Tita.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Dataset do Titanic\n",
    "\n",
    "1. Realizar uma análise exploratória dos dados.\n",
    "\n",
    "2. Responder à pergunta: \"Qual é a probabilidade de sobrevivência de uma mulher?\"\n",
    "\n",
    "3. Implementar a validação do modelo utilizando Cross Validation.\n",
    "\n",
    "4. Testar os modelos e realizar suas avaliações."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Import bibliotecas\n",
    "#\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Importando Dataframes do titanic"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(891, 15)"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Titanic Da web\n",
    "#\n",
    "df_titanic = sns.load_dataset('titanic')\n",
    "df_titanic.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 891 entries, 0 to 890\n",
      "Data columns (total 15 columns):\n",
      " #   Column       Non-Null Count  Dtype   \n",
      "---  ------       --------------  -----   \n",
      " 0   survived     891 non-null    int64   \n",
      " 1   pclass       891 non-null    int64   \n",
      " 2   sex          891 non-null    object  \n",
      " 3   age          714 non-null    float64 \n",
      " 4   sibsp        891 non-null    int64   \n",
      " 5   parch        891 non-null    int64   \n",
      " 6   fare         891 non-null    float64 \n",
      " 7   embarked     889 non-null    object  \n",
      " 8   class        891 non-null    category\n",
      " 9   who          891 non-null    object  \n",
      " 10  adult_male   891 non-null    bool    \n",
      " 11  deck         203 non-null    category\n",
      " 12  embark_town  889 non-null    object  \n",
      " 13  alive        891 non-null    object  \n",
      " 14  alone        891 non-null    bool    \n",
      "dtypes: bool(2), category(2), float64(2), int64(4), object(5)\n",
      "memory usage: 80.7+ KB\n",
      "None\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>sex</th>\n",
       "      <th>age</th>\n",
       "      <th>sibsp</th>\n",
       "      <th>parch</th>\n",
       "      <th>fare</th>\n",
       "      <th>embarked</th>\n",
       "      <th>class</th>\n",
       "      <th>who</th>\n",
       "      <th>adult_male</th>\n",
       "      <th>deck</th>\n",
       "      <th>embark_town</th>\n",
       "      <th>alive</th>\n",
       "      <th>alone</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>886</th>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>male</td>\n",
       "      <td>27.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>13.00</td>\n",
       "      <td>S</td>\n",
       "      <td>Second</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>no</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>887</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>female</td>\n",
       "      <td>19.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>30.00</td>\n",
       "      <td>S</td>\n",
       "      <td>First</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>B</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>yes</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>888</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>female</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>23.45</td>\n",
       "      <td>S</td>\n",
       "      <td>Third</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>no</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>889</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>male</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>30.00</td>\n",
       "      <td>C</td>\n",
       "      <td>First</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>C</td>\n",
       "      <td>Cherbourg</td>\n",
       "      <td>yes</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>890</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>32.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.75</td>\n",
       "      <td>Q</td>\n",
       "      <td>Third</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Queenstown</td>\n",
       "      <td>no</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     survived  pclass     sex   age  sibsp  parch   fare embarked   class  \\\n",
       "886         0       2    male  27.0      0      0  13.00        S  Second   \n",
       "887         1       1  female  19.0      0      0  30.00        S   First   \n",
       "888         0       3  female   NaN      1      2  23.45        S   Third   \n",
       "889         1       1    male  26.0      0      0  30.00        C   First   \n",
       "890         0       3    male  32.0      0      0   7.75        Q   Third   \n",
       "\n",
       "       who  adult_male deck  embark_town alive  alone  \n",
       "886    man        True  NaN  Southampton    no   True  \n",
       "887  woman       False    B  Southampton   yes   True  \n",
       "888  woman       False  NaN  Southampton    no  False  \n",
       "889    man        True    C    Cherbourg   yes   True  \n",
       "890    man        True  NaN   Queenstown    no   True  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "print(df_titanic.info())\n",
    "df_titanic.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(891, 12)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# titanic do Kaggle baixado em CSV\n",
    "#\n",
    "df_titanic_2 = pd.read_csv('train.csv')\n",
    "df_titanic_2.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>PassengerId</th>\n",
       "      <th>Survived</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Name</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>Embarked</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Braund, Mr. Owen Harris</td>\n",
       "      <td>male</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>A/5 21171</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
       "      <td>female</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>PC 17599</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>C85</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Heikkinen, Miss. Laina</td>\n",
       "      <td>female</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>STON/O2. 3101282</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n",
       "      <td>female</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>113803</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>C123</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Allen, Mr. William Henry</td>\n",
       "      <td>male</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>373450</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>886</th>\n",
       "      <td>887</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>Montvila, Rev. Juozas</td>\n",
       "      <td>male</td>\n",
       "      <td>27.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>211536</td>\n",
       "      <td>13.0000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>887</th>\n",
       "      <td>888</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Graham, Miss. Margaret Edith</td>\n",
       "      <td>female</td>\n",
       "      <td>19.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>112053</td>\n",
       "      <td>30.0000</td>\n",
       "      <td>B42</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>888</th>\n",
       "      <td>889</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Johnston, Miss. Catherine Helen \"Carrie\"</td>\n",
       "      <td>female</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>W./C. 6607</td>\n",
       "      <td>23.4500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>889</th>\n",
       "      <td>890</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Behr, Mr. Karl Howell</td>\n",
       "      <td>male</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>111369</td>\n",
       "      <td>30.0000</td>\n",
       "      <td>C148</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>890</th>\n",
       "      <td>891</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Dooley, Mr. Patrick</td>\n",
       "      <td>male</td>\n",
       "      <td>32.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>370376</td>\n",
       "      <td>7.7500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Q</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>891 rows × 12 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     PassengerId  Survived  Pclass  \\\n",
       "0              1         0       3   \n",
       "1              2         1       1   \n",
       "2              3         1       3   \n",
       "3              4         1       1   \n",
       "4              5         0       3   \n",
       "..           ...       ...     ...   \n",
       "886          887         0       2   \n",
       "887          888         1       1   \n",
       "888          889         0       3   \n",
       "889          890         1       1   \n",
       "890          891         0       3   \n",
       "\n",
       "                                                  Name     Sex   Age  SibSp  \\\n",
       "0                              Braund, Mr. Owen Harris    male  22.0      1   \n",
       "1    Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0      1   \n",
       "2                               Heikkinen, Miss. Laina  female  26.0      0   \n",
       "3         Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0      1   \n",
       "4                             Allen, Mr. William Henry    male  35.0      0   \n",
       "..                                                 ...     ...   ...    ...   \n",
       "886                              Montvila, Rev. Juozas    male  27.0      0   \n",
       "887                       Graham, Miss. Margaret Edith  female  19.0      0   \n",
