-
Notifications
You must be signed in to change notification settings - Fork 1
/
small
1238 lines (1238 loc) · 54.5 KB
/
small
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
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "Semantic-Search.ipynb",
"provenance": [],
"toc_visible": true,
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"accelerator": "GPU",
"widgets": {
"application/vnd.jupyter.widget-state+json": {
"3a1222a8fe1a4c388c1b9f932ce63768": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HBoxModel",
"state": {
"_view_name": "HBoxView",
"_dom_classes": [],
"_model_name": "HBoxModel",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.5.0",
"box_style": "",
"layout": "IPY_MODEL_61b3405264cc4fdba425f0486b918521",
"_model_module": "@jupyter-widgets/controls",
"children": [
"IPY_MODEL_f4e59ab68b4b4d8aa640a0e76541fc2b",
"IPY_MODEL_90b3b0d3e8644dde856dca51e01ebbef"
]
}
},
"61b3405264cc4fdba425f0486b918521": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"f4e59ab68b4b4d8aa640a0e76541fc2b": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"state": {
"_view_name": "ProgressView",
"style": "IPY_MODEL_749eb9397bb0478886f23977bf252408",
"_dom_classes": [],
"description": "Batches: 100%",
"_model_name": "FloatProgressModel",
"bar_style": "success",
"max": 1,
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": 1,
"_view_count": null,
"_view_module_version": "1.5.0",
"orientation": "horizontal",
"min": 0,
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_85e71e0e7f804620be6b1f2f5da588cb"
}
},
"90b3b0d3e8644dde856dca51e01ebbef": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"state": {
"_view_name": "HTMLView",
"style": "IPY_MODEL_2eb80dbc53fa45c9883fd690b345861d",
"_dom_classes": [],
"description": "",
"_model_name": "HTMLModel",
"placeholder": "",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": " 1/1 [00:01<00:00, 1.91s/it]",
"_view_count": null,
"_view_module_version": "1.5.0",
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_786be9d454004075979349de348c6466"
}
},
"749eb9397bb0478886f23977bf252408": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel",
"state": {
"_view_name": "StyleView",
"_model_name": "ProgressStyleModel",
"description_width": "initial",
"_view_module": "@jupyter-widgets/base",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.2.0",
"bar_color": null,
"_model_module": "@jupyter-widgets/controls"
}
},
"85e71e0e7f804620be6b1f2f5da588cb": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"2eb80dbc53fa45c9883fd690b345861d": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"state": {
"_view_name": "StyleView",
"_model_name": "DescriptionStyleModel",
"description_width": "",
"_view_module": "@jupyter-widgets/base",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.2.0",
"_model_module": "@jupyter-widgets/controls"
}
},
"786be9d454004075979349de348c6466": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"652d677ea6da496b800082ba584d25a0": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HBoxModel",
"state": {
"_view_name": "HBoxView",
"_dom_classes": [],
"_model_name": "HBoxModel",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.5.0",
"box_style": "",
"layout": "IPY_MODEL_424d4c3dcdd64e92b34a7fe4c70b7e5d",
"_model_module": "@jupyter-widgets/controls",
"children": [
"IPY_MODEL_2a9aad311a2942798fe03269524d3824",
"IPY_MODEL_af8475dc8adc4ce183a56299bacbbad2"
]
}
},
"424d4c3dcdd64e92b34a7fe4c70b7e5d": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"2a9aad311a2942798fe03269524d3824": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"state": {
"_view_name": "ProgressView",
"style": "IPY_MODEL_dfee41aa26c14dab88ceddb9b0b343e8",
"_dom_classes": [],
"description": "Batches: 100%",
"_model_name": "FloatProgressModel",
"bar_style": "success",
"max": 21,
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": 21,
"_view_count": null,
"_view_module_version": "1.5.0",
"orientation": "horizontal",
"min": 0,
