Hugging Face's logo

Akash-AG
/
gecs-classifier

Joblib
Model card Files
xet
 Community
Akash-AG commited on
Commit
daebb61
·
verified ·
1 Parent(s): 940e501

Upload folder using huggingface_hub

Browse files
Files changed (22) hide show
  1. models/cascade_L1_svm.joblib +3 -0
  2. models/cascade_L2_models.joblib +3 -0
  3. models/cascade_L3_models.joblib +3 -0
  4. models/cascade_taxonomy_tree.json +660 -0
  5. models/cascade_training_summary.json +23 -0
  6. models/cascade_vectorizer.pkl +3 -0
  7. models/mstar_labels_full.json +147 -0
  8. models/sub_industry_labels.json +430 -0
  9. models/t2_cascade_L1.joblib +3 -0
  10. models/t2_cascade_L2.joblib +3 -0
  11. models/t2_cascade_L3.joblib +3 -0
  12. models/t2_cascade_L4.joblib +3 -0
  13. models/t2_cascade_L4_seg.joblib +3 -0
  14. models/t2_cascade_seg_vec.pkl +3 -0
  15. models/t2_cascade_summary.json +26 -0
  16. models/t2_cascade_vectorizer.pkl +3 -0
  17. models/task1_rf_model.joblib +3 -0
  18. models/task1_rf_model.pkl +3 -0
  19. models/task1_svm_model.joblib +3 -0
  20. models/task1_tfidf_vectorizer.pkl +3 -0
  21. models/task2_svc_model.joblib +3 -0
  22. models/task2_tfidf_vectorizer.pkl +3 -0
models/cascade_L1_svm.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08f061dd2ab4ac604569495ccb6c63142d6862579cf2807b109f9cf270700bce
3
+ size 4401036
models/cascade_L2_models.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b13388dfa739d2772ca90e1cb95bde10e5803779bfb24e1d750c258a2e5f338e
3
+ size 20805790
models/cascade_L3_models.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d997b2c482ab8afa448b9dd634f4b00dbbaec477a364cd3c3ce24da9fbc0b44
3
+ size 44816750
models/cascade_taxonomy_tree.json ADDED
@@ -0,0 +1,660 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "code_counts": {
3
+ "10110010": 282,
4
+ "10120010": 533,
5
+ "10130010": 709,
6
+ "10130020": 944,
7
+ "10140010": 123,
8
+ "10140020": 153,
9
+ "10150010": 125,
10
+ "10150020": 113,
11
+ "10150030": 504,
12
+ "10150040": 372,
13
+ "10150050": 51,
14
+ "10150060": 114,
15
+ "10160010": 41,
16
+ "10160020": 496,
17
+ "10200010": 211,
18
+ "10200020": 191,
19
+ "10200030": 826,
20
+ "10200040": 68,
21
+ "10220010": 374,
22
+ "10230010": 155,
23
+ "10240010": 258,
24
+ "10240020": 251,
25
+ "10240030": 125,
26
+ "10250010": 329,
27
+ "10260010": 102,
28
+ "10270010": 428,
29
+ "10280010": 252,
30
+ "10280020": 219,
31
+ "10280030": 84,
32
+ "10280040": 134,
33
+ "10280050": 231,
34
+ "10280060": 496,
35
+ "10290010": 150,
36
+ "10290020": 352,
37
+ "10290030": 401,
38
+ "10290040": 189,
39
+ "10290050": 167,
40
+ "10310010": 2359,
41
+ "10320010": 202,
42
+ "10320020": 2165,
43
+ "10320030": 152,
44
+ "10330010": 791,
45
+ "10330020": 142,
46
+ "10340010": 326,
47
+ "10340020": 253,
48
+ "10340030": 53,
49
+ "10340040": 71,
50
+ "10340050": 115,
51
+ "10340060": 171,
52
+ "10350010": 48,
53
+ "10350020": 325,
54
+ "10360010": 743,
55
+ "10410010": 918,
56
+ "10410020": 1632,
57
+ "10410030": 275,
58
+ "10420010": 67,
59
+ "10420020": 87,
60
+ "10420030": 141,
61
+ "10420040": 174,
62
+ "10420050": 123,
63
+ "10420060": 199,
64
+ "10420070": 61,
65
+ "10420080": 91,
66
+ "10420090": 234,
67
+ "20510010": 76,
68
+ "20510020": 186,
69
+ "20520010": 164,
70
+ "20525010": 109,
71
+ "20525020": 435,
72
+ "20525030": 398,
73
+ "20525040": 1185,
74
+ "20540010": 293,
75
+ "20550010": 72,
76
+ "20550020": 222,
77
+ "20550030": 150,
78
+ "20560010": 104,
79
+ "20610010": 1036,
80
+ "20620010": 38,
81
+ "20620020": 1160,
82
+ "20630010": 33,
83
+ "20645010": 448,
84
+ "20645020": 155,
85
+ "20645030": 289,
86
+ "20650010": 707,
87
+ "20650020": 325,
88
+ "20660010": 237,
89
+ "20670010": 199,
90
+ "20710010": 78,
91
+ "20710020": 622,
92
+ "20720010": 183,
93
+ "20720020": 520,
94
+ "20720030": 173,
95
+ "20720040": 138,
96
+ "30810010": 593,
97
+ "30820010": 436,
98
+ "30820020": 180,
99
+ "30820030": 157,
100
+ "30820040": 485,
101
+ "30830010": 316,
102
+ "30830020": 263,
103
+ "30910010": 62,
104
+ "30910020": 527,
105
+ "30910030": 54,
106
+ "30910040": 288,
107
+ "30910050": 267,
108
+ "30910060": 344,
109
+ "30920010": 137,
110
+ "30920020": 28,
111
+ "31010010": 503,
112
+ "31020010": 771,
113
+ "31020020": 214,
114
+ "31020030": 263,
115
+ "31020040": 83,
116
+ "31020050": 204,
117
+ "31030010": 2358,
118
+ "31040010": 1358,
119
+ "31040020": 165,
120
+ "31040030": 481,
121
+ "31050010": 304,
122
+ "31060010": 235,
123
+ "31070010": 105,
124
+ "31070020": 1250,
125
+ "31070030": 215,
126
+ "31070040": 123,
127
+ "31070050": 150,
128
+ "31070060": 708,
129
+ "31080010": 168,
130
+ "31080020": 135,
131
+ "31080030": 204,
132
+ "31080040": 406,
133
+ "31080050": 78,
134
