{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# pandas\n",
    "import pandas as pd\n",
    "from pandas import Series,DataFrame\n",
    "\n",
    "# numpy, matplotlib, seaborn\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "sns.set_style('whitegrid')\n",
    "%matplotlib inline\n",
    "\n",
    "# machine learning\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.svm import SVC, LinearSVC\n",
    "from sklearn.ensemble import RandomForestClassifier"
   ]
  },
  {
   "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>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": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# get titanic & test csv files as a DataFrame\n",
    "titanic_df = pd.read_csv(\"./titanic/train.csv\")\n",
    "test_df    = pd.read_csv(\"./titanic/test.csv\")\n",
    "\n",
    "titanic_df.head()"
   ]
  },
  {
   "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 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",
      "None\n",
      "----------------------------\n",
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 418 entries, 0 to 417\n",
      "Data columns (total 11 columns):\n",
      "PassengerId    418 non-null int64\n",
      "Pclass         418 non-null int64\n",
      "Name           418 non-null object\n",
      "Sex            418 non-null object\n",
      "Age            332 non-null float64\n",
      "SibSp          418 non-null int64\n",
      "Parch          418 non-null int64\n",
      "Ticket         418 non-null object\n",
      "Fare           417 non-null float64\n",
      "Cabin          91 non-null object\n",
      "Embarked       418 non-null object\n",
      "dtypes: float64(2), int64(4), object(5)\n",
      "memory usage: 36.0+ KB\n",
      "None\n"
     ]
    }
   ],
   "source": [
    "print (titanic_df.info())\n",
    "print(\"----------------------------\")\n",
    "print (test_df.info())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "# drop unnecessary columns, these columns won't be useful in analysis and prediction\n",
    "titanic_df = titanic_df.drop(['Name','Ticket'], axis=1)\n",
    "test_df    = test_df.drop(['Name','Ticket'], axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Index(['PassengerId', 'Survived', 'Pclass', 'Sex', 'Age', 'SibSp', 'Parch',\n",
      "       'Fare', 'Cabin', 'Embarked'],\n",
      "      dtype='object')\n",
      "----------------------------\n",
      "Index(['PassengerId', 'Pclass', 'Sex', 'Age', 'SibSp', 'Parch', 'Fare',\n",
      "       'Cabin', 'Embarked'],\n",
      "      dtype='object')\n"
     ]
    }
   ],
   "source": [
    "print (titanic_df.columns)\n",
    "print ('----------------------------')\n",
    "print (test_df.columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\seaborn\\categorical.py:3666: UserWarning: The `factorplot` function has been renamed to `catplot`. The original name will be removed in a future release. Please update your code. Note that the default `kind` in `factorplot` (`'point'`) has changed `'strip'` in `catplot`.\n",
      "  warnings.warn(msg)\n",
      "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\seaborn\\categorical.py:3672: UserWarning: The `size` paramter has been renamed to `height`; please update your code.\n",
      "  warnings.warn(msg, UserWarning)\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 864x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA3sAAAE+CAYAAAA0xwkVAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDMuMC4zLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvnQurowAAIABJREFUeJzt3XmYXHWd7/F3d9JUWBKUiCwDMaDjd1pRHAIGBExAlEHQqCNe8QoIw0WciCwuqGwRnauyCggqiwsuuARxUAdkRgQhBHBaccLQfCGgLMNFQjQECGnSSd8/qlrLkHS6k6o+Xafer+fJw9nq1KdPml9+33N+55yOgYEBJEmSJEnl0ll0AEmSJElS41nsSZIkSVIJWexJkiRJUglZ7EmSJElSCVnsSZIkSVIJWexJkiRJUglZ7EmSJElSCVnsSZIkSVIJWexJkiRJUgmNLzrASN15550DlUql6BiSGmjZsmVPTJs2bcuic2wI2yapfMrQNoHtk1RGw22fWq7Yq1QqdHd3Fx1DUgP19PQ8WHSGDWXbJJVPGdomsH2Symi47ZPDOCVJkiSphCz2JEmSJKmELPYkSZIkqYRa7p49SZJUrBUrVvDII4+wfPnyoqM0xIQJE9huu+3o6uoqOookNZTFniRJGpFHHnmEiRMnMnXqVDo6OoqOs0EGBgZYvHgxjzzyCDvssEPRcSSpoRzGKUmSRmT58uVMnjy55Qs9gI6ODiZPnlyaq5SSVM9iT5IkjVgZCr1BZfpZJKmexZ4kSZIklZDFniRJ2mC33347e+yxB4ceeuif/3zoQx9a5+d++MMfcvbZZ6/Xd+6777709fWN6DN9fX3su+++6/V9ktRqfECLJElqiN13353zzjuv6BiSpBqLPUmS1DSHHnooEcF9993HJptswq677sott9zC0qVL+epXvwrAnXfeyeGHH87TTz/Nsccey8yZM7nuuuv49re//ef9nH/++dx3332cffbZdHV18a53vevP66688krmzZvHueeey5133sl5553HuHHj2H777