├── README
├── titanic_video1.ipynb
├── titanic_video2.ipynb
├── titanic_video3_4_validacao.ipynb
├── titanic_video5.ipynb
└── titanic_video6_final.ipynb


/README:
--------------------------------------------------------------------------------
1 | Material para o tutorial da playlist de vídeos sobre Machine Learning usando os dados do Titanic
2 | 
3 | https://www.youtube.com/playlist?list=PLwnip85KhroW8Q1JSNbgl06iNPeC0SDkx


--------------------------------------------------------------------------------
/titanic_video1.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "markdown",
  5 |    "metadata": {},
  6 |    "source": [
  7 |     "Para quem tiver curiosidade de saber como gerar uma sub igual à gender_submission, esse é o código."
  8 |    ]
  9 |   },
 10 |   {
 11 |    "cell_type": "code",
 12 |    "execution_count": 1,
 13 |    "metadata": {},
 14 |    "outputs": [],
 15 |    "source": [
 16 |     "import pandas as pd"
 17 |    ]
 18 |   },
 19 |   {
 20 |    "cell_type": "code",
 21 |    "execution_count": 12,
 22 |    "metadata": {},
 23 |    "outputs": [],
 24 |    "source": [
 25 |     "data = pd.read_csv(\"test.csv\")"
 26 |    ]
 27 |   },
 28 |   {
 29 |    "cell_type": "code",
 30 |    "execution_count": 13,
 31 |    "metadata": {},
 32 |    "outputs": [
 33 |     {
 34 |      "data": {
 35 |       "text/html": [
 36 |        "<div>\n",
 37 |        "<style scoped>\n",
 38 |        "    .dataframe tbody tr th:only-of-type {\n",
 39 |        "        vertical-align: middle;\n",
 40 |        "    }\n",
 41 |        "\n",
 42 |        "    .dataframe tbody tr th {\n",
 43 |        "        vertical-align: top;\n",
 44 |        "    }\n",
 45 |        "\n",
 46 |        "    .dataframe thead th {\n",
 47 |        "        text-align: right;\n",
 48 |        "    }\n",
 49 |        "</style>\n",
 50 |        "<table border=\"1\" class=\"dataframe\">\n",
 51 |        "  <thead>\n",
 52 |        "    <tr style=\"text-align: right;\">\n",
 53 |        "      <th></th>\n",
 54 |        "      <th>PassengerId</th>\n",
 55 |        "      <th>Pclass</th>\n",
 56 |        "      <th>Name</th>\n",
 57 |        "      <th>Sex</th>\n",
 58 |        "      <th>Age</th>\n",
 59 |        "      <th>SibSp</th>\n",
 60 |        "      <th>Parch</th>\n",
 61 |        "      <th>Ticket</th>\n",
 62 |        "      <th>Fare</th>\n",
 63 |        "      <th>Cabin</th>\n",
 64 |        "      <th>Embarked</th>\n",
 65 |        "    </tr>\n",
 66 |        "  </thead>\n",
 67 |        "  <tbody>\n",
 68 |        "    <tr>\n",
 69 |        "      <th>0</th>\n",
 70 |        "      <td>892</td>\n",
 71 |        "      <td>3</td>\n",
 72 |        "      <td>Kelly, Mr. James</td>\n",
 73 |        "      <td>male</td>\n",
 74 |        "      <td>34.5</td>\n",
 75 |        "      <td>0</td>\n",
 76 |        "      <td>0</td>\n",
 77 |        "      <td>330911</td>\n",
 78 |        "      <td>7.8292</td>\n",
 79 |        "      <td>NaN</td>\n",
 80 |        "      <td>Q</td>\n",
 81 |        "    </tr>\n",
 82 |        "    <tr>\n",
 83 |        "      <th>1</th>\n",
 84 |        "      <td>893</td>\n",
 85 |        "      <td>3</td>\n",
 86 |        "      <td>Wilkes, Mrs. James (Ellen Needs)</td>\n",
 87 |        "      <td>female</td>\n",
 88 |        "      <td>47.0</td>\n",
 89 |        "      <td>1</td>\n",
 90 |        "      <td>0</td>\n",
 91 |        "      <td>363272</td>\n",
 92 |        "      <td>7.0000</td>\n",
 93 |        "      <td>NaN</td>\n",
 94 |        "      <td>S</td>\n",
 95 |        "    </tr>\n",
 96 |        "    <tr>\n",
 97 |        "      <th>2</th>\n",
 98 |        "      <td>894</td>\n",
 99 |        "      <td>2</td>\n",
100 |        "      <td>Myles, Mr. Thomas Francis</td>\n",
101 |        "      <td>male</td>\n",
102 |        "      <td>62.0</td>\n",
103 |        "      <td>0</td>\n",
104 |        "      <td>0</td>\n",
105 |        "      <td>240276</td>\n",
106 |        "      <td>9.6875</td>\n",
107 |        "      <td>NaN</td>\n",
108 |        "      <td>Q</td>\n",
109 |        "    </tr>\n",
110 |        "    <tr>\n",
111 |        "      <th>3</th>\n",
112 |        "      <td>895</td>\n",
113 |        "      <td>3</td>\n",
114 |        "      <td>Wirz, Mr. Albert</td>\n",
115 |        "      <td>male</td>\n",
116 |        "      <td>27.0</td>\n",
117 |        "      <td>0</td>\n",
118 |        "      <td>0</td>\n",
119 |        "      <td>315154</td>\n",
120 |        "      <td>8.6625</td>\n",
121 |        "      <td>NaN</td>\n",
122 |        "      <td>S</td>\n",
123 |        "    </tr>\n",
124 |        "    <tr>\n",
125 |        "      <th>4</th>\n",
126 |        "      <td>896</td>\n",
127 |        "      <td>3</td>\n",
128 |        "      <td>Hirvonen, Mrs. Alexander (Helga E Lindqvist)</td>\n",
129 |        "      <td>female</td>\n",
130 |        "      <td>22.0</td>\n",
131 |        "      <td>1</td>\n",
132 |        "      <td>1</td>\n",
133 |        "      <td>3101298</td>\n",
134 |        "      <td>12.2875</td>\n",
135 |        "      <td>NaN</td>\n",
136 |        "      <td>S</td>\n",
137 |        "    </tr>\n",
138 |        "  </tbody>\n",
139 |        "</table>\n",
140 |        "</div>"
141 |       ],
142 |       "text/plain": [
143 |        "   PassengerId  Pclass                                          Name     Sex  \\\n",
144 |        "0          892       3                              Kelly, Mr. James    male   \n",
145 |        "1          893       3              Wilkes, Mrs. James (Ellen Needs)  female   \n",
146 |        "2          894       2                     Myles, Mr. Thomas Francis    male   \n",
147 |        "3          895       3                              Wirz, Mr. Albert    male   \n",
148 |        "4          896       3  Hirvonen, Mrs. Alexander (Helga E Lindqvist)  female   \n",
149 |        "\n",
150 |        "    Age  SibSp  Parch   Ticket     Fare Cabin Embarked  \n",
151 |        "0  34.5      0      0   330911   7.8292   NaN        Q  \n",
152 |        "1  47.0      1      0   363272   7.0000   NaN        S  \n",
153 |        "2  62.0      0      0   240276   9.6875   NaN        Q  \n",
154 |        "3  27.0      0      0   315154   8.6625   NaN        S  \n",
155 |        "4  22.0      1      1  3101298  12.2875   NaN        S  "
156 |       ]
157 |      },
158 |      "execution_count": 13,
159 |      "metadata": {},
160 |      "output_type": "execute_result"
161 |     }
162 |    ],
163 |    "source": [
164 |     "data.head()"
165 |    ]
166 |   },
167 |   {
168 |    "cell_type": "code",
169 |    "execution_count": 14,
170 |    "metadata": {},
171 |    "outputs": [
172 |     {
173 |      "data": {
174 |       "text/plain": [
175 |        "0    0\n",
176 |        "1    1\n",
177 |        "2    0\n",
178 |        "3    0\n",
179 |        "4    1\n",
180 |        "Name: Sex, dtype: int64"
181 |       ]
182 |      },
183 |      "execution_count": 14,
184 |      "metadata": {},
185 |      "output_type": "execute_result"
186 |     }
187 |    ],
188 |    "source": [
189 |     "e_feminino = (data['Sex'] == 'female').astype(int)\n",
190 |     "e_feminino.head()"
191 |    ]
192 |   },
193 |   {
194 |    "cell_type": "code",
195 |    "execution_count": 15,
196 |    "metadata": {},
197 |    "outputs": [
198 |     {
199 |      "data": {
200 |       "text/plain": [
201 |        "PassengerId\n",
202 |        "892    0\n",
203 |        "893    1\n",
204 |        "894    0\n",
205 |        "895    0\n",
206 |        "896    1\n",
207 |        "Name: Sex, dtype: int64"
208 |       ]
209 |      },
210 |      "execution_count": 15,
211 |      "metadata": {},
212 |      "output_type": "execute_result"
213 |     }
214 |    ],
215 |    "source": [
216 |     "e_feminino.index = data['PassengerId']\n",
217 |     "e_feminino.head()"
218 |    ]
219 |   },
220 |   {
221 |    "cell_type": "code",
222 |    "execution_count": 16,
223 |    "metadata": {},
224 |    "outputs": [
225 |     {
226 |      "data": {
227 |       "text/plain": [
228 |        "PassengerId\n",
229 |        "892    0\n",
230 |        "893    1\n",
231 |        "894    0\n",
232 |        "895    0\n",
233 |        "896    1\n",
234 |        "Name: Survived, dtype: int64"
235 |       ]
236 |      },
237 |      "execution_count": 16,
238 |      "metadata": {},
239 |      "output_type": "execute_result"
240 |     }
241 |    ],
242 |    "source": [
243 |     "e_feminino.name = 'Survived'\n",
244 |     "e_feminino.head()"
245 |    ]
246 |   },
247 |   {
248 |    "cell_type": "code",
249 |    "execution_count": 17,
250 |    "metadata": {},
251 |    "outputs": [],
252 |    "source": [
253 |     "e_feminino.to_csv('gender_submission.csv', header=True)"
254 |    ]
255 |   },
256 |   {
257 |    "cell_type": "code",
258 |    "execution_count": 18,
259 |    "metadata": {},
260 |    "outputs": [
261 |     {
262 |      "name": "stdout",
263 |      "output_type": "stream",
264 |      "text": [
265 |       "PassengerId,Survived\n",
266 |       "892,0\n",
267 |       "893,1\n",
268 |       "894,0\n",
269 |       "895,0\n",
270 |       "896,1\n",
271 |       "897,0\n",
272 |       "898,1\n",
273 |       "899,0\n",
274 |       "900,1\n"
275 |      ]
276 |     }
277 |    ],
278 |    "source": [
279 |     "!head -n10 gender_submission.csv"
280 |    ]
281 |   },
282 |   {
283 |    "cell_type": "code",
284 |    "execution_count": null,
285 |    "metadata": {},
286 |    "outputs": [],
287 |    "source": []
288 |   }
289 |  ],
290 |  "metadata": {
291 |   "kernelspec": {
292 |    "display_name": "Python 3",
293 |    "language": "python",
294 |    "name": "python3"
295 |   },
296 |   "language_info": {
297 |    "codemirror_mode": {
298 |     "name": "ipython",
299 |     "version": 3
300 |    },
301 |    "file_extension": ".py",
302 |    "mimetype": "text/x-python",
303 |    "name": "python",
304 |    "nbconvert_exporter": "python",
305 |    "pygments_lexer": "ipython3",
306 |    "version": "3.7.3"
307 |   }
308 |  },
309 |  "nbformat": 4,
310 |  "nbformat_minor": 4
311 | }
312 | 


--------------------------------------------------------------------------------
/titanic_video2.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 72,
  6 |    "metadata": {},
  7 |    "outputs": [],
  8 |    "source": [
  9 |     "import pandas as pd\n",
 10 |     "import numpy as np"
 11 |    ]
 12 |   },
 13 |   {
 14 |    "cell_type": "code",
 15 |    "execution_count": 73,
 16 |    "metadata": {},
 17 |    "outputs": [],
 18 |    "source": [
 19 |     "train = pd.read_csv(\"train.csv\")\n",
 20 |     "test = pd.read_csv(\"test.csv\")"
 21 |    ]
 22 |   },
 23 |   {
 24 |    "cell_type": "code",
 25 |    "execution_count": 74,
 26 |    "metadata": {},
 27 |    "outputs": [
 28 |     {
 29 |      "data": {
 30 |       "text/html": [
 31 |        "<div>\n",
 32 |        "<style scoped>\n",
 33 |        "    .dataframe tbody tr th:only-of-type {\n",
 34 |        "        vertical-align: middle;\n",
 35 |        "    }\n",
 36 |        "\n",
 37 |        "    .dataframe tbody tr th {\n",
 38 |        "        vertical-align: top;\n",
 39 |        "    }\n",
 40 |        "\n",
 41 |        "    .dataframe thead th {\n",
 42 |        "        text-align: right;\n",
 43 |        "    }\n",
 44 |        "</style>\n",
 45 |        "<table border=\"1\" class=\"dataframe\">\n",
 46 |        "  <thead>\n",
 47 |        "    <tr style=\"text-align: right;\">\n",
 48 |        "      <th></th>\n",
 49 |        "      <th>PassengerId</th>\n",
 50 |        "      <th>Survived</th>\n",
 51 |        "      <th>Pclass</th>\n",
 52 |        "      <th>Name</th>\n",
 53 |        "      <th>Sex</th>\n",
 54 |        "      <th>Age</th>\n",
 55 |        "      <th>SibSp</th>\n",
 56 |        "      <th>Parch</th>\n",
 57 |        "      <th>Ticket</th>\n",
 58 |        "      <th>Fare</th>\n",
 59 |        "      <th>Cabin</th>\n",
 60 |        "      <th>Embarked</th>\n",
 61 |        "    </tr>\n",
 62 |        "  </thead>\n",
 63 |        "  <tbody>\n",
 64 |        "    <tr>\n",
 65 |        "      <th>0</th>\n",
 66 |        "      <td>1</td>\n",
 67 |        "      <td>0</td>\n",
 68 |        "      <td>3</td>\n",
 69 |        "      <td>Braund, Mr. Owen Harris</td>\n",
 70 |        "      <td>male</td>\n",
 71 |        "      <td>22.0</td>\n",
 72 |        "      <td>1</td>\n",
 73 |        "      <td>0</td>\n",
 74 |        "      <td>A/5 21171</td>\n",
 75 |        "      <td>7.2500</td>\n",
 76 |        "      <td>NaN</td>\n",
 77 |        "      <td>S</td>\n",
 78 |        "    </tr>\n",
 79 |        "    <tr>\n",
 80 |        "      <th>1</th>\n",
 81 |        "      <td>2</td>\n",
 82 |        "      <td>1</td>\n",
 83 |        "      <td>1</td>\n",
 84 |        "      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
 85 |        "      <td>female</td>\n",
 86 |        "      <td>38.0</td>\n",
 87 |        "      <td>1</td>\n",
 88 |        "      <td>0</td>\n",
 89 |        "      <td>PC 17599</td>\n",
 90 |        "      <td>71.2833</td>\n",
 91 |        "      <td>C85</td>\n",
 92 |        "      <td>C</td>\n",
 93 |        "    </tr>\n",
 94 |        "    <tr>\n",
 95 |        "      <th>2</th>\n",
 96 |        "      <td>3</td>\n",
 97 |        "      <td>1</td>\n",
 98 |        "      <td>3</td>\n",
 99 |        "      <td>Heikkinen, Miss. Laina</td>\n",
100 |        "      <td>female</td>\n",
101 |        "      <td>26.0</td>\n",
102 |        "      <td>0</td>\n",
103 |        "      <td>0</td>\n",
104 |        "      <td>STON/O2. 3101282</td>\n",
105 |        "      <td>7.9250</td>\n",
106 |        "      <td>NaN</td>\n",
107 |        "      <td>S</td>\n",
108 |        "    </tr>\n",
109 |        "    <tr>\n",
110 |        "      <th>3</th>\n",
111 |        "      <td>4</td>\n",
112 |        "      <td>1</td>\n",
113 |        "      <td>1</td>\n",
114 |        "      <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n",
115 |        "      <td>female</td>\n",
116 |        "      <td>35.0</td>\n",
117 |        "      <td>1</td>\n",
118 |        "      <td>0</td>\n",
119 |        "      <td>113803</td>\n",
120 |        "      <td>53.1000</td>\n",
121 |        "      <td>C123</td>\n",
122 |        "      <td>S</td>\n",
123 |        "    </tr>\n",
124 |        "    <tr>\n",
125 |        "      <th>4</th>\n",
126 |        "      <td>5</td>\n",
127 |        "      <td>0</td>\n",
128 |        "      <td>3</td>\n",
129 |        "      <td>Allen, Mr. William Henry</td>\n",
130 |        "      <td>male</td>\n",
131 |        "      <td>35.0</td>\n",
132 |        "      <td>0</td>\n",
133 |        "      <td>0</td>\n",
134 |        "      <td>373450</td>\n",
135 |        "      <td>8.0500</td>\n",
136 |        "      <td>NaN</td>\n",
137 |        "      <td>S</td>\n",
138 |        "    </tr>\n",
139 |        "  </tbody>\n",
140 |        "</table>\n",
141 |        "</div>"
142 |       ],
143 |       "text/plain": [
144 |        "   PassengerId  Survived  Pclass  \\\n",
145 |        "0            1         0       3   \n",
146 |        "1            2         1       1   \n",
147 |        "2            3         1       3   \n",
148 |        "3            4         1       1   \n",
149 |        "4            5         0       3   \n",
150 |        "\n",
151 |        "                                                Name     Sex   Age  SibSp  \\\n",
152 |        "0                            Braund, Mr. Owen Harris    male  22.0      1   \n",
153 |        "1  Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0      1   \n",
154 |        "2                             Heikkinen, Miss. Laina  female  26.0      0   \n",
155 |        "3       Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0      1   \n",
