{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Logistic Regression with Kaggle Titanic data set"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Import packages and dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>PassengerId</th>\n",
       "      <th>Survived</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Name</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>Embarked</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Braund, Mr. Owen Harris</td>\n",
       "      <td>male</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>A/5 21171</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
       "      <td>female</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>PC 17599</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>C85</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Heikkinen, Miss. Laina</td>\n",
       "      <td>female</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>STON/O2. 3101282</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n",
       "      <td>female</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>113803</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>C123</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Allen, Mr. William Henry</td>\n",
       "      <td>male</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>373450</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   PassengerId  Survived  Pclass  \\\n",
       "0            1         0       3   \n",
       "1            2         1       1   \n",
       "2            3         1       3   \n",
       "3            4         1       1   \n",
       "4            5         0       3   \n",
       "\n",
       "                                                Name     Sex   Age  SibSp  \\\n",
       "0                            Braund, Mr. Owen Harris    male  22.0      1   \n",
       "1  Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0      1   \n",
       "2                             Heikkinen, Miss. Laina  female  26.0      0   \n",
       "3       Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0      1   \n",
       "4                           Allen, Mr. William Henry    male  35.0      0   \n",
       "\n",
       "   Parch            Ticket     Fare Cabin Embarked  \n",
       "0      0         A/5 21171   7.2500   NaN        S  \n",
       "1      0          PC 17599  71.2833   C85        C  \n",
       "2      0  STON/O2. 3101282   7.9250   NaN        S  \n",
       "3      0            113803  53.1000  C123        S  \n",
       "4      0            373450   8.0500   NaN        S  "
      ]
     },
     "execution_count": 89,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "%matplotlib inline\n",
    "\n",
    "train = pd.read_csv('titanic_train.csv') # Training set is already available\n",
    "train.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Check basic info about the data set including missing value"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 891 entries, 0 to 890\n",
      "Data columns (total 12 columns):\n",
      "PassengerId    891 non-null int64\n",
      "Survived       891 non-null int64\n",
      "Pclass         891 non-null int64\n",
      "Name           891 non-null object\n",
      "Sex            891 non-null object\n",
      "Age            714 non-null float64\n",
      "SibSp          891 non-null int64\n",
      "Parch          891 non-null int64\n",
      "Ticket         891 non-null object\n",
      "Fare           891 non-null float64\n",
      "Cabin          204 non-null object\n",
      "Embarked       889 non-null object\n",
      "dtypes: float64(2), int64(5), object(5)\n",
      "memory usage: 83.6+ KB\n"
     ]
    }
   ],
   "source": [
    "t=train.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>PassengerId</th>\n",
       "      <th>Survived</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Fare</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>891.000000</td>\n",
       "      <td>891.000000</td>\n",
       "      <td>891.000000</td>\n",
       "      <td>714.000000</td>\n",
       "      <td>891.000000</td>\n",
       "      <td>891.000000</td>\n",
       "      <td>891.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>446.000000</td>\n",
       "      <td>0.383838</td>\n",
       "      <td>2.308642</td>\n",
       "      <td>29.699118</td>\n",
       "      <td>0.523008</td>\n",
       "      <td>0.381594</td>\n",
       "      <td>32.204208</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>257.353842</td>\n",
       "      <td>0.486592</td>\n",
       "      <td>0.836071</td>\n",
       "      <td>14.526497</td>\n",
       "      <td>1.102743</td>\n",
       "      <td>0.806057</td>\n",