       "888           Johnston, Miss. Catherine Helen \"Carrie\"  female   NaN      1   \n",
       "889                              Behr, Mr. Karl Howell    male  26.0      0   \n",
       "890                                Dooley, Mr. Patrick    male  32.0      0   \n",
       "\n",
       "     Parch            Ticket     Fare Cabin Embarked  \n",
       "0        0         A/5 21171   7.2500   NaN        S  \n",
       "1        0          PC 17599  71.2833   C85        C  \n",
       "2        0  STON/O2. 3101282   7.9250   NaN        S  \n",
       "3        0            113803  53.1000  C123        S  \n",
       "4        0            373450   8.0500   NaN        S  \n",
       "..     ...               ...      ...   ...      ...  \n",
       "886      0            211536  13.0000   NaN        S  \n",
       "887      0            112053  30.0000   B42        S  \n",
       "888      2        W./C. 6607  23.4500   NaN        S  \n",
       "889      0            111369  30.0000  C148        C  \n",
       "890      0            370376   7.7500   NaN        Q  \n",
       "\n",
       "[891 rows x 12 columns]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_titanic_2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "PassengerId      0\n",
       "Survived         0\n",
       "Pclass           0\n",
       "Name             0\n",
       "Sex              0\n",
       "Age            177\n",
       "SibSp            0\n",
       "Parch            0\n",
       "Ticket           0\n",
       "Fare             0\n",
       "Cabin          687\n",
       "Embarked         2\n",
       "dtype: int64"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_titanic_2.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "survived         0\n",
       "pclass           0\n",
       "sex              0\n",
       "age            177\n",
       "sibsp            0\n",
       "parch            0\n",
       "fare             0\n",
       "embarked         2\n",
       "class            0\n",
       "who              0\n",
       "adult_male       0\n",
       "deck           688\n",
       "embark_town      2\n",
       "alive            0\n",
       "alone            0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_titanic.isnull().sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Decidi seguir com o dataset do CSV do Kaggle\n",
    "\n",
    "\n",
    "Inicio de analise exploratória do df_titanic_2\n",
    "\n",
    "Validando valores nullos"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 891 entries, 0 to 890\n",
      "Data columns (total 12 columns):\n",
      " #   Column       Non-Null Count  Dtype  \n",
      "---  ------       --------------  -----  \n",
      " 0   PassengerId  891 non-null    int64  \n",
      " 1   Survived     891 non-null    int64  \n",
      " 2   Pclass       891 non-null    int64  \n",
      " 3   Name         891 non-null    object \n",
      " 4   Sex          891 non-null    object \n",
      " 5   Age          714 non-null    float64\n",
      " 6   SibSp        891 non-null    int64  \n",
      " 7   Parch        891 non-null    int64  \n",
      " 8   Ticket       891 non-null    object \n",
      " 9   Fare         891 non-null    float64\n",
      " 10  Cabin        204 non-null    object \n",
      " 11  Embarked     889 non-null    object \n",
      "dtypes: float64(2), int64(5), object(5)\n",
      "memory usage: 83.7+ KB\n",
      "None\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>PassengerId</th>\n",
       "      <th>Survived</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Name</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>Embarked</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>886</th>\n",
       "      <td>887</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>Montvila, Rev. Juozas</td>\n",
       "      <td>male</td>\n",
       "      <td>27.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>211536</td>\n",
       "      <td>13.00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>887</th>\n",
       "      <td>888</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Graham, Miss. Margaret Edith</td>\n",
       "      <td>female</td>\n",
       "      <td>19.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>112053</td>\n",
       "      <td>30.00</td>\n",
       "      <td>B42</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>888</th>\n",
       "      <td>889</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Johnston, Miss. Catherine Helen \"Carrie\"</td>\n",
       "      <td>female</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>W./C. 6607</td>\n",
       "      <td>23.45</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>889</th>\n",
       "      <td>890</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Behr, Mr. Karl Howell</td>\n",
       "      <td>male</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>111369</td>\n",
       "      <td>30.00</td>\n",
       "      <td>C148</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>890</th>\n",
       "      <td>891</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Dooley, Mr. Patrick</td>\n",
       "      <td>male</td>\n",
       "      <td>32.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>370376</td>\n",
       "      <td>7.75</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Q</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     PassengerId  Survived  Pclass                                      Name  \\\n",
       "886          887         0       2                     Montvila, Rev. Juozas   \n",
       "887          888         1       1              Graham, Miss. Margaret Edith   \n",
       "888          889         0       3  Johnston, Miss. Catherine Helen \"Carrie\"   \n",
       "889          890         1       1                     Behr, Mr. Karl Howell   \n",
       "890          891         0       3                       Dooley, Mr. Patrick   \n",
       "\n",
       "        Sex   Age  SibSp  Parch      Ticket   Fare Cabin Embarked  \n",
       "886    male  27.0      0      0      211536  13.00   NaN        S  \n",
       "887  female  19.0      0      0      112053  30.00   B42        S  \n",
       "888  female   NaN      1      2  W./C. 6607  23.45   NaN        S  \n",
       "889    male  26.0      0      0      111369  30.00  C148        C  \n",
       "890    male  32.0      0      0      370376   7.75   NaN        Q  "
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "print(df_titanic_2.info())\n",
    "df_titanic_2.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x16b286f5848>"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(10,6))\n",
    "sns.heatmap(df_titanic_2.isna(),\n",
    "            cmap=\"YlGnBu_r\",\n",
    "            cbar_kws={'label': 'Missing Data'},\n",
    "           cbar=False,\n",
    "           yticklabels='auto')\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Antes de mais nada. A coluna Cabin vai sair"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_titanic_2.drop(['Cabin'], axis=1,inplace=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Analisando coluna Idade"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "80.13468013468014\n",
      "\n",
      "Isso demosntra 20% do nosso dataset. Algo que eu não gostaria de simplismente perder, mas não quero atribuir qualquer valor para eles\n",
      " Exemplo: simplismente jogar uma moda\n"
     ]
    }
   ],
   "source": [
    "# Analisando valores nullo em Idade. E gostaria de saber quanto ele representa em linhas do nosso dataset\n",
    "#\n",
    "print(\n",
    "    ((df_titanic_2.shape[0] - df_titanic_2.Age.isnull().sum()) * 100) / df_titanic_2.shape[0])\n",
    "# \n",
    "#\n",
    "print(\"\\nIsso demosntra 20% do nosso dataset. Algo que eu não gostaria de simplismente perder, mas não quero atribuir qualquer valor para eles\\n Exemplo: simplismente jogar uma moda\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "> Minha decisão aqui vai ser com relação em volta do sexo. Então ja que gostariamos de descobrir qual a chance de derterminado tipo de sexo sobreviver. Pretendo validar a moda dos dois sexos e atribuir valores a eles."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Analise valores nullos\n",
      "\n",
      "Sexo: Mascolino\n",
      " PassengerId      0\n",
      "Survived         0\n",
      "Pclass           0\n",
      "Name             0\n",
      "Sex              0\n",
      "Age            124\n",
      "SibSp            0\n",
      "Parch            0\n",
      "Ticket           0\n",
      "Fare             0\n",
      "Embarked         0\n",
      "dtype: int64 \n",
      "\n",
      "Sexo: Feminino\n",
      " PassengerId     0\n",
      "Survived        0\n",
      "Pclass          0\n",
      "Name            0\n",
      "Sex             0\n",
      "Age            53\n",
      "SibSp           0\n",
      "Parch           0\n",
      "Ticket          0\n",
      "Fare            0\n",
      "Embarked        2\n",
      "dtype: int64\n"
     ]
    }
   ],
   "source": [
    "print(\"Analise valores nullos\\n\\nSexo: Mascolino\\n\",df_titanic_2[df_titanic_2[\"Sex\"] == \"male\"].isnull().sum(),\"\\n\\nSexo: Feminino\\n\",df_titanic_2[df_titanic_2[\"Sex\"] == \"female\"].isnull().sum())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Tratativa dos dados coluna sexo "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'float'> <class 'float'>\n"
     ]
    }
   ],
   "source": [
    "df_tita_m, num_idade_m = df_titanic_2[df_titanic_2[\"Sex\"] == \"male\"], df_titanic_2[df_titanic_2[\"Sex\"] == \"male\"].Age.mode().tolist()[0]\n",
