2_titanic_example.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "# Titanic example"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "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",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>6</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Moran, Mr. James</td>\n",
       "      <td>male</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>330877</td>\n",
       "      <td>8.4583</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Q</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>McCarthy, Mr. Timothy J</td>\n",
       "      <td>male</td>\n",
       "      <td>54.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>17463</td>\n",
       "      <td>51.8625</td>\n",
       "      <td>E46</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>8</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Palsson, Master. Gosta Leonard</td>\n",
       "      <td>male</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>349909</td>\n",
       "      <td>21.0750</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>9</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)</td>\n",
       "      <td>female</td>\n",
       "      <td>27.0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>347742</td>\n",
       "      <td>11.1333</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>10</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>Nasser, Mrs. Nicholas (Adele Achem)</td>\n",
       "      <td>female</td>\n",
       "      <td>14.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>237736</td>\n",
       "      <td>30.0708</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C</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",
       "5            6         0       3   \n",
       "6            7         0       1   \n",
       "7            8         0       3   \n",
       "8            9         1       3   \n",
       "9           10         1       2   \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",
       "5                                   Moran, Mr. James    male   NaN      0   \n",
       "6                            McCarthy, Mr. Timothy J    male  54.0      0   \n",
       "7                     Palsson, Master. Gosta Leonard    male   2.0      3   \n",
       "8  Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)  female  27.0      0   \n",
       "9                Nasser, Mrs. Nicholas (Adele Achem)  female  14.0      1   \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  \n",
       "5      0            330877   8.4583   NaN        Q  \n",
       "6      0             17463  51.8625   E46        S  \n",
       "7      1            349909  21.0750   NaN        S  \n",
       "8      2            347742  11.1333   NaN        S  \n",
       "9      0            237736  30.0708   NaN        C  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_init = pd.read_csv(\"train.csv\")\n",
    "train_init.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "num examples is 891\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>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",
       "    <tr>\n",
       "      <th>PassengerId</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\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>2</th>\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>3</th>\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>4</th>\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>5</th>\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",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Moran, Mr. James</td>\n",
       "      <td>male</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>330877</td>\n",
       "      <td>8.4583</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Q</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>McCarthy, Mr. Timothy J</td>\n",
       "      <td>male</td>\n",
       "      <td>54.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>17463</td>\n",
       "      <td>51.8625</td>\n",
       "      <td>E46</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Palsson, Master. Gosta Leonard</td>\n",
       "      <td>male</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>349909</td>\n",
       "      <td>21.0750</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)</td>\n",
       "      <td>female</td>\n",
       "      <td>27.0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>347742</td>\n",
       "      <td>11.1333</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>Nasser, Mrs. Nicholas (Adele Achem)</td>\n",
       "      <td>female</td>\n",
       "      <td>14.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>237736</td>\n",
       "      <td>30.0708</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Survived  Pclass  \\\n",
       "PassengerId                     \n",
       "1                   0       3   \n",
       "2                   1       1   \n",
       "3                   1       3   \n",
       "4                   1       1   \n",
       "5                   0       3   \n",
       "6                   0       3   \n",
       "7                   0       1   \n",
       "8                   0       3   \n",
       "9                   1       3   \n",
       "10                  1       2   \n",
       "\n",
       "                                                          Name     Sex   Age  \\\n",
       "PassengerId                                                                    \n",
       "1                                      Braund, Mr. Owen Harris    male  22.0   \n",
       "2            Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0   \n",
       "3                                       Heikkinen, Miss. Laina  female  26.0   \n",
       "4                 Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0   \n",
       "5                                     Allen, Mr. William Henry    male  35.0   \n",
       "6                                             Moran, Mr. James    male   NaN   \n",
       "7                                      McCarthy, Mr. Timothy J    male  54.0   \n",
       "8                               Palsson, Master. Gosta Leonard    male   2.0   \n",
       "9            Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)  female  27.0   \n",
       "10                         Nasser, Mrs. Nicholas (Adele Achem)  female  14.0   \n",
       "\n",
       "             SibSp  Parch            Ticket     Fare Cabin Embarked  \n",
       "PassengerId                                                          \n",
       "1                1      0         A/5 21171   7.2500   NaN        S  \n",
       "2                1      0          PC 17599  71.2833   C85        C  \n",
       "3                0      0  STON/O2. 3101282   7.9250   NaN        S  \n",
       "4                1      0            113803  53.1000  C123        S  \n",
       "5                0      0            373450   8.0500   NaN        S  \n",
       "6                0      0            330877   8.4583   NaN        Q  \n",
       "7                0      0             17463  51.8625   E46        S  \n",
       "8                3      1            349909  21.0750   NaN        S  \n",
       "9                0      2            347742  11.1333   NaN        S  \n",
       "10               1      0            237736  30.0708   NaN        C  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_init = train_init.set_index(\"PassengerId\")\n",
    "print(\"num examples is\", len(train_init))\n",
    "train_init.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "PassengerId\n",
      "1     0\n",
      "2     1\n",
      "3     1\n",
      "4     1\n",
      "5     0\n",
      "6     0\n",
      "7     0\n",
      "8     0\n",
      "9     1\n",
      "10    1\n",
      "Name: Survived, dtype: int64\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>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",
       "    <tr>\n",
       "      <th>PassengerId</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\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>2</th>\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>3</th>\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>4</th>\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>5</th>\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",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>3</td>\n",
       "      <td>Moran, Mr. James</td>\n",
       "      <td>male</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>330877</td>\n",
       "      <td>8.4583</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Q</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>1</td>\n",
       "      <td>McCarthy, Mr. Timothy J</td>\n",
       "      <td>male</td>\n",
       "      <td>54.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>17463</td>\n",
       "      <td>51.8625</td>\n",
       "      <td>E46</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>3</td>\n",
       "      <td>Palsson, Master. Gosta Leonard</td>\n",
       "      <td>male</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>349909</td>\n",
       "      <td>21.0750</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>3</td>\n",
       "      <td>Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)</td>\n",
       "      <td>female</td>\n",
       "      <td>27.0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>347742</td>\n",
       "      <td>11.1333</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>2</td>\n",
       "      <td>Nasser, Mrs. Nicholas (Adele Achem)</td>\n",
       "      <td>female</td>\n",
       "      <td>14.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>237736</td>\n",
       "      <td>30.0708</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Pclass                                               Name  \\\n",
       "PassengerId                                                              \n",
       "1                 3                            Braund, Mr. Owen Harris   \n",
       "2                 1  Cumings, Mrs. John Bradley (Florence Briggs Th...   \n",
       "3                 3                             Heikkinen, Miss. Laina   \n",
       "4                 1       Futrelle, Mrs. Jacques Heath (Lily May Peel)   \n",
       "5                 3                           Allen, Mr. William Henry   \n",
       "6                 3                                   Moran, Mr. James   \n",
       "7                 1                            McCarthy, Mr. Timothy J   \n",
       "8                 3                     Palsson, Master. Gosta Leonard   \n",
       "9                 3  Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)   \n",
       "10                2                Nasser, Mrs. Nicholas (Adele Achem)   \n",
       "\n",
       "                Sex   Age  SibSp  Parch            Ticket     Fare Cabin  \\\n",
       "PassengerId                                                                \n",
       "1              male  22.0      1      0         A/5 21171   7.2500   NaN   \n",
       "2            female  38.0      1      0          PC 17599  71.2833   C85   \n",
       "3            female  26.0      0      0  STON/O2. 3101282   7.9250   NaN   \n",
       "4            female  35.0      1      0            113803  53.1000  C123   \n",
       "5              male  35.0      0      0            373450   8.0500   NaN   \n",
       "6              male   NaN      0      0            330877   8.4583   NaN   \n",
       "7              male  54.0      0      0             17463  51.8625   E46   \n",
       "8              male   2.0      3      1            349909  21.0750   NaN   \n",
       "9            female  27.0      0      2            347742  11.1333   NaN   \n",
       "10           female  14.0      1      0            237736  30.0708   NaN   \n",
       "\n",
       "            Embarked  \n",
       "PassengerId           \n",
       "1                  S  \n",
       "2                  C  \n",
       "3                  S  \n",
       "4                  S  \n",
       "5                  S  \n",
       "6                  Q  \n",
       "7                  S  \n",
       "8                  S  \n",
       "9                  S  \n",
       "10                 C  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_init, y_init = train_init.drop(columns=\"Survived\"), train_init[\"Survived\"]\n",
    "print(y_init.head(10))\n",
    "X_init.head(10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "# Първи модел\n",
    "\n",
    "Ще направим модел без никаква обработка на данните.\n",
    "\n",
    "Този модел ще ни служи за мерило колко сме постигнали."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "712 179\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>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",
       "    <tr>\n",
       "      <th>PassengerId</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>693</th>\n",
       "      <td>3</td>\n",
       "      <td>Lam, Mr. Ali</td>\n",
       "      <td>male</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1601</td>\n",
       "      <td>56.4958</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>482</th>\n",
       "      <td>2</td>\n",
       "      <td>Frost, Mr. Anthony Wood \"Archie\"</td>\n",
       "      <td>male</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>239854</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>528</th>\n",
       "      <td>1</td>\n",
       "      <td>Farthing, Mr. John</td>\n",
       "      <td>male</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>PC 17483</td>\n",
       "      <td>221.7792</td>\n",
       "      <td>C95</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>856</th>\n",
       "      <td>3</td>\n",
       "      <td>Aks, Mrs. Sam (Leah Rosen)</td>\n",
       "      <td>female</td>\n",
       "      <td>18.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>392091</td>\n",
       "      <td>9.3500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>802</th>\n",
       "      <td>2</td>\n",
       "      <td>Collyer, Mrs. Harvey (Charlotte Annie Tate)</td>\n",
       "      <td>female</td>\n",
       "      <td>31.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>C.A. 31921</td>\n",
       "      <td>26.2500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>653</th>\n",
       "      <td>3</td>\n",
       "      <td>Kalvik, Mr. Johannes Halvorsen</td>\n",
       "      <td>male</td>\n",
       "      <td>21.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8475</td>\n",
       "      <td>8.4333</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>510</th>\n",
       "      <td>3</td>\n",
       "      <td>Lang, Mr. Fang</td>\n",
       "      <td>male</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1601</td>\n",
       "      <td>56.4958</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>558</th>\n",
       "      <td>1</td>\n",
       "      <td>Robbins, Mr. Victor</td>\n",
       "      <td>male</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>PC 17757</td>\n",
       "      <td>227.5250</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>829</th>\n",
       "      <td>3</td>\n",
       "      <td>McCormack, Mr. Thomas Joseph</td>\n",
       "      <td>male</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>367228</td>\n",
       "      <td>7.7500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Q</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>3</td>\n",
       "      <td>Vander Planke, Mrs. Julius (Emelia Maria Vande...</td>\n",
       "      <td>female</td>\n",
       "      <td>31.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>345763</td>\n",
       "      <td>18.0000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Pclass                                               Name  \\\n",
       "PassengerId                                                              \n",
       "693               3                                       Lam, Mr. Ali   \n",
       "482               2                   Frost, Mr. Anthony Wood \"Archie\"   \n",
       "528               1                                 Farthing, Mr. John   \n",
       "856               3                         Aks, Mrs. Sam (Leah Rosen)   \n",
       "802               2        Collyer, Mrs. Harvey (Charlotte Annie Tate)   \n",
       "653               3                     Kalvik, Mr. Johannes Halvorsen   \n",
       "510               3                                     Lang, Mr. Fang   \n",
       "558               1                                Robbins, Mr. Victor   \n",
       "829               3                       McCormack, Mr. Thomas Joseph   \n",
       "19                3  Vander Planke, Mrs. Julius (Emelia Maria Vande...   \n",
       "\n",
       "                Sex   Age  SibSp  Parch      Ticket      Fare Cabin Embarked  \n",
       "PassengerId                                                                   \n",
       "693            male   NaN      0      0        1601   56.4958   NaN        S  \n",
       "482            male   NaN      0      0      239854    0.0000   NaN        S  \n",
       "528            male   NaN      0      0    PC 17483  221.7792   C95        S  \n",
       "856          female  18.0      0      1      392091    9.3500   NaN        S  \n",
       "802          female  31.0      1      1  C.A. 31921   26.2500   NaN        S  \n",
       "653            male  21.0      0      0        8475    8.4333   NaN        S  \n",
       "510            male  26.0      0      0        1601   56.4958   NaN        S  \n",
       "558            male   NaN      0      0    PC 17757  227.5250   NaN        C  \n",
       "829            male   NaN      0      0      367228    7.7500   NaN        Q  \n",
       "19           female  31.0      1      0      345763   18.0000   NaN        S  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "X_train, X_val, y_train, y_val = train_test_split(X_init, \n",
    "                                                  y_init, \n",
    "                                                  test_size=0.2, \n",
    "                                                  stratify=y_init, \n",
    "                                                  random_state=42)\n",
    "\n",
    "print(len(y_train), len(y_val))\n",
    "X_train.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "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>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>712.000000</td>\n",
       "      <td>575.000000</td>\n",
       "      <td>712.000000</td>\n",
       "      <td>712.000000</td>\n",
       "      <td>712.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>2.308989</td>\n",
       "      <td>29.807687</td>\n",
       "      <td>0.492978</td>\n",
       "      <td>0.390449</td>\n",
       "      <td>31.819826</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>0.833563</td>\n",
       "      <td>14.485211</td>\n",
       "      <td>1.060720</td>\n",
       "      <td>0.838134</td>\n",
       "      <td>48.059104</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\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>2.000000</td>\n",
       "      <td>21.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>7.895800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>3.000000</td>\n",
       "      <td>28.500000</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>3.000000</td>\n",
       "      <td>39.000000</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>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": [
       "           Pclass         Age       SibSp       Parch        Fare\n",
       "count  712.000000  575.000000  712.000000  712.000000  712.000000\n",
       "mean     2.308989   29.807687    0.492978    0.390449   31.819826\n",
