Hugging Face's logo

Riyan00b
/
Test

Joblib
Model card Files
xet
Community
Riyan00b commited on
Commit
02d1a41
·
verified ·
1 Parent(s): 27c30d3

Upload 4 files

Browse files
Files changed (4) hide show
  1. Ensemble ML.ipynb +1198 -0
  2. app.py +41 -0
  3. model.joblib +3 -0
  4. requirements.txt +4 -0
Ensemble ML.ipynb ADDED
@@ -0,0 +1,1198 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": 1,
6
+ "id": "d114e576",
7
+ "metadata": {},
8
+ "outputs": [],
9
+ "source": [
10
+ "import seaborn as sns\n",
11
+ "\n",
12
+ "df = sns.load_dataset('titanic')"
13
+ ]
14
+ },
15
+ {
16
+ "cell_type": "code",
17
+ "execution_count": 2,
18
+ "id": "62e20e15",
19
+ "metadata": {},
20
+ "outputs": [
21
+ {
22
+ "data": {
23
+ "text/html": [
24
+ "<div>\n",
25
+ "<style scoped>\n",
26
+ " .dataframe tbody tr th:only-of-type {\n",
27
+ " vertical-align: middle;\n",
28
+ " }\n",
29
+ "\n",
30
+ " .dataframe tbody tr th {\n",
31
+ " vertical-align: top;\n",
32
+ " }\n",
33
+ "\n",
34
+ " .dataframe thead th {\n",
35
+ " text-align: right;\n",
36
+ " }\n",
37
+ "</style>\n",
38
+ "<table border=\"1\" class=\"dataframe\">\n",
39
+ " <thead>\n",
40
+ " <tr style=\"text-align: right;\">\n",
41
+ " <th></th>\n",
42
+ " <th>survived</th>\n",
43
+ " <th>pclass</th>\n",
44
+ " <th>sex</th>\n",
45
+ " <th>age</th>\n",
46
+ " <th>sibsp</th>\n",
47
+ " <th>parch</th>\n",
48
+ " <th>fare</th>\n",
49
+ " <th>embarked</th>\n",
50
+ " <th>class</th>\n",
51
+ " <th>who</th>\n",
52
+ " <th>adult_male</th>\n",
53
+ " <th>deck</th>\n",
54
+ " <th>embark_town</th>\n",
55
+ " <th>alive</th>\n",
56
+ " <th>alone</th>\n",
57
+ " </tr>\n",
58
+ " </thead>\n",
59
+ " <tbody>\n",
60
+ " <tr>\n",
61
+ " <th>0</th>\n",
62
+ " <td>0</td>\n",
63
+ " <td>3</td>\n",
64
+ " <td>male</td>\n",
65
+ " <td>22.0</td>\n",
66
+ " <td>1</td>\n",
67
+ " <td>0</td>\n",
68
+ " <td>7.2500</td>\n",
69
+ " <td>S</td>\n",
70
+ " <td>Third</td>\n",
71
+ " <td>man</td>\n",
72
+ " <td>True</td>\n",
73
+ " <td>NaN</td>\n",
74
+ " <td>Southampton</td>\n",
75
+ " <td>no</td>\n",
76
+ " <td>False</td>\n",
77
+ " </tr>\n",
78
+ " <tr>\n",
79
+ " <th>1</th>\n",
80
+ " <td>1</td>\n",
81
+ " <td>1</td>\n",
82
+ " <td>female</td>\n",
83
+ " <td>38.0</td>\n",
84
+ " <td>1</td>\n",
85
+ " <td>0</td>\n",
86
+ " <td>71.2833</td>\n",
87
+ " <td>C</td>\n",
88
+ " <td>First</td>\n",
89
+ " <td>woman</td>\n",
90
+ " <td>False</td>\n",
91
+ " <td>C</td>\n",
92
+ " <td>Cherbourg</td>\n",
93
+ " <td>yes</td>\n",
94
+ " <td>False</td>\n",
95
+ " </tr>\n",
96
+ " <tr>\n",
97
+ " <th>2</th>\n",
98
+ " <td>1</td>\n",
99
+ " <td>3</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>7.9250</td>\n",
105
+ " <td>S</td>\n",
106
+ " <td>Third</td>\n",
107
+ " <td>woman</td>\n",
108
+ " <td>False</td>\n",
109
+ " <td>NaN</td>\n",
110
+ " <td>Southampton</td>\n",
111
+ " <td>yes</td>\n",
112
+ " <td>True</td>\n",
113
+ " </tr>\n",
114
+ " <tr>\n",
115
+ " <th>3</th>\n",
116
+ " <td>1</td>\n",
117
+ " <td>1</td>\n",
118
+ " <td>female</td>\n",
119
+ " <td>35.0</td>\n",
120
+ " <td>1</td>\n",
121
+ " <td>0</td>\n",
122
+ " <td>53.1000</td>\n",
123
+ " <td>S</td>\n",
124
+ " <td>First</td>\n",
125
+ " <td>woman</td>\n",
126
+ " <td>False</td>\n",
127
+ " <td>C</td>\n",
128
+ " <td>Southampton</td>\n",
129
+ " <td>yes</td>\n",
130
+ " <td>False</td>\n",
131
+ " </tr>\n",
132
+ " <tr>\n",
133
+ " <th>4</th>\n",
134
+ " <td>0</td>\n",
135
+ " <td>3</td>\n",
136
+ " <td>male</td>\n",
137
+ " <td>35.0</td>\n",
138
+ " <td>0</td>\n",
139
+ " <td>0</td>\n",
140
+ " <td>8.0500</td>\n",
141
+ " <td>S</td>\n",
142
+ " <td>Third</td>\n",
143
+ " <td>man</td>\n",
144
+ " <td>True</td>\n",
145
+ " <td>NaN</td>\n",
146
+ " <td>Southampton</td>\n",
147
+ " <td>no</td>\n",
148