    "df_tita_f, num_idade_f = df_titanic_2[df_titanic_2[\"Sex\"] == \"female\"], df_titanic_2[df_titanic_2[\"Sex\"] == \"female\"].Age.mode().tolist()[0]\n",
    "\n",
    "print(type(num_idade_f), type(num_idade_m))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\drife\\Downloads\\Programacao\\Anaconda\\lib\\site-packages\\ipykernel_launcher.py:1: 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: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  \"\"\"Entry point for launching an IPython kernel.\n",
      "C:\\Users\\drife\\Downloads\\Programacao\\Anaconda\\lib\\site-packages\\ipykernel_launcher.py:2: 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: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  \n"
     ]
    }
   ],
   "source": [
    "df_tita_m['Age'] = df_tita_m['Age'].fillna(num_idade_m)\n",
    "df_tita_f['Age'] = df_tita_f['Age'].fillna(num_idade_f)\n",
    "\n",
    "print(df_tita_f['Age'].isnull().sum())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(891, 11) \n",
      " PassengerId    0\n",
      "Survived       0\n",
      "Pclass         0\n",
      "Name           0\n",
      "Sex            0\n",
      "Age            0\n",
      "SibSp          0\n",
      "Parch          0\n",
      "Ticket         0\n",
      "Fare           0\n",
      "Embarked       2\n",
      "dtype: int64\n"
     ]
    }
   ],
   "source": [
    "df_titanic_2 = pd.concat([df_tita_m, df_tita_f])\n",
    "print(df_titanic_2.shape,\"\\n\",df_titanic_2.isnull().sum())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "cidade:  S\n"
     ]
    }
   ],
   "source": [
    "str_enbarque_cidade = df_titanic_2.Embarked.mode().tolist()[0]\n",
    "df_titanic_2['Embarked'] = df_titanic_2['Embarked'].fillna(str_enbarque_cidade)\n",
    "print(\"cidade: \",str_enbarque_cidade)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Agora com os nullos tratados, vamos olhar como estão os valores em geral"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Int64Index: 891 entries, 0 to 888\n",
      "Data columns (total 11 columns):\n",
      " #   Column       Non-Null Count  Dtype  \n",
      "---  ------       --------------  -----  \n",
      " 0   PassengerId  891 non-null    int64  \n",
      " 1   Survived     891 non-null    int64  \n",
      " 2   Pclass       891 non-null    int64  \n",
      " 3   Name         891 non-null    object \n",
      " 4   Sex          891 non-null    object \n",
      " 5   Age          891 non-null    float64\n",
      " 6   SibSp        891 non-null    int64  \n",
      " 7   Parch        891 non-null    int64  \n",
      " 8   Ticket       891 non-null    object \n",
      " 9   Fare         891 non-null    float64\n",
      " 10  Embarked     891 non-null    object \n",
      "dtypes: float64(2), int64(5), object(4)\n",
      "memory usage: 83.5+ KB\n",
      "None\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>PassengerId</th>\n",
       "      <th>Survived</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Name</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Braund, Mr. Owen Harris</td>\n",
       "      <td>male</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>A/5 21171</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Allen, Mr. William Henry</td>\n",
       "      <td>male</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>373450</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <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>19.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>330877</td>\n",
       "      <td>8.4583</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>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>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>880</th>\n",
       "      <td>881</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>Shelley, Mrs. William (Imanita Parrish Hall)</td>\n",
       "      <td>female</td>\n",
       "      <td>25.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>230433</td>\n",
       "      <td>26.0000</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>882</th>\n",
       "      <td>883</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Dahlberg, Miss. Gerda Ulrika</td>\n",
       "      <td>female</td>\n",
       "      <td>22.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7552</td>\n",
       "      <td>10.5167</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>885</th>\n",
       "      <td>886</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Rice, Mrs. William (Margaret Norton)</td>\n",
       "      <td>female</td>\n",
       "      <td>39.0</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "      <td>382652</td>\n",
       "      <td>29.1250</td>\n",
       "      <td>Q</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>887</th>\n",
       "      <td>888</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Graham, Miss. Margaret Edith</td>\n",
       "      <td>female</td>\n",
       "      <td>19.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>112053</td>\n",
       "      <td>30.0000</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>888</th>\n",
       "      <td>889</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Johnston, Miss. Catherine Helen \"Carrie\"</td>\n",
       "      <td>female</td>\n",
       "      <td>24.0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>W./C. 6607</td>\n",
       "      <td>23.4500</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>891 rows × 11 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     PassengerId  Survived  Pclass  \\\n",
       "0              1         0       3   \n",
       "4              5         0       3   \n",
       "5              6         0       3   \n",
       "6              7         0       1   \n",
       "7              8         0       3   \n",
       "..           ...       ...     ...   \n",
       "880          881         1       2   \n",
       "882          883         0       3   \n",
       "885          886         0       3   \n",
       "887          888         1       1   \n",
       "888          889         0       3   \n",
       "\n",
       "                                             Name     Sex   Age  SibSp  Parch  \\\n",
       "0                         Braund, Mr. Owen Harris    male  22.0      1      0   \n",
       "4                        Allen, Mr. William Henry    male  35.0      0      0   \n",
       "5                                Moran, Mr. James    male  19.0      0      0   \n",
       "6                         McCarthy, Mr. Timothy J    male  54.0      0      0   \n",
       "7                  Palsson, Master. Gosta Leonard    male   2.0      3      1   \n",
       "..                                            ...     ...   ...    ...    ...   \n",
       "880  Shelley, Mrs. William (Imanita Parrish Hall)  female  25.0      0      1   \n",
       "882                  Dahlberg, Miss. Gerda Ulrika  female  22.0      0      0   \n",
       "885          Rice, Mrs. William (Margaret Norton)  female  39.0      0      5   \n",
       "887                  Graham, Miss. Margaret Edith  female  19.0      0      0   \n",
       "888      Johnston, Miss. Catherine Helen \"Carrie\"  female  24.0      1      2   \n",
       "\n",
       "         Ticket     Fare Embarked  \n",
       "0     A/5 21171   7.2500        S  \n",
       "4        373450   8.0500        S  \n",
       "5        330877   8.4583        Q  \n",
       "6         17463  51.8625        S  \n",
       "7        349909  21.0750        S  \n",
       "..          ...      ...      ...  \n",
       "880      230433  26.0000        S  \n",
       "882        7552  10.5167        S  \n",
       "885      382652  29.1250        Q  \n",
       "887      112053  30.0000        S  \n",
       "888  W./C. 6607  23.4500        S  \n",
       "\n",
       "[891 rows x 11 columns]"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "print(df_titanic_2.info())\n",
    "df_titanic_2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Analisando porcentagem de cada sexo para saber se vai ser enviesado "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "64.75869809203142"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Prcentagem Homem\n",
    "#\n",
    "(df_tita_m.shape[0]*100)/df_titanic_2.shape[0] "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "35.24130190796858"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Prcentagem Mulher\n",
    "#\n",
    "(df_tita_f.shape[0]*100)/df_titanic_2.shape[0]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Podemos ver que tem muito mais dados para o sexo mscolino. O que pode comprometer o algoritimo.\n",
    "\n",
    "Mas antes para responder a pergunta de uma forma rapida sobre o sexo feminino. Vamos vereficar qual a chance de uma mulher sobreviver. Sem aplicar algoritimo."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead 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>Sex</th>\n",
       "      <th>Survived</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>male</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>male</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>male</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>male</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>male</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>880</th>\n",
       "      <td>female</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>882</th>\n",
       "      <td>female</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>885</th>\n",
       "      <td>female</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>887</th>\n",
       "      <td>female</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>888</th>\n",
       "      <td>female</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>891 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        Sex  Survived\n",
