-
Notifications
You must be signed in to change notification settings - Fork 0
/
finnlp_binary_imbalanced_experiment_1.log
721 lines (516 loc) · 53 KB
/
finnlp_binary_imbalanced_experiment_1.log
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
2024-01-26 09:02:28.047 | INFO | __main__:<module>:5 -
####################################### NEW EXECUTION #######################################
2024-01-26 09:02:28.048 | INFO | __main__:<module>:6 - Processors (cores) available: 38
2024-01-26 09:02:38.261 | INFO | __main__:<module>:4 - boards_list: ['usi', 'cib', 'bb_asset', 'dimep', 'coger gesub', 'disem']
2024-01-26 09:02:38.294 | INFO | __main__:<module>:2 -
####### usi EXECUTING #######
2024-01-26 09:02:38.296 | INFO | __main__:<module>:14 - total_relevant_documents_of_the_board: 819 - usi
2024-01-26 09:02:38.302 | INFO | __main__:<module>:15 - Total irrelevant documents of the department: 4051
2024-01-26 09:02:38.304 | INFO | __main__:<module>:18 - data_relevant_board: (819, 18) - usi
2024-01-26 09:02:38.308 | INFO | __main__:<module>:39 - data_irrelevant_board: (4051, 18) - usi
2024-01-26 09:02:38.312 | INFO | __main__:<module>:47 - df_final_dataset: (4870, 18) - usi
2024-01-26 09:02:38.313 | DEBUG | __main__:<module>:50 - [+] Start cleaning text and title
2024-01-26 09:03:15.134 | DEBUG | __main__:<module>:55 - [+] End cleaning text and title
2024-01-26 09:03:15.141 | DEBUG | __main__:<module>:61 - [+] Start TF-IDF
2024-01-26 09:03:19.648 | DEBUG | __main__:<module>:65 - [+] End TF-IDF
2024-01-26 09:03:19.650 | INFO | __main__:training_each_inductor_holdout:6 -
####### random_forest INDUCTOR EXECUTING ####### - usi
2024-01-26 09:03:19.652 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: RandomForestClassifier(n_jobs=38, random_state=42) - random_forest - usi
2024-01-26 09:03:19.652 | DEBUG | __main__:training_each_inductor_holdout:9 - [+] classifiers[key]['parameters']: {'n_estimators': [100, 400, 1000], 'max_depth': [10, 30, 100], 'criterion': ['entropy', 'log_loss', 'gini']} - random_forest - usi
2024-01-26 09:03:19.653 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - random_forest - usi
2024-01-26 09:07:37.675 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - random_forest - usi
2024-01-26 09:07:37.678 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: RandomForestClassifier(max_depth=100, n_jobs=38, random_state=42)
2024-01-26 09:07:38.305 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS random_forest - usi #######
2024-01-26 09:07:38.312 | SUCCESS | __main__:training_each_inductor_holdout:33 - random_forest - usi - test_precision: 0.9469387755102041
2024-01-26 09:07:38.315 | SUCCESS | __main__:training_each_inductor_holdout:35 - random_forest - usi - test_recall: 0.7073170731707317
2024-01-26 09:07:38.319 | SUCCESS | __main__:training_each_inductor_holdout:37 - random_forest - usi - test_f1_binary: 0.8097731239092496
2024-01-26 09:07:38.322 | SUCCESS | __main__:training_each_inductor_holdout:39 - random_forest - usi - test_f1_macro: 0.8884857193425273
2024-01-26 09:07:38.322 | INFO | __main__:training_each_inductor_holdout:6 -
####### svm INDUCTOR EXECUTING ####### - usi
2024-01-26 09:07:38.323 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: SVC(random_state=42) - svm - usi
2024-01-26 09:07:38.324 | DEBUG | __main__:training_each_inductor_holdout:9 - [+] classifiers[key]['parameters']: {'C': [0.025, 0.08, 0.1, 0.5, 0.8, 1.0, 2.0, 10.0, 100.0, 500.0, 1000.0], 'kernel': ['linear', 'poly', 'rbf', 'sigmoid']} - svm - usi
2024-01-26 09:07:38.325 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - svm - usi
2024-01-26 09:14:43.895 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - svm - usi
2024-01-26 09:14:43.897 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: SVC(C=10.0, kernel='linear', random_state=42)
2024-01-26 09:14:55.266 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS svm - usi #######
2024-01-26 09:14:55.271 | SUCCESS | __main__:training_each_inductor_holdout:33 - svm - usi - test_precision: 0.8945578231292517
2024-01-26 09:14:55.274 | SUCCESS | __main__:training_each_inductor_holdout:35 - svm - usi - test_recall: 0.801829268292683
2024-01-26 09:14:55.277 | SUCCESS | __main__:training_each_inductor_holdout:37 - svm - usi - test_f1_binary: 0.8456591639871384
2024-01-26 09:14:55.280 | SUCCESS | __main__:training_each_inductor_holdout:39 - svm - usi - test_f1_macro: 0.9081686168133615
2024-01-26 09:14:55.281 | INFO | __main__:training_each_inductor_holdout:6 -
####### xgboost INDUCTOR EXECUTING ####### - usi
2024-01-26 09:14:55.283 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: XGBClassifier(base_score=None, booster=None, callbacks=None,
colsample_bylevel=None, colsample_bynode=None,
colsample_bytree=None, device=None, early_stopping_rounds=None,
enable_categorical=False, eval_metric=None, feature_types=None,
gamma=None, grow_policy=None, importance_type=None,
interaction_constraints=None, learning_rate=None, max_bin=None,
max_cat_threshold=None, max_cat_to_onehot=None,
max_delta_step=None, max_depth=None, max_leaves=None,
min_child_weight=None, missing=nan, monotone_constraints=None,
multi_strategy=None, n_estimators=None, n_jobs=38, num_class=2,
num_parallel_tree=None, ...) - xgboost - usi
2024-01-26 09:14:55.284 | DEBUG | __main__:training_each_inductor_holdout:9 - [+] classifiers[key]['parameters']: {'objective': ['reg:squarederror', 'binary:logistic', 'multi:softmax', 'binary:hinge'], 'n_estimators': [100, 1000], 'max_depth': [10, 30], 'learning_rate': [0.01, 0.5]} - xgboost - usi
2024-01-26 09:14:55.284 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - xgboost - usi
2024-01-26 15:37:26.786 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - xgboost - usi
2024-01-26 15:37:26.790 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: XGBClassifier(base_score=None, booster=None, callbacks=None,
colsample_bylevel=None, colsample_bynode=None,
colsample_bytree=None, device=None, early_stopping_rounds=None,
enable_categorical=False, eval_metric=None, feature_types=None,
gamma=None, grow_policy=None, importance_type=None,
interaction_constraints=None, learning_rate=0.5, max_bin=None,
max_cat_threshold=None, max_cat_to_onehot=None,
max_delta_step=None, max_depth=10, max_leaves=None,
min_child_weight=None, missing=nan, monotone_constraints=None,
multi_strategy=None, n_estimators=1000, n_jobs=38, num_class=2,
num_parallel_tree=None, ...)