+ " <td>True</td>\n",
149
+ " </tr>\n",
150
+ " <tr>\n",
151
+ " <th>...</th>\n",
152
+ " <td>...</td>\n",
153
+ " <td>...</td>\n",
154
+ " <td>...</td>\n",
155
+ " <td>...</td>\n",
156
+ " <td>...</td>\n",
157
+ " <td>...</td>\n",
158
+ " <td>...</td>\n",
159
+ " <td>...</td>\n",
160
+ " <td>...</td>\n",
161
+ " <td>...</td>\n",
162
+ " <td>...</td>\n",
163
+ " <td>...</td>\n",
164
+ " <td>...</td>\n",
165
+ " <td>...</td>\n",
166
+ " <td>...</td>\n",
167
+ " </tr>\n",
168
+ " <tr>\n",
169
+ " <th>886</th>\n",
170
+ " <td>0</td>\n",
171
+ " <td>2</td>\n",
172
+ " <td>male</td>\n",
173
+ " <td>27.0</td>\n",
174
+ " <td>0</td>\n",
175
+ " <td>0</td>\n",
176
+ " <td>13.0000</td>\n",
177
+ " <td>S</td>\n",
178
+ " <td>Second</td>\n",
179
+ " <td>man</td>\n",
180
+ " <td>True</td>\n",
181
+ " <td>NaN</td>\n",
182
+ " <td>Southampton</td>\n",
183
+ " <td>no</td>\n",
184
+ " <td>True</td>\n",
185
+ " </tr>\n",
186
+ " <tr>\n",
187
+ " <th>887</th>\n",
188
+ " <td>1</td>\n",
189
+ " <td>1</td>\n",
190
+ " <td>female</td>\n",
191
+ " <td>19.0</td>\n",
192
+ " <td>0</td>\n",
193
+ " <td>0</td>\n",
194
+ " <td>30.0000</td>\n",
195
+ " <td>S</td>\n",
196
+ " <td>First</td>\n",
197
+ " <td>woman</td>\n",
198
+ " <td>False</td>\n",
199
+ " <td>B</td>\n",
200
+ " <td>Southampton</td>\n",
201
+ " <td>yes</td>\n",
202
+ " <td>True</td>\n",
203
+ " </tr>\n",
204
+ " <tr>\n",
205
+ " <th>888</th>\n",
206
+ " <td>0</td>\n",
207
+ " <td>3</td>\n",
208
+ " <td>female</td>\n",
209
+ " <td>NaN</td>\n",
210
+ " <td>1</td>\n",
211
+ " <td>2</td>\n",
212
+ " <td>23.4500</td>\n",
213
+ " <td>S</td>\n",
214
+ " <td>Third</td>\n",
215
+ " <td>woman</td>\n",
216
+ " <td>False</td>\n",
217
+ " <td>NaN</td>\n",
218
+ " <td>Southampton</td>\n",
219
+ " <td>no</td>\n",
220
+ " <td>False</td>\n",
221
+ " </tr>\n",
222
+ " <tr>\n",
223
+ " <th>889</th>\n",
224
+ " <td>1</td>\n",
225
+ " <td>1</td>\n",
226
+ " <td>male</td>\n",
227
+ " <td>26.0</td>\n",
228
+ " <td>0</td>\n",
229
+ " <td>0</td>\n",
230
+ " <td>30.0000</td>\n",
231
+ " <td>C</td>\n",
232
+ " <td>First</td>\n",
233
+ " <td>man</td>\n",
234
+ " <td>True</td>\n",
235
+ " <td>C</td>\n",
236
+ " <td>Cherbourg</td>\n",
237
+ " <td>yes</td>\n",
238
+ " <td>True</td>\n",
239
+ " </tr>\n",
240
+ " <tr>\n",
241
+ " <th>890</th>\n",
242
+ " <td>0</td>\n",
243
+ " <td>3</td>\n",
244
+ " <td>male</td>\n",
245
+ " <td>32.0</td>\n",
246
+ " <td>0</td>\n",
247
+ " <td>0</td>\n",
248
+ " <td>7.7500</td>\n",
249
+ " <td>Q</td>\n",
250
+ " <td>Third</td>\n",
251
+ " <td>man</td>\n",
252
+ " <td>True</td>\n",
253
+ " <td>NaN</td>\n",
254
+ " <td>Queenstown</td>\n",
255
+ " <td>no</td>\n",
256
+ " <td>True</td>\n",
257
+ " </tr>\n",
258
+ " </tbody>\n",
259
+ "</table>\n",
260
+ "<p>891 rows × 15 columns</p>\n",
261
+ "</div>"
262
+ ],
263
+ "text/plain": [
264
+ " survived pclass sex age sibsp parch fare embarked class \\\n",
265
+ "0 0 3 male 22.0 1 0 7.2500 S Third \n",
266
+ "1 1 1 female 38.0 1 0 71.2833 C First \n",
267
+ "2 1 3 female 26.0 0 0 7.9250 S Third \n",
268
+ "3 1 1 female 35.0 1 0 53.1000 S First \n",
269
+ "4 0 3 male 35.0 0 0 8.0500 S Third \n",
270
+ ".. ... ... ... ... ... ... ... ... ... \n",
271
+ "886 0 2 male 27.0 0 0 13.0000 S Second \n",
272
+ "887 1 1 female 19.0 0 0 30.0000 S First \n",
273
+ "888 0 3 female NaN 1 2 23.4500 S Third \n",
274
+ "889 1 1 male 26.0 0 0 30.0000 C First \n",
275
+ "890 0 3 male 32.0 0 0 7.7500 Q Third \n",
276
+ "\n",
277
+ " who adult_male deck embark_town alive alone \n",
278
+ "0 man True NaN Southampton no False \n",
279
+ "1 woman False C Cherbourg yes False \n",
280
+ "2 woman False NaN Southampton yes True \n",
281
+ "3 woman False C Southampton yes False \n",
282
+ "4 man True NaN Southampton no True \n",
