-
Notifications
You must be signed in to change notification settings - Fork 0
/
finnlp_binary_undersampling_experiment_1.log
724 lines (519 loc) · 53.1 KB
/
finnlp_binary_undersampling_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
722
723
724
2024-02-14 16:17:07.786 | INFO | __main__:<module>:5 -
####################################### NEW EXECUTION #######################################
2024-02-14 16:17:07.787 | INFO | __main__:<module>:6 - Processors (cores) available: 38
2024-02-14 16:17:18.469 | INFO | __main__:<module>:4 - boards_list: ['usi', 'cib', 'bb_asset', 'dimep', 'coger gesub', 'disem']
2024-02-14 16:17:18.502 | INFO | __main__:<module>:2 -
####### usi EXECUTING #######
2024-02-14 16:17:18.505 | INFO | __main__:<module>:14 - total_relevant_documents_of_the_board: 819 - usi
2024-02-14 16:17:18.511 | INFO | __main__:<module>:15 - Total irrelevant documents of the department: 4051
2024-02-14 16:17:18.513 | INFO | __main__:<module>:18 - data_relevant_board: (819, 18) - usi
2024-02-14 16:17:18.518 | INFO | __main__:<module>:39 - data_irrelevant_board: (819, 18) - usi
2024-02-14 16:17:18.522 | INFO | __main__:<module>:47 - df_final_dataset: (1638, 18) - usi
2024-02-14 16:17:18.522 | DEBUG | __main__:<module>:50 - [+] Start cleaning text and title
2024-02-14 16:17:27.096 | DEBUG | __main__:<module>:55 - [+] End cleaning text and title
2024-02-14 16:17:27.100 | DEBUG | __main__:<module>:61 - [+] Start TF-IDF
2024-02-14 16:17:28.110 | DEBUG | __main__:<module>:65 - [+] End TF-IDF
2024-02-14 16:17:28.112 | INFO | __main__:training_each_inductor_holdout:6 -
####### random_forest INDUCTOR EXECUTING ####### - usi
2024-02-14 16:17:28.114 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: RandomForestClassifier(n_jobs=38, random_state=42) - random_forest - usi
2024-02-14 16:17:28.115 | 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
2024-02-14 16:17:28.115 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - random_forest - usi
2024-02-14 16:19:25.906 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - random_forest - usi
2024-02-14 16:19:25.909 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: RandomForestClassifier(max_depth=100, n_jobs=38, random_state=42)
2024-02-14 16:19:26.310 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS random_forest - usi #######
2024-02-14 16:19:26.317 | SUCCESS | __main__:training_each_inductor_holdout:33 - random_forest - usi - test_precision: 0.9724409448818898
2024-02-14 16:19:26.320 | SUCCESS | __main__:training_each_inductor_holdout:35 - random_forest - usi - test_recall: 0.7530487804878049
2024-02-14 16:19:26.324 | SUCCESS | __main__:training_each_inductor_holdout:37 - random_forest - usi - test_f1_binary: 0.8487972508591065
2024-02-14 16:19:26.327 | SUCCESS | __main__:training_each_inductor_holdout:39 - random_forest - usi - test_f1_macro: 0.8641246528268136
2024-02-14 16:19:26.327 | INFO | __main__:training_each_inductor_holdout:6 -
####### svm INDUCTOR EXECUTING ####### - usi
2024-02-14 16:19:26.329 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: SVC(random_state=42) - svm - usi
2024-02-14 16:19:26.330 | 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
2024-02-14 16:19:26.330 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - svm - usi
2024-02-14 16:20:28.234 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - svm - usi
2024-02-14 16:20:28.236 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: SVC(C=100.0, kernel='linear', random_state=42)
2024-02-14 16:20:30.808 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS svm - usi #######
2024-02-14 16:20:30.812 | SUCCESS | __main__:training_each_inductor_holdout:33 - svm - usi - test_precision: 0.9075907590759076
2024-02-14 16:20:30.816 | SUCCESS | __main__:training_each_inductor_holdout:35 - svm - usi - test_recall: 0.8384146341463414
2024-02-14 16:20:30.819 | SUCCESS | __main__:training_each_inductor_holdout:37 - svm - usi - test_f1_binary: 0.8716323296354992
2024-02-14 16:20:30.822 | SUCCESS | __main__:training_each_inductor_holdout:39 - svm - usi - test_f1_macro: 0.876344799178983
2024-02-14 16:20:30.823 | INFO | __main__:training_each_inductor_holdout:6 -
####### xgboost INDUCTOR EXECUTING ####### - usi
2024-02-14 16:20:30.825 | 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
2024-02-14 16:20:30.826 | 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
2024-02-14 16:20:30.827 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - xgboost - usi
2024-02-14 21:32:54.679 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - xgboost - usi
2024-02-14 21:32:54.683 | 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, ...)