2024-01-26 15:38:29.506 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS xgboost - usi #######
2024-01-26 15:38:29.511 | SUCCESS | __main__:training_each_inductor_holdout:33 - xgboost - usi - test_precision: 0.92578125
2024-01-26 15:38:29.514 | SUCCESS | __main__:training_each_inductor_holdout:35 - xgboost - usi - test_recall: 0.7225609756097561
2024-01-26 15:38:29.518 | SUCCESS | __main__:training_each_inductor_holdout:37 - xgboost - usi - test_f1_binary: 0.8116438356164384
2024-01-26 15:38:29.521 | SUCCESS | __main__:training_each_inductor_holdout:39 - xgboost - usi - test_f1_macro: 0.8892156376149825
2024-01-26 15:38:29.522 | INFO | __main__:training_each_inductor_holdout:6 -
####### nb INDUCTOR EXECUTING ####### - usi
2024-01-26 15:38:29.523 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: MultinomialNB() - nb - usi
2024-01-26 15:38:29.523 | DEBUG | __main__:training_each_inductor_holdout:9 - [+] classifiers[key]['parameters']: {'alpha': [1, 0.1, 0.01, 0.001, 0.0001, 1e-05], 'force_alpha': [True, False], 'fit_prior': [True, False]} - nb - usi
2024-01-26 15:38:29.524 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - nb - usi
2024-01-26 15:38:31.907 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - nb - usi
2024-01-26 15:38:31.909 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: MultinomialNB(alpha=0.1, force_alpha=True)
2024-01-26 15:38:31.944 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS nb - usi #######
2024-01-26 15:38:31.948 | SUCCESS | __main__:training_each_inductor_holdout:33 - nb - usi - test_precision: 0.941908713692946
2024-01-26 15:38:31.951 | SUCCESS | __main__:training_each_inductor_holdout:35 - nb - usi - test_recall: 0.6920731707317073
2024-01-26 15:38:31.955 | SUCCESS | __main__:training_each_inductor_holdout:37 - nb - usi - test_f1_binary: 0.797891036906854
2024-01-26 15:38:31.958 | SUCCESS | __main__:training_each_inductor_holdout:39 - nb - usi - test_f1_macro: 0.881662681062384
2024-01-26 15:38:31.960 | SUCCESS | __main__:<module>:72 -
[+][+][+] SUCCESS! [+][+][+]
2024-01-26 15:38:31.961 | INFO | __main__:<module>:2 -
####### cib EXECUTING #######
2024-01-26 15:38:31.965 | INFO | __main__:<module>:14 - total_relevant_documents_of_the_board: 688 - cib
2024-01-26 15:38:31.973 | INFO | __main__:<module>:15 - Total irrelevant documents of the department: 1790
2024-01-26 15:38:31.975 | INFO | __main__:<module>:18 - data_relevant_board: (688, 18) - cib
2024-01-26 15:38:31.979 | INFO | __main__:<module>:39 - data_irrelevant_board: (1790, 18) - cib
2024-01-26 15:38:31.998 | INFO | __main__:<module>:47 - df_final_dataset: (2478, 18) - cib
2024-01-26 15:38:31.999 | DEBUG | __main__:<module>:50 - [+] Start cleaning text and title
2024-01-26 15:39:23.197 | DEBUG | __main__:<module>:55 - [+] End cleaning text and title
2024-01-26 15:39:23.202 | DEBUG | __main__:<module>:61 - [+] Start TF-IDF
2024-01-26 15:39:28.839 | DEBUG | __main__:<module>:65 - [+] End TF-IDF
2024-01-26 15:39:28.841 | INFO | __main__:training_each_inductor_holdout:6 -
####### random_forest INDUCTOR EXECUTING ####### - cib
2024-01-26 15:39:28.842 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: RandomForestClassifier(n_jobs=38, random_state=42) - random_forest - cib
2024-01-26 15:39:28.843 | DEBUG | __main__:training_each_inductor_holdout:9 - [+] classifiers[key]['parameters']: {'n_estimators': [100, 400, 1000], 'max_depth': [10, 30, 100], 'criterion': ['entropy', 'log_loss', 'gini']} - random_forest - cib
2024-01-26 15:39:28.843 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - random_forest - cib
2024-01-26 15:43:57.403 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - random_forest - cib
2024-01-26 15:43:57.406 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: RandomForestClassifier(max_depth=100, n_estimators=400, n_jobs=38,
random_state=42)
2024-01-26 15:43:59.318 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS random_forest - cib #######
2024-01-26 15:43:59.327 | SUCCESS | __main__:training_each_inductor_holdout:33 - random_forest - cib - test_precision: 0.7732558139534884
2024-01-26 15:43:59.330 | SUCCESS | __main__:training_each_inductor_holdout:35 - random_forest - cib - test_recall: 0.48363636363636364
2024-01-26 15:43:59.334 | SUCCESS | __main__:training_each_inductor_holdout:37 - random_forest - cib - test_f1_binary: 0.5950782997762863
2024-01-26 15:43:59.337 | SUCCESS | __main__:training_each_inductor_holdout:39 - random_forest - cib - test_f1_macro: 0.7386582129980976
2024-01-26 15:43:59.337 | INFO | __main__:training_each_inductor_holdout:6 -
####### svm INDUCTOR EXECUTING ####### - cib
2024-01-26 15:43:59.338 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: SVC(random_state=42) - svm - cib
2024-01-26 15:43:59.339 | DEBUG | __main__:training_each_inductor_holdout:9 - [+] classifiers[key]['parameters']: {'C': [0.025, 0.08, 0.1, 0.5, 0.8, 1.0, 2.0, 10.0, 100.0, 500.0, 1000.0], 'kernel': ['linear', 'poly', 'rbf', 'sigmoid']} - svm - cib
2024-01-26 15:43:59.340 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - svm - cib
2024-01-26 15:47:05.372 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - svm - cib
2024-01-26 15:47:05.374 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: SVC(C=100.0, kernel='linear', random_state=42)
2024-01-26 15:47:11.242 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS svm - cib #######
2024-01-26 15:47:11.246 | SUCCESS | __main__:training_each_inductor_holdout:33 - svm - cib - test_precision: 0.6462093862815884
2024-01-26 15:47:11.249 | SUCCESS | __main__:training_each_inductor_holdout:35 - svm - cib - test_recall: 0.6509090909090909
2024-01-26 15:47:11.252 | SUCCESS | __main__:training_each_inductor_holdout:37 - svm - cib - test_f1_binary: 0.6485507246376813
2024-01-26 15:47:11.255 | SUCCESS | __main__:training_each_inductor_holdout:39 - svm - cib - test_f1_macro: 0.7565379321512429
2024-01-26 15:47:11.256 | INFO | __main__:training_each_inductor_holdout:6 -