       "std      0.833563   14.485211    1.060720    0.838134   48.059104\n",
       "min      1.000000    0.420000    0.000000    0.000000    0.000000\n",
       "25%      2.000000   21.000000    0.000000    0.000000    7.895800\n",
       "50%      3.000000   28.500000    0.000000    0.000000   14.454200\n",
       "75%      3.000000   39.000000    1.000000    0.000000   31.000000\n",
       "max      3.000000   80.000000    8.000000    6.000000  512.329200"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\users\\iddilov\\appdata\\local\\programs\\python\\python36\\lib\\site-packages\\pandas\\core\\indexing.py:543: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
      "  self.obj[item] = s\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train score: 0.7120786516853933\n",
      "Val score: 0.6759776536312849\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=-1)]: Done   1 out of   1 | elapsed:    0.9s finished\n"
     ]
    }
   ],
   "source": [
    "from sklearn.linear_model import LogisticRegression\n",
    "\n",
    "model = LogisticRegression(solver=\"lbfgs\", random_state=42, n_jobs=-1, verbose=1)\n",
    "# solver:\n",
    "# liblinear е това което знаем\n",
    "# lbfgs by default\n",
    "# saga better for large datasets\n",
    "\n",
    "number_cols = [\"Pclass\", \"Age\", \"SibSp\", \"Parch\", \"Fare\"]\n",
    "fillv = X_train[\"Age\"].mean()\n",
    "X_train.loc[:, \"Age\"] = X_train[\"Age\"].fillna(fillv)\n",
    "X_val.loc[:, \"Age\"] = X_val[\"Age\"].fillna(fillv)\n",
    "\n",
    "trained_model = model.fit(X_train[number_cols], y_train)\n",
    "\n",
    "print(\"Train score:\", trained_model.score(X_train[number_cols], y_train))\n",
    "print(\"Val score:\", trained_model.score(X_val[number_cols], y_val))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    712.000000\n",
       "mean       0.383427\n",
       "std        0.486563\n",
       "min        0.000000\n",
       "25%        0.000000\n",
       "50%        0.000000\n",
       "75%        1.000000\n",
       "max        1.000000\n",
       "Name: Survived, dtype: float64"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 67.6% accuracy не звучи зле, ама да видим y колоната какво съдържа\n",
    "y_train.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\users\\iddilov\\appdata\\local\\programs\\python\\python36\\lib\\site-packages\\sklearn\\ensemble\\weight_boosting.py:29: DeprecationWarning: numpy.core.umath_tests is an internal NumPy module and should not be imported. It will be removed in a future NumPy release.\n",
      "  from numpy.core.umath_tests import inner1d\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train score: 0.7724719101123596\n",
      "Val score: 0.7039106145251397\n"
     ]
    }
   ],
   "source": [
    "# 38% оживели\n",
    "# значи не сме много по-добре от просто да казваме че всеки е умрял\n",
    "# да пробваме и с random forest\n",
    "\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "\n",
    "model = RandomForestClassifier(n_estimators=100, max_depth=4, n_jobs=-1, random_state=42)\n",
    "\n",
    "trained_model = model.fit(X_train[number_cols], y_train)\n",
    "\n",
    "print(\"Train score:\", trained_model.score(X_train[number_cols], y_train))\n",
    "print(\"Val score:\", trained_model.score(X_val[number_cols], y_val))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [],
   "source": [
    "# 70% e по-добре. И все пак наблюдаваме голям overfit.\n",
    "# Извод който можем да си направим е че някои от зависимостите не са линейни, иначе логистичната регресия щеше да ги улови."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "# Анализ на колоните\n",
    "По-точно ще се интересуваме коя колона как може да помогне за класификацията"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "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>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",
       "    <tr>\n",
       "      <th>PassengerId</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\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>2</th>\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>3</th>\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>4</th>\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>5</th>\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",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Moran, Mr. James</td>\n",
       "      <td>male</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>330877</td>\n",
       "      <td>8.4583</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Q</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>McCarthy, Mr. Timothy J</td>\n",
       "      <td>male</td>\n",
       "      <td>54.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>17463</td>\n",
       "      <td>51.8625</td>\n",
       "      <td>E46</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Palsson, Master. Gosta Leonard</td>\n",
       "      <td>male</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>349909</td>\n",
       "      <td>21.0750</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)</td>\n",
       "      <td>female</td>\n",
       "      <td>27.0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>347742</td>\n",
       "      <td>11.1333</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>Nasser, Mrs. Nicholas (Adele Achem)</td>\n",
       "      <td>female</td>\n",
       "      <td>14.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>237736</td>\n",
       "      <td>30.0708</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Survived  Pclass  \\\n",
       "PassengerId                     \n",
       "1                   0       3   \n",
       "2                   1       1   \n",
       "3                   1       3   \n",
       "4                   1       1   \n",
       "5                   0       3   \n",
       "6                   0       3   \n",
       "7                   0       1   \n",
       "8                   0       3   \n",
       "9                   1       3   \n",
       "10                  1       2   \n",
       "\n",
       "                                                          Name     Sex   Age  \\\n",
       "PassengerId                                                                    \n",
       "1                                      Braund, Mr. Owen Harris    male  22.0   \n",
       "2            Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0   \n",
       "3                                       Heikkinen, Miss. Laina  female  26.0   \n",
       "4                 Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0   \n",
       "5                                     Allen, Mr. William Henry    male  35.0   \n",
       "6                                             Moran, Mr. James    male   NaN   \n",
       "7                                      McCarthy, Mr. Timothy J    male  54.0   \n",
       "8                               Palsson, Master. Gosta Leonard    male   2.0   \n",
       "9            Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)  female  27.0   \n",
       "10                         Nasser, Mrs. Nicholas (Adele Achem)  female  14.0   \n",
       "\n",
       "             SibSp  Parch            Ticket     Fare Cabin Embarked  \n",
       "PassengerId                                                          \n",
       "1                1      0         A/5 21171   7.2500   NaN        S  \n",
       "2                1      0          PC 17599  71.2833   C85        C  \n",
       "3                0      0  STON/O2. 3101282   7.9250   NaN        S  \n",
       "4                1      0            113803  53.1000  C123        S  \n",
       "5                0      0            373450   8.0500   NaN        S  \n",
       "6                0      0            330877   8.4583   NaN        Q  \n",
       "7                0      0             17463  51.8625   E46        S  \n",
       "8                3      1            349909  21.0750   NaN        S  \n",
       "9                0      2            347742  11.1333   NaN        S  \n",
       "10               1      0            237736  30.0708   NaN        C  "
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_init.head(10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## P class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Да направим картинка от коя класа колко живи и умрели има... Така ще видим има ли значение\n",
    "\n",
    "AliveClass = [[len(train_init[(train_init.Survived == x) & (train_init.Pclass == y)]) for y in [1, 2, 3]] for x in [0, 1]]\n",
    "\n",
    "bar_width = 0.33\n",
    "r1 = np.arange(3)\n",
    "r2 = r1 + bar_width\n",
    "\n",
    "plt.bar(r1, AliveClass[0], width=bar_width, color=\"red\", label=\"Dead\")\n",
    "plt.bar(r2, AliveClass[1], width=bar_width, color=\"blue\", label=\"Alive\")\n",
    "\n",
    "plt.xlabel(\"Pclass\")\n",
    "plt.xticks(r1+bar_width/2, [1, 2, 3])\n",
    "\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "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>Survived</th>\n",
       "      <th>Name</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>isClass1</th>\n",
       "      <th>isClass2</th>\n",
       "      <th>isClass3</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PassengerId</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</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",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\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",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</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",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\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",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0</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",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0</td>\n",
       "      <td>Moran, Mr. James</td>\n",
       "      <td>male</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>330877</td>\n",
       "      <td>8.4583</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Q</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0</td>\n",
       "      <td>McCarthy, Mr. Timothy J</td>\n",
       "      <td>male</td>\n",
       "      <td>54.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>17463</td>\n",
       "      <td>51.8625</td>\n",
       "      <td>E46</td>\n",
       "      <td>S</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>0</td>\n",
       "      <td>Palsson, Master. Gosta Leonard</td>\n",
       "      <td>male</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>349909</td>\n",
       "      <td>21.0750</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>1</td>\n",
       "      <td>Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)</td>\n",
       "      <td>female</td>\n",
       "      <td>27.0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>347742</td>\n",
       "      <td>11.1333</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>1</td>\n",
       "      <td>Nasser, Mrs. Nicholas (Adele Achem)</td>\n",
       "      <td>female</td>\n",
       "      <td>14.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>237736</td>\n",
       "      <td>30.0708</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Survived                                               Name  \\\n",
       "PassengerId                                                                \n",
       "1                   0                            Braund, Mr. Owen Harris   \n",
       "2                   1  Cumings, Mrs. John Bradley (Florence Briggs Th...   \n",
       "3                   1                             Heikkinen, Miss. Laina   \n",
       "4                   1       Futrelle, Mrs. Jacques Heath (Lily May Peel)   \n",
       "5                   0                           Allen, Mr. William Henry   \n",
       "6                   0                                   Moran, Mr. James   \n",
       "7                   0                            McCarthy, Mr. Timothy J   \n",
       "8                   0                     Palsson, Master. Gosta Leonard   \n",
       "9                   1  Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)   \n",
       "10                  1                Nasser, Mrs. Nicholas (Adele Achem)   \n",
       "\n",
       "                Sex   Age  SibSp  Parch            Ticket     Fare Cabin  \\\n",
       "PassengerId                                                                \n",
       "1              male  22.0      1      0         A/5 21171   7.2500   NaN   \n",
       "2            female  38.0      1      0          PC 17599  71.2833   C85   \n",
       "3            female  26.0      0      0  STON/O2. 3101282   7.9250   NaN   \n",
       "4            female  35.0      1      0            113803  53.1000  C123   \n",
       "5              male  35.0      0      0            373450   8.0500   NaN   \n",
       "6              male   NaN      0      0            330877   8.4583   NaN   \n",
       "7              male  54.0      0      0             17463  51.8625   E46   \n",
       "8              male   2.0      3      1            349909  21.0750   NaN   \n",
       "9            female  27.0      0      2            347742  11.1333   NaN   \n",
       "10           female  14.0      1      0            237736  30.0708   NaN   \n",
       "\n",
       "            Embarked  isClass1  isClass2  isClass3  \n",
       "PassengerId                                         \n",
       "1                  S         0         0         1  \n",
       "2                  C         1         0         0  \n",
       "3                  S         0         0         1  \n",
       "4                  S         1         0         0  \n",
       "5                  S         0         0         1  \n",
       "6                  Q         0         0         1  \n",
       "7                  S         1         0         0  \n",
       "8                  S         0         0         1  \n",
       "9                  S         0         0         1  \n",
       "10                 C         0         1         0  "
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Веднага се забелязва че колкото по-висока класа си, толкова по-вероятно е да оживееш...\n",
    "# Да добавим one hot encoding на тази променлива към нашите данни\n",
    "\n",
    "data = train_init.copy()\n",
    "# Начин 1\n",
    "data[\"isClass1\"] = (data[\"Pclass\"] == 1) * 1\n",
    "data[\"isClass2\"] = (data[\"Pclass\"] == 2) * 1\n",
    "data[\"isClass3\"] = (data[\"Pclass\"] == 3) * 1\n",
    "data = data.drop(columns=\"Pclass\")\n",
    "data.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "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>Survived</th>\n",
       "      <th>Name</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>isClass_1</th>\n",
       "      <th>isClass_2</th>\n",
       "      <th>isClass_3</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PassengerId</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</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",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\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",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</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",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\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",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0</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",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0</td>\n",
       "      <td>Moran, Mr. James</td>\n",
       "      <td>male</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>330877</td>\n",
       "      <td>8.4583</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Q</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0</td>\n",
       "      <td>McCarthy, Mr. Timothy J</td>\n",
       "      <td>male</td>\n",
       "      <td>54.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>17463</td>\n",
       "      <td>51.8625</td>\n",
       "      <td>E46</td>\n",
       "      <td>S</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>0</td>\n",
       "      <td>Palsson, Master. Gosta Leonard</td>\n",
       "      <td>male</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>349909</td>\n",
       "      <td>21.0750</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>1</td>\n",
       "      <td>Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)</td>\n",
       "      <td>female</td>\n",
       "      <td>27.0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>347742</td>\n",
       "      <td>11.1333</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>1</td>\n",
       "      <td>Nasser, Mrs. Nicholas (Adele Achem)</td>\n",
       "      <td>female</td>\n",
       "      <td>14.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>237736</td>\n",
       "      <td>30.0708</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Survived                                               Name  \\\n",
       "PassengerId                                                                \n",
       "1                   0                            Braund, Mr. Owen Harris   \n",
       "2                   1  Cumings, Mrs. John Bradley (Florence Briggs Th...   \n",
       "3                   1                             Heikkinen, Miss. Laina   \n",
       "4                   1       Futrelle, Mrs. Jacques Heath (Lily May Peel)   \n",
       "5                   0                           Allen, Mr. William Henry   \n",
       "6                   0                                   Moran, Mr. James   \n",
       "7                   0                            McCarthy, Mr. Timothy J   \n",
       "8                   0                     Palsson, Master. Gosta Leonard   \n",
       "9                   1  Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)   \n",
       "10                  1                Nasser, Mrs. Nicholas (Adele Achem)   \n",
       "\n",
       "                Sex   Age  SibSp  Parch            Ticket     Fare Cabin  \\\n",
       "PassengerId                                                                \n",
       "1              male  22.0      1      0         A/5 21171   7.2500   NaN   \n",
       "2            female  38.0      1      0          PC 17599  71.2833   C85   \n",
       "3            female  26.0      0      0  STON/O2. 3101282   7.9250   NaN   \n",
       "4            female  35.0      1      0            113803  53.1000  C123   \n",
       "5              male  35.0      0      0            373450   8.0500   NaN   \n",
       "6              male   NaN      0      0            330877   8.4583   NaN   \n",
       "7              male  54.0      0      0             17463  51.8625   E46   \n",
       "8              male   2.0      3      1            349909  21.0750   NaN   \n",
       "9            female  27.0      0      2            347742  11.1333   NaN   \n",
       "10           female  14.0      1      0            237736  30.0708   NaN   \n",
       "\n",
       "            Embarked  isClass_1  isClass_2  isClass_3  \n",
       "PassengerId                                            \n",
       "1                  S          0          0          1  \n",
       "2                  C          1          0          0  \n",
       "3                  S          0          0          1  \n",
       "4                  S          1          0          0  \n",
       "5                  S          0          0          1  \n",
       "6                  Q          0          0          1  \n",
       "7                  S          1          0          0  \n",
       "8                  S          0          0          1  \n",
       "9                  S          0          0          1  \n",
