Add BERTopic model
Browse files- README.md +74 -0
- config.json +16 -0
- topic_embeddings.safetensors +3 -0
- topics.json +433 -0
README.md
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- bertopic
|
5 |
+
library_name: bertopic
|
6 |
+
pipeline_tag: text-classification
|
7 |
+
---
|
8 |
+
|
9 |
+
# rag-topic-model
|
10 |
+
|
11 |
+
This is a [BERTopic](https://github.com/MaartenGr/BERTopic) model.
|
12 |
+
BERTopic is a flexible and modular topic modeling framework that allows for the generation of easily interpretable topics from large datasets.
|
13 |
+
|
14 |
+
## Usage
|
15 |
+
|
16 |
+
To use this model, please install BERTopic:
|
17 |
+
|
18 |
+
```
|
19 |
+
pip install -U bertopic
|
20 |
+
```
|
21 |
+
|
22 |
+
You can use the model as follows:
|
23 |
+
|
24 |
+
```python
|
25 |
+
from bertopic import BERTopic
|
26 |
+
topic_model = BERTopic.load("apostolosfilippas/rag-topic-model")
|
27 |
+
|
28 |
+
topic_model.get_topic_info()
|
29 |
+
```
|
30 |
+
|
31 |
+
## Topic overview
|
32 |
+
|
33 |
+
* Number of topics: 5
|
34 |
+
* Number of training documents: 168
|
35 |
+
|
36 |
+
<details>
|
37 |
+
<summary>Click here for an overview of all topics.</summary>
|
38 |
+
|
39 |
+
| Topic ID | Topic Keywords | Topic Frequency | Label |
|
40 |
+
|----------|----------------|-----------------|-------|
|
41 |
+
| -1 | for - klarna - to - my - the | 15 | -1_for_klarna_to_my |
|
42 |
+
| 0 | klarna - my - declined - for - ve | 51 | 0_klarna_my_declined_for |
|
43 |
+
| 1 | payment - to - the - my - for | 50 | 1_payment_to_the_my |
|
44 |
+
| 2 | my - klarna - and - details - account | 28 | 2_my_klarna_and_details |
|
45 |
+
| 3 | store - the - it - refund - back | 24 | 3_store_the_it_refund |
|
46 |
+
|
47 |
+
</details>
|
48 |
+
|
49 |
+
## Training hyperparameters
|
50 |
+
|
51 |
+
* calculate_probabilities: False
|
52 |
+
* language: None
|
53 |
+
* low_memory: False
|
54 |
+
* min_topic_size: 10
|
55 |
+
* n_gram_range: (1, 1)
|
56 |
+
* nr_topics: auto
|
57 |
+
* seed_topic_list: None
|
58 |
+
* top_n_words: 10
|
59 |
+
* verbose: False
|
60 |
+
* zeroshot_min_similarity: 0.7
|
61 |
+
* zeroshot_topic_list: None
|
62 |
+
|
63 |
+
## Framework versions
|
64 |
+
|
65 |
+
* Numpy: 1.26.4
|
66 |
+
* HDBSCAN: 0.8.40
|
67 |
+
* UMAP: 0.5.7
|
68 |
+
* Pandas: 2.2.3
|
69 |
+
* Scikit-Learn: 1.6.1
|
70 |
+
* Sentence-transformers: 3.4.1
|
71 |
+
* Transformers: 4.50.1
|
72 |
+
* Numba: 0.61.2
|
73 |
+
* Plotly: 6.0.1
|
74 |
+
* Python: 3.11.7
|