2024-02-14 21:33:00.713 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS xgboost - usi #######
2024-02-14 21:33:00.718 | SUCCESS | __main__:training_each_inductor_holdout:33 - xgboost - usi - test_precision: 0.9543859649122807
2024-02-14 21:33:00.721 | SUCCESS | __main__:training_each_inductor_holdout:35 - xgboost - usi - test_recall: 0.8292682926829268
2024-02-14 21:33:00.724 | SUCCESS | __main__:training_each_inductor_holdout:37 - xgboost - usi - test_f1_binary: 0.8874388254486134
2024-02-14 21:33:00.727 | SUCCESS | __main__:training_each_inductor_holdout:39 - xgboost - usi - test_f1_macro: 0.894363189548341
2024-02-14 21:33:00.728 | INFO | __main__:training_each_inductor_holdout:6 -
####### nb INDUCTOR EXECUTING ####### - usi
2024-02-14 21:33:00.729 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: MultinomialNB() - nb - usi
2024-02-14 21:33:00.730 | 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
2024-02-14 21:33:00.731 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - nb - usi
2024-02-14 21:33:02.728 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - nb - usi
2024-02-14 21:33:02.731 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: MultinomialNB(alpha=1e-05, force_alpha=True)
2024-02-14 21:33:02.745 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS nb - usi #######
2024-02-14 21:33:02.750 | SUCCESS | __main__:training_each_inductor_holdout:33 - nb - usi - test_precision: 0.9341085271317829
2024-02-14 21:33:02.754 | SUCCESS | __main__:training_each_inductor_holdout:35 - nb - usi - test_recall: 0.7347560975609756
2024-02-14 21:33:02.758 | SUCCESS | __main__:training_each_inductor_holdout:37 - nb - usi - test_f1_binary: 0.8225255972696245
2024-02-14 21:33:02.763 | SUCCESS | __main__:training_each_inductor_holdout:39 - nb - usi - test_f1_macro: 0.8396374542821952
2024-02-14 21:33:02.764 | SUCCESS | __main__:<module>:72 -
[+][+][+] SUCCESS! [+][+][+]
2024-02-14 21:33:02.765 | INFO | __main__:<module>:2 -
####### cib EXECUTING #######
2024-02-14 21:33:02.769 | INFO | __main__:<module>:14 - total_relevant_documents_of_the_board: 688 - cib
2024-02-14 21:33:02.777 | INFO | __main__:<module>:15 - Total irrelevant documents of the department: 1790
2024-02-14 21:33:02.780 | INFO | __main__:<module>:18 - data_relevant_board: (688, 18) - cib
2024-02-14 21:33:02.785 | INFO | __main__:<module>:39 - data_irrelevant_board: (688, 18) - cib
2024-02-14 21:33:02.796 | INFO | __main__:<module>:47 - df_final_dataset: (1376, 18) - cib
2024-02-14 21:33:02.798 | DEBUG | __main__:<module>:50 - [+] Start cleaning text and title
2024-02-14 21:33:37.290 | DEBUG | __main__:<module>:55 - [+] End cleaning text and title
2024-02-14 21:33:37.294 | DEBUG | __main__:<module>:61 - [+] Start TF-IDF
2024-02-14 21:33:41.450 | DEBUG | __main__:<module>:65 - [+] End TF-IDF
2024-02-14 21:33:41.452 | INFO | __main__:training_each_inductor_holdout:6 -
####### random_forest INDUCTOR EXECUTING ####### - cib
2024-02-14 21:33:41.454 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: RandomForestClassifier(n_jobs=38, random_state=42) - random_forest - cib
2024-02-14 21:33:41.455 | 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
2024-02-14 21:33:41.456 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - random_forest - cib
2024-02-14 21:36:33.436 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - random_forest - cib
2024-02-14 21:36:33.440 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: RandomForestClassifier(criterion='entropy', max_depth=100, n_estimators=400,
n_jobs=38, random_state=42)
2024-02-14 21:36:35.560 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS random_forest - cib #######
2024-02-14 21:36:35.570 | SUCCESS | __main__:training_each_inductor_holdout:33 - random_forest - cib - test_precision: 0.8170731707317073
2024-02-14 21:36:35.575 | SUCCESS | __main__:training_each_inductor_holdout:35 - random_forest - cib - test_recall: 0.730909090909091
2024-02-14 21:36:35.579 | SUCCESS | __main__:training_each_inductor_holdout:37 - random_forest - cib - test_f1_binary: 0.7715930902111324
2024-02-14 21:36:35.583 | SUCCESS | __main__:training_each_inductor_holdout:39 - random_forest - cib - test_f1_macro: 0.7833869065513495
2024-02-14 21:36:35.584 | INFO | __main__:training_each_inductor_holdout:6 -
####### svm INDUCTOR EXECUTING ####### - cib
2024-02-14 21:36:35.585 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: SVC(random_state=42) - svm - cib
2024-02-14 21:36:35.586 | 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
2024-02-14 21:36:35.587 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - svm - cib
2024-02-14 21:37:57.403 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - svm - cib
2024-02-14 21:37:57.405 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: SVC(C=100.0, random_state=42)
2024-02-14 21:38:00.395 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS svm - cib #######
2024-02-14 21:38:00.403 | SUCCESS | __main__:training_each_inductor_holdout:33 - svm - cib - test_precision: 0.7977099236641222
2024-02-14 21:38:00.406 | SUCCESS | __main__:training_each_inductor_holdout:35 - svm - cib - test_recall: 0.76
2024-02-14 21:38:00.409 | SUCCESS | __main__:training_each_inductor_holdout:37 - svm - cib - test_f1_binary: 0.7783985102420857
2024-02-14 21:38:00.412 | SUCCESS | __main__:training_each_inductor_holdout:39 - svm - cib - test_f1_macro: 0.7838895206077685
2024-02-14 21:38:00.413 | INFO | __main__:training_each_inductor_holdout:6 -
####### xgboost INDUCTOR EXECUTING ####### - cib
2024-02-14 21:38:00.415 | 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
2024-02-14 21:38:00.416 | 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
2024-02-14 21:38:00.417 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - xgboost - cib
2024-02-15 04:19:02.448 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - xgboost - cib
2024-02-15 04:19:02.453 | 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=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, ...)