       "10                 C          0          1          0  "
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data = train_init.copy()\n",
    "# Начин 2\n",
    "data[[\"isClass_1\", \"isClass_2\", \"isClass_3\"]] = pd.get_dummies(data[\"Pclass\"], prefix=\"isClass\") # забележка ако колоните имат еднакви имена, ги напасва\n",
    "\n",
    "data = data.drop(columns = \"Pclass\")\n",
    "data.head(10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "# Sex\n",
    "Тая колона ще е straight forward"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Да започнем пак с графика, подобна на тази за класа\n",
    "\n",
    "AliveSex = [[len(data[(data.Survived == x) & (data.Sex == y)]) for y in ['male', 'female']] for x in [0, 1]]\n",
    "\n",
    "r1 = np.arange(2)\n",
    "r2 = r1+bar_width\n",
    "\n",
    "plt.bar(r1, AliveSex[0], color=\"red\", width=bar_width, label=\"dead\")\n",
    "plt.bar(r2, AliveSex[1], color=\"blue\", width=bar_width, label=\"alive\")\n",
    "\n",
    "plt.xlabel(\"Sex\")\n",
    "plt.xticks(r1+bar_width/2, [\"male\", \"female\"])\n",
    "\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "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>Survived</th>\n",
       "      <th>Name</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>isClass_1</th>\n",
       "      <th>isClass_2</th>\n",
       "      <th>isClass_3</th>\n",
       "      <th>female</th>\n",
       "      <th>male</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PassengerId</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>Braund, Mr. Owen Harris</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",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</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",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>Heikkinen, Miss. Laina</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",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</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",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0</td>\n",
       "      <td>Allen, Mr. William Henry</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",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0</td>\n",
       "      <td>Moran, Mr. James</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>330877</td>\n",
       "      <td>8.4583</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Q</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0</td>\n",
       "      <td>McCarthy, Mr. Timothy J</td>\n",
       "      <td>54.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>17463</td>\n",
       "      <td>51.8625</td>\n",
       "      <td>E46</td>\n",
       "      <td>S</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>0</td>\n",
       "      <td>Palsson, Master. Gosta Leonard</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>349909</td>\n",
       "      <td>21.0750</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>1</td>\n",
       "      <td>Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)</td>\n",
       "      <td>27.0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>347742</td>\n",
       "      <td>11.1333</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>1</td>\n",
       "      <td>Nasser, Mrs. Nicholas (Adele Achem)</td>\n",
       "      <td>14.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>237736</td>\n",
       "      <td>30.0708</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Survived                                               Name  \\\n",
       "PassengerId                                                                \n",
       "1                   0                            Braund, Mr. Owen Harris   \n",
       "2                   1  Cumings, Mrs. John Bradley (Florence Briggs Th...   \n",
       "3                   1                             Heikkinen, Miss. Laina   \n",
       "4                   1       Futrelle, Mrs. Jacques Heath (Lily May Peel)   \n",
       "5                   0                           Allen, Mr. William Henry   \n",
       "6                   0                                   Moran, Mr. James   \n",
       "7                   0                            McCarthy, Mr. Timothy J   \n",
       "8                   0                     Palsson, Master. Gosta Leonard   \n",
       "9                   1  Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)   \n",
       "10                  1                Nasser, Mrs. Nicholas (Adele Achem)   \n",
       "\n",
       "              Age  SibSp  Parch            Ticket     Fare Cabin Embarked  \\\n",
       "PassengerId                                                                 \n",
       "1            22.0      1      0         A/5 21171   7.2500   NaN        S   \n",
       "2            38.0      1      0          PC 17599  71.2833   C85        C   \n",
       "3            26.0      0      0  STON/O2. 3101282   7.9250   NaN        S   \n",
       "4            35.0      1      0            113803  53.1000  C123        S   \n",
       "5            35.0      0      0            373450   8.0500   NaN        S   \n",
       "6             NaN      0      0            330877   8.4583   NaN        Q   \n",
       "7            54.0      0      0             17463  51.8625   E46        S   \n",
       "8             2.0      3      1            349909  21.0750   NaN        S   \n",
       "9            27.0      0      2            347742  11.1333   NaN        S   \n",
       "10           14.0      1      0            237736  30.0708   NaN        C   \n",
       "\n",
       "             isClass_1  isClass_2  isClass_3  female  male  \n",
       "PassengerId                                                 \n",
       "1                    0          0          1       0     1  \n",
       "2                    1          0          0       1     0  \n",
       "3                    0          0          1       1     0  \n",
       "4                    1          0          0       1     0  \n",
       "5                    0          0          1       0     1  \n",
       "6                    0          0          1       0     1  \n",
       "7                    1          0          0       0     1  \n",
       "8                    0          0          1       0     1  \n",
       "9                    0          0          1       1     0  \n",
       "10                   0          1          0       1     0  "
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Очакван резултат... както и филма ни казва, жените по-скоро са оживявали и мъжете по-скоро умирали...\n",
    "\n",
    "data[[\"female\", \"male\"]] = pd.get_dummies(data[\"Sex\"])\n",
    "\n",
    "data = data.drop(columns = \"Sex\")\n",
    "data.head(10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "# Колоните Name и Age\n",
    "Кво общо имат? Name не е ли безполезна?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Master mean age: 4.574166666666667\n",
      "Mr mean age: 32.368090452261306\n",
      "Mrs mean age: 35.898148148148145\n",
      "Miss mean age: 21.773972602739725\n"
     ]
    }
   ],
   "source": [
    "# Name на първи поглед изглежда безполезна, но всъщност в name се съдържа информация за тва колко е дърт човек.\n",
    "# Виждате че вътре има префикси на имената на всеки - Mr., Mrs., Master.\n",
    "\n",
    "print(\"Master mean age:\", data.loc[data.Name.str.contains(\"Master.\", regex=False), \"Age\"].mean())\n",
    "print(\"Mr mean age:\", data.loc[data.Name.str.contains(\"Mr.\", regex=False), \"Age\"].mean())\n",
    "print(\"Mrs mean age:\", data.loc[data.Name.str.contains(\"Mrs.\", regex=False), \"Age\"].mean())\n",
    "print(\"Miss mean age:\", data.loc[data.Name.str.contains(\"Miss.\", regex=False), \"Age\"].mean())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "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>Survived</th>\n",
       "      <th>Name</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>isClass_1</th>\n",
       "      <th>isClass_2</th>\n",
       "      <th>isClass_3</th>\n",
       "      <th>female</th>\n",
       "      <th>male</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PassengerId</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>Braund, Mr. Owen Harris</td>\n",
       "      <td>22.00000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>A/5 21171</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
       "      <td>38.00000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>PC 17599</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>C85</td>\n",
       "      <td>C</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>Heikkinen, Miss. Laina</td>\n",
       "      <td>26.00000</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>STON/O2. 3101282</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n",
       "      <td>35.00000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>113803</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>C123</td>\n",
       "      <td>S</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0</td>\n",
       "      <td>Allen, Mr. William Henry</td>\n",
       "      <td>35.00000</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>373450</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0</td>\n",
       "      <td>Moran, Mr. James</td>\n",
       "      <td>32.36809</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>330877</td>\n",
       "      <td>8.4583</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Q</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0</td>\n",
       "      <td>McCarthy, Mr. Timothy J</td>\n",
       "      <td>54.00000</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>17463</td>\n",
       "      <td>51.8625</td>\n",
       "      <td>E46</td>\n",
       "      <td>S</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>0</td>\n",
       "      <td>Palsson, Master. Gosta Leonard</td>\n",
       "      <td>2.00000</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>349909</td>\n",
       "      <td>21.0750</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>1</td>\n",
       "      <td>Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)</td>\n",
       "      <td>27.00000</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>347742</td>\n",
       "      <td>11.1333</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>1</td>\n",
       "      <td>Nasser, Mrs. Nicholas (Adele Achem)</td>\n",
       "      <td>14.00000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>237736</td>\n",
       "      <td>30.0708</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Survived                                               Name  \\\n",
       "PassengerId                                                                \n",
       "1                   0                            Braund, Mr. Owen Harris   \n",
       "2                   1  Cumings, Mrs. John Bradley (Florence Briggs Th...   \n",
       "3                   1                             Heikkinen, Miss. Laina   \n",
       "4                   1       Futrelle, Mrs. Jacques Heath (Lily May Peel)   \n",
       "5                   0                           Allen, Mr. William Henry   \n",
       "6                   0                                   Moran, Mr. James   \n",
       "7                   0                            McCarthy, Mr. Timothy J   \n",
       "8                   0                     Palsson, Master. Gosta Leonard   \n",
       "9                   1  Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)   \n",
       "10                  1                Nasser, Mrs. Nicholas (Adele Achem)   \n",
       "\n",
       "                  Age  SibSp  Parch            Ticket     Fare Cabin Embarked  \\\n",
       "PassengerId                                                                     \n",
       "1            22.00000      1      0         A/5 21171   7.2500   NaN        S   \n",
       "2            38.00000      1      0          PC 17599  71.2833   C85        C   \n",
       "3            26.00000      0      0  STON/O2. 3101282   7.9250   NaN        S   \n",
       "4            35.00000      1      0            113803  53.1000  C123        S   \n",
       "5            35.00000      0      0            373450   8.0500   NaN        S   \n",
       "6            32.36809      0      0            330877   8.4583   NaN        Q   \n",
       "7            54.00000      0      0             17463  51.8625   E46        S   \n",
       "8             2.00000      3      1            349909  21.0750   NaN        S   \n",
       "9            27.00000      0      2            347742  11.1333   NaN        S   \n",
       "10           14.00000      1      0            237736  30.0708   NaN        C   \n",
       "\n",
       "             isClass_1  isClass_2  isClass_3  female  male  \n",
       "PassengerId                                                 \n",
       "1                    0          0          1       0     1  \n",
       "2                    1          0          0       1     0  \n",
       "3                    0          0          1       1     0  \n",
       "4                    1          0          0       1     0  \n",
       "5                    0          0          1       0     1  \n",
       "6                    0          0          1       0     1  \n",
       "7                    1          0          0       0     1  \n",
       "8                    0          0          1       0     1  \n",
       "9                    0          0          1       1     0  \n",
       "10                   0          1          0       1     0  "
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Да попълним с тази информация дупките в колоната Age\n",
    "data.loc[data.Name.str.contains(\"Master.\", regex=False), \"Age\"] = data.loc[data.Name.str.contains(\"Master.\", regex=False), \"Age\"].fillna(\n",
    "    data.loc[data.Name.str.contains(\"Master.\", regex=False), \"Age\"].mean()\n",
    ")\n",
    "data.loc[data.Name.str.contains(\"Mr.\", regex=False), \"Age\"] = data.loc[data.Name.str.contains(\"Mr.\", regex=False), \"Age\"].fillna(\n",
    "    data.loc[data.Name.str.contains(\"Mr.\", regex=False), \"Age\"].mean()\n",
    ")\n",
    "data.loc[data.Name.str.contains(\"Mrs.\", regex=False), \"Age\"] = data.loc[data.Name.str.contains(\"Mrs.\", regex=False), \"Age\"].fillna(\n",
    "    data.loc[data.Name.str.contains(\"Mrs.\", regex=False), \"Age\"].mean()\n",
    ")\n",
    "data.loc[data.Name.str.contains(\"Miss.\", regex=False), \"Age\"] = data.loc[data.Name.str.contains(\"Miss.\", regex=False), \"Age\"].fillna(\n",
    "    data.loc[data.Name.str.contains(\"Miss.\", regex=False), \"Age\"].mean()\n",
    ")\n",
    "\n",
    "data.loc[:, \"Age\"] = data.loc[:, \"Age\"].fillna(data.loc[:, \"Age\"].mean())\n",
    "\n",
    "data.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "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>Survived</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>isClass_1</th>\n",
       "      <th>isClass_2</th>\n",
       "      <th>isClass_3</th>\n",
       "      <th>female</th>\n",
       "      <th>male</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PassengerId</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>22.00000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>A/5 21171</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>38.00000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>PC 17599</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>C85</td>\n",
       "      <td>C</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>26.00000</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>STON/O2. 3101282</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>35.00000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>113803</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>C123</td>\n",
       "      <td>S</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0</td>\n",
       "      <td>35.00000</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>373450</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0</td>\n",
       "      <td>32.36809</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>330877</td>\n",
       "      <td>8.4583</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Q</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0</td>\n",
       "      <td>54.00000</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>17463</td>\n",
       "      <td>51.8625</td>\n",
       "      <td>E46</td>\n",
       "      <td>S</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>0</td>\n",
       "      <td>2.00000</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>349909</td>\n",
       "      <td>21.0750</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>1</td>\n",
       "      <td>27.00000</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>347742</td>\n",
       "      <td>11.1333</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>1</td>\n",
       "      <td>14.00000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>237736</td>\n",
       "      <td>30.0708</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Survived       Age  SibSp  Parch            Ticket     Fare  \\\n",
       "PassengerId                                                                \n",
       "1                   0  22.00000      1      0         A/5 21171   7.2500   \n",
       "2                   1  38.00000      1      0          PC 17599  71.2833   \n",
       "3                   1  26.00000      0      0  STON/O2. 3101282   7.9250   \n",
       "4                   1  35.00000      1      0            113803  53.1000   \n",
       "5                   0  35.00000      0      0            373450   8.0500   \n",
       "6                   0  32.36809      0      0            330877   8.4583   \n",
       "7                   0  54.00000      0      0             17463  51.8625   \n",
       "8                   0   2.00000      3      1            349909  21.0750   \n",
       "9                   1  27.00000      0      2            347742  11.1333   \n",
       "10                  1  14.00000      1      0            237736  30.0708   \n",
       "\n",
       "            Cabin Embarked  isClass_1  isClass_2  isClass_3  female  male  \n",
       "PassengerId                                                                \n",
       "1             NaN        S          0          0          1       0     1  \n",
       "2             C85        C          1          0          0       1     0  \n",
       "3             NaN        S          0          0          1       1     0  \n",
       "4            C123        S          1          0          0       1     0  \n",
       "5             NaN        S          0          0          1       0     1  \n",
       "6             NaN        Q          0          0          1       0     1  \n",
       "7             E46        S          1          0          0       0     1  \n",
       "8             NaN        S          0          0          1       0     1  \n",
       "9             NaN        S          0          0          1       1     0  \n",
       "10            NaN        C          0          1          0       1     0  "
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data = data.drop(columns = \"Name\")\n",
    "data.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Сега да видим картинка за връзката между възрастта и оцеляването както правихме последния път\n",
    "\n",
    "AgeMeans = [data.loc[data.Survived == x, \"Age\"].mean() for x in [0, 1]]\n",
    "\n",
    "plt.bar([0, 1], AgeMeans)\n",
    "\n",
    "plt.xticks([0, 1], [\"dead\", \"alive\"])\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 504x504 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Обаче това че средната възразст на умрелите е гд същата като на оживелите може и да не се дължи на това че няма връзка между\n",