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_8ea84ec8d2244a8ba92417ae56d108b5"
}
},
"af8475dc8adc4ce183a56299bacbbad2": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"state": {
"_view_name": "HTMLView",
"style": "IPY_MODEL_307ef651db6442529f5772eb1f2710d0",
"_dom_classes": [],
"description": "",
"_model_name": "HTMLModel",
"placeholder": "",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": " 21/21 [01:35<00:00, 4.57s/it]",
"_view_count": null,
"_view_module_version": "1.5.0",
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_11b54c21525840ad9c472bf571602162"
}
},
"dfee41aa26c14dab88ceddb9b0b343e8": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel",
"state": {
"_view_name": "StyleView",
"_model_name": "ProgressStyleModel",
"description_width": "initial",
"_view_module": "@jupyter-widgets/base",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.2.0",
"bar_color": null,
"_model_module": "@jupyter-widgets/controls"
}
},
"8ea84ec8d2244a8ba92417ae56d108b5": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"307ef651db6442529f5772eb1f2710d0": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"state": {
"_view_name": "StyleView",
"_model_name": "DescriptionStyleModel",
"description_width": "",
"_view_module": "@jupyter-widgets/base",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.2.0",
"_model_module": "@jupyter-widgets/controls"
}
},
"11b54c21525840ad9c472bf571602162": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
}
}
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/github/vizzies/Building-BERT-Model/blob/master/small\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "code",
"metadata": {
"id": "LG306zAvbptK",
"colab_type": "code",
"colab": {}
},
"source": [
"# from google.colab import drive\n",
"# drive.mount(‘/content/gdrive’)"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "LrhpWn-ObwQI",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 51
},
"outputId": "8770431c-d4f5-4ad5-cbab-5734f2608e72"
},
"source": [
"# GPU Setup\n",
"\n",
"import torch\n",
"\n",
"# If there's a GPU available...\n",
"if torch.cuda.is_available(): \n",
"\n",
" # Tell PyTorch to use the GPU. \n",
" device = torch.device(\"cuda\")\n",
"\n",
" print('There are %d GPU(s) available.' % torch.cuda.device_count())\n",
"\n",
" print('We will use the GPU:', torch.cuda.get_device_name(0))\n",
"\n",
"# If not...\n",
"else:\n",
" print('No GPU available, using the CPU instead.')\n",
" device = torch.device(\"cpu\")"
],
"execution_count": 8,
"outputs": [
{
"output_type": "stream",
"text": [
"There are 1 GPU(s) available.\n",
"We will use the GPU: Tesla T4\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Y5DnwN-Xb0ta",
"colab_type": "text"
},
"source": [
"# Import Data Below and Parse"
]
},
{
"cell_type": "code",
"metadata": {
"id": "n2Rflxlhb1Mu",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 272
},
"outputId": "46719dfc-fc3d-458c-da22-4517ceffa3ec"
},
"source": [
"import pandas\n",
"\n",
"import unicodedata\n",
"\n",
"# Import this into the Colab via the Files section\n",
"with open('/content/arc-code-ti-publications.pkl', 'rb') as f:\n",
" pubs = pandas.read_pickle(f)\n",
"\n",
"import re\n",
"TAG_RE = re.compile(r'<[^>]+>')\n",
"\n",
"def remove_tags(text):\n",
" return TAG_RE.sub('', text)\n",
" \n",
"def preprocess_text(sen):\n",
"\n",
" sentence = str(sen)\n",
"\n",
" # Removing html tags\n",
" sentence = remove_tags(sentence)\n",
"\n",
" # Remove hyphenation if at the end of a line\n",
" sentence = sentence.replace('-\\n', '')\n",
"\n",
" # Fix ligatures\n",
" sentence = unicodedata.normalize(\"NFKD\", sentence)\n",
"\n",
" # Remove punctuations and numbers\n",
" sentence = re.sub('[^a-zA-Z]', ' ', sentence)\n",
"\n",
" # Single character removal\n",
" sentence = re.sub(r\"\\s+[a-zA-Z]\\s+\", ' ', sentence)\n",
"\n",
" # Removing multiple spaces\n",
" sentence = re.sub(r'\\s+', ' ', sentence)\n",
"\n",
" return sentence\n",
"\n",
"# Not really needed any more but will leave in and just comment out\n",