+ "31080060": 468,
135
+ "31090010": 290,
136
+ "31110010": 1011,
137
+ "31110020": 1226,
138
+ "31110030": 893,
139
+ "31120010": 345,
140
+ "31120020": 266,
141
+ "31120030": 166,
142
+ "31120040": 749,
143
+ "31120050": 200,
144
+ "31120060": 271,
145
+ "31130010": 304,
146
+ "31130020": 365,
147
+ "31130030": 207
148
+ },
149
+ "group_to_codes": {
150
+ "10110": [
151
+ "10110010"
152
+ ],
153
+ "10120": [
154
+ "10120010"
155
+ ],
156
+ "10130": [
157
+ "10130010",
158
+ "10130020"
159
+ ],
160
+ "10140": [
161
+ "10140010",
162
+ "10140020"
163
+ ],
164
+ "10150": [
165
+ "10150010",
166
+ "10150020",
167
+ "10150030",
168
+ "10150040",
169
+ "10150050",
170
+ "10150060"
171
+ ],
172
+ "10160": [
173
+ "10160010",
174
+ "10160020"
175
+ ],
176
+ "10200": [
177
+ "10200010",
178
+ "10200020",
179
+ "10200030",
180
+ "10200040"
181
+ ],
182
+ "10220": [
183
+ "10220010"
184
+ ],
185
+ "10230": [
186
+ "10230010"
187
+ ],
188
+ "10240": [
189
+ "10240010",
190
+ "10240020",
191
+ "10240030"
192
+ ],
193
+ "10250": [
194
+ "10250010"
195
+ ],
196
+ "10260": [
197
+ "10260010"
198
+ ],
199
+ "10270": [
200
+ "10270010"
201
+ ],
202
+ "10280": [
203
+ "10280010",
204
+ "10280020",
205
+ "10280030",
206
+ "10280040",
207
+ "10280050",
208
+ "10280060"
209
+ ],
210
+ "10290": [
211
+ "10290010",
212
+ "10290020",
213
+ "10290030",
214
+ "10290040",
215
+ "10290050"
216
+ ],
217
+ "10310": [
218
+ "10310010"
219
+ ],
220
+ "10320": [
221
+ "10320010",
222
+ "10320020",
223
+ "10320030"
224
+ ],
225
+ "10330": [
226
+ "10330010",
227
+ "10330020"
228
+ ],
229
+ "10340": [
230
+ "10340010",
231
+ "10340020",
232
+ "10340030",
233
+ "10340040",
234
+ "10340050",
235
+ "10340060"
236
+ ],
237
+ "10350": [
238
+ "10350010",
239
+ "10350020"
240
+ ],
241
+ "10360": [
242
+ "10360010"
243
+ ],
244
+ "10410": [
245
+ "10410010",
246
+ "10410020",
247
+ "10410030"
248
+ ],
249
+ "10420": [
250
+ "10420010",
251
+ "10420020",
252
+ "10420030",
253
+ "10420040",
254
+ "10420050",
255
+ "10420060",
256
+ "10420070",
257
+ "10420080",
258
+ "10420090"
259
+ ],
260
+ "20510": [
261
+ "20510010",
262
+ "20510020"
263
+ ],
264
+ "20520": [
265
+ "20520010"
266
+ ],
267
+ "20525": [
268
+ "20525010",
269
+ "20525020",
270
+ "20525030",
271
+ "20525040"
272
+ ],
273
+ "20540": [
274
+ "20540010"
275
+ ],
276
+ "20550": [
277
+ "20550010",
278
+ "20550020",
279
+ "20550030"
280
+ ],
281
+ "20560": [
282
+ "20560010"
283
+ ],
284
+ "20610": [
285
+ "20610010"
286
+ ],
287
+ "20620": [
288
+ "20620010",
289
+ "20620020"
290
+ ],
291
+ "20630": [
292
+ "20630010"
293
+ ],
294
+ "20645": [
295
+ "20645010",
296
+ "20645020",
297
+ "20645030"
298
+ ],
299
+ "20650": [
300
+ "20650010",
301
+ "20650020"
302
+ ],
303
+ "20660": [
304
+ "20660010"
305
+ ],
306
+ "20670": [
307
+ "20670010"
308
+ ],
309
+ "20710": [
310
+ "20710010",
311
+ "20710020"
312
+ ],
313
+ "20720": [
314
+ "20720010",
315
+ "20720020",
316
+ "20720030",
317
+ "20720040"
318
+ ],
319
+ "30810": [
320
+ "30810010"
321
+ ],
322
+ "30820": [
323
+ "30820010",
324
+ "30820020",
325
+ "30820030",
326
+ "30820040"
327
+ ],
328
+ "30830": [
329
+ "30830010",
330
+ "30830020"
331
+ ],
332
+ "30910": [
333
+ "30910010",
334
+ "30910020",
335
+ "30910030",
336
+ "30910040",
337
+ "30910050",
338
+ "30910060"
339
+ ],
340
+ "30920": [
341
+ "30920010",
342
+ "30920020"
343
+ ],
344
+ "31010": [
345
+ "31010010"
346
+ ],
347
+ "31020": [
348
+ "31020010",
349
+ "31020020",
350
+ "31020030",
351
+ "31020040",
352
+ "31020050"
353
+ ],
354
+ "31030": [
355
+ "31030010"
356
+ ],
357
+ "31040": [
358
+ "31040010",
359
+ "31040020",
360
+ "31040030"
361
+ ],
362
+ "31050": [
363
+ "31050010"
364
+ ],
365
+ "31060": [
366
+ "31060010"
367
+ ],
368
+ "31070": [
369
+ "31070010",
370
+ "31070020",
371
+ "31070030",
372
+ "31070040",
373
+ "31070050",
374
+ "31070060"
375
+ ],
376
+ "31080": [
377
+ "31080010",
378
+ "31080020",
379
+ "31080030",
380
+ "31080040",
381
+ "31080050",
382
+ "31080060"
383
+ ],
384
+ "31090": [
385
+ "31090010"
386
+ ],
387
+ "31110": [
388
+ "31110010",
389
+ "31110020",
390
+ "31110030"
391
+ ],
392
+ "31120": [
393
+ "31120010",
394
+ "31120020",
395
+ "31120030",
396
+ "31120040",
397
+ "31120050",
398
+ "31120060"
399
+ ],
400
+ "31130": [
401
+ "31130010",
402
+ "31130020",
403
+ "31130030"
404
+ ]
405
+ },
406
+ "sector_to_codes": {
407
+ "101": [
408
+ "10110010",
409
+ "10120010",
410
+ "10130010",
411
+ "10130020",
412
+ "10140010",
413
+ "10140020",
414
+ "10150010",
415
+ "10150020",
416
+ "10150030",
417
+ "10150040",
418
+ "10150050",
419
+ "10150060",
420
+ "10160010",
421
+ "10160020"
422
+ ],
423
+ "102": [
424
+ "10200010",
425