283
+ ".. ... ... ... ... ... ... \n",
284
+ "886 man True NaN Southampton no True \n",
285
+ "887 woman False B Southampton yes True \n",
286
+ "888 woman False NaN Southampton no False \n",
287
+ "889 man True C Cherbourg yes True \n",
288
+ "890 man True NaN Queenstown no True \n",
289
+ "\n",
290
+ "[891 rows x 15 columns]"
291
+ ]
292
+ },
293
+ "execution_count": 2,
294
+ "metadata": {},
295
+ "output_type": "execute_result"
296
+ }
297
+ ],
298
+ "source": [
299
+ "df"
300
+ ]
301
+ },
302
+ {
303
+ "cell_type": "code",
304
+ "execution_count": 3,
305
+ "id": "0e8d87f9",
306
+ "metadata": {},
307
+ "outputs": [
308
+ {
309
+ "data": {
310
+ "text/plain": [
311
+ "Index(['survived', 'pclass', 'sex', 'age', 'sibsp', 'parch', 'fare',\n",
312
+ " 'embarked', 'class', 'who', 'adult_male', 'deck', 'embark_town',\n",
313
+ " 'alive', 'alone'],\n",
314
+ " dtype='object')"
315
+ ]
316
+ },
317
+ "execution_count": 3,
318
+ "metadata": {},
319
+ "output_type": "execute_result"
320
+ }
321
+ ],
322
+ "source": [
323
+ "df.columns"
324
+ ]
325
+ },
326
+ {
327
+ "cell_type": "code",
328
+ "execution_count": 4,
329
+ "id": "53c30023",
330
+ "metadata": {},
331
+ "outputs": [
332
+ {
333
+ "data": {
334
+ "text/html": [
335
+ "<div>\n",
336
+ "<style scoped>\n",
337
+ " .dataframe tbody tr th:only-of-type {\n",
338
+ " vertical-align: middle;\n",
339
+ " }\n",
340
+ "\n",
341
+ " .dataframe tbody tr th {\n",
342
+ " vertical-align: top;\n",
343
+ " }\n",
344
+ "\n",
345
+ " .dataframe thead th {\n",
346
+ " text-align: right;\n",
347
+ " }\n",
348
+ "</style>\n",
349
+ "<table border=\"1\" class=\"dataframe\">\n",
350
+ " <thead>\n",
351
+ " <tr style=\"text-align: right;\">\n",
352
+ " <th></th>\n",
353
+ " <th>survived</th>\n",
354
+ " <th>pclass</th>\n",
355
+ " <th>sex</th>\n",
356
+ " <th>age</th>\n",
357
+ " <th>parch</th>\n",
358
+ " <th>fare</th>\n",
359
+ " </tr>\n",
360
+ " </thead>\n",
361
+ " <tbody>\n",
362
+ " <tr>\n",
363
+ " <th>0</th>\n",
364
+ " <td>0</td>\n",
365
+ " <td>3</td>\n",
366
+ " <td>male</td>\n",
367
+ " <td>22.0</td>\n",
368
+ " <td>0</td>\n",
369
+ " <td>7.2500</td>\n",
370
+ " </tr>\n",
371
+ " <tr>\n",
372
+ " <th>1</th>\n",
373
+ " <td>1</td>\n",
374
+ " <td>1</td>\n",
375
+ " <td>female</td>\n",
376
+ " <td>38.0</td>\n",
377
+ " <td>0</td>\n",
378
+ " <td>71.2833</td>\n",
379
+ " </tr>\n",
380
+ " <tr>\n",
381
+ " <th>2</th>\n",
382
+ " <td>1</td>\n",
383
+ " <td>3</td>\n",
384
+ " <td>female</td>\n",
385
+ " <td>26.0</td>\n",
386
+ " <td>0</td>\n",
387
+ " <td>7.9250</td>\n",
388
+ " </tr>\n",
389
+ " <tr>\n",
390
+ " <th>3</th>\n",
391
+ " <td>1</td>\n",
392
+ " <td>1</td>\n",
393
+ " <td>female</td>\n",
394
+ " <td>35.0</td>\n",
395
+ " <td>0</td>\n",
396
+ " <td>53.1000</td>\n",
397
+ " </tr>\n",
398
+ " <tr>\n",
399
+ " <th>4</th>\n",
400
+ " <td>0</td>\n",
401
+ " <td>3</td>\n",
402
+ " <td>male</td>\n",
403
+ " <td>35.0</td>\n",
404
+ " <td>0</td>\n",
405
+ " <td>8.0500</td>\n",
406
+ " </tr>\n",
407
+ " <tr>\n",
408
+ " <th>...</th>\n",
409
+ " <td>...</td>\n",
410
+ " <td>...</td>\n",
411
+ " <td>...</td>\n",
412
+ " <td>...</td>\n",
413
+ " <td>...</td>\n",
414
+ " <td>...</td>\n",
415
+ " </tr>\n",
416
+ " <tr>\n",
417
+ " <th>886</th>\n",
418
+ " <td>0</td>\n",
419
+ " <td>2</td>\n",
420
+ " <td>male</td>\n",
421
+ " <td>27.0</td>\n",
422
+ " <td>0</td>\n",
423
+ " <td>13.0000</td>\n",
424
+ " </tr>\n",
425
+ " <tr>\n",
426
+ " <th>887</th>\n",
427
+ " <td>1</td>\n",
428
+ " <td>1</td>\n",
429
+ " <td>female</td>\n",
430
+ " <td>19.0</td>\n",
431
+ " <td>0</td>\n",
432
+ " <td>30.0000</td>\n",
433
+ " </tr>\n",
434
+ " <tr>\n",
435
+ " <th>888</th>\n",
436
+ " <td>0</td>\n",
437
+ " <td>3</td>\n",
438
+ " <td>female</td>\n",
439