####### xgboost INDUCTOR EXECUTING ####### - cib
2024-01-26 15:47:11.257 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: XGBClassifier(base_score=None, booster=None, callbacks=None,
colsample_bylevel=None, colsample_bynode=None,
colsample_bytree=None, device=None, early_stopping_rounds=None,
enable_categorical=False, eval_metric=None, feature_types=None,
gamma=None, grow_policy=None, importance_type=None,
interaction_constraints=None, learning_rate=None, max_bin=None,
max_cat_threshold=None, max_cat_to_onehot=None,
max_delta_step=None, max_depth=None, max_leaves=None,
min_child_weight=None, missing=nan, monotone_constraints=None,
multi_strategy=None, n_estimators=None, n_jobs=38, num_class=2,
num_parallel_tree=None, ...) - xgboost - cib
2024-01-26 15:47:11.258 | DEBUG | __main__:training_each_inductor_holdout:9 - [+] classifiers[key]['parameters']: {'objective': ['reg:squarederror', 'binary:logistic', 'multi:softmax', 'binary:hinge'], 'n_estimators': [100, 1000], 'max_depth': [10, 30], 'learning_rate': [0.01, 0.5]} - xgboost - cib
2024-01-26 15:47:11.259 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - xgboost - cib
2024-01-26 23:51:08.899 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - xgboost - cib
2024-01-26 23:51:08.903 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: XGBClassifier(base_score=None, booster=None, callbacks=None,
colsample_bylevel=None, colsample_bynode=None,
colsample_bytree=None, device=None, early_stopping_rounds=None,
enable_categorical=False, eval_metric=None, feature_types=None,
gamma=None, grow_policy=None, importance_type=None,
interaction_constraints=None, learning_rate=0.5, max_bin=None,
max_cat_threshold=None, max_cat_to_onehot=None,
max_delta_step=None, max_depth=10, max_leaves=None,
min_child_weight=None, missing=nan, monotone_constraints=None,
multi_strategy=None, n_estimators=1000, n_jobs=38, num_class=2,
num_parallel_tree=None, ...)
2024-01-26 23:52:31.508 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS xgboost - cib #######
2024-01-26 23:52:31.513 | SUCCESS | __main__:training_each_inductor_holdout:33 - xgboost - cib - test_precision: 0.7350427350427351
2024-01-26 23:52:31.516 | SUCCESS | __main__:training_each_inductor_holdout:35 - xgboost - cib - test_recall: 0.6254545454545455
2024-01-26 23:52:31.520 | SUCCESS | __main__:training_each_inductor_holdout:37 - xgboost - cib - test_f1_binary: 0.6758349705304519
2024-01-26 23:52:31.523 | SUCCESS | __main__:training_each_inductor_holdout:39 - xgboost - cib - test_f1_macro: 0.7819852818753954
2024-01-26 23:52:31.524 | INFO | __main__:training_each_inductor_holdout:6 -
####### nb INDUCTOR EXECUTING ####### - cib
2024-01-26 23:52:31.525 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: MultinomialNB() - nb - cib
2024-01-26 23:52:31.525 | DEBUG | __main__:training_each_inductor_holdout:9 - [+] classifiers[key]['parameters']: {'alpha': [1, 0.1, 0.01, 0.001, 0.0001, 1e-05], 'force_alpha': [True, False], 'fit_prior': [True, False]} - nb - cib
2024-01-26 23:52:31.526 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - nb - cib
2024-01-26 23:52:34.039 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - nb - cib
2024-01-26 23:52:34.041 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: MultinomialNB(alpha=0.001, fit_prior=False, force_alpha=True)
2024-01-26 23:52:34.071 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS nb - cib #######
2024-01-26 23:52:34.075 | SUCCESS | __main__:training_each_inductor_holdout:33 - nb - cib - test_precision: 0.5025380710659898
2024-01-26 23:52:34.079 | SUCCESS | __main__:training_each_inductor_holdout:35 - nb - cib - test_recall: 0.72
2024-01-26 23:52:34.082 | SUCCESS | __main__:training_each_inductor_holdout:37 - nb - cib - test_f1_binary: 0.5919282511210763
2024-01-26 23:52:34.085 | SUCCESS | __main__:training_each_inductor_holdout:39 - nb - cib - test_f1_macro: 0.6921618441917168
2024-01-26 23:52:34.086 | SUCCESS | __main__:<module>:72 -
[+][+][+] SUCCESS! [+][+][+]
2024-01-26 23:52:34.087 | INFO | __main__:<module>:2 -
####### bb_asset EXECUTING #######
2024-01-26 23:52:34.092 | INFO | __main__:<module>:14 - total_relevant_documents_of_the_board: 683 - bb_asset
2024-01-26 23:52:34.105 | INFO | __main__:<module>:15 - Total irrelevant documents of the department: 5234
2024-01-26 23:52:34.108 | INFO | __main__:<module>:18 - data_relevant_board: (683, 18) - bb_asset
2024-01-26 23:52:34.113 | INFO | __main__:<module>:39 - data_irrelevant_board: (5234, 18) - bb_asset
2024-01-26 23:52:34.128 | INFO | __main__:<module>:47 - df_final_dataset: (5917, 18) - bb_asset
2024-01-26 23:52:34.129 | DEBUG | __main__:<module>:50 - [+] Start cleaning text and title
2024-01-26 23:53:38.484 | DEBUG | __main__:<module>:55 - [+] End cleaning text and title
2024-01-26 23:53:38.492 | DEBUG | __main__:<module>:61 - [+] Start TF-IDF
2024-01-26 23:53:45.606 | DEBUG | __main__:<module>:65 - [+] End TF-IDF
2024-01-26 23:53:45.608 | INFO | __main__:training_each_inductor_holdout:6 -
####### random_forest INDUCTOR EXECUTING ####### - bb_asset
2024-01-26 23:53:45.610 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: RandomForestClassifier(n_jobs=38, random_state=42) - random_forest - bb_asset
2024-01-26 23:53:45.611 | DEBUG | __main__:training_each_inductor_holdout:9 - [+] classifiers[key]['parameters']: {'n_estimators': [100, 400, 1000], 'max_depth': [10, 30, 100], 'criterion': ['entropy', 'log_loss', 'gini']} - random_forest - bb_asset
2024-01-26 23:53:45.611 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - random_forest - bb_asset
2024-01-27 00:07:22.746 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - random_forest - bb_asset
2024-01-27 00:07:22.749 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: RandomForestClassifier(max_depth=100, n_jobs=38, random_state=42)
2024-01-27 00:07:23.472 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS random_forest - bb_asset #######
2024-01-27 00:07:23.479 | SUCCESS | __main__:training_each_inductor_holdout:33 - random_forest - bb_asset - test_precision: 0.680672268907563