+ "10200020",
426
+ "10200030",
427
+ "10200040",
428
+ "10220010",
429
+ "10230010",
430
+ "10240010",
431
+ "10240020",
432
+ "10240030",
433
+ "10250010",
434
+ "10260010",
435
+ "10270010",
436
+ "10280010",
437
+ "10280020",
438
+ "10280030",
439
+ "10280040",
440
+ "10280050",
441
+ "10280060",
442
+ "10290010",
443
+ "10290020",
444
+ "10290030",
445
+ "10290040",
446
+ "10290050"
447
+ ],
448
+ "103": [
449
+ "10310010",
450
+ "10320010",
451
+ "10320020",
452
+ "10320030",
453
+ "10330010",
454
+ "10330020",
455
+ "10340010",
456
+ "10340020",
457
+ "10340030",
458
+ "10340040",
459
+ "10340050",
460
+ "10340060",
461
+ "10350010",
462
+ "10350020",
463
+ "10360010"
464
+ ],
465
+ "104": [
466
+ "10410010",
467
+ "10410020",
468
+ "10410030",
469
+ "10420010",
470
+ "10420020",
471
+ "10420030",
472
+ "10420040",
473
+ "10420050",
474
+ "10420060",
475
+ "10420070",
476
+ "10420080",
477
+ "10420090"
478
+ ],
479
+ "205": [
480
+ "20510010",
481
+ "20510020",
482
+ "20520010",
483
+ "20525010",
484
+ "20525020",
485
+ "20525030",
486
+ "20525040",
487
+ "20540010",
488
+ "20550010",
489
+ "20550020",
490
+ "20550030",
491
+ "20560010"
492
+ ],
493
+ "206": [
494
+ "20610010",
495
+ "20620010",
496
+ "20620020",
497
+ "20630010",
498
+ "20645010",
499
+ "20645020",
500
+ "20645030",
501
+ "20650010",
502
+ "20650020",
503
+ "20660010",
504
+ "20670010"
505
+ ],
506
+ "207": [
507
+ "20710010",
508
+ "20710020",
509
+ "20720010",
510
+ "20720020",
511
+ "20720030",
512
+ "20720040"
513
+ ],
514
+ "308": [
515
+ "30810010",
516
+ "30820010",
517
+ "30820020",
518
+ "30820030",
519
+ "30820040",
520
+ "30830010",
521
+ "30830020"
522
+ ],
523
+ "309": [
524
+ "30910010",
525
+ "30910020",
526
+ "30910030",
527
+ "30910040",
528
+ "30910050",
529
+ "30910060",
530
+ "30920010",
531
+ "30920020"
532
+ ],
533
+ "310": [
534
+ "31010010",
535
+ "31020010",
536
+ "31020020",
537
+ "31020030",
538
+ "31020040",
539
+ "31020050",
540
+ "31030010",
541
+ "31040010",
542
+ "31040020",
543
+ "31040030",
544
+ "31050010",
545
+ "31060010",
546
+ "31070010",
547
+ "31070020",
548
+ "31070030",
549
+ "31070040",
550
+ "31070050",
551
+ "31070060",
552
+ "31080010",
553
+ "31080020",
554
+ "31080030",
555
+ "31080040",
556
+ "31080050",
557
+ "31080060",
558
+ "31090010"
559
+ ],
560
+ "311": [
561
+ "31110010",
562
+ "31110020",
563
+ "31110030",
564
+ "31120010",
565
+ "31120020",
566
+ "31120030",
567
+ "31120040",
568
+ "31120050",
569
+ "31120060",
570
+ "31130010",
571
+ "31130020",
572
+ "31130030"
573
+ ]
574
+ },
575
+ "sector_to_groups": {
576
+ "101": [
577
+ "10110",
578
+ "10120",
579
+ "10130",
580
+ "10140",
581
+ "10150",
582
+ "10160"
583
+ ],
584
+ "102": [
585
+ "10200",
586
+ "10220",
587
+ "10230",
588
+ "10240",
589
+ "10250",
590
+ "10260",
591
+ "10270",
592
+ "10280",
593
+ "10290"
594
+ ],
595
+ "103": [
596
+ "10310",
597
+ "10320",
598
+ "10330",
599
+ "10340",
600
+ "10350",
601
+ "10360"
602
+ ],
603
+ "104": [
604
+ "10410",
605
+ "10420"
606
+ ],
607
+ "205": [
608
+ "20510",
609
+ "20520",
610
+ "20525",
611
+ "20540",
612
+ "20550",
613
+ "20560"
614
+ ],
615
+ "206": [
616
+ "20610",
617
+ "20620",
618
+ "20630",
619
+ "20645",
620
+ "20650",
621
+ "20660",
622
+ "20670"
623
+ ],
624
+ "207": [
625
+ "20710",
626
+ "20720"
627
+ ],
628
+ "308": [
629
+ "30810",
630
+ "30820",
631
+ "30830"
632
+ ],
633
+ "309": [
634
+ "30910",
635
+ "30920"
636
+ ],
637
+ "310": [
638
+ "31010",
639
+ "31020",
640
+ "31030",
641
+ "31040",
642
+ "31050",
643
+ "31060",
644
+ "31070",
645
+ "31080",
646
+ "31090"
647
+ ],
648
+ "311": [
649
+ "31110",
650
+ "31120",
651
+ "31130"
652
+ ]
653
+ },
654
+ "summary": {
655
+ "code_count": 145,
656
+ "group_count": 55,
657
+ "rows": 53585,
658
+ "sector_count": 11
659
+ }
660
+ }
models/cascade_training_summary.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "rows": 53585,
3
+ "sector_count": 11,
4
+ "group_count": 55,
5
+ "code_count": 145,
6
+ "vectorizer": {
7
+ "max_features": 50000,
8
+ "vocabulary_size": 50000,
9
+ "ngram_range": [
10
+ 1,
11
+ 2
12
+ ],
13
+ "sublinear_tf": true,
14
+ "stop_words": "english"
15
+ },
16
+ "artifacts": {
17
+ "l1_type": "svm",
18
+ "l2_total": 11,
19
+ "l2_constants": 0,
20
+ "l3_total": 55,
21
+ "l3_constants": 22
22
+ }
23
+ }
models/cascade_vectorizer.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8f2c64076effd5c90852b9a74597cf2f27d0f3c5dc5c855976ecf05b092a608
3
+ size 2195363
models/mstar_labels_full.json ADDED
@@ -0,0 +1,147 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "10110010": "Single Segment",
3
+ "10120010": "Cement",
4
+ "10130010": "Single Segment",
5
+ "10130020": "Single segment",
