ychu612 commited on
Commit
2c781eb
·
verified ·
1 Parent(s): 2aaac46

Add BERTopic model

Browse files
Files changed (2) hide show
  1. topic_embeddings.safetensors +1 -1
  2. topics.json +203 -108
topic_embeddings.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0fa2b39b1ef3adb7fcc1df931b51a80087de8812693b38fc09d08549fb625bbc
3
  size 4696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:302df81a99498998bf0bffec1f06d427e467982837d53790c506bbbf1dadae02
3
  size 4696
topics.json CHANGED
@@ -1,241 +1,336 @@
1
  {
2
  "topic_representations": {
3
  "-1": [
4
- [
5
- "babi",
6
- 0.08787724392598305
7
- ],
8
  [
9
  "not",
10
- 0.06249659052219682
11
  ],
12
  [
13
  "hospit",
14
- 0.06055553048673081
15
  ],
16
  [
17
  "child",
18
- 0.05840527319178345
19
  ],
20
  [
21
- "mother",
22
- 0.05294361012710281
23
  ],
24
  [
25
- "day",
26
- 0.048777939455976894
 
 
 
 
27
  ],
28
  [
29
- "start",
30
- 0.04585905982612896
31
  ],
32
  [
33
- "pain",
34
- 0.04435300421332059
35
  ],
36
  [
37
- "birth",
38
- 0.04091761431073638
39
  ],
40
  [
41
- "month",
42
- 0.04079956591330975
43
  ]
44
  ],
45
  "0": [
46
  [
47
- "babi",
48
- 0.14997605595950095
49
  ],
50
  [
51
  "hospit",
52
- 0.07743351335006152
53
  ],
54
  [
55
- "mother",
56
- 0.07689592281190712
57
  ],
58
  [
59
  "not",
60
- 0.07416166184866439
61
  ],
62
  [
63
- "check",
64
- 0.0545912365597003
65
  ],
66
  [
67
- "told",
68
- 0.05453965453747262
69
  ],
70
  [
71
- "day",
72
- 0.0542647560058293
73
  ],
74
  [
75
- "went",
76
- 0.052349899081631526
77
  ],
78
  [
79
- "doctor",
80
- 0.046725070362320154
81
  ],
82
  [
83
  "clinic",
84
- 0.04651491968357182
85
  ]
86
  ],
87
  "1": [
88
  [
89
- "babi",
90
- 0.1340253607816117
91
  ],
92
  [
93
- "breath",
94
- 0.12314554477338885
95
  ],
96
  [
97
- "born",
98
- 0.1179134258788878
99
  ],
100
  [
101
- "day",
102
- 0.10229083073550035
103
  ],
104
  [
105
- "prematur",
106
- 0.08115845871832372
107
  ],
108
  [
109
- "problem",
110
- 0.07390519614899621
111
  ],
112
  [
113
- "month",
114
- 0.07281668961405308
115
  ],
116
  [
117
- "lung",
118
- 0.0600471749496312
119
  ],
120
  [
121
- "die",
122
- 0.05878914908440563
123
  ],
124
  [
125
- "hospit",
126
- 0.05838587687739996
127
  ]
128
  ]
129
  },
130
  "topics": [
131
- 1,
132
- -1,
133
- 1,
134
- -1,
135
- -1,
 
 
 
 
 
 
 
 
 
136
  -1,
 
 
 
 
 
 
 
 
137
  -1,
138
- 1,
139
  -1,
 
 
 
 
140
  1,
141
- -1,
142
  0,
143
- -1,
144
- -1,
 
145
  1,
146
  0,
147
- -1,
148
- -1,
149
- -1,
150
- -1,
151
- -1,
152
- -1,
153
- -1,
154
- -1,
155
  1,
156
  0,
157
  0,
158
  0,
159
  0,
160
- -1,
 
 
 
161
  1,
162
  0,
163
- -1,
164
- -1,
165
- -1,
166
  0,
167
  -1,
168
- -1,
169
- -1,
170
- -1,
171
  -1,
172
  -1,
173
  0,
174
  0,
175
  0,
176
- 1,
177
- -1,
178
- -1,
179
- -1,
180
- -1,
181
- -1,
182
- -1,
183
  0,
184
  0,
185
  0,
186
  0,
187
  0,
188
- -1,
 
 
 
 
 
 
 
