
       "      <td>17.00</td>\n",
       "      <td>35.00</td>\n",
       "      <td>40.0</td>\n",
       "      <td>49.00</td>\n",
       "      <td>80.0</td>\n",
       "      <td>118.0</td>\n",
       "      <td>0.542373</td>\n",
       "      <td>...</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>118.0</td>\n",
       "      <td>0.347458</td>\n",
       "      <td>0.478193</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"3\" valign=\"top\">2</th>\n",
       "      <th>Child</th>\n",
       "      <td>19.0</td>\n",
       "      <td>2.754211</td>\n",
       "      <td>6.384438</td>\n",
       "      <td>-20.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.50</td>\n",
       "      <td>13.0</td>\n",
       "      <td>19.0</td>\n",
       "      <td>2.052632</td>\n",
       "      <td>...</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>19.0</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>female</th>\n",
       "      <td>66.0</td>\n",
       "      <td>32.053030</td>\n",
       "      <td>9.862957</td>\n",
       "      <td>17.00</td>\n",
       "      <td>24.25</td>\n",
       "      <td>29.5</td>\n",
       "      <td>37.50</td>\n",
       "      <td>57.0</td>\n",
       "      <td>66.0</td>\n",
       "      <td>0.954545</td>\n",
       "      <td>...</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>66.0</td>\n",
       "      <td>0.909091</td>\n",
       "      <td>0.289683</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>male</th>\n",
       "      <td>99.0</td>\n",
       "      <td>33.262626</td>\n",
       "      <td>11.727637</td>\n",
       "      <td>16.00</td>\n",
       "      <td>25.00</td>\n",
       "      <td>30.0</td>\n",
       "      <td>36.75</td>\n",
       "      <td>70.0</td>\n",
       "      <td>99.0</td>\n",
       "      <td>0.424242</td>\n",
       "      <td>...</td>\n",
       "      <td>0.5</td>\n",
       "      <td>2.0</td>\n",
       "      <td>99.0</td>\n",
       "      <td>0.080808</td>\n",
       "      <td>0.273927</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"3\" valign=\"top\">3</th>\n",
       "      <th>Child</th>\n",
       "      <td>58.0</td>\n",
       "      <td>6.817586</td>\n",
       "      <td>4.717904</td>\n",
       "      <td>0.42</td>\n",
       "      <td>2.25</td>\n",
       "      <td>6.0</td>\n",
       "      <td>10.00</td>\n",
       "      <td>15.0</td>\n",
       "      <td>58.0</td>\n",
       "      <td>3.362069</td>\n",
       "      <td>...</td>\n",
       "      <td>4.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>58.0</td>\n",
       "      <td>0.431034</td>\n",
       "      <td>0.499546</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>female</th>\n",
       "      <td>114.0</td>\n",
       "      <td>25.513158</td>\n",
       "      <td>8.193852</td>\n",
       "      <td>16.00</td>\n",
       "      <td>21.50</td>\n",
       "      <td>21.5</td>\n",
       "      <td>28.75</td>\n",
       "      <td>63.0</td>\n",
       "      <td>114.0</td>\n",
       "      <td>1.447368</td>\n",
       "      <td>...</td>\n",
       "      <td>1.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>114.0</td>\n",
       "      <td>0.491228</td>\n",
       "      <td>0.502130</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>male</th>\n",
       "      <td>319.0</td>\n",
       "      <td>28.733542</td>\n",
       "      <td>14.782102</td>\n",
       "      <td>16.00</td>\n",
       "      <td>23.75</td>\n",
       "      <td>25.0</td>\n",
       "      <td>30.75</td>\n",
       "      <td>200.0</td>\n",
       "      <td>319.0</td>\n",
       "      <td>0.423197</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>319.0</td>\n",
       "      <td>0.119122</td>\n",
       "      <td>0.324441</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>9 rows × 56 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "             AgeFill                                                          \\\n",
       "               count       mean        std    min    25%   50%    75%    max   \n",
       "Class Person                                                                   \n",
       "1     Child      7.0   5.988571   7.492279  -5.00   1.46   4.0  12.50   15.0   \n",
       "      female    91.0  35.450549  12.305612  16.00  24.00  35.0  43.50   63.0   \n",
       "      male     118.0  42.080508  12.665143  17.00  35.00  40.0  49.00   80.0   \n",
       "2     Child     19.0   2.754211   6.384438 -20.00   1.00   3.0   5.50   13.0   \n",
       "      female    66.0  32.053030   9.862957  17.00  24.25  29.5  37.50   57.0   \n",
       "      male      99.0  33.262626  11.727637  16.00  25.00  30.0  36.75   70.0   \n",