2024-02-15 04:22:16.528 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS xgboost - cib #######
2024-02-15 04:22:16.533 | SUCCESS | __main__:training_each_inductor_holdout:33 - xgboost - cib - test_precision: 0.7977099236641222
2024-02-15 04:22:16.536 | SUCCESS | __main__:training_each_inductor_holdout:35 - xgboost - cib - test_recall: 0.76
2024-02-15 04:22:16.539 | SUCCESS | __main__:training_each_inductor_holdout:37 - xgboost - cib - test_f1_binary: 0.7783985102420857
2024-02-15 04:22:16.542 | SUCCESS | __main__:training_each_inductor_holdout:39 - xgboost - cib - test_f1_macro: 0.7838895206077685
2024-02-15 04:22:16.543 | INFO | __main__:training_each_inductor_holdout:6 -
####### nb INDUCTOR EXECUTING ####### - cib
2024-02-15 04:22:16.543 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: MultinomialNB() - nb - cib
2024-02-15 04:22:16.544 | 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
2024-02-15 04:22:16.545 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - nb - cib
2024-02-15 04:22:19.048 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - nb - cib
2024-02-15 04:22:19.050 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: MultinomialNB(alpha=1e-05, force_alpha=True)
2024-02-15 04:22:19.075 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS nb - cib #######
2024-02-15 04:22:19.080 | SUCCESS | __main__:training_each_inductor_holdout:33 - nb - cib - test_precision: 0.6727941176470589
2024-02-15 04:22:19.083 | SUCCESS | __main__:training_each_inductor_holdout:35 - nb - cib - test_recall: 0.6654545454545454
2024-02-15 04:22:19.087 | SUCCESS | __main__:training_each_inductor_holdout:37 - nb - cib - test_f1_binary: 0.6691042047531992
2024-02-15 04:22:19.090 | SUCCESS | __main__:training_each_inductor_holdout:39 - nb - cib - test_f1_macro: 0.6714890393135365
2024-02-15 04:22:19.091 | SUCCESS | __main__:<module>:72 -
[+][+][+] SUCCESS! [+][+][+]
2024-02-15 04:22:19.092 | INFO | __main__:<module>:2 -
####### bb_asset EXECUTING #######
2024-02-15 04:22:19.096 | INFO | __main__:<module>:14 - total_relevant_documents_of_the_board: 683 - bb_asset
2024-02-15 04:22:19.110 | INFO | __main__:<module>:15 - Total irrelevant documents of the department: 5234
2024-02-15 04:22:19.113 | INFO | __main__:<module>:18 - data_relevant_board: (683, 18) - bb_asset
2024-02-15 04:22:19.120 | INFO | __main__:<module>:39 - data_irrelevant_board: (683, 18) - bb_asset
2024-02-15 04:22:19.130 | INFO | __main__:<module>:47 - df_final_dataset: (1366, 18) - bb_asset
2024-02-15 04:22:19.131 | DEBUG | __main__:<module>:50 - [+] Start cleaning text and title
2024-02-15 04:22:39.277 | DEBUG | __main__:<module>:55 - [+] End cleaning text and title
2024-02-15 04:22:39.282 | DEBUG | __main__:<module>:61 - [+] Start TF-IDF
2024-02-15 04:22:41.779 | DEBUG | __main__:<module>:65 - [+] End TF-IDF
2024-02-15 04:22:41.781 | INFO | __main__:training_each_inductor_holdout:6 -
####### random_forest INDUCTOR EXECUTING ####### - bb_asset
2024-02-15 04:22:41.783 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: RandomForestClassifier(n_jobs=38, random_state=42) - random_forest - bb_asset
2024-02-15 04:22:41.784 | 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
2024-02-15 04:22:41.785 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - random_forest - bb_asset
2024-02-15 04:24:49.608 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - random_forest - bb_asset
2024-02-15 04:24:49.610 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: RandomForestClassifier(max_depth=100, n_estimators=1000, n_jobs=38,
random_state=42)
2024-02-15 04:24:53.574 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS random_forest - bb_asset #######
2024-02-15 04:24:53.581 | SUCCESS | __main__:training_each_inductor_holdout:33 - random_forest - bb_asset - test_precision: 0.9527896995708155
2024-02-15 04:24:53.586 | SUCCESS | __main__:training_each_inductor_holdout:35 - random_forest - bb_asset - test_recall: 0.8131868131868132
2024-02-15 04:24:53.589 | SUCCESS | __main__:training_each_inductor_holdout:37 - random_forest - bb_asset - test_f1_binary: 0.8774703557312253