156 |        "4                           Allen, Mr. William Henry    male  35.0      0   \n",
157 |        "\n",
158 |        "   Parch            Ticket     Fare Cabin Embarked  \n",
159 |        "0      0         A/5 21171   7.2500   NaN        S  \n",
160 |        "1      0          PC 17599  71.2833   C85        C  \n",
161 |        "2      0  STON/O2. 3101282   7.9250   NaN        S  \n",
162 |        "3      0            113803  53.1000  C123        S  \n",
163 |        "4      0            373450   8.0500   NaN        S  "
164 |       ]
165 |      },
166 |      "execution_count": 74,
167 |      "metadata": {},
168 |      "output_type": "execute_result"
169 |     }
170 |    ],
171 |    "source": [
172 |     "train.head()"
173 |    ]
174 |   },
175 |   {
176 |    "cell_type": "code",
177 |    "execution_count": 75,
178 |    "metadata": {},
179 |    "outputs": [],
180 |    "source": [
181 |     "from sklearn.ensemble import RandomForestClassifier"
182 |    ]
183 |   },
184 |   {
185 |    "cell_type": "code",
186 |    "execution_count": 76,
187 |    "metadata": {},
188 |    "outputs": [],
189 |    "source": [
190 |     "modelo = RandomForestClassifier(n_estimators=100, n_jobs=-1, random_state=0)\n"
191 |    ]
192 |   },
193 |   {
194 |    "cell_type": "code",
195 |    "execution_count": 77,
196 |    "metadata": {},
197 |    "outputs": [
198 |     {
199 |      "data": {
200 |       "text/plain": [
201 |        "male      577\n",
202 |        "female    314\n",
203 |        "Name: Sex, dtype: int64"
204 |       ]
205 |      },
206 |      "execution_count": 77,
207 |      "metadata": {},
208 |      "output_type": "execute_result"
209 |     }
210 |    ],
211 |    "source": [
212 |     "train['Sex'].value_counts()"
213 |    ]
214 |   },
215 |   {
216 |    "cell_type": "code",
217 |    "execution_count": 78,
218 |    "metadata": {},
219 |    "outputs": [],
220 |    "source": [
221 |     "def transformar_sexo(valor):\n",
222 |     "    if valor == 'female':\n",
223 |     "        return 1\n",
224 |     "    else:\n",
225 |     "        return 0\n",
226 |     "    \n",
227 |     "train['Sex_binario'] = train['Sex'].map(transformar_sexo)\n",
228 |     "        "
229 |    ]
230 |   },
231 |   {
232 |    "cell_type": "code",
233 |    "execution_count": 79,
234 |    "metadata": {},
235 |    "outputs": [
236 |     {
237 |      "data": {
238 |       "text/html": [
239 |        "<div>\n",
240 |        "<style scoped>\n",
241 |        "    .dataframe tbody tr th:only-of-type {\n",
242 |        "        vertical-align: middle;\n",
243 |        "    }\n",
244 |        "\n",
245 |        "    .dataframe tbody tr th {\n",
246 |        "        vertical-align: top;\n",
247 |        "    }\n",
248 |        "\n",
249 |        "    .dataframe thead th {\n",
250 |        "        text-align: right;\n",
251 |        "    }\n",
252 |        "</style>\n",
253 |        "<table border=\"1\" class=\"dataframe\">\n",
254 |        "  <thead>\n",
255 |        "    <tr style=\"text-align: right;\">\n",
256 |        "      <th></th>\n",
257 |        "      <th>PassengerId</th>\n",
258 |        "      <th>Survived</th>\n",
259 |        "      <th>Pclass</th>\n",
260 |        "      <th>Name</th>\n",
261 |        "      <th>Sex</th>\n",
262 |        "      <th>Age</th>\n",
263 |        "      <th>SibSp</th>\n",
264 |        "      <th>Parch</th>\n",
265 |        "      <th>Ticket</th>\n",
266 |        "      <th>Fare</th>\n",
267 |        "      <th>Cabin</th>\n",
268 |        "      <th>Embarked</th>\n",
269 |        "      <th>Sex_binario</th>\n",
270 |        "    </tr>\n",
271 |        "  </thead>\n",
272 |        "  <tbody>\n",
273 |        "    <tr>\n",
274 |        "      <th>0</th>\n",
275 |        "      <td>1</td>\n",
276 |        "      <td>0</td>\n",
277 |        "      <td>3</td>\n",
278 |        "      <td>Braund, Mr. Owen Harris</td>\n",
279 |        "      <td>male</td>\n",
280 |        "      <td>22.0</td>\n",
281 |        "      <td>1</td>\n",
282 |        "      <td>0</td>\n",
283 |        "      <td>A/5 21171</td>\n",
284 |        "      <td>7.2500</td>\n",
285 |        "      <td>NaN</td>\n",
286 |        "      <td>S</td>\n",
287 |        "      <td>0</td>\n",
288 |        "    </tr>\n",
289 |        "    <tr>\n",
290 |        "      <th>1</th>\n",
291 |        "      <td>2</td>\n",
292 |        "      <td>1</td>\n",
293 |        "      <td>1</td>\n",
294 |        "      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
295 |        "      <td>female</td>\n",
296 |        "      <td>38.0</td>\n",
297 |        "      <td>1</td>\n",
298 |        "      <td>0</td>\n",
299 |        "      <td>PC 17599</td>\n",
300 |        "      <td>71.2833</td>\n",
301 |        "      <td>C85</td>\n",
302 |        "      <td>C</td>\n",
303 |        "      <td>1</td>\n",
304 |        "    </tr>\n",
305 |        "    <tr>\n",
306 |        "      <th>2</th>\n",
307 |        "      <td>3</td>\n",
308 |        "      <td>1</td>\n",
309 |        "      <td>3</td>\n",
310 |        "      <td>Heikkinen, Miss. Laina</td>\n",
311 |        "      <td>female</td>\n",
312 |        "      <td>26.0</td>\n",
313 |        "      <td>0</td>\n",
314 |        "      <td>0</td>\n",
315 |        "      <td>STON/O2. 3101282</td>\n",
316 |        "      <td>7.9250</td>\n",
317 |        "      <td>NaN</td>\n",
318 |        "      <td>S</td>\n",
319 |        "      <td>1</td>\n",
320 |        "    </tr>\n",
321 |        "    <tr>\n",
322 |        "      <th>3</th>\n",
323 |        "      <td>4</td>\n",
324 |        "      <td>1</td>\n",
325 |        "      <td>1</td>\n",
326 |        "      <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n",
327 |        "      <td>female</td>\n",
328 |        "      <td>35.0</td>\n",
329 |        "      <td>1</td>\n",
330 |        "      <td>0</td>\n",
331 |        "      <td>113803</td>\n",
332 |        "      <td>53.1000</td>\n",
333 |        "      <td>C123</td>\n",
334 |        "      <td>S</td>\n",
335 |        "      <td>1</td>\n",
336 |        "    </tr>\n",
337 |        "    <tr>\n",
338 |        "      <th>4</th>\n",
339 |        "      <td>5</td>\n",
340 |        "      <td>0</td>\n",
341 |        "      <td>3</td>\n",
342 |        "      <td>Allen, Mr. William Henry</td>\n",
343 |        "      <td>male</td>\n",
344 |        "      <td>35.0</td>\n",
345 |        "      <td>0</td>\n",
346 |        "      <td>0</td>\n",
347 |        "      <td>373450</td>\n",
348 |        "      <td>8.0500</td>\n",
349 |        "      <td>NaN</td>\n",
350 |        "      <td>S</td>\n",
351 |        "      <td>0</td>\n",
352 |        "    </tr>\n",
353 |        "  </tbody>\n",
354 |        "</table>\n",
355 |        "</div>"
356 |       ],
357 |       "text/plain": [
358 |        "   PassengerId  Survived  Pclass  \\\n",
359 |        "0            1         0       3   \n",
360 |        "1            2         1       1   \n",
361 |        "2            3         1       3   \n",
362 |        "3            4         1       1   \n",
363 |        "4            5         0       3   \n",
364 |        "\n",
365 |        "                                                Name     Sex   Age  SibSp  \\\n",
366 |        "0                            Braund, Mr. Owen Harris    male  22.0      1   \n",
367 |        "1  Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0      1   \n",
368 |        "2                             Heikkinen, Miss. Laina  female  26.0      0   \n",
369 |        "3       Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0      1   \n",
370 |        "4                           Allen, Mr. William Henry    male  35.0      0   \n",
371 |        "\n",
372 |        "   Parch            Ticket     Fare Cabin Embarked  Sex_binario  \n",
373 |        "0      0         A/5 21171   7.2500   NaN        S            0  \n",
374 |        "1      0          PC 17599  71.2833   C85        C            1  \n",
375 |        "2      0  STON/O2. 3101282   7.9250   NaN        S            1  \n",
376 |        "3      0            113803  53.1000  C123        S            1  \n",
377 |        "4      0            373450   8.0500   NaN        S            0  "
378 |       ]
379 |      },
380 |      "execution_count": 79,
381 |      "metadata": {},
382 |      "output_type": "execute_result"
383 |     }
384 |    ],
385 |    "source": [
386 |     "train.head()"
387 |    ]
388 |   },
389 |   {
390 |    "cell_type": "code",
391 |    "execution_count": 80,
392 |    "metadata": {},
393 |    "outputs": [],
394 |    "source": [
395 |     "variaveis = ['Sex_binario', 'Age']"
396 |    ]
397 |   },
398 |   {
399 |    "cell_type": "code",
400 |    "execution_count": 81,
401 |    "metadata": {},
402 |    "outputs": [],
403 |    "source": [
404 |     "X = train[variaveis]\n",
405 |     "y = train['Survived']"
406 |    ]
407 |   },
408 |   {
409 |    "cell_type": "code",
410 |    "execution_count": 82,
411 |    "metadata": {},
412 |    "outputs": [
413 |     {
414 |      "data": {
415 |       "text/html": [
416 |        "<div>\n",
417 |        "<style scoped>\n",
418 |        "    .dataframe tbody tr th:only-of-type {\n",
419 |        "        vertical-align: middle;\n",
420 |        "    }\n",
421 |        "\n",
422 |        "    .dataframe tbody tr th {\n",
423 |        "        vertical-align: top;\n",
424 |        "    }\n",
425 |        "\n",
426 |        "    .dataframe thead th {\n",
427 |        "        text-align: right;\n",
428 |        "    }\n",
429 |        "</style>\n",
430 |        "<table border=\"1\" class=\"dataframe\">\n",
431 |        "  <thead>\n",
432 |        "    <tr style=\"text-align: right;\">\n",
433 |        "      <th></th>\n",
434 |        "      <th>Sex_binario</th>\n",
435 |        "      <th>Age</th>\n",
436 |        "    </tr>\n",
437 |        "  </thead>\n",
438 |        "  <tbody>\n",
439 |        "    <tr>\n",
440 |        "      <th>0</th>\n",
441 |        "      <td>0</td>\n",
442 |        "      <td>22.0</td>\n",
443 |        "    </tr>\n",
444 |        "    <tr>\n",
445 |        "      <th>1</th>\n",
446 |        "      <td>1</td>\n",
447 |        "      <td>38.0</td>\n",
448 |        "    </tr>\n",
449 |        "    <tr>\n",
450 |        "      <th>2</th>\n",
451 |        "      <td>1</td>\n",
452 |        "      <td>26.0</td>\n",
453 |        "    </tr>\n",
454 |        "    <tr>\n",
455 |        "      <th>3</th>\n",
456 |        "      <td>1</td>\n",
457 |        "      <td>35.0</td>\n",
458 |        "    </tr>\n",
459 |        "    <tr>\n",
460 |        "      <th>4</th>\n",
461 |        "      <td>0</td>\n",
462 |        "      <td>35.0</td>\n",
463 |        "    </tr>\n",
464 |        "  </tbody>\n",
465 |        "</table>\n",
466 |        "</div>"
467 |       ],
468 |       "text/plain": [
469 |        "   Sex_binario   Age\n",
470 |        "0            0  22.0\n",
471 |        "1            1  38.0\n",
472 |        "2            1  26.0\n",
473 |        "3            1  35.0\n",
474 |        "4            0  35.0"
475 |       ]
476 |      },
477 |      "execution_count": 82,
478 |      "metadata": {},
479 |      "output_type": "execute_result"
480 |     }
481 |    ],
482 |    "source": [
483 |     "X.head()"
484 |    ]
485 |   },
486 |   {
487 |    "cell_type": "code",
488 |    "execution_count": 83,
489 |    "metadata": {},
490 |    "outputs": [
491 |     {
492 |      "data": {
493 |       "text/plain": [
494 |        "0    0\n",
495 |        "1    1\n",
496 |        "2    1\n",
497 |        "3    1\n",
498 |        "4    0\n",
499 |        "Name: Survived, dtype: int64"
500 |       ]
501 |      },
502 |      "execution_count": 83,
503 |      "metadata": {},
504 |      "output_type": "execute_result"
505 |     }
506 |    ],
507 |    "source": [
508 |     "y.head()"
509 |    ]
510 |   },
511 |   {
512 |    "cell_type": "code",
513 |    "execution_count": 84,
514 |    "metadata": {},
515 |    "outputs": [
516 |     {
517 |      "ename": "ValueError",
518 |      "evalue": "Input contains NaN, infinity or a value too large for dtype('float32').",
519 |      "output_type": "error",
520 |      "traceback": [
521 |       "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
522 |       "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
523 |       "\u001b[0;32m<ipython-input-84-f51e829b4c32>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mmodelo\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
524 |       "\u001b[0;32m~/anaconda3/lib/python3.7/site-packages/sklearn/ensemble/forest.py\u001b[0m in \u001b[0;36mfit\u001b[0;34m(self, X, y, sample_weight)\u001b[0m\n\u001b[1;32m    248\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    249\u001b[0m         \u001b[0;31m# Validate or convert input data\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 250\u001b[0;31m         \u001b[0mX\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcheck_array\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maccept_sparse\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"csc\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mDTYPE\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    251\u001b[0m         \u001b[0my\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcheck_array\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0my\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maccept_sparse\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'csc'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mensure_2d\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    252\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0msample_weight\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
525 |       "\u001b[0;32m~/anaconda3/lib/python3.7/site-packages/sklearn/utils/validation.py\u001b[0m in \u001b[0;36mcheck_array\u001b[0;34m(array, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, warn_on_dtype, estimator)\u001b[0m\n\u001b[1;32m    571\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mforce_all_finite\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    572\u001b[0m             _assert_all_finite(array,\n\u001b[0;32m--> 573\u001b[0;31m                                allow_nan=force_all_finite == 'allow-nan')\n\u001b[0m\u001b[1;32m    574\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    575\u001b[0m     \u001b[0mshape_repr\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_shape_repr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0marray\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
526 |       "\u001b[0;32m~/anaconda3/lib/python3.7/site-packages/sklearn/utils/validation.py\u001b[0m in \u001b[0;36m_assert_all_finite\u001b[0;34m(X, allow_nan)\u001b[0m\n\u001b[1;32m     54\u001b[0m                 not allow_nan and not np.isfinite(X).all()):\n\u001b[1;32m     55\u001b[0m             \u001b[0mtype_err\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m'infinity'\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mallow_nan\u001b[0m \u001b[0;32melse\u001b[0m \u001b[0;34m'NaN, infinity'\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 56\u001b[0;31m             \u001b[0;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmsg_err\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mformat\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtype_err\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mX\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdtype\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     57\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     58\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
527 |       "\u001b[0;31mValueError\u001b[0m: Input contains NaN, infinity or a value too large for dtype('float32')."