TnjjDN47rnn+MhHPsLSpUuZMmXKqB8DSSpK6Yq9vhUrqXSNKzpG4TwOkjR2FN0mj9b333bbbRx66KF/np8xYwYAr371qznllFP4p3/6JyZMmMDXvvY1TjrpJH71q18BsPHGG3PJJZfwxz/+kYMPPpjXv/71/P73v+eSSy5h44035rTTTuOWW25hq622oq+vjx/84AcAXHDBBXzzm9+kt7eX888/n87OTk499VS+853vMHnyZL7whS9w9dVX89xzz/Hyl7+cE044gd/+9rfcfvvtTT8Waj8D/X10jK8UHaNwHoexpXTFXqVrHNM+ekXRMQrXc9ZhRUeQJNUU/W/TaP2bsKZhnDfddBOvfOUrAZg0aRIve9nL/jw9eL/dtGnT/vwKhIkTJ7JkyRImT57MSSedxKabbsoDDzzAa17zGoDnvQtv/vz5jBs3jnHjxrF48WIef/xxjj/+eKD6iog999yTP/3pT+y9994A7LzzzowfX7ruj8aAjvEVHjrjVUXHKNyU0xYUHUF1fECLJEkq1IIF1c7hokWLWLZsGV1dXVxwwQWcd955fOYzn6FSqTAwMABAZ+dfd10uvvhiJk2axJVXXskLX/hCtt56ay6++GK++c1vcswxxzB9+nR23HFH7rzzTgDuvvtu+vv7R/cHlKSCeGpLkiQ1xOrDOIFhvax8+fLlHHbYYSxbtowzzjiDzTbbjF122YW3v/3tbLLJJkyaNInHH3+c7bbbbo2fP+WUUzj44IPZY489OPnkkzn66KMZGBhg00035cwzz2S33XbjE5/4BIcccgg77rgjXV1dDfl5JWmss9iTJEkbbPr06cyfP3/IbeqHeJ588sl/nn7HO97xvG3PP//8tX7PoBtuuAGASqXCv//7vwMwdepU9tprr+d97qyzzhoymySVkcM4JUmSJKmELPYkSZIkqYQs9iRJkiSphCz2JEmSJKmELPYkSZIkqYQs9iRJUsP1rVg5pvcnSe3AVy9IkqSGq3SNY9pHr2jY/nrOOmyd21xyySXceuutdHZ20tHRwQknnMBOO+3UsAyS1Gos9iRJUstbuHAhN9xwA1deeSUdHR309vZy0kkncc011xQdTZIK4zBOSZLU8rbYYgseffRR5s6dyx/+8Ae6u7uZO3du0bEkqVBe2ZPUdiLixUAP8EagH/g6MADcBczOzFURcTpwYG398Zl5R0FxJQ3DFltswZe+9CW+9a1vcdFFFzFhwgROOOEE9t9//6KjSVJhLPYktZWI6AK+AjxbW3QucEpm3hgRXwZmRcSDwAxgOrA9cBWwWxF5JQ3Pgw8+yGabbcZnP/tZABYsWMDRRx/N9OnTecELXlBwOkkqRtOKvYj4BPBWYCPgYuAmPHsuqXhnA18GPlGbn0a1fQK4FngTkMD1mTkAPBQR4yNiy8xctLad9vX10dvb28TYamXd3d1FR2jo7+eKFSt49tlnh9xm4403btj3DRrqOxcsWMD3v/99LrjgAiqVCltvvTWbbropzz333DqzQvVn8v9hSWXTlGIvImYCrwP2BDYBPoJnzyUVLCLeByzKzJ/VTkgBdNSKOoCngM2BScDiuo8OLl9rsVepVMZEh15am0b+fvb29q6zmOtbsXJYT9Acrr4VK4f8zoMOOoiHH36Yww47jE022YSBgQE+/vGP8+IXv3hY++/q6nreMerp6dmgzJJUtGZd2dsfWABcTbXT9FHg/zAKZ8/tbP2FZyil5zkSGIiI/YDXAFcA9T3BicASYGltevXlkoap0jVu1Pf3gQ98gA984AMN/V5JamXNKvZeBLwEOAjYAbgG6PTs+ejyOKlVjNbZ88x8/eB0RNwIHAOcFREzM/NG4ADgF8BC4MyIOBvYjmr79cSohJQkSWqQZhV7i4F7MvM5ICNiOdVhmoM8ey5prPgwcGlEbAT0AnMzc2VE3AzMp/qKmtlFBpQkSVofzSr2bgGOi4hzgW2ATYGfe/Zc0liRmTPrZmesYf0cYM4oxZEkSWq4phR7mfmTiHg9cAd/OSv+Ozx7LkmStFYR0Un1KeY7A33AUZm5sG79BVQfgPdUbdGszHxy1INKaglNe/VCZn5sDYs9ey5JkrR2bwMmZOYeEbE7cA4wq279LsD+joSSNBydRQeQJEnlM9DfN6b3N4btBVwHkJm3AbsOrqhd9ftb4JKImBcRRxYTUVKraNqVPUmS1L46xld46IxXNWx/U05bsM5t7rvvPs466yyeffZZli1bxowZMzj22GPp6OhoWI5RMAmoH5a5MiLGZ2Y/1WcgXEj13cXjgF9ExH9m5n8NtcN1vbZKjeFT0P/C37exw2JPkiS1vKVLl3LiiSdy4YUXMnXqVFauXMlxxx3Hd7/7XQ455JCi443E6k8q76wVegDLgPMzcxlARNxA9d6+IYs9X1ul0ebvW/MN97VVFnuSJKnl/fznP2f69OlMnToVgHHjxvH5z3+erq6uYoON3DzgLcD3a/fs1V/SfDnw3YjYheqtOHsB3xj9iJJahcWeJElqeY8//jjbb7/9Xy3bdNNNC0qzQa4G3hgRtwIdwBERcSKwMDOviYhvA7cBK4ArMvO/C8wqaYyz2JMkSS1v22235e677/6rZQ8//DCPPfYYu+22W0GpRi4zVwHHrLb4nrr1ZwJnjmooSS3Lp3FKkqSWt88++3DzzTfz0EMPAbBixQo+97nPce+99xacTJKK45U9SZLUcAP9fcN6guZI9tcxvrLW9Zttthmf+9znOOWUUxgYGOCZZ55hn3324T3veU/DMkhSq7HYkyRJDTdUYdas/e20005cccUVDf1eSWplDuOUJEmSpBKy2JMkSZKkErLYkyRJkqQSstiTJEmSpBKy2JMkSZKkErLYkyRJDdfX3zem9ydJ7cBXL0iSpIarjK+w54V7Nmx/846dt85t7rrrLs4991yeffZZBgYGmD59OrNnz2ajjTZqWA5JaiVe2ZMkSS3vscce46Mf/SinnnoqV155JVdeeSVdXV189rOfLTqaJBXGYk+SJLW8H/3oRxx88MHssMMOAHR0dDB79mxuuukmli9fXnA6SSqGxZ4kSWp5jz76KNtvv/1fLevo6OBFL3oRixYtKiiVJBXLYk+SJLW8bbfdlocffvivlq1atYpHH32UyZMnF5RKkorlA1oktY2IGAdcCgSwEjgC2Bz4MXBfbbMvZeb3IuJ04ECgHzg+M+8oILKkYZo1axZHHnkk++67L1tssQXHH388W221Ffvssw+bbLJJ0fEkqRAWe5LayVsAMnPPiJgJnEu10Ds3M88Z3CgidgFmANOB7YGrgN1GPa3Uwvr6+4b1BM2R7K8yvrLW9dtssw1nnXUWn/70p3nmmWdYvnw5nZ2dvOhFL2LJkiW84AUvaFgWSWoVFnuS2kZm/igiflKbfQnwB2AaEBExi+rVveOBvYDrM3MAeCgixkfElpnpjT/SMA1VmDVrfzvttBOXX375Xy2755576OrqamgWSWoVFnuS2kpm9kfEN4C3A+8E/ga4LDN7IuJk4HRgCbC47mNPUR3uudZir6+vj97e3uYFV0vr7u4uOkJDfz9XrFjBs88+27D9NdNLXvISgHXmXbFihf8PSyodiz1JbSczD4+Ik4Dbgddl5v/UVl0NXAj8KzCx7iMTqRaAa1WpVMZEh15am0b+fvb29rLxxhs3bH9jQVdX1/OOUU9PT0FpJKkxfBqnpLYREYdGxCdqs8uAVcAPI+K1tWVvAHqAecD+EdEZEVOAzsx8YvQTS2PXwMBA0REapkw/iyTV88qepHbyQ+BrEfFLoIvq/XkPA1+MiOeAx4CjM3NpRNwMzKd6Umx2UYGlsWjChAksXryYyZMn09HRUXScDTIwMMDixYuZMGFC0VEkqeEs9iS1jcx8BnjXGla9bg3bzgHmNDmS1JK22247HnnkkdK8rHzChAlst912RceQpIaz2JMkSSPS1dXFDjvsUHQMSdI6eM+eJEmSJJWQxZ4kSZIklZDFniRJkiSVUNPu2YuI3wBP1mZ/B3wFOB/oB67PzE9FRCdwMbAz0AcclZkLm5VJkiRJktpFU4q9iJgAkJkz65bdCfwj8ADw04jYBZgKTMjMPSJid+AcYFYzMkmSJElSO2nWlb2dgU0i4vrad8wBKpl5P0BE/Izqy4u3Aa4DyMzbImLXde24r6+P3t7eta7v7u7e4PBlMdRxkiRJklRuzSr2lgFnA5cBfwtcCyypW/8UsCMwib8M9QRYGRHjM7N/bTuuVCoWdMPkcVKr6OnpKTqCJElS6TSr2LsXWJiZA8C9EfEksEXd+olUi79NatODOocq9CRJkiRJw9Osp3EeSfX+OyJiW6pF3TMR8dKI6AD2B24G5gFvrm23O7CgSXkkSZIkqa0068re5cDXI+IWYIBq8bcK+DYwjurTOG+PiF8Bb4yIW4EO4Igm5ZEkSZKkttKUYi8znwPes4ZVu6+23SrgmGZkkCRJkqR25kvVJUmSJKmELPYkSZIkqYQs9iRJkiSphCz2JEmSJKmELPYkSZIkqYSa9eoFSZIkjVBEdAIXAzsDfcBRmblwDdv8FPjXzPzy6KeU1Cq8sidJkjR2vA2YkJl7AB8HzlnDNp8BthjVVJJaksWeJEnS2LEXcB1AZt4G7Fq/MiLeCawCrh39aJJajcM4JUmSxo5JwJN18ysjYnxm9kfETsB7gHcCpw13h319ffT29jY4plbX3d1ddIQxw9+3scNiT5IkaexYCkysm+/MzP7a9GHA3wA3AFOB5yLi95l53VA7rFQqFiIaVf6+NV9PT8+wtrPYk9Q2ImIccCkQwErgCKAD+DowANwFzM7MVRFxOnAg0A8cn5l3FBJaUruZB7wF+H5E7A4sGFyRmR8bnI6IOcBj6yr0JLU379mT1E7eApCZe1IdAnVu7c8pmbk31cJvVkTsAswApgPvBi4qJq6kNnQ1sDwibgXOA06IiBMj4q0F55LUgryyJ6ltZOaPIuIntdmXAH+gevXuptqya4E3AQlcn5kDwEMRMT4itszMRaMeWlJbycxVwDGrLb5nDdvNGZVAklqaxZ6ktlJ7yME3gLdTfcjBQbWiDuApYHOqD0hYXPexweVrLfZ8AIKGMhbuX/H3U1Ir6OvvozK+UnSMwjXqOFjsSWo7mXl4RJwE3A5sXLdqIrCE5z8gYXD5WvkABI11/n6O3HAfgCCpcSrjK+x54Z5FxyjcvGPnNWQ/3rMnqW1ExKER8Yna7DKq76r6z4iYWVt2AHAz1Qck7B8RnRExherT8J4Y9cCSJEkbwCt7ktrJD4GvRcQvgS7geKAXuDQiNqpNz83MlRFxMzCf6kmx2UUFliRJWl8We5LaRmY+A7xrDatmrGHbOcCcJkeSJElqGodxSpIkSVIJWexJkiRJUglZ7EmSJElSCVnsSZIkSVIJWexJkiRJUglZ7EmSJElSCVnsSZIkSVIJWexJkiRJUglZ7EmSJElSCVnsSZIkSVIJWexJkiRJUglZ7EmSJElSCVnsSZIkSVIJWexJkiRJUgmNb9aOI+LFQA/wRqAf+DowANwFzM7MVRFxOnBgbf3xmXlHs/JIkiRJUjtpypW9iOgCvgI8W1t0LnBKZu4NdACzImIXYAYwHXg3cFEzskiSJElSO2rWMM6zgS8Dj9bmpwE31aavBfYD9gKuz8yBzHwIGB8RWzYpjyRJkiS1lYYP44yI9wGLMvNnEfGJ2uKOzByoTT8FbA5MAhbXfXRw+aKh9t/X10dvb+9a13d3d69n8vIZ6jhJkiRJKrdm3LN3JDAQEfsBrwGuAF5ct34isARYWpteffmQKpWKBd0weZzUKnp6eoqOIEltq2/FSipd44qOUTiPg8qo4cVeZr5+cDoibgSOAc6KiJmZeSNwAPALYCFwZkScDWwHdGbmE43OI0mSpLWrdI1j2kevKDpG4XrOOqzoCFLDNe1pnKv5MHBpRGwE9AJzM3NlRNwMzKd67+DsUcoiSZIkSaXX1GIvM2fWzc5Yw/o5wJxmZpAkSZKkdjRaV/YkqXC118J8FZgKVIDPAI8APwbuq232pcz8nu8BlSRJrc5iT1I7eS+wODMPjYjJwG+AM4BzM/OcwY1Wew/o9sBVwG4F5JUkSVpvFnuS2skPgLl18/1U3wMaETGL6tW946l7DyjwUESMj4gtM3PIV8NI0qCIeP3a1mXmL0czi6T2ZbEnqW1k5tMAETGRatF3CtXhnJdlZk9EnAycTvU1MCN6D+i63gGq9jYWXoXj7+eo+0Dtvy8FNgJ+Bfw98DQws6BMktqMxZ6kthIR2wNXAxdn5nci4gWZOfiOz6uBC4F/ZYTvAfUdoBrr/P0cuQ15B2hmHgIQET8FZmVmf0SMA37aoHiStE6dRQeQpNESEVsB1wMnZeZXa4t/FhGvrU2/AegB5gH7R0RnREzB94BKWn/b1E2PB15cVBBJ7ccre5LaySeBFwKnRsSptWUnAl+IiOeAx4CjM3Op7wGV1CCXA/8dEXcBr6A6VFySRoXFnqS2kZnHAcetYdXr1rDtHHwPqKQNlJkXRcQ3gb8DHnCUgKTR5DBOSZKkJomIV1K9T+9y4KiIOKjgSJLayLCKvYg4arX5DzUnjiQNn22TpBZwAXAE8ATVgm9OoWkktZUhh3FGxCHAW4F9ImLf2uJxwE5UGy9JGnW2TZJaSWYujIiBzFwUEU8VnUdS+1jXPXvXAf8PmAx8pbZsFXB/M0NJ0jrYNklqFX+MiPcDm0bEu1nHa1wkqZGGLPYy80/AjcCNEfFiYMJwPidJzWTbJKmF/BPVJwE/Aexam1+riOgELgZ2BvqAozJzYd362cD7gAHgjMz8SXNiSyqDYXWMIuIi4EDgUaCDagPzvKfXSdJosm2S1AI+BVyamXcPc/u3ARMyc4+I2B04B5gFEBEvAv4ZeA3Vk1x3R8RPM3OgCbkllcBwz4JPB3bMzFXNDCNJI2TbJGmsmwecGRETga8B38vMZ4fYfi+qQ9XJzNsiYtfBFZn5RETsnJn9ETEVWGKhJ2kowy32FlI9g7SsiVkkaaRsmySNaZk5F5gbEdsA5wFfAF4wxEcmAU/Wza+MiPGZ2V/bX39EfJDqFcNhPZCqr6+P3t7eta7v7u4ezm7awlDHaV08jn/hcWyMDTmOg4Zb7E0BHoyIwTHjA5npUClJRbNtkjSmRcQU4HDgH4FfAwes4yNLgYl1852Dhd6gzPxiRFwCXBsR+2TmL4baYaVSsQM9TB6nxvA4NsZQx7Gnp2dY+xhusXfIMLeTpNFk2yRprLsKuAzYOzOH89qFecBbgO/X7tlbMLgiIgL4LNXCcQXVB7g4jF3SWg232Dt8DcvOaGQQSVoPtk2SxqSI2C4zHwHeS/XhUdvUhnKSmfcO8dGrgTdGxK1UHzx1REScCCzMzGsi4rfA/No+r83Mm5r6g0hqacMt9v5Q+28HsAvQ2Zw4kjQitk2SxqoTa3++vNryAWDftX2o9sCpY1ZbfE/d+k9RvV9PktZpWMVeZn6lfj4irm1OHEkaPtsmSWNVZp5YmzwfuManBksqwnDfs/fyutltqD4UQZIKZdskqQXsB3w6Iq4BLs/MB4oOJKl9DHcYZ/3Z8+XAR5qQRZJGqqXbpr4VK6l0jWvb75faQWZ+MCI2ovpi9C9GxEaZuV/RuSS1h+EO49wnIiYDLwUeyMwnmhtLktat1dumStc4pn30isK+v+eswwr7bqnNvBbYH9gKmFtwFkltZFgPM4iIg4FbgU8Ct0XEe5uaSpKGwbZJ0lgXEXcDs4ErM3NaZn626EyS2sdwh3GeCEzLzKcjYiJwA/Ct5sWSpGGxbZI01n0tM88qOoSk9jTcx5SvysynAWovBF3evEiSNGy2TZLGugMiwptjJRViuFf27o+Ic4BfAnsD9zcvkiQNm22TpLFuS+DRiPgd1XfsDWTm6wrOJKlNDLfYuwSYAbwROITqTcaSVDTbJklj3UFFB5DUvoY7jPNc4OrM/CCwW21ekopm2yRprDt8DX8kaVQMt9jrz8y7AWovA13VvEiSNGy2TZLGuj/U/jwObAdMKTaOpHYy3GGcD0bE/wXmU31XzP80L5IkDduI2qaI6AK+CkwFKsBngLuBr1O9l+YuYHZmroqI04EDgX7g+My8o0k/g6QSy8yv1M9HxLVFZZHUfoZb7B0BHAO8Geil2kFaq9pTpy4FAlhZ+3wHdqgkNdaI2ibgvcDizDy09jL23wB3Aqdk5o0R8WVgVkQ8SPVewOnA9sBVVIeJStKIRMTL62a3xSt7kkbRsIq9zFwOfGEE+31L7XN7RsRMqvfRdGCHSlIDrUfb9ANgbt18PzANuKk2fy3wJiCB6zNzAHgoIsZHxJaZuagBsSW1l69QPdG9BbAY+HCxcSS1k+Fe2RuRzPxRRPykNvsSqmPVD8QOlaQCDb6Tr/YC9rnAKcDZtTYI4Clgc2AS1U4Zqy1fa9vU19dHb2/viPJ0d3ePaPtmGGlmrR//rttPROwCXE71hPZBwJeATYCNiswlqb00pdgDyMz+iPgG8HbgncBBo9GhGgv/oI4V/sMuPV9EbA9cDVycmd+JiDPrVk8ElgBLa9OrL1+rSqXSku1PK2bW+vHveuR6eno25OP/Ahyemc9FxGeAA4CFVE94X9OAeJK0Tk0r9gAy8/CIOAm4Hdi4blXbdaiK4HFSq9jADtWwRcRWwPXABzPz57XFv4mImZl5I9XO2C+odsjOjIizqT49rzMznxiVkJLKojMz/ysitgU2zcxfA0SETw2WNGqG++qFEYmIQyPiE7XZZVQfh/6ftfv3oNqhuhmYB+wfEZ0RMQU7VJKa65PAC4FTI+LGiLiR6lDOT0XEfKrDq+ZmZg/VNmo+1XuJZxeUV1LrGuxj