6
+ "10140010": "Single Segment",
7
+ "10140020": "Paper",
8
+ "10150010": "Single segment",
9
+ "10150020": "Copper",
10
+ "10150030": "Single Segment",
11
+ "10150040": "Single Segment",
12
+ "10150050": "Silver",
13
+ "10150060": "Single Segment",
14
+ "10160010": "Single Segment",
15
+ "10160020": "Single segment",
16
+ "10200010": "Single Segment",
17
+ "10200020": "Single segment",
18
+ "10200030": "Single segment",
19
+ "10200040": "Single segment",
20
+ "10220010": "Single Segment",
21
+ "10230010": "Single Segment",
22
+ "10240010": "Single Segment",
23
+ "10240020": "Single Segment",
24
+ "10240030": "Footwear",
25
+ "10250010": "Single Segment",
26
+ "10260010": "Single Segment",
27
+ "10270010": "Single Segment",
28
+ "10280010": "Single Segment",
29
+ "10280020": "Retail",
30
+ "10280030": "Single Segment",
31
+ "10280040": "Single Segment",
32
+ "10280050": "Single Segment",
33
+ "10280060": "Single Segment",
34
+ "10290010": "Single Segment",
35
+ "10290020": "Single Segment",
36
+ "10290030": "Hotel",
37
+ "10290040": "Single Segment",
38
+ "10290050": "Tourism",
39
+ "10310010": "Single Segment",
40
+ "10320010": "International Banking",
41
+ "10320020": "Single Segment",
42
+ "10320030": "Mortgage Banking",
43
+ "10330010": "Single Segment",
44
+ "10330020": "Single Segment",
45
+ "10340010": "Life Insurance",
46
+ "10340020": "Insurance",
47
+ "10340030": "Reinsurance",
48
+ "10340040": "Single Segment",
49
+ "10340050": "Insurance",
50
+ "10340060": "Insurance",
51
+ "10350010": "Single Segment",
52
+ "10350020": "Others",
53
+ "10360010": "Single Segment",
54
+ "10410010": "Property development",
55
+ "10410020": "Property investment",
56
+ "10410030": "Real estate",
57
+ "10420010": "Single Segment",
58
+ "10420020": "Hospitality",
59
+ "10420030": "Industrial",
60
+ "10420040": "Office",
61
+ "10420050": "Single segment",
62
+ "10420060": "Single Segment",
63
+ "10420070": "Single Segment",
64
+ "10420080": "Single Segment",
65
+ "10420090": "Single Segment",
66
+ "20510010": "Single Segment",
67
+ "20510020": "Single Segment",
68
+ "20520010": "Beverages",
69
+ "20525010": "Sugar",
70
+ "20525020": "Single Segment",
71
+ "20525030": "Single Segment",
72
+ "20525040": "Single Segment",
73
+ "20540010": "Education",
74
+ "20550010": "Single Segment",
75
+ "20550020": "Single Segment",
76
+ "20550030": "Retail",
77
+ "20560010": "Single Segment",
78
+ "20610010": "Single Segment",
79
+ "20620010": "Pharmaceuticals",
80
+ "20620020": "Single segment",
81
+ "20630010": "Single Segment",
82
+ "20645010": "Healthcare",
83
+ "20645020": "Retail",
84
+ "20645030": "Single Segment",
85
+ "20650010": "Single Segment",
86
+ "20650020": "Single Segment",
87
+ "20660010": "Single Segment",
88
+ "20670010": "Distribution",
89
+ "20710010": "Power",
90
+ "20710020": "Energy",
91
+ "20720010": "Water",
92
+ "20720020": "Single Segment",
93
+ "20720030": "Gas",
94
+ "20720040": "Energy",
95
+ "30810010": "Single Segment",
96
+ "30820010": "Single Segment",
97
+ "30820020": "Single Segment",
98
+ "30820030": "Single Segment",
99
+ "30820040": "Single Segment",
100
+ "30830010": "Single Segment",
101
+ "30830020": "Single Segment",
102
+ "30910010": "Drilling",
103
+ "30910020": "Single Segment",
104
+ "30910030": "Single segment",
105
+ "30910040": "Single Segment",
106
+ "30910050": "Refining",
107
+ "30910060": "Single Segment",
108
+ "30920010": "Coal",
109
+ "30920020": "Uranium",
110
+ "31010010": "Single Segment",
111
+ "31020010": "Single Segment",
112
+ "31020020": "Single Segment",
113
+ "31020030": "Single Segment",
114
+ "31020040": "Other",
115
+ "31020050": "Single Segment",
116
+ "31030010": "Others",
117
+ "31040010": "Construction",
118
+ "31040020": "Single Segment",
119
+ "31040030": "Single Segment",
120
+ "31050010": "Single Segment",
121
+ "31060010": "Single Segment",
122
+ "31070010": "Single Segment",
123
+ "31070020": "Single Segment",
124
+ "31070030": "Single Segment",
125
+ "31070040": "Single Segment",
126
+ "31070050": "Single segment",
127
+ "31070060": "Single Segment",
128
+ "31080010": "Aviation",
129
+ "31080020": "Single Segment",
130
+ "31080030": "Single Segment",
131
+ "31080040": "Single Segment",
132
+ "31080050": "Truckload",
133
+ "31080060": "Logistics",
134
+ "31090010": "Single segment",
135
+ "31110010": "Single Segment",
136
+ "31110020": "Single Segment",
137
+ "31110030": "Single Segment",
138
+ "31120010": "Single segment",
139
+ "31120020": "Single Segment",
140
+ "31120030": "Single Segment",
141
+ "31120040": "Single Segment",
142
+ "31120050": "Single Segment",
143
+ "31120060": "Single segment",
144
+ "31130010": "Single segment",
145