2024-02-15 04:24:53.592 | SUCCESS | __main__:training_each_inductor_holdout:39 - random_forest - bb_asset - test_f1_macro: 0.8860140894302385
2024-02-15 04:24:53.593 | INFO | __main__:training_each_inductor_holdout:6 -
####### svm INDUCTOR EXECUTING ####### - bb_asset
2024-02-15 04:24:53.594 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: SVC(random_state=42) - svm - bb_asset
2024-02-15 04:24:53.595 | 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
2024-02-15 04:24:53.596 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - svm - bb_asset
2024-02-15 04:25:51.480 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - svm - bb_asset
2024-02-15 04:25:51.482 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: SVC(C=10.0, random_state=42)
2024-02-15 04:25:54.023 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS svm - bb_asset #######
2024-02-15 04:25:54.027 | SUCCESS | __main__:training_each_inductor_holdout:33 - svm - bb_asset - test_precision: 0.9444444444444444
2024-02-15 04:25:54.030 | SUCCESS | __main__:training_each_inductor_holdout:35 - svm - bb_asset - test_recall: 0.8095238095238095
2024-02-15 04:25:54.034 | SUCCESS | __main__:training_each_inductor_holdout:37 - svm - bb_asset - test_f1_binary: 0.8717948717948718
2024-02-15 04:25:54.037 | SUCCESS | __main__:training_each_inductor_holdout:39 - svm - bb_asset - test_f1_macro: 0.8805311667321889
2024-02-15 04:25:54.037 | INFO | __main__:training_each_inductor_holdout:6 -
####### xgboost INDUCTOR EXECUTING ####### - bb_asset
2024-02-15 04:25:54.039 | 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
2024-02-15 04:25:54.040 | 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
2024-02-15 04:25:54.041 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - xgboost - bb_asset
2024-02-15 09:36:59.686 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - xgboost - bb_asset
2024-02-15 09:36:59.689 | 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, ...)
2024-02-15 09:37:21.198 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS xgboost - bb_asset #######
2024-02-15 09:37:21.203 | SUCCESS | __main__:training_each_inductor_holdout:33 - xgboost - bb_asset - test_precision: 0.9537815126050421
2024-02-15 09:37:21.206 | SUCCESS | __main__:training_each_inductor_holdout:35 - xgboost - bb_asset - test_recall: 0.8315018315018315
2024-02-15 09:37:21.209 | SUCCESS | __main__:training_each_inductor_holdout:37 - xgboost - bb_asset - test_f1_binary: 0.888454011741683
2024-02-15 09:37:21.211 | SUCCESS | __main__:training_each_inductor_holdout:39 - xgboost - bb_asset - test_f1_macro: 0.8953419286838775
2024-02-15 09:37:21.212 | INFO | __main__:training_each_inductor_holdout:6 -
####### nb INDUCTOR EXECUTING ####### - bb_asset
2024-02-15 09:37:21.219 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: MultinomialNB() - nb - bb_asset
2024-02-15 09:37:21.220 | 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
2024-02-15 09:37:21.222 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - nb - bb_asset
2024-02-15 09:37:23.274 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - nb - bb_asset
2024-02-15 09:37:23.277 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: MultinomialNB(alpha=1e-05, force_alpha=True)
2024-02-15 09:37:23.296 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS nb - bb_asset #######
2024-02-15 09:37:23.300 | SUCCESS | __main__:training_each_inductor_holdout:33 - nb - bb_asset - test_precision: 0.9159663865546218
2024-02-15 09:37:23.303 | SUCCESS | __main__:training_each_inductor_holdout:35 - nb - bb_asset - test_recall: 0.7985347985347986
2024-02-15 09:37:23.306 | SUCCESS | __main__:training_each_inductor_holdout:37 - nb - bb_asset - test_f1_binary: 0.8532289628180039
2024-02-15 09:37:23.310 | SUCCESS | __main__:training_each_inductor_holdout:39 - nb - bb_asset - test_f1_macro: 0.8622920114261545
2024-02-15 09:37:23.311 | SUCCESS | __main__:<module>:72 -
[+][+][+] SUCCESS! [+][+][+]
2024-02-15 09:37:23.312 | INFO | __main__:<module>:2 -
####### dimep EXECUTING #######