+ " <td>NaN</td>\n",
440
+ " <td>2</td>\n",
441
+ " <td>23.4500</td>\n",
442
+ " </tr>\n",
443
+ " <tr>\n",
444
+ " <th>889</th>\n",
445
+ " <td>1</td>\n",
446
+ " <td>1</td>\n",
447
+ " <td>male</td>\n",
448
+ " <td>26.0</td>\n",
449
+ " <td>0</td>\n",
450
+ " <td>30.0000</td>\n",
451
+ " </tr>\n",
452
+ " <tr>\n",
453
+ " <th>890</th>\n",
454
+ " <td>0</td>\n",
455
+ " <td>3</td>\n",
456
+ " <td>male</td>\n",
457
+ " <td>32.0</td>\n",
458
+ " <td>0</td>\n",
459
+ " <td>7.7500</td>\n",
460
+ " </tr>\n",
461
+ " </tbody>\n",
462
+ "</table>\n",
463
+ "<p>891 rows × 6 columns</p>\n",
464
+ "</div>"
465
+ ],
466
+ "text/plain": [
467
+ " survived pclass sex age parch fare\n",
468
+ "0 0 3 male 22.0 0 7.2500\n",
469
+ "1 1 1 female 38.0 0 71.2833\n",
470
+ "2 1 3 female 26.0 0 7.9250\n",
471
+ "3 1 1 female 35.0 0 53.1000\n",
472
+ "4 0 3 male 35.0 0 8.0500\n",
473
+ ".. ... ... ... ... ... ...\n",
474
+ "886 0 2 male 27.0 0 13.0000\n",
475
+ "887 1 1 female 19.0 0 30.0000\n",
476
+ "888 0 3 female NaN 2 23.4500\n",
477
+ "889 1 1 male 26.0 0 30.0000\n",
478
+ "890 0 3 male 32.0 0 7.7500\n",
479
+ "\n",
480
+ "[891 rows x 6 columns]"
481
+ ]
482
+ },
483
+ "execution_count": 4,
484
+ "metadata": {},
485
+ "output_type": "execute_result"
486
+ }
487
+ ],
488
+ "source": [
489
+ "df = df.drop(columns=['who', 'adult_male','alive','sibsp','alone','embark_town','embarked','deck','class'])\n",
490
+ "\n",
491
+ "df"
492
+ ]
493
+ },
494
+ {
495
+ "cell_type": "code",
496
+ "execution_count": 5,
497
+ "id": "3223a012",
498
+ "metadata": {},
499
+ "outputs": [
500
+ {
501
+ "data": {
502
+ "text/plain": [
503
+ "array(['male', 'female'], dtype=object)"
504
+ ]
505
+ },
506
+ "execution_count": 5,
507
+ "metadata": {},
508
+ "output_type": "execute_result"
509
+ }
510
+ ],
511
+ "source": [
512
+ "df['sex'].unique()"
513
+ ]
514
+ },
515
+ {
516
+ "cell_type": "code",
517
+ "execution_count": 6,
518
+ "id": "d86ef363",
519
+ "metadata": {},
520
+ "outputs": [
521
+ {
522
+ "data": {
523
+ "text/html": [
524
+ "<div>\n",
525
+ "<style scoped>\n",
526
+ " .dataframe tbody tr th:only-of-type {\n",
527
+ " vertical-align: middle;\n",
528
+ " }\n",
529
+ "\n",
530
+ " .dataframe tbody tr th {\n",
531
+ " vertical-align: top;\n",
532
+ " }\n",
533
+ "\n",
534
+ " .dataframe thead th {\n",
535
+ " text-align: right;\n",
536
+ " }\n",
537
+ "</style>\n",
538
+ "<table border=\"1\" class=\"dataframe\">\n",
539
+ " <thead>\n",
540
+ " <tr style=\"text-align: right;\">\n",
541
+ " <th></th>\n",
542
+ " <th>survived</th>\n",
543
+ " <th>pclass</th>\n",
544
+ " <th>sex</th>\n",
545
+ " <th>age</th>\n",
546
+ " <th>parch</th>\n",
547
+ " <th>fare</th>\n",
548
+ " </tr>\n",
549
+ " </thead>\n",
550
+ " <tbody>\n",
551
+ " <tr>\n",
552
+ " <th>0</th>\n",
553
+ " <td>0</td>\n",
554
+ " <td>3</td>\n",
555
+ " <td>0</td>\n",
556
+ " <td>22.0</td>\n",
557
+ " <td>0</td>\n",
558
+ " <td>7.2500</td>\n",
559
+ " </tr>\n",
560
+ " <tr>\n",
561
+ " <th>1</th>\n",
562
+ " <td>1</td>\n",
563
+ " <td>1</td>\n",
564
+ " <td>1</td>\n",
565
+ " <td>38.0</td>\n",
566
+ " <td>0</td>\n",
567
+ " <td>71.2833</td>\n",
568
+ " </tr>\n",
569
+ " <tr>\n",
570
+ " <th>2</th>\n",
571
+ " <td>1</td>\n",
572
+ " <td>3</td>\n",
573
+ " <td>1</td>\n",
574
+ " <td>26.0</td>\n",
575
+ " <td>0</td>\n",
576
+ " <td>7.9250</td>\n",
577
+ " </tr>\n",
578
+ " <tr>\n",
579
+ " <th>3</th>\n",
580
+ " <td>1</td>\n",
581
+ " <td>1</td>\n",
582
+ " <td>1</td>\n",
583
+ " <td>35.0</td>\n",
584
+ " <td>0</td>\n",
585
+ " <td>53.1000</td>\n",
586
+ " </tr>\n",
587
+ " <tr>\n",
588
+ " <th>4</th>\n",
589
+ " <td>0</td>\n",
590
+ " <td>3</td>\n",
591
+ " <td>0</td>\n",
592
+ " <td>35.0</td>\n",
593
+ " <td>0</td>\n",
594
+ " <td>8.0500</td>\n",
595
