ivanleomk commited on
Commit
4e63008
·
verified ·
1 Parent(s): a9d57c2

Add BERTopic model

Browse files
Files changed (2) hide show
  1. topic_embeddings.safetensors +1 -1
  2. topics.json +184 -226
topic_embeddings.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1384d89ba5fb76e29d40fbf2f181cc734803e4f0132a177597658df4740d522
3
  size 7768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49c23a4ff853ab98e18f2d8f65c3860ed7860997624ec7b5aac473581ecaae2f
3
  size 7768
topics.json CHANGED
@@ -2,466 +2,424 @@
2
  "topic_representations": {
3
  "-1": [
4
  [
5
- "the",
6
- 0.09492240491569903
7
  ],
8
  [
9
- "verification",
10
- 0.06970153771334807
11
  ],
12
  [
13
- "my",
14
- 0.06435254147435229
15
  ],
16
  [
17
  "for",
18
- 0.06319899047478812
19
  ],
20
  [
21
- "code",
22
- 0.057297419223293365
23
  ],
24
  [
25
- "whats",
26
- 0.05231884901424003
27
  ],
28
  [
29
- "step",
30
- 0.05048680075415213
31
  ],
32
  [
33
- "email",
34
- 0.04766755006544382
35
  ],
36
  [
37
- "to",
38
- 0.04691532073995217
39
  ],
40
  [
41
- "up",
42
- 0.046032377461675815
43
  ]
44
  ],
45
  "0": [
46
  [
47
- "klarna",
48
- 0.09050803422673742
49
  ],
50
  [
51
- "to",
52
- 0.07953560782302285
53
  ],
54
  [
55
  "my",
56
- 0.06794819842776671
57
  ],
58
  [
59
- "and",
60
- 0.054212681447924974
61
  ],
62
  [
63
- "the",
64
- 0.05221408034992652
65
  ],
66
  [
67
- "for",
68
- 0.04986631308226638
69
  ],
70
  [
71
- "im",
72
- 0.046128149776214315
73
  ],
74
  [
75
- "but",
76
- 0.04290244254915681
77
  ],
78
  [
79
- "card",
80
- 0.038263701287704434
81
  ],
82
  [
83
- "with",
84
- 0.03806685276761612
85
  ]
86
  ],
87
  "1": [
88
  [
89
  "my",
90
- 0.0775192391698972
91
  ],
92
  [
93
  "the",
94
- 0.07083659770502172
95
  ],
96
  [
97
- "return",
98
- 0.06282550489124095
99
  ],
100
  [
101
- "store",
102
- 0.06030699514817177
103
  ],
104
  [
105
- "still",
106
- 0.05232050981790259
107
  ],
108
  [
109
- "and",
110
- 0.048850488312254275
111
  ],
112
  [
113
- "to",
114
- 0.04440410670920632
115
  ],
116
  [
117
- "but",
118
- 0.04435407181783497
119
  ],
120
  [
121
- "weeks",
122
- 0.04390700519309823
123
  ],
124
  [
125
- "refund",
126
- 0.04301759717367365
127
  ]
128
  ],
129
  "2": [
130
  [
131
- "card",
132
- 0.15173156476046484
133
  ],
134
  [
135
- "onetime",
136
- 0.09616516102360437
137
  ],
138
  [
139
  "my",
140
- 0.06662856796086986
141
  ],
142
  [
143
- "it",
144
- 0.06433874526122811
145
  ],
146
  [
147
- "for",
148
- 0.062288342197053426
149
  ],
150
  [
151
- "but",
152
- 0.05809184320425647
153
  ],
154
  [
155
- "to",
156
- 0.049909093780171436
157
  ],
158
  [
159
- "and",
160
- 0.04702598592456893
161
  ],
162
  [
163
- "is",
164
- 0.04567791318517409
165
  ],
166
  [
167
- "the",
168
- 0.044549831866569335
169
  ]
170
  ],
171
  "3": [
172
  [
173
- "payment",
174
- 0.12112085020085236
175
  ],
176
  [
177
- "my",
178
- 0.0998606282868899
179
  ],
180
  [
181
- "due",
182
- 0.09304345529961551
183
  ],
184
  [
185
- "date",
186
- 0.08822107880850269
187
  ],
188
  [
189
- "the",
190
- 0.07715617939671793
191
  ],
192
  [
193
- "is",
194
- 0.06934959789854092
195
  ],
196
  [
197
- "cant",
198
- 0.06277156684324331
199
  ],
200
  [
201
- "plan",
202
- 0.06161981560504852
203
  ],
204
  [
205
- "than",
206
- 0.04929585248403881
207
  ],
208
  [
209
- "an",
210
- 0.04763634941129883
211
  ]
212
  ]
213
  },
214
  "topics": [
215
- 0,
216
- 3,
217
- 0,
218
- 0,
219
- 0,
220
- 1,
221
- 1,
222
- 0,
223
- 3,
224
- 0,
225
  2,
226
- 0,
227
- 1,
228
  3,
229
  2,
230
- 0,
231
  1,
 