       "3     Child     58.0   6.817586   4.717904   0.42   2.25   6.0  10.00   15.0   \n",
       "      female   114.0  25.513158   8.193852  16.00  21.50  21.5  28.75   63.0   \n",
       "      male     319.0  28.733542  14.782102  16.00  23.75  25.0  30.75  200.0   \n",
       "\n",
       "             Family_members           ...  Siblings Count      Survived  \\\n",
       "                      count      mean ...             75%  max    count   \n",
       "Class Person                          ...                                 \n",
       "1     Child             7.0  2.142857 ...             1.0  1.0      7.0   \n",
       "      female           91.0  0.967033 ...             1.0  3.0     91.0   \n",
       "      male            118.0  0.542373 ...             1.0  3.0    118.0   \n",
       "2     Child            19.0  2.052632 ...             1.0  2.0     19.0   \n",
       "      female           66.0  0.954545 ...             1.0  3.0     66.0   \n",
       "      male             99.0  0.424242 ...             0.5  2.0     99.0   \n",
       "3     Child            58.0  3.362069 ...             4.0  5.0     58.0   \n",
       "      female          114.0  1.447368 ...             1.0  8.0    114.0   \n",
       "      male            319.0  0.423197 ...             0.0  8.0    319.0   \n",
       "\n",
       "                                                           \n",
       "                  mean       std  min  25%  50%  75%  max  \n",
       "Class Person                                               \n",
       "1     Child   0.857143  0.377964  0.0  1.0  1.0  1.0  1.0  \n",
       "      female  0.978022  0.147424  0.0  1.0  1.0  1.0  1.0  \n",
       "      male    0.347458  0.478193  0.0  0.0  0.0  1.0  1.0  \n",
       "2     Child   1.000000  0.000000  1.0  1.0  1.0  1.0  1.0  \n",
       "      female  0.909091  0.289683  0.0  1.0  1.0  1.0  1.0  \n",
       "      male    0.080808  0.273927  0.0  0.0  0.0  0.0  1.0  \n",
       "3     Child   0.431034  0.499546  0.0  0.0  0.0  1.0  1.0  \n",
       "      female  0.491228  0.502130  0.0  0.0  0.0  1.0  1.0  \n",
       "      male    0.119122  0.324441  0.0  0.0  0.0  0.0  1.0  \n",
       "\n",
       "[9 rows x 56 columns]"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby([df['Class'], df['Person']]).describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Number of children in:\\n   Class 1: 7\\n   Class 2: 19\\n   Class 3: 58'"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "'''Number of children in:\n",
    "   Class 1: 7\n",
    "   Class 2: 19\n",
    "   Class 3: 58'''"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 10) Fit a classification model which can predict whether a person survived or not by taking features as Class, Gender, Age, Siblings Count, Parents Count, Fare, Embarked:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Passenger ID</th>\n",
       "      <th>Class</th>\n",
       "      <th>Name</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Siblings Count</th>\n",
       "      <th>Parents Count</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>Survived</th>\n",
       "      <th>AgeFill</th>\n",
       "      <th>Family_members</th>\n",
       "      <th>Alone/With Family</th>\n",
       "      <th>Person</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Alexander Harris</td>\n",
       "      <td>male</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7250.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>With Family</td>\n",
       "      <td>male</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>Frank Parsons</td>\n",
       "      <td>female</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71283.3</td>\n",
       "      <td>Los Angeles</td>\n",
       "      <td>1</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>With Family</td>\n",
       "      <td>female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>Anthony Churchill</td>\n",
       "      <td>female</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7925.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>1</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>Alone</td>\n",
       "      <td>female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>Alexandra Hughes</td>\n",
       "      <td>female</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53100.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>1</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>With Family</td>\n",
       "      <td>female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>3</td>\n",
       "      <td>Joan Fraser</td>\n",
       "      <td>male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8050.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>0</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>Alone</td>\n",