2024-01-27 00:07:23.483 | SUCCESS | __main__:training_each_inductor_holdout:35 - random_forest - bb_asset - test_recall: 0.2967032967032967
2024-01-27 00:07:23.486 | SUCCESS | __main__:training_each_inductor_holdout:37 - random_forest - bb_asset - test_f1_binary: 0.413265306122449
2024-01-27 00:07:23.489 | SUCCESS | __main__:training_each_inductor_holdout:39 - random_forest - bb_asset - test_f1_macro: 0.6801471625038777
2024-01-27 00:07:23.490 | INFO | __main__:training_each_inductor_holdout:6 -
####### svm INDUCTOR EXECUTING ####### - bb_asset
2024-01-27 00:07:23.491 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: SVC(random_state=42) - svm - bb_asset
2024-01-27 00:07:23.492 | DEBUG | __main__:training_each_inductor_holdout:9 - [+] classifiers[key]['parameters']: {'C': [0.025, 0.08, 0.1, 0.5, 0.8, 1.0, 2.0, 10.0, 100.0, 500.0, 1000.0], 'kernel': ['linear', 'poly', 'rbf', 'sigmoid']} - svm - bb_asset
2024-01-27 00:07:23.492 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - svm - bb_asset
2024-01-27 00:16:37.348 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - svm - bb_asset
2024-01-27 00:16:37.350 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: SVC(C=2.0, kernel='linear', random_state=42)
2024-01-27 00:16:53.857 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS svm - bb_asset #######
2024-01-27 00:16:53.862 | SUCCESS | __main__:training_each_inductor_holdout:33 - svm - bb_asset - test_precision: 0.7081339712918661
2024-01-27 00:16:53.865 | SUCCESS | __main__:training_each_inductor_holdout:35 - svm - bb_asset - test_recall: 0.5421245421245421
2024-01-27 00:16:53.868 | SUCCESS | __main__:training_each_inductor_holdout:37 - svm - bb_asset - test_f1_binary: 0.6141078838174273
2024-01-27 00:16:53.871 | SUCCESS | __main__:training_each_inductor_holdout:39 - svm - bb_asset - test_f1_macro: 0.7851818817017523
2024-01-27 00:16:53.872 | INFO | __main__:training_each_inductor_holdout:6 -
####### xgboost INDUCTOR EXECUTING ####### - bb_asset
2024-01-27 00:16:53.873 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: XGBClassifier(base_score=None, booster=None, callbacks=None,
colsample_bylevel=None, colsample_bynode=None,
colsample_bytree=None, device=None, early_stopping_rounds=None,
enable_categorical=False, eval_metric=None, feature_types=None,
gamma=None, grow_policy=None, importance_type=None,
interaction_constraints=None, learning_rate=None, max_bin=None,
max_cat_threshold=None, max_cat_to_onehot=None,
max_delta_step=None, max_depth=None, max_leaves=None,
min_child_weight=None, missing=nan, monotone_constraints=None,
multi_strategy=None, n_estimators=None, n_jobs=38, num_class=2,
num_parallel_tree=None, ...) - xgboost - bb_asset
2024-01-27 00:16:53.874 | DEBUG | __main__:training_each_inductor_holdout:9 - [+] classifiers[key]['parameters']: {'objective': ['reg:squarederror', 'binary:logistic', 'multi:softmax', 'binary:hinge'], 'n_estimators': [100, 1000], 'max_depth': [10, 30], 'learning_rate': [0.01, 0.5]} - xgboost - bb_asset
2024-01-27 00:16:53.875 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - xgboost - bb_asset
2024-01-27 10:51:06.928 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - xgboost - bb_asset
2024-01-27 10:51:06.933 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: XGBClassifier(base_score=None, booster=None, callbacks=None,
colsample_bylevel=None, colsample_bynode=None,
colsample_bytree=None, device=None, early_stopping_rounds=None,
enable_categorical=False, eval_metric=None, feature_types=None,
gamma=None, grow_policy=None, importance_type=None,
interaction_constraints=None, learning_rate=0.01, max_bin=None,
max_cat_threshold=None, max_cat_to_onehot=None,
max_delta_step=None, max_depth=30, max_leaves=None,
min_child_weight=None, missing=nan, monotone_constraints=None,
multi_strategy=None, n_estimators=100, n_jobs=38, num_class=2,
num_parallel_tree=None, ...)
2024-01-27 10:52:54.176 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS xgboost - bb_asset #######
2024-01-27 10:52:54.181 | SUCCESS | __main__:training_each_inductor_holdout:33 - xgboost - bb_asset - test_precision: 0.6108597285067874
2024-01-27 10:52:54.185 | SUCCESS | __main__:training_each_inductor_holdout:35 - xgboost - bb_asset - test_recall: 0.4945054945054945
2024-01-27 10:52:54.188 | SUCCESS | __main__:training_each_inductor_holdout:37 - xgboost - bb_asset - test_f1_binary: 0.5465587044534413
2024-01-27 10:52:54.192 | SUCCESS | __main__:training_each_inductor_holdout:39 - xgboost - bb_asset - test_f1_macro: 0.7468642578870981
2024-01-27 10:52:54.193 | INFO | __main__:training_each_inductor_holdout:6 -
####### nb INDUCTOR EXECUTING ####### - bb_asset
2024-01-27 10:52:54.194 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: MultinomialNB() - nb - bb_asset
2024-01-27 10:52:54.194 | DEBUG | __main__:training_each_inductor_holdout:9 - [+] classifiers[key]['parameters']: {'alpha': [1, 0.1, 0.01, 0.001, 0.0001, 1e-05], 'force_alpha': [True, False], 'fit_prior': [True, False]} - nb - bb_asset
2024-01-27 10:52:54.195 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - nb - bb_asset
2024-01-27 10:52:56.896 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - nb - bb_asset
2024-01-27 10:52:56.899 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: MultinomialNB(alpha=0.001, force_alpha=True)
2024-01-27 10:52:56.938 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS nb - bb_asset #######
2024-01-27 10:52:56.943 | SUCCESS | __main__:training_each_inductor_holdout:33 - nb - bb_asset - test_precision: 0.5483870967741935
2024-01-27 10:52:56.947 | SUCCESS | __main__:training_each_inductor_holdout:35 - nb - bb_asset - test_recall: 0.684981684981685
2024-01-27 10:52:56.950 | SUCCESS | __main__:training_each_inductor_holdout:37 - nb - bb_asset - test_f1_binary: 0.6091205211726384
2024-01-27 10:52:56.954 | SUCCESS | __main__:training_each_inductor_holdout:39 - nb - bb_asset - test_f1_macro: 0.7754340469940861