2024-02-15 09:37:23.315 | INFO | __main__:<module>:14 - total_relevant_documents_of_the_board: 600 - dimep
2024-02-15 09:37:23.325 | INFO | __main__:<module>:15 - Total irrelevant documents of the department: 3619
2024-02-15 09:37:23.327 | INFO | __main__:<module>:18 - data_relevant_board: (600, 18) - dimep
2024-02-15 09:37:23.334 | INFO | __main__:<module>:39 - data_irrelevant_board: (600, 18) - dimep
2024-02-15 09:37:23.347 | INFO | __main__:<module>:47 - df_final_dataset: (1200, 18) - dimep
2024-02-15 09:37:23.348 | DEBUG | __main__:<module>:50 - [+] Start cleaning text and title
2024-02-15 09:37:29.594 | DEBUG | __main__:<module>:55 - [+] End cleaning text and title
2024-02-15 09:37:29.599 | DEBUG | __main__:<module>:61 - [+] Start TF-IDF
2024-02-15 09:37:30.283 | DEBUG | __main__:<module>:65 - [+] End TF-IDF
2024-02-15 09:37:30.285 | INFO | __main__:training_each_inductor_holdout:6 -
####### random_forest INDUCTOR EXECUTING ####### - dimep
2024-02-15 09:37:30.286 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: RandomForestClassifier(n_jobs=38, random_state=42) - random_forest - dimep
2024-02-15 09:37:30.287 | 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
2024-02-15 09:37:30.287 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - random_forest - dimep
2024-02-15 09:40:14.398 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - random_forest - dimep
2024-02-15 09:40:14.402 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: RandomForestClassifier(criterion='entropy', max_depth=10, n_jobs=38,
random_state=42)
2024-02-15 09:40:14.823 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS random_forest - dimep #######
2024-02-15 09:40:14.829 | SUCCESS | __main__:training_each_inductor_holdout:33 - random_forest - dimep - test_precision: 0.7952218430034129
2024-02-15 09:40:14.834 | SUCCESS | __main__:training_each_inductor_holdout:35 - random_forest - dimep - test_recall: 0.9708333333333333
2024-02-15 09:40:14.838 | SUCCESS | __main__:training_each_inductor_holdout:37 - random_forest - dimep - test_f1_binary: 0.874296435272045
2024-02-15 09:40:14.840 | SUCCESS | __main__:training_each_inductor_holdout:39 - random_forest - dimep - test_f1_macro: 0.8586938850833293
2024-02-15 09:40:14.841 | INFO | __main__:training_each_inductor_holdout:6 -
####### svm INDUCTOR EXECUTING ####### - dimep
2024-02-15 09:40:14.843 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: SVC(random_state=42) - svm - dimep
2024-02-15 09:40:14.844 | 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
2024-02-15 09:40:14.845 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - svm - dimep
2024-02-15 09:40:37.572 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - svm - dimep
2024-02-15 09:40:37.574 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: SVC(C=0.8, kernel='sigmoid', random_state=42)
2024-02-15 09:40:38.251 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS svm - dimep #######
2024-02-15 09:40:38.256 | SUCCESS | __main__:training_each_inductor_holdout:33 - svm - dimep - test_precision: 0.8438661710037175
2024-02-15 09:40:38.260 | SUCCESS | __main__:training_each_inductor_holdout:35 - svm - dimep - test_recall: 0.9458333333333333
2024-02-15 09:40:38.264 | SUCCESS | __main__:training_each_inductor_holdout:37 - svm - dimep - test_f1_binary: 0.8919449901768172
2024-02-15 09:40:38.267 | SUCCESS | __main__:training_each_inductor_holdout:39 - svm - dimep - test_f1_macro: 0.884996885332311
2024-02-15 09:40:38.269 | INFO | __main__:training_each_inductor_holdout:6 -
####### xgboost INDUCTOR EXECUTING ####### - dimep
2024-02-15 09:40:38.270 | 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
2024-02-15 09:40:38.272 | 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
2024-02-15 09:40:38.273 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - xgboost - dimep
2024-02-15 16:33:17.009 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - xgboost - dimep
2024-02-15 16:33:17.012 | 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=1000, n_jobs=38, num_class=2,
num_parallel_tree=None, ...)