"# full_texts = []\n",
"# sentences = list(pubs['Text'])\n",
"# for sen in sentences:\n",
"# full_texts.append(preprocess_text(str(sen)))\n",
"\n",
"pubs.drop(pubs[pubs['Text'] == 'PDF error occurred'].index, inplace = True) \n",
"\n",
"pubs.drop_duplicates(subset=['Text'])\n",
"\n",
"pubs['Text Processed'] = pubs.apply(lambda row: preprocess_text(row['Text']), axis=1)\n",
"\n",
"pubs['Word Count'] = pubs.apply(lambda row: len(row['Text Processed'].split()), axis=1)\n",
"\n",
"text_df = pubs[['Text Processed',]].copy()\n",
"\n",
"print(text_df)\n"
],
"execution_count": 9,
"outputs": [
{
"output_type": "stream",
"text": [
" Text Processed\n",
"Index \n",
"0 Adaptive Stress Testing of Trajectory Predicti...\n",
"1 Capturing Analyzing Requirements with FRET Dim...\n",
"3 The Ten Lockheed Martin Cyber Physical Challen...\n",
"4 Generation of Formal Requirements from Structu...\n",
"5 Formal Requirements Elicitation with FRET Dimi...\n",
"... ...\n",
"669 A Flexible Evolvable Architecture for Constell...\n",
"670 Extended Abstract General Purpose Data Driven ...\n",
"671 PARAMETRIC ANALYSIS OF HOVER TEST VEHICLE USI...\n",
"672 Bringing Web to Government Research Case Stud...\n",
"673 Online Detection and Modeling of Safety Bounda...\n",
"\n",
"[666 rows x 1 columns]\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "QwtovYHgcObq",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 462
},
"outputId": "87ea5627-6125-4162-da3b-9804495267ae"
},
"source": [
"!pip install -U sentence-transformers"
],
"execution_count": 10,
"outputs": [
{
"output_type": "stream",
"text": [
"Requirement already up-to-date: sentence-transformers in /usr/local/lib/python3.6/dist-packages (0.3.6)\n",
"Requirement already satisfied, skipping upgrade: transformers<3.2.0,>=3.1.0 in /usr/local/lib/python3.6/dist-packages (from sentence-transformers) (3.1.0)\n",
"Requirement already satisfied, skipping upgrade: scipy in /usr/local/lib/python3.6/dist-packages (from sentence-transformers) (1.4.1)\n",
"Requirement already satisfied, skipping upgrade: nltk in /usr/local/lib/python3.6/dist-packages (from sentence-transformers) (3.2.5)\n",
"Requirement already satisfied, skipping upgrade: numpy in /usr/local/lib/python3.6/dist-packages (from sentence-transformers) (1.18.5)\n",
"Requirement already satisfied, skipping upgrade: scikit-learn in /usr/local/lib/python3.6/dist-packages (from sentence-transformers) (0.22.2.post1)\n",
"Requirement already satisfied, skipping upgrade: tqdm in /usr/local/lib/python3.6/dist-packages (from sentence-transformers) (4.41.1)\n",
"Requirement already satisfied, skipping upgrade: torch>=1.2.0 in /usr/local/lib/python3.6/dist-packages (from sentence-transformers) (1.6.0+cu101)\n",
"Requirement already satisfied, skipping upgrade: regex!=2019.12.17 in /usr/local/lib/python3.6/dist-packages (from transformers<3.2.0,>=3.1.0->sentence-transformers) (2019.12.20)\n",
"Requirement already satisfied, skipping upgrade: sentencepiece!=0.1.92 in /usr/local/lib/python3.6/dist-packages (from transformers<3.2.0,>=3.1.0->sentence-transformers) (0.1.91)\n",
"Requirement already satisfied, skipping upgrade: packaging in /usr/local/lib/python3.6/dist-packages (from transformers<3.2.0,>=3.1.0->sentence-transformers) (20.4)\n",
"Requirement already satisfied, skipping upgrade: sacremoses in /usr/local/lib/python3.6/dist-packages (from transformers<3.2.0,>=3.1.0->sentence-transformers) (0.0.43)\n",
"Requirement already satisfied, skipping upgrade: tokenizers==0.8.1.rc2 in /usr/local/lib/python3.6/dist-packages (from transformers<3.2.0,>=3.1.0->sentence-transformers) (0.8.1rc2)\n",
"Requirement already satisfied, skipping upgrade: requests in /usr/local/lib/python3.6/dist-packages (from transformers<3.2.0,>=3.1.0->sentence-transformers) (2.23.0)\n",
"Requirement already satisfied, skipping upgrade: filelock in /usr/local/lib/python3.6/dist-packages (from transformers<3.2.0,>=3.1.0->sentence-transformers) (3.0.12)\n",