2024-01-27 10:52:56.955 | SUCCESS | __main__:<module>:72 -
[+][+][+] SUCCESS! [+][+][+]
2024-01-27 10:52:56.956 | INFO | __main__:<module>:2 -
####### dimep EXECUTING #######
2024-01-27 10:52:56.960 | INFO | __main__:<module>:14 - total_relevant_documents_of_the_board: 600 - dimep
2024-01-27 10:52:56.972 | INFO | __main__:<module>:15 - Total irrelevant documents of the department: 3619
2024-01-27 10:52:56.974 | INFO | __main__:<module>:18 - data_relevant_board: (600, 18) - dimep
2024-01-27 10:52:56.980 | INFO | __main__:<module>:39 - data_irrelevant_board: (3619, 18) - dimep
2024-01-27 10:52:57.006 | INFO | __main__:<module>:47 - df_final_dataset: (4219, 18) - dimep
2024-01-27 10:52:57.007 | DEBUG | __main__:<module>:50 - [+] Start cleaning text and title
2024-01-27 10:53:33.395 | DEBUG | __main__:<module>:55 - [+] End cleaning text and title
2024-01-27 10:53:33.402 | DEBUG | __main__:<module>:61 - [+] Start TF-IDF
2024-01-27 10:53:37.710 | DEBUG | __main__:<module>:65 - [+] End TF-IDF
2024-01-27 10:53:37.712 | INFO | __main__:training_each_inductor_holdout:6 -
####### random_forest INDUCTOR EXECUTING ####### - dimep
2024-01-27 10:53:37.713 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: RandomForestClassifier(n_jobs=38, random_state=42) - random_forest - dimep
2024-01-27 10:53:37.715 | DEBUG | __main__:training_each_inductor_holdout:9 - [+] classifiers[key]['parameters']: {'n_estimators': [100, 400, 1000], 'max_depth': [10, 30, 100], 'criterion': ['entropy', 'log_loss', 'gini']} - random_forest - dimep
2024-01-27 10:53:37.716 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - random_forest - dimep
2024-01-27 11:13:47.310 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - random_forest - dimep
2024-01-27 11:13:47.312 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: RandomForestClassifier(max_depth=100, n_jobs=38, random_state=42)
2024-01-27 11:13:48.895 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS random_forest - dimep #######
2024-01-27 11:13:48.901 | SUCCESS | __main__:training_each_inductor_holdout:33 - random_forest - dimep - test_precision: 0.5533333333333333
2024-01-27 11:13:48.905 | SUCCESS | __main__:training_each_inductor_holdout:35 - random_forest - dimep - test_recall: 0.3458333333333333
2024-01-27 11:13:48.908 | SUCCESS | __main__:training_each_inductor_holdout:37 - random_forest - dimep - test_f1_binary: 0.4256410256410257
2024-01-27 11:13:48.911 | SUCCESS | __main__:training_each_inductor_holdout:39 - random_forest - dimep - test_f1_macro: 0.6753121404159583
2024-01-27 11:13:48.911 | INFO | __main__:training_each_inductor_holdout:6 -
####### svm INDUCTOR EXECUTING ####### - dimep
2024-01-27 11:13:48.912 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: SVC(random_state=42) - svm - dimep
2024-01-27 11:13:48.913 | DEBUG | __main__:training_each_inductor_holdout:9 - [+] classifiers[key]['parameters']: {'C': [0.025, 0.08, 0.1, 0.5, 0.8, 1.0, 2.0, 10.0, 100.0, 500.0, 1000.0], 'kernel': ['linear', 'poly', 'rbf', 'sigmoid']} - svm - dimep
2024-01-27 11:13:48.914 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - svm - dimep
2024-01-27 11:17:38.805 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - svm - dimep
2024-01-27 11:17:38.807 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: SVC(C=2.0, kernel='linear', random_state=42)
2024-01-27 11:17:46.594 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS svm - dimep #######
2024-01-27 11:17:46.599 | SUCCESS | __main__:training_each_inductor_holdout:33 - svm - dimep - test_precision: 0.6039603960396039
2024-01-27 11:17:46.602 | SUCCESS | __main__:training_each_inductor_holdout:35 - svm - dimep - test_recall: 0.5083333333333333
2024-01-27 11:17:46.606 | SUCCESS | __main__:training_each_inductor_holdout:37 - svm - dimep - test_f1_binary: 0.5520361990950226
2024-01-27 11:17:46.609 | SUCCESS | __main__:training_each_inductor_holdout:39 - svm - dimep - test_f1_macro: 0.7422757682591677
2024-01-27 11:17:46.610 | INFO | __main__:training_each_inductor_holdout:6 -
####### xgboost INDUCTOR EXECUTING ####### - dimep
2024-01-27 11:17:46.612 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: XGBClassifier(base_score=None, booster=None, callbacks=None,
colsample_bylevel=None, colsample_bynode=None,
colsample_bytree=None, device=None, early_stopping_rounds=None,
enable_categorical=False, eval_metric=None, feature_types=None,
gamma=None, grow_policy=None, importance_type=None,
interaction_constraints=None, learning_rate=None, max_bin=None,
max_cat_threshold=None, max_cat_to_onehot=None,
max_delta_step=None, max_depth=None, max_leaves=None,
min_child_weight=None, missing=nan, monotone_constraints=None,
multi_strategy=None, n_estimators=None, n_jobs=38, num_class=2,
num_parallel_tree=None, ...) - xgboost - dimep
2024-01-27 11:17:46.613 | DEBUG | __main__:training_each_inductor_holdout:9 - [+] classifiers[key]['parameters']: {'objective': ['reg:squarederror', 'binary:logistic', 'multi:softmax', 'binary:hinge'], 'n_estimators': [100, 1000], 'max_depth': [10, 30], 'learning_rate': [0.01, 0.5]} - xgboost - dimep
2024-01-27 11:17:46.614 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - xgboost - dimep
2024-01-27 22:41:37.617 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - xgboost - dimep
2024-01-27 22:41:37.621 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: XGBClassifier(base_score=None, booster=None, callbacks=None,
colsample_bylevel=None, colsample_bynode=None,
colsample_bytree=None, device=None, early_stopping_rounds=None,
enable_categorical=False, eval_metric=None, feature_types=None,
gamma=None, grow_policy=None, importance_type=None,
interaction_constraints=None, learning_rate=0.5, max_bin=None,
max_cat_threshold=None, max_cat_to_onehot=None,
max_delta_step=None, max_depth=10, max_leaves=None,
min_child_weight=None, missing=nan, monotone_constraints=None,
multi_strategy=None, n_estimators=100, n_jobs=38, num_class=2,
num_parallel_tree=None, ...)