       "0      male         0\n",
       "4      male         0\n",
       "5      male         0\n",
       "6      male         0\n",
       "7      male         0\n",
       "..      ...       ...\n",
       "880  female         1\n",
       "882  female         0\n",
       "885  female         0\n",
       "887  female         1\n",
       "888  female         0\n",
       "\n",
       "[891 rows x 2 columns]"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_tita_2colunas = df_titanic_2[[\"Sex\",\"Survived\"]]\n",
    "df_tita_2colunas"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Podemos analisar que em geral mulher sobreviveu mais do que homem\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Somatória de todos os 1 \"sobrevieventes\"\n",
    "#\n",
    "df_groupSum = df_tita_2colunas.groupby(['Sex'])[\"Survived\"].sum()\n",
    "df_groupSum.plot.barh()\n",
    "# Add title\n",
    "plt.title('Numero de pessoas que sobreviveram por sexo');\n",
    "\n",
    "print(\"Podemos analisar que em geral mulher sobreviveu mais do que homem\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "total de sobrevientes femininas entre as mulheres:  74.2 %\n",
      "total de sobrevientes femininas:  26.15 %\n"
     ]
    }
   ],
   "source": [
    "# Criando dataframe com a contegem de cada sexo\n",
    "#\n",
    "df_groupCount = df_tita_2colunas.groupby(['Sex'])[\"Survived\"].count()\n",
    "#\n",
    "# Resposta\n",
    "\n",
    "\n",
    "print(\"total de sobrevientes femininas entre as mulheres: \",np.round((df_groupSum[\"female\"]*100 )/ df_groupCount[\"female\"],decimals=2),\"%\")\n",
    "\n",
    "print(\"total de sobrevientes femininas: \",np.round((df_groupSum[\"female\"]*100 )/ df_groupCount.sum(),decimals=2),\"%\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Uma vez respondido. Agora vamos entrar com o modelo de ML\n",
    "\n",
    "Isso é um problema do que afinal?\n",
    "\n",
    "1. primeiro, temos um valor Y como saida. Então vamos usar modelos *SUPERVISIONADO*\n",
    "2. Não é série temporal. Então não estamos olhando para problemas e respóstas contendo tempo.\n",
    "3. A saida não é um valoir continuo, e sim *CATEGÓRICO*. Portanto isso é um problema de *REGRESS LOGÍSTICA*\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Modelos em mente\n",
    "\n",
    "> Naive Bayes\n",
    "\n",
    "> Regressão Logística (Logistic Regression)\n",
    "\n",
    "> Clustering ou algoritmos de agrupamento - KNN\n",
    "\n",
    "> Árvore de decisão\n",
    "\n",
    "> Florestas Aleatórias\n",
    "\n",
    "> SVM"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "# Modelos\n",
    "#\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.naive_bayes import GaussianNB\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn import svm, tree\n",
    "\n",
    "# Separação de treino\n",
    "#\n",
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "# Normalisação dos dados\n",
    "#\n",
    "from sklearn.preprocessing import LabelEncoder, StandardScaler\n",
    "\n",
    "# Redução de Dimensionalidade\n",
    "#\n",
    "from sklearn.decomposition import PCA\n",
    "\n",
    "\n",
    "# Metricas de resultados\n",
    "#\n",
    "from sklearn.metrics import confusion_matrix, accuracy_score, classification_report, precision_score, recall_score, \\\n",
    "                            f1_score, ConfusionMatrixDisplay\n",
    "\n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "def component_analysis(e, plot='none'):\n",
    "    varexp = 100* e/e.sum()\n",
    "    cumvarexp = np.cumsum(varexp)\n",
    "    # Plotando os autovalores\n",
    "    if (plot=='eigen'):\n",
    "        plt.figure(figsize = (4,4))\n",
    "        plt.plot(e, '-o')\n",
    "        plt.grid(True)\n",
    "        plt.xlabel('Componente', fontsize = 15)\n",
    "        plt.ylabel('Autovalor', fontsize = 15)\n",
    "        xint = []\n",
    "        locs, labels = plt.xticks()\n",
    "        for each in locs:\n",
    "            xint.append(int(each))\n",
    "        plt.xticks(xint)\n",
    "\n",
    "    # Plotando a explicação da variancia\n",
    "    if (plot=='varexp'):\n",
    "        plt.figure(figsize = (4,4))\n",
    "        plt.plot(cumvarexp, '-o')\n",
    "        plt.xlabel('Componente', fontsize = 15)\n",
    "        plt.ylabel('% da variancia explicada', fontsize = 15)\n",
    "        plt.grid(True)\n",
    "        xint = []\n",
    "        locs, labels = plt.xticks()\n",
    "        for each in locs:\n",
    "            xint.append(int(each))\n",
    "        plt.xticks(xint)\n",
    "\n",
    "    plt.show()\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "le_s = LabelEncoder()\n",
    "le_e = LabelEncoder()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['female' 'male'] [0 1]\n"
     ]
    }
   ],
   "source": [
    "le_s.fit(df_titanic_2.Sex)\n",
    "df_titanic_2[\"Sex\"] = le_s.transform(df_titanic_2.Sex)\n",
    "print(le_s.classes_, le_s.transform(le_s.classes_))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['C' 'Q' 'S'] [0 1 2]\n"
     ]
    }
   ],
   "source": [
    "le_e.fit(df_titanic_2.Embarked)\n",
    "df_titanic_2[\"Embarked\"] = le_e.transform(df_titanic_2.Embarked)\n",
    "print(le_e.classes_, le_e.transform(le_e.classes_))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Index(['PassengerId', 'Survived', 'Pclass', 'Name', 'Sex', 'Age', 'SibSp',\n",
      "       'Parch', 'Ticket', 'Fare', 'Embarked'],\n",
      "      dtype='object')\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>PassengerId</th>\n",
       "      <th>Survived</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Name</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Braund, Mr. Owen Harris</td>\n",
       "      <td>1</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>2</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>1</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>2</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>1</td>\n",
       "      <td>19.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>330877</td>\n",
       "      <td>8.4583</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   PassengerId  Survived  Pclass                      Name  Sex   Age  SibSp  \\\n",
       "0            1         0       3   Braund, Mr. Owen Harris    1  22.0      1   \n",
       "4            5         0       3  Allen, Mr. William Henry    1  35.0      0   \n",
       "5            6         0       3          Moran, Mr. James    1  19.0      0   \n",
       "\n",
       "   Parch     Ticket    Fare  Embarked  \n",
       "0      0  A/5 21171  7.2500         2  \n",
       "4      0     373450  8.0500         2  \n",
       "5      0     330877  8.4583         1  "
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "print(df_titanic_2.columns)\n",
    "df_titanic_2.head(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Survived</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>19.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.4583</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>54.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>51.8625</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>21.0750</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>880</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>25.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>26.0000</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>882</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>10.5167</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>885</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>39.0</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "      <td>29.1250</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>887</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>19.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>30.0000</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>888</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>24.0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>23.4500</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>891 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Survived  Pclass  Sex   Age  SibSp  Parch     Fare  Embarked\n",
       "0           0       3    1  22.0      1      0   7.2500         2\n",
       "4           0       3    1  35.0      0      0   8.0500         2\n",
       "5           0       3    1  19.0      0      0   8.4583         1\n",
       "6           0       1    1  54.0      0      0  51.8625         2\n",
       "7           0       3    1   2.0      3      1  21.0750         2\n",
       "..        ...     ...  ...   ...    ...    ...      ...       ...\n",
       "880         1       2    0  25.0      0      1  26.0000         2\n",
       "882         0       3    0  22.0      0      0  10.5167         2\n",
       "885         0       3    0  39.0      0      5  29.1250         1\n",
       "887         1       1    0  19.0      0      0  30.0000         2\n",
       "888         0       3    0  24.0      1      2  23.4500         2\n",
       "\n",
       "[891 rows x 8 columns]"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_titanic_tratado = df_titanic_2[['Survived', 'Pclass','Sex', 'Age', 'SibSp','Parch','Fare', 'Embarked']]\n",
    "df_titanic_tratado"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Aqui começa a minha pesquisa de modelos aplicaveis"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[9.30762461e-01 6.81252209e-02 4.86328019e-04 2.18525511e-04\n",
      " 1.78131065e-04 1.54541268e-04 7.47921778e-05]\n"
     ]
    }
   ],
   "source": [
    "\n",
    "\n",
    "#### Montando opções de dados tabulares\n",
    "#\n",
    "#\n",
    "#\n",