528 |      ]
529 |     }
530 |    ],
531 |    "source": [
532 |     "modelo.fit(X, y)"
533 |    ]
534 |   },
535 |   {
536 |    "cell_type": "code",
537 |    "execution_count": 85,
538 |    "metadata": {},
539 |    "outputs": [],
540 |    "source": [
541 |     "X = X.fillna(-1)"
542 |    ]
543 |   },
544 |   {
545 |    "cell_type": "code",
546 |    "execution_count": 86,
547 |    "metadata": {},
548 |    "outputs": [
549 |     {
550 |      "data": {
551 |       "text/plain": [
552 |        "RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',\n",
553 |        "            max_depth=None, max_features='auto', max_leaf_nodes=None,\n",
554 |        "            min_impurity_decrease=0.0, min_impurity_split=None,\n",
555 |        "            min_samples_leaf=1, min_samples_split=2,\n",
556 |        "            min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=-1,\n",
557 |        "            oob_score=False, random_state=0, verbose=0, warm_start=False)"
558 |       ]
559 |      },
560 |      "execution_count": 86,
561 |      "metadata": {},
562 |      "output_type": "execute_result"
563 |     }
564 |    ],
565 |    "source": [
566 |     "modelo.fit(X, y)"
567 |    ]
568 |   },
569 |   {
570 |    "cell_type": "code",
571 |    "execution_count": 87,
572 |    "metadata": {},
573 |    "outputs": [
574 |     {
575 |      "ename": "KeyError",
576 |      "evalue": "\"['Sex_binario'] not in index\"",
577 |      "output_type": "error",
578 |      "traceback": [
579 |       "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
580 |       "\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
581 |       "\u001b[0;32m<ipython-input-87-6c6ff93e2959>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mX_prev\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtest\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mvariaveis\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
582 |       "\u001b[0;32m~/anaconda3/lib/python3.7/site-packages/pandas/core/frame.py\u001b[0m in \u001b[0;36m__getitem__\u001b[0;34m(self, key)\u001b[0m\n\u001b[1;32m   2932\u001b[0m                 \u001b[0mkey\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlist\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2933\u001b[0m             indexer = self.loc._convert_to_indexer(key, axis=1,\n\u001b[0;32m-> 2934\u001b[0;31m                                                    raise_missing=True)\n\u001b[0m\u001b[1;32m   2935\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2936\u001b[0m         \u001b[0;31m# take() does not accept boolean indexers\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
583 |       "\u001b[0;32m~/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py\u001b[0m in \u001b[0;36m_convert_to_indexer\u001b[0;34m(self, obj, axis, is_setter, raise_missing)\u001b[0m\n\u001b[1;32m   1352\u001b[0m                 kwargs = {'raise_missing': True if is_setter else\n\u001b[1;32m   1353\u001b[0m                           raise_missing}\n\u001b[0;32m-> 1354\u001b[0;31m                 \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_get_listlike_indexer\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mobj\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1355\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1356\u001b[0m             \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
584 |       "\u001b[0;32m~/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py\u001b[0m in \u001b[0;36m_get_listlike_indexer\u001b[0;34m(self, key, axis, raise_missing)\u001b[0m\n\u001b[1;32m   1159\u001b[0m         self._validate_read_indexer(keyarr, indexer,\n\u001b[1;32m   1160\u001b[0m                                     \u001b[0mo\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_get_axis_number\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0maxis\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1161\u001b[0;31m                                     raise_missing=raise_missing)\n\u001b[0m\u001b[1;32m   1162\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0mkeyarr\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mindexer\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1163\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
585 |       "\u001b[0;32m~/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py\u001b[0m in \u001b[0;36m_validate_read_indexer\u001b[0;34m(self, key, indexer, axis, raise_missing)\u001b[0m\n\u001b[1;32m   1250\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mname\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;34m'loc'\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mraise_missing\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1251\u001b[0m                 \u001b[0mnot_found\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlist\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mset\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m-\u001b[0m \u001b[0mset\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0max\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1252\u001b[0;31m                 \u001b[0;32mraise\u001b[0m \u001b[0mKeyError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"{} not in index\"\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mformat\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnot_found\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1253\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1254\u001b[0m             \u001b[0;31m# we skip the warning on Categorical/Interval\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
586 |       "\u001b[0;31mKeyError\u001b[0m: \"['Sex_binario'] not in index\""
587 |      ]
588 |     }
589 |    ],
590 |    "source": [
591 |     "X_prev = test[variaveis]"
592 |    ]
593 |   },
594 |   {
595 |    "cell_type": "code",
596 |    "execution_count": 88,
597 |    "metadata": {},
598 |    "outputs": [],
599 |    "source": [
600 |     "test['Sex_binario'] = test['Sex'].map(transformar_sexo)"
601 |    ]
602 |   },
603 |   {
604 |    "cell_type": "code",
605 |    "execution_count": 89,
606 |    "metadata": {},
607 |    "outputs": [
608 |     {
609 |      "data": {
610 |       "text/html": [
611 |        "<div>\n",
612 |        "<style scoped>\n",
613 |        "    .dataframe tbody tr th:only-of-type {\n",
614 |        "        vertical-align: middle;\n",
615 |        "    }\n",
616 |        "\n",
617 |        "    .dataframe tbody tr th {\n",
618 |        "        vertical-align: top;\n",
619 |        "    }\n",
620 |        "\n",
621 |        "    .dataframe thead th {\n",
622 |        "        text-align: right;\n",
623 |        "    }\n",
624 |        "</style>\n",
625 |        "<table border=\"1\" class=\"dataframe\">\n",
626 |        "  <thead>\n",
627 |        "    <tr style=\"text-align: right;\">\n",
628 |        "      <th></th>\n",
629 |        "      <th>Sex_binario</th>\n",
630 |        "      <th>Age</th>\n",
631 |        "    </tr>\n",
632 |        "  </thead>\n",
633 |        "  <tbody>\n",
634 |        "    <tr>\n",
635 |        "      <th>0</th>\n",
636 |        "      <td>0</td>\n",
637 |        "      <td>34.5</td>\n",
638 |        "    </tr>\n",
639 |        "    <tr>\n",
640 |        "      <th>1</th>\n",
641 |        "      <td>1</td>\n",
642 |        "      <td>47.0</td>\n",
643 |        "    </tr>\n",
644 |        "    <tr>\n",
645 |        "      <th>2</th>\n",
646 |        "      <td>0</td>\n",
647 |        "      <td>62.0</td>\n",
648 |        "    </tr>\n",
649 |        "    <tr>\n",
650 |        "      <th>3</th>\n",
651 |        "      <td>0</td>\n",
652 |        "      <td>27.0</td>\n",
653 |        "    </tr>\n",
654 |        "    <tr>\n",
655 |        "      <th>4</th>\n",
656 |        "      <td>1</td>\n",
657 |        "      <td>22.0</td>\n",
658 |        "    </tr>\n",
659 |        "  </tbody>\n",
660 |        "</table>\n",
661 |        "</div>"
662 |       ],
663 |       "text/plain": [
664 |        "   Sex_binario   Age\n",
665 |        "0            0  34.5\n",
666 |        "1            1  47.0\n",
667 |        "2            0  62.0\n",
668 |        "3            0  27.0\n",
669 |        "4            1  22.0"
670 |       ]
671 |      },
672 |      "execution_count": 89,
673 |      "metadata": {},
674 |      "output_type": "execute_result"
675 |     }
676 |    ],
677 |    "source": [
678 |     "X_prev = test[variaveis]\n",
679 |     "X_prev = X_prev.fillna(-1)\n",
680 |     "X_prev.head()"
681 |    ]
682 |   },
683 |   {
684 |    "cell_type": "code",
685 |    "execution_count": 90,
686 |    "metadata": {},
687 |    "outputs": [
688 |     {
689 |      "data": {
690 |       "text/plain": [
691 |        "array([0, 1, 0, 1, 1, 0, 1, 0, 1, 0, 0, 0, 1, 0, 1, 1, 0, 0, 1, 0, 0, 1,\n",
692 |        "       1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 1,\n",
693 |        "       0, 0, 0, 0, 1, 1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 1,\n",
694 |        "       1, 0, 0, 1, 1, 0, 1, 0, 1, 0, 0, 1, 0, 1, 1, 0, 1, 0, 0, 0, 1, 1,\n",
695 |        "       1, 0, 1, 0, 1, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0, 0, 0, 0,\n",
696 |        "       0, 1, 1, 1, 1, 0, 0, 1, 0, 1, 0, 0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 0,\n",
697 |        "       1, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1,\n",
698 |        "       1, 0, 1, 1, 0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 1, 1, 0, 1, 0, 0, 0, 1,\n",
699 |        "       0, 0, 1, 1, 0, 0, 1, 0, 1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1,\n",
700 |        "       0, 1, 1, 1, 0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 0, 1, 1, 0, 1, 0, 1, 0,\n",
701 |        "       1, 0, 1, 0, 1, 1, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0,\n",
702 |        "       0, 0, 0, 0, 1, 0, 1, 1, 1, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1,\n",
703 |        "       0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0,\n",
704 |        "       0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1,\n",
705 |        "       0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0,\n",
706 |        "       1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 0, 0,\n",
707 |        "       0, 1, 1, 0, 1, 0, 0, 1, 0, 1, 1, 1, 0, 1, 0, 1, 0, 0, 0, 1, 1, 0,\n",
708 |        "       1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 1, 0, 1, 1, 0, 0, 1,\n",
709 |        "       0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 0, 0, 0])"
710 |       ]
711 |      },
712 |      "execution_count": 90,
713 |      "metadata": {},
714 |      "output_type": "execute_result"
715 |     }
716 |    ],
717 |    "source": [
718 |     "p = modelo.predict(X_prev)\n",
719 |     "p"
720 |    ]
721 |   },
722 |   {
723 |    "cell_type": "code",
724 |    "execution_count": 91,
725 |    "metadata": {},
726 |    "outputs": [
727 |     {
728 |      "data": {
729 |       "text/html": [
730 |        "<div>\n",
731 |        "<style scoped>\n",
732 |        "    .dataframe tbody tr th:only-of-type {\n",
733 |        "        vertical-align: middle;\n",
734 |        "    }\n",
735 |        "\n",
736 |        "    .dataframe tbody tr th {\n",
737 |        "        vertical-align: top;\n",
738 |        "    }\n",
739 |        "\n",
740 |        "    .dataframe thead th {\n",
741 |        "        text-align: right;\n",
742 |        "    }\n",
743 |        "</style>\n",
744 |        "<table border=\"1\" class=\"dataframe\">\n",
745 |        "  <thead>\n",
746 |        "    <tr style=\"text-align: right;\">\n",
747 |        "      <th></th>\n",
748 |        "      <th>PassengerId</th>\n",
749 |        "      <th>Pclass</th>\n",
750 |        "      <th>Name</th>\n",
751 |        "      <th>Sex</th>\n",
752 |        "      <th>Age</th>\n",
753 |        "      <th>SibSp</th>\n",
754 |        "      <th>Parch</th>\n",
755 |        "      <th>Ticket</th>\n",
756 |        "      <th>Fare</th>\n",
757 |        "      <th>Cabin</th>\n",
758 |        "      <th>Embarked</th>\n",
759 |        "      <th>Sex_binario</th>\n",
760 |        "    </tr>\n",
761 |        "  </thead>\n",
762 |        "  <tbody>\n",
763 |        "    <tr>\n",
764 |        "      <th>0</th>\n",
765 |        "      <td>892</td>\n",
766 |        "      <td>3</td>\n",
767 |        "      <td>Kelly, Mr. James</td>\n",
768 |        "      <td>male</td>\n",
769 |        "      <td>34.5</td>\n",
770 |        "      <td>0</td>\n",
771 |        "      <td>0</td>\n",
772 |        "      <td>330911</td>\n",
773 |        "      <td>7.8292</td>\n",
774 |        "      <td>NaN</td>\n",
775 |        "      <td>Q</td>\n",
776 |        "      <td>0</td>\n",
777 |        "    </tr>\n",
778 |        "    <tr>\n",
779 |        "      <th>1</th>\n",
780 |        "      <td>893</td>\n",
781 |        "      <td>3</td>\n",
782 |        "      <td>Wilkes, Mrs. James (Ellen Needs)</td>\n",
783 |        "      <td>female</td>\n",
784 |        "      <td>47.0</td>\n",
785 |        "      <td>1</td>\n",
786 |        "      <td>0</td>\n",
787 |        "      <td>363272</td>\n",
788 |        "      <td>7.0000</td>\n",
789 |        "      <td>NaN</td>\n",
790 |        "      <td>S</td>\n",
791 |        "      <td>1</td>\n",
792 |        "    </tr>\n",
793 |        "    <tr>\n",
794 |        "      <th>2</th>\n",
795 |        "      <td>894</td>\n",
796 |        "      <td>2</td>\n",
797 |        "      <td>Myles, Mr. Thomas Francis</td>\n",
798 |        "      <td>male</td>\n",
799 |        "      <td>62.0</td>\n",
800 |        "      <td>0</td>\n",
801 |        "      <td>0</td>\n",
802 |        "      <td>240276</td>\n",
803 |        "      <td>9.6875</td>\n",
804 |        "      <td>NaN</td>\n",
805 |        "      <td>Q</td>\n",
806 |        "      <td>0</td>\n",
807 |        "    </tr>\n",
808 |        "    <tr>\n",
809 |        "      <th>3</th>\n",
810 |        "      <td>895</td>\n",
811 |        "      <td>3</td>\n",
812 |        "      <td>Wirz, Mr. Albert</td>\n",