2024-01-27 22:41:55.676 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS xgboost - dimep #######
2024-01-27 22:41:55.682 | SUCCESS | __main__:training_each_inductor_holdout:33 - xgboost - dimep - test_precision: 0.5699481865284974
2024-01-27 22:41:55.686 | SUCCESS | __main__:training_each_inductor_holdout:35 - xgboost - dimep - test_recall: 0.4583333333333333
2024-01-27 22:41:55.689 | SUCCESS | __main__:training_each_inductor_holdout:37 - xgboost - dimep - test_f1_binary: 0.5080831408775982
2024-01-27 22:41:55.692 | SUCCESS | __main__:training_each_inductor_holdout:39 - xgboost - dimep - test_f1_macro: 0.7178540067282996
2024-01-27 22:41:55.693 | INFO | __main__:training_each_inductor_holdout:6 -
####### nb INDUCTOR EXECUTING ####### - dimep
2024-01-27 22:41:55.695 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: MultinomialNB() - nb - dimep
2024-01-27 22:41:55.695 | DEBUG | __main__:training_each_inductor_holdout:9 - [+] classifiers[key]['parameters']: {'alpha': [1, 0.1, 0.01, 0.001, 0.0001, 1e-05], 'force_alpha': [True, False], 'fit_prior': [True, False]} - nb - dimep
2024-01-27 22:41:55.696 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - nb - dimep
2024-01-27 22:41:58.144 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - nb - dimep
2024-01-27 22:41:58.147 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: MultinomialNB(alpha=0.0001, fit_prior=False, force_alpha=True)
2024-01-27 22:41:58.178 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS nb - dimep #######
2024-01-27 22:41:58.182 | SUCCESS | __main__:training_each_inductor_holdout:33 - nb - dimep - test_precision: 0.40638297872340423
2024-01-27 22:41:58.186 | SUCCESS | __main__:training_each_inductor_holdout:35 - nb - dimep - test_recall: 0.7958333333333333
2024-01-27 22:41:58.190 | SUCCESS | __main__:training_each_inductor_holdout:37 - nb - dimep - test_f1_binary: 0.5380281690140845
2024-01-27 22:41:58.193 | SUCCESS | __main__:training_each_inductor_holdout:39 - nb - dimep - test_f1_macro: 0.7074987056623311
2024-01-27 22:41:58.194 | SUCCESS | __main__:<module>:72 -
[+][+][+] SUCCESS! [+][+][+]
2024-01-27 22:41:58.195 | INFO | __main__:<module>:2 -
####### coger gesub EXECUTING #######
2024-01-27 22:41:58.199 | INFO | __main__:<module>:14 - total_relevant_documents_of_the_board: 534 - coger gesub
2024-01-27 22:41:58.210 | INFO | __main__:<module>:15 - Total irrelevant documents of the department: 2594
2024-01-27 22:41:58.213 | INFO | __main__:<module>:18 - data_relevant_board: (534, 18) - coger gesub
2024-01-27 22:41:58.218 | INFO | __main__:<module>:39 - data_irrelevant_board: (2594, 18) - coger gesub
2024-01-27 22:41:58.240 | INFO | __main__:<module>:47 - df_final_dataset: (3128, 18) - coger gesub
2024-01-27 22:41:58.241 | DEBUG | __main__:<module>:50 - [+] Start cleaning text and title
2024-01-27 22:42:23.282 | DEBUG | __main__:<module>:55 - [+] End cleaning text and title
2024-01-27 22:42:23.288 | DEBUG | __main__:<module>:61 - [+] Start TF-IDF
2024-01-27 22:42:26.192 | DEBUG | __main__:<module>:65 - [+] End TF-IDF
2024-01-27 22:42:26.194 | INFO | __main__:training_each_inductor_holdout:6 -
####### random_forest INDUCTOR EXECUTING ####### - coger gesub
2024-01-27 22:42:26.195 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: RandomForestClassifier(n_jobs=38, random_state=42) - random_forest - coger gesub
2024-01-27 22:42:26.196 | DEBUG | __main__:training_each_inductor_holdout:9 - [+] classifiers[key]['parameters']: {'n_estimators': [100, 400, 1000], 'max_depth': [10, 30, 100], 'criterion': ['entropy', 'log_loss', 'gini']} - random_forest - coger gesub
2024-01-27 22:42:26.196 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - random_forest - coger gesub
2024-01-27 22:45:05.618 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - random_forest - coger gesub
2024-01-27 22:45:05.620 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: RandomForestClassifier(max_depth=100, n_jobs=38, random_state=42)
2024-01-27 22:45:06.143 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS random_forest - coger gesub #######
2024-01-27 22:45:06.149 | SUCCESS | __main__:training_each_inductor_holdout:33 - random_forest - coger gesub - test_precision: 0.810126582278481
2024-01-27 22:45:06.153 | SUCCESS | __main__:training_each_inductor_holdout:35 - random_forest - coger gesub - test_recall: 0.29906542056074764
2024-01-27 22:45:06.157 | SUCCESS | __main__:training_each_inductor_holdout:37 - random_forest - coger gesub - test_f1_binary: 0.43686006825938567
2024-01-27 22:45:06.160 | SUCCESS | __main__:training_each_inductor_holdout:39 - random_forest - coger gesub - test_f1_macro: 0.681116601293872
2024-01-27 22:45:06.160 | INFO | __main__:training_each_inductor_holdout:6 -
####### svm INDUCTOR EXECUTING ####### - coger gesub
2024-01-27 22:45:06.161 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: SVC(random_state=42) - svm - coger gesub
2024-01-27 22:45:06.162 | DEBUG | __main__:training_each_inductor_holdout:9 - [+] classifiers[key]['parameters']: {'C': [0.025, 0.08, 0.1, 0.5, 0.8, 1.0, 2.0, 10.0, 100.0, 500.0, 1000.0], 'kernel': ['linear', 'poly', 'rbf', 'sigmoid']} - svm - coger gesub
2024-01-27 22:45:06.163 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - svm - coger gesub
2024-01-27 22:48:40.812 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - svm - coger gesub
2024-01-27 22:48:40.814 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: SVC(kernel='linear', random_state=42)
2024-01-27 22:48:48.357 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS svm - coger gesub #######
2024-01-27 22:48:48.362 | SUCCESS | __main__:training_each_inductor_holdout:33 - svm - coger gesub - test_precision: 0.7685185185185185
2024-01-27 22:48:48.365 | SUCCESS | __main__:training_each_inductor_holdout:35 - svm - coger gesub - test_recall: 0.3878504672897196
2024-01-27 22:48:48.368 | SUCCESS | __main__:training_each_inductor_holdout:37 - svm - coger gesub - test_f1_binary: 0.515527950310559
2024-01-27 22:48:48.370 | SUCCESS | __main__:training_each_inductor_holdout:39 - svm - coger gesub - test_f1_macro: 0.7220169540737029