    "\n",
    "\n",
    "# Separando em matriz valores dependentes e independentes\n",
    "#\n",
    "# nosso targuet \"y\"\n",
    "Y = df_titanic_tratado['Survived'].values\n",
    "# nossos valores\n",
    "x = df_titanic_tratado.drop(['Survived'], axis=1).values\n",
    "\n",
    "\n",
    "# Variaveis\n",
    "#\n",
    "pca = PCA()\n",
    "sc = StandardScaler()\n",
    "\n",
    "\n",
    "# Vamos normalizar os dados da tabela\n",
    "#\n",
    "X_norm = sc.fit_transform(x)\n",
    "\n",
    "# Vamos construir opções de dados tabulares com PCA\n",
    "#\n",
    "X_pca = pca.fit_transform(x)\n",
    "print(pca.explained_variance_ratio_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(891, 7)"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(891, 7)"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_norm.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(891, 7)"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_pca.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[9.30762461e-01 6.81252209e-02 4.86328019e-04 2.18525511e-04\n",
      " 1.78131065e-04 1.54541268e-04 7.47921778e-05] \n",
      "\n",
      "Exemplo dos tres mais siginificativos:  [9.30762461e-01 6.81252209e-02 4.86328019e-04]\n",
      "\n",
      "\n",
      "Total soma:  0.9999999999999998\n"
     ]
    }
   ],
   "source": [
    "# Essa é a separação feita do PCA referente dos maiores relacionados\n",
    "#\n",
    "print(pca.explained_variance_ratio_,\"\\n\\nExemplo dos tres mais siginificativos: \", pca.explained_variance_ratio_[:3])\n",
    "\n",
    "# A soma tem que dar 100%\n",
    "#\n",
    "print(\"\\n\\nTotal soma: \",pca.explained_variance_ratio_.sum())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 288x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Aqui é o plot para ver quem da mais. \n",
    "#\n",
    "component_analysis(pca.explained_variance_ratio_, plot=\"varexp\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[9.30762461e-01 6.81252209e-02 4.86328019e-04]\n"
     ]
    }
   ],
   "source": [
    "# Instânciando e treinando nosso PCA\n",
    "pca = PCA(3)\n",
    "pca.fit(x)\n",
    "print(pca.explained_variance_ratio_)\n",
    "\n",
    "# Vamos construir opções de dados tabulares com PCA\n",
    "#\n",
    "X_pca = pca.fit_transform(x)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[-25.15008928,  -5.01287064,   0.35765547],\n",
       "       [-23.90196778,   7.96590211,  -0.21881133],\n",
       "       [-24.04685803,  -8.03412335,  -0.76463422],\n",
       "       ...,\n",
       "       [ -2.67920151,  11.17457971,   1.78538957],\n",
       "       [ -2.50280141,  -8.74711259,  -0.87559684],\n",
       "       [ -8.88264298,  -3.60070008,   1.23891104]])"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_pca"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Tamanho dos dados:  891 \n",
      "Tamanho de Treino: (757,) \n",
      "Tamanho de Prova:  (134,)\n"
     ]
    }
   ],
   "source": [
    "### Dividindo em Train Test\n",
    "#\n",
    "#\n",
    "\n",
    "# Padrão\n",
    "X_train, X_test, y_train, y_test = train_test_split(x, Y, test_size=0.15, random_state = 0)\n",
    "print(\"Tamanho dos dados: \",len(Y),\"\\nTamanho de Treino:\",y_train.shape,\"\\nTamanho de Prova: \",y_test.shape )\n",
    "\n",
    "# pca\n",
    "X_pca_train, X_pca_test, y_pca_train, y_pca_test = train_test_split(X_pca, Y, test_size=0.15, random_state = 0)\n",
    "\n",
    "# norm\n",
    "X_norm_train, X_norm_test, y_norm_train, y_norm_test = train_test_split(X_norm, Y, test_size=0.15, random_state = 0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "knn:\n",
      "               precision    recall  f1-score   support\n",
      "\n",
      "           0       0.74      0.82      0.78        78\n",
      "           1       0.71      0.61      0.65        56\n",
      "\n",
      "    accuracy                           0.73       134\n",
      "   macro avg       0.73      0.71      0.72       134\n",
      "weighted avg       0.73      0.73      0.73       134\n",
      "\n"
     ]
    }
   ],
   "source": [
    "### Padrão\n",
    "#\n",
    "#\n",
    "\n",
    "# KNN\n",
    "#\n",
    "knn = KNeighborsClassifier()\n",
    "#\n",
    "knn.fit(X_train, y_train)\n",
    "#\n",
    "# Calcular a acurácia do modelo nos dados de teste\n",
    "X_pred_knn = knn.predict(X_test)\n",
    "#\n",
    "print(\"knn:\\n\",classification_report(y_test,X_pred_knn))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "knn:\n",
      "               precision    recall  f1-score   support\n",
      "\n",
      "           0       0.71      0.78      0.74        78\n",
      "           1       0.65      0.55      0.60        56\n",
      "\n",
      "    accuracy                           0.69       134\n",
      "   macro avg       0.68      0.67      0.67       134\n",
      "weighted avg       0.68      0.69      0.68       134\n",
      "\n",
      "\n",
      " Gaussian:\n",
      "               precision    recall  f1-score   support\n",
      "\n",
      "           0       0.64      0.95      0.76        78\n",
      "           1       0.78      0.25      0.38        56\n",
      "\n",
      "    accuracy                           0.66       134\n",
      "   macro avg       0.71      0.60      0.57       134\n",
      "weighted avg       0.70      0.66      0.60       134\n",
      "\n"
     ]
    }
   ],
   "source": [
    "### PCA\n",
    "#\n",
    "#\n",
    "\n",
    "# KNN\n",
    "#\n",
    "knn_pca = KNeighborsClassifier()\n",
    "#\n",
    "knn_pca.fit(X_pca_train, y_pca_train)\n",
    "#\n",
    "# Calcular a acurácia do modelo nos dados de teste\n",
    "X_pca_pred_knn = knn_pca.predict(X_pca_test)\n",
    "#\n",
    "print(\"knn:\\n\",classification_report(y_pca_test,X_pca_pred_knn))\n",
    "\n",
    "\n",
    "\n",
    "# Gaus\n",
    "#\n",
    "gnb = GaussianNB()\n",
    "#\n",
    "gnb.fit(X_pca_train, y_pca_train)\n",
    "#\n",
    "# Calcular a acurácia do modelo nos dados de teste\n",
    "X_pred_gnb = gnb.predict(X_pca_test)\n",
    "#\n",
    "print(\"\\n Gaussian:\\n\",classification_report(y_pca_test,X_pred_gnb))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "knn:\n",
      "               precision    recall  f1-score   support\n",
      "\n",
      "           0       0.79      0.83      0.81        78\n",
      "           1       0.75      0.70      0.72        56\n",
      "\n",
      "    accuracy                           0.78       134\n",
      "   macro avg       0.77      0.76      0.77       134\n",
      "weighted avg       0.77      0.78      0.77       134\n",
      "\n",
      "\n",
      " Gaussian:\n",
      "               precision    recall  f1-score   support\n",
      "\n",
      "           0       0.78      0.73      0.75        78\n",
      "           1       0.66      0.71      0.68        56\n",
      "\n",
      "    accuracy                           0.72       134\n",
      "   macro avg       0.72      0.72      0.72       134\n",
      "weighted avg       0.73      0.72      0.73       134\n",
      "\n"
     ]
    }
   ],
   "source": [
    "### SC\n",
    "#\n",
    "#\n",
    "\n",
    "\n",
    "# KNN\n",
    "#\n",
    "knn_norm = KNeighborsClassifier()\n",
    "#\n",
    "knn_norm.fit(X_norm_train, y_norm_train)\n",
    "#\n",
    "# Calcular a acurácia do modelo nos dados de teste\n",
    "X_norm_pred_knn = knn_norm.predict(X_norm_test)\n",
    "#\n",
    "print(\"knn:\\n\",classification_report(y_norm_test,X_norm_pred_knn))\n",
    "\n",
    "\n",
    "\n",
    "# Gaus\n",
    "#\n",
    "gnb_norm = GaussianNB()\n",
    "#\n",
    "gnb_norm.fit(X_norm_train, y_norm_train)\n",
    "#\n",
    "# Calcular a acurácia do modelo nos dados de teste\n",
    "X_norm_pred_gnb = gnb_norm.predict(X_norm_test)\n",
    "#\n",
    "print(\"\\n Gaussian:\\n\",classification_report(y_norm_test,X_norm_pred_gnb))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Como não mudou muitoa coisa. Vamos Começar a vereficar que modelo melhor tem resultado e como chgar no hiperparametro de cada um deles. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import cross_val_score"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### SVC model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [],
   "source": [
    "model_svc = svm.SVC(kernel='linear', C=1, random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.67 (+/- 0.05)\n"
     ]
    }
   ],
   "source": [
    "scores_svc = cross_val_score(model_svc, X_pca, Y, cv=3)\n",
    "print(\"Accuracy: %0.2f (+/- %0.2f)\" % (scores_svc.mean(), scores_svc.std() * 2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.78 (+/- 0.37)\n"
     ]
    }
   ],
   "source": [
    "scores_svc = cross_val_score(model_svc, x, Y, cv=5)\n",
    "print(\"Accuracy: %0.2f (+/- %0.2f)\" % (scores_svc.mean(), scores_svc.std() * 2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.78 (+/- 0.37)\n"
     ]
    }
   ],
   "source": [
    "scores_svc = cross_val_score(model_svc, X_norm, Y, cv=5)\n",
    "print(\"Accuracy: %0.2f (+/- %0.2f)\" % (scores_svc.mean(), scores_svc.std() * 2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.67 (+/- 0.10)\n",
      "Accuracy: 0.68 (+/- 0.06)\n",
      "Accuracy: 0.78 (+/- 0.30)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "SVC()"
      ]
     },
     "execution_count": 96,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model_svcPadrao = svm.SVC()\n",
    "\n",
    "scores_svc = cross_val_score(model_svcPadrao, x, Y, cv=5)\n",
    "print(\"Accuracy: %0.2f (+/- %0.2f)\" % (scores_svc.mean(), scores_svc.std() * 2))\n",
    "\n",
    "\n",
    "scores_svc = cross_val_score(model_svcPadrao, X_pca, Y, cv=3)\n",
    "print(\"Accuracy: %0.2f (+/- %0.2f)\" % (scores_svc.mean(), scores_svc.std() * 2))\n",