       "      <td>male</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Passenger ID  Class               Name  Gender  Siblings Count  \\\n",
       "0             1      3   Alexander Harris    male               1   \n",
       "1             2      1      Frank Parsons  female               1   \n",
       "2             3      3  Anthony Churchill  female               0   \n",
       "3             4      1   Alexandra Hughes  female               1   \n",
       "4             5      3        Joan Fraser    male               0   \n",
       "\n",
       "   Parents Count     Fare     Embarked  Survived  AgeFill  Family_members  \\\n",
       "0              0   7250.0     New York         0     22.0               1   \n",
       "1              0  71283.3  Los Angeles         1     38.0               1   \n",
       "2              0   7925.0     New York         1     26.0               0   \n",
       "3              0  53100.0     New York         1     35.0               1   \n",
       "4              0   8050.0     New York         0     35.0               0   \n",
       "\n",
       "  Alone/With Family  Person  \n",
       "0       With Family    male  \n",
       "1       With Family  female  \n",
       "2             Alone  female  \n",
       "3       With Family  female  \n",
       "4             Alone    male  "
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [],
   "source": [
    "# FIRST CONVERT STRING VALUES OF OUR FEATURES INTO FLOAT/INT VALUES: This can also be done by labelencoder(), but i like doing it like this:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['female', 'male']"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#for Gender:\n",
    "sexes = sorted(df['Gender'].unique())\n",
    "sexes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'female': 0, 'male': 1}"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gender_mapping = dict(zip(sexes, range(0, len(sexes) + 1)))\n",
    "gender_mapping"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Passenger ID</th>\n",
       "      <th>Class</th>\n",
       "      <th>Name</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Siblings Count</th>\n",
       "      <th>Parents Count</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>Survived</th>\n",
       "      <th>AgeFill</th>\n",
       "      <th>Family_members</th>\n",
       "      <th>Alone/With Family</th>\n",
       "      <th>Person</th>\n",
       "      <th>Genderfill</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Alexander Harris</td>\n",
       "      <td>male</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7250.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>With Family</td>\n",
       "      <td>male</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>Frank Parsons</td>\n",
       "      <td>female</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71283.3</td>\n",
       "      <td>Los Angeles</td>\n",
       "      <td>1</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>With Family</td>\n",
       "      <td>female</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>Anthony Churchill</td>\n",
       "      <td>female</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7925.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>1</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>Alone</td>\n",
       "      <td>female</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>Alexandra Hughes</td>\n",
       "      <td>female</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53100.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>1</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>With Family</td>\n",
       "      <td>female</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>3</td>\n",
       "      <td>Joan Fraser</td>\n",
       "      <td>male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8050.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>0</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>Alone</td>\n",
       "      <td>male</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Passenger ID  Class               Name  Gender  Siblings Count  \\\n",
       "0             1      3   Alexander Harris    male               1   \n",
       "1             2      1      Frank Parsons  female               1   \n",
       "2             3      3  Anthony Churchill  female               0   \n",
       "3             4      1   Alexandra Hughes  female               1   \n",
       "4             5      3        Joan Fraser    male               0   \n",
       "\n",
       "   Parents Count     Fare     Embarked  Survived  AgeFill  Family_members  \\\n",