/QPwHwARUeGvT3JLUlM168reD4GvRcQvgS7geKpPyrs0IjaqTc/NzJURMdih6sQOlaQmyszjgOPWsGrGGradA8xpciRJ5fUfETGP6gPo3hoRL6V63973io0lqZ006wEtzwDvWsMqO1SSJKn0MvPzEXEN8HhmLh4s9jLz6qKzSWofTb1nT5IkqV1lZm/d9P3A/QXGkdSGmnLPniRJkiSpWBZ7kiRJklRCFnuSJEmSVEIWe5IkSZJUQhZ7kiRJklRCFnuSJEmSVEIWe5IkSZJUQhZ7kiRJklRCFnuSJEmSVEIWe5IkSZJUQhZ7kiRJklRCFnuSJEmSVEIWe5IkSZJUQhZ7kiRJklRCFnuSJEmSVEIWe5IkSZJUQhZ7kiRJklRC44sOIEmSpKqI6AQuBnYG+oCjMnNh3foTgHfXZv8tMz81+ikltQqv7EmSJI0dbwMmZOYewMeBcwZXRMSOwP8GXgfsAbwpIl5dSEpJLcFiT5IkaezYC7gOIDNvA3atW/cw8A+ZuTIzVwFdwPLRjyipVTiMU1LbiYjpwOczc2ZE7AL8GLivtvpLmfm9iDgdOBDoB47PzDsKiiupvUwCnqybXxkR4zOzPzNXAE9ERAdwFvCbzLx3XTvs6+ujt7d3reu7u7s3NHNpDHWc1sXj+Bcex8bYkOM4yGJPUluJiI8BhwLP1BbtApybmfVDpXYBZgDTge2Bq4DdRjmqpPa0FJhYN9+Zmf2DMxExAfgq8BTwz8PZYaVSsQM9TB6nxvA4NsZQx7Gnp2dY+3AYp6R2cz/wjrr5acCBEfHLiLg8IiZSHUZ1fWYOZOZDwPiI2LKIsJLazjzgzQARsTuwYHBF7YrevwK/zcz3Z+bKYiJKahVe2ZPUVjLzqoiYWrfoDuCyzOyJiJOB04ElwOK6bZ4CNgcWrW2/6xomtSZj4cxnI4aIaN38u9YIXA28MSJuBTqAIyLiRGAhMI7qqINKRBxQ2/4TmTm/mKiSxjqLPUnt7urMXDI4DVxI9cx5/TCqiVQLwLVq1WFSrZhZ68e/65Eb7jCpRqo9eOWY1RbfUzc9YRTjSGpxDuOU1O5+FhGvrU2/AeihOoxq/4jojIgpVO+ZeaKwhJIkSevBK3uS2t0HgC9GxHPAY8DRmbk0Im4G5lM9KTa7yICSJEnrw2JPUtvJzN8Du9emf031BcWrbzMHmDOauSRJkhqNqCr1AAAQIUlEQVTJYZySJEmSVEIWe5IkSZJUQhZ7kiRJklRCDb9nLyK6gK8CU4EK8BngbuDrwABwFzA7M1dFxOnAgUA/cHxm3tHoPJIkSZLUjppxZe+9wOLM3Bs4APgicC5wSm1ZBzArInah+mLQ6cC7gYuakEWSJEmS2lIzir0fAKfWzfcD04CbavPXAvsBewHXZ+ZAZj4EjI+ILZuQR5IkSZLaTsOHcWbm0wARMRGYC5wCnJ2ZA7VNngI2ByYBi+s+Orh80VD77+vro7e3d63ru7u71zt72Qx1nCRJkiSVW1PesxcR2wNXAxdn5nci4sy61ROBJcDS2vTqy4dUqVQs6IbJ46RW0dPTU3QESZKk0mn4MM6I2Aq4HjgpM79aW/ybiJhZmz4AuBmYB+wfEZ0RMQXozMwnGp1HkiRJktpRM67sfRJ4IXBqRAzeu3cccEFEbAT0AnMzc2VE3AzMp1p0zm5CFkmSJElqS824Z+84qsXd6masYds5wJxGZ5AkSZKkdudL1SVJkiSphCz2JEmSJKmELPYkSZIkqYQs9iRJkiSphCz2JEmSJKmELPYkSZIkqYQs9iRJkiSphCz2tEYD/X1FRxgTPA6SJElqVQ1/qbrKoWN8hYfOeFXRMQo35bQFRUeQJEmS1otX9iRJkiSphCz2JEmSJKmEHMYpqe1ExHTg85k5MyJeBnwdGADuAmZn5qqIOB04EOgHjs/MOwoLLEmStB68sieprUTEx4DLgAm1RecCp2Tm3kAHMCsidgFmANOBdwMXFZFVkiRpQ1jsSWo39wPvqJufBtxUm74W2A/YC7g+Mwcy8yFgfERsOboxJUmSNozDOCW1lcy8KiKm1i3qyMyB2vRTwObAJGBx3TaDyxetbb99fX309vaOKEt3d/eItm+GkWbW+vHvWpJUBIs9Se1uVd30RGAJsLQ2vfrytapUKmOiQz9SrZhZ68e/65Hr6ekpOoIkbRCHcUpqd7+JiJm16QOAm4F5wP4R0RkRU4DOzHyiqICSJEnrwyt7ktrdh4FLI2IjoBeYm5krI+JmYD7Vk2KziwwoSZK0Piz2JLWdzPw9sHtt+l6qT95cfZs5wJzRzDXaBvr76BhfafsMkiSVlcWeJLWpjvEVHjrjVYVmmHLagkK/X5KkMvOePUmSJEkqIYs9SZIkSSohiz1JkiRJKiGLPUmSJEkqIYs9SZIkSSohn8YpSZI0RkREJ3AxsDPQBxyVmQtX22ZL4FbgVZm5fPRTSmoVXtmTJEkaO94GTMjMPYCPA+fUr4yI/YHrga0KyCapxVjsSZIkjR17AdcBZOZtwK6rrV8F7Af8cZRzSWpBDuOUJEkaOyYBT9bNr4yI8ZnZD5CZ/w4QEcPeYV9fH729vWtd393dvX5JS2io47QuHse/8Dg2xoYcx0EWe5IkldxAfx8d4yttn6FFLAUm1s13DhZ666tSqdiBHiaPU2N4HBtjqOPY09MzrH1Y7EmSVHId4ys8dMarCs0w5bQFhX5/C5kHvAX4fkTsDnjgJK03iz1JkqSx42rgjRFxK9ABHBERJwILM/OaYqNJajVNK/YiYjrw+cycGREvA74ODAB3AbMzc1VEnA4cCPQDx2fmHc3KI0mSNNZl5irgmNUW37OG7aaOSiBJLa0pT+OMiI8BlwETaovOBU7JzL2pnqWaFRG7ADOA6cC7gYuakUWSJEmS2lGzXr1wP/COuvlpwE216WupPjJ4L+D6zBzIzIeA8bWXhEqSJEmSNlBThnFm5lURMbVuUUdmDtSmnwI2p/po4cV12wwuXzTUvn188PD52NvGaMRjbyVJkqTRNloPaFlVNz0RWMLzHy08uHxIPj54+DxOjeFxbL7hPj5YkiRJw9esYZyr+01EzKxNHwDcTPXRwvtHRGdETKH6HpknRimPJEmSJJXaaF3Z+zBwaURsBPQCczNzZUTcDMynWnTOHqUskiRJklR6TSv2MvP3wO616XupPnlz9W3mAHOalUGSJEmS2tVoDeOUJEmSJI0iiz1JkiRJKqHRumdPksa0iPgN8GRt9nfAV4DzgX6q7wT9VFHZJEmS1ofFnqS2FxETADJzZt2yO4F/BB4AfhoRu2Tmr4tJKEmSNHIWe1IT9fX3URlfKTpG4VrgOOwMbBIR11NtF+cAlcy8HyAifga8AVhrsdfX10dvb++IvtR3OFaN9Li1Iv+uq9rh71qSxhKLPamJKuMr7HnhnkXHKNy8Y+cVHWFdlgFnA5cBfwtcCyypW/8UsONQO6hUKnbo15PHrX202t91T09P0REkaYNY7EkS3AsszMwB4N6IeBLYom79RP66+JM0QmPhCv9YyCBJo8liT5LgSOBVwD9HxLbAJsAzEfFSqvfs7Q/4gBZpA4yFkQ4tMMpAkhrKYk+S4HLg6xFxCzBAtfhbBXwbGEf1aZy3F5hPkiRpxCz2JLW9zHwOeM8aVu0+2lkkSZIaxZeqS5IkSVIJWexJkiRJUglZ7EmSJElSCVnsSZIkSVIJWexJkiRJUglZ7EmSJElSCVnsSZIkSVIJWexJkgrT199XdIQxkUGSpGbwpeqSpMJUxlfY88I9C80w79h5hX6/JEnN4pU9SZIkSSohiz1JkiRJKiGLPUmSJEkqIYs9SZIkSSohiz1JkiRJKiGLPUmSJEkqIYs9SZIkSSohiz1JkiRJKiGLPUmSJEkqIYs9SZIkSSohiz1JkiRJKiGLPUmSJEkqIYs9SZIkSSqh8UUHiIhO4GJgZ6APOCozFxabSlK7s22SVIR1tT0R8X+A9wP9wGcy8yeFBJXUEsbClb23ARMycw/g48A5BeeRJLBtklSMtbY9EbE18CFgT2B/4LMRUSkkpaSWMBaKvb2A6wAy8zZg12LjSBJg2ySpGEO1Pa8F5mVmX2Y+CSwEXj36ESW1io6BgYFCA0TEZcBVmXltbf4hYMfM7F/T9j09PYuAB0cxoqTme8m0adO2LDpEPdsmSRTQNg3V9kTEe4FXZeZJtXVXAFdk5n8MtU/bJ6mUhtU+FX7PHrAUmFg337m2zhTAWOsQSiot2yZJRRiq7Vl93URgybp2aPskta+xMIxzHvBmgIjYHVhQbBxJAmybJBVjqLbnDmDviJgQEZsD3cBdox9RUqsYC1f2rgbeGBG3Ah3AEQXnkSSwbZJUjOe1PRFxIrAwM6+JiAuAm6mesD85M5cXmFXSGFf4PXuSJEmSpMYbC8M4JUmSJEkNZrEnSZIkSSU0