    "# възрастта и оцеляването\n",
    "\n",
    "# Да видим нов тип графика която най-често е полезна при връзка между категорийни и числови променливи\n",
    "plt.figure(figsize=(7, 7))\n",
    "plt.boxplot([data.loc[data.Survived == x, \"Age\"] for x in [0, 1]])\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Така може да забележим че разпределенията са различни, хистограми ще са полезни\n",
    "\n",
    "diff = 10\n",
    "maxAge = int(data.Age.max())\n",
    "AliveAge = [[len(data[(data.Survived == x) & (data.Age >= y) & (data.Age < y+diff)]) for y in range(0, maxAge, diff)] for x in [0, 1]]\n",
    "\n",
    "r1 = np.arange(maxAge//diff)\n",
    "r2 = r1 + bar_width\n",
    "\n",
    "plt.bar(r1, AliveAge[0], color=\"red\", width=bar_width, label=\"dead\")\n",
    "plt.bar(r2, AliveAge[1], color=\"blue\", width=bar_width, label=\"alive\")\n",
    "\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "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>Survived</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>isClass_1</th>\n",
       "      <th>isClass_2</th>\n",
       "      <th>isClass_3</th>\n",
       "      <th>female</th>\n",
       "      <th>male</th>\n",
       "      <th>Age0-9</th>\n",
       "      <th>Age10-19</th>\n",
       "      <th>Age20-29</th>\n",
       "      <th>Age30-39</th>\n",
       "      <th>Age40-49</th>\n",
       "      <th>Age50-59</th>\n",
       "      <th>Age60-69</th>\n",
       "      <th>Age70-79</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PassengerId</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>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",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>PC 17599</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>C85</td>\n",
       "      <td>C</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>STON/O2. 3101282</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>113803</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>C123</td>\n",
       "      <td>S</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>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",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>330877</td>\n",
       "      <td>8.4583</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Q</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>17463</td>\n",
       "      <td>51.8625</td>\n",
       "      <td>E46</td>\n",
       "      <td>S</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>349909</td>\n",
       "      <td>21.0750</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>347742</td>\n",
       "      <td>11.1333</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>237736</td>\n",
       "      <td>30.0708</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Survived  SibSp  Parch            Ticket     Fare Cabin Embarked  \\\n",
       "PassengerId                                                                     \n",
       "1                   0      1      0         A/5 21171   7.2500   NaN        S   \n",
       "2                   1      1      0          PC 17599  71.2833   C85        C   \n",
       "3                   1      0      0  STON/O2. 3101282   7.9250   NaN        S   \n",
       "4                   1      1      0            113803  53.1000  C123        S   \n",
       "5                   0      0      0            373450   8.0500   NaN        S   \n",
       "6                   0      0      0            330877   8.4583   NaN        Q   \n",
       "7                   0      0      0             17463  51.8625   E46        S   \n",
       "8                   0      3      1            349909  21.0750   NaN        S   \n",
       "9                   1      0      2            347742  11.1333   NaN        S   \n",
       "10                  1      1      0            237736  30.0708   NaN        C   \n",
       "\n",
       "             isClass_1  isClass_2  isClass_3  female  male  Age0-9  Age10-19  \\\n",
       "PassengerId                                                                    \n",
       "1                    0          0          1       0     1       0         0   \n",
       "2                    1          0          0       1     0       0         0   \n",
       "3                    0          0          1       1     0       0         0   \n",
       "4                    1          0          0       1     0       0         0   \n",
       "5                    0          0          1       0     1       0         0   \n",
       "6                    0          0          1       0     1       0         0   \n",
       "7                    1          0          0       0     1       0         0   \n",
       "8                    0          0          1       0     1       1         0   \n",
       "9                    0          0          1       1     0       0         0   \n",
       "10                   0          1          0       1     0       0         1   \n",
       "\n",
       "             Age20-29  Age30-39  Age40-49  Age50-59  Age60-69  Age70-79  \n",
       "PassengerId                                                              \n",
       "1                   1         0         0         0         0         0  \n",
       "2                   0         1         0         0         0         0  \n",
       "3                   1         0         0         0         0         0  \n",
       "4                   0         1         0         0         0         0  \n",
       "5                   0         1         0         0         0         0  \n",
       "6                   0         1         0         0         0         0  \n",
       "7                   0         0         0         1         0         0  \n",
       "8                   0         0         0         0         0         0  \n",
       "9                   1         0         0         0         0         0  \n",
       "10                  0         0         0         0         0         0  "
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Така виждаме разликата в хистограмите година за година. Явно е че децата имат по-голям процент оцелели.\n",
    "# Ще вкарам тези години през 10 в 10 различни колони\n",
    "\n",
    "for i in range(0, maxAge, diff):\n",
    "    data[f\"Age{i}-{i+diff-1}\"] = ((data[\"Age\"] >= i) & (data[\"Age\"] < i+diff)) * 1\n",
    "    \n",
    "data = data.drop(columns = \"Age\")\n",
    "data.head(10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "# Parch and SibSp\n",
    "Брой родители и деца и брой братя и сестри"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Да направим boxplot-чета\n",
    "\n",
    "plt.boxplot([data.loc[data.Survived==x, \"SibSp\"] for x in [0, 1]], vert=False)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.boxplot([data.loc[data.Survived==x, \"Parch\"] for x in [0, 1]], vert=False)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "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>Survived</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>isClass_1</th>\n",
       "      <th>isClass_2</th>\n",
       "      <th>isClass_3</th>\n",
       "      <th>female</th>\n",
       "      <th>male</th>\n",
       "      <th>Age0-9</th>\n",
       "      <th>Age10-19</th>\n",
       "      <th>Age20-29</th>\n",
       "      <th>Age30-39</th>\n",
       "      <th>Age40-49</th>\n",
       "      <th>Age50-59</th>\n",
       "      <th>Age60-69</th>\n",
       "      <th>Age70-79</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PassengerId</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>A/5 21171</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>PC 17599</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>C85</td>\n",
       "      <td>C</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>STON/O2. 3101282</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>113803</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>C123</td>\n",
       "      <td>S</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>373450</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>330877</td>\n",
       "      <td>8.4583</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Q</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>17463</td>\n",
       "      <td>51.8625</td>\n",
       "      <td>E46</td>\n",
       "      <td>S</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>349909</td>\n",
       "      <td>21.0750</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>347742</td>\n",
       "      <td>11.1333</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>237736</td>\n",
       "      <td>30.0708</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Survived  Parch            Ticket     Fare Cabin Embarked  \\\n",
       "PassengerId                                                              \n",
       "1                   0      0         A/5 21171   7.2500   NaN        S   \n",
       "2                   1      0          PC 17599  71.2833   C85        C   \n",
       "3                   1      0  STON/O2. 3101282   7.9250   NaN        S   \n",
       "4                   1      0            113803  53.1000  C123        S   \n",
       "5                   0      0            373450   8.0500   NaN        S   \n",
       "6                   0      0            330877   8.4583   NaN        Q   \n",
       "7                   0      0             17463  51.8625   E46        S   \n",
       "8                   0      1            349909  21.0750   NaN        S   \n",
       "9                   1      2            347742  11.1333   NaN        S   \n",
       "10                  1      0            237736  30.0708   NaN        C   \n",
       "\n",
       "             isClass_1  isClass_2  isClass_3  female  male  Age0-9  Age10-19  \\\n",
       "PassengerId                                                                    \n",
       "1                    0          0          1       0     1       0         0   \n",
       "2                    1          0          0       1     0       0         0   \n",
       "3                    0          0          1       1     0       0         0   \n",
       "4                    1          0          0       1     0       0         0   \n",
       "5                    0          0          1       0     1       0         0   \n",
       "6                    0          0          1       0     1       0         0   \n",
       "7                    1          0          0       0     1       0         0   \n",
       "8                    0          0          1       0     1       1         0   \n",
       "9                    0          0          1       1     0       0         0   \n",
       "10                   0          1          0       1     0       0         1   \n",
       "\n",
       "             Age20-29  Age30-39  Age40-49  Age50-59  Age60-69  Age70-79  \n",
       "PassengerId                                                              \n",
       "1                   1         0         0         0         0         0  \n",
       "2                   0         1         0         0         0         0  \n",
       "3                   1         0         0         0         0         0  \n",
       "4                   0         1         0         0         0         0  \n",
       "5                   0         1         0         0         0         0  \n",
       "6                   0         1         0         0         0         0  \n",
       "7                   0         0         0         1         0         0  \n",
       "8                   0         0         0         0         0         0  \n",
       "9                   1         0         0         0         0         0  \n",
       "10                  0         0         0         0         0         0  "
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Изглежда броя братя, сестри е безполезен, само outlier-ите се отличават\n",
    "# Обаче в броя деца и родители има някаква разлика. Тея с повече деца и родители явно живеят повече.\n",
    "# Тъй като в случая връзката изглежда колкото повече толкова по-добре, няма да one hot encode-вам\n",
    "\n",
    "data = data.drop(columns = \"SibSp\")\n",
    "data.head(10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "# Ticket and Fare"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "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>Survived</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>isClass_1</th>\n",
       "      <th>isClass_2</th>\n",
       "      <th>isClass_3</th>\n",
       "      <th>female</th>\n",
       "      <th>male</th>\n",
       "      <th>Age0-9</th>\n",
       "      <th>Age10-19</th>\n",
       "      <th>Age20-29</th>\n",
       "      <th>Age30-39</th>\n",
       "      <th>Age40-49</th>\n",
       "      <th>Age50-59</th>\n",
       "      <th>Age60-69</th>\n",
       "      <th>Age70-79</th>\n",
       "      <th>TicketFreq</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PassengerId</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>C85</td>\n",
       "      <td>C</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</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>0</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>C123</td>\n",
       "      <td>S</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.4583</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Q</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>51.8625</td>\n",
       "      <td>E46</td>\n",
       "      <td>S</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>21.0750</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>11.1333</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>30.0708</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Survived  Parch     Fare Cabin Embarked  isClass_1  isClass_2  \\\n",
       "PassengerId                                                                  \n",
       "1                   0      0   7.2500   NaN        S          0          0   \n",
       "2                   1      0  71.2833   C85        C          1          0   \n",
       "3                   1      0   7.9250   NaN        S          0          0   \n",
       "4                   1      0  53.1000  C123        S          1          0   \n",
       "5                   0      0   8.0500   NaN        S          0          0   \n",
       "6                   0      0   8.4583   NaN        Q          0          0   \n",
       "7                   0      0  51.8625   E46        S          1          0   \n",
       "8                   0      1  21.0750   NaN        S          0          0   \n",
       "9                   1      2  11.1333   NaN        S          0          0   \n",
       "10                  1      0  30.0708   NaN        C          0          1   \n",
       "\n",
       "             isClass_3  female  male  Age0-9  Age10-19  Age20-29  Age30-39  \\\n",
       "PassengerId                                                                  \n",
       "1                    1       0     1       0         0         1         0   \n",
       "2                    0       1     0       0         0         0         1   \n",
       "3                    1       1     0       0         0         1         0   \n",
       "4                    0       1     0       0         0         0         1   \n",
       "5                    1       0     1       0         0         0         1   \n",
       "6                    1       0     1       0         0         0         1   \n",
       "7                    0       0     1       0         0         0         0   \n",
       "8                    1       0     1       1         0         0         0   \n",
       "9                    1       1     0       0         0         1         0   \n",
       "10                   0       1     0       0         1         0         0   \n",
       "\n",
       "             Age40-49  Age50-59  Age60-69  Age70-79  TicketFreq  \n",
       "PassengerId                                                      \n",
       "1                   0         0         0         0           1  \n",
       "2                   0         0         0         0           1  \n",
       "3                   0         0         0         0           1  \n",
       "4                   0         0         0         0           2  \n",
       "5                   0         0         0         0           1  \n",
       "6                   0         0         0         0           1  \n",
       "7                   0         1         0         0           1  \n",
       "8                   0         0         0         0           4  \n",
       "9                   0         0         0         0           3  \n",
       "10                  0         0         0         0           2  "
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Ticket изглежда безполезно, от описанието на данните в kaggle има яснота че някои номера на билети се срещат по над веднъж,\n",
    "# така че може би всеки билет колко пъти се среща би дало някакъв сигнал\n",
    "\n",
    "# Правя го квадратно ма е на 1 ред :D\n",
    "data[\"TicketFreq\"] = [sum(data[\"Ticket\"]==x) for x in data[\"Ticket\"]]\n",
    "data = data.drop(columns=\"Ticket\")\n",
    "data.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Ся пак 2 boxplot-а\n",
    "\n",
    "plt.boxplot([data.loc[data.Survived==x, \"TicketFreq\"] for x in [0, 1]], vert=False)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.boxplot([data.loc[data.Survived==x, \"Fare\"] for x in [0, 1]], vert=False)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "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>Survived</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>isClass_1</th>\n",
       "      <th>isClass_2</th>\n",
       "      <th>isClass_3</th>\n",
       "      <th>female</th>\n",
       "      <th>male</th>\n",
       "      <th>Age0-9</th>\n",
       "      <th>Age10-19</th>\n",
       "      <th>Age20-29</th>\n",
       "      <th>Age30-39</th>\n",
       "      <th>Age40-49</th>\n",
       "      <th>Age50-59</th>\n",
       "      <th>Age60-69</th>\n",
       "      <th>Age70-79</th>\n",
       "      <th>TicketFreq</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PassengerId</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>C85</td>\n",
       "      <td>C</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</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>0</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>C123</td>\n",
       "      <td>S</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.4583</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Q</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>51.8625</td>\n",
       "      <td>E46</td>\n",
       "      <td>S</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>21.0750</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>11.1333</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>30.0708</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Survived  Parch     Fare Cabin Embarked  isClass_1  isClass_2  \\\n",
       "PassengerId                                                                  \n",
       "1                   0      0   7.2500   NaN        S          0          0   \n",
       "2                   1      0  71.2833   C85        C          1          0   \n",
       "3                   1      0   7.9250   NaN        S          0          0   \n",
       "4                   1      0  53.1000  C123        S          1          0   \n",
       "5                   0      0   8.0500   NaN        S          0          0   \n",
       "6                   0      0   8.4583   NaN        Q          0          0   \n",