 
232
  0,
233
- 1,
234
  0,
 
235
  1,
236
  1,
237
- 0,
 
238
  0,
239
  1,
240
- 0,
241
- 2,
242
- 3,
243
- 3,
244
  1,
 
 
 
245
  0,
246
- 0,
 
247
  0,
248
  1,
249
- 3,
250
- 3,
251
  1,
 
252
  1,
253
  0,
254
  0,
255
- 1,
256
  0,
 
257
  1,
258
- 0,
259
- 0,
260
- 3,
261
- 3,
262
  1,
263
- 2,
264
- 0,
265
  1,
266
  0,
267
  0,
268
  0,
269
  1,
270
- 1,
271
  -1,
272
  3,
273
- 3,
274
- 1,
275
- 2,
276
  0,
277
- 2,
278
- 2,
279
- 2,
280
  0,
281
  1,
282
  2,
283
  1,
284
- 1,
285
- 0,
286
  0,
287
  3,
288
  1,
289
- 2,
290
  3,
291
- 1,
 
292
  0,
293
  0,
294
  0,
295
- 3,
296
  0,
297
- 2,
298
- 3,
299
- 1,
300
  0,
301
- 1,
302
- 1,
303
  0,
304
  0,
305
- 1,
306
- -1,
307
  0,
308
- 3,
309
- 2,
310
  0,
311
- 2,
312
- 1,
313
- -1,
314
- -1,
315
  0,
 
316
  1,
317
  0,
318
- 1,
319
- -1,
320
  0,
321
- 2,
322
- 3,
323
  0,
324
- 3,
325
- 1,
326
- 1,
327
  0,
328
  0,
329
- 3,
330
- 3,
331
- 1,
332
- 1,
333
- 3,
334
- 3,
335
- 1,
336
  0,
337
  0,
338
- 3,
339
  0,
340
- 1,
341
- 3,
342
- 1,
343
- 1,
344
  0,
345
  0,
346
  0,
347
  0,
348
- 1,
349
  0,
350
  0,
351
- -1,
352
  0,
353
  0,
354
  0,
355
- -1,
356
  0,
357
  0,
358
  0,
359
- -1,
360
- -1,
361
  0,
362
  0,
363
- 2,
364
  0,
365
- 1,
366
  0,
367
  0,
368
  0,
369
  0,
370
  0,
371
- 2,
372
- 1,
373
  0,
374
  0,
375
  0,
376
- -1,
377
  0,
 
 
 
 
 
 
378
  0,
379
  -1,
380
  0,
381
  1,
382
- -1,
383
- 2,
384
  2,
385
  2,
386
  1,
387
  1,
 
 
388
  1,
389
- 2,
390
- 0,
391
- 0,
392
- 2,
393
- 0,
394
- 0,
395
- 0,
396
  0,
 
 
 
 
 
 
397
  0,
 
398
  0,
 
399
  0,
 
 
400
  0,
 
 
401
  0,
402
  0,
 
403
  0,
 
404
  0,
405
- 2,
406
- 1,
407
  1,
408
  2,
 
 
 
 
409
  -1,
410
- 2,
411
  1,
412
  1,
413
- 2,
414
- 2,
415
  1,
 
 
416
  1,
 
 
 
 
 
 
417
  1,
 
 
 
 
 
 
 
418
  1,
419
  1,
420
  1,
421
- 2,
422
  1,
423
- -1,
424
  1,
425
  1,
426
- 2,
427
  1,
428
  1,
 
 
429
  1,
430
  1,
431
- 0,
432
- 0,
433
- -1,
434
- 0,
435
  -1,
436
  1,
437
  1,
438
  2,
439
- 0,
440
- 0,
441
- 0,
442
- 1,
443
- 0,
444
- 0,
445
- 0,
446
- 1,
447
  2,
448
  2,
449
- 1,
450
  2,
 
 
 
 
 
 
451
  -1,
452
  -1,
453
- 1,
454
  -1,
455
- 2,
456
- 0,
457
- 0
458
  ],
459
  "topic_sizes": {
460
- "0": 98,
461
- "3": 24,
462
- "1": 69,
463
- "2": 33,
464
- "-1": 19
465
  },
466
  "topic_mapper": [
467
  [
@@ -472,30 +430,30 @@
472
  [
473
  0,
474
  0,
475
- 3
476
  ],
477
  [
478
  1,
479
  1,
480
- 0
481
  ],
482
  [
483
  2,
484
  2,
485
- 2
486
  ],
487
  [
488
  3,
489
  3,
490
- 1
491
  ]
492
  ],
493
  "topic_labels": {
494
- "-1": "-1_the_verification_my_for",
495
- "0": "0_klarna_to_my_and",
496
- "1": "1_my_the_return_store",
497
- "2": "2_card_onetime_my_it",
498
- "3": "3_payment_my_due_date"
499
  },
500
  "custom_labels": null,
501
  "_outliers": 1,
 