813 |        "      <td>male</td>\n",
814 |        "      <td>27.0</td>\n",
815 |        "      <td>0</td>\n",
816 |        "      <td>0</td>\n",
817 |        "      <td>315154</td>\n",
818 |        "      <td>8.6625</td>\n",
819 |        "      <td>NaN</td>\n",
820 |        "      <td>S</td>\n",
821 |        "      <td>0</td>\n",
822 |        "    </tr>\n",
823 |        "    <tr>\n",
824 |        "      <th>4</th>\n",
825 |        "      <td>896</td>\n",
826 |        "      <td>3</td>\n",
827 |        "      <td>Hirvonen, Mrs. Alexander (Helga E Lindqvist)</td>\n",
828 |        "      <td>female</td>\n",
829 |        "      <td>22.0</td>\n",
830 |        "      <td>1</td>\n",
831 |        "      <td>1</td>\n",
832 |        "      <td>3101298</td>\n",
833 |        "      <td>12.2875</td>\n",
834 |        "      <td>NaN</td>\n",
835 |        "      <td>S</td>\n",
836 |        "      <td>1</td>\n",
837 |        "    </tr>\n",
838 |        "  </tbody>\n",
839 |        "</table>\n",
840 |        "</div>"
841 |       ],
842 |       "text/plain": [
843 |        "   PassengerId  Pclass                                          Name     Sex  \\\n",
844 |        "0          892       3                              Kelly, Mr. James    male   \n",
845 |        "1          893       3              Wilkes, Mrs. James (Ellen Needs)  female   \n",
846 |        "2          894       2                     Myles, Mr. Thomas Francis    male   \n",
847 |        "3          895       3                              Wirz, Mr. Albert    male   \n",
848 |        "4          896       3  Hirvonen, Mrs. Alexander (Helga E Lindqvist)  female   \n",
849 |        "\n",
850 |        "    Age  SibSp  Parch   Ticket     Fare Cabin Embarked  Sex_binario  \n",
851 |        "0  34.5      0      0   330911   7.8292   NaN        Q            0  \n",
852 |        "1  47.0      1      0   363272   7.0000   NaN        S            1  \n",
853 |        "2  62.0      0      0   240276   9.6875   NaN        Q            0  \n",
854 |        "3  27.0      0      0   315154   8.6625   NaN        S            0  \n",
855 |        "4  22.0      1      1  3101298  12.2875   NaN        S            1  "
856 |       ]
857 |      },
858 |      "execution_count": 91,
859 |      "metadata": {},
860 |      "output_type": "execute_result"
861 |     }
862 |    ],
863 |    "source": [
864 |     "test.head()"
865 |    ]
866 |   },
867 |   {
868 |    "cell_type": "code",
869 |    "execution_count": 92,
870 |    "metadata": {},
871 |    "outputs": [
872 |     {
873 |      "data": {
874 |       "text/plain": [
875 |        "(418,)"
876 |       ]
877 |      },
878 |      "execution_count": 92,
879 |      "metadata": {},
880 |      "output_type": "execute_result"
881 |     }
882 |    ],
883 |    "source": [
884 |     "sub = pd.Series(p, index=test['PassengerId'], name='Survived')\n",
885 |     "sub.shape"
886 |    ]
887 |   },
888 |   {
889 |    "cell_type": "code",
890 |    "execution_count": 93,
891 |    "metadata": {},
892 |    "outputs": [],
893 |    "source": [
894 |     "sub.to_csv(\"primeiro_modelo.csv\", header=True)"
895 |    ]
896 |   },
897 |   {
898 |    "cell_type": "code",
899 |    "execution_count": 94,
900 |    "metadata": {},
901 |    "outputs": [
902 |     {
903 |      "name": "stdout",
904 |      "output_type": "stream",
905 |      "text": [
906 |       "PassengerId,Survived\n",
907 |       "892,0\n",
908 |       "893,1\n",
909 |       "894,0\n",
910 |       "895,1\n",
911 |       "896,1\n",
912 |       "897,0\n",
913 |       "898,1\n",
914 |       "899,0\n",
915 |       "900,1\n"
916 |      ]
917 |     }
918 |    ],
919 |    "source": [
920 |     "!head -n10 primeiro_modelo.csv"
921 |    ]
922 |   },
923 |   {
924 |    "cell_type": "code",
925 |    "execution_count": null,
926 |    "metadata": {},
927 |    "outputs": [],
928 |    "source": []
929 |   }
930 |  ],
931 |  "metadata": {
932 |   "kernelspec": {
933 |    "display_name": "Python 3",
934 |    "language": "python",
935 |    "name": "python3"
936 |   },
937 |   "language_info": {
938 |    "codemirror_mode": {
939 |     "name": "ipython",
940 |     "version": 3
941 |    },
942 |    "file_extension": ".py",
943 |    "mimetype": "text/x-python",
944 |    "name": "python",
945 |    "nbconvert_exporter": "python",
946 |    "pygments_lexer": "ipython3",
947 |    "version": "3.7.3"
948 |   }
949 |  },
950 |  "nbformat": 4,
951 |  "nbformat_minor": 4
952 | }
953 | 


--------------------------------------------------------------------------------
/titanic_video3_4_validacao.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 26,
  6 |    "metadata": {},
  7 |    "outputs": [],
  8 |    "source": [
  9 |     "import pandas as pd\n",
 10 |     "import numpy as np"
 11 |    ]
 12 |   },
 13 |   {
 14 |    "cell_type": "code",
 15 |    "execution_count": 27,
 16 |    "metadata": {},
 17 |    "outputs": [],
 18 |    "source": [
 19 |     "def transformar_sexo(valor):\n",
 20 |     "    if valor == 'female':\n",
 21 |     "        return 1\n",
 22 |     "    else:\n",
 23 |     "        return 0"
 24 |    ]
 25 |   },
 26 |   {
 27 |    "cell_type": "code",
 28 |    "execution_count": 34,
 29 |    "metadata": {},
 30 |    "outputs": [],
 31 |    "source": [
 32 |     "train = pd.read_csv(\"train.csv\")\n",
 33 |     "test = pd.read_csv(\"test.csv\")\n",
 34 |     "\n",
 35 |     "train['Sex_binario'] = train['Sex'].map(transformar_sexo)\n",
 36 |     "test['Sex_binario'] = test['Sex'].map(transformar_sexo)\n",
 37 |     "\n",
 38 |     "variaveis = ['Sex_binario', 'Age']\n",
 39 |     "\n",
 40 |     "X = train[variaveis].fillna(-1)\n",
 41 |     "y = train['Survived']"
 42 |    ]
 43 |   },
 44 |   {
 45 |    "cell_type": "code",
 46 |    "execution_count": 35,
 47 |    "metadata": {},
 48 |    "outputs": [
 49 |     {
 50 |      "data": {
 51 |       "text/html": [
 52 |        "<div>\n",
 53 |        "<style scoped>\n",
 54 |        "    .dataframe tbody tr th:only-of-type {\n",
 55 |        "        vertical-align: middle;\n",
 56 |        "    }\n",
 57 |        "\n",
 58 |        "    .dataframe tbody tr th {\n",
 59 |        "        vertical-align: top;\n",
 60 |        "    }\n",
 61 |        "\n",
 62 |        "    .dataframe thead th {\n",
 63 |        "        text-align: right;\n",
 64 |        "    }\n",
 65 |        "</style>\n",
 66 |        "<table border=\"1\" class=\"dataframe\">\n",
 67 |        "  <thead>\n",
 68 |        "    <tr style=\"text-align: right;\">\n",
 69 |        "      <th></th>\n",
 70 |        "      <th>PassengerId</th>\n",
 71 |        "      <th>Survived</th>\n",
 72 |        "      <th>Pclass</th>\n",
 73 |        "      <th>Name</th>\n",
 74 |        "      <th>Sex</th>\n",
 75 |        "      <th>Age</th>\n",
 76 |        "      <th>SibSp</th>\n",
 77 |        "      <th>Parch</th>\n",
 78 |        "      <th>Ticket</th>\n",
 79 |        "      <th>Fare</th>\n",
 80 |        "      <th>Cabin</th>\n",
 81 |        "      <th>Embarked</th>\n",
 82 |        "      <th>Sex_binario</th>\n",
 83 |        "    </tr>\n",
 84 |        "  </thead>\n",
 85 |        "  <tbody>\n",
 86 |        "    <tr>\n",
 87 |        "      <th>0</th>\n",
 88 |        "      <td>1</td>\n",
 89 |        "      <td>0</td>\n",
 90 |        "      <td>3</td>\n",
 91 |        "      <td>Braund, Mr. Owen Harris</td>\n",
 92 |        "      <td>male</td>\n",
 93 |        "      <td>22.0</td>\n",
 94 |        "      <td>1</td>\n",
 95 |        "      <td>0</td>\n",
 96 |        "      <td>A/5 21171</td>\n",
 97 |        "      <td>7.2500</td>\n",
 98 |        "      <td>NaN</td>\n",
 99 |        "      <td>S</td>\n",
100 |        "      <td>0</td>\n",
101 |        "    </tr>\n",
102 |        "    <tr>\n",
103 |        "      <th>1</th>\n",
104 |        "      <td>2</td>\n",
105 |        "      <td>1</td>\n",
106 |        "      <td>1</td>\n",
107 |        "      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
108 |        "      <td>female</td>\n",
109 |        "      <td>38.0</td>\n",
110 |        "      <td>1</td>\n",
111 |        "      <td>0</td>\n",
112 |        "      <td>PC 17599</td>\n",
113 |        "      <td>71.2833</td>\n",
114 |        "      <td>C85</td>\n",
115 |        "      <td>C</td>\n",
116 |        "      <td>1</td>\n",
117 |        "    </tr>\n",
118 |        "    <tr>\n",
119 |        "      <th>2</th>\n",
120 |        "      <td>3</td>\n",
121 |        "      <td>1</td>\n",
122 |        "      <td>3</td>\n",
123 |        "      <td>Heikkinen, Miss. Laina</td>\n",
124 |        "      <td>female</td>\n",
125 |        "      <td>26.0</td>\n",
126 |        "      <td>0</td>\n",
127 |        "      <td>0</td>\n",
128 |        "      <td>STON/O2. 3101282</td>\n",
129 |        "      <td>7.9250</td>\n",
130 |        "      <td>NaN</td>\n",
131 |        "      <td>S</td>\n",
132 |        "      <td>1</td>\n",
133 |        "    </tr>\n",
134 |        "    <tr>\n",
135 |        "      <th>3</th>\n",
136 |        "      <td>4</td>\n",
137 |        "      <td>1</td>\n",
138 |        "      <td>1</td>\n",
139 |        "      <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n",
140 |        "      <td>female</td>\n",
141 |        "      <td>35.0</td>\n",
142 |        "      <td>1</td>\n",
143 |        "      <td>0</td>\n",
144 |        "      <td>113803</td>\n",
145 |        "      <td>53.1000</td>\n",
146 |        "      <td>C123</td>\n",
147 |        "      <td>S</td>\n",
148 |        "      <td>1</td>\n",
149 |        "    </tr>\n",
150 |        "    <tr>\n",
151 |        "      <th>4</th>\n",
152 |        "      <td>5</td>\n",
153 |        "      <td>0</td>\n",
154 |        "      <td>3</td>\n",
155 |        "      <td>Allen, Mr. William Henry</td>\n",
156 |        "      <td>male</td>\n",
157 |        "      <td>35.0</td>\n",
158 |        "      <td>0</td>\n",
159 |        "      <td>0</td>\n",
160 |        "      <td>373450</td>\n",
161 |        "      <td>8.0500</td>\n",
162 |        "      <td>NaN</td>\n",
163 |        "      <td>S</td>\n",
164 |        "      <td>0</td>\n",
165 |        "    </tr>\n",
166 |        "  </tbody>\n",
167 |        "</table>\n",
168 |        "</div>"
169 |       ],
170 |       "text/plain": [
171 |        "   PassengerId  Survived  Pclass  \\\n",
172 |        "0            1         0       3   \n",
173 |        "1            2         1       1   \n",
174 |        "2            3         1       3   \n",
175 |        "3            4         1       1   \n",
176 |        "4            5         0       3   \n",
177 |        "\n",
178 |        "                                                Name     Sex   Age  SibSp  \\\n",
179 |        "0                            Braund, Mr. Owen Harris    male  22.0      1   \n",
180 |        "1  Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0      1   \n",
181 |        "2                             Heikkinen, Miss. Laina  female  26.0      0   \n",
182 |        "3       Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0      1   \n",
183 |        "4                           Allen, Mr. William Henry    male  35.0      0   \n",
184 |        "\n",
185 |        "   Parch            Ticket     Fare Cabin Embarked  Sex_binario  \n",
186 |        "0      0         A/5 21171   7.2500   NaN        S            0  \n",
187 |        "1      0          PC 17599  71.2833   C85        C            1  \n",
188 |        "2      0  STON/O2. 3101282   7.9250   NaN        S            1  \n",
189 |        "3      0            113803  53.1000  C123        S            1  \n",
190 |        "4      0            373450   8.0500   NaN        S            0  "
191 |       ]
192 |      },
193 |      "execution_count": 35,
194 |      "metadata": {},
195 |      "output_type": "execute_result"
196 |     }
197 |    ],
198 |    "source": [
199 |     "train.head()"
200 |    ]
201 |   },
202 |   {
203 |    "cell_type": "code",
204 |    "execution_count": 30,
205 |    "metadata": {},
206 |    "outputs": [],
207 |    "source": [
208 |     "from sklearn.ensemble import RandomForestClassifier\n",
209 |     "from sklearn.model_selection import train_test_split"
210 |    ]
211 |   },
212 |   {
213 |    "cell_type": "code",
214 |    "execution_count": 31,
215 |    "metadata": {},
216 |    "outputs": [
217 |     {
218 |      "data": {
219 |       "text/plain": [
220 |        "array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])"
221 |       ]
222 |      },
223 |      "execution_count": 31,
224 |      "metadata": {},
225 |      "output_type": "execute_result"
226 |     }
227 |    ],
228 |    "source": [
229 |     "X_falso = np.arange(10)\n",
230 |     "X_falso"
231 |    ]
232 |   },
233 |   {
234 |    "cell_type": "code",
235 |    "execution_count": 32,
236 |    "metadata": {},
237 |    "outputs": [
238 |     {
239 |      "data": {
240 |       "text/plain": [
241 |        "[array([6, 7, 3, 0, 5]), array([2, 8, 4, 9, 1])]"
242 |       ]
243 |      },
244 |      "execution_count": 32,
245 |      "metadata": {},
246 |      "output_type": "execute_result"
247 |     }
248 |    ],
249 |    "source": [
250 |     "np.random.seed(0)\n",
251 |     "train_test_split(X_falso, test_size=0.5)"
252 |    ]
253 |   },
254 |   {
255 |    "cell_type": "code",
256 |    "execution_count": 48,
257 |    "metadata": {},
258 |    "outputs": [],
259 |    "source": [
260 |     "np.random.seed(1)\n",
261 |     "X_treino, X_valid, y_treino, y_valid = train_test_split(X, y, test_size=0.5)"
262 |    ]
263 |   },
264 |   {
265 |    "cell_type": "code",
266 |    "execution_count": 49,
267 |    "metadata": {},
268 |    "outputs": [
269 |     {
270 |      "data": {
271 |       "text/html": [
272 |        "<div>\n",
273 |        "<style scoped>\n",
274 |        "    .dataframe tbody tr th:only-of-type {\n",
275 |        "        vertical-align: middle;\n",
276 |        "    }\n",
277 |        "\n",
278 |        "    .dataframe tbody tr th {\n",