Fu7ZK42I+DiwH7AKGAA+mZk9xaZqPRHxSuBMYBNgM+DfgDmZ6ZhjaQyJiOnA5zNzZtFZ1BwR0QlcDOwM9AFHZebCYlOpTOw7NYZ9J62NxV6DRMQrgLcCe2bmQES8BvgG1X8gNUwR8QLgu8A7MvO+iBgH/AB4P/DlQsO1mIiYBnyWasPfCfwC+FRmPldoMJVCRHwMOBR4pugsaqq3ARMyc4/akyHPAWYVnEklYd+pMew7NUZZ+00O42ycx4EpwJER8TeZeSfw2oIztaJZwA2ZeR9AZq4EDgO+WmiqFhMR2wHfAj6YmXsBe1I9K39eocFUJvcD7yg6hJpuL+A6gMy8Ddi12DgqGftOjWHfaQOVud9ksdcgmfkEtbNTwPyIuAc4qNhULWlb4IH6BZn5dKufVSnAYcBlmXkvQG0Yx6eBN0fExoUmUylk5lXAiqJzqOkmAU/Wza+MCEcFqSHsOzWMfacNV9p+k8Veg0TEy4ClmXlkZk4B3gt8KSK2KDhaq3kQ2L5+QUTsEBGvLyhPq3oJz2/4B4A/AFsXkkhSK1oKTKyb78zM/qLCqFzsOzWMfacNV9p+k8Ve47yaagM1oTZ/L9WzoSuLi9SSfgL8Q0S8FCAiuoBzgZ0KTdV6HgR2rF9Qe9DCFKrDZiRpOOYBbwao3bO3oNg4Khn7To1h32nDlbbf5EvVGygiTgbeBTxNtZD+fGb+qNhUrad2g+xZVI/hRODHVG+Q9Zd1mCJie+B6qsNjFgHfBx4B+jPz6CKzqTwiYirw3czcvegsao66p3G+GugAjsjMe4pNpTKx79QY9p02TJn7TRZ7UknVGv7/S/URzJsAj1EdjnBiZv6xyGySJEljSVn7TRZ7UhuJiFcDD2Tm00VnkSRJGsvK0G+y2JMkSZKkEvIBLZIkSZJUQhZ7kiRJklRCFnuSJEmSVEIWe5IkSZJUQuOLDqDWFxEzqb6P5O66xYsy8+B1fO59wN9l5sfX4zt/X/vs8hF8ZgJwT2ZOHen3SWp9EfFxYD9gFTAAfDIze9ZzX18Azs3Mh9bz898FvpyZN67P5yW1NvtOGi0We2qUGzLz3UWHkKQ1iYhXUH1Z7p6ZORARrwG+Aey8PvvLzOMbmU9SW7LvpKaz2FPTRMSNwG+BnYCngZuB/YEXAG+qbbZHRPwcmATMycyfRsQ7gdlAR22bd9b28XngOeCSuu84pravQ4DdgX8BVgL3A+8HKsC3gRcCC5v0o0oa+x4HpgBHRsR1mXlnRLy21k4dk5n31NqTrYGvAz8GFgP/BhwBvKJWJF4E/AdwHHAM8C3gnZn5+4g4GNgLOA24HJhc++4PZeaCiJgNHAX8P+DFo/JTS2op9p3UaN6zp0bZNyJurPvz0dryOzLzDVQbjmWZ+UaqQxZm1NY/Q3VY1YHAFyOiE3g5cGBmzgSSaiMHMCEz987Mb9bmjwX2Bg6m2pBdCrwjM2cA/wO8r/bnrsx8PfCV5vzoksa6zHyC2pU9YH5E3AMcNMRHtgbelJlnAv8F7B0RFWAm1UJw0OXAYbXp91Fthz4J/Dwz9wGOBr4UEZtTLRB3B2YBGzXmJ5PUwuw7qem8sqdGed5QhIg4EPh1bXYJfxmX/idgQm36lswcAB6PiCepngl/HPhGRDwN/B0wv7Ztrvad+wH9mbkyIl4MbAN8PyIANgauB14EXAeQmbdHxIpG/LCSWktEvAxYmplH1uZ3pXrV7rG6zTrqpn+Xmc/Vpi8FDqdaAF6Tmf21dgaqZ79viYjLgEmZeVdEvIpqJ+5/1bZ5IdW27L8zs6/2/Xc0/IeU1GrsO6npvLKnZhtYx/rdACJia2AzqmeZPgW8m+pwp2f5Swds1WqfnQX8qTYc4QngEWBW7azWvwC/AO4B9qh9x98DXRv240hqUa+meoVtsLN0L/Ak1aGa29SW7VK3fX1783Pg74EjqV7J+7PMXAr0AOcBX6stvgc4r9YWvYtqQfgA8IqI2DgixtX2J0lrYt9JDeOVPTXKvrVx5vU2HsbnNo6IG6g2Vu8HlgLzqJ7Veobqmaxtgd+t5fMfAu6g2hk7DvhpbTjDUqpDq34JfC0ibqHaePWN4GeSVBKZ+cOI6AZur5357gQ+SrWTdFFEPEx1CNOaPjsQEXOB/TJzTfevXEr1LPiRtfl/AS6PiKP5yz01iyLiNOBWYBHV9k1Se7PvpKbrGBhY18kDSZIkSVKrcRinJEmSJJWQxZ4kSZIklZDFniRJkiSVkMWeJEmSJJWQxZ4kSZIklZDFniRJkiSVkMWeJEmSJJXQ/wcHRn93fzJdugAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 1080x360 with 3 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Embarked\n",
    "\n",
    "# only in titanic_df, fill the two missing values with the most occurred value, which is \"S\".\n",
    "titanic_df[\"Embarked\"] = titanic_df[\"Embarked\"].fillna(\"S\")\n",
    "\n",
    "# plot\n",
    "sns.factorplot('Embarked','Survived', data=titanic_df,size=4,aspect=3)\n",
    "\n",
    "fig, (axis1,axis2,axis3) = plt.subplots(1,3,figsize=(15,5))\n",
    "sns.countplot(x='Embarked', data=titanic_df, ax=axis1)\n",
    "sns.countplot(x='Survived', hue=\"Embarked\", data=titanic_df, order=[1,0], ax=axis2)\n",
    "\n",
    "# group by embarked, and get the mean for survived passengers for each value in Embarked\n",
    "embark_perc = titanic_df[[\"Embarked\", \"Survived\"]].groupby(['Embarked'],as_index=False).mean()\n",
    "sns.barplot(x='Embarked', y='Survived', data=embark_perc,order=['S','C','Q'],ax=axis3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Fare\n",
    "\n",
    "# only for test_df, since there is a missing \"Fare\" values\n",
    "test_df[\"Fare\"].fillna(test_df[\"Fare\"].median(), inplace=True)\n",
    "\n",
    "# convert from float to int\n",
    "titanic_df['Fare'] = titanic_df['Fare'].astype(int)\n",
    "test_df['Fare']    = test_df['Fare'].astype(int)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x1171178d0>"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x216 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# get fare for survived & didn't survive passengers \n",
    "fare_not_survived = titanic_df[\"Fare\"][titanic_df[\"Survived\"] == 0]\n",
    "fare_survived     = titanic_df[\"Fare\"][titanic_df[\"Survived\"] == 1]\n",
    "\n",
    "# get average and std for fare of survived/not survived passengers\n",
    "avgerage_fare = pd.DataFrame([fare_not_survived.mean(), fare_survived.mean()])\n",
    "std_fare      = pd.DataFrame([fare_not_survived.std(), fare_survived.std()])\n",
    "\n",
    "# plot\n",
    "titanic_df['Fare'].plot(kind='hist', figsize=(15,3),bins=100, xlim=(0,50))\n",
    "\n",