2024-02-15 16:34:11.449 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS xgboost - dimep #######
2024-02-15 16:34:11.454 | SUCCESS | __main__:training_each_inductor_holdout:33 - xgboost - dimep - test_precision: 0.8410852713178295
2024-02-15 16:34:11.458 | SUCCESS | __main__:training_each_inductor_holdout:35 - xgboost - dimep - test_recall: 0.9041666666666667
2024-02-15 16:34:11.461 | SUCCESS | __main__:training_each_inductor_holdout:37 - xgboost - dimep - test_f1_binary: 0.8714859437751005
2024-02-15 16:34:11.464 | SUCCESS | __main__:training_each_inductor_holdout:39 - xgboost - dimep - test_f1_macro: 0.8664789026234809
2024-02-15 16:34:11.464 | INFO | __main__:training_each_inductor_holdout:6 -
####### nb INDUCTOR EXECUTING ####### - dimep
2024-02-15 16:34:11.465 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: MultinomialNB() - nb - dimep
2024-02-15 16:34:11.466 | 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
2024-02-15 16:34:11.467 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - nb - dimep
2024-02-15 16:34:13.778 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - nb - dimep
2024-02-15 16:34:13.781 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: MultinomialNB(alpha=1e-05, force_alpha=True)
2024-02-15 16:34:13.800 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS nb - dimep #######
2024-02-15 16:34:13.805 | SUCCESS | __main__:training_each_inductor_holdout:33 - nb - dimep - test_precision: 0.823943661971831
2024-02-15 16:34:13.809 | SUCCESS | __main__:training_each_inductor_holdout:35 - nb - dimep - test_recall: 0.975
2024-02-15 16:34:13.812 | SUCCESS | __main__:training_each_inductor_holdout:37 - nb - dimep - test_f1_binary: 0.8931297709923663
2024-02-15 16:34:13.815 | SUCCESS | __main__:training_each_inductor_holdout:39 - nb - dimep - test_f1_macro: 0.8823447020099446
2024-02-15 16:34:13.817 | SUCCESS | __main__:<module>:72 -
[+][+][+] SUCCESS! [+][+][+]
2024-02-15 16:34:13.818 | INFO | __main__:<module>:2 -
####### coger gesub EXECUTING #######
2024-02-15 16:34:13.822 | INFO | __main__:<module>:14 - total_relevant_documents_of_the_board: 534 - coger gesub
2024-02-15 16:34:13.831 | INFO | __main__:<module>:15 - Total irrelevant documents of the department: 2594
2024-02-15 16:34:13.833 | INFO | __main__:<module>:18 - data_relevant_board: (534, 18) - coger gesub
2024-02-15 16:34:13.839 | INFO | __main__:<module>:39 - data_irrelevant_board: (534, 18) - coger gesub
2024-02-15 16:34:13.854 | INFO | __main__:<module>:47 - df_final_dataset: (1068, 18) - coger gesub
2024-02-15 16:34:13.856 | DEBUG | __main__:<module>:50 - [+] Start cleaning text and title
2024-02-15 16:34:23.528 | DEBUG | __main__:<module>:55 - [+] End cleaning text and title
2024-02-15 16:34:23.532 | DEBUG | __main__:<module>:61 - [+] Start TF-IDF
2024-02-15 16:34:24.777 | DEBUG | __main__:<module>:65 - [+] End TF-IDF
2024-02-15 16:34:24.778 | INFO | __main__:training_each_inductor_holdout:6 -
####### random_forest INDUCTOR EXECUTING ####### - coger gesub
2024-02-15 16:34:24.780 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: RandomForestClassifier(n_jobs=38, random_state=42) - random_forest - coger gesub
2024-02-15 16:34:24.781 | 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
2024-02-15 16:34:24.782 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - random_forest - coger gesub
2024-02-15 16:36:15.522 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - random_forest - coger gesub
2024-02-15 16:36:15.526 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: RandomForestClassifier(max_depth=10, n_estimators=400, n_jobs=38,
random_state=42)
2024-02-15 16:36:16.997 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS random_forest - coger gesub #######
2024-02-15 16:36:17.004 | SUCCESS | __main__:training_each_inductor_holdout:33 - random_forest - coger gesub - test_precision: 0.7821011673151751
2024-02-15 16:36:17.010 | SUCCESS | __main__:training_each_inductor_holdout:35 - random_forest - coger gesub - test_recall: 0.9392523364485982
2024-02-15 16:36:17.014 | SUCCESS | __main__:training_each_inductor_holdout:37 - random_forest - coger gesub - test_f1_binary: 0.8535031847133758
2024-02-15 16:36:17.017 | SUCCESS | __main__:training_each_inductor_holdout:39 - random_forest - coger gesub - test_f1_macro: 0.8371412027462983
2024-02-15 16:36:17.019 | INFO | __main__:training_each_inductor_holdout:6 -
####### svm INDUCTOR EXECUTING ####### - coger gesub
2024-02-15 16:36:17.020 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: SVC(random_state=42) - svm - coger gesub
2024-02-15 16:36:17.021 | 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
2024-02-15 16:36:17.022 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - svm - coger gesub
2024-02-15 16:36:51.255 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - svm - coger gesub
2024-02-15 16:36:51.258 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: SVC(kernel='poly', random_state=42)
2024-02-15 16:36:52.772 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS svm - coger gesub #######
2024-02-15 16:36:52.776 | SUCCESS | __main__:training_each_inductor_holdout:33 - svm - coger gesub - test_precision: 0.7619047619047619
2024-02-15 16:36:52.779 | SUCCESS | __main__:training_each_inductor_holdout:35 - svm - coger gesub - test_recall: 0.9719626168224299
2024-02-15 16:36:52.782 | SUCCESS | __main__:training_each_inductor_holdout:37 - svm - coger gesub - test_f1_binary: 0.8542094455852155
2024-02-15 16:36:52.785 | SUCCESS | __main__:training_each_inductor_holdout:39 - svm - coger gesub - test_f1_macro: 0.8308987607329872
2024-02-15 16:36:52.786 | INFO | __main__:training_each_inductor_holdout:6 -
####### xgboost INDUCTOR EXECUTING ####### - coger gesub
2024-02-15 16:36:52.788 | 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
2024-02-15 16:36:52.789 | 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
2024-02-15 16:36:52.790 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - xgboost - coger gesub
2024-02-15 20:57:51.127 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - xgboost - coger gesub
2024-02-15 20:57:51.131 | 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=1000, n_jobs=38, num_class=2,
num_parallel_tree=None, ...)