       "      <td>49.693429</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.420000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>223.500000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>20.125000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>7.910400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>446.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>28.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>14.454200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>668.500000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>38.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>31.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>891.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>80.000000</td>\n",
       "      <td>8.000000</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>512.329200</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       PassengerId    Survived      Pclass         Age       SibSp  \\\n",
       "count   891.000000  891.000000  891.000000  714.000000  891.000000   \n",
       "mean    446.000000    0.383838    2.308642   29.699118    0.523008   \n",
       "std     257.353842    0.486592    0.836071   14.526497    1.102743   \n",
       "min       1.000000    0.000000    1.000000    0.420000    0.000000   \n",
       "25%     223.500000    0.000000    2.000000   20.125000    0.000000   \n",
       "50%     446.000000    0.000000    3.000000   28.000000    0.000000   \n",
       "75%     668.500000    1.000000    3.000000   38.000000    1.000000   \n",
       "max     891.000000    1.000000    3.000000   80.000000    8.000000   \n",
       "\n",
       "            Parch        Fare  \n",
       "count  891.000000  891.000000  \n",
       "mean     0.381594   32.204208  \n",
       "std      0.806057   49.693429  \n",
       "min      0.000000    0.000000  \n",
       "25%      0.000000    7.910400  \n",
       "50%      0.000000   14.454200  \n",
       "75%      0.000000   31.000000  \n",
       "max      6.000000  512.329200  "
      ]
     },
     "execution_count": 91,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "d=train.describe()\n",
    "d"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Exploratory analysis and plots"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Plot a bar diagram to check the number of numeric entries**\n",
    "\n",
    "From the bar diagram, it shows that there are some age entries missing as the number of count for 'Age' is less than the other counts. We can do some impute/transformation of the data to fill-up the missing entries."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.text.Text at 0x2acbc65c0f0>"
      ]
     },
     "execution_count": 92,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXUAAAE5CAYAAABvZ7DfAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x2acbc62df28>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "dT=d.T\n",
    "dT.plot.bar(y='count')\n",
    "plt.title(\"Bar plot of the count of numeric features\",fontsize=17)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Check the relative size of survived and not-survived**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x2acbc63f240>"
      ]
     },
     "execution_count": 93,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYMAAAEFCAYAAAABjYvXAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x2acbacc0f60>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.set_style('whitegrid')\n",
    "sns.countplot(x='Survived',data=train,palette='RdBu_r')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Is there a pattern for the survivability based on sex?**\n",
    "\n",
    "It looks like more female survived than males!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x2acbc7034a8>"
      ]
     },
     "execution_count": 94,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYMAAAEFCAYAAAABjYvXAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x2acbac66d30>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.set_style('whitegrid')\n",
    "sns.countplot(x='Survived',hue='Sex',data=train,palette='RdBu_r')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**What about any pattern related to passenger class?**\n",
    "\n",
    "It looks like disproportionately large number of 3rd class passengers died!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x2acbc75b208>"
      ]
     },
     "execution_count": 95,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYMAAAEFCAYAAAABjYvXAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nrgAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x2acbc775780>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.set_style('whitegrid')\n",
    "sns.countplot(x='Survived',hue='Pclass',data=train,palette='rainbow')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Following code extracts and plots the fraction of passenger count that survived, by each class**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.text.Text at 0x2acbc8c99e8>"
      ]
     },
     "execution_count": 96,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXIAAAEUCAYAAAA2ib1OAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x2acbc880588>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "f_class_survived=train.groupby('Pclass')['Survived'].mean()\n",
    "f_class_survived = pd.DataFrame(f_class_survived)\n",
    "f_class_survived\n",