+ " </tr>\n",
596
+ " <tr>\n",
597
+ " <th>...</th>\n",
598
+ " <td>...</td>\n",
599
+ " <td>...</td>\n",
600
+ " <td>...</td>\n",
601
+ " <td>...</td>\n",
602
+ " <td>...</td>\n",
603
+ " <td>...</td>\n",
604
+ " </tr>\n",
605
+ " <tr>\n",
606
+ " <th>886</th>\n",
607
+ " <td>0</td>\n",
608
+ " <td>2</td>\n",
609
+ " <td>0</td>\n",
610
+ " <td>27.0</td>\n",
611
+ " <td>0</td>\n",
612
+ " <td>13.0000</td>\n",
613
+ " </tr>\n",
614
+ " <tr>\n",
615
+ " <th>887</th>\n",
616
+ " <td>1</td>\n",
617
+ " <td>1</td>\n",
618
+ " <td>1</td>\n",
619
+ " <td>19.0</td>\n",
620
+ " <td>0</td>\n",
621
+ " <td>30.0000</td>\n",
622
+ " </tr>\n",
623
+ " <tr>\n",
624
+ " <th>888</th>\n",
625
+ " <td>0</td>\n",
626
+ " <td>3</td>\n",
627
+ " <td>1</td>\n",
628
+ " <td>NaN</td>\n",
629
+ " <td>2</td>\n",
630
+ " <td>23.4500</td>\n",
631
+ " </tr>\n",
632
+ " <tr>\n",
633
+ " <th>889</th>\n",
634
+ " <td>1</td>\n",
635
+ " <td>1</td>\n",
636
+ " <td>0</td>\n",
637
+ " <td>26.0</td>\n",
638
+ " <td>0</td>\n",
639
+ " <td>30.0000</td>\n",
640
+ " </tr>\n",
641
+ " <tr>\n",
642
+ " <th>890</th>\n",
643
+ " <td>0</td>\n",
644
+ " <td>3</td>\n",
645
+ " <td>0</td>\n",
646
+ " <td>32.0</td>\n",
647
+ " <td>0</td>\n",
648
+ " <td>7.7500</td>\n",
649
+ " </tr>\n",
650
+ " </tbody>\n",
651
+ "</table>\n",
652
+ "<p>891 rows × 6 columns</p>\n",
653
+ "</div>"
654
+ ],
655
+ "text/plain": [
656
+ " survived pclass sex age parch fare\n",
657
+ "0 0 3 0 22.0 0 7.2500\n",
658
+ "1 1 1 1 38.0 0 71.2833\n",
659
+ "2 1 3 1 26.0 0 7.9250\n",
660
+ "3 1 1 1 35.0 0 53.1000\n",
661
+ "4 0 3 0 35.0 0 8.0500\n",
662
+ ".. ... ... ... ... ... ...\n",
663
+ "886 0 2 0 27.0 0 13.0000\n",
664
+ "887 1 1 1 19.0 0 30.0000\n",
665
+ "888 0 3 1 NaN 2 23.4500\n",
666
+ "889 1 1 0 26.0 0 30.0000\n",
667
+ "890 0 3 0 32.0 0 7.7500\n",
668
+ "\n",
669
+ "[891 rows x 6 columns]"
670
+ ]
671
+ },
672
+ "execution_count": 6,
673
+ "metadata": {},
674
+ "output_type": "execute_result"
675
+ }
676
+ ],
677
+ "source": [
678
+ "df['sex'] = df['sex'].map({'male':0,'female':1})\n",
679
+ "\n",
680
+ "df"
681
+ ]
682
+ },
683
+ {
684
+ "cell_type": "code",
685
+ "execution_count": 7,
686
+ "id": "c4e3253f",
687
+ "metadata": {},
688
+ "outputs": [
689
+ {
690
+ "data": {
691
+ "text/plain": [
692
+ "survived 0\n",
693
+ "pclass 0\n",
694
+ "sex 0\n",
695
+ "age 177\n",
696
+ "parch 0\n",
697
+ "fare 0\n",
698
+ "dtype: int64"
699
+ ]
700
+ },
701
+ "execution_count": 7,
702
+ "metadata": {},
703
+ "output_type": "execute_result"
704
+ }
705
+ ],
706
+ "source": [
707
+ "df.isnull().sum()"
708
+ ]
709
+ },
710
+ {
711
+ "cell_type": "code",
712
+ "execution_count": 8,
713
+ "id": "6329f3d8",
714
+ "metadata": {},
715
+ "outputs": [
716
+ {
717
+ "data": {
718
+ "text/plain": [
719
+ "count 714.000000\n",
720
+ "mean 29.699118\n",
721
+ "std 14.526497\n",
722
+ "min 0.420000\n",
723
+ "25% 20.125000\n",
724
+ "50% 28.000000\n",
725
+ "75% 38.000000\n",
726
+ "max 80.000000\n",
727
+ "Name: age, dtype: float64"
728
+ ]
729
+ },
730
+ "execution_count": 8,
731
+ "metadata": {},
732
+ "output_type": "execute_result"
733
+ }
734
+ ],
735
+ "source": [
736
+ "df['age'].describe()"
737
+ ]
738
+ },
739
+ {
740
+ "cell_type": "code",
741
+ "execution_count": 9,
742
+ "id": "8fe71869",
743
+ "metadata": {},
744
+ "outputs": [
745
+ {
746
+ "data": {
747
+ "text/plain": [
748
+ "28.0"
749
+ ]
750
+ },
751
+ "execution_count": 9,
752
+ "metadata": {},
753
+ "output_type": "execute_result"
754
+ }
755
+ ],
756
+ "source": [
757
+ "df['age'].median()"
758
+ ]
759
+ },
760
+ {
761
+ "cell_type": "code",
762
+ "execution_count": 10,
763
+ "id": "ff80b834",
764
+ "metadata": {},
765
+ "outputs": [
766
+ {
767
+ "data": {
768
+ "text/plain": [
769
+ "survived 0\n",