    "\n",
    "scores_svc = cross_val_score(model_svcPadrao, X_norm, Y, cv=5)\n",
    "print(\"Accuracy: %0.2f (+/- %0.2f)\" % (scores_svc.mean(), scores_svc.std() * 2))\n",
    "\n",
    "model_svcPadrao.fit(X_norm, Y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##### knn Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.69 (+/- 0.11)\n"
     ]
    }
   ],
   "source": [
    "scores_knn = cross_val_score(knn, x, Y, cv=5)\n",
    "print(\"Accuracy: %0.2f (+/- %0.2f)\" % (scores_knn.mean(), scores_knn.std() * 2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.68 (+/- 0.08)\n"
     ]
    }
   ],
   "source": [
    "scores_knn = cross_val_score(knn, X_pca, Y, cv=5)\n",
    "print(\"Accuracy: %0.2f (+/- %0.2f)\" % (scores_knn.mean(), scores_knn.std() * 2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.76 (+/- 0.25)\n"
     ]
    }
   ],
   "source": [
    "scores_knn = cross_val_score(knn, X_norm, Y, cv=5)\n",
    "print(\"Accuracy: %0.2f (+/- %0.2f)\" % (scores_knn.mean(), scores_knn.std() * 2))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "gnb Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.75 (+/- 0.27)\n"
     ]
    }
   ],
   "source": [
    "scores_gnb = cross_val_score(gnb, x, Y, cv=5)\n",
    "print(\"Accuracy: %0.2f (+/- %0.2f)\" % (scores_gnb.mean(), scores_gnb.std() * 2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.67 (+/- 0.09)\n"
     ]
    }
   ],
   "source": [
    "scores_gnb = cross_val_score(gnb, X_pca, Y, cv=5)\n",
    "print(\"Accuracy: %0.2f (+/- %0.2f)\" % (scores_gnb.mean(), scores_gnb.std() * 2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.75 (+/- 0.27)\n"
     ]
    }
   ],
   "source": [
    "scores_gnb = cross_val_score(gnb, X_norm, Y, cv=5)\n",
    "print(\"Accuracy: %0.2f (+/- %0.2f)\" % (scores_gnb.mean(), scores_gnb.std() * 2))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "tree Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [],
   "source": [
    "model_tree = tree.DecisionTreeClassifier()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.74 (+/- 0.23)\n"
     ]
    }
   ],
   "source": [
    "scores_tree = cross_val_score(model_tree, x, Y, cv=5)\n",
    "print(\"Accuracy: %0.2f (+/- %0.2f)\" % (scores_tree.mean(), scores_tree.std() * 2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.67 (+/- 0.09)\n"
     ]
    }
   ],
   "source": [
    "scores_tree = cross_val_score(model_tree, X_pca, Y, cv=5)\n",
    "print(\"Accuracy: %0.2f (+/- %0.2f)\" % (scores_tree.mean(), scores_tree.std() * 2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.74 (+/- 0.24)\n"
     ]
    }
   ],
   "source": [
    "scores_tree = cross_val_score(model_tree, X_norm, Y, cv=5)\n",
    "print(\"Accuracy: %0.2f (+/- %0.2f)\" % (scores_tree.mean(), scores_tree.std() * 2))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "LogisticRegression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [],
   "source": [
    "model_lRegress = LogisticRegression()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.76 (+/- 0.32)\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\drife\\Downloads\\Programacao\\Anaconda\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:765: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  extra_warning_msg=_LOGISTIC_SOLVER_CONVERGENCE_MSG)\n"
     ]
    }
   ],
   "source": [
    "scores_lRegress = cross_val_score(model_lRegress, x, Y, cv=5)\n",
    "print(\"Accuracy: %0.2f (+/- %0.2f)\" % (scores_lRegress.mean(), scores_lRegress.std() * 2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.67 (+/- 0.08)\n"
     ]
    }
   ],
   "source": [
    "scores_lRegress = cross_val_score(model_lRegress, X_pca, Y, cv=5)\n",
    "print(\"Accuracy: %0.2f (+/- %0.2f)\" % (scores_lRegress.mean(), scores_lRegress.std() * 2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.76 (+/- 0.32)\n"
     ]
    }
   ],
   "source": [
    "scores_lRegress = cross_val_score(model_lRegress, X_norm, Y, cv=5)\n",
    "print(\"Accuracy: %0.2f (+/- %0.2f)\" % (scores_lRegress.mean(), scores_lRegress.std() * 2))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "O resultado do PCA ja me mostra resultados piores, Pretendo usar a SC e os valores normais.\n",
    "E gostaria de vlidar em cima dos modelos de melhor resultado."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Agora vamos criar um modelo monstro, padrão Frankenstein"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.ensemble import VotingClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Validação com Voting\n",
    "voting_classifier = VotingClassifier([(\"SVC\",svm.SVC(kernel='linear', C=1)),\n",
    "                                     (\"gnb\", GaussianNB() ),\n",
    "                                     (\"L_Regress\",LogisticRegression())])\n",
    "\n",
    "voting_classifier_Norm = VotingClassifier([(\"SVC\",svm.SVC(kernel='linear', C=1)),\n",
    "                                          (\"KNN\",KNeighborsClassifier()),\n",
    "                                          (\"gnb\", GaussianNB()),\n",
    "                                          (\"tree\", tree.DecisionTreeClassifier()),\n",
    "                                          (\"L_Regress\",LogisticRegression())])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\drife\\Downloads\\Programacao\\Anaconda\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:765: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  extra_warning_msg=_LOGISTIC_SOLVER_CONVERGENCE_MSG)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "VotingClassifier(estimators=[('SVC', SVC(C=1, kernel='linear')),\n",
       "                             ('KNN', KNeighborsClassifier()),\n",
       "                             ('gnb', GaussianNB()),\n",
       "                             ('tree', DecisionTreeClassifier()),\n",
       "                             ('L_Regress', LogisticRegression())])"
      ]
     },
     "execution_count": 64,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# X_train, X_test, y_train, y_test = train_test_split(x, Y, test_size=0.15, random_state = 0)\n",
    "\n",
    "#X_norm_train, X_norm_test, y_norm_train, y_norm_test = train_test_split(X_norm, Y, test_size=0.15, random_state = 0)\n",
    "\n",
    "\n",
    "# Treianndo Monstro\n",
    "#\n",
    "voting_classifier.fit(X_train,y_train)\n",
    "#\n",
    "voting_classifier_Norm.fit(X_norm_train,y_norm_train)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[62 16]\n",
      " [17 39]]\n",
      "0.753731343283582\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.78      0.79      0.79        78\n",
      "           1       0.71      0.70      0.70        56\n",
      "\n",
      "    accuracy                           0.75       134\n",
      "   macro avg       0.75      0.75      0.75       134\n",
      "weighted avg       0.75      0.75      0.75       134\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# Verificando a metrica\n",
    "\n",
    "y_pred = voting_classifier.predict(X_test)\n",
    "\n",
    "cm = confusion_matrix(y_test, y_pred)\n",
    "print(cm)\n",
    "print(accuracy_score(y_test, y_pred))\n",
    "print(classification_report(y_test, y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[ 2 76]\n",
      " [ 0 56]]\n",
      "0.43283582089552236\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       1.00      0.03      0.05        78\n",
      "           1       0.42      1.00      0.60        56\n",
      "\n",
      "    accuracy                           0.43       134\n",
      "   macro avg       0.71      0.51      0.32       134\n",
      "weighted avg       0.76      0.43      0.28       134\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# Verificando a metrica\n",
    "\n",
    "y_norm_pred = voting_classifier.predict(X_norm_test)\n",
    "\n",
    "cm = confusion_matrix(y_norm_test, y_norm_pred)\n",
    "print(cm)\n",
    "print(accuracy_score(y_norm_test, y_norm_pred))\n",
    "print(classification_report(y_norm_test, y_norm_pred))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Com CorssV"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 107,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\drife\\Downloads\\Programacao\\Anaconda\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:765: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  extra_warning_msg=_LOGISTIC_SOLVER_CONVERGENCE_MSG)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.77 (+/- 0.33)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "VotingClassifier(estimators=[('SVC', SVC(C=1, kernel='linear')),\n",
       "                             ('gnb', GaussianNB()),\n",
       "                             ('L_Regress', LogisticRegression())])"
      ]
     },
     "execution_count": 107,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "scores_Vt = cross_val_score(voting_classifier, x, Y, cv=5)\n",
    "print(\"Accuracy: %0.2f (+/- %0.2f)\" % (scores_Vt.mean(), scores_Vt.std() * 2))\n",
    "\n",
    "voting_classifier.fit(x, Y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.76 (+/- 0.33)\n"
     ]
    }
   ],
   "source": [
    "scores_Vt_norm = cross_val_score(voting_classifier_Norm, X_norm, Y, cv=5)\n",
    "print(\"Accuracy: %0.2f (+/- %0.2f)\" % (scores_Vt_norm.mean(), scores_Vt_norm.std() * 2))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### visualização em tabela"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Model</th>\n",
       "      <th>Score</th>\n",
       "      <th>DP</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Support Vector Machines</td>\n",
       "      <td>0.782399</td>\n",
       "      <td>0.303191</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Voting S_G_LR</td>\n",
       "      <td>0.766725</td>\n",