    "avgerage_fare.index.names = std_fare.index.names = [\"Survived\"]\n",
    "avgerage_fare.plot(yerr=std_fare,kind='bar',legend=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/anaconda3/lib/python3.6/site-packages/ipykernel_launcher.py:28: 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",
      "/anaconda3/lib/python3.6/site-packages/ipykernel_launcher.py:29: 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"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x1171c7da0>"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x288 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Age \n",
    "\n",
    "fig, (axis1,axis2) = plt.subplots(1,2,figsize=(15,4))\n",
    "axis1.set_title('Original Age values - Titanic')\n",
    "axis2.set_title('New Age values - Titanic')\n",
    "\n",
    "# get average, std, and number of NaN values in titanic_df\n",
    "average_age_titanic   = titanic_df[\"Age\"].mean()\n",
    "std_age_titanic       = titanic_df[\"Age\"].std()\n",
    "count_nan_age_titanic = titanic_df[\"Age\"].isnull().sum()\n",
    "\n",
    "# get average, std, and number of NaN values in test_df\n",
    "average_age_test   = test_df[\"Age\"].mean()\n",
    "std_age_test       = test_df[\"Age\"].std()\n",
    "count_nan_age_test = test_df[\"Age\"].isnull().sum()\n",
    "\n",
    "# generate random numbers between (mean - std) & (mean + std)\n",
    "rand_1 = np.random.randint(average_age_titanic - std_age_titanic, average_age_titanic + std_age_titanic, \n",
    "                           size = count_nan_age_titanic)\n",
    "rand_2 = np.random.randint(average_age_test - std_age_test, average_age_test + std_age_test, \n",
    "                           size = count_nan_age_test)\n",
    "\n",
    "# plot original Age values\n",
    "# NOTE: drop all null values, and convert to int\n",
    "titanic_df['Age'].dropna().astype(int).hist(bins=70, ax=axis1)\n",
    "\n",
    "# fill NaN values in Age column with random values generated\n",
    "titanic_df[\"Age\"][np.isnan(titanic_df[\"Age\"])] = rand_1\n",
    "test_df[\"Age\"][np.isnan(test_df[\"Age\"])] = rand_2\n",
    "\n",
    "# convert from float to int\n",
    "titanic_df['Age'] = titanic_df['Age'].astype(int)\n",
    "test_df['Age']    = test_df['Age'].astype(int)\n",
    "        \n",
    "# plot new Age Values\n",
    "titanic_df['Age'].hist(bins=70, ax=axis2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x1170758d0>"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 911x216 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1296x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# .... continue with plot Age column\n",
    "\n",
    "# peaks for survived/not survived passengers by their age\n",
    "facet = sns.FacetGrid(titanic_df, hue=\"Survived\",aspect=4)\n",
    "facet.map(sns.kdeplot,'Age',shade= True)\n",
    "facet.set(xlim=(0, titanic_df['Age'].max()))\n",
    "facet.add_legend()\n",
    "\n",
    "# average survived passengers by age\n",
    "fig, axis1 = plt.subplots(1,1,figsize=(18,4))\n",
    "average_age = titanic_df[[\"Age\", \"Survived\"]].groupby(['Age'],as_index=False).mean()\n",
    "sns.barplot(x='Age', y='Survived', data=average_age)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Cabin\n",
    "# It has a lot of NaN values, so it won't cause a remarkable impact on prediction\n",
    "titanic_df.drop(\"Cabin\",axis=1,inplace=True)\n",
    "test_df.drop(\"Cabin\",axis=1,inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.FacetGrid at 0x11572a048>"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x216 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "g = sns.FacetGrid(titanic_df, col='Survived')\n",
    "g.map(plt.hist, 'Parch')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.FacetGrid at 0x11572a4e0>"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x216 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "g = sns.FacetGrid(titanic_df, col='Survived')\n",
    "g.map(plt.hist, 'SibSp')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/anaconda3/lib/python3.6/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"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[Text(0,0,'With Family'), Text(0,0,'Alone')]"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x360 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Family\n",
    "\n",
    "# Instead of having two columns Parch & SibSp, \n",