770
+ "pclass 0\n",
771
+ "sex 0\n",
772
+ "age 0\n",
773
+ "parch 0\n",
774
+ "fare 0\n",
775
+ "dtype: int64"
776
+ ]
777
+ },
778
+ "execution_count": 10,
779
+ "metadata": {},
780
+ "output_type": "execute_result"
781
+ }
782
+ ],
783
+ "source": [
784
+ "df['age'] = df['age'].fillna(30)\n",
785
+ "\n",
786
+ "df.isnull().sum()"
787
+ ]
788
+ },
789
+ {
790
+ "cell_type": "code",
791
+ "execution_count": 11,
792
+ "id": "a1920396",
793
+ "metadata": {},
794
+ "outputs": [],
795
+ "source": [
796
+ "x = df.drop(columns=['survived']) #features\n",
797
+ "\n",
798
+ "y = df['survived'] #target"
799
+ ]
800
+ },
801
+ {
802
+ "cell_type": "code",
803
+ "execution_count": 12,
804
+ "id": "a04b824d",
805
+ "metadata": {},
806
+ "outputs": [],
807
+ "source": [
808
+ "# importing ensemble model"
809
+ ]
810
+ },
811
+ {
812
+ "cell_type": "code",
813
+ "execution_count": 13,
814
+ "id": "ce1742de",
815
+ "metadata": {},
816
+ "outputs": [],
817
+ "source": [
818
+ "from sklearn.ensemble import RandomForestClassifier"
819
+ ]
820
+ },
821
+ {
822
+ "cell_type": "code",
823
+ "execution_count": 14,
824
+ "id": "5d4b0678",
825
+ "metadata": {},
826
+ "outputs": [],
827
+ "source": [
828
+ "from sklearn.model_selection import train_test_split"
829
+ ]
830
+ },
831
+ {
832
+ "cell_type": "code",
833
+ "execution_count": 15,
834
+ "id": "e0dec475",
835
+ "metadata": {},
836
+ "outputs": [],
837
+ "source": [
838
+ "x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.2,random_state=42)"
839
+ ]
840
+ },
841
+ {
842
+ "cell_type": "code",
843
+ "execution_count": 24,
844
+ "id": "205ddbfe",
845
+ "metadata": {},
846
+ "outputs": [
847
+ {
848
+ "data": {
849
+ "text/html": [
850
+ "<div>\n",
851
+ "<style scoped>\n",
852
+ " .dataframe tbody tr th:only-of-type {\n",
853
+ " vertical-align: middle;\n",
854
+ " }\n",
855
+ "\n",
856
+ " .dataframe tbody tr th {\n",
857
+ " vertical-align: top;\n",
858
+ " }\n",
859
+ "\n",
860
+ " .dataframe thead th {\n",
861
+ " text-align: right;\n",
862
+ " }\n",
863
+ "</style>\n",
864
+ "<table border=\"1\" class=\"dataframe\">\n",
865
+ " <thead>\n",
866
+ " <tr style=\"text-align: right;\">\n",
867
+ " <th></th>\n",
868
+ " <th>pclass</th>\n",
869
+ " <th>sex</th>\n",
870
+ " <th>age</th>\n",
871
+ " <th>parch</th>\n",
872
+ " <th>fare</th>\n",
873
+ " </tr>\n",
874
+ " </thead>\n",
875
+ " <tbody>\n",
876
+ " <tr>\n",
877
+ " <th>331</th>\n",
878
+ " <td>1</td>\n",
879
+ " <td>0</td>\n",
880
+ " <td>45.5</td>\n",
881
+ " <td>0</td>\n",
882
+ " <td>28.5000</td>\n",
883
+ " </tr>\n",
884
+ " <tr>\n",
885
+ " <th>733</th>\n",
886
+ " <td>2</td>\n",
887
+ " <td>0</td>\n",
888
+ " <td>23.0</td>\n",
889
+ " <td>0</td>\n",
890
+ " <td>13.0000</td>\n",
891
+ " </tr>\n",
892
+ " <tr>\n",
893
+ " <th>382</th>\n",
894
+ " <td>3</td>\n",
895
+ " <td>0</td>\n",
896
+ " <td>32.0</td>\n",
897
+ " <td>0</td>\n",
898
+ " <td>7.9250</td>\n",
899
+ " </tr>\n",
900
+ " <tr>\n",
901
+ " <th>704</th>\n",
902
+ " <td>3</td>\n",
903
+ " <td>0</td>\n",
904
+ " <td>26.0</td>\n",
905
+ " <td>0</td>\n",
906
+ " <td>7.8542</td>\n",
907
+ " </tr>\n",
908
+ " <tr>\n",
909
+ " <th>813</th>\n",
910
+ " <td>3</td>\n",
911
+ " <td>1</td>\n",
912
+ " <td>6.0</td>\n",
913
+ " <td>2</td>\n",
914
+ " <td>31.2750</td>\n",
915
+ " </tr>\n",
916
+ " <tr>\n",
917
+ " <th>...</th>\n",
918
+ " <td>...</td>\n",
919
+ " <td>...</td>\n",
920
+ " <td>...</td>\n",
921
+ " <td>...</td>\n",
922
+ " <td>...</td>\n",
923
+ " </tr>\n",
924
+ " <tr>\n",
925
+ " <th>106</th>\n",
926
+ " <td>3</td>\n",
927
+ " <td>1</td>\n",
928
+ " <td>21.0</td>\n",
929
+ " <td>0</td>\n",
930
+ " <td>7.6500</td>\n",
931
+ " </tr>\n",
932
+ " <tr>\n",
933
+ " <th>270</th>\n",
934
+ " <td>1</td>\n",
935