       "      <td>0.334379</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Voting Norm S_K_G_T_LR</td>\n",
       "      <td>0.762231</td>\n",
       "      <td>0.326377</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>knn_norm</td>\n",
       "      <td>0.758816</td>\n",
       "      <td>0.249070</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>L_Regress_norm</td>\n",
       "      <td>0.756619</td>\n",
       "      <td>0.321062</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>gnb</td>\n",
       "      <td>0.746475</td>\n",
       "      <td>0.273130</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>tree</td>\n",
       "      <td>0.739677</td>\n",
       "      <td>0.237569</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                     Model     Score        DP\n",
       "0  Support Vector Machines  0.782399  0.303191\n",
       "1            Voting S_G_LR  0.766725  0.334379\n",
       "2   Voting Norm S_K_G_T_LR  0.762231  0.326377\n",
       "4                 knn_norm  0.758816  0.249070\n",
       "3           L_Regress_norm  0.756619  0.321062\n",
       "5                      gnb  0.746475  0.273130\n",
       "6                     tree  0.739677  0.237569"
      ]
     },
     "execution_count": 69,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "models = pd.DataFrame({\n",
    "    'Model': ['Support Vector Machines','Voting S_G_LR','Voting Norm S_K_G_T_LR','L_Regress_norm','knn_norm','gnb','tree'],\n",
    "    'Score': [scores_svc.mean(),scores_Vt.mean(), scores_Vt_norm.mean(), scores_lRegress.mean(),scores_knn.mean(),scores_gnb.mean(),scores_tree.mean()],\n",
    "'DP': [scores_svc.std() * 2, scores_Vt.std() * 2, scores_Vt_norm.std() * 2, scores_lRegress.std() * 2, scores_knn.std() * 2, scores_gnb.std() * 2,scores_tree.std() * 2]})\n",
    "\n",
    "models.sort_values(by='Score', ascending=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Puxando Base Teste"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(418, 11)"
      ]
     },
     "execution_count": 70,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# titanic do Kaggle baixado em CSV\n",
    "#\n",
    "df_titanic_test = pd.read_csv('test.csv')\n",
    "df_titanic_test.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_titanic_test.drop(['Ticket','Cabin','Name'], axis=1,inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "PassengerId     0\n",
       "Pclass          0\n",
       "Sex             0\n",
       "Age            86\n",
       "SibSp           0\n",
       "Parch           0\n",
       "Fare            1\n",
       "Embarked        0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 72,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_titanic_test.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(418, 8)"
      ]
     },
     "execution_count": 73,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "####df_titanic_test.dropna(subset=['Fare'],axis=0, inplace=True)\n",
    "num_meanFeare = df_titanic_test[\"Fare\"].mean()\n",
    "df_titanic_test[\"Fare\"] = df_titanic_test[\"Fare\"].fillna(num_meanFeare)\n",
    "\n",
    "df_titanic_test.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "PassengerId     0\n",
       "Pclass          0\n",
       "Sex             0\n",
       "Age            86\n",
       "SibSp           0\n",
       "Parch           0\n",
       "Fare            0\n",
       "Embarked        0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 74,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_titanic_test.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_titanic_test['Age'] = df_titanic_test['Age'].fillna(np.round(df_titanic_test['Age'].mean(), 0))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['Survived', 'Pclass', 'Sex', 'Age', 'SibSp', 'Parch', 'Fare',\n",
       "       'Embarked'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 76,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_titanic_tratado.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['PassengerId', 'Pclass', 'Sex', 'Age', 'SibSp', 'Parch', 'Fare',\n",
       "       'Embarked'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 77,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_titanic_test.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(418, 8)\n"
     ]
    }
   ],
   "source": [
    "print(df_titanic_test.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>PassengerId</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>892</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>34.5</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.8292</td>\n",
       "      <td>Q</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>893</td>\n",
       "      <td>3</td>\n",
       "      <td>female</td>\n",
       "      <td>47.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7.0000</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>894</td>\n",
       "      <td>2</td>\n",
       "      <td>male</td>\n",
       "      <td>62.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>9.6875</td>\n",
       "      <td>Q</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>895</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>27.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.6625</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>896</td>\n",
       "      <td>3</td>\n",
       "      <td>female</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>12.2875</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>413</th>\n",
       "      <td>1305</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>30.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>414</th>\n",
       "      <td>1306</td>\n",
       "      <td>1</td>\n",
       "      <td>female</td>\n",
       "      <td>39.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>108.9000</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>415</th>\n",
       "      <td>1307</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>38.5</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>416</th>\n",
       "      <td>1308</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>30.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>417</th>\n",
       "      <td>1309</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>30.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>22.3583</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>418 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     PassengerId  Pclass     Sex   Age  SibSp  Parch      Fare Embarked\n",
       "0            892       3    male  34.5      0      0    7.8292        Q\n",
       "1            893       3  female  47.0      1      0    7.0000        S\n",
       "2            894       2    male  62.0      0      0    9.6875        Q\n",
       "3            895       3    male  27.0      0      0    8.6625        S\n",
       "4            896       3  female  22.0      1      1   12.2875        S\n",
       "..           ...     ...     ...   ...    ...    ...       ...      ...\n",
       "413         1305       3    male  30.0      0      0    8.0500        S\n",
       "414         1306       1  female  39.0      0      0  108.9000        C\n",
       "415         1307       3    male  38.5      0      0    7.2500        S\n",
       "416         1308       3    male  30.0      0      0    8.0500        S\n",
       "417         1309       3    male  30.0      1      1   22.3583        C\n",
       "\n",
       "[418 rows x 8 columns]"
      ]
     },
     "execution_count": 82,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_titanic_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "    </tr>\n",
       "    <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",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>892</th>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>34.5</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.8292</td>\n",
       "      <td>Q</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>893</th>\n",
       "      <td>3</td>\n",
       "      <td>female</td>\n",
       "      <td>47.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7.0000</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>894</th>\n",
       "      <td>2</td>\n",
       "      <td>male</td>\n",
       "      <td>62.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>9.6875</td>\n",
       "      <td>Q</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>895</th>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>27.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.6625</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>896</th>\n",
       "      <td>3</td>\n",
       "      <td>female</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>12.2875</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1305</th>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>30.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1306</th>\n",
       "      <td>1</td>\n",
       "      <td>female</td>\n",
       "      <td>39.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>108.9000</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1307</th>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>38.5</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1308</th>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>30.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1309</th>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>30.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>22.3583</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>418 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "             Pclass     Sex   Age  SibSp  Parch      Fare Embarked\n",
       "PassengerId                                                       \n",