2024-01-27 22:48:48.371 | INFO | __main__:training_each_inductor_holdout:6 -
####### xgboost INDUCTOR EXECUTING ####### - coger gesub
2024-01-27 22:48:48.373 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: XGBClassifier(base_score=None, booster=None, callbacks=None,
colsample_bylevel=None, colsample_bynode=None,
colsample_bytree=None, device=None, early_stopping_rounds=None,
enable_categorical=False, eval_metric=None, feature_types=None,
gamma=None, grow_policy=None, importance_type=None,
interaction_constraints=None, learning_rate=None, max_bin=None,
max_cat_threshold=None, max_cat_to_onehot=None,
max_delta_step=None, max_depth=None, max_leaves=None,
min_child_weight=None, missing=nan, monotone_constraints=None,
multi_strategy=None, n_estimators=None, n_jobs=38, num_class=2,
num_parallel_tree=None, ...) - xgboost - coger gesub
2024-01-27 22:48:48.374 | DEBUG | __main__:training_each_inductor_holdout:9 - [+] classifiers[key]['parameters']: {'objective': ['reg:squarederror', 'binary:logistic', 'multi:softmax', 'binary:hinge'], 'n_estimators': [100, 1000], 'max_depth': [10, 30], 'learning_rate': [0.01, 0.5]} - xgboost - coger gesub
2024-01-27 22:48:48.374 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - xgboost - coger gesub
2024-01-28 05:20:16.613 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - xgboost - coger gesub
2024-01-28 05:20:16.617 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: XGBClassifier(base_score=None, booster=None, callbacks=None,
colsample_bylevel=None, colsample_bynode=None,
colsample_bytree=None, device=None, early_stopping_rounds=None,
enable_categorical=False, eval_metric=None, feature_types=None,
gamma=None, grow_policy=None, importance_type=None,
interaction_constraints=None, learning_rate=0.5, max_bin=None,
max_cat_threshold=None, max_cat_to_onehot=None,
max_delta_step=None, max_depth=10, max_leaves=None,
min_child_weight=None, missing=nan, monotone_constraints=None,
multi_strategy=None, n_estimators=100, n_jobs=38, num_class=2,
num_parallel_tree=None, ...)
2024-01-28 05:20:29.114 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS xgboost - coger gesub #######
2024-01-28 05:20:29.119 | SUCCESS | __main__:training_each_inductor_holdout:33 - xgboost - coger gesub - test_precision: 0.6423357664233577
2024-01-28 05:20:29.122 | SUCCESS | __main__:training_each_inductor_holdout:35 - xgboost - coger gesub - test_recall: 0.411214953271028
2024-01-28 05:20:29.125 | SUCCESS | __main__:training_each_inductor_holdout:37 - xgboost - coger gesub - test_f1_binary: 0.5014245014245013
2024-01-28 05:20:29.128 | SUCCESS | __main__:training_each_inductor_holdout:39 - xgboost - coger gesub - test_f1_macro: 0.7100712846184282
2024-01-28 05:20:29.129 | INFO | __main__:training_each_inductor_holdout:6 -
####### nb INDUCTOR EXECUTING ####### - coger gesub
2024-01-28 05:20:29.130 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: MultinomialNB() - nb - coger gesub
2024-01-28 05:20:29.130 | DEBUG | __main__:training_each_inductor_holdout:9 - [+] classifiers[key]['parameters']: {'alpha': [1, 0.1, 0.01, 0.001, 0.0001, 1e-05], 'force_alpha': [True, False], 'fit_prior': [True, False]} - nb - coger gesub
2024-01-28 05:20:29.131 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - nb - coger gesub
2024-01-28 05:20:31.589 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - nb - coger gesub
2024-01-28 05:20:31.591 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: MultinomialNB(alpha=0.01, force_alpha=True)
2024-01-28 05:20:31.622 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS nb - coger gesub #######
2024-01-28 05:20:31.627 | SUCCESS | __main__:training_each_inductor_holdout:33 - nb - coger gesub - test_precision: 0.5367965367965368
2024-01-28 05:20:31.630 | SUCCESS | __main__:training_each_inductor_holdout:35 - nb - coger gesub - test_recall: 0.5794392523364486
2024-01-28 05:20:31.634 | SUCCESS | __main__:training_each_inductor_holdout:37 - nb - coger gesub - test_f1_binary: 0.5573033707865169
2024-01-28 05:20:31.637 | SUCCESS | __main__:training_each_inductor_holdout:39 - nb - coger gesub - test_f1_macro: 0.7308129287152594
2024-01-28 05:20:31.638 | SUCCESS | __main__:<module>:72 -
[+][+][+] SUCCESS! [+][+][+]
2024-01-28 05:20:31.639 | INFO | __main__:<module>:2 -
####### disem EXECUTING #######
2024-01-28 05:20:31.643 | INFO | __main__:<module>:14 - total_relevant_documents_of_the_board: 439 - disem
2024-01-28 05:20:31.652 | INFO | __main__:<module>:15 - Total irrelevant documents of the department: 1558
2024-01-28 05:20:31.655 | INFO | __main__:<module>:18 - data_relevant_board: (439, 18) - disem
2024-01-28 05:20:31.660 | INFO | __main__:<module>:39 - data_irrelevant_board: (1558, 18) - disem
2024-01-28 05:20:31.678 | INFO | __main__:<module>:47 - df_final_dataset: (1997, 18) - disem
2024-01-28 05:20:31.678 | DEBUG | __main__:<module>:50 - [+] Start cleaning text and title
2024-01-28 05:20:56.880 | DEBUG | __main__:<module>:55 - [+] End cleaning text and title
2024-01-28 05:20:56.887 | DEBUG | __main__:<module>:61 - [+] Start TF-IDF
2024-01-28 05:20:59.984 | DEBUG | __main__:<module>:65 - [+] End TF-IDF
2024-01-28 05:20:59.986 | INFO | __main__:training_each_inductor_holdout:6 -
####### random_forest INDUCTOR EXECUTING ####### - disem
2024-01-28 05:20:59.987 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: RandomForestClassifier(n_jobs=38, random_state=42) - random_forest - disem
2024-01-28 05:20:59.989 | DEBUG | __main__:training_each_inductor_holdout:9 - [+] classifiers[key]['parameters']: {'n_estimators': [100, 400, 1000], 'max_depth': [10, 30, 100], 'criterion': ['entropy', 'log_loss', 'gini']} - random_forest - disem
2024-01-28 05:20:59.990 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - random_forest - disem
2024-01-28 05:26:16.963 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - random_forest - disem
2024-01-28 05:26:16.966 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: RandomForestClassifier(criterion='entropy', max_depth=100, n_jobs=38,
random_state=42)
2024-01-28 05:26:17.539 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS random_forest - disem #######