       "0              0   7250.0     New York         0     22.0               1   \n",
       "1              0  71283.3  Los Angeles         1     38.0               1   \n",
       "2              0   7925.0     New York         1     26.0               0   \n",
       "3              0  53100.0     New York         1     35.0               1   \n",
       "4              0   8050.0     New York         0     35.0               0   \n",
       "\n",
       "  Alone/With Family  Person  Genderfill  \n",
       "0       With Family    male           1  \n",
       "1       With Family  female           0  \n",
       "2             Alone  female           0  \n",
       "3       With Family  female           0  \n",
       "4             Alone    male           1  "
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Genderfill'] = df['Gender'].map(gender_mapping).astype(int)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['Chicago', 'Los Angeles', 'New York']"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#for Embarked:\n",
    "cities= sorted(df['Embarked'].unique())\n",
    "cities\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'Chicago': 0, 'Los Angeles': 1, 'New York': 2}"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "city_mapping = dict(zip(cities, range(0, len(cities) + 1)))\n",
    "city_mapping"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Passenger ID</th>\n",
       "      <th>Class</th>\n",
       "      <th>Name</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Siblings Count</th>\n",
       "      <th>Parents Count</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>Survived</th>\n",
       "      <th>AgeFill</th>\n",
       "      <th>Family_members</th>\n",
       "      <th>Alone/With Family</th>\n",
       "      <th>Person</th>\n",
       "      <th>Genderfill</th>\n",
       "      <th>Embarkedfill</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Alexander Harris</td>\n",
       "      <td>male</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7250.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>With Family</td>\n",
       "      <td>male</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>Frank Parsons</td>\n",
       "      <td>female</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71283.3</td>\n",
       "      <td>Los Angeles</td>\n",
       "      <td>1</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>With Family</td>\n",
       "      <td>female</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>Anthony Churchill</td>\n",
       "      <td>female</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7925.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>1</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>Alone</td>\n",
       "      <td>female</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>Alexandra Hughes</td>\n",
       "      <td>female</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53100.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>1</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>With Family</td>\n",
       "      <td>female</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>3</td>\n",
       "      <td>Joan Fraser</td>\n",
       "      <td>male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8050.0</td>\n",
       "      <td>New York</td>\n",
       "      <td>0</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>Alone</td>\n",
       "      <td>male</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Passenger ID  Class               Name  Gender  Siblings Count  \\\n",
       "0             1      3   Alexander Harris    male               1   \n",
       "1             2      1      Frank Parsons  female               1   \n",
       "2             3      3  Anthony Churchill  female               0   \n",
       "3             4      1   Alexandra Hughes  female               1   \n",
       "4             5      3        Joan Fraser    male               0   \n",
       "\n",
       "   Parents Count     Fare     Embarked  Survived  AgeFill  Family_members  \\\n",
       "0              0   7250.0     New York         0     22.0               1   \n",
       "1              0  71283.3  Los Angeles         1     38.0               1   \n",
       "2              0   7925.0     New York         1     26.0               0   \n",
       "3              0  53100.0     New York         1     35.0               1   \n",
       "4              0   8050.0     New York         0     35.0               0   \n",
       "\n",
       "  Alone/With Family  Person  Genderfill  Embarkedfill  \n",
       "0       With Family    male           1             2  \n",
       "1       With Family  female           0             1  \n",