       "892               3    male  34.5      0      0    7.8292        Q\n",
       "893               3  female  47.0      1      0    7.0000        S\n",
       "894               2    male  62.0      0      0    9.6875        Q\n",
       "895               3    male  27.0      0      0    8.6625        S\n",
       "896               3  female  22.0      1      1   12.2875        S\n",
       "...             ...     ...   ...    ...    ...       ...      ...\n",
       "1305              3    male  30.0      0      0    8.0500        S\n",
       "1306              1  female  39.0      0      0  108.9000        C\n",
       "1307              3    male  38.5      0      0    7.2500        S\n",
       "1308              3    male  30.0      0      0    8.0500        S\n",
       "1309              3    male  30.0      1      1   22.3583        C\n",
       "\n",
       "[418 rows x 7 columns]"
      ]
     },
     "execution_count": 84,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "##df_tita_test.drop(['PassengerId'], axis=1,inplace=True)\n",
    "df_titanic_test.set_index(['PassengerId'],inplace=True)\n",
    "df_titanic_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Embarked</th>\n",
       "    </tr>\n",
       "    <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",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>892</th>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>34.5</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.8292</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>893</th>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>47.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7.0000</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>894</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>62.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>9.6875</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>895</th>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>27.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.6625</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>896</th>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>12.2875</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1305</th>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>30.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1306</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>39.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>108.9000</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1307</th>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>38.5</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1308</th>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>30.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1309</th>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>30.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>22.3583</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>418 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "             Pclass  Sex   Age  SibSp  Parch      Fare  Embarked\n",
       "PassengerId                                                     \n",
       "892               3    1  34.5      0      0    7.8292         1\n",
       "893               3    0  47.0      1      0    7.0000         2\n",
       "894               2    1  62.0      0      0    9.6875         1\n",
       "895               3    1  27.0      0      0    8.6625         2\n",
       "896               3    0  22.0      1      1   12.2875         2\n",
       "...             ...  ...   ...    ...    ...       ...       ...\n",
       "1305              3    1  30.0      0      0    8.0500         2\n",
       "1306              1    0  39.0      0      0  108.9000         0\n",
       "1307              3    1  38.5      0      0    7.2500         2\n",
       "1308              3    1  30.0      0      0    8.0500         2\n",
       "1309              3    1  30.0      1      1   22.3583         0\n",
       "\n",
       "[418 rows x 7 columns]"
      ]
     },
     "execution_count": 85,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_titanic_test[\"Sex\"] = le_s.transform(df_titanic_test.Sex)\n",
    "\n",
    "df_titanic_test[\"Embarked\"] = le_e.transform(df_titanic_test.Embarked)\n",
    "\n",
    "df_titanic_test"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Mais uma validação de ML"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[ 3.      1.     34.5     0.      0.      7.8292  1.    ]\n",
      " [ 3.      0.     47.      1.      0.      7.      2.    ]\n",
      " [ 2.      1.     62.      0.      0.      9.6875  1.    ]\n",
      " [ 3.      1.     27.      0.      0.      8.6625  2.    ]\n",
      " [ 3.      0.     22.      1.      1.     12.2875  2.    ]\n",
      " [ 3.      1.     14.      0.      0.      9.225   2.    ]]\n",
      "\n",
      "Norm: [[ 0.82737724  0.73769513  0.48950741 -0.4745452  -0.47367361 -0.49078316\n",
      "  -0.67817453]\n",
      " [ 0.82737724 -1.35557354  1.41256602  0.43279337 -0.47367361 -0.50747884\n",
      "   0.58595414]\n",
      " [-0.36936484  0.73769513  2.52023635 -0.4745452  -0.47367361 -0.45336687\n",
      "  -0.67817453]\n",
      " [ 0.82737724  0.73769513 -0.06432776 -0.4745452  -0.47367361 -0.47400493\n",
      "   0.58595414]\n",
      " [ 0.82737724 -1.35557354 -0.4335512   0.43279337  0.76762988 -0.40101668\n",
      "   0.58595414]\n",
      " [ 0.82737724  0.73769513 -1.02430871 -0.4745452  -0.47367361 -0.46267916\n",
      "   0.58595414]]\n"
     ]
    }
   ],
   "source": [
    "# nosso targuet \"y\"\n",
    "###Y_tita = df_tita_test['Survived'].values\n",
    "# nossos valores\n",
    "###x_tita = df_tita_test.drop(['Survived'], axis=1).values\n",
    "x_tita = df_titanic_test.values\n",
    "\n",
    "# Norm\n",
    "x_tita_norm = sc.transform(x_tita)\n",
    "\n",
    "print(x_tita[:6])\n",
    "print(\"\\nNorm:\",x_tita_norm[:6])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_titanic_test[\"Survived\"] = 0\n",
    "df_titanic_RESPOSTA = df_titanic_test[[\"Survived\"]]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Subiting modeles response"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model:  SVC() \n",
      "Response: [0 0 0 0 0 0 1 0 1 0 0 0 1 0 1 1 0 0 0 1 0 1 1 0 1 0 1 0 0 0 0 0 0 0 0 0 1\n",
      " 1 0 0 0 0 0 1 1 0 0 0 1 0 0 0 1 1 0 0 0 0 0 1 0 0 0 1 0 1 1 0 0 0 1 0 1 0\n",
      " 1 0 0 1 0 1 1 0 0 0 0 0 1 1 1 1 1 0 1 0 0 0 1 0 1 0 1 0 0 0 1 0 0 0 0 0 0\n",
      " 1 1 1 1 0 0 1 0 1 1 0 1 0 0 1 0 1 0 0 0 0 0 0 0 0 0 0 1 0 0 1 0 0 0 0 0 0\n",
      " 0 0 1 0 0 0 0 0 1 1 0 0 1 1 1 0 0 0 0 0 1 1 0 0 0 0 0 1 1 0 1 1 0 0 1 0 1\n",
      " 0 1 0 0 0 0 0 0 0 1 0 1 1 0 1 1 1 0 1 0 0 1 0 1 0 0 0 0 1 0 0 1 0 1 0 1 0\n",
      " 1 0 1 1 0 1 0 0 0 1 0 0 0 0 0 0 1 1 1 1 0 0 0 0 1 0 1 1 1 0 0 0 0 0 0 0 1\n",
      " 0 0 0 1 1 0 0 0 0 1 0 0 0 1 1 0 1 0 0 0 0 1 1 1 1 1 0 0 0 0 0 0 1 0 0 0 0\n",
      " 1 0 0 0 0 0 0 0 1 1 1 1 0 0 0 0 0 1 1 1 0 0 0 0 0 0 0 0 1 0 1 0 0 0 1 0 0\n",
      " 1 0 0 0 0 0 0 0 0 0 1 0 1 0 1 0 1 1 0 0 0 1 0 1 0 0 0 0 1 1 0 1 0 0 1 1 0\n",
      " 0 1 0 0 1 1 0 0 0 0 0 0 1 1 0 1 0 0 0 0 0 1 1 0 0 1 0 1 0 0 1 0 1 0 0 0 0\n",
      " 0 1 1 1 1 1 0 1 0 0 0]\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\drife\\Downloads\\Programacao\\Anaconda\\lib\\site-packages\\ipykernel_launcher.py:5: 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: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  \"\"\"\n"
     ]
    }
   ],
   "source": [
    "y_tita_pred_model_svcPadrao = model_svcPadrao.predict(x_tita_norm)\n",
    "\n",
    "print( \"Model: \",model_svcPadrao,\"\\nResponse:\", y_tita_pred_model_svcPadrao)\n",
    "\n",
    "df_titanic_RESPOSTA[\"Survived\"] = y_tita_pred_model_svcPadrao\n",
    "df_titanic_RESPOSTA.to_csv('y_tita_pred_model_svcPadrao.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 109,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model:  VotingClassifier(estimators=[('SVC', SVC(C=1, kernel='linear')),\n",
      "                             ('gnb', GaussianNB()),\n",
      "                             ('L_Regress', LogisticRegression())]) \n",
      "Response: [0 1 0 0 1 0 1 0 1 0 0 0 1 0 1 1 0 0 1 1 0 0 1 1 1 0 1 0 0 0 0 0 1 1 0 0 1\n",
      " 1 0 0 0 0 0 1 1 0 0 0 1 1 0 0 1 1 0 0 0 0 0 1 0 0 0 1 1 1 1 0 1 1 1 0 1 1\n",
      " 1 1 0 1 0 1 0 0 0 0 0 0 1 1 1 0 1 0 1 0 1 0 1 0 1 0 1 0 0 0 1 0 0 0 0 0 0\n",
      " 1 1 1 1 0 0 1 1 1 1 0 1 0 0 1 0 0 0 0 0 0 1 0 0 0 0 0 1 0 0 1 0 0 0 0 0 0\n",
      " 0 0 1 0 0 1 0 0 1 1 0 1 1 0 1 0 0 1 0 0 1 1 0 0 0 0 0 1 1 0 1 1 0 0 1 0 1\n",
      " 0 1 0 0 0 0 0 0 0 0 0 1 1 0 1 1 0 0 1 0 1 1 0 1 0 0 0 0 1 0 0 1 0 1 0 1 0\n",
      " 1 0 1 1 0 1 0 0 0 1 0 0 0 0 0 0 1 1 1 1 0 0 0 0 1 0 1 1 1 0 1 0 0 0 0 0 1\n",
      " 0 0 0 1 1 0 0 0 0 1 0 0 0 1 1 0 1 0 0 0 0 1 0 1 1 1 0 0 0 0 0 0 1 0 0 0 0\n",
      " 1 0 0 0 0 0 0 0 1 1 0 0 0 1 0 0 0 1 1 1 0 0 0 0 0 0 0 0 1 0 1 0 0 0 1 0 0\n",
      " 1 0 0 0 0 0 0 0 0 0 1 0 1 0 1 0 1 1 0 0 0 1 0 1 0 0 1 0 1 1 0 1 0 0 1 1 0\n",
      " 0 1 0 0 1 1 1 0 0 0 0 0 1 1 0 1 0 0 0 0 1 1 0 0 0 1 0 1 0 0 1 0 1 0 0 0 0\n",
      " 0 1 1 1 1 1 0 1 0 0 0]\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\drife\\Downloads\\Programacao\\Anaconda\\lib\\site-packages\\ipykernel_launcher.py:6: 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: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  \n"
     ]
    }
   ],
   "source": [
    "y_tita_pred_voting_classifier = voting_classifier.predict(x_tita)\n",
    "\n",
    "\n",
    "print( \"Model: \",voting_classifier,\"\\nResponse:\", y_tita_pred_voting_classifier)\n",
    "\n",
    "df_titanic_RESPOSTA[\"Survived\"] = y_tita_pred_voting_classifier\n",
    "df_titanic_RESPOSTA.to_csv('y_tita_pred_voting_classifier.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}