+ " <td>0</td>\n",
936
+ " <td>30.0</td>\n",
937
+ " <td>0</td>\n",
938
+ " <td>31.0000</td>\n",
939
+ " </tr>\n",
940
+ " <tr>\n",
941
+ " <th>860</th>\n",
942
+ " <td>3</td>\n",
943
+ " <td>0</td>\n",
944
+ " <td>41.0</td>\n",
945
+ " <td>0</td>\n",
946
+ " <td>14.1083</td>\n",
947
+ " </tr>\n",
948
+ " <tr>\n",
949
+ " <th>435</th>\n",
950
+ " <td>1</td>\n",
951
+ " <td>1</td>\n",
952
+ " <td>14.0</td>\n",
953
+ " <td>2</td>\n",
954
+ " <td>120.0000</td>\n",
955
+ " </tr>\n",
956
+ " <tr>\n",
957
+ " <th>102</th>\n",
958
+ " <td>1</td>\n",
959
+ " <td>0</td>\n",
960
+ " <td>21.0</td>\n",
961
+ " <td>1</td>\n",
962
+ " <td>77.2875</td>\n",
963
+ " </tr>\n",
964
+ " </tbody>\n",
965
+ "</table>\n",
966
+ "<p>712 rows × 5 columns</p>\n",
967
+ "</div>"
968
+ ],
969
+ "text/plain": [
970
+ " pclass sex age parch fare\n",
971
+ "331 1 0 45.5 0 28.5000\n",
972
+ "733 2 0 23.0 0 13.0000\n",
973
+ "382 3 0 32.0 0 7.9250\n",
974
+ "704 3 0 26.0 0 7.8542\n",
975
+ "813 3 1 6.0 2 31.2750\n",
976
+ ".. ... ... ... ... ...\n",
977
+ "106 3 1 21.0 0 7.6500\n",
978
+ "270 1 0 30.0 0 31.0000\n",
979
+ "860 3 0 41.0 0 14.1083\n",
980
+ "435 1 1 14.0 2 120.0000\n",
981
+ "102 1 0 21.0 1 77.2875\n",
982
+ "\n",
983
+ "[712 rows x 5 columns]"
984
+ ]
985
+ },
986
+ "execution_count": 24,
987
+ "metadata": {},
988
+ "output_type": "execute_result"
989
+ }
990
+ ],
991
+ "source": [
992
+ "x_train"
993
+ ]
994
+ },
995
+ {
996
+ "cell_type": "raw",
997
+ "id": "4c79ec9f",
998
+ "metadata": {},
999
+ "source": [
1000
+ "len(x_train)"
1001
+ ]
1002
+ },
1003
+ {
1004
+ "cell_type": "code",
1005
+ "execution_count": 17,
1006
+ "id": "36a7215d",
1007
+ "metadata": {},
1008
+ "outputs": [
1009
+ {
1010
+ "data": {
1011
+ "text/plain": [
1012
+ "179"
1013
+ ]
1014
+ },
1015
+ "execution_count": 17,
1016
+ "metadata": {},
1017
+ "output_type": "execute_result"
1018
+ }
1019
+ ],
1020
+ "source": [
1021
+ "len(x_test)"
1022
+ ]
1023
+ },
1024
+ {
1025
+ "cell_type": "code",
1026
+ "execution_count": 18,
1027
+ "id": "d67f0925",
1028
+ "metadata": {},
1029
+ "outputs": [
1030
+ {
1031
+ "data": {
1032
+ "text/html": [
1033
+ "<style>#sk-container-id-1 {color: black;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestClassifier(max_depth=7, n_estimators=50, random_state=42)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestClassifier</label><div class=\"sk-toggleable__content\"><pre>RandomForestClassifier(max_depth=7, n_estimators=50, random_state=42)</pre></div></div></div></div></div>"
1034
+ ],
1035
+ "text/plain": [
1036
+ "RandomForestClassifier(max_depth=7, n_estimators=50, random_state=42)"
1037
+ ]
1038
+ },
1039
+ "execution_count": 18,
1040
+ "metadata": {},
1041
+ "output_type": "execute_result"
1042
+ }
1043
+ ],
1044
+ "source": [
1045
+ "rf = RandomForestClassifier(n_estimators=50,random_state=42,max_depth=7)\n",
1046
+ "\n",
1047
+ "rf.fit(x_train,y_train)"
1048
+ ]
1049
+ },
1050
+ {
1051
+ "cell_type": "markdown",
1052
+ "id": "e7d6c68c",
1053
+ "metadata": {},
1054
+ "source": [
1055
+ "- n_estimators: number of trees\n",
1056
+ "- random_state: fixing the selection\n",
1057
+ "- max_depth: tree depth (level)"
1058
+ ]
1059
+ },
1060
+ {
1061
+ "cell_type": "code",
1062
+ "execution_count": 19,
1063
+ "id": "0a9b3ca8",
1064
+ "metadata": {},
1065
+ "outputs": [],
1066
+ "source": [
1067
+ "y_pred = rf.predict(x_test)"
1068
+ ]
1069
+ },
1070
+ {
1071
+ "cell_type": "code",
1072
+ "execution_count": 20,
1073
+ "id": "6f63656d",
1074
+ "metadata": {},
1075
+ "outputs": [],
1076
+ "source": [
1077
+ "from sklearn.metrics import classification_report"
1078
+ ]
1079
+ },
1080
+ {
1081
+ "cell_type": "code",
1082
+ "execution_count": 21,
1083
+ "id": "ce9e2bd6",
1084
+ "metadata": {},
1085