2024-02-15 20:59:12.959 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS xgboost - coger gesub #######
2024-02-15 20:59:12.964 | SUCCESS | __main__:training_each_inductor_holdout:33 - xgboost - coger gesub - test_precision: 0.8214285714285714
2024-02-15 20:59:12.968 | SUCCESS | __main__:training_each_inductor_holdout:35 - xgboost - coger gesub - test_recall: 0.8598130841121495
2024-02-15 20:59:12.971 | SUCCESS | __main__:training_each_inductor_holdout:37 - xgboost - coger gesub - test_f1_binary: 0.8401826484018264
2024-02-15 20:59:12.974 | SUCCESS | __main__:training_each_inductor_holdout:39 - xgboost - coger gesub - test_f1_macro: 0.8363592667846452
2024-02-15 20:59:12.974 | INFO | __main__:training_each_inductor_holdout:6 -
####### nb INDUCTOR EXECUTING ####### - coger gesub
2024-02-15 20:59:12.975 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: MultinomialNB() - nb - coger gesub
2024-02-15 20:59:12.976 | 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
2024-02-15 20:59:12.977 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - nb - coger gesub
2024-02-15 20:59:15.198 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - nb - coger gesub
2024-02-15 20:59:15.200 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: MultinomialNB(alpha=0.1, force_alpha=True)
2024-02-15 20:59:15.218 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS nb - coger gesub #######
2024-02-15 20:59:15.222 | SUCCESS | __main__:training_each_inductor_holdout:33 - nb - coger gesub - test_precision: 0.7795275590551181
2024-02-15 20:59:15.225 | SUCCESS | __main__:training_each_inductor_holdout:35 - nb - coger gesub - test_recall: 0.9252336448598131
2024-02-15 20:59:15.228 | SUCCESS | __main__:training_each_inductor_holdout:37 - nb - coger gesub - test_f1_binary: 0.8461538461538461
2024-02-15 20:59:15.230 | SUCCESS | __main__:training_each_inductor_holdout:39 - nb - coger gesub - test_f1_macro: 0.8302934179222838
2024-02-15 20:59:15.231 | SUCCESS | __main__:<module>:72 -
[+][+][+] SUCCESS! [+][+][+]
2024-02-15 20:59:15.232 | INFO | __main__:<module>:2 -
####### disem EXECUTING #######
2024-02-15 20:59:15.236 | INFO | __main__:<module>:14 - total_relevant_documents_of_the_board: 439 - disem
2024-02-15 20:59:15.243 | INFO | __main__:<module>:15 - Total irrelevant documents of the department: 1558
2024-02-15 20:59:15.246 | INFO | __main__:<module>:18 - data_relevant_board: (439, 18) - disem
2024-02-15 20:59:15.251 | INFO | __main__:<module>:39 - data_irrelevant_board: (439, 18) - disem
2024-02-15 20:59:15.267 | INFO | __main__:<module>:47 - df_final_dataset: (878, 18) - disem
2024-02-15 20:59:15.268 | DEBUG | __main__:<module>:50 - [+] Start cleaning text and title
2024-02-15 20:59:29.305 | DEBUG | __main__:<module>:55 - [+] End cleaning text and title
2024-02-15 20:59:29.309 | DEBUG | __main__:<module>:61 - [+] Start TF-IDF
2024-02-15 20:59:31.059 | DEBUG | __main__:<module>:65 - [+] End TF-IDF
2024-02-15 20:59:31.061 | INFO | __main__:training_each_inductor_holdout:6 -
####### random_forest INDUCTOR EXECUTING ####### - disem
2024-02-15 20:59:31.062 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: RandomForestClassifier(n_jobs=38, random_state=42) - random_forest - disem
2024-02-15 20:59:31.064 | 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
2024-02-15 20:59:31.065 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - random_forest - disem
2024-02-15 21:01:27.374 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - random_forest - disem
2024-02-15 21:01:27.377 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: RandomForestClassifier(criterion='entropy', max_depth=100, n_estimators=400,
n_jobs=38, random_state=42)
2024-02-15 21:01:29.037 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS random_forest - disem #######
2024-02-15 21:01:29.043 | SUCCESS | __main__:training_each_inductor_holdout:33 - random_forest - disem - test_precision: 0.84
2024-02-15 21:01:29.049 | SUCCESS | __main__:training_each_inductor_holdout:35 - random_forest - disem - test_recall: 0.9545454545454546