 
 
 
 
 
 
189
  0,
190
  1,
191
- -1,
192
- -1,
193
- -1,
194
  0,
195
  1,
196
  0,
197
  1,
 
 
 
 
 
 
 
 
 
 
 
 
198
  0,
199
- -1,
200
  0,
201
- -1,
202
- -1,
203
- -1,
204
- -1,
205
- -1,
206
  0,
207
  -1,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
208
  -1,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
209
  -1,
 
 
210
  -1,
211
- -1,
 
 
 
 
 
 
 
 
 
 
212
  1,
 
 
 
213
  -1,
 
 
 
214
  -1,
 
 
215
  -1,
216
  0,
 
217
  -1,
218
  -1,
219
- 0,
220
  -1,
221
  0,
222
  -1,
223
  0,
224
- -1,
225
  0,
226
  -1,
227
- -1,
228
  1,
229
  -1,
 
230
  -1,
231
- 1,
232
  -1,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
233
  0
234
  ],
235
  "topic_sizes": {
236
- "1": 14,
237
- "-1": 61,
238
- "0": 28
239
  },
240
  "topic_mapper": [
241
  [
@@ -258,9 +353,9 @@
258
  ]
259
  ],
260
  "topic_labels": {
261
- "-1": "-1_babi_not_hospit_child",
262
- "0": "0_babi_hospit_mother_not",
263
- "1": "1_babi_breath_born_day"
264
  },
265
  "custom_labels": null,
266
  "_outliers": 1,
 
1
  {
2
  "topic_representations": {
3
  "-1": [
 
 
 
 
4
  [
5
  "not",
6
+ 0.08884998353167763
7
  ],
8
  [
9
  "hospit",
10
+ 0.06774641279829727
11
  ],
12
  [
13
  "child",
14
+ 0.06528612391960899
15
  ],
16
  [
17
+ "well",
18
+ 0.06056196043852575
19
  ],
20
  [
21
+ "pas",
22
+ 0.060391708935210654
23
+ ],
24
+ [
25
+ "clinic",
26
+ 0.059648981713654264
27
  ],
28
  [
29
+ "babi",
30
+ 0.05611401838645225
31
  ],
32
  [
33
+ "day",
34
+ 0.05539450713352081
35
  ],
36
  [
37
+ "doctor",
38
+ 0.052339481077182566
39
  ],
40
  [
41
+ "mother",
42
+ 0.05202270248576627
43
  ]
44
  ],
45
  "0": [
46
  [
47
+ "child",
48
+ 0.07034195543319399
49
  ],
50
  [
51
  "hospit",
52
+ 0.07029980576961407
53
  ],
54
  [
55
+ "babi",
56
+ 0.06610786550811855
57
  ],
58
  [
59
  "not",
60
+ 0.05642717081433925
61
  ],
62
  [
63
+ "day",
64
+ 0.056204965605915605
65
  ],
66
  [
67
+ "mother",
68
+ 0.052431937019415856
69
  ],
70
  [
71
+ "doctor",
72
+ 0.03880767720205223
73
  ],
74
  [
75
+ "pas",
76
+ 0.037582171606197944
77
  ],
78
  [
79
+ "after",
80
+ 0.03753383265414973
81
  ],
82
  [
83
  "clinic",
84
+ 0.036716489493350664
85
  ]
86
  ],
87
  "1": [
88
  [
89
+ "hiv",
90
+ 0.09420349107837497
91
  ],
92
  [
93
+ "babi",
94
+ 0.08380449156732242
95
  ],
96
  [
97
+ "mother",
98
+ 0.07171776197229678
99
  ],
100
  [
101
+ "not",
102
+ 0.06804851712908734
103
  ],
104
  [
105
+ "month",
106
+ 0.05908080568156073
107
  ],
108
  [
109
+ "got",
110
+ 0.05435547172123843
111
  ],
112
  [
113
+ "hospit",
114
+ 0.04775842158425419
115
  ],
116
  [
117
+ "clinic",
118
+ 0.045227183468219634
119
  ],
120
  [
121
+ "respond",
122
+ 0.045158160700012405
123
  ],
124
  [
125
+ "born",
126
+ 0.041168497068004614
127
  ]
128
  ]
129
  },
130
  "topics": [
131
+ 0,
132
+ 0,
133
+ 0,
134
+ 0,
135
+ 0,
136
+ 0,
137
+ 0,
138
+ 0,
139
+ 0,
140
+ 0,
141
+ 0,
142
+ 0,
143
+ 0,
144
+ 0,
145
  -1,
146
+ 0,
147
+ 0,
148
+ 0,
149
+ 0,
150
+ 0,
151
+ 0,
152
+ 0,
153
+ 0,
154
  -1,
 