+ "31130020": "Single segment",
146
+ "31130030": "Single Segment"
147
+ }
models/sub_industry_labels.json ADDED
@@ -0,0 +1,430 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "1011001001": "Crop Protection",
3
+ "1011001002": "Ammonia",
4
+ "1011001003": "Trading",
5
+ "1011001004": "Fertilizers",
6
+ "1012001001": "Mineral products",
7
+ "1012001002": "Concrete",
8
+ "1012001003": "Concrete",
9
+ "1012001004": "Distribution",
10
+ "1012001005": "Performance Surfaces",
11
+ "1012001006": "Cement",
12
+ "1012001099": "Building materials",
13
+ "1013001001": "Wholesale business",
14
+ "1013001002": "Petrochemical",
15
+ "1013001003": "Chemicals",
16
+ "1013001004": "ONM Environmental",
17
+ "1013001099": "Chemicals",
18
+ "1013002001": "Telko",
19
+ "1013002002": "Dyno Nobel Americas (DNA)",
20
+ "1013002003": "Adhesive Solutions",
21
+ "1013002004": "Performance Coatings",
22
+ "1013002005": "Nutrition & Care",
23
+ "1013002006": "Gas & Services",
24
+ "1013002007": "Gloves",
25
+ "1013002008": "Global markets & Technologies",
26
+ "1013002009": "Performance Chemicals",
27
+ "1013002010": "Plastic",
28
+ "1013002011": "Renewables",
29
+ "1014001001": "Wood products",
30
+ "1014001002": "Wood Products",
31
+ "1014001003": "Direct Purchase and Original Design Manufacturer (ODM)",
32
+ "1014001004": "Wood Processing",
33
+ "1014001005": "Forestry and Other Activities",
34
+ "1014001006": "Forest activity",
35
+ "1014001007": "Forest",
36
+ "1014001008": "Forestry",
37
+ "1014002001": "Paper",
38
+ "1014002002": "Pulp",
39
+ "1014002003": "Trading Division",
40
+ "1015001001": "Aluminium",
41
+ "1015001002": "Primary aluminum plate",
42
+ "1015002001": "Copper",
43
+ "1015002002": "Trading",
44
+ "1015002003": "Copper Royalty",
45
+ "1015003001": "Mining",
46
+ "1015003002": "Minerals Management",
47
+ "1015003003": "Other Non-Metallurgical",
48
+ "1015003099": "Mining",
49
+ "1015004001": "Exploration",
50
+ "1015004002": "Royalty interests",
51
+ "1015005001": "Silvertip",
52
+ "1015005002": "Steel-making Royalty",
53
+ "1015006001": "Exploration",
54
+ "1015006002": "Mining",
55
+ "1016001001": "Metallurgical (MET)",
56
+ "1016002001": "Iron Ore",
57
+ "1016002002": "Royalty",
58
+ "1016002003": "Steel",
59
+ "1016002004": "Trading",
60
+ "1020001001": "Automotive",
61
+ "1020001002": "Others",
62
+ "1020002001": "Engine",
63
+ "1020002002": "Motorcycles",
64
+ "1020002003": "Automotive",
65
+ "1020002004": "Mobility technology solutions",
66
+ "1020003001": "Tire",
67
+ "1020003002": "Automotive",
68
+ "1020003003": "Single segment",
69
+ "1020003004": "Motive power",
70
+ "1020004002": "Marine",
71
+ "1020004003": "Electric Mobility & Other Vehicles",
72
+ "1020004099": "Corporate / All Other",
73
+ "1022001001": "Goods",
74
+ "1022001002": "Home & Outdoor",
75
+ "1022001003": "International segment",
76
+ "1022001004": "Bedding Products",
77
+ "1022001005": "Wholesale",
78
+ "1022001006": "Manufacturing",
79
+ "1022001007": "Lighting",
80
+ "1023001001": "Housing",
81
+ "1023001002": "Renovation",
82
+ "1024001001": "Spinning",
83
+ "1024001002": "Vincenzo Zucchi and Branches",
84
+ "1024001003": "Fibertex Nonwovens",
85
+ "1024001099": "Textile",
86
+ "1024002001": "Textile",
87
+ "1024002003": "Wholesale",
88
+ "1024003001": "Footwear",
89
+ "1024003002": "Wholesale",
90
+ "1024003003": "Manufacturing",
91
+ "1025001001": "Beverage packaging, Europe, Middle East and Africa (EMEA)",
92
+ "1025001002": "Packaging",
93
+ "1025001003": "Amorim Cork",
94
+ "1025001004": "Packaging",
95
+ "1025001005": "Foodservice Packaging",
96
+ "1025001099": "Packaging",
97
+ "1026001001": "Legal Services",
98
+ "1026001002": "Cemetery",
99
+ "1027001001": "Others",
100
+ "1028001001": "Retail",
101
+ "1028002001": "Retail",
102
+ "1028003001": "Water Solutions",
103
+ "1028003002": "Retail-Flooring",
104
+ "1028003099": "Home Fashion",
105
+ "1028004001": "Other",
106
+ "1028005001": "Food Delivery",
107
+ "1028005002": "E-commerce",
108
+ "1028006001": "Retail",
109
+ "1028006002": "Charging Services",
110
+ "1028006003": "Publishing",
111
+ "1028006004": "Rebel",
112
+ "1028006005": "Retail",
113
+ "1028006006": "Home Shopping",
114
+ "1028006007": "Direct-to-Consumer",
115
+ "1028006008": "Retail",
116
+ "1028006009": "Retail - Company-owned stores",
117
+ "1028006099": "Retail",
118
+ "1029001001": "Online",
119
+ "1029001002": "Gaming",
120
+ "1029002001": "North America",
121
+ "1029002002": "Others",
122
+ "1029002003": "Cruise",
123
+ "1029002099": "Others",
124
+ "1029003001": "Hotel",
125
+ "1029004001": "Hospitality",
126
+ "1029004002": "Casino",
127
+ "1029005001": "Travel business",
128