config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"calculate_probabilities": false,
|
3 |
+
"language": null,
|
4 |
+
"low_memory": false,
|
5 |
+
"min_topic_size": 10,
|
6 |
+
"n_gram_range": [
|
7 |
+
1,
|
8 |
+
1
|
9 |
+
],
|
10 |
+
"nr_topics": "auto",
|
11 |
+
"seed_topic_list": null,
|
12 |
+
"top_n_words": 10,
|
13 |
+
"verbose": false,
|
14 |
+
"zeroshot_min_similarity": 0.7,
|
15 |
+
"zeroshot_topic_list": null
|
16 |
+
}
|
topic_embeddings.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03b618de1995888187647d51b92bf5264397d9940827813be2bcad17dd3bc68c
|
3 |
+
size 7768
|
topics.json
ADDED
@@ -0,0 +1,433 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"topic_representations": {
|
3 |
+
"-1": [
|
4 |
+
[
|
5 |
+
"for",
|
6 |
+
0.06602511651625986
|
7 |
+
],
|
8 |
+
[
|
9 |
+
"klarna",
|
10 |
+
0.06438953438618288
|
11 |
+
],
|
12 |
+
[
|
13 |
+
"to",
|
14 |
+
0.0588484734166664
|
15 |
+
],
|
16 |
+
[
|
17 |
+
"my",
|
18 |
+
0.0574797691276483
|
19 |
+
],
|
20 |
+
[
|
21 |
+
"the",
|
22 |
+
0.05650736581105164
|
23 |
+
],
|
24 |
+
[
|
25 |
+
"but",
|
26 |
+
0.050391580561394415
|
27 |
+
],
|
28 |
+
[
|
29 |
+
"payment",
|
30 |
+
0.04423445960277377
|
31 |
+
],
|
32 |
+
[
|
33 |
+
"card",
|
34 |
+
0.04413108718210577
|
35 |
+
],
|
36 |
+
[
|
37 |
+
"using",
|
38 |
+
0.04281002577647979
|
39 |
+
],
|
40 |
+
[
|
41 |
+
"just",
|
42 |
+
0.039667471149400856
|
43 |
+
]
|
44 |
+
],
|
45 |
+
"0": [
|
46 |
+
[
|
47 |
+
"klarna",
|
48 |
+
0.0684502885090884
|
49 |
+
],
|
50 |
+
[
|
51 |
+
"my",
|
52 |
+
0.06587602342538006
|
53 |
+
],
|
54 |
+
[
|
55 |
+
"declined",
|
56 |
+
0.06268185270099286
|
57 |
+
],
|
58 |
+
[
|
59 |
+
"for",
|
60 |
+
0.05184770062228036
|
61 |
+
],
|
62 |
+
[
|
63 |
+
"ve",
|
64 |
+
0.0514886647186727
|
65 |
+
],
|
66 |
+
[
|
67 |
+
"the",
|
68 |
+
0.050923634011540604
|
69 |
+
],
|
70 |
+
[
|
71 |
+
"in",
|
72 |
+
0.05051278288225979
|
73 |
+
],
|
74 |
+
[
|
75 |
+
"with",
|
76 |
+
0.04270783667311336
|
77 |
+
],
|
78 |
+
[
|
79 |
+
"what",
|
80 |
+
0.040295476736352545
|
81 |
+
],
|
82 |
+
[
|
83 |
+
"to",
|
84 |
+
0.039236097768212165
|
85 |
+
]
|
86 |
+
],
|
87 |
+
"1": [
|
88 |
+
[
|
89 |
+
"payment",
|
90 |
+
0.09882734039896089
|
91 |
+
],
|
92 |
+
[
|
93 |
+
"to",
|
94 |
+
0.09353077326027964
|
95 |
+
],
|
96 |
+
[
|
97 |
+
"the",
|
98 |
+
0.08362522226811411
|
99 |
+
],
|
100 |
+
[
|
101 |
+
"my",
|
102 |
+
0.07677260183954467
|
103 |
+
],
|
104 |
+
[
|
105 |
+
"for",
|
106 |
+
0.0694800029933506
|
107 |
+
],
|
108 |
+
[
|
109 |
+
"due",
|
110 |
+