       "7                   0      0  51.8625   E46        S          1          0   \n",
       "8                   0      1  21.0750   NaN        S          0          0   \n",
       "9                   1      2  11.1333   NaN        S          0          0   \n",
       "10                  1      0  30.0708   NaN        C          0          1   \n",
       "\n",
       "             isClass_3  female  male  Age0-9  Age10-19  Age20-29  Age30-39  \\\n",
       "PassengerId                                                                  \n",
       "1                    1       0     1       0         0         1         0   \n",
       "2                    0       1     0       0         0         0         1   \n",
       "3                    1       1     0       0         0         1         0   \n",
       "4                    0       1     0       0         0         0         1   \n",
       "5                    1       0     1       0         0         0         1   \n",
       "6                    1       0     1       0         0         0         1   \n",
       "7                    0       0     1       0         0         0         0   \n",
       "8                    1       0     1       1         0         0         0   \n",
       "9                    1       1     0       0         0         1         0   \n",
       "10                   0       1     0       0         1         0         0   \n",
       "\n",
       "             Age40-49  Age50-59  Age60-69  Age70-79  TicketFreq  \n",
       "PassengerId                                                      \n",
       "1                   0         0         0         0           1  \n",
       "2                   0         0         0         0           1  \n",
       "3                   0         0         0         0           1  \n",
       "4                   0         0         0         0           2  \n",
       "5                   0         0         0         0           1  \n",
       "6                   0         0         0         0           1  \n",
       "7                   0         1         0         0           1  \n",
       "8                   0         0         0         0           4  \n",
       "9                   0         0         0         0           3  \n",
       "10                  0         0         0         0           2  "
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Ами така като гледам TicketFreq носи някъв потенциално минимален сигнал, Цената като че ли носи повече сигнал.\n",
    "# Хубавото и при двете е че имаме наредба спрямо survived, така че може да не ги енкодваме.\n",
    "# Съответно няма да ги пипам повече.\n",
    "data.head(10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "# Cabin\n",
    "Безполезна ли е тази колона"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.7710437710437711"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sum(data.Cabin.isna())/len(data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [],
   "source": [
    "# 77% NaN\n",
    "# Освен това останалите стойности са уникални... Ква полза може да имаме?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "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>Survived</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>isClass_1</th>\n",
       "      <th>isClass_2</th>\n",
       "      <th>isClass_3</th>\n",
       "      <th>female</th>\n",
       "      <th>male</th>\n",
       "      <th>Age0-9</th>\n",
       "      <th>Age10-19</th>\n",
       "      <th>Age20-29</th>\n",
       "      <th>Age30-39</th>\n",
       "      <th>Age40-49</th>\n",
       "      <th>Age50-59</th>\n",
       "      <th>Age60-69</th>\n",
       "      <th>Age70-79</th>\n",
       "      <th>TicketFreq</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PassengerId</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>C</td>\n",
       "      <td>C</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</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>0</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>C</td>\n",
       "      <td>S</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.4583</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Q</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>51.8625</td>\n",
       "      <td>E</td>\n",
       "      <td>S</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>21.0750</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>11.1333</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>30.0708</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Survived  Parch     Fare Cabin Embarked  isClass_1  isClass_2  \\\n",
       "PassengerId                                                                  \n",
       "1                   0      0   7.2500   NaN        S          0          0   \n",
       "2                   1      0  71.2833     C        C          1          0   \n",
       "3                   1      0   7.9250   NaN        S          0          0   \n",
       "4                   1      0  53.1000     C        S          1          0   \n",
       "5                   0      0   8.0500   NaN        S          0          0   \n",
       "6                   0      0   8.4583   NaN        Q          0          0   \n",
       "7                   0      0  51.8625     E        S          1          0   \n",
       "8                   0      1  21.0750   NaN        S          0          0   \n",
       "9                   1      2  11.1333   NaN        S          0          0   \n",
       "10                  1      0  30.0708   NaN        C          0          1   \n",
       "\n",
       "             isClass_3  female  male  Age0-9  Age10-19  Age20-29  Age30-39  \\\n",
       "PassengerId                                                                  \n",
       "1                    1       0     1       0         0         1         0   \n",
       "2                    0       1     0       0         0         0         1   \n",
       "3                    1       1     0       0         0         1         0   \n",
       "4                    0       1     0       0         0         0         1   \n",
       "5                    1       0     1       0         0         0         1   \n",
       "6                    1       0     1       0         0         0         1   \n",
       "7                    0       0     1       0         0         0         0   \n",
       "8                    1       0     1       1         0         0         0   \n",
       "9                    1       1     0       0         0         1         0   \n",
       "10                   0       1     0       0         1         0         0   \n",
       "\n",
       "             Age40-49  Age50-59  Age60-69  Age70-79  TicketFreq  \n",
       "PassengerId                                                      \n",
       "1                   0         0         0         0           1  \n",
       "2                   0         0         0         0           1  \n",
       "3                   0         0         0         0           1  \n",
       "4                   0         0         0         0           2  \n",
       "5                   0         0         0         0           1  \n",
       "6                   0         0         0         0           1  \n",
       "7                   0         1         0         0           1  \n",
       "8                   0         0         0         0           4  \n",
       "9                   0         0         0         0           3  \n",
       "10                  0         0         0         0           2  "
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Отговор: може да видим Първите букви които сигурно отговарят на палуба или нещо такова\n",
    "# И все пак дори първата буква да носи сигнал, тя ще влияе на само 23% от данните,\n",
    "# т.е. колко полезен може да е този атрибут е умножено по 1/4 щото само в толкова от данните изобщо може да повлияе...\n",
    "# И без тва си утрепахме много време... Да видим дали ще се струва?\n",
    "data[\"Cabin\"] = data[\"Cabin\"].str[0]\n",
    "data.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([nan, 'C', 'E', 'G', 'D', 'A', 'B', 'F', 'T'], dtype=object)"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "vals = data[\"Cabin\"].unique()\n",
    "vals"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [],
   "source": [
    "vals = vals[1:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "AliveCabin = [[sum((data.Cabin == y) & (data.Survived == x)) for y in vals] for x in [0, 1]]\n",
    "\n",
    "r1 = np.arange(len(vals))\n",
    "r2 = r1 + bar_width\n",
    "\n",
    "plt.bar(r1, AliveCabin[0], color=\"red\", width=bar_width, label=\"dead\")\n",
    "plt.bar(r2, AliveCabin[1], color=\"blue\", width=bar_width, label=\"alive\")\n",
    "\n",
    "plt.xticks(r1+bar_width/2, vals)\n",
    "\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "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>Survived</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "      <th>isClass_1</th>\n",
       "      <th>isClass_2</th>\n",
       "      <th>isClass_3</th>\n",
       "      <th>female</th>\n",
       "      <th>male</th>\n",
       "      <th>Age0-9</th>\n",
       "      <th>...</th>\n",
       "      <th>Age70-79</th>\n",
       "      <th>TicketFreq</th>\n",
       "      <th>Cabin_A</th>\n",
       "      <th>Cabin_B</th>\n",
       "      <th>Cabin_C</th>\n",
       "      <th>Cabin_D</th>\n",
       "      <th>Cabin_E</th>\n",
       "      <th>Cabin_F</th>\n",
       "      <th>Cabin_G</th>\n",
       "      <th>Cabin_T</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PassengerId</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>C</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>S</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.4583</td>\n",
       "      <td>Q</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>51.8625</td>\n",
       "      <td>S</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>21.0750</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>11.1333</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>30.0708</td>\n",
       "      <td>C</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>10 rows × 26 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "             Survived  Parch     Fare Embarked  isClass_1  isClass_2  \\\n",
       "PassengerId                                                            \n",
       "1                   0      0   7.2500        S          0          0   \n",
       "2                   1      0  71.2833        C          1          0   \n",
       "3                   1      0   7.9250        S          0          0   \n",
       "4                   1      0  53.1000        S          1          0   \n",
       "5                   0      0   8.0500        S          0          0   \n",
       "6                   0      0   8.4583        Q          0          0   \n",
       "7                   0      0  51.8625        S          1          0   \n",
       "8                   0      1  21.0750        S          0          0   \n",
       "9                   1      2  11.1333        S          0          0   \n",
       "10                  1      0  30.0708        C          0          1   \n",
       "\n",
       "             isClass_3  female  male  Age0-9   ...     Age70-79  TicketFreq  \\\n",
       "PassengerId                                    ...                            \n",
       "1                    1       0     1       0   ...            0           1   \n",
       "2                    0       1     0       0   ...            0           1   \n",
       "3                    1       1     0       0   ...            0           1   \n",
       "4                    0       1     0       0   ...            0           2   \n",
       "5                    1       0     1       0   ...            0           1   \n",
       "6                    1       0     1       0   ...            0           1   \n",
       "7                    0       0     1       0   ...            0           1   \n",
       "8                    1       0     1       1   ...            0           4   \n",
       "9                    1       1     0       0   ...            0           3   \n",
       "10                   0       1     0       0   ...            0           2   \n",
       "\n",
       "             Cabin_A  Cabin_B  Cabin_C  Cabin_D  Cabin_E  Cabin_F  Cabin_G  \\\n",
       "PassengerId                                                                  \n",
       "1                  0        0        0        0        0        0        0   \n",
       "2                  0        0        1        0        0        0        0   \n",
       "3                  0        0        0        0        0        0        0   \n",
       "4                  0        0        1        0        0        0        0   \n",
       "5                  0        0        0        0        0        0        0   \n",
       "6                  0        0        0        0        0        0        0   \n",
       "7                  0        0        0        0        1        0        0   \n",
       "8                  0        0        0        0        0        0        0   \n",
       "9                  0        0        0        0        0        0        0   \n",
       "10                 0        0        0        0        0        0        0   \n",
       "\n",
       "             Cabin_T  \n",
       "PassengerId           \n",
       "1                  0  \n",
       "2                  0  \n",
       "3                  0  \n",
       "4                  0  \n",
       "5                  0  \n",
       "6                  0  \n",
       "7                  0  \n",
       "8                  0  \n",
       "9                  0  \n",
       "10                 0  \n",
       "\n",
       "[10 rows x 26 columns]"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Интересно, като цяло тези за които има данни оживяват повечко\n",
    "# Все пак трябва да имаме предвид статистическата незначимост на сравнително малкото количество данни.\n",
    "# Ся кат се замисля възможно е начина по който са събирали тея данни е да питат оцелелите абе в коя каюта беше? Случайно да познаваш някои другу в кои каюти са били?\n",
    "# Ще ги добавя все пак.\n",
    "data[sorted([\"Cabin_\"+v for v in vals])] = pd.get_dummies(data[\"Cabin\"], prefix=\"Cabin\")\n",
    "data = data.drop(columns = \"Cabin\")\n",
    "data.head(10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "# Embarked\n",
    "Почти сме готови с feature engineering"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "vals = data.Embarked.unique()\n",
    "\n",
    "AliveEmbarked = [[sum((data.Survived == x) & (data.Embarked == y)) for y in vals] for x in [0, 1]]\n",
    "\n",
    "r1 = np.arange(len(vals))\n",
    "r2 = r1 + bar_width\n",
    "\n",
    "plt.bar(r1, AliveEmbarked[0], color=\"red\", width=bar_width, label=\"dead\")\n",
    "plt.bar(r2, AliveEmbarked[1], color=\"blue\", width=bar_width, label=\"alive\")\n",
    "\n",
    "plt.xticks(r1+bar_width/2, vals)\n",
    "\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "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>Survived</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Fare</th>\n",
       "      <th>isClass_1</th>\n",
       "      <th>isClass_2</th>\n",
       "      <th>isClass_3</th>\n",
       "      <th>female</th>\n",
       "      <th>male</th>\n",
       "      <th>Age0-9</th>\n",
       "      <th>Age10-19</th>\n",
       "      <th>...</th>\n",
       "      <th>Cabin_B</th>\n",
       "      <th>Cabin_C</th>\n",
       "      <th>Cabin_D</th>\n",
       "      <th>Cabin_E</th>\n",
       "      <th>Cabin_F</th>\n",
       "      <th>Cabin_G</th>\n",
       "      <th>Cabin_T</th>\n",
       "      <th>Embarked_C</th>\n",
       "      <th>Embarked_Q</th>\n",
       "      <th>Embarked_S</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PassengerId</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.4583</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>51.8625</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>21.0750</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>11.1333</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>30.0708</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>10 rows × 28 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "             Survived  Parch     Fare  isClass_1  isClass_2  isClass_3  \\\n",
       "PassengerId                                                              \n",
       "1                   0      0   7.2500          0          0          1   \n",
       "2                   1      0  71.2833          1          0          0   \n",
       "3                   1      0   7.9250          0          0          1   \n",
       "4                   1      0  53.1000          1          0          0   \n",
       "5                   0      0   8.0500          0          0          1   \n",
       "6                   0      0   8.4583          0          0          1   \n",
       "7                   0      0  51.8625          1          0          0   \n",
       "8                   0      1  21.0750          0          0          1   \n",
       "9                   1      2  11.1333          0          0          1   \n",
       "10                  1      0  30.0708          0          1          0   \n",
       "\n",
       "             female  male  Age0-9  Age10-19     ...      Cabin_B  Cabin_C  \\\n",
       "PassengerId                                     ...                         \n",
       "1                 0     1       0         0     ...            0        0   \n",
       "2                 1     0       0         0     ...            0        1   \n",
       "3                 1     0       0         0     ...            0        0   \n",
       "4                 1     0       0         0     ...            0        1   \n",
       "5                 0     1       0         0     ...            0        0   \n",
       "6                 0     1       0         0     ...            0        0   \n",
       "7                 0     1       0         0     ...            0        0   \n",
       "8                 0     1       1         0     ...            0        0   \n",
       "9                 1     0       0         0     ...            0        0   \n",
       "10                1     0       0         1     ...            0        0   \n",
       "\n",
       "             Cabin_D  Cabin_E  Cabin_F  Cabin_G  Cabin_T  Embarked_C  \\\n",
       "PassengerId                                                            \n",
       "1                  0        0        0        0        0           0   \n",
       "2                  0        0        0        0        0           1   \n",
       "3                  0        0        0        0        0           0   \n",
       "4                  0        0        0        0        0           0   \n",
       "5                  0        0        0        0        0           0   \n",
       "6                  0        0        0        0        0           0   \n",
       "7                  0        1        0        0        0           0   \n",
       "8                  0        0        0        0        0           0   \n",
       "9                  0        0        0        0        0           0   \n",
       "10                 0        0        0        0        0           1   \n",
       "\n",
       "             Embarked_Q  Embarked_S  \n",
       "PassengerId                          \n",
       "1                     0           1  \n",