       "2             Alone  female           0             2  \n",
       "3       With Family  female           0             2  \n",
       "4             Alone    male           1             2  "
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Embarkedfill'] = df['Embarked'].map(city_mapping).astype(int)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Training: Class, Gender, Age, Siblings Count, Parents Count, Fare, Embarked\n",
    "cols = [1,13,9,4,5,6,14]\n",
    "\n",
    "X_train= df.iloc[:, cols].as_matrix().astype(np.float)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[3.00000e+00, 1.00000e+00, 2.20000e+01, ..., 0.00000e+00,\n",
       "        7.25000e+03, 2.00000e+00],\n",
       "       [1.00000e+00, 0.00000e+00, 3.80000e+01, ..., 0.00000e+00,\n",
       "        7.12833e+04, 1.00000e+00],\n",
       "       [3.00000e+00, 0.00000e+00, 2.60000e+01, ..., 0.00000e+00,\n",
       "        7.92500e+03, 2.00000e+00],\n",
       "       ...,\n",
       "       [3.00000e+00, 0.00000e+00, 2.15000e+01, ..., 2.00000e+00,\n",
       "        2.34500e+04, 2.00000e+00],\n",
       "       [1.00000e+00, 1.00000e+00, 2.60000e+01, ..., 0.00000e+00,\n",
       "        3.00000e+04, 1.00000e+00],\n",
       "       [3.00000e+00, 1.00000e+00, 3.20000e+01, ..., 0.00000e+00,\n",
       "        7.75000e+03, 0.00000e+00]])"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 0.82737724,  0.73769513, -0.48599284, ..., -0.47367361,\n",
       "        -0.50244517,  0.56883712],\n",
       "       [-1.56610693, -1.35557354,  0.56980332, ..., -0.47367361,\n",
       "         0.78684529, -1.00518113],\n",
       "       [ 0.82737724, -1.35557354, -0.2220438 , ..., -0.47367361,\n",
       "        -0.48885426,  0.56883712],\n",
       "       ...,\n",
       "       [ 0.82737724, -1.35557354, -0.51898647, ...,  2.00893337,\n",
       "        -0.17626324,  0.56883712],\n",
       "       [-1.56610693,  0.73769513, -0.2220438 , ..., -0.47367361,\n",
       "        -0.04438104, -1.00518113],\n",
       "       [ 0.82737724,  0.73769513,  0.17387976, ..., -0.47367361,\n",
       "        -0.49237783, -2.57919938]])"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#to convert into matrix having mean= 0 and std dev= 1\n",
    "from sklearn import preprocessing\n",
    "scaler = preprocessing.StandardScaler()\n",
    "X = scaler.fit_transform(X_train)\n",
    "X"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1,\n",
       "       1, 1, 0, 1, 0, 0, 1, 0, 0, 1, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 1,\n",
       "       1, 0, 0, 1, 0, 0, 0, 0, 1, 1, 0, 1, 1, 0, 1, 0, 0, 1, 0, 0, 0, 1,\n",
       "       1, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 0,\n",
       "       1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1,\n",
       "       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 1, 0, 0, 0,\n",
       "       0, 1, 0, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0,\n",
       "       0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0,\n",
       "       0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 1, 0, 0, 1, 0, 1, 1, 1, 1, 0, 0,\n",
       "       1, 0, 0, 0, 0, 0, 1, 0, 0, 1, 1, 1, 0, 1, 0, 0, 0, 1, 1, 0, 1, 0,\n",
       "       1, 0, 0, 0, 1, 0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 1,\n",
       "       0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 1, 0, 0,\n",
       "       0, 0, 0, 1, 1, 1, 0, 1, 1, 0, 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0,\n",
       "       1, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 0, 1, 0, 1, 1, 1,\n",
       "       0, 1, 1, 1, 0, 0, 0, 1, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 1, 1, 1,\n",
       "       1, 0, 0, 0, 1, 0, 0, 1, 1, 0, 1, 1, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0,\n",
       "       0, 0, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0,\n",
       "       0, 1, 1, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 1, 0, 1, 1, 1, 0, 1, 1, 0,\n",
       "       0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0, 1, 1,\n",
       "       0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 1, 1, 1, 0, 0, 1, 0, 1, 0, 0,\n",
       "       1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 0, 1, 0, 1, 1, 0, 1, 0,\n",
       "       0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1,\n",
       "       1, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0,\n",
       "       1, 1, 0, 1, 1, 0, 1, 1, 0, 0, 1, 0, 1, 0, 1, 0, 0, 1, 0, 0, 1, 0,\n",
       "       0, 0, 1, 0, 0, 1, 0, 1, 0, 1, 0, 1, 1, 0, 0, 1, 0, 0, 1, 1, 0, 1,\n",
       "       1, 0, 0, 1, 1, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1,\n",
       "       1, 1, 0, 0, 1, 1, 0, 1, 1, 1, 0, 0, 0, 1, 0, 1, 0, 0, 0, 1, 0, 0,\n",