0.06434756124704745
|
111 |
+
],
|
112 |
+
[
|
113 |
+
"is",
|
114 |
+
0.060984550473916356
|
115 |
+
],
|
116 |
+
[
|
117 |
+
"pay",
|
118 |
+
0.05410201464634094
|
119 |
+
],
|
120 |
+
[
|
121 |
+
"bought",
|
122 |
+
0.05257795446732636
|
123 |
+
],
|
124 |
+
[
|
125 |
+
"card",
|
126 |
+
0.048551252035772596
|
127 |
+
]
|
128 |
+
],
|
129 |
+
"2": [
|
130 |
+
[
|
131 |
+
"my",
|
132 |
+
0.10820482052156193
|
133 |
+
],
|
134 |
+
[
|
135 |
+
"klarna",
|
136 |
+
0.0778837462113562
|
137 |
+
],
|
138 |
+
[
|
139 |
+
"and",
|
140 |
+
0.07387174047283641
|
141 |
+
],
|
142 |
+
[
|
143 |
+
"details",
|
144 |
+
0.07121357997239698
|
145 |
+
],
|
146 |
+
[
|
147 |
+
"account",
|
148 |
+
0.06107877265996873
|
149 |
+
],
|
150 |
+
[
|
151 |
+
"call",
|
152 |
+
0.05786738490569826
|
153 |
+
],
|
154 |
+
[
|
155 |
+
"card",
|
156 |
+
0.05459288080457491
|
157 |
+
],
|
158 |
+
[
|
159 |
+
"someone",
|
160 |
+
0.05113457291213346
|
161 |
+
],
|
162 |
+
[
|
163 |
+
"this",
|
164 |
+
0.051056373196725964
|
165 |
+
],
|
166 |
+
[
|
167 |
+
"worried",
|
168 |
+
0.04984950598067789
|
169 |
+
]
|
170 |
+
],
|
171 |
+
"3": [
|
172 |
+
[
|
173 |
+
"store",
|
174 |
+
0.08068849143662853
|
175 |
+
],
|
176 |
+
[
|
177 |
+
"the",
|
178 |
+
0.07418625377113114
|
179 |
+
],
|
180 |
+
[
|
181 |
+
"it",
|
182 |
+
0.07287641056570636
|
183 |
+
],
|
184 |
+
[
|
185 |
+
"refund",
|
186 |
+
0.06783625470050814
|
187 |
+
],
|
188 |
+
[
|
189 |
+
"back",
|
190 |
+
0.06783625470050814
|
191 |
+
],
|
192 |
+
[
|
193 |
+
"for",
|
194 |
+
0.06532535937718241
|
195 |
+
],
|
196 |
+
[
|
197 |
+
"to",
|
198 |
+
0.06124252441610852
|
199 |
+
],
|
200 |
+
[
|
201 |
+
"credit",
|
202 |
+
0.0593815717854626
|
203 |
+
],
|
204 |
+
[
|
205 |
+
"ago",
|
206 |
+
0.05849200859752171
|
207 |
+
],
|
208 |
+
[
|
209 |
+
"days",
|
210 |
+
0.05706008655023621
|
211 |
+
]
|
212 |
+
]
|
213 |
+
},
|
214 |
+
"topics": [
|
215 |
+
2,
|
216 |
+
3,
|
217 |
+
0,
|
218 |
+
2,
|
219 |
+
-1,
|
220 |
+
3,
|
221 |
+
-1,
|
222 |
+
-1,
|
223 |
+
-1,
|
224 |
+
-1,
|
225 |
+
-1,
|
226 |
+
0,
|
227 |
+
1,
|
228 |
+
-1,
|
229 |
+
1,
|
230 |
+
-1,
|
231 |
+
-1,
|
232 |
+
-1,
|
233 |
+
0,
|
234 |
+
-1,
|
235 |
+
3,
|
236 |
+
-1,
|
237 |
+
-1,
|
238 |
+
-1,
|
239 |
+
1,
|
240 |
+
-1,
|
241 |
+
-1,
|
242 |
+
-1,
|
243 |
+
0,
|
244 |
+
1,
|
245 |
+
1,
|
246 |
+
-1,
|
247 |
+
-1,
|
248 |
+
-1,
|
249 |
+
0,
|
250 |
+
3,
|
251 |
+
3,
|
252 |
+
3,
|
253 |
+
3,
|
254 |
+
0,
|
255 |
+
-1,
|
256 |
+
0,
|
257 |
+
-1,
|
258 |
+
1,
|
259 |
+
3,
|
260 |
+
1,
|
261 |
+