       "2                     0           0  \n",
       "3                     0           1  \n",
       "4                     0           1  \n",
       "5                     0           1  \n",
       "6                     1           0  \n",
       "7                     0           1  \n",
       "8                     0           1  \n",
       "9                     0           1  \n",
       "10                    0           0  \n",
       "\n",
       "[10 rows x 28 columns]"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Има сигнал, са виждам че има и nan, но при one hot encoding e ок да го оставим така.\n",
    "vals = vals[:-1]\n",
    "data[sorted([\"Embarked_\"+v for v in vals])] = pd.get_dummies(data[\"Embarked\"], prefix=\"Embarked\")\n",
    "data = data.drop(columns = \"Embarked\")\n",
    "data.head(10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "# Няколко думи за статистика\n",
    "При този анализ на връзки между feature-и често се използват статистически тестове.\n",
    "Няколко думи за това..."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "# Да си направим моделите"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "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>params</th>\n",
       "      <th>rank_test_score</th>\n",
       "      <th>mean_train_score</th>\n",
       "      <th>mean_test_score</th>\n",
       "      <th>mean_fit_time</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>{'C': 0.01}</td>\n",
       "      <td>5</td>\n",
       "      <td>0.799938</td>\n",
       "      <td>0.784512</td>\n",
       "      <td>0.003189</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>{'C': 0.1}</td>\n",
       "      <td>4</td>\n",
       "      <td>0.805837</td>\n",
       "      <td>0.793490</td>\n",
       "      <td>0.003787</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>{'C': 1}</td>\n",
       "      <td>3</td>\n",
       "      <td>0.819867</td>\n",
       "      <td>0.803591</td>\n",
       "      <td>0.005395</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>{'C': 10.0}</td>\n",
       "      <td>2</td>\n",
       "      <td>0.822952</td>\n",
       "      <td>0.804714</td>\n",
       "      <td>0.006601</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>{'C': 100.0}</td>\n",
       "      <td>1</td>\n",
       "      <td>0.823232</td>\n",
       "      <td>0.808081</td>\n",
       "      <td>0.007404</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         params  rank_test_score  mean_train_score  mean_test_score  \\\n",
       "0   {'C': 0.01}                5          0.799938         0.784512   \n",
       "1    {'C': 0.1}                4          0.805837         0.793490   \n",
       "2      {'C': 1}                3          0.819867         0.803591   \n",
       "3   {'C': 10.0}                2          0.822952         0.804714   \n",
       "4  {'C': 100.0}                1          0.823232         0.808081   \n",
       "\n",
       "   mean_fit_time  \n",
       "0       0.003189  \n",
       "1       0.003787  \n",
       "2       0.005395  \n",
       "3       0.006601  \n",
       "4       0.007404  "
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Директно ще ви покажа grid search (нахалния начин да научкаме хиперпараметрите :D)\n",
    "\n",
    "from sklearn.model_selection import GridSearchCV\n",
    "\n",
    "log_reg = LogisticRegression(random_state=42)\n",
    "\n",
    "params = {\n",
    "    'C' : [1e-2, 1e-1, 1, 1e1, 1e2]\n",
    "}\n",
    "\n",
    "gs = GridSearchCV(log_reg, params, scoring=\"accuracy\", cv=5, n_jobs=-1, return_train_score=True)\n",
    "\n",
    "X_train = data.drop(columns = \"Survived\")\n",
    "y_train = data[\"Survived\"]\n",
    "\n",
    "gs.fit(X_train, y_train)\n",
    "\n",
    "results = pd.DataFrame(gs.cv_results_)\n",
    "results[[\"params\", \"rank_test_score\", \"mean_train_score\", \"mean_test_score\", \"mean_fit_time\"]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "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>params</th>\n",
       "      <th>rank_test_score</th>\n",
       "      <th>mean_train_score</th>\n",
       "      <th>mean_test_score</th>\n",
       "      <th>mean_fit_time</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>{'C': 10.0}</td>\n",
       "      <td>5</td>\n",
       "      <td>0.822952</td>\n",
       "      <td>0.804714</td>\n",
       "      <td>0.005192</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>{'C': 100.0}</td>\n",
       "      <td>1</td>\n",
       "      <td>0.823232</td>\n",
       "      <td>0.808081</td>\n",
       "      <td>0.006590</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>{'C': 1000.0}</td>\n",
       "      <td>1</td>\n",
       "      <td>0.823233</td>\n",
       "      <td>0.808081</td>\n",
       "      <td>0.009001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>{'C': 10000.0}</td>\n",
       "      <td>1</td>\n",
       "      <td>0.823233</td>\n",
       "      <td>0.808081</td>\n",
       "      <td>0.010205</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>{'C': 100000.0}</td>\n",
       "      <td>1</td>\n",
       "      <td>0.823513</td>\n",
       "      <td>0.808081</td>\n",
       "      <td>0.008620</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            params  rank_test_score  mean_train_score  mean_test_score  \\\n",
       "0      {'C': 10.0}                5          0.822952         0.804714   \n",
       "1     {'C': 100.0}                1          0.823232         0.808081   \n",
       "2    {'C': 1000.0}                1          0.823233         0.808081   \n",
       "3   {'C': 10000.0}                1          0.823233         0.808081   \n",
       "4  {'C': 100000.0}                1          0.823513         0.808081   \n",
       "\n",
       "   mean_fit_time  \n",
       "0       0.005192  \n",
       "1       0.006590  \n",
       "2       0.009001  \n",
       "3       0.010205  \n",
       "4       0.008620  "
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "params = {\n",
    "    'C' : [1e1, 1e2, 1e3, 1e4, 1e5]\n",
    "}\n",
    "\n",
    "gs = GridSearchCV(log_reg, params, scoring=\"accuracy\", cv=5, n_jobs=-1, return_train_score=True)\n",
    "\n",
    "gs.fit(X_train, y_train)\n",
    "\n",
    "results = pd.DataFrame(gs.cv_results_)\n",
    "results[[\"params\", \"rank_test_score\", \"mean_train_score\", \"mean_test_score\", \"mean_fit_time\"]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[-1.69558190e-01,  4.50525498e-03,  1.11348730e+00,\n",
       "         8.80482137e-01, -2.60580768e-01,  2.25651260e+00,\n",
       "        -5.23123934e-01,  3.51687264e-01, -1.65985178e+00,\n",
       "        -1.74322794e+00, -1.75105113e+00, -2.14718428e+00,\n",
       "        -2.64174832e+00, -2.69362330e+00, -5.74543074e+00,\n",
       "        -2.62490862e-01,  5.40954992e-01,  8.91841666e-01,\n",
       "         2.88595351e-01,  1.31464619e+00,  1.70365905e+00,\n",
       "         9.88383302e-01, -9.45522162e-01, -2.40871393e+00,\n",
       "        -8.34444576e-01, -9.82119618e-01, -1.40053690e+00]])"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# По принцип има и опцията refit на GridSearchCV, по дифолт е True...\n",
    "# Малко ще свършим неговата работа ама има полза\n",
    "\n",
    "log_reg = LogisticRegression(C=100, random_state=42)\n",
    "\n",
    "log_reg.fit(X_train, y_train)\n",
    "\n",
    "log_reg.coef_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 864x432 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "log_reg.coef_\n",
    "plt.figure(figsize = (12, 6))\n",
    "args = list(X_train.columns) + [\"intercept\"]\n",
    "plt.bar(np.arange(len(args)), \n",
    "        np.concatenate(\n",
    "            (log_reg.coef_.reshape(-1), log_reg.intercept_.reshape(-1)),\n",
    "            axis=None\n",
    "        ))\n",
    "plt.xticks(np.arange(len(args)), args, rotation=50)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "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>params</th>\n",
       "      <th>rank_test_score</th>\n",
       "      <th>mean_train_score</th>\n",
       "      <th>mean_test_score</th>\n",
       "      <th>mean_fit_time</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>{'max_depth': 5, 'min_samples_leaf': 10, 'n_es...</td>\n",
       "      <td>1</td>\n",
       "      <td>0.817901</td>\n",
       "      <td>0.811448</td>\n",
       "      <td>0.086800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>{'max_depth': 10, 'min_samples_leaf': 10, 'n_e...</td>\n",
       "      <td>2</td>\n",
       "      <td>0.828287</td>\n",
       "      <td>0.808081</td>\n",
       "      <td>0.081000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>{'max_depth': 10, 'min_samples_leaf': 10, 'n_e...</td>\n",
       "      <td>3</td>\n",
       "      <td>0.828845</td>\n",
       "      <td>0.803591</td>\n",
       "      <td>0.226197</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>{'max_depth': 2, 'min_samples_leaf': 10, 'n_es...</td>\n",
       "      <td>4</td>\n",
       "      <td>0.810891</td>\n",
       "      <td>0.802469</td>\n",
       "      <td>0.250799</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>{'max_depth': 5, 'min_samples_leaf': 10, 'n_es...</td>\n",
       "      <td>5</td>\n",
       "      <td>0.816217</td>\n",
       "      <td>0.799102</td>\n",
       "      <td>0.029600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>{'max_depth': 10, 'min_samples_leaf': 10, 'n_e...</td>\n",
       "      <td>6</td>\n",
       "      <td>0.821837</td>\n",
       "      <td>0.797980</td>\n",
       "      <td>0.029400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>{'max_depth': 5, 'min_samples_leaf': 10, 'n_es...</td>\n",
       "      <td>6</td>\n",
       "      <td>0.824075</td>\n",
       "      <td>0.797980</td>\n",
       "      <td>0.260600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>{'max_depth': 3, 'min_samples_leaf': 10, 'n_es...</td>\n",
       "      <td>6</td>\n",
       "      <td>0.806401</td>\n",
       "      <td>0.797980</td>\n",
       "      <td>0.080200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>{'max_depth': 5, 'min_samples_leaf': 30, 'n_es...</td>\n",
       "      <td>9</td>\n",
       "      <td>0.796015</td>\n",
       "      <td>0.794613</td>\n",
       "      <td>0.077800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>{'max_depth': 3, 'min_samples_leaf': 10, 'n_es...</td>\n",
       "      <td>10</td>\n",
       "      <td>0.812850</td>\n",
       "      <td>0.793490</td>\n",
       "      <td>0.259400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>{'max_depth': 3, 'min_samples_leaf': 10, 'n_es...</td>\n",
       "      <td>11</td>\n",
       "      <td>0.803313</td>\n",
       "      <td>0.791246</td>\n",
       "      <td>0.027801</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>{'max_depth': 2, 'min_samples_leaf': 10, 'n_es...</td>\n",
       "      <td>12</td>\n",
       "      <td>0.790125</td>\n",
       "      <td>0.789001</td>\n",
       "      <td>0.017786</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>{'max_depth': 5, 'min_samples_leaf': 30, 'n_es...</td>\n",
       "      <td>12</td>\n",
       "      <td>0.799379</td>\n",
       "      <td>0.789001</td>\n",
       "      <td>0.261400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>{'max_depth': 5, 'min_samples_leaf': 30, 'n_es...</td>\n",
       "      <td>12</td>\n",
       "      <td>0.792090</td>\n",
       "      <td>0.789001</td>\n",
       "      <td>0.028599</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30</th>\n",
       "      <td>{'max_depth': 10, 'min_samples_leaf': 30, 'n_e...</td>\n",
       "      <td>12</td>\n",
       "      <td>0.791528</td>\n",
       "      <td>0.789001</td>\n",
       "      <td>0.028800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31</th>\n",
       "      <td>{'max_depth': 10, 'min_samples_leaf': 30, 'n_e...</td>\n",
       "      <td>12</td>\n",
       "      <td>0.792089</td>\n",
       "      <td>0.789001</td>\n",
       "      <td>0.080400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>{'max_depth': 2, 'min_samples_leaf': 30, 'n_es...</td>\n",
       "      <td>17</td>\n",
       "      <td>0.790406</td>\n",
       "      <td>0.787879</td>\n",
       "      <td>0.027399</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>{'max_depth': 3, 'min_samples_leaf': 100, 'n_e...</td>\n",
       "      <td>18</td>\n",
       "      <td>0.786754</td>\n",
       "      <td>0.786756</td>\n",
       "      <td>0.075800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>34</th>\n",
       "      <td>{'max_depth': 10, 'min_samples_leaf': 100, 'n_...</td>\n",
       "      <td>18</td>\n",
       "      <td>0.786754</td>\n",
       "      <td>0.786756</td>\n",
       "      <td>0.067199</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>{'max_depth': 3, 'min_samples_leaf': 30, 'n_es...</td>\n",
       "      <td>18</td>\n",
       "      <td>0.787316</td>\n",
       "      <td>0.786756</td>\n",
       "      <td>0.078800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>{'max_depth': 3, 'min_samples_leaf': 30, 'n_es...</td>\n",
       "      <td>18</td>\n",
       "      <td>0.786754</td>\n",
       "      <td>0.786756</td>\n",
       "      <td>0.028400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>33</th>\n",
       "      <td>{'max_depth': 10, 'min_samples_leaf': 100, 'n_...</td>\n",
       "      <td>18</td>\n",
       "      <td>0.786754</td>\n",
       "      <td>0.786756</td>\n",
       "      <td>0.027000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>{'max_depth': 2, 'min_samples_leaf': 100, 'n_e...</td>\n",
       "      <td>18</td>\n",
       "      <td>0.786754</td>\n",
       "      <td>0.786756</td>\n",
       "      <td>0.077200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>{'max_depth': 2, 'min_samples_leaf': 100, 'n_e...</td>\n",
       "      <td>18</td>\n",
       "      <td>0.786754</td>\n",
       "      <td>0.786756</td>\n",
       "      <td>0.028000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>{'max_depth': 5, 'min_samples_leaf': 100, 'n_e...</td>\n",
       "      <td>18</td>\n",
       "      <td>0.786754</td>\n",
       "      <td>0.786756</td>\n",
       "      <td>0.027200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>{'max_depth': 5, 'min_samples_leaf': 100, 'n_e...</td>\n",
       "      <td>18</td>\n",
       "      <td>0.786754</td>\n",
       "      <td>0.786756</td>\n",
       "      <td>0.075200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>32</th>\n",
       "      <td>{'max_depth': 10, 'min_samples_leaf': 30, 'n_e...</td>\n",
       "      <td>18</td>\n",
       "      <td>0.796855</td>\n",
       "      <td>0.786756</td>\n",
       "      <td>0.194805</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>{'max_depth': 2, 'min_samples_leaf': 30, 'n_es...</td>\n",
       "      <td>18</td>\n",
       "      <td>0.786754</td>\n",
       "      <td>0.786756</td>\n",
       "      <td>0.080200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>{'max_depth': 2, 'min_samples_leaf': 10, 'n_es...</td>\n",
       "      <td>18</td>\n",
       "      <td>0.792086</td>\n",
       "      <td>0.786756</td>\n",
       "      <td>0.065391</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>{'max_depth': 3, 'min_samples_leaf': 100, 'n_e...</td>\n",
       "      <td>18</td>\n",
       "      <td>0.786754</td>\n",
       "      <td>0.786756</td>\n",
       "      <td>0.029600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>{'max_depth': 2, 'min_samples_leaf': 30, 'n_es...</td>\n",
       "      <td>31</td>\n",
       "      <td>0.799111</td>\n",
       "      <td>0.777778</td>\n",
       "      <td>0.248600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>{'max_depth': 3, 'min_samples_leaf': 30, 'n_es...</td>\n",
       "      <td>31</td>\n",
       "      <td>0.800231</td>\n",
       "      <td>0.777778</td>\n",
       "      <td>0.254799</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>{'max_depth': 3, 'min_samples_leaf': 100, 'n_e...</td>\n",
       "      <td>33</td>\n",
       "      <td>0.775252</td>\n",
       "      <td>0.773288</td>\n",
       "      <td>0.258599</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>{'max_depth': 2, 'min_samples_leaf': 100, 'n_e...</td>\n",
       "      <td>33</td>\n",
       "      <td>0.775813</td>\n",
       "      <td>0.773288</td>\n",
       "      <td>0.249799</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>{'max_depth': 5, 'min_samples_leaf': 100, 'n_e...</td>\n",
       "      <td>33</td>\n",
       "      <td>0.775252</td>\n",
       "      <td>0.773288</td>\n",
       "      <td>0.244400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>35</th>\n",
       "      <td>{'max_depth': 10, 'min_samples_leaf': 100, 'n_...</td>\n",
       "      <td>33</td>\n",
       "      <td>0.775252</td>\n",
       "      <td>0.773288</td>\n",
       "      <td>0.156005</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                               params  rank_test_score  \\\n",
       "19  {'max_depth': 5, 'min_samples_leaf': 10, 'n_es...                1   \n",
       "28  {'max_depth': 10, 'min_samples_leaf': 10, 'n_e...                2   \n",
       "29  {'max_depth': 10, 'min_samples_leaf': 10, 'n_e...                3   \n",
       "2   {'max_depth': 2, 'min_samples_leaf': 10, 'n_es...                4   \n",
       "18  {'max_depth': 5, 'min_samples_leaf': 10, 'n_es...                5   \n",
       "27  {'max_depth': 10, 'min_samples_leaf': 10, 'n_e...                6   \n",
       "20  {'max_depth': 5, 'min_samples_leaf': 10, 'n_es...                6   \n",
       "10  {'max_depth': 3, 'min_samples_leaf': 10, 'n_es...                6   \n",
       "22  {'max_depth': 5, 'min_samples_leaf': 30, 'n_es...                9   \n",
       "11  {'max_depth': 3, 'min_samples_leaf': 10, 'n_es...               10   \n",
       "9   {'max_depth': 3, 'min_samples_leaf': 10, 'n_es...               11   \n",
       "0   {'max_depth': 2, 'min_samples_leaf': 10, 'n_es...               12   \n",
       "23  {'max_depth': 5, 'min_samples_leaf': 30, 'n_es...               12   \n",
       "21  {'max_depth': 5, 'min_samples_leaf': 30, 'n_es...               12   \n",
       "30  {'max_depth': 10, 'min_samples_leaf': 30, 'n_e...               12   \n",
       "31  {'max_depth': 10, 'min_samples_leaf': 30, 'n_e...               12   \n",
       "3   {'max_depth': 2, 'min_samples_leaf': 30, 'n_es...               17   \n",
       "16  {'max_depth': 3, 'min_samples_leaf': 100, 'n_e...               18   \n",
       "34  {'max_depth': 10, 'min_samples_leaf': 100, 'n_...               18   \n",
       "13  {'max_depth': 3, 'min_samples_leaf': 30, 'n_es...               18   \n",
       "12  {'max_depth': 3, 'min_samples_leaf': 30, 'n_es...               18   \n",
       "33  {'max_depth': 10, 'min_samples_leaf': 100, 'n_...               18   \n",
       "7   {'max_depth': 2, 'min_samples_leaf': 100, 'n_e...               18   \n",
       "6   {'max_depth': 2, 'min_samples_leaf': 100, 'n_e...               18   \n",
       "24  {'max_depth': 5, 'min_samples_leaf': 100, 'n_e...               18   \n",
       "25  {'max_depth': 5, 'min_samples_leaf': 100, 'n_e...               18   \n",
       "32  {'max_depth': 10, 'min_samples_leaf': 30, 'n_e...               18   \n",
       "4   {'max_depth': 2, 'min_samples_leaf': 30, 'n_es...               18   \n",
       "1   {'max_depth': 2, 'min_samples_leaf': 10, 'n_es...               18   \n",
       "15  {'max_depth': 3, 'min_samples_leaf': 100, 'n_e...               18   \n",
       "5   {'max_depth': 2, 'min_samples_leaf': 30, 'n_es...               31   \n",
       "14  {'max_depth': 3, 'min_samples_leaf': 30, 'n_es...               31   \n",