155
  -1,
156
+ 0,
157
+ 0,
158
+ 0,
159
+ 0,
160
  1,
 
161
  0,
162
+ 0,
163
+ 0,
164
+ 0,
165
  1,
166
  0,
167
+ 0,
168
+ 0,
 
 
 
 
 
 
169
  1,
170
  0,
171
  0,
172
  0,
173
  0,
174
+ 0,
175
+ 0,
176
+ 0,
177
+ 0,
178
  1,
179
  0,
180
+ 0,
 
 
181
  0,
182
  -1,
183
+ 0,
184
+ 0,
 
185
  -1,
186
  -1,
187
  0,
188
  0,
189
  0,
 
 
 
 
 
 
 
190
  0,
191
  0,
192
  0,
193
  0,
194
  0,
195
+ 0,
196
+ 0,
197
+ 0,
198
+ 0,
199
+ 0,
200
+ 0,
201
+ 0,
202
+ 0,
203
+ 0,
204
+ 0,
205
+ 0,
206
+ 0,
207
+ 0,
208
+ 0,
209
  0,
210
  1,
211
+ 1,
 
 
212
  0,
213
  1,
214
  0,
215
  1,
216
+ 1,
217
+ 1,
218
+ 0,
219
+ 0,
220
+ 0,
221
+ 0,
222
+ 0,
223
+ 0,
224
+ 0,
225
+ 0,
226
+ 0,
227
+ 0,
228
  0,
 
229
  0,
 
 
 
 
 
230
  0,
231
  -1,
232
+ 0,
233
+ 0,
234
+ 0,
235
+ 0,
236
+ 1,
237
+ 0,
238
+ 0,
239
+ 0,
240
+ 0,
241
+ 0,
242
+ 0,
243
+ 0,
244
+ 0,
245
+ 0,
246
  -1,
247
+ 0,
248
+ 0,
249
+ 0,
250
+ 0,
251
+ 0,
252
+ 0,
253
+ 0,
254
+ 0,
255
+ 0,
256
+ 0,
257
+ 0,
258
+ 0,
259
+ 0,
260
+ 0,
261
+ 0,
262
+ 0,
263
+ 1,
264
+ 0,
265
+ 0,
266
+ 0,
267
+ 0,
268
  -1,
269
+ 0,
270
+ 0,
271
  -1,
272
+ 0,
273
+ 0,
274
+ 0,
275
+ 0,
276
+ 0,
277
+ 0,
278
+ 0,
279
+ 0,
280
+ 0,
281
+ 0,
282
+ 0,
283
  1,
284
+ 0,
285
+ 0,
286
+ 0,
287
  -1,
288
+ 0,
289
+ 0,
290
+ 0,
291
  -1,
292
+ 0,
293
+ 0,
294
  -1,
295
  0,
296
+ 0,
297
  -1,
298
  -1,
 
299
  -1,
300
  0,
301
  -1,
302
  0,
303
+ 0,
304
  0,
305
  -1,
306
+ 0,
307
  1,
308
  -1,
309
+ 0,
310
  -1,
311
+ 0,
312
  -1,
313
+ 1,
314
+ 0,
315
+ 0,
316
+ 0,
317
+ 0,
318
+ 0,
319
+ 0,
320
+ 0,
321
+ 0,
322
+ 0,
323
+ 0,
324
+ 0,
325
+ 0,
326
+ 0,
327
+ 0,
328
  0
329
  ],
330
  "topic_sizes": {
331
+ "0": 162,
332
+ "-1": 21,
333
+ "1": 15
334
  },
335
  "topic_mapper": [
336
  [
 
353
  ]
354
  ],
355
  "topic_labels": {
356
+ "-1": "-1_not_hospit_child_well",
357
+ "0": "0_child_hospit_babi_not",
358
+ "1": "1_hiv_babi_mother_not"
359
  },
360
  "custom_labels": null,
361
  "_outliers": 1,