       "       0, 0, 1, 0, 0, 1, 1, 0, 0, 0, 1, 0, 0, 1, 1, 1, 0, 0, 1, 0, 0, 1,\n",
       "       0, 0, 1, 0, 0, 1, 1, 0, 0, 0, 0, 1, 0, 0, 1, 0, 1, 0, 0, 1, 0, 0,\n",
       "       0, 0, 0, 1, 0, 1, 1, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0,\n",
       "       1, 0, 0, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0, 0, 1, 0, 1, 0, 1,\n",
       "       0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 1, 0, 0, 1, 1, 0, 0,\n",
       "       0, 0, 1, 1, 1, 1, 1, 0, 1, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0, 0, 1, 0,\n",
       "       1, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 1, 0, 1, 0, 0, 1,\n",
       "       0, 0, 1, 1, 0, 0, 1, 1, 0, 0, 0, 1, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0,\n",
       "       0, 0, 0, 0, 1, 0, 0, 1, 0, 1, 1, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0,\n",
       "       0, 0, 0, 0, 1, 1, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0,\n",
       "       0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 1,\n",
       "       0, 0, 1, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 1, 1, 1,\n",
       "       1, 0, 0, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 0, 0, 1, 1, 0, 0, 0, 1,\n",
       "       1, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0])"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y = df['Survived'].as_matrix().astype(np.int)\n",
    "y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'CROSS VALIDATION and checking the accuracy of the classifiers:'"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "'''CROSS VALIDATION and checking the accuracy of the classifiers:'''"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [],
   "source": [
    "def stratified_cv(X, y, clf_class, shuffle=True, n_folds=10, **kwargs):\n",
    "    stratified_k_fold = cross_validation.StratifiedKFold(y, n_folds=n_folds, shuffle=shuffle)\n",
    "    y_pred = y.copy()\n",
    "    for ii, jj in stratified_k_fold:\n",
    "        X_train, X_test = X[ii], X[jj]\n",
    "        y_train = y[ii]\n",
    "        clf = clf_class(**kwargs)\n",
    "        clf.fit(X_train,y_train)\n",
    "        y_pred[jj] = clf.predict(X_test)\n",
    "    return y_pred"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\welcome\\Anaconda2\\lib\\site-packages\\sklearn\\cross_validation.py:41: DeprecationWarning: This module was deprecated in version 0.18 in favor of the model_selection module into which all the refactored classes and functions are moved. Also note that the interface of the new CV iterators are different from that of this module. This module will be removed in 0.20.\n",
      "  \"This module will be removed in 0.20.\", DeprecationWarning)\n"
     ]
    }
   ],
   "source": [
    "import sklearn as ske\n",
    "\n",
    "from sklearn import cross_validation\n",
    "from sklearn import tree\n",
    "from sklearn import svm\n",
    "from sklearn import ensemble\n",
    "from sklearn import neighbors\n",
    "from sklearn import linear_model\n",
    "from sklearn import metrics"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\welcome\\Anaconda2\\lib\\site-packages\\sklearn\\linear_model\\stochastic_gradient.py:128: FutureWarning: max_iter and tol parameters have been added in <class 'sklearn.linear_model.passive_aggressive.PassiveAggressiveClassifier'> in 0.19. If both are left unset, they default to max_iter=5 and tol=None. If tol is not None, max_iter defaults to max_iter=1000. From 0.21, default max_iter will be 1000, and default tol will be 1e-3.\n",
      "  \"and default tol will be 1e-3.\" % type(self), FutureWarning)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Passive Aggressive Classifier: 0.69\n",
      "Gradient Boosting Classifier:  0.83\n",
      "Support vector machine(SVM):   0.82\n",
      "Random Forest Classifier:      0.82\n",
      "K Nearest Neighbor Classifier: 0.80\n",
      "Logistic Regression:           0.80\n"
     ]
    }
   ],
   "source": [
    "print('Passive Aggressive Classifier: {:.2f}'.format(metrics.accuracy_score(y, stratified_cv(X, y, linear_model.PassiveAggressiveClassifier))))\n",
    "print('Gradient Boosting Classifier:  {:.2f}'.format(metrics.accuracy_score(y, stratified_cv(X, y, ensemble.GradientBoostingClassifier))))\n",
    "print('Support vector machine(SVM):   {:.2f}'.format(metrics.accuracy_score(y, stratified_cv(X, y, svm.SVC))))\n",
    "print('Random Forest Classifier:      {:.2f}'.format(metrics.accuracy_score(y, stratified_cv(X, y, ensemble.RandomForestClassifier))))\n",
    "print('K Nearest Neighbor Classifier: {:.2f}'.format(metrics.accuracy_score(y, stratified_cv(X, y, neighbors.KNeighborsClassifier))))\n",