279 |        "        vertical-align: top;\n",
280 |        "    }\n",
281 |        "\n",
282 |        "    .dataframe thead th {\n",
283 |        "        text-align: right;\n",
284 |        "    }\n",
285 |        "</style>\n",
286 |        "<table border=\"1\" class=\"dataframe\">\n",
287 |        "  <thead>\n",
288 |        "    <tr style=\"text-align: right;\">\n",
289 |        "      <th></th>\n",
290 |        "      <th>Sex_binario</th>\n",
291 |        "      <th>Age</th>\n",
292 |        "    </tr>\n",
293 |        "  </thead>\n",
294 |        "  <tbody>\n",
295 |        "    <tr>\n",
296 |        "      <th>394</th>\n",
297 |        "      <td>1</td>\n",
298 |        "      <td>24.00</td>\n",
299 |        "    </tr>\n",
300 |        "    <tr>\n",
301 |        "      <th>851</th>\n",
302 |        "      <td>0</td>\n",
303 |        "      <td>74.00</td>\n",
304 |        "    </tr>\n",
305 |        "    <tr>\n",
306 |        "      <th>373</th>\n",
307 |        "      <td>0</td>\n",
308 |        "      <td>22.00</td>\n",
309 |        "    </tr>\n",
310 |        "    <tr>\n",
311 |        "      <th>523</th>\n",
312 |        "      <td>1</td>\n",
313 |        "      <td>44.00</td>\n",
314 |        "    </tr>\n",
315 |        "    <tr>\n",
316 |        "      <th>78</th>\n",
317 |        "      <td>0</td>\n",
318 |        "      <td>0.83</td>\n",
319 |        "    </tr>\n",
320 |        "  </tbody>\n",
321 |        "</table>\n",
322 |        "</div>"
323 |       ],
324 |       "text/plain": [
325 |        "     Sex_binario    Age\n",
326 |        "394            1  24.00\n",
327 |        "851            0  74.00\n",
328 |        "373            0  22.00\n",
329 |        "523            1  44.00\n",
330 |        "78             0   0.83"
331 |       ]
332 |      },
333 |      "execution_count": 49,
334 |      "metadata": {},
335 |      "output_type": "execute_result"
336 |     }
337 |    ],
338 |    "source": [
339 |     "X_treino.head()"
340 |    ]
341 |   },
342 |   {
343 |    "cell_type": "code",
344 |    "execution_count": 50,
345 |    "metadata": {},
346 |    "outputs": [
347 |     {
348 |      "data": {
349 |       "text/plain": [
350 |        "((445, 2), (446, 2), (445,), (446,))"
351 |       ]
352 |      },
353 |      "execution_count": 50,
354 |      "metadata": {},
355 |      "output_type": "execute_result"
356 |     }
357 |    ],
358 |    "source": [
359 |     "X_treino.shape, X_valid.shape, y_treino.shape, y_valid.shape"
360 |    ]
361 |   },
362 |   {
363 |    "cell_type": "code",
364 |    "execution_count": 51,
365 |    "metadata": {},
366 |    "outputs": [
367 |     {
368 |      "data": {
369 |       "text/plain": [
370 |        "RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',\n",
371 |        "            max_depth=None, max_features='auto', max_leaf_nodes=None,\n",
372 |        "            min_impurity_decrease=0.0, min_impurity_split=None,\n",
373 |        "            min_samples_leaf=1, min_samples_split=2,\n",
374 |        "            min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=-1,\n",
375 |        "            oob_score=False, random_state=0, verbose=0, warm_start=False)"
376 |       ]
377 |      },
378 |      "execution_count": 51,
379 |      "metadata": {},
380 |      "output_type": "execute_result"
381 |     }
382 |    ],
383 |    "source": [
384 |     "modelo = RandomForestClassifier(n_estimators=100, n_jobs=-1, random_state=0)\n",
385 |     "modelo.fit(X_treino, y_treino)"
386 |    ]
387 |   },
388 |   {
389 |    "cell_type": "code",
390 |    "execution_count": 52,
391 |    "metadata": {},
392 |    "outputs": [],
393 |    "source": [
394 |     "p = modelo.predict(X_valid)"
395 |    ]
396 |   },
397 |   {
398 |    "cell_type": "code",
399 |    "execution_count": 53,
400 |    "metadata": {},
401 |    "outputs": [
402 |     {
403 |      "data": {
404 |       "text/plain": [
405 |        "0.7466367713004485"
406 |       ]
407 |      },
408 |      "execution_count": 53,
409 |      "metadata": {},
410 |      "output_type": "execute_result"
411 |     }
412 |    ],
413 |    "source": [
414 |     "np.mean(y_valid == p)"
415 |    ]
416 |   },
417 |   {
418 |    "cell_type": "code",
419 |    "execution_count": 54,
420 |    "metadata": {},
421 |    "outputs": [
422 |     {
423 |      "data": {
424 |       "text/plain": [
425 |        "0.7623318385650224"
426 |       ]
427 |      },
428 |      "execution_count": 54,
429 |      "metadata": {},
430 |      "output_type": "execute_result"
431 |     }
432 |    ],
433 |    "source": [
434 |     "p = (X_valid['Sex_binario'] == 1).astype(np.int64)\n",
435 |     "np.mean(y_valid == p)"
436 |    ]
437 |   },
438 |   {
439 |    "cell_type": "markdown",
440 |    "metadata": {},
441 |    "source": [
442 |     "## Validação cruzada"
443 |    ]
444 |   },
445 |   {
446 |    "cell_type": "code",
447 |    "execution_count": 55,
448 |    "metadata": {},
449 |    "outputs": [
450 |     {
451 |      "data": {
452 |       "text/plain": [
453 |        "array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])"
454 |       ]
455 |      },
456 |      "execution_count": 55,
457 |      "metadata": {},
458 |      "output_type": "execute_result"
459 |     }
460 |    ],
461 |    "source": [
462 |     "X_falso"
463 |    ]
464 |   },
465 |   {
466 |    "cell_type": "code",
467 |    "execution_count": 56,
468 |    "metadata": {},
469 |    "outputs": [],
470 |    "source": [
471 |     "from sklearn.model_selection import KFold"
472 |    ]
473 |   },
474 |   {
475 |    "cell_type": "code",
476 |    "execution_count": 57,
477 |    "metadata": {},
478 |    "outputs": [
479 |     {
480 |      "data": {
481 |       "text/plain": [
482 |        "\u001b[0;31mInit signature:\u001b[0m \u001b[0mKFold\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mn_splits\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'warn'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mshuffle\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrandom_state\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
483 |        "\u001b[0;31mDocstring:\u001b[0m     \n",
484 |        "K-Folds cross-validator\n",
485 |        "\n",
486 |        "Provides train/test indices to split data in train/test sets. Split\n",
487 |        "dataset into k consecutive folds (without shuffling by default).\n",
488 |        "\n",
489 |        "Each fold is then used once as a validation while the k - 1 remaining\n",
490 |        "folds form the training set.\n",
491 |        "\n",
492 |        "Read more in the :ref:`User Guide <cross_validation>`.\n",
493 |        "\n",
494 |        "Parameters\n",
495 |        "----------\n",
496 |        "n_splits : int, default=3\n",
497 |        "    Number of folds. Must be at least 2.\n",
498 |        "\n",
499 |        "    .. versionchanged:: 0.20\n",
500 |        "        ``n_splits`` default value will change from 3 to 5 in v0.22.\n",
501 |        "\n",
502 |        "shuffle : boolean, optional\n",
503 |        "    Whether to shuffle the data before splitting into batches.\n",
504 |        "\n",
505 |        "random_state : int, RandomState instance or None, optional, default=None\n",
506 |        "    If int, random_state is the seed used by the random number generator;\n",
507 |        "    If RandomState instance, random_state is the random number generator;\n",
508 |        "    If None, the random number generator is the RandomState instance used\n",
509 |        "    by `np.random`. Used when ``shuffle`` == True.\n",
510 |        "\n",
511 |        "Examples\n",
512 |        "--------\n",
513 |        ">>> from sklearn.model_selection import KFold\n",
514 |        ">>> X = np.array([[1, 2], [3, 4], [1, 2], [3, 4]])\n",
515 |        ">>> y = np.array([1, 2, 3, 4])\n",
516 |        ">>> kf = KFold(n_splits=2)\n",
517 |        ">>> kf.get_n_splits(X)\n",
518 |        "2\n",
519 |        ">>> print(kf)  # doctest: +NORMALIZE_WHITESPACE\n",
520 |        "KFold(n_splits=2, random_state=None, shuffle=False)\n",
521 |        ">>> for train_index, test_index in kf.split(X):\n",
522 |        "...    print(\"TRAIN:\", train_index, \"TEST:\", test_index)\n",
523 |        "...    X_train, X_test = X[train_index], X[test_index]\n",
524 |        "...    y_train, y_test = y[train_index], y[test_index]\n",
525 |        "TRAIN: [2 3] TEST: [0 1]\n",
526 |        "TRAIN: [0 1] TEST: [2 3]\n",
527 |        "\n",
528 |        "Notes\n",
529 |        "-----\n",
530 |        "The first ``n_samples % n_splits`` folds have size\n",
531 |        "``n_samples // n_splits + 1``, other folds have size\n",
532 |        "``n_samples // n_splits``, where ``n_samples`` is the number of samples.\n",
533 |        "\n",
534 |        "Randomized CV splitters may return different results for each call of\n",
535 |        "split. You can make the results identical by setting ``random_state``\n",
536 |        "to an integer.\n",
537 |        "\n",
538 |        "See also\n",
539 |        "--------\n",
540 |        "StratifiedKFold\n",
541 |        "    Takes group information into account to avoid building folds with\n",
542 |        "    imbalanced class distributions (for binary or multiclass\n",
543 |        "    classification tasks).\n",
544 |        "\n",
545 |        "GroupKFold: K-fold iterator variant with non-overlapping groups.\n",
546 |        "\n",
547 |        "RepeatedKFold: Repeats K-Fold n times.\n",
548 |        "\u001b[0;31mFile:\u001b[0m           ~/anaconda3/lib/python3.7/site-packages/sklearn/model_selection/_split.py\n",
549 |        "\u001b[0;31mType:\u001b[0m           ABCMeta\n",
550 |        "\u001b[0;31mSubclasses:\u001b[0m     \n"
551 |       ]
552 |      },
553 |      "metadata": {},
554 |      "output_type": "display_data"
555 |     }
556 |    ],
557 |    "source": [
558 |     "?KFold"
559 |    ]
560 |   },
561 |   {
562 |    "cell_type": "code",
563 |    "execution_count": 59,
564 |    "metadata": {},
565 |    "outputs": [
566 |     {
567 |      "name": "stdout",
568 |      "output_type": "stream",
569 |      "text": [
570 |       "Treino: [0 1 3 5 6 7]\n",
571 |       "Valid: [2 4 8 9]\n",
572 |       "\n",
573 |       "Treino: [0 2 3 4 5 8 9]\n",
574 |       "Valid: [1 6 7]\n",
575 |       "\n",
576 |       "Treino: [1 2 4 6 7 8 9]\n",
577 |       "Valid: [0 3 5]\n",
578 |       "\n"
579 |      ]
580 |     }
581 |    ],
582 |    "source": [
583 |     "kf = KFold(3, shuffle=True, random_state=0)\n",
584 |     "for linhas_treino, linhas_valid in kf.split(X_falso):\n",
585 |     "    print(\"Treino:\", linhas_treino)\n",
586 |     "    print(\"Valid:\", linhas_valid)\n",
587 |     "    print()"
588 |    ]
589 |   },
590 |   {
591 |    "cell_type": "code",
592 |    "execution_count": 72,
593 |    "metadata": {},
594 |    "outputs": [
595 |     {
596 |      "name": "stdout",
597 |      "output_type": "stream",
598 |      "text": [
599 |       "Rep: 0\n",
600 |       "Treino: 712\n",
601 |       "Valid: 179\n",
602 |       "Acc: 0.7988826815642458\n",
603 |       "\n",
604 |       "Treino: 713\n",
605 |       "Valid: 178\n",
606 |       "Acc: 0.7359550561797753\n",
607 |       "\n",
608 |       "Treino: 713\n",
609 |       "Valid: 178\n",
610 |       "Acc: 0.7808988764044944\n",
611 |       "\n",
612 |       "Treino: 713\n",
613 |       "Valid: 178\n",
614 |       "Acc: 0.797752808988764\n",
615 |       "\n",
616 |       "Treino: 713\n",
617 |       "Valid: 178\n",
618 |       "Acc: 0.7808988764044944\n",
619 |       "\n",
620 |       "Rep: 1\n",
621 |       "Treino: 712\n",
622 |       "Valid: 179\n",
623 |       "Acc: 0.7374301675977654\n",
624 |       "\n",
625 |       "Treino: 713\n",
626 |       "Valid: 178\n",
627 |       "Acc: 0.7247191011235955\n",
628 |       "\n",
629 |       "Treino: 713\n",
630 |       "Valid: 178\n",
631 |       "Acc: 0.7808988764044944\n",
632 |       "\n",
633 |       "Treino: 713\n",
634 |       "Valid: 178\n",
635 |       "Acc: 0.7921348314606742\n",
636 |       "\n",
637 |       "Treino: 713\n",
638 |       "Valid: 178\n",
639 |       "Acc: 0.7921348314606742\n",
640 |       "\n",
641 |       "Rep: 2\n",
642 |       "Treino: 712\n",
643 |       "Valid: 179\n",
644 |       "Acc: 0.7653631284916201\n",
645 |       "\n",
646 |       "Treino: 713\n",
647 |       "Valid: 178\n",
648 |       "Acc: 0.7865168539325843\n",
649 |       "\n",
650 |       "Treino: 713\n",
651 |       "Valid: 178\n",
652 |       "Acc: 0.7865168539325843\n",
653 |       "\n",
654 |       "Treino: 713\n",
655 |       "Valid: 178\n",
656 |       "Acc: 0.7808988764044944\n",
657 |       "\n",
658 |       "Treino: 713\n",
659 |       "Valid: 178\n",
660 |       "Acc: 0.7640449438202247\n",
661 |       "\n",
662 |       "Rep: 3\n",
663 |       "Treino: 712\n",
664 |       "Valid: 179\n",
665 |       "Acc: 0.7653631284916201\n",
666 |       "\n",
667 |       "Treino: 713\n",
668 |       "Valid: 178\n",
669 |       "Acc: 0.7471910112359551\n",
670 |       "\n",
671 |       "Treino: 713\n",
672 |       "Valid: 178\n",
673 |       "Acc: 0.7808988764044944\n",
674 |       "\n",
675 |       "Treino: 713\n",
676 |       "Valid: 178\n",
677 |       "Acc: 0.7415730337078652\n",
678 |       "\n",
679 |       "Treino: 713\n",
680 |       "Valid: 178\n",
681 |       "Acc: 0.8202247191011236\n",
682 |       "\n",
683 |       "Rep: 4\n",
684 |       "Treino: 712\n",
685 |       "Valid: 179\n",
686 |       "Acc: 0.7988826815642458\n",
687 |       "\n",
688 |       "Treino: 713\n",
689 |       "Valid: 178\n",
690 |       "Acc: 0.797752808988764\n",
691 |       "\n",
692 |       "Treino: 713\n",
693 |       "Valid: 178\n",
694 |       "Acc: 0.7752808988764045\n",
695 |       "\n",
696 |       "Treino: 713\n",
697 |       "Valid: 178\n",
698 |       "Acc: 0.7415730337078652\n",
699 |       "\n",
700 |       "Treino: 713\n",
701 |       "Valid: 178\n",
702 |       "Acc: 0.7471910112359551\n",
703 |       "\n",
704 |       "Rep: 5\n",
705 |       "Treino: 712\n",
706 |       "Valid: 179\n",