"Requirement already satisfied, skipping upgrade: dataclasses; python_version < \"3.7\" in /usr/local/lib/python3.6/dist-packages (from transformers<3.2.0,>=3.1.0->sentence-transformers) (0.7)\n",
"Requirement already satisfied, skipping upgrade: six in /usr/local/lib/python3.6/dist-packages (from nltk->sentence-transformers) (1.15.0)\n",
"Requirement already satisfied, skipping upgrade: joblib>=0.11 in /usr/local/lib/python3.6/dist-packages (from scikit-learn->sentence-transformers) (0.16.0)\n",
"Requirement already satisfied, skipping upgrade: future in /usr/local/lib/python3.6/dist-packages (from torch>=1.2.0->sentence-transformers) (0.16.0)\n",
"Requirement already satisfied, skipping upgrade: pyparsing>=2.0.2 in /usr/local/lib/python3.6/dist-packages (from packaging->transformers<3.2.0,>=3.1.0->sentence-transformers) (2.4.7)\n",
"Requirement already satisfied, skipping upgrade: click in /usr/local/lib/python3.6/dist-packages (from sacremoses->transformers<3.2.0,>=3.1.0->sentence-transformers) (7.1.2)\n",
"Requirement already satisfied, skipping upgrade: certifi>=2017.4.17 in /usr/local/lib/python3.6/dist-packages (from requests->transformers<3.2.0,>=3.1.0->sentence-transformers) (2020.6.20)\n",
"Requirement already satisfied, skipping upgrade: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /usr/local/lib/python3.6/dist-packages (from requests->transformers<3.2.0,>=3.1.0->sentence-transformers) (1.24.3)\n",
"Requirement already satisfied, skipping upgrade: chardet<4,>=3.0.2 in /usr/local/lib/python3.6/dist-packages (from requests->transformers<3.2.0,>=3.1.0->sentence-transformers) (3.0.4)\n",
"Requirement already satisfied, skipping upgrade: idna<3,>=2.5 in /usr/local/lib/python3.6/dist-packages (from requests->transformers<3.2.0,>=3.1.0->sentence-transformers) (2.10)\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Ucmaa9IScZjU",
"colab_type": "text"
},
"source": [
"## BERT Sentence Tranformers Semantic Search"
]
},
{
"cell_type": "code",
"metadata": {
"id": "7jVvreBycPSM",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000,
"referenced_widgets": [
"3a1222a8fe1a4c388c1b9f932ce63768",
"61b3405264cc4fdba425f0486b918521",
"f4e59ab68b4b4d8aa640a0e76541fc2b",
"90b3b0d3e8644dde856dca51e01ebbef",
"749eb9397bb0478886f23977bf252408",
"85e71e0e7f804620be6b1f2f5da588cb",
"2eb80dbc53fa45c9883fd690b345861d",
"786be9d454004075979349de348c6466",
"652d677ea6da496b800082ba584d25a0",
"424d4c3dcdd64e92b34a7fe4c70b7e5d",
"2a9aad311a2942798fe03269524d3824",
"af8475dc8adc4ce183a56299bacbbad2",
"dfee41aa26c14dab88ceddb9b0b343e8",
"8ea84ec8d2244a8ba92417ae56d108b5",
"307ef651db6442529f5772eb1f2710d0",
"11b54c21525840ad9c472bf571602162"
]
},
"outputId": "511d149d-4f89-421d-e2ad-dbc6d1ca1ae4"
},
"source": [
"\"\"\"\n",
"This is a simple application for sentence embeddings: semantic search\n",
"given query sentence,this finds the most similar sentence in this corpus\n",
"script outputs for various queries the top 5 most similar publications in the corpus\n",
"*Used open source code to aid in development\n",
"\"\"\"\n",
"from sentence_transformers import SentenceTransformer\n",
"import scipy.spatial\n",
"import pickle as pkl\n",
"embedder = SentenceTransformer('bert-base-nli-mean-tokens')\n",
"\n",
"sentences = list(text_df['Text Processed'])\n",
"\n",
"# Eaxmple query sentences\n",
"queries = ['How to evolve architecture for constellations and simulation', 'Build behavior of complex aerospace and modeling of safety']\n",
"query_embeddings = embedder.encode(queries,show_progress_bar=True)\n",
"text_embeddings = embedder.encode(sentences, show_progress_bar=True)\n",
"#\n",
"# Find the closest 5 sentences of the corpus for each query sentence based on cosine similarity\n",
"closest_n = 5\n",
"print(\"\\nTop 5 most similar sentences in corpus:\")\n",
"for query, query_embedding in zip(queries, query_embeddings):\n",
" distances = scipy.spatial.distance.cdist([query_embedding], text_embeddings, \"cosine\")[0]\n",