    "f_class_survived.plot.bar(y='Survived')\n",
    "plt.title(\"Fraction of passengers survived by class\",fontsize=17)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**What about any pattern related to having sibling and spouse?**\n",
    "\n",
    "It looks like there is a weak trend that chance of survibility increased if there were more number of sibling or spouse"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x2acbc8accf8>"
      ]
     },
     "execution_count": 97,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYMAAAEFCAYAAAABjYvXAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x2acbc62dcf8>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.set_style('whitegrid')\n",
    "sns.countplot(x='Survived',hue='SibSp',data=train,palette='rainbow')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**How does the overall age distribution look like?**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 98,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x2acbc925438>"
      ]
     },
     "execution_count": 98,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAmQAAAGQCAYAAAAA+nwuAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x2acbc9a6390>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.xlabel(\"Age of the passengers\",fontsize=18)\n",
    "plt.ylabel(\"Count\",fontsize=18)\n",
    "plt.title(\"Age histogram of the passengers\",fontsize=22)\n",
    "train['Age'].hist(bins=30,color='darkred',alpha=0.7,figsize=(10,6))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**How does the age distribution look like across passenger class?**\n",
    "\n",
    "It looks like that the average age is different for three classes and it generally decreases from 1st class to 3rd class."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 99,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x2acbc8737b8>"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAtQAAAJUCAYAAAA1nbEoAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzt3X+UlnWd//HXDMMggiOWkSVpoma57iZgIOebWKxIZW6G\nFKiLuVi7ZqRTVqBHwM09kuuPMrHFWs2EiG0FzR/tdgpMUoothn6RtdZxrZBkNRGGkGFkvn/0Zb6Z\nqOCHmWu45/E4h3Ouue+573kz91wzz/nMdV93XUdHR0cAAICXpL7qAQAAYG8mqAEAoICgBgCAAoIa\nAAAKCGoAACggqAEAoEBD1QOUWLVqVdUjAADQS4wYMWKnl+/VQZ08/38MAAD2lBdayHXIBwAAFBDU\nAABQQFADAEABQQ0AAAUENQAAFBDUAABQQFADAEABQQ0AAAUENQAAFBDUAABQQFADAEABQQ0AAAUE\nNQAAFBDUAABQQFADAEABQQ0AAAUENQAAFBDUAABQQFADAECBhqo+8LZt2zJjxoysXbs29fX1ufzy\ny9PQ0JAZM2akrq4uRx55ZGbPnp36es0PAEDPVVlQ33fffWlvb8+iRYvywAMP5DOf+Uy2bduW5ubm\njBo1KrNmzcrSpUszbty4qkYEAIAXVdny72GHHZZnnnkm27dvT2traxoaGrJmzZqMHDkySTJmzJis\nWLGiqvEAAGCXVLZCve+++2bt2rV5+9vfnieffDLz5s3L97///dTV1SVJBgwYkE2bNlU13l5l7ty5\nWbZsWdVj7JYdj+1+++1X8SS7Z+zYsZk2bVrVYwAAPUhlQX3LLbfkzW9+cy666KKsW7cu73vf+7Jt\n27bO6zdv3pympqYXvZ9Vq1Z15Zh7hcceeyxtbW1Vj7FbtmzZkiTp169fxZPsnscee8zXHADwLJUF\ndVNTU/r27Zsk2X///dPe3p6jjz46K1euzKhRo7J8+fIcf/zxL3o/I0aM6OpRe7y98XMwYcKEJMmS\nJUsqngQA4MW90IJaZUF9zjnn5JJLLsmZZ56Zbdu25SMf+UiOOeaYzJw5M9dee22GDh2a8ePHVzUe\nAADsksqCesCAAbnuuuuec/mCBQsqmAYAAF4aJ3kGAIACghoAAAoIagAAKCCoAQCggKAGAIACghoA\nAAoIagAAKCCoAQCggKAGAIACghoAAAoIagAAKCCoAQCggKAGAIACghoAAAoIagAAKCCoAQCggKAG\nAIACghoAAAoIagAAKCCoAQCggKAGAIACghoAAAoIagAAKCCoAQCggKAGAIACghoAAAoIagAAKCCo\nAQCggKAGAIACghoAoIu1tLSkpaWl6jHoIg1VDwAAUOtuuummJMnw4cMrnoSuYIUaAKALtbS0ZPXq\n1Vm9erVV6holqAEAutCO1ek/36Z2CGoAACggqAEAutC55567021qhyclAgB0oeHDh2fYsGGd29Qe\nQQ0A0MWsTNc2QQ0A0MWsTNc2x1ADAEABQQ0AAAUENQAAFBDUAABQQFADAEABQQ0AAAUENQAAFBDU\nAABQQFADAEABQQ0AAAUENQAAFBDUAABQQFADAEABQQ0A0MVaWlrS0tJS9Rh0kYaqBwAAqHU33XRT\nkmT48OEVT0JXsEINANCFWlpasnr16qxevdoqdY0S1AC9iD87Q/fbsTr959vUjsoO+ViyZEluv/32\nJMnWrVvz4IMPZuHChbniiitSV1eXI488MrNnz059veYH2FP82Rlgz6usVidMmJD58+dn/vz5+Yu/\n+ItceumlueGGG9Lc3JyFCxemo6MjS5curWo8gJrjz85QjXPPPXen29SOypd/f/KTn+SXv/xlJk2a\nlDVr1mTkyJFJkjFjxmTFihUVTwdQO/zZGaoxfPjwDBs2LMOGDfPXoRpV+Vk+brzxxnzoQx9KknR0\ndKSuri5JMmDAgGzatOlFb79q1aounY+u0dbWlsTjB93pT7+nbtq0yf4H3eiEE05I4uderao0qDdu\n3JiHH344xx9/fJI863jpzZs3p6mp6UXvY8SIEV02H12nsbExiccPulNzc3OmTZvWuW2lDLqPn3d7\nvxf6ZajSQz6+//3vZ/To0Z1vH3300Vm5cmWSZPny5TnuuOOqGg2g5vizM0DXqHSF+uGHH86QIUM6\n354+fXpmzpyZa6+9NkOHDs348eMrnA6g9nhCFMCeV2lQv//973/W24cddlgWLFhQ0TQAtc/KNMCe\nV/lZPgAAYG8mqAEAoICgBgCAAoIaAAAKCGoAACggqAEAoICgBgCAAoIaAAAKCGoAACggqAEAoICg\nBgCAAoIaAAAKCGoAACggqAEAoICgBgCAAoIaAAAKCGqAXqSlpSUtLS1VjwFQUxqqHgCA7nPTTTcl\nSYYPH17xJAC1wwo1QC/R0tKS1atXZ/Xq1VapAfYgQQ3QS+xYnf7zbQDKCGoAACggqAF6iXPPPXen\n2wCU8aREgF5i+PDhGTZsWOc20H12PG/BvlebBDVAL2JlGqrhDDu1TVAD9CJ+mEP323GGnR3b9sPa\n4xhqAIAu5Aw7tU9QAwBAAUENANCFnGGn9jmGGgCgCznDTu0T1AAAXczKdG0T1AAAXczKdG1zDDUA\nABQQ1AAAUEBQAwBAAUENANDFWlpa0tLSUvUYdBFPSgQA6GI7XiHRkxNrkxVqAIAu1NLSktWrV2f1\n6tVWqWuUoAYA6EI7Vqf/fJvaIagBAKCAoAYA6EJ/+iqJXjGxNnlSIgBAFxo+fHiGDRvWuU3tEdQA\nvciOJ0T5oQ7dy8p0bRPUAL2IU3dBNexztc0x1AC9hFN3AXQNQQ3QSzh1F0DXENQAAFBAUAP0Ek7d\nBdA1PCkRoJdw6i6ojjPs1DZBDdCLWJmGajjDTm0T1AC9iB/m0P12nGFnx7b9sPY4hhoAoAs5w07t\nE9QAAFBAUAMAdCFn2Kl9jqEG6EWcaQC6nzPs1L5Kg/rGG2/MsmXLsm3btpxxxhkZOXJkZsyYkbq6\nuhx55JGZPXt26ustogPsKc40ANWwMl3bKqvVlStXZvXq1fnKV76S+fPn53e/+13mzJmT5ubmLFy4\nMB0dHVm6dGlV4wHUnB1nGli9enXnSjXQPYYPH+4X2RpWWVDff//9ed3rXpcPfehDOe+88/KWt7wl\na9asyciRI5MkY8aMyYoVK6oaD6DmONMAQNeo7JCPJ598Mo8++mjmzZuX3/72t/ngBz+Yjo6O1NXV\nJUkGDBiQTZs2vej9rFq1qqtHpQu0tbUl8fhBd/rT76mbNm2y/wHsIZUF9aBBgzJ06NA0NjZm6NCh\n6devX373u991Xr958+Y0NTW96P2MGDGiK8ekizQ2Nibx+EF3am5uzrRp0zq3/fkZYNe90CJEZYd8\njBgxIt/5znfS0dGRxx57LFu2bMno0aOzcuXKJMny5ctz3HHHVTUeQM0ZPnx4jjjiiBxxxBFiGrpZ\nS0uL5y7UsMpWqN/61rfm+9//fiZOnJiOjo7MmjUrQ4YMycyZM3Pttddm6NChGT9+fFXjAQDsMc6w\nU9sqPW3eJz7xiedctmDBggomAah9LS0t+eUvf9m57Qc7dI8dZ9jZsW3fqz1O8gzQSzjLB1TDvlf7\nBDUAABQQ1AC9xJ++UptXbYPuY9+rfZUeQw1A9xk+fHiGDRvWuQ10D/te7RPUAL2I1TGohn2vtglq\ngF7E6hhUw75X2xxDDQAABQQ1AAAUENQAAFBAUAMAQAFBDdCLLFq0KIsWLap6DICa4iwfAL3IzTff\nnCSZPHlyxZMA1A4r1AC9xKJFi9La2prW1lar1AB7kKAG6CV2rE7/+TYAZQQ1AAAUENQAvcTUqVN3\nug1AGUEN0EtMnjw5AwcOzMCBAz0pEWAPcpYPgF7EyjTAnieoAXoRK9MAe55DPgAAulhLS0taWlqq\nHoMuYoUaAKCL3XTTTUmS4cOHVzwJXcEKNQBAF2ppacnq1auzevVqq9Q1SlADAHShHavTf75N7RDU\nAABQQFADAHShc889d6fb1A5PSgQoMHfu3CxbtqzqMXbZpk2bkiT77bdfxZPsnrFjx2batGlVjwEv\nyfDhwzNs2LDObWqPoAboRbZs2ZJk7wtq2NtZma5tghqgwLRp0/aqldMJEyYkSZYsWVLxJNC7WJmu\nbY6hBgCAAoIaAAAKCGoAACggqAEAoICgBgCAAoIaAAAKCGoAACggqAEAoICgBgCAAoIaAAAKCGoA\nACggqAEAoICgBgCAAoIaAAAKCGoAACggqAEAoICgBgCAAoIaAAAKCGoAACggqAEAoICgBgCAAoIa\nAAAKNFQ9AADA7po7d26WLVtW9Ri7bNOmTUmS/fbbr+JJds/YsWMzbdq0qsfo8axQAwB0sS1btmTL\nli1Vj0EXsUINAOx1pk2btletnE6YMCFJsmTJkoonoStYoQYAgAKVrlC/+93vzsCBA5MkQ4YMyXnn\nnZcZM2akrq4uRx55ZGbPnp36es0PAEDPVVlQb926NR0dHZk/f37nZeedd16am5szatSozJo1K0uX\nLs24ceOqGhEAAF5UZcu/P//5z7Nly5ZMnTo1Z599dn74wx9mzZo1GTlyZJJkzJgxWbFiRVXjAQDA\nLqlshXqfffbJueeem/e85z35n//5n3zgAx9IR0dH6urqkiQDBgzoPMXMC1m1alVXj0oXaGtrS+Lx\ng+5m34Nq2PdqW2VBfdhhh+XQQw9NXV1dDjvssAwaNChr1qzpvH7z5s1pamp60fsZMWJEV45JF2ls\nbEzi8YPuZt+Datj39n4v9MtQZYd83HbbbfnUpz6VJHnsscfS2tqa//N//k9WrlyZJFm+fHmOO+64\nqsYDAIBdUtkK9cSJE3PxxRfnjDPOSF1dXa644ooccMABmTlzZq699toMHTo048ePr2o8AADYJZUF\ndWNjY6655prnXL5gwYIKpgEAgJfGKyXuxHnnnZf169dXPUZN2/H53fHKUXSNwYMHZ968eVWPAQA1\nTVDvxPr167Pud+vzTP3+VY9Ss+q3902S/Hb91oonqV19tj9V9QgA0CsI6ufxTP3+WXfAxVWPAS/Z\nq56cU/UIANAreF1vAAAoIKgBAKCAoAYAgAKCGgAACghqAAAoIKgBAKCAoAYAgAKCGgAACghqAAAo\nIKgBAKCAoAYAgAKCGgAACghqAAAoIKgBAKCAoAYAgAKCGgAACghqAAAoIKgBAKCAoAYAgAKCGgAA\nCghqAAAoIKgBAKCAoAYAgAKCGgAACghqAAAoIKgBAKCAoAYAgAKCGgAACghqAAAoIKgBAKCAoAYA\ngAKCGgAACghqAAAoIKgBAKCAoAYAgAKCGgAACghqAAAoIKgBAKBAw+7eoL29PT/5yU+ybt26jBw5\nMvvss0+eeeaZ7L///l0xHwAA9Gi7tUL9H//xH3nLW96SM888MxdddFEeeuihrFq1KieeeGL+9V//\ntatmBACAHmuXg/r+++/PRRddlNe+9rWZPn16Ojo6kiRDhgzJ6173ulxzzTX52te+1mWDAgBAT7TL\nQX3DDTfkmGOOya233pp3vetdnZcffvjhWbhwYYYNG5YvfelLXTIkAAD0VLsc1A8++GBOOeWU1Nc/\n9yYNDQ155zvfmYcffniPDgcAAD3dLgd13759097e/rzXb9iwIX379t0jQwEAwN5il4N65MiRue22\n27J169bnXLd+/fosXLgwI0aM2KPDAQBAT7fLp8376Ec/mkmTJuVv/uZvMmbMmNTV1WXp0qX59re/\nndtvvz1tbW254IILunJWAADocXZ5hfrwww/Pl7/85QwePDjz589PR0dHFixYkC996Us55JBDcsst\nt+QNb3hDV84KAAA9zm69sMtRRx2V+fPnZ8OGDfn1r3+d7du35+CDD84rXvGKrpoPAAB6tN1+pcQk\nGTRoUAYNGrSnZwEAgL3OLgf12LFjU1dX97zX19XVpbGxMS9/+cvzV3/1V/m7v/u7HHjggXtkSAAA\n6Kl2+Rjq0aNHp7W1NWvXrk2/fv3yhje8Iccee2wGDRqURx99NI8//ngOOOCAbNiwITfffHNOO+20\nPProo105OwAAVG6Xg/roo4/Oli1b8rnPfS5f//rXM3fu3FxzzTVZvHhxvvKVr6S+vj6nnXZa7rrr\nrtxxxx1Jkuuuu+4F7/OJJ57IiSeemF/96ld55JFHcsYZZ+TMM8/M7Nmzs3379rL/GQAAdINdDuov\nfvGLOfvsszN27NjnXHfsscdmypQp+fznP5/kj09ePOOMM/LAAw887/1t27Yts2bNyj777JMkmTNn\nTpqbm7Nw4cJ0dHRk6dKlu/t/AQCAbrfLQf3EE0/kla985fNe//KXvzyPPfZY59uDBw9Oa2vr877/\nlVdemcmTJ2fw4MFJkjVr1mTkyJFJkjFjxmTFihW7OhoAAFRml5+UeMQRR+T222/PpEmT0tjY+Kzr\n2tracscdd2To0KGdl61ZsyavfvWrd3pfS5Ysycte9rKccMIJnavaHR0dnU96HDBgQDZt2rRLc61a\ntWpX/wu7rK2tbY/fJ1Shra2tS/YR9l47vr/5uoDuZd+rbbsc1NOmTcv555+fd73rXZk8eXIOPfTQ\nNDY25uGHH87ixYvz4IMP5jOf+UyS5LLLLsttt92WD3/4wzu9r8WLF6euri7f/e538+CDD2b69On5\n/e9/33n95s2b09TUtEtzdcXLnf/xF4bnvsQ67G0aGxu7ZB9h77VjQcTXBXQv+97e74V+GdrloD7x\nxBMzd+7cXHHFFZkzZ07nanJHR0de9apX5brrrsvJJ5+c3//+97ntttty6qmnZurUqTu9ry9/+cud\n21OmTMlll12Wq666KitXrsyoUaOyfPnyHH/88bs6GgAAVGa3XtjlrW99a9761rfmF7/4RR555JG0\nt7dnyJAhOeigg/K1r30t73znO3PXXXdl9erV6du3724NMn369MycOTPXXntthg4dmvHjx+/W7QEA\noAov6ZUSjzrqqAwdOjRLly7NDTfckAceeCDt7e3p06dP6urqdium58+f37m9YMGClzIOAABUZreD\n+qc//WmWLFmSe+65Jxs3bkxHR0cOPPDAnH766Zk0aVJXzAgAAD3WLgX1E088ka997Wu5/fbb88tf\n/vJZZ+T48Ic/nH/4h39IQ8NLWuwGAIC92vNWcHt7e5YtW5YlS5bk/vvvT3t7exobG3PiiSdm3Lhx\nOeqoozJx4sS8/vWvF9MAAPRaz1vCb37zm/PUU09l4MCBGTduXMaNG5cxY8Zk4MCBSZK1a9d225AA\nANBTPW9Qb9iwIfvuu29OPfXUjBo1Km9605s6YxoAAPij5w3qL33pS7nrrrty99135ytf+Urq6upy\n7LHH5uSTT864ceO6c0YAAOixnjeoR40alVGjRmXWrFm57777ctddd+W+++5LS0tLrrzyyrz2ta9N\nXV1d/vCHP3TnvAAA0KO86LMJGxsbO4+hbm1tzTe+8Y3cfffdWblyZTo6OjJ9+vQsWbIkEydOzLhx\n4zpfWhMAAHqD3To9x8CBA3P66afn9NNPz//+7//mnnvuyV133ZXvfve7+d73vpempqasXLmyq2YF\nAIAep/6l3vAVr3hFzjnnnCxevDj/+Z//mfPPPz+DBg3ak7MBAECP95KD+k+99rWvzYc//OF84xvf\n2BN3BwAAe409EtQAANBbCWoAACjgNcN3YuPGjemz/em86sk5VY8CL1mf7U9l48Z9qh4DAGqeFWoA\nAChghXonmpqasvHpfll3wMVVjwIv2auenJOmpn5VjwEANc8KNQAAFBDUAABQQFADAEABx1ADPcZ5\n552X9evXVz1GTdvx+Z0wYULFk9S+wYMHZ968eVWPAXQDQQ30GOvXr8+63z2W9n4Dqx6lZtXX9UmS\n/ObJzRVPUtsatrZWPQLQjQQ10KO09xuY3x7/d1WPAUWGfO+LVY8AdCPHUAMAQAFBDQAABQQ1AAAU\nENQAAFBAUAMAQAFBDQAABQQ1AAAUENQAAFBAUAMAQAFBDQAABQQ1AAAUENQAAFBAUAMAQAFBDQAA\nBQQ1AAAUENQAAFBAUAMAQAFBDQAABQQ1AAAUENQAAFBAUAMAQAFBDQAABRqqHgAAqNZ5552X9evX\nVz1GTdvx+Z0wYULFk9S+wYMHZ968ed36MQU1APRy69evz7rHHkv7wP5Vj1Kz6vv88aCA32zeWPEk\nta2hdUs1H7eSjwoA9CjtA/vnt1PfWfUYUGTIzXdX8nEdQw0AAAUENQAAFBDUAABQQFADAEABQQ0A\nAAUENQAAFBDUAABQoLLzUD/zzDO59NJL8/DDD6euri7/+I//mH79+mXGjBmpq6vLkUcemdmzZ6e+\nXvMDANBzVRbU9957b5Jk0aJFWblyZT796U+no6Mjzc3NGTVqVGbNmpWlS5dm3LhxVY0IAAAvqrLl\n35NOOimXX355kuTRRx9NU1NT1qxZk5EjRyZJxowZkxUrVlQ1HgAA7JJKX3q8oaEh06dPzze/+c18\n9rOfzQMPPJC6urokyYABA7Jp06YXvY9Vq1bt8bna2tr2+H1CFdra2rpkH+kq9j1qyd60/9n3qCVV\n7HuVBnWSXHnllfnYxz6W9773vdm6dWvn5Zs3b05TU9OL3n7EiBF7fKbGxsYkW1/0/aCna2xs7JJ9\npKs0NjYmm7dVPQbsEXvT/tfY2Jhse7rqMWCP6Kp974UivbJDPu64447ceOONSZL+/funrq4uxxxz\nTFauXJkkWb58eY477riqxgMAgF1S2Qr1ySefnIsvvjhnnXVW2tvbc8kll+Twww/PzJkzc+2112bo\n0KEZP358VeMBAMAuqSyo991331x33XXPuXzBggUVTAMAAC+NkzwDAECByp+UCLDDxo0b07B1S4Z8\n74tVjwJFGra2ZuPGZ6oeA+gmVqgBAKCAFWqgx2hqaspTz/TJb4//u6pHgSJDvvfFNDUNqHoMoJtY\noQYAgAKCGgAACghqAAAoIKgBAKCAoAYAgAKCGgAACghqAAAoIKgBAKCAoAYAgAJeKfF59Nn+VF71\n5Jyqx6hZ9dv/kCTZXr9vxZPUrj7bn0oyuOoxAKDmCeqdGDxYhHS19eufSpIMHtyv4klq2WBfywDQ\nDQT1TsybN6/qEWrehAkTkiRLliypeBIAgDKOoQYAgAKCGgAACghqAAAoIKgBAKCAoAYAgAKCGgAA\nCghqAAAoIKgBAKCAoAYAgAKCGgAACghqAAAoIKgBAKCAoAYAgAKCGgAACghqAAAoIKgBAKBAQ9UD\nAADV2rhxYxq2bMmQm++uehQo0tC6JRuf6f6Pa4UaAAAKWKEGgF6uqakpT/VJfjv1nVWPAkWG3Hx3\nmgY0dfvHtUINAAAFBDUAABQQ1AAAUMAx1ECP0rC1NUO+98Wqx6hZ9e1PJ0m2N+xT8SS1rWFra5IB\nVY8BdBNBDfQYgwcPrnqEmrd+/eYkyeADxF7XGuDrGXoRQQ30GPPmzat6hJo3YcKEJMmSJUsqngSg\ndjiGGgAACghqAAAoIKgBAKCAoAYAgAKCGgAACghqAAAoIKgBAKCAoAYAgAKCGgAACghqAAAoIKgB\nAKCAoAYAgAKCGgAACjRU8UG3bduWSy65JGvXrk1bW1s++MEP5ogjjsiMGTNSV1eXI488MrNnz059\nvd4HAKBnqySo77zzzgwaNChXXXVVNmzYkNNOOy2vf/3r09zcnFGjRmXWrFlZunRpxo0bV8V4AACw\nyypZAn7b296WCy+8MEnS0dGRPn36ZM2aNRk5cmSSZMyYMVmxYkUVowEAwG6pJKgHDBiQgQMHprW1\nNRdccEGam5vT0dGRurq6zus3bdpUxWgAALBbKjnkI0nWrVuXD33oQznzzDNz6qmn5qqrruq8bvPm\nzWlqatql+1m1alVXjUgXamtrS+Lxg+5m32NndnxdQC1oa2vr9u9xlQT1448/nqlTp2bWrFkZPXp0\nkuToo4/OypUrM2rUqCxfvjzHH3/8Lt3XiBEjunJUukhjY2MSjx90N/seO9PY2Jhse7rqMWCPaGxs\n7JLvcS8U6ZUc8jFv3rxs3Lgxn/vc5zJlypRMmTIlzc3Nuf766zNp0qRs27Yt48ePr2I0AADYLZWs\nUF966aW59NJLn3P5ggULKpgGAABeOid6BgCAAoIaAAAKCGoAACggqAEAoICgBgCAAoIaAAAKCGoA\nAChQ2UuPAwA9R0Prlgy5+e6qx6hZ9U//8eXdt+/TWPEkta2hdUsyoKn7P263f0QAoEcZPHhw1SPU\nvPWb1ydJBlcQe73KgKZKvp4FNQD0cvPmzat6hJo3YcKEJMmSJUsqnoSu4BhqAAAoIKgBAKCAoAYA\ngAKCGgAACghqAAAoIKgBAKCAoAYAgAKCGgAACghqAAAoIKgBAKCAoAYAgAKCGgAACghqAAAoIKgB\nAKCAoAYAgAKCGgAACghqAAAoIKgBAKCAoAYAgAKCGgAACghqAAAoIKgBAKCAoAYAgAKCGgAACghq\nAAAoIKgBAKCAoAYAgAKCGgAACghqAAAoIKgBAKCAoAYAgAKCGgAACghqAAAoIKgBAKCAoAYAgAKC\nGgAACghqAAAoIKgBAKCAoAYAgAKCGgAACghqAAAoIKgBAKCAoAYAgAKCGgAAClQa1D/60Y8yZcqU\nJMkjjzySM844I2eeeWZmz56d7du3VzkaAADsksqC+gtf+EIuvfTSbN26NUkyZ86cNDc3Z+HCheno\n6MjSpUurGg0AAHZZZUF9yCGH5Prrr+98e82aNRk5cmSSZMyYMVmxYkVVowEAwC6rLKjHjx+fhoaG\nzrc7OjpSV1eXJBkwYEA2bdpU1WgAALDLGl78XbpHff3/b/vNmzenqalpl263atWqrhqJLtTW1pbE\n4wfdzb4H1bDv1bYeE9RHH310Vq5cmVGjRmX58uU5/vjjd+l2I0aM6OLJ6AqNjY1JPH7Q3ex7UA37\n3t7vhX4Z6jGnzZs+fXquv/76TJo0Kdu2bcv48eOrHgkAAF5UpSvUQ4YMyVe/+tUkyWGHHZYFCxZU\nOQ4AAOy2HrNCDQAAeyNBDQAABQQ1AAAUENQAAFBAUAMAQAFBDQAABQQ1AAAUENQAAFBAUAMAQAFB\nDQAABQRqzFy3AAAMLUlEQVQ1AAAUENQAAFBAUAMAQAFBDQAABQQ1AAAUENQAAFBAUAMAQAFBDQAA\nBQQ1AAAUENQAAFBAUAMAQAFBDQAABQQ1AAAUENQAAFBAUAMAQAFBDQAABQQ1AAAUENQAAFBAUAMA\nQAFBDQAABQQ1AAAUENQAAFCgoeoBAPZmc+fOzbJly6oeY5etX78+STJhwoSKJ9k9Y8eOzbRp06oe\nA2CnBDVAL9K/f/+qRwCoOYIaoMC0adOsnAL0co6hBuhFrr766lx99dVVjwFQUwQ1QC9yxx135I47\n7qh6DICaIqgBeomrr74627dvz/bt261SA+xBghqgl/jTlWmr1AB7jqAGAIACghqglzjttNN2ug1A\nGUEN0Et87GMf2+k2AGWchxqgF2lo8G0fYE+zQg3QSyxatCjt7e1pb2/PokWLqh4HoGYIaoBe4uab\nb97pNgBlBDUAABQQ1AC9xNSpU3e6DUAZQQ3QS0yePDl9+/ZN3759M3ny5KrHAagZnu4N0IvU1dVV\nPQJAzbFCDdBLLFq0KG1tbWlra3OWD4A9SFAD9BLO8gHQNRzyUQPmzp2bZcuWVT3Gblm/fn2SZMKE\nCRVPsnvGjh2badOmVT0GvCRbt27d6TYAZQQ1lejfv3/VI0Cv09HRsdNtAMoI6howbdo0q6bAi9q+\nfftOtwEo06OCevv27bnsssvyi1/8Io2Njfmnf/qnHHrooVWPBVATDjrooDz66KOd27A329sOd3So\nY23rUU9K/Na3vpW2trb827/9Wy666KJ86lOfqnokgJpxySWX7HQb6Hr9+/d3uGMN61Er1KtWrcoJ\nJ5yQJDn22GPz05/+tOKJAGrH8OHD8+pXv7pzG/ZmDnekJ+lRQd3a2pqBAwd2vt2nT5+0t7enoaFH\njQmw17IyDbDn9ahSHThwYDZv3tz59vbt2180pletWtXVYwHUHN87AfacHhXUw4cPz7333pt3vOMd\n+eEPf5jXve51L3qbESNGdMNkAAD0Zi+0ENGjgnrcuHF54IEHMnny5HR0dOSKK66oeiQAAHhBPSqo\n6+vr88lPfrLqMQAAYJf1qNPmAQDA3kZQAwBAAUENAAAFBDUAABQQ1AAAUEBQAwBAAUENAAAFBDUA\nABQQ1AAAUEBQAwBAAUENAAAFBDUAABQQ1AAAUEBQAwBAAUENAAAFBDUAABQQ1AAAUEBQAwBAgYaq\nByi1atWqqkcAAKAXq+vo6OioeggAANhbOeQDAAAKCGoAACggqAEAoICgBgCAAoIaAAAKCGoq8aMf\n/ShTpkypegzoVbZt25aPf/zjOfPMMzNx4sQsXbq06pGgV3jmmWdy8cUXZ/LkyTnjjDPy3//931WP\nxB6215+Hmr3PF77whdx5553p379/1aNAr3LnnXdm0KBBueqqq7Jhw4acdtpp+eu//uuqx4Kad++9\n9yZJFi1alJUrV+bTn/50/uVf/qXiqdiTrFDT7Q455JBcf/31VY8Bvc7b3va2XHjhhUmSjo6O9OnT\np+KJoHc46aSTcvnllydJHn300TQ1NVU8EXuaFWq63fjx4/Pb3/626jGg1xkwYECSpLW1NRdccEGa\nm5srngh6j4aGhkyfPj3f/OY389nPfrbqcdjDrFAD9CLr1q3L2WefnXe961059dRTqx4HepUrr7wy\n3/jGNzJz5sz84Q9/qHoc9iBBDdBLPP7445k6dWo+/vGPZ+LEiVWPA73GHXfckRtvvDFJ0r9//9TV\n1aW+XoLVEo8mQC8xb968bNy4MZ/73OcyZcqUTJkyJU8//XTVY0HNO/nkk/Ozn/0sZ511Vs4999xc\ncskl2Weffaoeiz2orqOjo6PqIQAAYG9lhRoAAAoIagAAKCCoAQCggKAGAIACghoAAAp4pUSAHmTG\njBm5/fbbn3VZfX19+vfvn8MPPzxnnnlm3v3ud+/y/Y0dOzYHH3xw5s+fv6dHBeD/EdQAPdDFF1+c\nAw44IEnS0dGR1tbW3HnnnZkxY0aefPLJTJ06teIJAdhBUAP0QCeddFKGDBnyrMsmTpyYd7zjHbnh\nhhvyt3/7t2lsbKxoOgD+lGOoAfYS++yzT8aOHZvW1tY89NBDVY8DwP9jhRpgL1JXV5ckeeaZZ5Ik\nP/rRjzJ37tysXr06ffr0yRvf+MZcdNFFOeqoo3Z6+46OjixatCiLFy/Or371q7S3t+fggw/OhAkT\n8oEPfKDz/p966qnMmTMn3/ve9/L444/noIMOytvf/vZMmzYt/fr1S5K0tbXlqquuyrJly/LYY4/l\n5S9/ecaOHZvm5ubsv//+3fDZAOgZBDXAXmL79u35r//6rzQ2Nubwww/PD37wg5xzzjkZPHhw3v/+\n92efffbJrbfemrPPPjuLFy9+ziEjSfKZz3wm8+bNy7vf/e68973vzebNm3PHHXfkmmuuyYABA3LW\nWWclSZqbm/Ozn/0sZ599dgYPHpzVq1fn85//fDZs2JDLL788SfLJT34yd999d84+++y85jWvyUMP\nPZQvf/nLeeSRR3LzzTd36+cGoEqCGqAH2rhxY37/+98n+eNq9Nq1a3PLLbfk5z//ec4555wMGDAg\nV155ZQYNGpTFixd3PoHxxBNPzDve8Y4sXLgwn/jEJ551n9u2bcuCBQtyyimn5FOf+lTn5e95z3sy\nevTofOc738lZZ52VJ554IitWrMgnPvGJnHvuuZ3v09HRkd/85jedt7vrrrty+umn56Mf/WjnZfvu\nu2++853vZPPmzRkwYECXfX4AehJBDdAD7ezUeI2NjZkyZUouuuiiPPHEE/nxj3+cqVOndsZ0khx2\n2GFZvHhxXvWqVz3n9n379s2KFSuybdu2Z13+5JNPZuDAgfnDH/6QJNlvv/2y7777ZuHChRkyZEhO\nOOGE7LvvvpkzZ86zbnfQQQfl61//eo455picdNJJaWpqSnNzc5qbm/fEpwBgryGoAXqgq666Kgce\neGCSP56HuqmpKYcffnjn8ctr165Nkhx66KHPue3RRx/9vPfbt2/ffPvb387SpUvz8MMP55FHHslT\nTz2V5I/HVyd/DPdPfvKTmTlzZi644II0NjZm5MiROfnkk3Paaad1znDZZZelubk5F198cWbOnJlj\njz0248aNy+mnn5799ttvz30yAHo4QQ3QAw0fPnynx0DvsH379iT//0mKu6KjoyPnn39+7r333owY\nMSLDhg3LpEmT8qY3vSnve9/7nvW+p556ak444YR861vfyn333ZcVK1bk/vvvz8KFC/Pv//7vaWxs\nzOjRo3Pvvfd2/nvggQcyZ86c3HLLLVmyZEle9rKXvbT/PMBeRlAD7IV2HNLx61//+jnXXXXVVdl/\n//3z93//98+6/Ac/+EHuvffenH/++bnwwgs7L29vb8+GDRvymte8JkmyefPmPPjggznyyCMzceLE\nTJw4sfOMHrfeemvuv//+vPnNb86DDz6Ygw46KKecckpOOeWUbN++PV/84hfzz//8z7nnnnsyZcqU\nLvwMAPQczkMNsBd65Stfmde//vW555570tra2nn5b37zm9x66615/PHHn3ObDRs2JEmOOOKIZ13+\n1a9+NVu2bEl7e3uS5KGHHspZZ52V2267rfN9GhsbOw8l6dOnT5588slMmjQpN954Y+f71NfX5y//\n8i87twF6CyvUAHupiy++OO9///tz+umn5z3veU/q6+uzYMGCNDU15QMf+MBz3n/YsGEZOHBg5syZ\nk7Vr12b//ffPypUr8/Wvfz39+vXL5s2bkyRvfOMbc9xxx+XTn/501q1bl6OOOirr1q3LggULMnTo\n0IwePTqNjY059dRTs3DhwmzZsiXDhg3Lhg0bsmDBghx44IF5+9vf3t2fDoDK1HXseBYKAJWbMWNG\nbr/99ixduvQFj6HeYdWqVfnsZz+bH//4x+nXr1/e9KY35eMf/3gOOeSQJMnYsWNz8MEHZ/78+Z3v\nf/XVV+fnP/95Ghsbc9hhh+Xss8/Oj3/849x6661Zvnx5DjzwwGzYsCFz587Nvffem/Xr12f//ffP\nW97yllx44YV5xStekSR5+umn8/nPfz733HNP1q1bl/79+2f06NH5yEc+stMnSwLUKkENAAAFHOQG\nAAAFBDUAABQQ1AAAUEBQAwBAAUENAAAFBDUAABQQ1AAAUEBQAwBAAUENAAAFBDUAABT4v2D3gY1I\npo9ZAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x2acbc9f5f98>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(12, 10))\n",
    "plt.xlabel(\"Passenger Class\",fontsize=18)\n",
    "plt.ylabel(\"Age\",fontsize=18)\n",
    "sns.boxplot(x='Pclass',y='Age',data=train,palette='winter')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.text.Text at 0x2acbcc993c8>"
      ]
     },
     "execution_count": 100,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEZCAYAAACaWyIJAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nhBAi5ygICCFEzlEQEEKInPt/zZkLM45eTnAAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x2acbcbb9160>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "f_class_Age=train.groupby('Pclass')['Age'].mean()\n",
    "f_class_Age = pd.DataFrame(f_class_Age)\n",
    "f_class_Age.plot.bar(y='Age')\n",
    "plt.title(\"Average age of passengers by class\",fontsize=17)\n",
    "plt.ylabel(\"Age (years)\", fontsize=17)\n",
    "plt.xlabel(\"Passenger class\", fontsize=17)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Data wrangling (impute and drop)\n",
    "* Impute age (by averaging)\n",
    "* Drop unncessary features\n",
    "* Convert categorical features to dummy variables"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Define a function to impute (fill-up missing values) age feature"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 101,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "a=list(f_class_Age['Age'])\n",
    "\n",
    "def impute_age(cols):\n",
    "    Age = cols[0]\n",
    "    Pclass = cols[1]\n",
    "    \n",
    "    if pd.isnull(Age):\n",
    "\n",
    "        if Pclass == 1:\n",
    "            return a[0]\n",
    "\n",
    "        elif Pclass == 2:\n",
    "            return a[1]\n",
    "\n",
    "        else:\n",
    "            return a[2]\n",
    "\n",
    "    else:\n",
    "        return Age"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Apply the above-defined function and plot the count of numeric features**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 102,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.text.Text at 0x2acbccf43c8>"
      ]
     },
     "execution_count": 102,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXUAAAE5CAYAAABvZ7DfAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nFfzrruS0eAAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x2acbcbede48>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "train['Age'] = train[['Age','Pclass']].apply(impute_age,axis=1)\n",
    "d=train.describe()\n",
    "dT=d.T\n",
    "dT.plot.bar(y='count')\n",
    "plt.title(\"Bar plot of the count of numeric features\",fontsize=17)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Drop the 'Cabin' feature and any other null value"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>PassengerId</th>\n",