707 |       "Acc: 0.7653631284916201\n",
708 |       "\n",
709 |       "Treino: 713\n",
710 |       "Valid: 178\n",
711 |       "Acc: 0.7415730337078652\n",
712 |       "\n",
713 |       "Treino: 713\n",
714 |       "Valid: 178\n",
715 |       "Acc: 0.8370786516853933\n",
716 |       "\n",
717 |       "Treino: 713\n",
718 |       "Valid: 178\n",
719 |       "Acc: 0.7471910112359551\n",
720 |       "\n",
721 |       "Treino: 713\n",
722 |       "Valid: 178\n",
723 |       "Acc: 0.702247191011236\n",
724 |       "\n",
725 |       "Rep: 6\n",
726 |       "Treino: 712\n",
727 |       "Valid: 179\n",
728 |       "Acc: 0.7821229050279329\n",
729 |       "\n",
730 |       "Treino: 713\n",
731 |       "Valid: 178\n",
732 |       "Acc: 0.8146067415730337\n",
733 |       "\n",
734 |       "Treino: 713\n",
735 |       "Valid: 178\n",
736 |       "Acc: 0.7752808988764045\n",
737 |       "\n",
738 |       "Treino: 713\n",
739 |       "Valid: 178\n",
740 |       "Acc: 0.7134831460674157\n",
741 |       "\n",
742 |       "Treino: 713\n",
743 |       "Valid: 178\n",
744 |       "Acc: 0.7247191011235955\n",
745 |       "\n",
746 |       "Rep: 7\n",
747 |       "Treino: 712\n",
748 |       "Valid: 179\n",
749 |       "Acc: 0.7150837988826816\n",
750 |       "\n",
751 |       "Treino: 713\n",
752 |       "Valid: 178\n",
753 |       "Acc: 0.7247191011235955\n",
754 |       "\n",
755 |       "Treino: 713\n",
756 |       "Valid: 178\n",
757 |       "Acc: 0.8370786516853933\n",
758 |       "\n",
759 |       "Treino: 713\n",
760 |       "Valid: 178\n",
761 |       "Acc: 0.8033707865168539\n",
762 |       "\n",
763 |       "Treino: 713\n",
764 |       "Valid: 178\n",
765 |       "Acc: 0.7808988764044944\n",
766 |       "\n",
767 |       "Rep: 8\n",
768 |       "Treino: 712\n",
769 |       "Valid: 179\n",
770 |       "Acc: 0.7597765363128491\n",
771 |       "\n",
772 |       "Treino: 713\n",
773 |       "Valid: 178\n",
774 |       "Acc: 0.7921348314606742\n",
775 |       "\n",
776 |       "Treino: 713\n",
777 |       "Valid: 178\n",
778 |       "Acc: 0.7921348314606742\n",
779 |       "\n",
780 |       "Treino: 713\n",
781 |       "Valid: 178\n",
782 |       "Acc: 0.7696629213483146\n",
783 |       "\n",
784 |       "Treino: 713\n",
785 |       "Valid: 178\n",
786 |       "Acc: 0.7640449438202247\n",
787 |       "\n",
788 |       "Rep: 9\n",
789 |       "Treino: 712\n",
790 |       "Valid: 179\n",
791 |       "Acc: 0.7039106145251397\n",
792 |       "\n",
793 |       "Treino: 713\n",
794 |       "Valid: 178\n",
795 |       "Acc: 0.7584269662921348\n",
796 |       "\n",
797 |       "Treino: 713\n",
798 |       "Valid: 178\n",
799 |       "Acc: 0.7415730337078652\n",
800 |       "\n",
801 |       "Treino: 713\n",
802 |       "Valid: 178\n",
803 |       "Acc: 0.8033707865168539\n",
804 |       "\n",
805 |       "Treino: 713\n",
806 |       "Valid: 178\n",
807 |       "Acc: 0.7921348314606742\n",
808 |       "\n"
809 |      ]
810 |     }
811 |    ],
812 |    "source": [
813 |     "resultados = []\n",
814 |     "for rep in range(10):\n",
815 |     "    print(\"Rep:\", rep)\n",
816 |     "    kf = KFold(5, shuffle=True, random_state=rep)\n",
817 |     "    \n",
818 |     "    for linhas_treino, linhas_valid in kf.split(X):\n",
819 |     "        print(\"Treino:\", linhas_treino.shape[0])\n",
820 |     "        print(\"Valid:\", linhas_valid.shape[0])\n",
821 |     "\n",
822 |     "        X_treino, X_valid = X.iloc[linhas_treino], X.iloc[linhas_valid]\n",
823 |     "        y_treino, y_valid = y.iloc[linhas_treino], y.iloc[linhas_valid]\n",
824 |     "\n",
825 |     "        modelo = RandomForestClassifier(n_estimators=100, n_jobs=-1, random_state=0)\n",
826 |     "        modelo.fit(X_treino, y_treino)\n",
827 |     "\n",
828 |     "        p = modelo.predict(X_valid)\n",
829 |     "\n",
830 |     "        acc = np.mean(y_valid == p)\n",
831 |     "        resultados.append(acc)\n",
832 |     "        print(\"Acc:\", acc)\n",
833 |     "        print()\n",
834 |     "        #print(X_treino.head())\n",
835 |     "        #print()"
836 |    ]
837 |   },
838 |   {
839 |    "cell_type": "code",
840 |    "execution_count": 73,
841 |    "metadata": {},
842 |    "outputs": [
843 |     {
844 |      "data": {
845 |       "text/plain": [
846 |        "50"
847 |       ]
848 |      },
849 |      "execution_count": 73,
850 |      "metadata": {},
851 |      "output_type": "execute_result"
852 |     }
853 |    ],
854 |    "source": [
855 |     "len(resultados)"
856 |    ]
857 |   },
858 |   {
859 |    "cell_type": "code",
860 |    "execution_count": 74,
861 |    "metadata": {},
862 |    "outputs": [
863 |     {
864 |      "data": {
865 |       "text/plain": [
866 |        "0.7692593057560732"
867 |       ]
868 |      },
869 |      "execution_count": 74,
870 |      "metadata": {},
871 |      "output_type": "execute_result"
872 |     }
873 |    ],
874 |    "source": [
875 |     "np.mean(resultados)"
876 |    ]
877 |   },
878 |   {
879 |    "cell_type": "markdown",
880 |    "metadata": {},
881 |    "source": [
882 |     "## Criar submission"
883 |    ]
884 |   },
885 |   {
886 |    "cell_type": "code",
887 |    "execution_count": 92,
888 |    "metadata": {},
889 |    "outputs": [
890 |     {
891 |      "data": {
892 |       "text/plain": [
893 |        "(418,)"
894 |       ]
895 |      },
896 |      "execution_count": 92,
897 |      "metadata": {},
898 |      "output_type": "execute_result"
899 |     }
900 |    ],
901 |    "source": [
902 |     "sub = pd.Series(p, index=test['PassengerId'], name='Survived')\n",
903 |     "sub.shape"
904 |    ]
905 |   },
906 |   {
907 |    "cell_type": "code",
908 |    "execution_count": 93,
909 |    "metadata": {},
910 |    "outputs": [],
911 |    "source": [
912 |     "sub.to_csv(\"primeiro_modelo.csv\", header=True)"
913 |    ]
914 |   },
915 |   {
916 |    "cell_type": "code",
917 |    "execution_count": 94,
918 |    "metadata": {},
919 |    "outputs": [
920 |     {
921 |      "name": "stdout",
922 |      "output_type": "stream",
923 |      "text": [
924 |       "PassengerId,Survived\n",
925 |       "892,0\n",
926 |       "893,1\n",
927 |       "894,0\n",
928 |       "895,1\n",
929 |       "896,1\n",
930 |       "897,0\n",
931 |       "898,1\n",
932 |       "899,0\n",
933 |       "900,1\n"
934 |      ]
935 |     }
936 |    ],
937 |    "source": [
938 |     "!head -n10 primeiro_modelo.csv"
939 |    ]
940 |   },
941 |   {
942 |    "cell_type": "code",
943 |    "execution_count": null,
944 |    "metadata": {},
945 |    "outputs": [],
946 |    "source": []
947 |   }
948 |  ],
949 |  "metadata": {
950 |   "kernelspec": {
951 |    "display_name": "Python 3",
952 |    "language": "python",
953 |    "name": "python3"
954 |   },
955 |   "language_info": {
956 |    "codemirror_mode": {
957 |     "name": "ipython",
958 |     "version": 3
959 |    },
960 |    "file_extension": ".py",
961 |    "mimetype": "text/x-python",
962 |    "name": "python",
963 |    "nbconvert_exporter": "python",
964 |    "pygments_lexer": "ipython3",
965 |    "version": "3.7.3"
966 |   }
967 |  },
968 |  "nbformat": 4,
969 |  "nbformat_minor": 4
970 | }
971 | 


--------------------------------------------------------------------------------
/titanic_video5.ipynb:
--------------------------------------------------------------------------------
   1 | {
   2 |  "cells": [
   3 |   {
   4 |    "cell_type": "code",
   5 |    "execution_count": 2,
   6 |    "metadata": {},
   7 |    "outputs": [],
   8 |    "source": [
   9 |     "import pandas as pd\n",
  10 |     "import numpy as np"
  11 |    ]
  12 |   },
  13 |   {
  14 |    "cell_type": "code",
  15 |    "execution_count": 3,
  16 |    "metadata": {},
  17 |    "outputs": [],
  18 |    "source": [
  19 |     "def transformar_sexo(valor):\n",
  20 |     "    if valor == 'female':\n",
  21 |     "        return 1\n",
  22 |     "    else:\n",
  23 |     "        return 0"
  24 |    ]
  25 |   },
  26 |   {
  27 |    "cell_type": "code",
  28 |    "execution_count": 28,
  29 |    "metadata": {},
  30 |    "outputs": [],
  31 |    "source": [
  32 |     "train = pd.read_csv(\"train.csv\")\n",
  33 |     "test = pd.read_csv(\"test.csv\")\n",
  34 |     "\n",
  35 |     "train['Sex_binario'] = train['Sex'].map(transformar_sexo)\n",
  36 |     "test['Sex_binario'] = test['Sex'].map(transformar_sexo)\n",
  37 |     "\n",
  38 |     "variaveis = ['Sex_binario', 'Age']\n",
  39 |     "\n",
  40 |     "X = train[variaveis].fillna(-1)\n",
  41 |     "y = train['Survived']"
  42 |    ]
  43 |   },
  44 |   {
  45 |    "cell_type": "code",
  46 |    "execution_count": 5,
  47 |    "metadata": {},
  48 |    "outputs": [
  49 |     {
  50 |      "data": {
  51 |       "text/html": [
  52 |        "<div>\n",
  53 |        "<style scoped>\n",
  54 |        "    .dataframe tbody tr th:only-of-type {\n",
  55 |        "        vertical-align: middle;\n",
  56 |        "    }\n",
  57 |        "\n",
  58 |        "    .dataframe tbody tr th {\n",
  59 |        "        vertical-align: top;\n",
  60 |        "    }\n",
  61 |        "\n",
  62 |        "    .dataframe thead th {\n",
  63 |        "        text-align: right;\n",
  64 |        "    }\n",
  65 |        "</style>\n",
  66 |        "<table border=\"1\" class=\"dataframe\">\n",
  67 |        "  <thead>\n",
  68 |        "    <tr style=\"text-align: right;\">\n",
  69 |        "      <th></th>\n",
  70 |        "      <th>PassengerId</th>\n",
  71 |        "      <th>Survived</th>\n",
  72 |        "      <th>Pclass</th>\n",
  73 |        "      <th>Name</th>\n",
  74 |        "      <th>Sex</th>\n",
  75 |        "      <th>Age</th>\n",
  76 |        "      <th>SibSp</th>\n",
  77 |        "      <th>Parch</th>\n",
  78 |        "      <th>Ticket</th>\n",
  79 |        "      <th>Fare</th>\n",
  80 |        "      <th>Cabin</th>\n",
  81 |        "      <th>Embarked</th>\n",
  82 |        "      <th>Sex_binario</th>\n",
  83 |        "    </tr>\n",
  84 |        "  </thead>\n",
  85 |        "  <tbody>\n",
  86 |        "    <tr>\n",
  87 |        "      <th>0</th>\n",
  88 |        "      <td>1</td>\n",
  89 |        "      <td>0</td>\n",
  90 |        "      <td>3</td>\n",
  91 |        "      <td>Braund, Mr. Owen Harris</td>\n",
  92 |        "      <td>male</td>\n",
  93 |        "      <td>22.0</td>\n",
  94 |        "      <td>1</td>\n",
  95 |        "      <td>0</td>\n",
  96 |        "      <td>A/5 21171</td>\n",
  97 |        "      <td>7.2500</td>\n",
  98 |        "      <td>NaN</td>\n",
  99 |        "      <td>S</td>\n",
 100 |        "      <td>0</td>\n",
 101 |        "    </tr>\n",
 102 |        "    <tr>\n",
 103 |        "      <th>1</th>\n",
 104 |        "      <td>2</td>\n",
 105 |        "      <td>1</td>\n",
 106 |        "      <td>1</td>\n",
 107 |        "      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
 108 |        "      <td>female</td>\n",
 109 |        "      <td>38.0</td>\n",
 110 |        "      <td>1</td>\n",
 111 |        "      <td>0</td>\n",
 112 |        "      <td>PC 17599</td>\n",
 113 |        "      <td>71.2833</td>\n",
 114 |        "      <td>C85</td>\n",
 115 |        "      <td>C</td>\n",
 116 |        "      <td>1</td>\n",
 117 |        "    </tr>\n",
 118 |        "    <tr>\n",
 119 |        "      <th>2</th>\n",
 120 |        "      <td>3</td>\n",
 121 |        "      <td>1</td>\n",
 122 |        "      <td>3</td>\n",
 123 |        "      <td>Heikkinen, Miss. Laina</td>\n",
 124 |        "      <td>female</td>\n",
 125 |        "      <td>26.0</td>\n",
 126 |        "      <td>0</td>\n",
 127 |        "      <td>0</td>\n",
 128 |        "      <td>STON/O2. 3101282</td>\n",
 129 |        "      <td>7.9250</td>\n",
 130 |        "      <td>NaN</td>\n",
 131 |        "      <td>S</td>\n",
 132 |        "      <td>1</td>\n",
 133 |        "    </tr>\n",
 134 |        "    <tr>\n",
 135 |        "      <th>3</th>\n",
 136 |        "      <td>4</td>\n",
 137 |        "      <td>1</td>\n",
 138 |        "      <td>1</td>\n",
 139 |        "      <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n",
 140 |        "      <td>female</td>\n",
 141 |        "      <td>35.0</td>\n",
 142 |        "      <td>1</td>\n",
 143 |        "      <td>0</td>\n",
 144 |        "      <td>113803</td>\n",
 145 |        "      <td>53.1000</td>\n",
 146 |        "      <td>C123</td>\n",
 147 |        "      <td>S</td>\n",
 148 |        "      <td>1</td>\n",
 149 |        "    </tr>\n",
 150 |        "    <tr>\n",
 151 |        "      <th>4</th>\n",
 152 |        "      <td>5</td>\n",
 153 |        "      <td>0</td>\n",
 154 |        "      <td>3</td>\n",
 155 |        "      <td>Allen, Mr. William Henry</td>\n",
 156 |        "      <td>male</td>\n",
 157 |        "      <td>35.0</td>\n",
 158 |        "      <td>0</td>\n",
 159 |        "      <td>0</td>\n",
 160 |        "      <td>373450</td>\n",
 161 |        "      <td>8.0500</td>\n",
 162 |        "      <td>NaN</td>\n",
 163 |        "      <td>S</td>\n",
 164 |        "      <td>0</td>\n",
 165 |        "    </tr>\n",
 166 |        "  </tbody>\n",
 167 |        "</table>\n",
 168 |        "</div>"
 169 |       ],
 170 |       "text/plain": [
 171 |        "   PassengerId  Survived  Pclass  \\\n",
 172 |        "0            1         0       3   \n",
 173 |        "1            2         1       1   \n",
 174 |        "2            3         1       3   \n",
 175 |        "3            4         1       1   \n",
 176 |        "4            5         0       3   \n",
 177 |        "\n",
 178 |        "                                                Name     Sex   Age  SibSp  \\\n",
 179 |        "0                            Braund, Mr. Owen Harris    male  22.0      1   \n",
 180 |        "1  Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0      1   \n",
 181 |        "2                             Heikkinen, Miss. Laina  female  26.0      0   \n",