2
  "topic_representations": {
3
  "-1": [
4
  [
5
+ "my",
6
+ 0.08799518181080801
7
  ],
8
  [
9
+ "account",
10
+ 0.059326501658507606
11
  ],
12
  [
13
+ "to",
14
+ 0.05276628466164253
15
  ],
16
  [
17
  "for",
18
+ 0.04988337664069772
19
  ],
20
  [
21
+ "klarna",
22
+ 0.04966294371387129
23
  ],
24
  [
25
+ "it",
26
+ 0.04817724739565724
27
  ],
28
  [
29
+ "and",
30
+ 0.04773332320924559
31
  ],
32
  [
33
+ "do",
34
+ 0.04746120132680609
35
  ],
36
  [
37
+ "now",
38
+ 0.04657601990689071
39
  ],
40
  [
41
+ "email",
42
+ 0.04610841330633907
43
  ]
44
  ],
45
  "0": [
46
  [
47
+ "refund",
48
+ 0.09940422642761668
49
  ],
50
  [
51
+ "nike",
52
+ 0.07683032839135416
53
  ],
54
  [
55
  "my",
56
+ 0.06939647373960416
57
  ],
58
  [
59
+ "for",
60
+ 0.06825921599830054
61
  ],
62
  [
63
+ "store",
64
+ 0.06529203162826891
65
  ],
66
  [
67
+ "returned",
68
+ 0.06417307365166852
69
  ],
70
  [
71
+ "to",
72
+ 0.05811550975406103
73
  ],
74
  [
75
+ "credit",
76
+ 0.054852815073062305
77
  ],
78
  [
79
+ "week",
80
+ 0.05161486059714016
81
  ],
82
  [
83
+ "got",
84
+ 0.0488549541590847
85
  ]
86
  ],
87
  "1": [
88
  [
89
  "my",
90
+ 0.08194872925948056
91
  ],
92
  [
93
  "the",
94
+ 0.07582570872862474
95
  ],
96
  [
97
+ "payment",
98
+ 0.06359397504213297
99
  ],
100
  [
101
+ "for",
102
+ 0.060504478365630956
103
  ],
104
  [
105
+ "to",
106
+ 0.05802307617868586
107
  ],
108
  [
109
+ "klarna",
110
+ 0.0532866752528021
111
  ],
112
  [
113
+ "pay",
114
+ 0.05328022874120398
115
  ],
116
  [
117
+ "it",
118
+ 0.04944506969554296
119
  ],
120
  [
121
+ "balance",
122
+ 0.04677175837053031
123
  ],
124
  [
125
+ "in",
126
+ 0.043295871574472254
127
  ]
128
  ],
129
  "2": [
130
  [
131
+ "to",
132
+ 0.08611821245586847
133
  ],
134
  [
135
+ "email",
136
+ 0.08542131137508129
137
  ],
138
  [
139
  "my",
140
+ 0.08050445649493329
141
  ],
142
  [
143
+ "account",
144
+ 0.06594563387765413
145
  ],
146
  [
147
+ "the",
148
+ 0.06273399836043649
149
  ],
150
  [
151
+ "im",
152
+ 0.062281987551117794
153
  ],
154
  [
155
+ "and",
156
+ 0.06190215495844553
157
  ],
158
  [
159
+ "klarna",
160
+ 0.06133766738838671
161
  ],
162
  [
163
+ "cant",
164
+ 0.059394864282436975
165
  ],
166
  [
167
+ "log",
168
+ 0.05335902378528902
169
  ]
170
  ],
171
  "3": [
172
  [
173
+ "card",
174
+ 0.18371592789949523
175
  ],
176
  [
177
+ "klarna",
178
+ 0.14533398247003027
179
  ],
180
  [
181
+ "it",
182
+ 0.10769781494531844
183
  ],
184
  [
185
+ "to",
186
+ 0.10616073937878079
187
  ],
188
  [
189
+ "need",
190
+ 0.08696456690340622
191
  ],
192
  [
193
+ "details",
194
+ 0.08692015580897279
195
  ],
196
  [
197
+ "my",
198
+ 0.08524048255658959
199
  ],
200
  [
201
+ "call",
202
+ 0.08396077556372948
203
  ],
204
  [
205
+ "do",
206
+ 0.08355148983573155
207
  ],
208
  [
209
+ "what",
210
+ 0.08115660687999471
211
  ]
212
  ]
213
  },
214
  "topics": [
 
 
 
 
 
 
 
 
 