1,
|
262 |
+
-1,
|
263 |
+
-1,
|
264 |
+
0,
|
265 |
+
-1,
|
266 |
+
1,
|
267 |
+
-1,
|
268 |
+
-1,
|
269 |
+
-1,
|
270 |
+
-1,
|
271 |
+
2,
|
272 |
+
-1,
|
273 |
+
2,
|
274 |
+
1,
|
275 |
+
0,
|
276 |
+
2,
|
277 |
+
0,
|
278 |
+
-1,
|
279 |
+
0,
|
280 |
+
2,
|
281 |
+
-1,
|
282 |
+
-1,
|
283 |
+
2,
|
284 |
+
2,
|
285 |
+
2,
|
286 |
+
2,
|
287 |
+
2,
|
288 |
+
2,
|
289 |
+
2,
|
290 |
+
2,
|
291 |
+
0,
|
292 |
+
2,
|
293 |
+
2,
|
294 |
+
2,
|
295 |
+
0,
|
296 |
+
2,
|
297 |
+
-1,
|
298 |
+
2,
|
299 |
+
2,
|
300 |
+
0,
|
301 |
+
2,
|
302 |
+
2,
|
303 |
+
-1,
|
304 |
+
-1,
|
305 |
+
-1,
|
306 |
+
-1,
|
307 |
+
0,
|
308 |
+
-1,
|
309 |
+
0,
|
310 |
+
3,
|
311 |
+
3,
|
312 |
+
3,
|
313 |
+
0,
|
314 |
+
3,
|
315 |
+
-1,
|
316 |
+
-1,
|
317 |
+
3,
|
318 |
+
3,
|
319 |
+
0,
|
320 |
+
0,
|
321 |
+
0,
|
322 |
+
1,
|
323 |
+
1,
|
324 |
+
1,
|
325 |
+
1,
|
326 |
+
-1,
|
327 |
+
1,
|
328 |
+
0,
|
329 |
+
0,
|
330 |
+
0,
|
331 |
+
0,
|
332 |
+
-1,
|
333 |
+
0,
|
334 |
+
0,
|
335 |
+
0,
|
336 |
+
0,
|
337 |
+
-1,
|
338 |
+
0,
|
339 |
+
-1,
|
340 |
+
0,
|
341 |
+
0,
|
342 |
+
0,
|
343 |
+
0,
|
344 |
+
0,
|
345 |
+
0,
|
346 |
+
0,
|
347 |
+
0,
|
348 |
+
-1,
|
349 |
+
0,
|
350 |
+
0,
|
351 |
+
0,
|
352 |
+
0,
|
353 |
+
-1,
|
354 |
+
0,
|
355 |
+
0,
|
356 |
+
0,
|
357 |
+
-1,
|
358 |
+
0,
|
359 |
+
0,
|
360 |
+
0,
|
361 |
+
0,
|
362 |
+
0,
|
363 |
+
2,
|
364 |
+
1,
|
365 |
+
1,
|
366 |
+
0,
|
367 |
+
2,
|
368 |
+
-1,
|
369 |
+
1,
|
370 |
+
-1,
|
371 |
+
-1,
|
372 |
+
1,
|
373 |
+
1,
|
374 |
+
1,
|
375 |
+
1,
|
376 |
+
1,
|
377 |
+
1,
|
378 |
+
1,
|
379 |
+
1,
|
380 |
+
1,
|
381 |
+
3,
|
382 |
+
1
|
383 |
+
],
|
384 |
+
"topic_sizes": {
|
385 |
+
"2": 24,
|
386 |
+
"3": 15,
|
387 |
+
"0": 50,
|
388 |
+
"-1": 51,
|
389 |
+
"1": 28
|
390 |
+
},
|
391 |
+
"topic_mapper": [
|
392 |
+
[
|
393 |
+
-1,
|
394 |
+
-1,
|
395 |
+
-1,
|
396 |
+
-1
|
397 |
+
],
|
398 |
+
[
|
399 |
+
0,
|
400 |
+
0,
|
401 |
+
0,
|
402 |
+
2
|
403 |
+
],
|
404 |
+
[
|
405 |
+
1,
|
406 |
+
1,
|
407 |
+
1,
|
408 |
+
0
|
409 |
+
],
|
410 |
+
[
|
411 |
+
2,
|
412 |
+
2,
|
413 |
+
2,
|
414 |
+
3
|
415 |
+
],
|
416 |
+
[
|
417 |
+
3,
|
418 |
+
3,
|
419 |
+
3,
|
420 |
+
1
|
421 |
+
]
|
422 |
+
],
|
423 |
+
"topic_labels": {
|
424 |
+
"-1": "-1_for_klarna_to_my",
|
425 |
+
"0": "0_klarna_my_declined_for",
|
426 |
+
"1": "1_payment_to_the_my",
|
427 |
+
"2": "2_my_klarna_and_details",
|
428 |
+
"3": "3_store_the_it_refund"
|
429 |
+
},
|
430 |
+
"custom_labels": null,
|
431 |
+
"_outliers": 1,
|
432 |
+
"topic_aspects": {}
|
433 |
+
}
|