    "# we can have only one column represent if the passenger had any family member aboard or not,\n",
    "# Meaning, if having any family member(whether parent, brother, ...etc) will increase chances of Survival or not.\n",
    "titanic_df['Family'] =  titanic_df[\"Parch\"] + titanic_df[\"SibSp\"]\n",
    "titanic_df['Family'].loc[titanic_df['Family'] > 0] = 1\n",
    "titanic_df['Family'].loc[titanic_df['Family'] == 0] = 0\n",
    "\n",
    "test_df['Family'] =  test_df[\"Parch\"] + test_df[\"SibSp\"]\n",
    "test_df['Family'].loc[test_df['Family'] > 0] = 1\n",
    "test_df['Family'].loc[test_df['Family'] == 0] = 0\n",
    "\n",
    "# drop Parch & SibSp\n",
    "titanic_df = titanic_df.drop(['SibSp','Parch'], axis=1)\n",
    "test_df    = test_df.drop(['SibSp','Parch'], axis=1)\n",
    "\n",
    "# plot\n",
    "fig, (axis1,axis2) = plt.subplots(1,2,sharex=True,figsize=(10,5))\n",
    "\n",
    "# sns.factorplot('Family',data=titanic_df,kind='count',ax=axis1)\n",
    "sns.countplot(x='Family', data=titanic_df, order=[1,0], ax=axis1)\n",
    "\n",
    "# average of survived for those who had/didn't have any family member\n",
    "family_perc = titanic_df[[\"Family\", \"Survived\"]].groupby(['Family'],as_index=False).mean()\n",
    "sns.barplot(x='Family', y='Survived', data=family_perc, order=[1,0], ax=axis2)\n",
    "\n",
    "axis1.set_xticklabels([\"With Family\",\"Alone\"], rotation=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x1a1fd22748>"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Sex\n",
    "sns.countplot(titanic_df['Sex'], hue=titanic_df['Survived'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x360 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Sex\n",
    "\n",
    "# As we see, children(age < ~16) on aboard seem to have a high chances for Survival.\n",
    "# So, we can classify passengers as males, females, and child\n",
    "def get_person(passenger):\n",
    "    age,sex = passenger\n",
    "    return 'child' if age < 16 else sex\n",
    "    \n",
    "titanic_df['Person'] = titanic_df[['Age','Sex']].apply(get_person,axis=1)\n",
    "test_df['Person']    = test_df[['Age','Sex']].apply(get_person,axis=1)\n",
    "\n",
    "# No need to use Sex column since we created Person column\n",
    "titanic_df.drop(['Sex'],axis=1,inplace=True)\n",
    "test_df.drop(['Sex'],axis=1,inplace=True)\n",
    "\n",
    "# create dummy variables for Person column, & drop Male as it has the lowest average of survived passengers\n",
    "person_dummies_titanic  = pd.get_dummies(titanic_df['Person'])\n",
    "person_dummies_titanic.columns = ['Child','Female','Male']\n",
    "person_dummies_titanic.drop(['Male'], axis=1, inplace=True)\n",
    "\n",
    "person_dummies_test  = pd.get_dummies(test_df['Person'])\n",
    "person_dummies_test.columns = ['Child','Female','Male']\n",
    "person_dummies_test.drop(['Male'], axis=1, inplace=True)\n",
    "\n",
    "titanic_df = titanic_df.join(person_dummies_titanic)\n",
    "test_df    = test_df.join(person_dummies_test)\n",
    "\n",
    "fig, (axis1,axis2) = plt.subplots(1,2,figsize=(10,5))\n",
    "\n",
    "# sns.factorplot('Person',data=titanic_df,kind='count',ax=axis1)\n",
    "sns.countplot(x='Person', data=titanic_df, ax=axis1)\n",
    "\n",
    "# average of survived for each Person(male, female, or child)\n",
    "person_perc = titanic_df[[\"Person\", \"Survived\"]].groupby(['Person'],as_index=False).mean()\n",
    "sns.barplot(x='Person', y='Survived', data=person_perc, ax=axis2, order=['male','female','child'])\n",
    "\n",
    "titanic_df.drop(['Person'],axis=1,inplace=True)\n",
    "test_df.drop(['Person'],axis=1,inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x1a2036cf60>"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.countplot(titanic_df['Pclass'], hue=titanic_df['Survived'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 360x360 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Pclass\n",
    "\n",
    "# sns.factorplot('Pclass',data=titanic_df,kind='count',order=[1,2,3])\n",
    "sns.factorplot('Pclass','Survived',order=[1,2,3], data=titanic_df,size=5)\n",
    "\n",
    "# create dummy variables for Pclass column, & drop 3rd class as it has the lowest average of survived passengers\n",
    "pclass_dummies_titanic  = pd.get_dummies(titanic_df['Pclass'])\n",
    "pclass_dummies_titanic.columns = ['Class_1','Class_2','Class_3']\n",
    "pclass_dummies_titanic = pclass_dummies_titanic.drop(['Class_3'], axis=1)\n",