"\n",
" results = zip(range(len(distances)), distances)\n",
" results = sorted(results, key=lambda x: x[1])\n",
"\n",
" print(\"------------------------User Query: ------------------------\")\n",
" print(\"--\",query,\"--\")\n",
" print(\"------------------------------------------------------------\")\n",
"\n",
"\n",
"# Print out all information for the publications related to user query and a relevancy score\n",
" for idx, distance in results[0:closest_n]:\n",
" print(\"Relevancy Score: \", \"(Score: %.0f%%)\" % ((1-distance) * 100.0) , \"\\n\" )\n",
" row_dict = pubs.iloc[idx].to_dict() # pubs.loc[pubs.index== sentences[idx]].to_dict()\n",
" #print(row_dict)\n",
" print(\"Title: \" , row_dict[\"Title\"] , \"\\n\")\n",
" print(\"Authors: \" , row_dict[\"Authors\"] , \"\\n\")\n",
" print(\"Date: \" , row_dict[\"Date\"] , \"\\n\")\n",
" print(\"Link: \" , row_dict[\"Link\"] , \"\\n\")\n",
" print(\"Abstract Length: \" , row_dict[\"Abstract Length\"] , \"\\n\")\n",
" print(\"Abstract: \" , row_dict[\"Abstract\"] , \"\\n\")\n",
" print(\"-------------------------------------------\")"
],
"execution_count": 12,
"outputs": [
{
"output_type": "display_data",
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "3a1222a8fe1a4c388c1b9f932ce63768",
"version_minor": 0,
"version_major": 2
},
"text/plain": [
"HBox(children=(FloatProgress(value=0.0, description='Batches', max=1.0, style=ProgressStyle(description_width=…"
]
},
"metadata": {
"tags": []
}
},
{
"output_type": "stream",
"text": [
"\n"
],
"name": "stdout"
},
{
"output_type": "display_data",
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "652d677ea6da496b800082ba584d25a0",
"version_minor": 0,
"version_major": 2
},
"text/plain": [
"HBox(children=(FloatProgress(value=0.0, description='Batches', max=21.0, style=ProgressStyle(description_width…"
]
},
"metadata": {
"tags": []
}
},
{
"output_type": "stream",
"text": [
"\n",
"\n",
"Top 5 most similar sentences in corpus:\n",
"\n",
"\n",
"---------------------------------------------------------\n",
"------------------------User Query------------------------\n",
"-- How to evolve architecture for constellations and simulation --\n",
"------------------------------------------------------------\n",
"Score: (Score: 67.4187) %\n",
"\n",
"Title: Fault Diagnostics and Prognostics for Large Segmented SRM's \n",
"\n",
"Authors: Dimitry Luchinsky,Vadim Smelyanskiy,Viatcheslav Osipov,Dogan Timucin \n",
"\n",
"Date: 03/07/09 \n",
"\n",
"Link: http://ti.arc.nasa.gov/publications/245/download/ \n",
"\n",
"Abstract Length: 1544 \n",
"\n",
"Abstract: \n",
"\n",
" \n",
"Abstract—Prognostics has taken center stage in Condition \n",
"Based Maintenance (CBM) where it is desired to estimate \n",
"Remaining Useful Life (RUL) of a system so that remedial \n",
"measures may be taken in advance to avoid catastrophic \n",
"events or unwanted downtimes. Validation of such \n",
"predictions is an important but difficult proposition and a \n",
"lack of appropriate evaluation methods renders prognostics \n",
"meaningless. Evaluation methods currently used in the \n",
"research community are not standardized and in many cases \n",
"do not sufficiently assess key performance aspects expected \n",
"out of a prognostics algorithm. In this paper we introduce \n",
"several new evaluation metrics tailored for prognostics and \n",
"show that they can effectively evaluate various algorithms as \n",
"compared to other conventional metrics. Four prognostic \n",
"algorithms, Relevance Vector Machine (RVM), Gaussian \n",
"Process Regression (GPR), Artificial Neural Network \n",
"(ANN), and Polynomial Regression (PR), are compared. \n",
"These algorithms vary in complexity and their ability to \n",
"manage uncertainty around predicted estimates. Results \n",
"show that the new metrics rank these algorithms in a \n",
"different manner; depending on the requirements and \n",
"constraints suitable metrics may be chosen. Beyond these \n",