 182 |        "3       Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0      1   \n",
 183 |        "4                           Allen, Mr. William Henry    male  35.0      0   \n",
 184 |        "\n",
 185 |        "   Parch            Ticket     Fare Cabin Embarked  Sex_binario  \n",
 186 |        "0      0         A/5 21171   7.2500   NaN        S            0  \n",
 187 |        "1      0          PC 17599  71.2833   C85        C            1  \n",
 188 |        "2      0  STON/O2. 3101282   7.9250   NaN        S            1  \n",
 189 |        "3      0            113803  53.1000  C123        S            1  \n",
 190 |        "4      0            373450   8.0500   NaN        S            0  "
 191 |       ]
 192 |      },
 193 |      "execution_count": 5,
 194 |      "metadata": {},
 195 |      "output_type": "execute_result"
 196 |     }
 197 |    ],
 198 |    "source": [
 199 |     "train.head()"
 200 |    ]
 201 |   },
 202 |   {
 203 |    "cell_type": "code",
 204 |    "execution_count": 6,
 205 |    "metadata": {},
 206 |    "outputs": [],
 207 |    "source": [
 208 |     "from sklearn.ensemble import RandomForestClassifier\n",
 209 |     "from sklearn.model_selection import RepeatedKFold"
 210 |    ]
 211 |   },
 212 |   {
 213 |    "cell_type": "code",
 214 |    "execution_count": null,
 215 |    "metadata": {},
 216 |    "outputs": [],
 217 |    "source": [
 218 |     "resultados = []\n",
 219 |     "kf = RepeatedKFold(n_splits=2, n_repeats=10, random_state=10)\n",
 220 |     "\n",
 221 |     "for linhas_treino, linhas_valid in kf.split(X):\n",
 222 |     "    print(\"Treino:\", linhas_treino.shape[0])\n",
 223 |     "    print(\"Valid:\", linhas_valid.shape[0])\n",
 224 |     "\n",
 225 |     "    X_treino, X_valid = X.iloc[linhas_treino], X.iloc[linhas_valid]\n",
 226 |     "    y_treino, y_valid = y.iloc[linhas_treino], y.iloc[linhas_valid]\n",
 227 |     "\n",
 228 |     "    modelo = RandomForestClassifier(n_estimators=100, n_jobs=-1, random_state=0)\n",
 229 |     "    modelo.fit(X_treino, y_treino)\n",
 230 |     "\n",
 231 |     "    p = modelo.predict(X_valid)\n",
 232 |     "\n",
 233 |     "    acc = np.mean(y_valid == p)\n",
 234 |     "    resultados.append(acc)\n",
 235 |     "    print(\"Acc:\", acc)\n",
 236 |     "    print()\n",
 237 |     "    #print(X_treino.head())\n",
 238 |     "    #print()"
 239 |    ]
 240 |   },
 241 |   {
 242 |    "cell_type": "code",
 243 |    "execution_count": 12,
 244 |    "metadata": {},
 245 |    "outputs": [
 246 |     {
 247 |      "name": "stdout",
 248 |      "output_type": "stream",
 249 |      "text": [
 250 |       "Populating the interactive namespace from numpy and matplotlib\n"
 251 |      ]
 252 |     },
 253 |     {
 254 |      "name": "stderr",
 255 |      "output_type": "stream",
 256 |      "text": [
 257 |       "/Users/mario/anaconda3/lib/python3.7/site-packages/IPython/core/magics/pylab.py:160: UserWarning: pylab import has clobbered these variables: ['test']\n",
 258 |       "`%matplotlib` prevents importing * from pylab and numpy\n",
 259 |       "  \"\\n`%matplotlib` prevents importing * from pylab and numpy\"\n"
 260 |      ]
 261 |     }
 262 |    ],
 263 |    "source": [
 264 |     "%matplotlib inline\n",
 265 |     "%pylab inline"
 266 |    ]
 267 |   },
 268 |   {
 269 |    "cell_type": "code",
 270 |    "execution_count": 14,
 271 |    "metadata": {},
 272 |    "outputs": [
 273 |     {
 274 |      "data": {
 275 |       "text/plain": [
 276 |        "0.759601451100922"
 277 |       ]
 278 |      },
 279 |      "execution_count": 14,
 280 |      "metadata": {},
 281 |      "output_type": "execute_result"
 282 |     }
 283 |    ],
 284 |    "source": [
 285 |     "np.mean(resultados)"
 286 |    ]
 287 |   },
 288 |   {
 289 |    "cell_type": "code",
 290 |    "execution_count": 13,
 291 |    "metadata": {},
 292 |    "outputs": [
 293 |     {
 294 |      "data": {
 295 |       "text/plain": [
 296 |        "(array([2., 1., 3., 6., 4., 2., 1., 0., 0., 1.]),\n",
 297 |        " array([0.73542601, 0.74165869, 0.74789137, 0.75412405, 0.76035673,\n",
 298 |        "        0.76658941, 0.77282209, 0.77905477, 0.78528745, 0.79152013,\n",
 299 |        "        0.79775281]),\n",
 300 |        " <a list of 10 Patch objects>)"
 301 |       ]
 302 |      },
 303 |      "execution_count": 13,
 304 |      "metadata": {},
 305 |      "output_type": "execute_result"
 306 |     },
 307 |     {
 308 |      "data": {
 309 |       "image/png": "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\n",
 310 |       "text/plain": [
 311 |        "<Figure size 432x288 with 1 Axes>"
 312 |       ]
 313 |      },
 314 |      "metadata": {
 315 |       "needs_background": "light"
 316 |      },
 317 |      "output_type": "display_data"
 318 |     }
 319 |    ],
 320 |    "source": [
 321 |     "pylab.hist(resultados)"
 322 |    ]
 323 |   },
 324 |   {
 325 |    "cell_type": "markdown",
 326 |    "metadata": {},
 327 |    "source": [
 328 |     "# Novas variáveis"
 329 |    ]
 330 |   },
 331 |   {
 332 |    "cell_type": "markdown",
 333 |    "metadata": {},
 334 |    "source": [
 335 |     "modelo anterior = 0.759601451100922"
 336 |    ]
 337 |   },
 338 |   {
 339 |    "cell_type": "code",
 340 |    "execution_count": 15,
 341 |    "metadata": {},
 342 |    "outputs": [
 343 |     {
 344 |      "data": {
 345 |       "text/html": [
 346 |        "<div>\n",
 347 |        "<style scoped>\n",
 348 |        "    .dataframe tbody tr th:only-of-type {\n",
 349 |        "        vertical-align: middle;\n",
 350 |        "    }\n",
 351 |        "\n",
 352 |        "    .dataframe tbody tr th {\n",
 353 |        "        vertical-align: top;\n",
 354 |        "    }\n",
 355 |        "\n",
 356 |        "    .dataframe thead th {\n",
 357 |        "        text-align: right;\n",
 358 |        "    }\n",
 359 |        "</style>\n",
 360 |        "<table border=\"1\" class=\"dataframe\">\n",
 361 |        "  <thead>\n",
 362 |        "    <tr style=\"text-align: right;\">\n",
 363 |        "      <th></th>\n",
 364 |        "      <th>PassengerId</th>\n",
 365 |        "      <th>Survived</th>\n",
 366 |        "      <th>Pclass</th>\n",
 367 |        "      <th>Name</th>\n",
 368 |        "      <th>Sex</th>\n",
 369 |        "      <th>Age</th>\n",
 370 |        "      <th>SibSp</th>\n",
 371 |        "      <th>Parch</th>\n",
 372 |        "      <th>Ticket</th>\n",
 373 |        "      <th>Fare</th>\n",
 374 |        "      <th>Cabin</th>\n",
 375 |        "      <th>Embarked</th>\n",
 376 |        "      <th>Sex_binario</th>\n",
 377 |        "    </tr>\n",
 378 |        "  </thead>\n",
 379 |        "  <tbody>\n",
 380 |        "    <tr>\n",
 381 |        "      <th>0</th>\n",
 382 |        "      <td>1</td>\n",
 383 |        "      <td>0</td>\n",
 384 |        "      <td>3</td>\n",
 385 |        "      <td>Braund, Mr. Owen Harris</td>\n",
 386 |        "      <td>male</td>\n",
 387 |        "      <td>22.0</td>\n",
 388 |        "      <td>1</td>\n",
 389 |        "      <td>0</td>\n",
 390 |        "      <td>A/5 21171</td>\n",
 391 |        "      <td>7.2500</td>\n",
 392 |        "      <td>NaN</td>\n",
 393 |        "      <td>S</td>\n",
 394 |        "      <td>0</td>\n",
 395 |        "    </tr>\n",
 396 |        "    <tr>\n",
 397 |        "      <th>1</th>\n",
 398 |        "      <td>2</td>\n",
 399 |        "      <td>1</td>\n",
 400 |        "      <td>1</td>\n",
 401 |        "      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
 402 |        "      <td>female</td>\n",
 403 |        "      <td>38.0</td>\n",
 404 |        "      <td>1</td>\n",
 405 |        "      <td>0</td>\n",
 406 |        "      <td>PC 17599</td>\n",
 407 |        "      <td>71.2833</td>\n",
 408 |        "      <td>C85</td>\n",
 409 |        "      <td>C</td>\n",
 410 |        "      <td>1</td>\n",
 411 |        "    </tr>\n",
 412 |        "    <tr>\n",
 413 |        "      <th>2</th>\n",
 414 |        "      <td>3</td>\n",
 415 |        "      <td>1</td>\n",
 416 |        "      <td>3</td>\n",
 417 |        "      <td>Heikkinen, Miss. Laina</td>\n",
 418 |        "      <td>female</td>\n",
 419 |        "      <td>26.0</td>\n",
 420 |        "      <td>0</td>\n",
 421 |        "      <td>0</td>\n",
 422 |        "      <td>STON/O2. 3101282</td>\n",
 423 |        "      <td>7.9250</td>\n",
 424 |        "      <td>NaN</td>\n",
 425 |        "      <td>S</td>\n",
 426 |        "      <td>1</td>\n",
 427 |        "    </tr>\n",
 428 |        "    <tr>\n",
 429 |        "      <th>3</th>\n",
 430 |        "      <td>4</td>\n",
 431 |        "      <td>1</td>\n",
 432 |        "      <td>1</td>\n",
 433 |        "      <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n",
 434 |        "      <td>female</td>\n",
 435 |        "      <td>35.0</td>\n",
 436 |        "      <td>1</td>\n",
 437 |        "      <td>0</td>\n",
 438 |        "      <td>113803</td>\n",
 439 |        "      <td>53.1000</td>\n",
 440 |        "      <td>C123</td>\n",
 441 |        "      <td>S</td>\n",
 442 |        "      <td>1</td>\n",
 443 |        "    </tr>\n",
 444 |        "    <tr>\n",
 445 |        "      <th>4</th>\n",
 446 |        "      <td>5</td>\n",
 447 |        "      <td>0</td>\n",
 448 |        "      <td>3</td>\n",
 449 |        "      <td>Allen, Mr. William Henry</td>\n",
 450 |        "      <td>male</td>\n",
 451 |        "      <td>35.0</td>\n",
 452 |        "      <td>0</td>\n",
 453 |        "      <td>0</td>\n",
 454 |        "      <td>373450</td>\n",
 455 |        "      <td>8.0500</td>\n",
 456 |        "      <td>NaN</td>\n",
 457 |        "      <td>S</td>\n",
 458 |        "      <td>0</td>\n",
 459 |        "    </tr>\n",
 460 |        "  </tbody>\n",
 461 |        "</table>\n",
 462 |        "</div>"
 463 |       ],
 464 |       "text/plain": [
 465 |        "   PassengerId  Survived  Pclass  \\\n",
 466 |        "0            1         0       3   \n",
 467 |        "1            2         1       1   \n",
 468 |        "2            3         1       3   \n",
 469 |        "3            4         1       1   \n",
 470 |        "4            5         0       3   \n",
 471 |        "\n",
 472 |        "                                                Name     Sex   Age  SibSp  \\\n",
 473 |        "0                            Braund, Mr. Owen Harris    male  22.0      1   \n",
 474 |        "1  Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0      1   \n",
 475 |        "2                             Heikkinen, Miss. Laina  female  26.0      0   \n",
 476 |        "3       Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0      1   \n",
 477 |        "4                           Allen, Mr. William Henry    male  35.0      0   \n",
 478 |        "\n",
 479 |        "   Parch            Ticket     Fare Cabin Embarked  Sex_binario  \n",
 480 |        "0      0         A/5 21171   7.2500   NaN        S            0  \n",
 481 |        "1      0          PC 17599  71.2833   C85        C            1  \n",
 482 |        "2      0  STON/O2. 3101282   7.9250   NaN        S            1  \n",
 483 |        "3      0            113803  53.1000  C123        S            1  \n",
 484 |        "4      0            373450   8.0500   NaN        S            0  "
 485 |       ]
 486 |      },
 487 |      "execution_count": 15,
 488 |      "metadata": {},
 489 |      "output_type": "execute_result"
 490 |     }
 491 |    ],
 492 |    "source": [
 493 |     "train.head()"
 494 |    ]
 495 |   },
 496 |   {
 497 |    "cell_type": "code",
 498 |    "execution_count": 29,
 499 |    "metadata": {},
 500 |    "outputs": [],
 501 |    "source": [
 502 |     "variaveis = ['Sex_binario', 'Age', 'Pclass', 'SibSp', 'Parch', 'Fare']"
 503 |    ]
 504 |   },
 505 |   {
 506 |    "cell_type": "code",
 507 |    "execution_count": 30,
 508 |    "metadata": {},
 509 |    "outputs": [],
 510 |    "source": [
 511 |     "X = train[variaveis].fillna(-1)\n",
 512 |     "y = train['Survived']"
 513 |    ]
 514 |   },
 515 |   {
 516 |    "cell_type": "code",
 517 |    "execution_count": 19,
 518 |    "metadata": {},
 519 |    "outputs": [
 520 |     {
 521 |      "name": "stdout",
 522 |      "output_type": "stream",
 523 |      "text": [
 524 |       "Treino: 445\n",
 525 |       "Valid: 446\n",
 526 |       "Acc: 0.7869955156950673\n",
 527 |       "\n",
 528 |       "Treino: 446\n",
 529 |       "Valid: 445\n",
 530 |       "Acc: 0.7797752808988764\n",
 531 |       "\n",
 532 |       "Treino: 445\n",
 533 |       "Valid: 446\n",
 534 |       "Acc: 0.827354260089686\n",
 535 |       "\n",
 536 |       "Treino: 446\n",
 537 |       "Valid: 445\n",
 538 |       "Acc: 0.8179775280898877\n",
 539 |       "\n",
 540 |       "Treino: 445\n",
 541 |       "Valid: 446\n",
 542 |       "Acc: 0.7847533632286996\n",
 543 |       "\n",
 544 |       "Treino: 446\n",
 545 |       "Valid: 445\n",
 546 |       "Acc: 0.7842696629213484\n",
 547 |       "\n",
 548 |       "Treino: 445\n",
 549 |       "Valid: 446\n",
 550 |       "Acc: 0.8161434977578476\n",
 551 |       "\n",
 552 |       "Treino: 446\n",
 553 |       "Valid: 445\n",
 554 |       "Acc: 0.7842696629213484\n",
 555 |       "\n",
 556 |       "Treino: 445\n",
 557 |       "Valid: 446\n",
 558 |       "Acc: 0.8004484304932735\n",
 559 |       "\n",
 560 |       "Treino: 446\n",
 561 |       "Valid: 445\n",
 562 |       "Acc: 0.8\n",
 563 |       "\n",
 564 |       "Treino: 445\n",
 565 |       "Valid: 446\n",
 566 |       "Acc: 0.8183856502242153\n",
 567 |       "\n",
 568 |       "Treino: 446\n",
 569 |       "Valid: 445\n",
 570 |       "Acc: 0.802247191011236\n",
 571 |       "\n",
 572 |       "Treino: 445\n",
 573 |       "Valid: 446\n",
 574 |       "Acc: 0.8116591928251121\n",
 575 |       "\n",
 576 |       "Treino: 446\n",
 577 |       "Valid: 445\n",
 578 |       "Acc: 0.8067415730337079\n",
 579 |       "\n",
 580 |       "Treino: 445\n",