    "\n",
    "pclass_dummies_test  = pd.get_dummies(test_df['Pclass'])\n",
    "pclass_dummies_test.columns = ['Class_1','Class_2','Class_3']\n",
    "pclass_dummies_test.drop(['Class_3'], axis=1, inplace=True)\n",
    "\n",
    "titanic_df.drop(['Pclass'],axis=1,inplace=True)\n",
    "test_df.drop(['Pclass'],axis=1,inplace=True)\n",
    "\n",
    "titanic_df = titanic_df.join(pclass_dummies_titanic)\n",
    "test_df    = test_df.join(pclass_dummies_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "# define training and testing sets\n",
    "\n",
    "X_train = titanic_df.drop(['PassengerId',\"Survived\"],axis=1)\n",
    "Y_train = titanic_df[\"Survived\"]\n",
    "X_test  = test_df.drop(\"PassengerId\",axis=1).copy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8125701459034792"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Logistic Regression\n",
    "\n",
    "logreg = LogisticRegression()\n",
    "\n",
    "logreg.fit(X_train, Y_train)\n",
    "\n",
    "Y_pred = logreg.predict(X_test)\n",
    "\n",
    "logreg.score(X_train, Y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8585858585858586"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Support Vector Machines\n",
    "\n",
    "svc = SVC()\n",
    "\n",
    "svc.fit(X_train, Y_train)\n",
    "\n",
    "Y_pred = svc.predict(X_test)\n",
    "\n",
    "svc.score(X_train, Y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9652076318742986"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Random Forests\n",
    "\n",
    "random_forest = RandomForestClassifier(n_estimators=100)\n",
    "\n",
    "random_forest.fit(X_train, Y_train)\n",
    "\n",
    "Y_pred = random_forest.predict(X_test)\n",
    "\n",
    "random_forest.score(X_train, Y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Features</th>\n",
       "      <th>Coefficient Estimate</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Age</td>\n",
       "      <td>-0.023379</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Fare</td>\n",
       "      <td>0.000835</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>C</td>\n",
       "      <td>0.594886</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Q</td>\n",
       "      <td>0.280388</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Family</td>\n",
       "      <td>-0.217172</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Child</td>\n",
       "      <td>1.753677</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Female</td>\n",
       "      <td>2.760550</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Class_1</td>\n",
       "      <td>1.998658</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Class_2</td>\n",
       "      <td>1.118209</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Features  Coefficient Estimate\n",
       "0      Age             -0.023379\n",
       "1     Fare              0.000835\n",
       "2        C              0.594886\n",
       "3        Q              0.280388\n",
       "4   Family             -0.217172\n",
       "5    Child              1.753677\n",
       "6   Female              2.760550\n",
       "7  Class_1              1.998658\n",
       "8  Class_2              1.118209"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# get Correlation Coefficient for each feature using Logistic Regression\n",
    "coeff_df = pd.DataFrame(titanic_df.columns.delete([0,1]))\n",
    "coeff_df.columns = ['Features']\n",
    "coeff_df[\"Coefficient Estimate\"] = pd.Series(logreg.coef_[0])\n",
    "\n",
    "# preview\n",
    "coeff_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "class Student(object): \n",
    "    def __init__(self, name, score):\n",
    "        self.name = name\n",
    "        self.score = score\n",
    "    def get_grade(self):\n",
    "        if self.score >= 90:\n",
    "            return 'A'\n",
    "        else:\n",
    "            return 'B'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Lisa B\n"
     ]
    }
   ],
   "source": [
    "lisa = Student('Lisa', 80)\n",
    "print (lisa.name, lisa.get_grade())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<_sre.SRE_Match object; span=(6, 10), match=' Mr.'>"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import re\n",
    "name = 'Braid, Mr. Owen Harris'\n",
    "re.search(' [A-Za-z]+\\.', name)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}