2024-02-15 21:01:29.052 | SUCCESS | __main__:training_each_inductor_holdout:37 - random_forest - disem - test_f1_binary: 0.8936170212765958
2024-02-15 21:01:29.055 | SUCCESS | __main__:training_each_inductor_holdout:39 - random_forest - disem - test_f1_macro: 0.8858329008822003
2024-02-15 21:01:29.056 | INFO | __main__:training_each_inductor_holdout:6 -
####### svm INDUCTOR EXECUTING ####### - disem
2024-02-15 21:01:29.057 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: SVC(random_state=42) - svm - disem
2024-02-15 21:01:29.058 | 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
2024-02-15 21:01:29.059 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - svm - disem
2024-02-15 21:01:47.910 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - svm - disem
2024-02-15 21:01:47.912 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: SVC(C=0.1, kernel='sigmoid', random_state=42)
2024-02-15 21:01:48.694 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS svm - disem #######
2024-02-15 21:01:48.698 | SUCCESS | __main__:training_each_inductor_holdout:33 - svm - disem - test_precision: 0.7510729613733905
2024-02-15 21:01:48.702 | SUCCESS | __main__:training_each_inductor_holdout:35 - svm - disem - test_recall: 0.9943181818181818
2024-02-15 21:01:48.705 | SUCCESS | __main__:training_each_inductor_holdout:37 - svm - disem - test_f1_binary: 0.8557457212713936
2024-02-15 21:01:48.708 | SUCCESS | __main__:training_each_inductor_holdout:39 - svm - disem - test_f1_macro: 0.8278728606356968
2024-02-15 21:01:48.709 | INFO | __main__:training_each_inductor_holdout:6 -
####### xgboost INDUCTOR EXECUTING ####### - disem
2024-02-15 21:01:48.711 | 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
2024-02-15 21:01:48.712 | 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
2024-02-15 21:01:48.713 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - xgboost - disem
2024-02-16 01:21:22.733 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - xgboost - disem
2024-02-16 01:21:22.736 | 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=30, 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, ...)
2024-02-16 01:21:35.289 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS xgboost - disem #######
2024-02-16 01:21:35.293 | SUCCESS | __main__:training_each_inductor_holdout:33 - xgboost - disem - test_precision: 0.861878453038674
2024-02-16 01:21:35.297 | SUCCESS | __main__:training_each_inductor_holdout:35 - xgboost - disem - test_recall: 0.8863636363636364
2024-02-16 01:21:35.299 | SUCCESS | __main__:training_each_inductor_holdout:37 - xgboost - disem - test_f1_binary: 0.8739495798319329
2024-02-16 01:21:35.302 | SUCCESS | __main__:training_each_inductor_holdout:39 - xgboost - disem - test_f1_macro: 0.8721332913568887
2024-02-16 01:21:35.303 | INFO | __main__:training_each_inductor_holdout:6 -
####### nb INDUCTOR EXECUTING ####### - disem
2024-02-16 01:21:35.304 | DEBUG | __main__:training_each_inductor_holdout:8 - [+] classifiers[key]['estimator']: MultinomialNB() - nb - disem
2024-02-16 01:21:35.305 | 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
2024-02-16 01:21:35.306 | DEBUG | __main__:training_each_inductor_holdout:19 - [+] Start GridSearchCV - nb - disem
2024-02-16 01:21:37.292 | DEBUG | __main__:training_each_inductor_holdout:21 - [+] End GridSearchCV - nb - disem
2024-02-16 01:21:37.294 | INFO | __main__:training_each_inductor_holdout:23 - search.best_estimator_: MultinomialNB(alpha=1e-05, force_alpha=True)
2024-02-16 01:21:37.309 | SUCCESS | __main__:training_each_inductor_holdout:31 -
####### METRICS nb - disem #######
2024-02-16 01:21:37.312 | SUCCESS | __main__:training_each_inductor_holdout:33 - nb - disem - test_precision: 0.8088235294117647
2024-02-16 01:21:37.315 | SUCCESS | __main__:training_each_inductor_holdout:35 - nb - disem - test_recall: 0.9375
2024-02-16 01:21:37.318 | SUCCESS | __main__:training_each_inductor_holdout:37 - nb - disem - test_f1_binary: 0.868421052631579
2024-02-16 01:21:37.321 | SUCCESS | __main__:training_each_inductor_holdout:39 - nb - disem - test_f1_macro: 0.857050032488629
2024-02-16 01:21:37.322 | SUCCESS | __main__:<module>:72 -
[+][+][+] SUCCESS! [+][+][+]