       "17  {'max_depth': 3, 'min_samples_leaf': 100, 'n_e...               33   \n",
       "8   {'max_depth': 2, 'min_samples_leaf': 100, 'n_e...               33   \n",
       "26  {'max_depth': 5, 'min_samples_leaf': 100, 'n_e...               33   \n",
       "35  {'max_depth': 10, 'min_samples_leaf': 100, 'n_...               33   \n",
       "\n",
       "    mean_train_score  mean_test_score  mean_fit_time  \n",
       "19          0.817901         0.811448       0.086800  \n",
       "28          0.828287         0.808081       0.081000  \n",
       "29          0.828845         0.803591       0.226197  \n",
       "2           0.810891         0.802469       0.250799  \n",
       "18          0.816217         0.799102       0.029600  \n",
       "27          0.821837         0.797980       0.029400  \n",
       "20          0.824075         0.797980       0.260600  \n",
       "10          0.806401         0.797980       0.080200  \n",
       "22          0.796015         0.794613       0.077800  \n",
       "11          0.812850         0.793490       0.259400  \n",
       "9           0.803313         0.791246       0.027801  \n",
       "0           0.790125         0.789001       0.017786  \n",
       "23          0.799379         0.789001       0.261400  \n",
       "21          0.792090         0.789001       0.028599  \n",
       "30          0.791528         0.789001       0.028800  \n",
       "31          0.792089         0.789001       0.080400  \n",
       "3           0.790406         0.787879       0.027399  \n",
       "16          0.786754         0.786756       0.075800  \n",
       "34          0.786754         0.786756       0.067199  \n",
       "13          0.787316         0.786756       0.078800  \n",
       "12          0.786754         0.786756       0.028400  \n",
       "33          0.786754         0.786756       0.027000  \n",
       "7           0.786754         0.786756       0.077200  \n",
       "6           0.786754         0.786756       0.028000  \n",
       "24          0.786754         0.786756       0.027200  \n",
       "25          0.786754         0.786756       0.075200  \n",
       "32          0.796855         0.786756       0.194805  \n",
       "4           0.786754         0.786756       0.080200  \n",
       "1           0.792086         0.786756       0.065391  \n",
       "15          0.786754         0.786756       0.029600  \n",
       "5           0.799111         0.777778       0.248600  \n",
       "14          0.800231         0.777778       0.254799  \n",
       "17          0.775252         0.773288       0.258599  \n",
       "8           0.775813         0.773288       0.249799  \n",
       "26          0.775252         0.773288       0.244400  \n",
       "35          0.775252         0.773288       0.156005  "
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# И сега да пробваме с RandomForest\n",
    "\n",
    "rforest = RandomForestClassifier(random_state=42)\n",
    "\n",
    "params = {\n",
    "    \"n_estimators\": [10, 30, 100],\n",
    "    \"max_depth\" : [2, 3, 5, 10],\n",
    "    \"min_samples_leaf\" : [10, 30, 100]\n",
    "}\n",
    "\n",
    "gs = GridSearchCV(rforest, params, scoring=\"accuracy\", cv=5, n_jobs=-1, return_train_score=True)\n",
    "\n",
    "gs.fit(X_train, y_train)\n",
    "\n",
    "results = pd.DataFrame(gs.cv_results_)\n",
    "results[[\"params\", \"rank_test_score\", \"mean_train_score\", \"mean_test_score\", \"mean_fit_time\"]].sort_values(\"rank_test_score\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "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>params</th>\n",
       "      <th>rank_test_score</th>\n",
       "      <th>mean_train_score</th>\n",
       "      <th>mean_test_score</th>\n",
       "      <th>mean_fit_time</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>41</th>\n",
       "      <td>{'max_depth': 15, 'min_samples_leaf': 3, 'n_es...</td>\n",
       "      <td>1</td>\n",
       "      <td>0.878514</td>\n",
       "      <td>0.827160</td>\n",
       "      <td>0.254599</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>32</th>\n",
       "      <td>{'max_depth': 10, 'min_samples_leaf': 3, 'n_es...</td>\n",
       "      <td>2</td>\n",
       "      <td>0.877674</td>\n",
       "      <td>0.826038</td>\n",
       "      <td>0.274000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31</th>\n",
       "      <td>{'max_depth': 10, 'min_samples_leaf': 3, 'n_es...</td>\n",
       "      <td>2</td>\n",
       "      <td>0.872062</td>\n",
       "      <td>0.826038</td>\n",
       "      <td>0.083000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>40</th>\n",
       "      <td>{'max_depth': 15, 'min_samples_leaf': 3, 'n_es...</td>\n",
       "      <td>4</td>\n",
       "      <td>0.876549</td>\n",
       "      <td>0.824916</td>\n",
       "      <td>0.083000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>{'max_depth': 10, 'min_samples_leaf': 1, 'n_es...</td>\n",
       "      <td>5</td>\n",
       "      <td>0.928459</td>\n",
       "      <td>0.823793</td>\n",
       "      <td>0.086199</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>{'max_depth': 10, 'min_samples_leaf': 1, 'n_es...</td>\n",
       "      <td>6</td>\n",
       "      <td>0.931826</td>\n",
       "      <td>0.819304</td>\n",
       "      <td>0.278199</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39</th>\n",
       "      <td>{'max_depth': 15, 'min_samples_leaf': 3, 'n_es...</td>\n",
       "      <td>7</td>\n",
       "      <td>0.872621</td>\n",
       "      <td>0.818182</td>\n",
       "      <td>0.029800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30</th>\n",
       "      <td>{'max_depth': 10, 'min_samples_leaf': 3, 'n_es...</td>\n",
       "      <td>7</td>\n",
       "      <td>0.869253</td>\n",
       "      <td>0.818182</td>\n",
       "      <td>0.030800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>{'max_depth': 10, 'min_samples_leaf': 1, 'n_es...</td>\n",
       "      <td>9</td>\n",
       "      <td>0.925650</td>\n",
       "      <td>0.815937</td>\n",
       "      <td>0.030201</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>{'max_depth': 5, 'min_samples_leaf': 1, 'n_est...</td>\n",
       "      <td>10</td>\n",
       "      <td>0.856630</td>\n",
       "      <td>0.812570</td>\n",
       "      <td>0.266600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>{'max_depth': 5, 'min_samples_leaf': 3, 'n_est...</td>\n",
       "      <td>10</td>\n",
       "      <td>0.846811</td>\n",
       "      <td>0.812570</td>\n",
       "      <td>0.259599</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>{'max_depth': 5, 'min_samples_leaf': 10, 'n_es...</td>\n",
       "      <td>12</td>\n",
       "      <td>0.817901</td>\n",
       "      <td>0.811448</td>\n",
       "      <td>0.082200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>{'max_depth': 5, 'min_samples_leaf': 3, 'n_est...</td>\n",
       "      <td>13</td>\n",
       "      <td>0.835869</td>\n",
       "      <td>0.810325</td>\n",
       "      <td>0.029600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>{'max_depth': 5, 'min_samples_leaf': 3, 'n_est...</td>\n",
       "      <td>13</td>\n",
       "      <td>0.837555</td>\n",
       "      <td>0.810325</td>\n",
       "      <td>0.079599</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>{'max_depth': 5, 'min_samples_leaf': 1, 'n_est...</td>\n",
       "      <td>15</td>\n",
       "      <td>0.845685</td>\n",
       "      <td>0.808081</td>\n",
       "      <td>0.082600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>34</th>\n",
       "      <td>{'max_depth': 10, 'min_samples_leaf': 10, 'n_e...</td>\n",
       "      <td>15</td>\n",
       "      <td>0.828287</td>\n",
       "      <td>0.808081</td>\n",
       "      <td>0.080001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>{'max_depth': 5, 'min_samples_leaf': 1, 'n_est...</td>\n",
       "      <td>15</td>\n",
       "      <td>0.840073</td>\n",
       "      <td>0.808081</td>\n",
       "      <td>0.028400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>43</th>\n",
       "      <td>{'max_depth': 15, 'min_samples_leaf': 10, 'n_e...</td>\n",
       "      <td>18</td>\n",
       "      <td>0.827446</td>\n",
       "      <td>0.805836</td>\n",
       "      <td>0.082399</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>44</th>\n",
       "      <td>{'max_depth': 15, 'min_samples_leaf': 10, 'n_e...</td>\n",
       "      <td>18</td>\n",
       "      <td>0.828564</td>\n",
       "      <td>0.805836</td>\n",
       "      <td>0.197405</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>{'max_depth': 3, 'min_samples_leaf': 1, 'n_est...</td>\n",
       "      <td>20</td>\n",
       "      <td>0.806400</td>\n",
       "      <td>0.804714</td>\n",
       "      <td>0.027400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>35</th>\n",
       "      <td>{'max_depth': 10, 'min_samples_leaf': 10, 'n_e...</td>\n",
       "      <td>21</td>\n",
       "      <td>0.828845</td>\n",
       "      <td>0.803591</td>\n",
       "      <td>0.266800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>{'max_depth': 2, 'min_samples_leaf': 3, 'n_est...</td>\n",
       "      <td>21</td>\n",
       "      <td>0.802468</td>\n",
       "      <td>0.803591</td>\n",
       "      <td>0.080000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>{'max_depth': 2, 'min_samples_leaf': 1, 'n_est...</td>\n",
       "      <td>23</td>\n",
       "      <td>0.801625</td>\n",
       "      <td>0.802469</td>\n",
       "      <td>0.063590</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>{'max_depth': 2, 'min_samples_leaf': 10, 'n_es...</td>\n",
       "      <td>23</td>\n",
       "      <td>0.810891</td>\n",
       "      <td>0.802469</td>\n",
       "      <td>0.249599</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>{'max_depth': 3, 'min_samples_leaf': 1, 'n_est...</td>\n",
       "      <td>25</td>\n",
       "      <td>0.806960</td>\n",
       "      <td>0.801347</td>\n",
       "      <td>0.077200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>{'max_depth': 3, 'min_samples_leaf': 3, 'n_est...</td>\n",
       "      <td>26</td>\n",
       "      <td>0.807242</td>\n",
       "      <td>0.800224</td>\n",
       "      <td>0.079601</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>{'max_depth': 3, 'min_samples_leaf': 3, 'n_est...</td>\n",
       "      <td>26</td>\n",
       "      <td>0.805838</td>\n",
       "      <td>0.800224</td>\n",
       "      <td>0.028800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>38</th>\n",
       "      <td>{'max_depth': 15, 'min_samples_leaf': 1, 'n_es...</td>\n",
       "      <td>28</td>\n",
       "      <td>0.955390</td>\n",
       "      <td>0.799102</td>\n",
       "      <td>0.291600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>37</th>\n",
       "      <td>{'max_depth': 15, 'min_samples_leaf': 1, 'n_es...</td>\n",
       "      <td>28</td>\n",
       "      <td>0.953987</td>\n",
       "      <td>0.799102</td>\n",
       "      <td>0.089801</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>{'max_depth': 2, 'min_samples_leaf': 1, 'n_est...</td>\n",
       "      <td>28</td>\n",
       "      <td>0.808926</td>\n",
       "      <td>0.799102</td>\n",
       "      <td>0.252799</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>42</th>\n",
       "      <td>{'max_depth': 15, 'min_samples_leaf': 10, 'n_e...</td>\n",
       "      <td>28</td>\n",
       "      <td>0.822399</td>\n",
       "      <td>0.799102</td>\n",
       "      <td>0.028800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>{'max_depth': 5, 'min_samples_leaf': 10, 'n_es...</td>\n",
       "      <td>28</td>\n",
       "      <td>0.816217</td>\n",
       "      <td>0.799102</td>\n",
       "      <td>0.027999</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>{'max_depth': 2, 'min_samples_leaf': 3, 'n_est...</td>\n",
       "      <td>33</td>\n",
       "      <td>0.809207</td>\n",
       "      <td>0.797980</td>\n",
       "      <td>0.246200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>33</th>\n",
       "      <td>{'max_depth': 10, 'min_samples_leaf': 10, 'n_e...</td>\n",
       "      <td>33</td>\n",
       "      <td>0.821837</td>\n",
       "      <td>0.797980</td>\n",
       "      <td>0.029400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>36</th>\n",
       "      <td>{'max_depth': 15, 'min_samples_leaf': 1, 'n_es...</td>\n",
       "      <td>33</td>\n",
       "      <td>0.943886</td>\n",
       "      <td>0.797980</td>\n",
       "      <td>0.031800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>{'max_depth': 5, 'min_samples_leaf': 10, 'n_es...</td>\n",
       "      <td>33</td>\n",
       "      <td>0.824075</td>\n",
       "      <td>0.797980</td>\n",
       "      <td>0.263800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>{'max_depth': 3, 'min_samples_leaf': 10, 'n_es...</td>\n",
       "      <td>33</td>\n",
       "      <td>0.806401</td>\n",
       "      <td>0.797980</td>\n",
       "      <td>0.077400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>{'max_depth': 3, 'min_samples_leaf': 10, 'n_es...</td>\n",
       "      <td>38</td>\n",
       "      <td>0.812850</td>\n",
       "      <td>0.793490</td>\n",
       "      <td>0.263400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>{'max_depth': 3, 'min_samples_leaf': 3, 'n_est...</td>\n",
       "      <td>38</td>\n",
       "      <td>0.811731</td>\n",
       "      <td>0.793490</td>\n",
       "      <td>0.251000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>{'max_depth': 3, 'min_samples_leaf': 1, 'n_est...</td>\n",
       "      <td>40</td>\n",
       "      <td>0.811731</td>\n",
       "      <td>0.792368</td>\n",
       "      <td>0.259400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>{'max_depth': 3, 'min_samples_leaf': 10, 'n_es...</td>\n",
       "      <td>41</td>\n",
       "      <td>0.803313</td>\n",
       "      <td>0.791246</td>\n",
       "      <td>0.030200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>{'max_depth': 2, 'min_samples_leaf': 3, 'n_est...</td>\n",
       "      <td>42</td>\n",
       "      <td>0.792372</td>\n",
       "      <td>0.790123</td>\n",
       "      <td>0.028400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>{'max_depth': 2, 'min_samples_leaf': 10, 'n_es...</td>\n",
       "      <td>43</td>\n",
       "      <td>0.790125</td>\n",
       "      <td>0.789001</td>\n",
       "      <td>0.030201</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>{'max_depth': 2, 'min_samples_leaf': 1, 'n_est...</td>\n",
       "      <td>43</td>\n",
       "      <td>0.792934</td>\n",
       "      <td>0.789001</td>\n",
       "      <td>0.017805</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>{'max_depth': 2, 'min_samples_leaf': 10, 'n_es...</td>\n",
       "      <td>45</td>\n",
       "      <td>0.792086</td>\n",
       "      <td>0.786756</td>\n",
       "      <td>0.079601</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                               params  rank_test_score  \\\n",
       "41  {'max_depth': 15, 'min_samples_leaf': 3, 'n_es...                1   \n",
       "32  {'max_depth': 10, 'min_samples_leaf': 3, 'n_es...                2   \n",
       "31  {'max_depth': 10, 'min_samples_leaf': 3, 'n_es...                2   \n",
       "40  {'max_depth': 15, 'min_samples_leaf': 3, 'n_es...                4   \n",
       "28  {'max_depth': 10, 'min_samples_leaf': 1, 'n_es...                5   \n",
       "29  {'max_depth': 10, 'min_samples_leaf': 1, 'n_es...                6   \n",
       "39  {'max_depth': 15, 'min_samples_leaf': 3, 'n_es...                7   \n",
       "30  {'max_depth': 10, 'min_samples_leaf': 3, 'n_es...                7   \n",
       "27  {'max_depth': 10, 'min_samples_leaf': 1, 'n_es...                9   \n",
       "20  {'max_depth': 5, 'min_samples_leaf': 1, 'n_est...               10   \n",
       "23  {'max_depth': 5, 'min_samples_leaf': 3, 'n_est...               10   \n",
       "25  {'max_depth': 5, 'min_samples_leaf': 10, 'n_es...               12   \n",
       "21  {'max_depth': 5, 'min_samples_leaf': 3, 'n_est...               13   \n",
       "22  {'max_depth': 5, 'min_samples_leaf': 3, 'n_est...               13   \n",
       "19  {'max_depth': 5, 'min_samples_leaf': 1, 'n_est...               15   \n",
       "34  {'max_depth': 10, 'min_samples_leaf': 10, 'n_e...               15   \n",
       "18  {'max_depth': 5, 'min_samples_leaf': 1, 'n_est...               15   \n",
       "43  {'max_depth': 15, 'min_samples_leaf': 10, 'n_e...               18   \n",
       "44  {'max_depth': 15, 'min_samples_leaf': 10, 'n_e...               18   \n",
       "9   {'max_depth': 3, 'min_samples_leaf': 1, 'n_est...               20   \n",
       "35  {'max_depth': 10, 'min_samples_leaf': 10, 'n_e...               21   \n",
       "4   {'max_depth': 2, 'min_samples_leaf': 3, 'n_est...               21   \n",
       "1   {'max_depth': 2, 'min_samples_leaf': 1, 'n_est...               23   \n",
       "8   {'max_depth': 2, 'min_samples_leaf': 10, 'n_es...               23   \n",
       "10  {'max_depth': 3, 'min_samples_leaf': 1, 'n_est...               25   \n",
       "13  {'max_depth': 3, 'min_samples_leaf': 3, 'n_est...               26   \n",
       "12  {'max_depth': 3, 'min_samples_leaf': 3, 'n_est...               26   \n",
       "38  {'max_depth': 15, 'min_samples_leaf': 1, 'n_es...               28   \n",
       "37  {'max_depth': 15, 'min_samples_leaf': 1, 'n_es...               28   \n",
       "2   {'max_depth': 2, 'min_samples_leaf': 1, 'n_est...               28   \n",
       "42  {'max_depth': 15, 'min_samples_leaf': 10, 'n_e...               28   \n",
       "24  {'max_depth': 5, 'min_samples_leaf': 10, 'n_es...               28   \n",
       "5   {'max_depth': 2, 'min_samples_leaf': 3, 'n_est...               33   \n",
       "33  {'max_depth': 10, 'min_samples_leaf': 10, 'n_e...               33   \n",
       "36  {'max_depth': 15, 'min_samples_leaf': 1, 'n_es...               33   \n",
       "26  {'max_depth': 5, 'min_samples_leaf': 10, 'n_es...               33   \n",
       "16  {'max_depth': 3, 'min_samples_leaf': 10, 'n_es...               33   \n",
       "17  {'max_depth': 3, 'min_samples_leaf': 10, 'n_es...               38   \n",
       "14  {'max_depth': 3, 'min_samples_leaf': 3, 'n_est...               38   \n",
       "11  {'max_depth': 3, 'min_samples_leaf': 1, 'n_est...               40   \n",
       "15  {'max_depth': 3, 'min_samples_leaf': 10, 'n_es...               41   \n",
       "3   {'max_depth': 2, 'min_samples_leaf': 3, 'n_est...               42   \n",
       "6   {'max_depth': 2, 'min_samples_leaf': 10, 'n_es...               43   \n",
       "0   {'max_depth': 2, 'min_samples_leaf': 1, 'n_est...               43   \n",
       "7   {'max_depth': 2, 'min_samples_leaf': 10, 'n_es...               45   \n",
       "\n",
       "    mean_train_score  mean_test_score  mean_fit_time  \n",
       "41          0.878514         0.827160       0.254599  \n",
       "32          0.877674         0.826038       0.274000  \n",
       "31          0.872062         0.826038       0.083000  \n",
       "40          0.876549         0.824916       0.083000  \n",
       "28          0.928459         0.823793       0.086199  \n",
       "29          0.931826         0.819304       0.278199  \n",
       "39          0.872621         0.818182       0.029800  \n",
       "30          0.869253         0.818182       0.030800  \n",
       "27          0.925650         0.815937       0.030201  \n",
       "20          0.856630         0.812570       0.266600  \n",
       "23          0.846811         0.812570       0.259599  \n",
       "25          0.817901         0.811448       0.082200  \n",
       "21          0.835869         0.810325       0.029600  \n",