 581 |       "Valid: 446\n",
 582 |       "Acc: 0.820627802690583\n",
 583 |       "\n",
 584 |       "Treino: 446\n",
 585 |       "Valid: 445\n",
 586 |       "Acc: 0.7887640449438202\n",
 587 |       "\n",
 588 |       "Treino: 445\n",
 589 |       "Valid: 446\n",
 590 |       "Acc: 0.8385650224215246\n",
 591 |       "\n",
 592 |       "Treino: 446\n",
 593 |       "Valid: 445\n",
 594 |       "Acc: 0.8044943820224719\n",
 595 |       "\n",
 596 |       "Treino: 445\n",
 597 |       "Valid: 446\n",
 598 |       "Acc: 0.7982062780269058\n",
 599 |       "\n",
 600 |       "Treino: 446\n",
 601 |       "Valid: 445\n",
 602 |       "Acc: 0.8112359550561797\n",
 603 |       "\n"
 604 |      ]
 605 |     }
 606 |    ],
 607 |    "source": [
 608 |     "resultados = []\n",
 609 |     "kf = RepeatedKFold(n_splits=2, n_repeats=10, random_state=10)\n",
 610 |     "\n",
 611 |     "for linhas_treino, linhas_valid in kf.split(X):\n",
 612 |     "    print(\"Treino:\", linhas_treino.shape[0])\n",
 613 |     "    print(\"Valid:\", linhas_valid.shape[0])\n",
 614 |     "\n",
 615 |     "    X_treino, X_valid = X.iloc[linhas_treino], X.iloc[linhas_valid]\n",
 616 |     "    y_treino, y_valid = y.iloc[linhas_treino], y.iloc[linhas_valid]\n",
 617 |     "\n",
 618 |     "    modelo = RandomForestClassifier(n_estimators=100, n_jobs=-1, random_state=0)\n",
 619 |     "    modelo.fit(X_treino, y_treino)\n",
 620 |     "\n",
 621 |     "    p = modelo.predict(X_valid)\n",
 622 |     "\n",
 623 |     "    acc = np.mean(y_valid == p)\n",
 624 |     "    resultados.append(acc)\n",
 625 |     "    print(\"Acc:\", acc)\n",
 626 |     "    print()\n",
 627 |     "    #print(X_treino.head())\n",
 628 |     "    #print()"
 629 |    ]
 630 |   },
 631 |   {
 632 |    "cell_type": "code",
 633 |    "execution_count": 20,
 634 |    "metadata": {},
 635 |    "outputs": [
 636 |     {
 637 |      "data": {
 638 |       "text/plain": [
 639 |        "(array([4., 2., 0., 4., 2., 2., 4., 0., 1., 1.]),\n",
 640 |        " array([0.77977528, 0.78565426, 0.79153323, 0.7974122 , 0.80329118,\n",
 641 |        "        0.80917015, 0.81504913, 0.8209281 , 0.82680707, 0.83268605,\n",
 642 |        "        0.83856502]),\n",
 643 |        " <a list of 10 Patch objects>)"
 644 |       ]
 645 |      },
 646 |      "execution_count": 20,
 647 |      "metadata": {},
 648 |      "output_type": "execute_result"
 649 |     },
 650 |     {
 651 |      "data": {
 652 |       "image/png": "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\n",
 653 |       "text/plain": [
 654 |        "<Figure size 432x288 with 1 Axes>"
 655 |       ]
 656 |      },
 657 |      "metadata": {
 658 |       "needs_background": "light"
 659 |      },
 660 |      "output_type": "display_data"
 661 |     }
 662 |    ],
 663 |    "source": [
 664 |     "pylab.hist(resultados)"
 665 |    ]
 666 |   },
 667 |   {
 668 |    "cell_type": "code",
 669 |    "execution_count": 21,
 670 |    "metadata": {},
 671 |    "outputs": [
 672 |     {
 673 |      "data": {
 674 |       "text/plain": [
 675 |        "0.8041457147175896"
 676 |       ]
 677 |      },
 678 |      "execution_count": 21,
 679 |      "metadata": {},
 680 |      "output_type": "execute_result"
 681 |     }
 682 |    ],
 683 |    "source": [
 684 |     "np.mean(resultados)"
 685 |    ]
 686 |   },
 687 |   {
 688 |    "cell_type": "markdown",
 689 |    "metadata": {},
 690 |    "source": [
 691 |     "# Retreinar o modelo"
 692 |    ]
 693 |   },
 694 |   {
 695 |    "cell_type": "code",
 696 |    "execution_count": 25,
 697 |    "metadata": {},
 698 |    "outputs": [
 699 |     {
 700 |      "data": {
 701 |       "text/html": [
 702 |        "<div>\n",
 703 |        "<style scoped>\n",
 704 |        "    .dataframe tbody tr th:only-of-type {\n",
 705 |        "        vertical-align: middle;\n",
 706 |        "    }\n",
 707 |        "\n",
 708 |        "    .dataframe tbody tr th {\n",
 709 |        "        vertical-align: top;\n",
 710 |        "    }\n",
 711 |        "\n",
 712 |        "    .dataframe thead th {\n",
 713 |        "        text-align: right;\n",
 714 |        "    }\n",
 715 |        "</style>\n",
 716 |        "<table border=\"1\" class=\"dataframe\">\n",
 717 |        "  <thead>\n",
 718 |        "    <tr style=\"text-align: right;\">\n",
 719 |        "      <th></th>\n",
 720 |        "      <th>Sex_binario</th>\n",
 721 |        "      <th>Age</th>\n",
 722 |        "      <th>Pclass</th>\n",
 723 |        "      <th>SibSp</th>\n",
 724 |        "      <th>Parch</th>\n",
 725 |        "      <th>Fare</th>\n",
 726 |        "    </tr>\n",
 727 |        "  </thead>\n",
 728 |        "  <tbody>\n",
 729 |        "    <tr>\n",
 730 |        "      <th>0</th>\n",
 731 |        "      <td>0</td>\n",
 732 |        "      <td>22.0</td>\n",
 733 |        "      <td>3</td>\n",
 734 |        "      <td>1</td>\n",
 735 |        "      <td>0</td>\n",
 736 |        "      <td>7.2500</td>\n",
 737 |        "    </tr>\n",
 738 |        "    <tr>\n",
 739 |        "      <th>1</th>\n",
 740 |        "      <td>1</td>\n",
 741 |        "      <td>38.0</td>\n",
 742 |        "      <td>1</td>\n",
 743 |        "      <td>1</td>\n",
 744 |        "      <td>0</td>\n",
 745 |        "      <td>71.2833</td>\n",
 746 |        "    </tr>\n",
 747 |        "    <tr>\n",
 748 |        "      <th>2</th>\n",
 749 |        "      <td>1</td>\n",
 750 |        "      <td>26.0</td>\n",
 751 |        "      <td>3</td>\n",
 752 |        "      <td>0</td>\n",
 753 |        "      <td>0</td>\n",
 754 |        "      <td>7.9250</td>\n",
 755 |        "    </tr>\n",
 756 |        "    <tr>\n",
 757 |        "      <th>3</th>\n",
 758 |        "      <td>1</td>\n",
 759 |        "      <td>35.0</td>\n",
 760 |        "      <td>1</td>\n",
 761 |        "      <td>1</td>\n",
 762 |        "      <td>0</td>\n",
 763 |        "      <td>53.1000</td>\n",
 764 |        "    </tr>\n",
 765 |        "    <tr>\n",
 766 |        "      <th>4</th>\n",
 767 |        "      <td>0</td>\n",
 768 |        "      <td>35.0</td>\n",
 769 |        "      <td>3</td>\n",
 770 |        "      <td>0</td>\n",
 771 |        "      <td>0</td>\n",
 772 |        "      <td>8.0500</td>\n",
 773 |        "    </tr>\n",
 774 |        "  </tbody>\n",
 775 |        "</table>\n",
 776 |        "</div>"
 777 |       ],
 778 |       "text/plain": [
 779 |        "   Sex_binario   Age  Pclass  SibSp  Parch     Fare\n",
 780 |        "0            0  22.0       3      1      0   7.2500\n",
 781 |        "1            1  38.0       1      1      0  71.2833\n",
 782 |        "2            1  26.0       3      0      0   7.9250\n",
 783 |        "3            1  35.0       1      1      0  53.1000\n",
 784 |        "4            0  35.0       3      0      0   8.0500"
 785 |       ]
 786 |      },
 787 |      "execution_count": 25,
 788 |      "metadata": {},
 789 |      "output_type": "execute_result"
 790 |     }
 791 |    ],
 792 |    "source": [
 793 |     "X.head()"
 794 |    ]
 795 |   },
 796 |   {
 797 |    "cell_type": "code",
 798 |    "execution_count": 26,
 799 |    "metadata": {},
 800 |    "outputs": [
 801 |     {
 802 |      "data": {
 803 |       "text/plain": [
 804 |        "0    0\n",
 805 |        "1    1\n",
 806 |        "2    1\n",
 807 |        "3    1\n",
 808 |        "4    0\n",
 809 |        "Name: Survived, dtype: int64"
 810 |       ]
 811 |      },
 812 |      "execution_count": 26,
 813 |      "metadata": {},
 814 |      "output_type": "execute_result"
 815 |     }
 816 |    ],
 817 |    "source": [
 818 |     "y.head()"
 819 |    ]
 820 |   },
 821 |   {
 822 |    "cell_type": "code",
 823 |    "execution_count": 31,
 824 |    "metadata": {},
 825 |    "outputs": [
 826 |     {
 827 |      "data": {
 828 |       "text/html": [
 829 |        "<div>\n",
 830 |        "<style scoped>\n",
 831 |        "    .dataframe tbody tr th:only-of-type {\n",
 832 |        "        vertical-align: middle;\n",
 833 |        "    }\n",
 834 |        "\n",
 835 |        "    .dataframe tbody tr th {\n",
 836 |        "        vertical-align: top;\n",
 837 |        "    }\n",
 838 |        "\n",
 839 |        "    .dataframe thead th {\n",
 840 |        "        text-align: right;\n",
 841 |        "    }\n",
 842 |        "</style>\n",
 843 |        "<table border=\"1\" class=\"dataframe\">\n",
 844 |        "  <thead>\n",
 845 |        "    <tr style=\"text-align: right;\">\n",
 846 |        "      <th></th>\n",
 847 |        "      <th>Sex_binario</th>\n",
 848 |        "      <th>Age</th>\n",
 849 |        "      <th>Pclass</th>\n",
 850 |        "      <th>SibSp</th>\n",
 851 |        "      <th>Parch</th>\n",
 852 |        "      <th>Fare</th>\n",
 853 |        "    </tr>\n",
 854 |        "  </thead>\n",
 855 |        "  <tbody>\n",
 856 |        "    <tr>\n",
 857 |        "      <th>0</th>\n",
 858 |        "      <td>0</td>\n",
 859 |        "      <td>34.5</td>\n",
 860 |        "      <td>3</td>\n",
 861 |        "      <td>0</td>\n",
 862 |        "      <td>0</td>\n",
 863 |        "      <td>7.8292</td>\n",
 864 |        "    </tr>\n",
 865 |        "    <tr>\n",
 866 |        "      <th>1</th>\n",
 867 |        "      <td>1</td>\n",
 868 |        "      <td>47.0</td>\n",
 869 |        "      <td>3</td>\n",
 870 |        "      <td>1</td>\n",
 871 |        "      <td>0</td>\n",
 872 |        "      <td>7.0000</td>\n",
 873 |        "    </tr>\n",
 874 |        "    <tr>\n",
 875 |        "      <th>2</th>\n",
 876 |        "      <td>0</td>\n",
 877 |        "      <td>62.0</td>\n",
 878 |        "      <td>2</td>\n",
 879 |        "      <td>0</td>\n",
 880 |        "      <td>0</td>\n",
 881 |        "      <td>9.6875</td>\n",
 882 |        "    </tr>\n",
 883 |        "    <tr>\n",
 884 |        "      <th>3</th>\n",
 885 |        "      <td>0</td>\n",
 886 |        "      <td>27.0</td>\n",
 887 |        "      <td>3</td>\n",
 888 |        "      <td>0</td>\n",
 889 |        "      <td>0</td>\n",
 890 |        "      <td>8.6625</td>\n",
 891 |        "    </tr>\n",
 892 |        "    <tr>\n",
 893 |        "      <th>4</th>\n",
 894 |        "      <td>1</td>\n",
 895 |        "      <td>22.0</td>\n",
 896 |        "      <td>3</td>\n",
 897 |        "      <td>1</td>\n",
 898 |        "      <td>1</td>\n",
 899 |        "      <td>12.2875</td>\n",
 900 |        "    </tr>\n",
 901 |        "  </tbody>\n",
 902 |        "</table>\n",
 903 |        "</div>"
 904 |       ],
 905 |       "text/plain": [
 906 |        "   Sex_binario   Age  Pclass  SibSp  Parch     Fare\n",
 907 |        "0            0  34.5       3      0      0   7.8292\n",
 908 |        "1            1  47.0       3      1      0   7.0000\n",
 909 |        "2            0  62.0       2      0      0   9.6875\n",
 910 |        "3            0  27.0       3      0      0   8.6625\n",
 911 |        "4            1  22.0       3      1      1  12.2875"
 912 |       ]
 913 |      },
 914 |      "execution_count": 31,
 915 |      "metadata": {},
 916 |      "output_type": "execute_result"
 917 |     }
 918 |    ],
 919 |    "source": [
 920 |     "test[variaveis].head()"
 921 |    ]
 922 |   },
 923 |   {
 924 |    "cell_type": "code",
 925 |    "execution_count": 32,
 926 |    "metadata": {},
 927 |    "outputs": [],
 928 |    "source": [
 929 |     "modelo = RandomForestClassifier(n_estimators=100, n_jobs=-1, random_state=0)\n",
 930 |     "modelo.fit(X, y)\n",
 931 |     "\n",
 932 |     "p = modelo.predict(test[variaveis].fillna(-1))"
 933 |    ]
 934 |   },
 935 |   {
 936 |    "cell_type": "markdown",
 937 |    "metadata": {},
 938 |    "source": [
 939 |     "## Criar submission"
 940 |    ]
 941 |   },
 942 |   {
 943 |    "cell_type": "code",
 944 |    "execution_count": 47,
 945 |    "metadata": {},
 946 |    "outputs": [
 947 |     {
 948 |      "data": {
 949 |       "text/plain": [
 950 |        "(418,)"
 951 |       ]
 952 |      },
 953 |      "execution_count": 47,
 954 |      "metadata": {},
 955 |      "output_type": "execute_result"
 956 |     }
 957 |    ],
 958 |    "source": [
 959 |     "sub = pd.Series(p, index=test['PassengerId'], name='Survived')\n",
 960 |     "sub.shape"
 961 |    ]
 962 |   },
 963 |   {
 964 |    "cell_type": "code",
 965 |    "execution_count": 48,
 966 |    "metadata": {},
 967 |    "outputs": [],
 968 |    "source": [
 969 |     "sub.to_csv(\"modelo_video5.csv\", header=True)"
 970 |    ]
 971 |   },
 972 |   {
 973 |    "cell_type": "code",
 974 |    "execution_count": 49,
 975 |    "metadata": {},
 976 |    "outputs": [
 977 |     {
 978 |      "name": "stdout",
 979 |      "output_type": "stream",
 980 |      "text": [
 981 |       "PassengerId,Survived\n",
 982 |       "892,0\n",
 983 |       "893,0\n",
 984 |       "894,1\n",
 985 |       "895,1\n",
 986 |       "896,1\n",
 987 |       "897,0\n",
 988 |       "898,0\n",
 989 |       "899,0\n",
 990 |       "900,1\n"
 991 |      ]
 992 |     }
 993 |    ],
 994 |    "source": [
 995 |     "!head -n10 modelo_video5.csv"
 996 |    ]
 997 |   },
 998 |   {
 999 |    "cell_type": "code",
1000 |    "execution_count": null,
1001 |    "metadata": {},
1002 |    "outputs": [],
1003 |    "source": []
1004 |   }
1005 |  ],
1006 |  "metadata": {
1007 |   "kernelspec": {
1008 |    "display_name": "Python 3",
1009 |    "language": "python",
1010 |    "name": "python3"
1011 |   },
1012 |   "language_info": {
1013 |    "codemirror_mode": {
1014 |     "name": "ipython",
1015 |     "version": 3
1016 |    },
1017 |    "file_extension": ".py",
1018 |    "mimetype": "text/x-python",
1019 |    "name": "python",
1020 |    "nbconvert_exporter": "python",
1021 |    "pygments_lexer": "ipython3",
1022 |    "version": "3.7.3"
1023 |   }
1024 |  },
1025 |  "nbformat": 4,
1026 |  "nbformat_minor": 4
1027 | }
1028 | 


--------------------------------------------------------------------------------