    "print('Logistic Regression:           {:.2f}'.format(metrics.accuracy_score(y, stratified_cv(X, y, linear_model.LogisticRegression))))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Mean accuracy of SVM: 0.975308641975'"
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#SVM TRAINING AND FITTING:\n",
    "from sklearn.svm import SVC\n",
    "svc = SVC()\n",
    "clf = svm.SVC(C=100, gamma=10000)\n",
    "clf.fit(X, y)  \n",
    "\n",
    "\n",
    "#training features\n",
    "train_features = X\n",
    "\n",
    "# 'Survived' column values\n",
    "train_target = y\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 SVM: {0}\".format(score)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25 )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(668L, 7L)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "array([[ 0.82737724,  0.73769513,  0.96572688, ...,  0.76762988,\n",
       "        -0.32425319,  0.56883712],\n",
       "       [ 0.82737724,  0.73769513, -0.02408202, ..., -0.47367361,\n",
       "        -0.45714213,  0.56883712],\n",
       "       [-0.36936484, -1.35557354,  1.69158674, ..., -0.47367361,\n",
       "        -0.32626666,  0.56883712],\n",
       "       ...,\n",
       "       [ 0.82737724,  0.73769513, -0.5519801 , ..., -0.47367361,\n",
       "        -0.48885426,  0.56883712],\n",
       "       [ 0.82737724,  0.73769513, -0.48599284, ..., -0.47367361,\n",
       "        -0.50294854, -1.00518113],\n",
       "       [ 0.82737724,  0.73769513, -0.28803106, ..., -0.47367361,\n",
       "        -0.49187446,  0.56883712]])"
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "print X_train.shape\n",
    "X_train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(668L,)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "array([0, 1, 1, 1, 0, 0, 1, 0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 1, 1, 1, 1, 0,\n",
       "       1, 1, 0, 0, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 1, 1, 0, 0, 0, 1,\n",
       "       0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1,\n",
       "       1, 1, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0, 1, 0, 0, 0, 0,\n",
       "       0, 0, 0, 0, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 0, 1, 0, 0, 1,\n",
       "       0, 0, 1, 0, 1, 1, 1, 0, 1, 1, 1, 0, 1, 0, 0, 0, 0, 1, 1, 1, 0, 0,\n",
       "       0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 1, 1, 1, 0, 1, 0, 1, 0, 1, 0, 0, 0,\n",
       "       0, 1, 0, 1, 0, 0, 0, 1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0,\n",
       "       0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 1, 1, 1, 0, 1, 0, 1, 0, 0, 1, 0,\n",
       "       1, 1, 0, 1, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 1, 1, 0,\n",
       "       1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 1, 1, 1, 0, 0, 0, 1, 0,\n",
       "       0, 0, 0, 1, 0, 0, 1, 0, 1, 0, 0, 1, 0, 0, 1, 0, 0, 0, 1, 1, 0, 1,\n",
       "       0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 1, 1, 0, 0, 1, 0, 0, 1, 0, 1, 0,\n",
       "       0, 1, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 1, 0, 1, 1, 0, 0, 1, 0, 0,\n",
       "       0, 0, 0, 0, 1, 1, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 1, 1, 1, 0, 0,\n",
       "       1, 0, 1, 0, 1, 0, 0, 1, 0, 0, 1, 0, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0,\n",
       "       0, 1, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 1,\n",
       "       1, 0, 1, 0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0,\n",
       "       0, 0, 1, 0, 1, 0, 0, 1, 0, 0, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1,\n",
       "       0, 1, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0, 0, 0, 0, 1, 0, 1,\n",
       "       1, 0, 0, 1, 1, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0,\n",
       "       1, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0, 0, 1, 0, 1, 0, 0, 1, 1, 0, 0, 0,\n",
       "       1, 1, 0, 0, 1, 0, 1, 0, 0, 0, 1, 0, 1, 0, 1, 1, 0, 1, 1, 0, 0, 0,\n",
       "       1, 1, 1, 1, 0, 1, 0, 0, 1, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 0,\n",
       "       1, 0, 0, 0, 1, 0, 1, 0, 1, 1, 1, 1, 0, 0, 0, 1, 1, 0, 1, 0, 1, 1,\n",
       "       0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 1, 0, 0, 1, 1,\n",
       "       1, 0, 1, 1, 0, 0, 1, 1, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1,\n",
       "       0, 0, 1, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0, 0,\n",
       "       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 1, 1, 0, 0,\n",
       "       0, 1, 1, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 1, 0,\n",
       "       0, 0, 0, 1, 0, 0, 1, 0])"
      ]
     },
     "execution_count": 60,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "print y_train.shape\n",