+ "1029005002": "Tourism",
129
+ "1031001001": "Single Segment",
130
+ "1031001002": "Asset Management",
131
+ "1031001003": "Wealth Management",
132
+ "1031001004": "Private Equity",
133
+ "1031001005": "Trust",
134
+ "1031001099": "Asset management",
135
+ "1032001001": "International Banking",
136
+ "1032001002": "Commercial Banking",
137
+ "1032001003": "Single Segment",
138
+ "1032001099": "Treasury",
139
+ "1032002001": "Banking",
140
+ "1032002002": "Corporate banking",
141
+ "1032002099": "Treasury",
142
+ "1032003001": "Mortgage Banking",
143
+ "1033001001": "Investment Banking",
144
+ "1033001002": "Securities",
145
+ "1033002001": "Markets",
146
+ "1033002002": "Ratings",
147
+ "1033002003": "Commodity Insights",
148
+ "1034001001": "Life Insurance",
149
+ "1034001002": "Health",
150
+ "1034002001": "Insurance",
151
+ "1034002002": "Motor",
152
+ "1034002003": "Casualty",
153
+ "1034002004": "Bamboo",
154
+ "1034003001": "Reinsurance",
155
+ "1034004001": "Enact",
156
+ "1034004002": "Nib Travel",
157
+ "1034004099": "Insurance",
158
+ "1034005001": "Insurance",
159
+ "1034006001": "Insurance",
160
+ "1035001001": "Single segment",
161
+ "1035002001": "Others",
162
+ "1035002002": "Others",
163
+ "1036001001": "Leasing business",
164
+ "1036001002": "Servicing",
165
+ "1036001003": "Factoring",
166
+ "1041001001": "Property development",
167
+ "1041001002": "Property development",
168
+ "1041002001": "Property investment",
169
+ "1041002002": "Property management",
170
+ "1041002003": "Others",
171
+ "1041003001": "Real estate",
172
+ "1042001001": "Outpatient Medical",
173
+ "1042001099": "Senior Housing Operating Portfolio (SHOP)",
174
+ "1042002001": "Hotels",
175
+ "1042003001": "Industrial",
176
+ "1042004001": "Office",
177
+ "1042005001": "Single segment",
178
+ "1042005002": "Home Sales and Rentals Operations",
179
+ "1042006001": "Retail",
180
+ "1042006002": "Retail",
181
+ "1042007001": "Single Segment",
182
+ "1042008001": "Billboard",
183
+ "1042008002": "Domestic Site Leasing",
184
+ "1042008003": "Timberlands",
185
+ "1042008099": "Wood Products",
186
+ "1042009001": "Other",
187
+ "2051001001": "Beer",
188
+ "2051002001": "Single segment",
189
+ "2051002002": "Spirits",
190
+ "2052001001": "Beverages",
191
+ "2052001002": "Beverages",
192
+ "2052501001": "Sugar",
193
+ "2052501002": "International",
194
+ "2052501099": "Single segment",
195
+ "2052502001": "Plantation",
196
+ "2052502002": "Farming",
197
+ "2052502003": "Poultry",
198
+ "2052502004": "Farming",
199
+ "2052503001": "Home Care",
200
+ "2052503002": "Cosmetics",
201
+ "2052504001": "Food",
202
+ "2052504002": "Consumer Health Products",
203
+ "2052504003": "Ice Cream",
204
+ "2054001001": "Education",
205
+ "2054001002": "Direct offices",
206
+ "2055001001": "Consumables",
207
+ "2055002001": "Wholesale",
208
+ "2055003001": "Retail",
209
+ "2056001001": "Tobacco",
210
+ "2056001002": "Distribution",
211
+ "2061001001": "Single Segment",
212
+ "2061001002": "Single Segment",
213
+ "2061001003": "Ionis operations",
214
+ "2061001004": "Single Segment",
215
+ "2062001001": "Pharmaceutical",
216
+ "2062002001": "Pharmaceuticals",
217
+ "2063001001": "Medicaid",
218
+ "2064501001": "Healthcare",
219
+ "2064501002": "Healthcare",
220
+ "2064501003": "Nursing care business",
221
+ "2064501004": "Healthcare services",
222
+ "2064502001": "Retail",
223
+ "2064503001": "Scientific, Technical & Medical",
224
+ "2064503002": "Global Technology",
225
+ "2064503003": "Patient Care",
226
+ "2064503004": "Houston We Have Software",
227
+ "2064503099": "Single Segment",
228
+ "2065001001": "Diagnostics",
229
+ "2065001002": "Medical",
230
+ "2065002001": "Dental business",
231
+ "2065002002": "Life Sciences",
232
+ "2065002003": "Others",
233
+ "2066001001": "Diagnostics",
234
+ "2066001002": "Discovery and Safety Assessment (DSA)",
235
+ "2067001001": "Third party products",
236
+ "2067001002": "Distribution",
237
+ "2067001099": "Distribution",
238
+ "2071001001": "Energy",
239
+ "2071001002": "Heat generation in of the Russian Federation",
240
+ "2071001003": "Cogeneration",
241
+ "2071001004": "Emirates Central Cooling Systems Corporation PJSC (EMPOWER)",
242
+ "2071002001": "Renewables",
243
+ "2071002002": "Clean Energy Ventures (CEV)",
244
+ "2071002003": "Renewables",
245
+ "2071002004": "Tidal Stream",
246
+ "2071002005": "Energy",
247
+ "2071002006": "Product",
248
+ "2071002007": "Thermal power stations",
249
+ "2071002008": "Gas",
250
+ "2071002009": "Energy",
251
+ "2071002010": "Sale of power",
252
+ "2071002011": "Geothermal energy",
253
+ "2071002012": "Own Operation",
254
+ "2071002013": "Energy",
255
+ "2072001001": "Water",