       "22          0.837555         0.810325       0.079599  \n",
       "19          0.845685         0.808081       0.082600  \n",
       "34          0.828287         0.808081       0.080001  \n",
       "18          0.840073         0.808081       0.028400  \n",
       "43          0.827446         0.805836       0.082399  \n",
       "44          0.828564         0.805836       0.197405  \n",
       "9           0.806400         0.804714       0.027400  \n",
       "35          0.828845         0.803591       0.266800  \n",
       "4           0.802468         0.803591       0.080000  \n",
       "1           0.801625         0.802469       0.063590  \n",
       "8           0.810891         0.802469       0.249599  \n",
       "10          0.806960         0.801347       0.077200  \n",
       "13          0.807242         0.800224       0.079601  \n",
       "12          0.805838         0.800224       0.028800  \n",
       "38          0.955390         0.799102       0.291600  \n",
       "37          0.953987         0.799102       0.089801  \n",
       "2           0.808926         0.799102       0.252799  \n",
       "42          0.822399         0.799102       0.028800  \n",
       "24          0.816217         0.799102       0.027999  \n",
       "5           0.809207         0.797980       0.246200  \n",
       "33          0.821837         0.797980       0.029400  \n",
       "36          0.943886         0.797980       0.031800  \n",
       "26          0.824075         0.797980       0.263800  \n",
       "16          0.806401         0.797980       0.077400  \n",
       "17          0.812850         0.793490       0.263400  \n",
       "14          0.811731         0.793490       0.251000  \n",
       "11          0.811731         0.792368       0.259400  \n",
       "15          0.803313         0.791246       0.030200  \n",
       "3           0.792372         0.790123       0.028400  \n",
       "6           0.790125         0.789001       0.030201  \n",
       "0           0.792934         0.789001       0.017805  \n",
       "7           0.792086         0.786756       0.079601  "
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "params = {\n",
    "    \"n_estimators\": [10, 30, 100],\n",
    "    \"max_depth\" : [2, 3, 5, 10, 15],\n",
    "    \"min_samples_leaf\" : [1, 3, 10]\n",
    "}\n",
    "\n",
    "gs = GridSearchCV(rforest, params, scoring=\"accuracy\", cv=5, n_jobs=-1, return_train_score=True)\n",
    "\n",
    "gs.fit(X_train, y_train)\n",
    "\n",
    "results = pd.DataFrame(gs.cv_results_)\n",
    "results[[\"params\", \"rank_test_score\", \"mean_train_score\", \"mean_test_score\", \"mean_fit_time\"]].sort_values(\"rank_test_score\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([2.67380876e-02, 1.61983064e-01, 3.88340146e-02, 1.98470083e-02,\n",
       "       8.23273771e-02, 2.21958812e-01, 2.13205396e-01, 4.19685416e-02,\n",
       "       6.11561066e-03, 1.22726031e-02, 1.84035492e-02, 7.60662058e-03,\n",
       "       3.35011276e-03, 3.57255598e-03, 2.85153298e-04, 6.43862462e-02,\n",
       "       3.56398552e-03, 6.17099927e-03, 6.29124613e-03, 6.58429856e-03,\n",
       "       1.13559342e-02, 1.13385114e-03, 2.18204993e-04, 0.00000000e+00,\n",
       "       1.42530519e-02, 8.42966358e-03, 1.91440122e-02])"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 82.7% е по-добре\n",
    "\n",
    "rforest = RandomForestClassifier(n_estimators = 100, \n",
    "                                 max_depth = 15,\n",
    "                                 min_samples_leaf = 3,\n",
    "                                 random_state=42)\n",
    "\n",
    "rforest.fit(X_train, y_train)\n",
    "\n",
    "rforest.feature_importances_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 864x432 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize = (12, 6))\n",
    "args = X_train.columns\n",
    "plt.bar(np.arange(len(args)), \n",
    "        rforest.feature_importances_)\n",
    "plt.xticks(np.arange(len(args)), args, rotation=50)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "# Да си качим отговора в kaggle"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [],
   "source": [
    "# Ще ни трябва функция която прави цялата обработка и върху тестовите данни\n",
    "# бая копи пейст... ама внимавайте бая (навсякъде където запълвате със стойности)!!!\n",
    "\n",
    "def process_test(data):\n",
    "    data[[\"isClass_1\", \"isClass_2\", \"isClass_3\"]] = pd.get_dummies(data[\"Pclass\"], prefix=\"isClass\")\n",
    "    data = data.drop(columns = \"Pclass\")\n",
    "    data[[\"female\", \"male\"]] = pd.get_dummies(data[\"Sex\"])\n",
    "    data = data.drop(columns = \"Sex\")\n",
    "\n",
    "    data.loc[data.Name.str.contains(\"Master.\", regex=False), \"Age\"] = data.loc[data.Name.str.contains(\"Master.\", regex=False), \"Age\"].fillna(\n",
    "        train_init.loc[train_init.Name.str.contains(\"Master.\", regex=False), \"Age\"].mean()\n",
    "    )\n",
    "    data.loc[data.Name.str.contains(\"Mr.\", regex=False), \"Age\"] = data.loc[data.Name.str.contains(\"Mr.\", regex=False), \"Age\"].fillna(\n",
    "        train_init.loc[train_init.Name.str.contains(\"Mr.\", regex=False), \"Age\"].mean()\n",
    "    )\n",
    "    data.loc[data.Name.str.contains(\"Mrs.\", regex=False), \"Age\"] = data.loc[data.Name.str.contains(\"Mrs.\", regex=False), \"Age\"].fillna(\n",
    "        train_init.loc[train_init.Name.str.contains(\"Mrs.\", regex=False), \"Age\"].mean()\n",
    "    )\n",
    "    data.loc[data.Name.str.contains(\"Miss.\", regex=False), \"Age\"] = data.loc[data.Name.str.contains(\"Miss.\", regex=False), \"Age\"].fillna(\n",
    "        train_init.loc[train_init.Name.str.contains(\"Miss.\", regex=False), \"Age\"].mean()\n",
    "    )\n",
    "\n",
    "    data.loc[:, \"Age\"] = data.loc[:, \"Age\"].fillna(train_init.loc[:, \"Age\"].mean())\n",
    "\n",
    "    data = data.drop(columns = \"Name\")\n",
    "\n",
    "    diff = 10\n",
    "    maxAge = int(train_init.Age.max())\n",
    "    for i in range(0, maxAge, diff):\n",
    "        data[\"Age\"+str(i)+\"-\"+str(i+diff-1)] = ((data[\"Age\"] >= i) & (data[\"Age\"] < i+diff)) * 1\n",
    "\n",
    "    data = data.drop(columns = \"Age\")\n",
    "\n",
    "    data = data.drop(columns = \"SibSp\")\n",
    "\n",
    "    data[\"TicketFreq\"] = [sum(data[\"Ticket\"]==x) for x in data[\"Ticket\"]] #тва може да е по-кадърно ма ме мързи\n",
    "    data = data.drop(columns=\"Ticket\")\n",
    "\n",
    "    vals = train_init[\"Cabin\"].str[0].unique()\n",
    "    vals = vals[1:]\n",
    "    vals.sort()\n",
    "    data[\"Cabin\"] = data[\"Cabin\"].str[0]\n",
    "    for v in vals:\n",
    "        data[\"Cabin_\"+v] = (data[\"Cabin\"] == v) * 1\n",
    "    data = data.drop(columns = \"Cabin\")\n",
    "\n",
    "    vals = train_init.Embarked.unique()\n",
    "    vals = vals[:-1]\n",
    "    data[sorted([\"Embarked_\"+v for v in vals])] = pd.get_dummies(data[\"Embarked\"], prefix=\"Embarked\")\n",
    "    data = data.drop(columns = \"Embarked\")\n",
    "    \n",
    "    return data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "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>Parch</th>\n",
       "      <th>Fare</th>\n",
       "      <th>isClass_1</th>\n",
       "      <th>isClass_2</th>\n",
       "      <th>isClass_3</th>\n",
       "      <th>female</th>\n",
       "      <th>male</th>\n",
       "      <th>Age0-9</th>\n",
       "      <th>Age10-19</th>\n",
       "      <th>Age20-29</th>\n",
       "      <th>...</th>\n",
       "      <th>Cabin_B</th>\n",
       "      <th>Cabin_C</th>\n",
       "      <th>Cabin_D</th>\n",
       "      <th>Cabin_E</th>\n",
       "      <th>Cabin_F</th>\n",
       "      <th>Cabin_G</th>\n",
       "      <th>Cabin_T</th>\n",
       "      <th>Embarked_C</th>\n",
       "      <th>Embarked_Q</th>\n",
       "      <th>Embarked_S</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PassengerId</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>892</th>\n",
       "      <td>0</td>\n",
       "      <td>7.8292</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>893</th>\n",
       "      <td>0</td>\n",
       "      <td>7.0000</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>894</th>\n",
       "      <td>0</td>\n",
       "      <td>9.6875</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>895</th>\n",
       "      <td>0</td>\n",
       "      <td>8.6625</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>896</th>\n",
       "      <td>1</td>\n",
       "      <td>12.2875</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>897</th>\n",
       "      <td>0</td>\n",
       "      <td>9.2250</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>898</th>\n",
       "      <td>0</td>\n",
       "      <td>7.6292</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>899</th>\n",
       "      <td>1</td>\n",
       "      <td>29.0000</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>900</th>\n",
       "      <td>0</td>\n",
       "      <td>7.2292</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>901</th>\n",
       "      <td>0</td>\n",
       "      <td>24.1500</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>10 rows × 27 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "             Parch     Fare  isClass_1  isClass_2  isClass_3  female  male  \\\n",
       "PassengerId                                                                  \n",
       "892              0   7.8292          0          0          1       0     1   \n",
       "893              0   7.0000          0          0          1       1     0   \n",
       "894              0   9.6875          0          1          0       0     1   \n",
       "895              0   8.6625          0          0          1       0     1   \n",
       "896              1  12.2875          0          0          1       1     0   \n",
       "897              0   9.2250          0          0          1       0     1   \n",
       "898              0   7.6292          0          0          1       1     0   \n",
       "899              1  29.0000          0          1          0       0     1   \n",
       "900              0   7.2292          0          0          1       1     0   \n",
       "901              0  24.1500          0          0          1       0     1   \n",
       "\n",
       "             Age0-9  Age10-19  Age20-29     ...      Cabin_B  Cabin_C  \\\n",
       "PassengerId                                 ...                         \n",
       "892               0         0         0     ...            0        0   \n",
       "893               0         0         0     ...            0        0   \n",
       "894               0         0         0     ...            0        0   \n",
       "895               0         0         1     ...            0        0   \n",
       "896               0         0         1     ...            0        0   \n",
       "897               0         1         0     ...            0        0   \n",
       "898               0         0         0     ...            0        0   \n",
       "899               0         0         1     ...            0        0   \n",
       "900               0         1         0     ...            0        0   \n",
       "901               0         0         1     ...            0        0   \n",
       "\n",
       "             Cabin_D  Cabin_E  Cabin_F  Cabin_G  Cabin_T  Embarked_C  \\\n",
       "PassengerId                                                            \n",
       "892                0        0        0        0        0           0   \n",
       "893                0        0        0        0        0           0   \n",
       "894                0        0        0        0        0           0   \n",
       "895                0        0        0        0        0           0   \n",
       "896                0        0        0        0        0           0   \n",
       "897                0        0        0        0        0           0   \n",
       "898                0        0        0        0        0           0   \n",
       "899                0        0        0        0        0           0   \n",
       "900                0        0        0        0        0           1   \n",
       "901                0        0        0        0        0           0   \n",
       "\n",
       "             Embarked_Q  Embarked_S  \n",
       "PassengerId                          \n",
       "892                   1           0  \n",
       "893                   0           1  \n",
       "894                   1           0  \n",
       "895                   0           1  \n",
       "896                   0           1  \n",
       "897                   0           1  \n",
       "898                   1           0  \n",
       "899                   0           1  \n",
       "900                   0           0  \n",
       "901                   0           1  \n",
       "\n",
       "[10 rows x 27 columns]"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_test = pd.read_csv(\"test.csv\")\n",
    "X_test = X_test.set_index(\"PassengerId\")\n",
    "\n",
    "X_test = process_test(X_test)\n",
    "X_test.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Parch         0\n",
       "Fare          1\n",
       "isClass_1     0\n",
       "isClass_2     0\n",
       "isClass_3     0\n",
       "female        0\n",
       "male          0\n",
       "Age0-9        0\n",
       "Age10-19      0\n",
       "Age20-29      0\n",
       "Age30-39      0\n",
       "Age40-49      0\n",
       "Age50-59      0\n",
       "Age60-69      0\n",
       "Age70-79      0\n",
       "TicketFreq    0\n",
       "Cabin_A       0\n",
       "Cabin_B       0\n",
       "Cabin_C       0\n",
       "Cabin_D       0\n",
       "Cabin_E       0\n",
       "Cabin_F       0\n",
       "Cabin_G       0\n",
       "Cabin_T       0\n",
       "Embarked_C    0\n",
       "Embarked_Q    0\n",
       "Embarked_S    0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_test.isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [],
   "source": [
    "X_test[\"Fare\"].fillna(train_init[\"Fare\"].mean(), inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Parch         0\n",
       "Fare          0\n",
       "isClass_1     0\n",
       "isClass_2     0\n",
       "isClass_3     0\n",
       "female        0\n",
       "male          0\n",
       "Age0-9        0\n",
       "Age10-19      0\n",
       "Age20-29      0\n",
       "Age30-39      0\n",
       "Age40-49      0\n",
       "Age50-59      0\n",
       "Age60-69      0\n",
       "Age70-79      0\n",
       "TicketFreq    0\n",
       "Cabin_A       0\n",
       "Cabin_B       0\n",
       "Cabin_C       0\n",
       "Cabin_D       0\n",
       "Cabin_E       0\n",
       "Cabin_F       0\n",
       "Cabin_G       0\n",
       "Cabin_T       0\n",
       "Embarked_C    0\n",
       "Embarked_Q    0\n",
       "Embarked_S    0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_test.isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 1, 0, 1, 1, 0, 0, 0, 1, 0, 1,\n",
       "       1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1,\n",
       "       1, 0, 0, 0, 1, 1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 1,\n",
       "       1, 0, 0, 1, 1, 0, 0, 0, 1, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 1, 1,\n",
       "       1, 1, 0, 0, 1, 0, 0, 0, 1, 0, 1, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0,\n",
       "       0, 1, 1, 1, 1, 0, 0, 1, 0, 1, 1, 0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 0,\n",
       "       0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1,\n",
       "       0, 0, 1, 1, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1,\n",
       "       1, 0, 1, 1, 0, 0, 1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 1,\n",
       "       0, 0, 1, 1, 0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 0, 1, 1, 0, 1, 0, 1, 0,\n",
       "       1, 0, 1, 0, 1, 1, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1,\n",
       "       0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1,\n",
       "       0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 0,\n",
       "       0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1,\n",
       "       0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0,\n",
       "       1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 1, 0, 1, 1, 0,\n",
       "       0, 0, 1, 0, 1, 0, 0, 1, 0, 1, 1, 0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0,\n",
       "       1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 1, 0, 1, 0, 0, 0, 1,\n",
       "       0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 1, 0, 0, 1],\n",
       "      dtype=int64)"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rforest.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PassengerId</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>892</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>893</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>894</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>895</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>896</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>897</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>898</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>899</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>900</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>901</th>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Empty DataFrame\n",
       "Columns: []\n",
       "Index: [892, 893, 894, 895, 896, 897, 898, 899, 900, 901]"
      ]
     },
     "execution_count": 54,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "prediction = X_test.drop(columns = X_test.columns)\n",
    "prediction.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "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>Survived</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PassengerId</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>892</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>893</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>894</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>895</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>896</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>897</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>898</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>899</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>900</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>901</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Survived\n",
       "PassengerId          \n",
       "892                 0\n",
       "893                 0\n",
       "894                 0\n",
       "895                 0\n",
       "896                 0\n",
       "897                 0\n",
       "898                 1\n",
       "899                 0\n",
       "900                 1\n",
       "901                 0"
      ]
     },
     "execution_count": 55,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "prediction[\"Survived\"] = rforest.predict(X_test)\n",
    "prediction.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [],
   "source": [
    "prediction.to_csv(\"prediction.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {
    "slideshow": {
     "slide_type": "subslide"
    }
   },
   "outputs": [],
   "source": [
    "# test accuracy 0.78947, позиция 3337/14122\n",
    "# коментар\n",
    "# side notе: с друг ноутбук имам 0.80382 ама тва не е ясно колко statistically significant e"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "celltoolbar": "Slideshow",
  "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": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}