2024-01-28 05:26:17.547 | SUCCESS | __main__:training_each_inductor_holdout:33 - random_forest - disem - test_precision: 0.6804123711340206
2024-01-28 05:26:17.550 | SUCCESS | __main__:training_each_inductor_holdout:35 - random_forest - disem - test_recall: 0.375
2024-01-28 05:26:17.553 | SUCCESS | __main__:training_each_inductor_holdout:37 - random_forest - disem - test_f1_binary: 0.48351648351648346
2024-01-28 05:26:17.556 | SUCCESS | __main__:training_each_inductor_holdout:39 - random_forest - disem - test_f1_macro: 0.6885506945884304
2024-01-28 05:26:17.557 | INFO | __main__:training_each_inductor_holdout:6 -
####### svm INDUCTOR EXECUTING ####### - disem
2024-01-28 05:26:17.558 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: SVC(random_state=42) - svm - disem
2024-01-28 05:26:17.559 | DEBUG | __main__:training_each_inductor_holdout:9 - [+] classifiers[key]['parameters']: {'C': [0.025, 0.08, 0.1, 0.5, 0.8, 1.0, 2.0, 10.0, 100.0, 500.0, 1000.0], 'kernel': ['linear', 'poly', 'rbf', 'sigmoid']} - svm - disem
2024-01-28 05:26:17.559 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - svm - disem
2024-01-28 05:27:48.162 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - svm - disem
2024-01-28 05:27:48.164 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: SVC(C=10.0, kernel='sigmoid', random_state=42)
2024-01-28 05:27:51.162 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS svm - disem #######
2024-01-28 05:27:51.166 | SUCCESS | __main__:training_each_inductor_holdout:33 - svm - disem - test_precision: 0.6692913385826772
2024-01-28 05:27:51.169 | SUCCESS | __main__:training_each_inductor_holdout:35 - svm - disem - test_recall: 0.48295454545454547
2024-01-28 05:27:51.172 | SUCCESS | __main__:training_each_inductor_holdout:37 - svm - disem - test_f1_binary: 0.5610561056105611
2024-01-28 05:27:51.175 | SUCCESS | __main__:training_each_inductor_holdout:39 - svm - disem - test_f1_macro: 0.7291767014539292
2024-01-28 05:27:51.176 | INFO | __main__:training_each_inductor_holdout:6 -
####### xgboost INDUCTOR EXECUTING ####### - disem
2024-01-28 05:27:51.177 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: XGBClassifier(base_score=None, booster=None, callbacks=None,
colsample_bylevel=None, colsample_bynode=None,
colsample_bytree=None, device=None, early_stopping_rounds=None,
enable_categorical=False, eval_metric=None, feature_types=None,
gamma=None, grow_policy=None, importance_type=None,
interaction_constraints=None, learning_rate=None, max_bin=None,
max_cat_threshold=None, max_cat_to_onehot=None,
max_delta_step=None, max_depth=None, max_leaves=None,
min_child_weight=None, missing=nan, monotone_constraints=None,
multi_strategy=None, n_estimators=None, n_jobs=38, num_class=2,
num_parallel_tree=None, ...) - xgboost - disem
2024-01-28 05:27:51.178 | DEBUG | __main__:training_each_inductor_holdout:9 - [+] classifiers[key]['parameters']: {'objective': ['reg:squarederror', 'binary:logistic', 'multi:softmax', 'binary:hinge'], 'n_estimators': [100, 1000], 'max_depth': [10, 30], 'learning_rate': [0.01, 0.5]} - xgboost - disem
2024-01-28 05:27:51.179 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - xgboost - disem
2024-01-28 14:11:02.057 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - xgboost - disem
2024-01-28 14:11:02.061 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: XGBClassifier(base_score=None, booster=None, callbacks=None,
colsample_bylevel=None, colsample_bynode=None,
colsample_bytree=None, device=None, early_stopping_rounds=None,
enable_categorical=False, eval_metric=None, feature_types=None,
gamma=None, grow_policy=None, importance_type=None,
interaction_constraints=None, learning_rate=0.5, max_bin=None,
max_cat_threshold=None, max_cat_to_onehot=None,
max_delta_step=None, max_depth=10, max_leaves=None,
min_child_weight=None, missing=nan, monotone_constraints=None,
multi_strategy=None, n_estimators=100, n_jobs=38, num_class=2,
num_parallel_tree=None, ...)
2024-01-28 14:11:10.615 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS xgboost - disem #######
2024-01-28 14:11:10.622 | SUCCESS | __main__:training_each_inductor_holdout:33 - xgboost - disem - test_precision: 0.6610169491525424
2024-01-28 14:11:10.626 | SUCCESS | __main__:training_each_inductor_holdout:35 - xgboost - disem - test_recall: 0.4431818181818182
2024-01-28 14:11:10.630 | SUCCESS | __main__:training_each_inductor_holdout:37 - xgboost - disem - test_f1_binary: 0.5306122448979592
2024-01-28 14:11:10.633 | SUCCESS | __main__:training_each_inductor_holdout:39 - xgboost - disem - test_f1_macro: 0.7123920120195317
2024-01-28 14:11:10.634 | INFO | __main__:training_each_inductor_holdout:6 -
####### nb INDUCTOR EXECUTING ####### - disem
2024-01-28 14:11:10.634 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: MultinomialNB() - nb - disem
2024-01-28 14:11:10.635 | DEBUG | __main__:training_each_inductor_holdout:9 - [+] classifiers[key]['parameters']: {'alpha': [1, 0.1, 0.01, 0.001, 0.0001, 1e-05], 'force_alpha': [True, False], 'fit_prior': [True, False]} - nb - disem
2024-01-28 14:11:10.636 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - nb - disem
2024-01-28 14:11:13.102 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - nb - disem
2024-01-28 14:11:13.104 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: MultinomialNB(alpha=0.01, fit_prior=False, force_alpha=True)
2024-01-28 14:11:13.128 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS nb - disem #######
2024-01-28 14:11:13.132 | SUCCESS | __main__:training_each_inductor_holdout:33 - nb - disem - test_precision: 0.5234375
2024-01-28 14:11:13.135 | SUCCESS | __main__:training_each_inductor_holdout:35 - nb - disem - test_recall: 0.7613636363636364
2024-01-28 14:11:13.139 | SUCCESS | __main__:training_each_inductor_holdout:37 - nb - disem - test_f1_binary: 0.6203703703703703
2024-01-28 14:11:13.142 | SUCCESS | __main__:training_each_inductor_holdout:39 - nb - disem - test_f1_macro: 0.7398592846706054
2024-01-28 14:11:13.143 | SUCCESS | __main__:<module>:72 -
[+][+][+] SUCCESS! [+][+][+]