256
+ "2072001002": "Water",
257
+ "2072001003": "Water",
258
+ "2072001004": "Single Segment",
259
+ "2072002001": "T-Power",
260
+ "2072002002": "Power",
261
+ "2072002003": "Power",
262
+ "2072002004": "Electric power generation (Nuclear)",
263
+ "2072002005": "Integrated Energy",
264
+ "2072002006": "Distribution",
265
+ "2072002007": "Others",
266
+ "2072003001": "New Energy Technologies Strategic Business Unit (SBU)",
267
+ "2072003002": "Wisconsin Power and Light Company (WPL)",
268
+ "2072003003": "Gas",
269
+ "2072004001": "Energy",
270
+ "3081001001": "Telecommunications",
271
+ "3081001002": "Business",
272
+ "3082001001": "Media",
273
+ "3082001002": "Digital marketing",
274
+ "3082001003": "Marketing",
275
+ "3082002001": "Media",
276
+ "3082002002": "Havas Group",
277
+ "3082003001": "Broadcast",
278
+ "3082003002": "Radio",
279
+ "3082004001": "Television",
280
+ "3082004002": "Cinema operation",
281
+ "3082004003": "Theme park operation",
282
+ "3082004004": "Sports Business",
283
+ "3082004005": "Music",
284
+ "3082004006": "Media",
285
+ "3082004007": "Bell Media",
286
+ "3083001001": "Media",
287
+ "3083001002": "Classifieds",
288
+ "3083002001": "Single segment",
289
+ "3091001001": "Drilling Services",
290
+ "3091001002": "Drilling",
291
+ "3091002001": "Upstream",
292
+ "3091002002": "Exploration and Production",
293
+ "3091003001": "Downstream",
294
+ "3091004001": "Pipeline and Storage",
295
+ "3091004002": "Midstream",
296
+ "3091004003": "Transmission",
297
+ "3091004005": "Oil & Gas Royalties",
298
+ "3091005001": "Refining",
299
+ "3091005002": "Marketing",
300
+ "3091006001": "Sensing & Monitoring (SMO)",
301
+ "3091006002": "Production Services",
302
+ "3092001001": "Mining",
303
+ "3092002001": "Uranium",
304
+ "3101001001": "Defence",
305
+ "3101001002": "Shipbuilding",
306
+ "3101001004": "Marine",
307
+ "3101001005": "Aerospace",
308
+ "3101001006": "Expeditionary Services",
309
+ "3102001001": "Print",
310
+ "3102001002": "Others",
311
+ "3102001003": "Licensing",
312
+ "3102001004": "Financial Services",
313
+ "3102001005": "Legal",
314
+ "3102001099": "Others",
315
+ "3102002001": "Consulting",
316
+ "3102002002": "Research",
317
+ "3102003001": "Engine Leasing",
318
+ "3102003002": "Leasing",
319
+ "3102003003": "Healthy life service",
320
+ "3102003004": "Leasing",
321
+ "3102003005": "Aircraft ownership and leasing",
322
+ "3102003099": "Leasing business",
323
+ "3102004001": "Security",
324
+ "3102004003": "Safety",
325
+ "3102005001": "Recruitment",
326
+ "3102005002": "Others",
327
+ "3103001001": "Others",
328
+ "3104001001": "Engineering",
329
+ "3104001002": "Construction",
330
+ "3104001003": "Construction business",
331
+ "3104001007": "Airports",
332
+ "3104001008": "Civil engineering",
333
+ "3104001009": "Electric Vehicle Charging (EV)",
334
+ "3104001010": "United States building services",
335
+ "3104001099": "Construction",
336
+ "3104002001": "Infrastructure",
337
+ "3104002002": "Service business",
338
+ "3104003001": "Ruukki Construction",
339
+ "3104003002": "Energy saving business",
340
+ "3104003004": "Ventilation Systems",
341
+ "3104003005": "Safety",
342
+ "3104003099": "Manufacturing",
343
+ "3105001001": "Construction machinery business",
344
+ "3105001002": "Manufacturing",
345
+ "3105001003": "Commercial Vehicles",
346
+ "3105001004": "Sustainable mobility",
347
+ "3105001005": "Agriculture",
348
+ "3106001001": "Distribution",
349
+ "3106001002": "Distribution",
350
+ "3107001001": "ACCO Brands North America",
351
+ "3107001002": "Industry",
352
+ "3107002001": "Industrial",
353
+ "3107002002": "Machinery",
354
+ "3107002003": "Food",
355
+ "3107002004": "Corporate and other",
356
+ "3107002005": "Technologies",
357
+ "3107002006": "Electrolyser",
358
+ "3107002007": "Energy",
359
+ "3107002008": "Renewables",
360
+ "3107002098": "Single segment",
361
+ "3107002099": "Climate & Sustainability Technologies",
362
+ "3107003001": "Manufacturing",
363
+ "3107004001": "Environmental Solutions",
364
+ "3107004002": "Engineering",
365
+ "3107004003": "Engineered Systems segment",
366
+ "3107005001": "Outdoor power equipment",
367
+ "3107006001": "Cables",
368
+ "3107006002": "RF Connector and Cable Assembly",
369
+ "3107006003": "Power Systems",
370
+ "3107006004": "Others",
371
+ "3107006005": "Air and Liquid Processing (ALP)",
372
+ "3107006099": "Professional",
373
+ "3108001001": "Aviation",
374
+ "3108001002": "Leisure",
375
+ "3108001099": "Other",
376
+ "3108002001": "Air Transport",
377
+ "3108002002": "Overnight Air Cargo",
378
+ "3108003001": "Transportation business",
379
+ "3108003002": "Railroad",
380
+ "3108003003": "Manufacturing",