+ "outputs": [
1086
+ {
1087
+ "name": "stdout",
1088
+ "output_type": "stream",
1089
+ "text": [
1090
+ " precision recall f1-score support\n",
1091
+ "\n",
1092
+ " 0 0.79 0.90 0.84 105\n",
1093
+ " 1 0.82 0.66 0.73 74\n",
1094
+ "\n",
1095
+ " accuracy 0.80 179\n",
1096
+ " macro avg 0.80 0.78 0.79 179\n",
1097
+ "weighted avg 0.80 0.80 0.79 179\n",
1098
+ "\n"
1099
+ ]
1100
+ }
1101
+ ],
1102
+ "source": [
1103
+ "cr = classification_report(y_test,y_pred)\n",
1104
+ "\n",
1105
+ "print(cr)"
1106
+ ]
1107
+ },
1108
+ {
1109
+ "cell_type": "code",
1110
+ "execution_count": 22,
1111
+ "id": "0897a811",
1112
+ "metadata": {},
1113
+ "outputs": [],
1114
+ "source": [
1115
+ "from joblib import dump"
1116
+ ]
1117
+ },
1118
+ {
1119
+ "cell_type": "code",
1120
+ "execution_count": 23,
1121
+ "id": "0c4a3032",
1122
+ "metadata": {},
1123
+ "outputs": [
1124
+ {
1125
+ "data": {
1126
+ "text/plain": [
1127
+ "['model.joblib']"
1128
+ ]
1129
+ },
1130
+ "execution_count": 23,
1131
+ "metadata": {},
1132
+ "output_type": "execute_result"
1133
+ }
1134
+ ],
1135
+ "source": [
1136
+ "dump(rf,\"model.joblib\")"
1137
+ ]
1138
+ },
1139
+ {
1140
+ "cell_type": "code",
1141
+ "execution_count": 25,
1142
+ "id": "920011aa",
1143
+ "metadata": {},
1144
+ "outputs": [
1145
+ {
1146
+ "name": "stderr",
1147
+ "output_type": "stream",
1148
+ "text": [
1149
+ "C:\\Users\\uwais\\anaconda3\\Lib\\site-packages\\sklearn\\base.py:465: UserWarning: X does not have valid feature names, but RandomForestClassifier was fitted with feature names\n",
1150
+ " warnings.warn(\n"
1151
+ ]
1152
+ },
1153
+ {
1154
+ "data": {
1155
+ "text/plain": [
1156
+ "array([0], dtype=int64)"
1157
+ ]
1158
+ },
1159
+ "execution_count": 25,
1160
+ "metadata": {},
1161
+ "output_type": "execute_result"
1162
+ }
1163
+ ],
1164
+ "source": [
1165
+ "rf.predict([[1,0,45,2,120]])"
1166
+ ]
1167
+ },
1168
+ {
1169
+ "cell_type": "code",
1170
+ "execution_count": null,
1171
+ "id": "0504f1f2",
1172
+ "metadata": {},
1173
+ "outputs": [],
1174
+ "source": []
1175
+ }
1176
+ ],
1177
+ "metadata": {
1178
+ "kernelspec": {
1179
+ "display_name": "Python 3 (ipykernel)",
1180
+ "language": "python",
1181
+ "name": "python3"
1182
+ },
1183
+ "language_info": {
1184
+ "codemirror_mode": {
1185
+ "name": "ipython",
1186
+ "version": 3
1187
+ },
1188
+ "file_extension": ".py",
1189
+ "mimetype": "text/x-python",
1190
+ "name": "python",
1191
+ "nbconvert_exporter": "python",
1192
+ "pygments_lexer": "ipython3",
1193
+ "version": "3.11.5"
1194
+ }
1195
+ },
1196
+ "nbformat": 4,
1197
+ "nbformat_minor": 5
1198
+ }
app.py ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python
2
+ # coding: utf-8
3
+
4
+ # In[3]:
5
+
6
+
7
+ # !pip install gradio
8
+ import gradio as gr
9
+ from joblib import load
10
+
11
+ model = load("model.joblib")
12
+
13
+ def prediction(pclass,sex,age,parch,fare):
14
+
15
+ inp = [[pclass,sex,age,parch,fare]]
16
+
17
+ pre = model.predict(inp)[0]
18
+
19
+ return "Alive" if pre==1 else "Dead"
20
+
21
+
22
+ iface = gr.Interface(
23
+ fn = prediction,
24
+ inputs = [gr.Number(label="Passenger Class"),
25
+ gr.Number(label="Gender (0:Male,1:Female)"),
26
+ gr.Number(label="Age"),
27
+ gr.Number(label="No. of People"),
28
+ gr.Number(label="Fare")],
29
+
30
+ outputs = "text",
31
+ title = "Survival Possibility",
32
+ description = "This is a calculator which tells you the Alive/Dead possibility.")
33
+
34
+ iface.launch()
35
+
36
+
37
+ # In[ ]:
38
+
39
+
40
+
41
+
model.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c2eaa610e62e62f4e7a5e73dbfd010955204cdb2cdbb4282294b6ae980992b8
3
+ size 424137
requirements.txt ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ joblib
2
+ gradio
3
+ pandas
4
+ scikit-learn