Add BERTopic model
Browse files- .gitattributes +1 -0
- README.md +78 -0
- config.json +16 -0
- ctfidf.safetensors +3 -0
- ctfidf_config.json +3 -0
- topic_embeddings.safetensors +3 -0
- topics.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
ctfidf_config.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- bertopic
|
5 |
+
library_name: bertopic
|
6 |
+
pipeline_tag: text-classification
|
7 |
+
---
|
8 |
+
|
9 |
+
# HDBSCAN_45_8_ngram3
|
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("Trubnik1967/HDBSCAN_45_8_ngram3")
|
27 |
+
|
28 |
+
topic_model.get_topic_info()
|
29 |
+
```
|
30 |
+
|
31 |
+
## Topic overview
|
32 |
+
|
33 |
+
* Number of topics: 9
|
34 |
+
* Number of training documents: 29572
|
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 | но 44444444444444444444444111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111 - 44444444444444444444444111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111 - но - - | 540 | -1_но 44444444444444444444444111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111_44444444444444444444444111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111_но_ |
|
42 |
+
| 0 | не - деньга - продавец - товар - прийти | 2 | 0_не_деньга_продавец_товар |
|
43 |
+
| 1 | размер - не - маленький - но - продавец | 15435 | 1_размер_не_маленький_но |
|
44 |
+
| 2 | не - ткань - нитка - шов - торчать | 7050 | 2_не_ткань_нитка_шов |
|
45 |
+
| 3 | качество - не - плохой - ужасный - качество не | 2407 | 3_качество_не_плохой_ужасный |
|
46 |
+
| 4 | цвет - не - фото - цвет не - картинка | 1354 | 4_цвет_не_фото_цвет не |
|
47 |
+
| 5 | брак - прийти - дырка - не - прийти брак | 1247 | 5_брак_прийти_дырка_не |
|
48 |
+
| 6 | запах - не - стирка - ужасный - качество | 980 | 6_запах_не_стирка_ужасный |
|
49 |
+
| 7 | описание - соответствовать - не соответствовать - соответствовать описание - не | 557 | 7_описание_соответствовать_не соответствовать_соответствовать описание |
|
50 |
+
|
51 |
+
</details>
|
52 |
+
|
53 |
+
## Training hyperparameters
|
54 |
+
|
55 |
+
* calculate_probabilities: True
|
56 |
+
* language: None
|
57 |
+
* low_memory: False
|
58 |
+
* min_topic_size: 100
|
59 |
+
* n_gram_range: (1, 3)
|
60 |
+
* nr_topics: 9
|
61 |
+
* seed_topic_list: None
|
62 |
+
* top_n_words: 10
|
63 |
+
* verbose: True
|
64 |
+
* zeroshot_min_similarity: None
|
65 |
+
* zeroshot_topic_list: None
|
66 |
+
|
67 |
+
## Framework versions
|
68 |
+
|
69 |
+
* Numpy: 1.25.2
|
70 |
+
* HDBSCAN: 0.8.33
|
71 |
+
* UMAP: 0.5.5
|
72 |
+
* Pandas: 1.5.3
|
73 |
+
* Scikit-Learn: 1.2.2
|
74 |
+
* Sentence-transformers: 2.5.1
|
75 |
+
* Transformers: 4.39.0
|
76 |
+
* Numba: 0.58.1
|
77 |
+
* Plotly: 5.15.0
|
78 |
+
* Python: 3.10.12
|
config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"calculate_probabilities": true,
|
3 |
+
"language": null,
|
4 |
+
"low_memory": false,
|
5 |
+
"min_topic_size": 100,
|
6 |
+
"n_gram_range": [
|
7 |
+
1,
|
8 |
+
3
|
9 |
+
],
|
10 |
+
"nr_topics": 9,
|
11 |
+
"seed_topic_list": null,
|
12 |
+
"top_n_words": 10,
|
13 |
+
"verbose": true,
|
14 |
+
"zeroshot_min_similarity": null,
|
15 |
+
"zeroshot_topic_list": null
|
16 |
+
}
|
ctfidf.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8c876a1142af435b157209aa378885af0d5a80ef01be7d5f0c48bf30c611425
|
3 |
+
size 12303104
|
ctfidf_config.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45539a37eb21d1aabf03dde55509be3347dab9ddc7edac829d36c3b5d774dfcc
|
3 |
+
size 65645571
|
topic_embeddings.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08b7b57a6e7827f6e76bbd5bc11fded36aa450f1ca59d9b09d6fcf7ee0a05f1e
|
3 |
+
size 27736
|
topics.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|