381
+ "3108003004": "Other businesses",
382
+ "3108003005": "Transportation",
383
+ "3108003006": "Transportation",
384
+ "3108004001": "Ferry Operations and Other",
385
+ "3108004002": "Global Short Sea Shipping",
386
+ "3108004003": "Port services",
387
+ "3108004004": "Shipping",
388
+ "3108004005": "Ship chartering services",
389
+ "3108004006": "Others",
390
+ "3108004007": "Transport",
391
+ "3108004008": "Container vessels segment",
392
+ "3108005001": "Truckload",
393
+ "3108006001": "Delivery",
394
+ "3108006002": "Logistics",
395
+ "3109001001": "Recycling",
396
+ "3109001002": "Environmental operation",
397
+ "3109001004": "Recycling",
398
+ "3109001005": "Ciclus Ambiental",
399
+ "3109001006": "Sewage",
400
+ "3109001007": "Environmental Services",
401
+ "3111001001": "Cloud Services Business (Discontinued operations)",
402
+ "3111001002": "Green Technologies",
403
+ "3111001003": "Consulting",
404
+ "3111001099": "Others",
405
+ "3111002001": "Fintech",
406
+ "3111002002": "Others",
407
+ "3111002003": "Edtech",
408
+ "3111002004": "RiskOn International, Inc. (ROI)",
409
+ "3111002005": "Software",
410
+ "3111003001": "Single Segment",
411
+ "3111003002": "More Personal Computing",
412
+ "3111003003": "Tucows Domains",
413
+ "3111003004": "Digital Agreements",
414
+ "3111003005": "Product licenses and related activities",
415
+ "3111003006": "Payments",
416
+ "3111003099": "Other",
417
+ "3112001001": "Enterprise",
418
+ "3112001002": "Smart Infrastructure Solutions",
419
+ "3112002001": "Single Segment",
420
+ "3112003001": "Consumer Electronics",
421
+ "3112004001": "Others",
422
+ "3112004002": "Printed Circuit Board (PCB) Business",
423
+ "3112005001": "Electronics",
424
+ "3112005002": "Distribution",
425
+ "3112006001": "Digital Imaging",
426
+ "3113001001": "Semiconductor",
427
+ "3113002001": "Single Segment",
428
+ "3113002002": "Storage Business Unit (SBU)",
429
+ "3113003001": "Solar"
430
+ }
models/t2_cascade_L1.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:937b08fcec2d04ae4ecbf6fcfd7bec52b73875b59f0d564e7aa3396630a9f973
3
+ size 7041036
models/t2_cascade_L2.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b439823cb5d388110c71dd3f26e1ab1640ea9503fc22435f6dbe1a7bc158b1c6
3
+ size 33285806
models/t2_cascade_L3.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78203548f4ba45faa7a0e4b6e85da7f86b6fb0d7bbb2532e11ed23063406bf7f
3
+ size 71696814
models/t2_cascade_L4.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22bc24d8ae125f051eba029ab40afca46afa4e6d0334a559d64952db714392e4
3
+ size 212532544
models/t2_cascade_L4_seg.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0fc044a00bf6bed817db212a362f9051774e68bcb7340cc8596752429c3e96a
3
+ size 159411888
models/t2_cascade_seg_vec.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73a683057e36668d042384176723d212b5fdfb5c4ca6b10cfa0e209bec7e6629
3
+ size 2646345
models/t2_cascade_summary.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "rows": 27537,
3
+ "train_rows": 22029,
4
+ "test_rows": 5508,
5
+ "sub_code_count": 428,
6
+ "mstar_count": 145,
7
+ "macro_f1": 0.5541,
8
+ "accuracy": 0.7435,
9
+ "mstar_accuracy": 0.8842,
10
+ "deberta_baseline": 36.39,
11
+ "oracle_ceiling": 62.26,
12
+ "l4_vectorizer": {
13
+ "max_features": 60000,
14
+ "vocabulary_size": 60000,
15
+ "text": "SegmentName + SegmentDescription",
16
+ "ngram_range": [
17
+ 1,
18
+ 2
19
+ ]
20
+ },
21
+ "l4_artifacts": {
22
+ "total": 145,
23
+ "trivial": 40
24
+ },
25
+ "t1_cascade_used_for": "L1->L2->L3 (MSTAR prediction)"
26
+ }
models/t2_cascade_vectorizer.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf216365496e1bf9c89c1d39c0423517c24b54223e0f7a7b5e2864b805ca5afd
3
+ size 3549872
models/task1_rf_model.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0a0257472c8b4579eadd1f1659438d9aaba177b66085cded461bdf6d3248285
3
+ size 4953930
models/task1_rf_model.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e6e77d7af8c982de9e74db80d6b71fa5afae3ad6a4c495a3dbb60d85ec56c6a
3
+ size 11603167
models/task1_svm_model.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af89429e4877241f7a85e9c50adb37aae1851cc6b384954c39a64ab789a00eaa
3
+ size 58003124
models/task1_tfidf_vectorizer.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd41d4550644191612c1793b82c1048ce297b1cd52b577a11be9c72bfa7fb770
3
+ size 2195363
models/task2_svc_model.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9488eb08fd1a2c424a70a689e8020d2461308cfa6b14d7449a91e56927cd06f5
3
+ size 28806556
models/task2_tfidf_vectorizer.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b27908bc038cf1fa886bcd8f39ee4237886a7df14483126877705b7d0ba3cc91
3
+ size 423425