       "      <th>Survived</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Name</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Braund, Mr. Owen Harris</td>\n",
       "      <td>male</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>A/5 21171</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
       "      <td>female</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>PC 17599</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Heikkinen, Miss. Laina</td>\n",
       "      <td>female</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>STON/O2. 3101282</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n",
       "      <td>female</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>113803</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Allen, Mr. William Henry</td>\n",
       "      <td>male</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>373450</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   PassengerId  Survived  Pclass  \\\n",
       "0            1         0       3   \n",
       "1            2         1       1   \n",
       "2            3         1       3   \n",
       "3            4         1       1   \n",
       "4            5         0       3   \n",
       "\n",
       "                                                Name     Sex   Age  SibSp  \\\n",
       "0                            Braund, Mr. Owen Harris    male  22.0      1   \n",
       "1  Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0      1   \n",
       "2                             Heikkinen, Miss. Laina  female  26.0      0   \n",
       "3       Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0      1   \n",
       "4                           Allen, Mr. William Henry    male  35.0      0   \n",
       "\n",
       "   Parch            Ticket     Fare Embarked  \n",
       "0      0         A/5 21171   7.2500        S  \n",
       "1      0          PC 17599  71.2833        C  \n",
       "2      0  STON/O2. 3101282   7.9250        S  \n",
       "3      0            113803  53.1000        S  \n",
       "4      0            373450   8.0500        S  "
      ]
     },
     "execution_count": 103,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train.drop('Cabin',axis=1,inplace=True)\n",
    "train.dropna(inplace=True)\n",
    "train.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Drop other unnecessary features like 'PassengerId', 'Name', 'Ticket'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Survived</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>female</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>female</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>female</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Survived  Pclass     Sex   Age  SibSp  Parch     Fare Embarked\n",
       "0         0       3    male  22.0      1      0   7.2500        S\n",
       "1         1       1  female  38.0      1      0  71.2833        C\n",
       "2         1       3  female  26.0      0      0   7.9250        S\n",
       "3         1       1  female  35.0      1      0  53.1000        S\n",
       "4         0       3    male  35.0      0      0   8.0500        S"
      ]
     },
     "execution_count": 105,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train.drop(['PassengerId','Name','Ticket'],axis=1,inplace=True)\n",
    "train.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Convert categorial feature like 'Sex' and 'Embarked' to dummy variables"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Use pandas 'get_dummies()' function**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 109,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "sex = pd.get_dummies(train['Sex'],drop_first=True)\n",
    "embark = pd.get_dummies(train['Embarked'],drop_first=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Now drop the 'Sex' and 'Embarked' columns and concatenate the new dummy variables**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 110,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Survived</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Fare</th>\n",
       "      <th>male</th>\n",
       "      <th>Q</th>\n",
       "      <th>S</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Survived  Pclass   Age  SibSp  Parch     Fare  male  Q  S\n",
       "0         0       3  22.0      1      0   7.2500     1  0  1\n",
       "1         1       1  38.0      1      0  71.2833     0  0  0\n",
       "2         1       3  26.0      0      0   7.9250     0  0  1\n",
       "3         1       1  35.0      1      0  53.1000     0  0  1\n",
       "4         0       3  35.0      0      0   8.0500     1  0  1"
      ]
     },
     "execution_count": 110,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train.drop(['Sex','Embarked'],axis=1,inplace=True)\n",
    "train = pd.concat([train,sex,embark],axis=1)\n",
    "train.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This data set is now ready for logistic regression analysis!"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Logistic Regression model fit and prediction\n",