 
215
  2,
 
 
216
  3,
217
  2,
 
218
  1,
219
+ -1,
220
+ -1,
221
  0,
 
222
  0,
223
+ -1,
224
  1,
225
  1,
226
+ 2,
227
+ 2,
228
  0,
229
  1,
 
 
 
 
230
  1,
231
+ -1,
232
+ -1,
233
+ 2,
234
  0,
235
+ 2,
236
+ -1,
237
  0,
238
  1,
239
+ -1,
 
240
  1,
241
+ -1,
242
  1,
243
  0,
244
  0,
 
245
  0,
246
+ 2,
247
  1,
 
 
 
 
248
  1,
 
 
249
  1,
250
  0,
251
  0,
252
  0,
253
  1,
254
+ 2,
255
  -1,
256
  3,
 
 
 
257
  0,
258
+ 0,
 
 
259
  0,
260
  1,
261
  2,
262
  1,
263
+ 2,
 
264
  0,
265
  3,
266
  1,
 
267
  3,
268
+ 2,
269
+ -1,
270
  0,
271
  0,
272
  0,
 
273
  0,
 
 
 
274
  0,
 
 
275
  0,
276
  0,
 
 
277
  0,
 
 
278
  0,
 
 
 
 
279
  0,
280
+ -1,
281
  1,
282
  0,
 
 
283
  0,
 
 
284
  0,
 
 
 
285
  0,
286
  0,
 
 
 
 
 
 
 
287
  0,
288
  0,
 
289
  0,
 
 
 
 
290
  0,
291
  0,
292
  0,
293
  0,
 
294
  0,
295
  0,
 
296
  0,
297
  0,
298
  0,
 
299
  0,
300
  0,
301
  0,
 
 
302
  0,
303
  0,
 
304
  0,
 
305
  0,
306
  0,
307
  0,
308
  0,
309
  0,
 
 
310
  0,
311
  0,
312
  0,
 
313
  0,
314
+ -1,
315
+ 1,
316
+ -1,
317
+ 3,
318
+ -1,
319
+ 1,
320
  0,
321
  -1,
322
  0,
323
  1,
 
 
324
  2,
325
  2,
326
  1,
327
  1,
328
+ -1,
329
+ 3,
330
  1,
331
+ 1,
332
+ 3,
 
 
 
 
 
333
  0,
334
+ 1,
335
+ 1,
336
+ 1,
337
+ 1,
338
+ -1,
339
+ 3,
340
  0,
341
+ -1,
342
  0,
343
+ 2,
344
  0,
345
+ 2,
346
+ -1,
347
  0,
348
+ 1,
349
+ 2,
350
  0,
351
  0,
352
+ 2,
353
  0,
354
+ -1,
355
  0,
 
 
356
  1,
357
  2,
358
+ 1,
359
+ -1,
360
+ -1,
361
+ 0,
362
  -1,
 
363
  1,
364
  1,
365
+ 3,
 
366
  1,
367
+ 2,
368
+ 0,
369
  1,
370
+ 3,
371
+ 3,
372
+ 2,
373
+ -1,
374
+ 0,
375
+ 0,
376
  1,
377
+ -1,
378
+ 0,
379
+ 2,
380
+ -1,
381
+ 0,
382
+ 0,
383
+ -1,
384
  1,
385
  1,
386
  1,
 
387
  1,
 
388
  1,
389
  1,
 
390
  1,
391
  1,
392
+ 3,
393
+ 3,
394
  1,
395
  1,
 
 
 
 
396
  -1,
397
  1,
398
  1,
399
  2,
 
 
 
 
 
 
 
 
400
  2,
401
  2,
 
402
  2,
403
+ 2,
404
+ 2,
405
+ 2,
406
+ 2,
407
+ 2,
408
+ 0,
409
  -1,
410
  -1,
411
+ 3,
412
  -1,
413
+ 3,
414
+ 3,
415
+ -1
416
  ],
417
  "topic_sizes": {
418
+ "2": 30,
419
+ "3": 16,
420
+ "1": 47,
421
+ "-1": 32,
422
+ "0": 76
423
  },
424
  "topic_mapper": [
425
  [
 
430
  [
431
  0,
432
  0,
433
+ 0
434
  ],
435
  [
436
  1,
437
  1,
438
+ 1
439
  ],
440
  [
441
  2,
442
  2,
443
+ 3
444
  ],
445
  [
446
  3,
447
  3,
448
+ 2
449
  ]
450
  ],
451
  "topic_labels": {
452
+ "-1": "-1_my_account_to_for",
453
+ "0": "0_refund_nike_my_for",
454
+ "1": "1_my_the_payment_for",
455
+ "2": "2_to_email_my_account",
456
+ "3": "3_card_klarna_it_to"
457
  },
458
  "custom_labels": null,
459
  "_outliers": 1,