"results, this paper offers ideas about how metrics suitable to \n",
"prognostics may be designed so \n",
"the evaluation \n",
"procedure can be standardized. 1 2 \n",
" \n",
"\n",
"-------------------------------------------\n",
"Score: (Score: 66.6870) %\n",
"\n",
"Title: Evolving Systems and Adaptive Key Component Control \n",
"\n",
"Authors: Susan Frost,Mark Balas \n",
"\n",
"Date: 12/31/09 \n",
"\n",
"Link: http://ti.arc.nasa.gov/publications/820/download/ \n",
"\n",
"Abstract Length: 625 \n",
"\n",
"Abstract: \n",
"\n",
"1. Introduction\n",
"We propose a new framework called Evolving Systems to describe the self-assembly, or au-\n",
"tonomous assembly, of actively controlled dynamical subsystems into an Evolved System\n",
"with a higher purpose. An introduction to Evolving Systems and exploration of the essential\n",
"topics of the control and stability properties of Evolving Systems is provided. This chapter\n",
"defines a framework for Evolving Systems, develops theory and control solutions for funda-\n",
"mental characteristics of Evolving Systems, and provides illustrative examples of Evolving\n",
"Systems and their control with adaptive key component controllers. \n",
"\n",
"-------------------------------------------\n",
"Score: (Score: 66.3958) %\n",
"\n",
"Title: Time-Varying Modification of Reference Model for Adaptive Control with Performance Optimization \n",
"\n",
"Authors: Nhan Nguyen,Kelley Hashemi \n",
"\n",
"Date: 06/28/18 \n",
"\n",
"Link: http://ti.arc.nasa.gov/publications/53412/download/ \n",
"\n",
"Abstract Length: 863 \n",
"\n",
"Abstract: \n",
"\n",
"Abstract—This paper presents a new adaptive control ap-\n",
"proach that involves a performance optimization objective.\n",
"The control synthesis involves the design of a performance\n",
"optimizing adaptive controller from a subset of control\n",
"inputs. The resulting effect of the performance optimizing\n",
"adaptive controller is to modify the initial reference model\n",
"into a time-varying reference model which satisfies the\n",
"performance optimization requirement obtained from an\n",
"optimal control problem. The time-varying reference model\n",
"modification is accomplished by the real-time solutions of\n",
"the time-varying Riccati and Sylvester equations coupled\n",
"with the least-squares parameter estimation of the sen-\n",
"sitivities of the performance metric. The effectiveness of\n",
"the proposed method is demonstrated by an application of\n",
"maneuver load alleviation control for a flexible aircraft. \n",
"\n",
"-------------------------------------------\n",
"Score: (Score: 65.7705) %\n",
"\n",
"Title: Performance Optimizing Adaptive Control with Time-Varying Reference Model Modification \n",
"\n",
"Authors: Nhan Nguyen,Kelley Hashemi \n",
"\n",
"Date: 06/21/17 \n",
"\n",
"Link: http://ti.arc.nasa.gov/publications/42886/download/ \n",
"\n",
"Abstract Length: 863 \n",
"\n",
"Abstract: \n",
"\n",
"Abstract—This paper presents a new adaptive control ap-\n",
"proach that involves a performance optimization objective.\n",
"The control synthesis involves the design of a performance\n",
"optimizing adaptive controller from a subset of control\n",
"inputs. The resulting effect of the performance optimizing\n",
"adaptive controller is to modify the initial reference model\n",
"into a time-varying reference model which satisfies the\n",
"performance optimization requirement obtained from an\n",
"optimal control problem. The time-varying reference model\n",
"modification is accomplished by the real-time solutions of\n",
"the time-varying Riccati and Sylvester equations coupled\n",
"with the least-squares parameter estimation of the sen-\n",
"sitivities of the performance metric. The effectiveness of\n",
"the proposed method is demonstrated by an application of\n",
"maneuver load alleviation control for a flexible aircraft. \n",
"\n",
"-------------------------------------------\n",
"Score: (Score: 65.5662) %\n",
"\n",