    "\n",
    "Let's start by splitting our data into a training set and test set (there is another test.csv file that you can play around with in case you want to use all this data for training)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 187,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "X_train, X_test, y_train, y_test = train_test_split(train.drop('Survived',axis=1), \n",
    "                                                    train['Survived'], test_size=0.30, \n",
    "                                                    random_state=111)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### F1-score as a fucntion of regularization (penalty) parameter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 193,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYoAAAEfCAYAAABf1YHgAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nSUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x2acbec964e0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.metrics import classification_report\n",
    "nsimu=201\n",
    "penalty=[0]*nsimu\n",
    "logmodel=[0]*nsimu\n",
    "predictions =[0]*nsimu\n",
    "class_report = [0]*nsimu\n",
    "f1=[0]*nsimu\n",
    "for i in range(1,nsimu):\n",
    "        logmodel[i] =(LogisticRegression(C=i/1000,tol=1e-4, max_iter=100,n_jobs=4))\n",
    "        logmodel[i].fit(X_train,y_train)\n",
    "        predictions[i] = logmodel[i].predict(X_test)\n",
    "        class_report[i] = classification_report(y_test,predictions[i])\n",
    "        l=class_report[i].split()\n",
    "        f1[i] = l[len(l)-2]\n",
    "        penalty[i]=1000/i\n",
    "\n",
    "plt.scatter(penalty[1:len(penalty)-2],f1[1:len(f1)-2])\n",
    "plt.title(\"F1-score vs. regularization parameter\",fontsize=20)\n",
    "plt.xlabel(\"Penalty parameter\",fontsize=17)\n",
    "plt.ylabel(\"F1-score on test data\",fontsize=17)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### F1-score as a function of test set size (fraction)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 197,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYwAAAEfCAYAAABSy/GnAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nwWAYhmEkwQaDYRiGkcT/A1bF4GYpcXNuAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x2acbcc90d30>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "nsimu=101\n",
    "class_report = [0]*nsimu\n",
    "f1=[0]*nsimu\n",
    "test_fraction =[0]*nsimu\n",
    "for i in range(1,nsimu):\n",
    "        X_train, X_test, y_train, y_test = train_test_split(train.drop('Survived',axis=1), \n",
    "                                                    train['Survived'], test_size=0.1+(i-1)*0.007, \n",
    "                                                    random_state=111)\n",
    "        logmodel =(LogisticRegression(C=1,tol=1e-4, max_iter=1000,n_jobs=4))\n",
    "        logmodel.fit(X_train,y_train)\n",
    "        predictions = logmodel.predict(X_test)\n",
    "        class_report[i] = classification_report(y_test,predictions)\n",
    "        l=class_report[i].split()\n",
    "        f1[i] = l[len(l)-2]\n",
    "        test_fraction[i]=0.1+(i-1)*0.007\n",
    "\n",
    "plt.plot(test_fraction[1:len(test_fraction)-2],f1[1:len(f1)-2])\n",
    "plt.title(\"F1-score vs. test set size (fraction)\",fontsize=20)\n",
    "plt.xlabel(\"Test set size (fraction)\",fontsize=17)\n",
    "plt.ylabel(\"F1-score on test data\",fontsize=17)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### F1-score as a function of random seed of test/train split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 201,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAY4AAAEfCAYAAABWPiGaAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nBFb4/QPXAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x2acbec576a0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "nsimu=101\n",
    "class_report = [0]*nsimu\n",
    "f1=[0]*nsimu\n",
    "random_init =[0]*nsimu\n",
    "for i in range(1,nsimu):\n",
    "        X_train, X_test, y_train, y_test = train_test_split(train.drop('Survived',axis=1), \n",
    "                                                    train['Survived'], test_size=0.3, \n",
    "                                                    random_state=i+100)\n",
    "        logmodel =(LogisticRegression(C=1,tol=1e-5, max_iter=1000,n_jobs=4))\n",
    "        logmodel.fit(X_train,y_train)\n",
    "        predictions = logmodel.predict(X_test)\n",
    "        class_report[i] = classification_report(y_test,predictions)\n",
    "        l=class_report[i].split()\n",
    "        f1[i] = l[len(l)-2]\n",
    "        random_init[i]=i+100\n",
    "\n",
    "plt.plot(random_init[1:len(random_init)-2],f1[1:len(f1)-2])\n",
    "plt.title(\"F1-score vs. random initialization seed\",fontsize=20)\n",
    "plt.xlabel(\"Random initialization seed\",fontsize=17)\n",
    "plt.ylabel(\"F1-score on test data\",fontsize=17)\n",
    "plt.show()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}