    "y_train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(223L, 7L)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "array([[-0.36936484, -1.35557354,  0.96572688, ..., -0.47367361,\n",
       "        -0.12491979,  0.56883712],\n",
       "       [ 0.82737724,  0.73769513,  1.22967592, ..., -0.47367361,\n",
       "        -0.49027979,  0.56883712],\n",
       "       [-0.36936484,  0.73769513,  0.37184154, ..., -0.47367361,\n",
       "        -0.43700744,  0.56883712],\n",
       "       ...,\n",
       "       [ 0.82737724,  0.73769513, -0.28803106, ..., -0.47367361,\n",
       "        -0.49237783, -2.57919938],\n",
       "       [ 0.82737724,  0.73769513, -0.28803106, ..., -0.47367361,\n",
       "        -0.50294854, -1.00518113],\n",
       "       [ 0.82737724,  0.73769513, -0.28803106, ..., -0.47367361,\n",
       "        -0.48944219,  0.56883712]])"
      ]
     },
     "execution_count": 61,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "print X_test.shape\n",
    "X_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(223L,)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "array([0, 0, 0, 0, 0, 1, 1, 1, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1,\n",
       "       1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 0, 0, 1, 1, 0, 1,\n",
       "       0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 1, 1, 1, 0, 0, 1, 0, 1, 0, 1, 1, 0,\n",
       "       1, 1, 0, 0, 0, 1, 0, 0, 0, 0, 1, 1, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0,\n",
       "       1, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 1, 0, 0, 0, 1, 1, 0, 0, 0, 0,\n",
       "       0, 1, 1, 0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 1, 1, 1, 1, 0, 1, 0, 1, 0,\n",
       "       0, 0, 1, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0,\n",
       "       0, 1, 1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 1, 1, 1,\n",
       "       0, 0, 1, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0,\n",
       "       1, 0, 0, 1, 0, 1, 0, 1, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 1,\n",
       "       0, 0, 0])"
      ]
     },
     "execution_count": 62,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "print y_test.shape\n",
    "y_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Mean accuracy of SVM: 0.850299401198'"
      ]
     },
     "execution_count": 63,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#SVM TRAINING AND FITTING:\n",
    "from sklearn.svm import SVC\n",
    "svc = SVC()\n",
    "clf1 = svm.SVC()\n",
    "clf1.fit(X_train, y_train)  \n",
    "\n",
    "\n",
    "#training features\n",
    "train_features = X_train\n",
    "\n",
    "# 'Survived' column values\n",
    "train_target = y_train\n",
    "\n",
    "# Fit the model to our training data\n",
    "clf1 = clf1.fit(train_features, train_target)\n",
    "score = clf1.score(train_features, train_target)\n",
    "\"Mean accuracy of SVM: {0}\".format(score)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Calculating AUC:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.cross_validation import cross_val_score\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn.svm import SVC\n",
    "from sklearn.ensemble import RandomForestClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 187,
   "metadata": {},
   "outputs": [],
   "source": [
    "clf1 = LogisticRegression(penalty='l2',C=0.001,random_state=42)\n",
    "clf2 = DecisionTreeClassifier(max_depth=5,criterion='entropy',random_state=42)\n",
    "clf3 = KNeighborsClassifier(n_neighbors=5,p=2,metric='minkowski')\n",
    "clf4 = svm.SVC(C=0.001, gamma=100, kernel='linear')\n",
    "clf5 = RandomForestClassifier(n_estimators=100, random_state =42, min_samples_leaf = 5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 188,
   "metadata": {},
   "outputs": [],
   "source": [
    "labels= [\"LOGREG\", \"DT\", \"KNN\", \"SVM\", \"RF\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 189,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "ROC AUC: 0.84 (+/- 0.04) [LOGREG]\n",
      "ROC AUC: 0.84 (+/- 0.07) [DT]\n",
      "ROC AUC: 0.85 (+/- 0.07) [KNN]\n",
      "ROC AUC: 0.85 (+/- 0.05) [SVM]\n",
      "ROC AUC: 0.88 (+/- 0.06) [RF]\n"
     ]
    }
   ],
   "source": [
    "clf_labels = [clf1, clf2, clf3, clf4, clf5]\n",
    "for clf, label in zip(clf_labels, labels):\n",
    "    scores = cross_val_score(estimator=clf,X=X_train,y=y_train,cv=10,scoring='roc_auc')\n",
    "    print(\"ROC AUC: %0.2f (+/- %0.2f) [%s]\" % (scores.mean(), scores.std(), label))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "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": "2.7.15"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}