rociortizb
commited on
Commit
•
a1e4e72
1
Parent(s):
6dd7881
Add BERTopic model
Browse files- README.md +117 -0
- config.json +15 -0
- topic_embeddings.safetensors +3 -0
- topics.json +0 -0
README.md
ADDED
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- bertopic
|
5 |
+
library_name: bertopic
|
6 |
+
pipeline_tag: text-classification
|
7 |
+
---
|
8 |
+
|
9 |
+
# rugby
|
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("Anonymised/rugby")
|
27 |
+
|
28 |
+
topic_model.get_topic_info()
|
29 |
+
```
|
30 |
+
|
31 |
+
## Topic overview
|
32 |
+
|
33 |
+
* Number of topics: 50
|
34 |
+
* Number of training documents: 27774
|
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 |
+
| 0 | premiership - premiership rugby - gloucester - bristol - saints | 1226 | Premiership - England |
|
42 |
+
| 1 | hansen - foster - blacks - cane - steve hansen | 1077 | New Zealand Rugby - New Zealand |
|
43 |
+
| 2 | erasmus - rassie - springboks - rassie erasmus - boks | 1001 | South Africa Rugby - South Africa |
|
44 |
+
| 3 | marler - farrell - vunipola - tuilagi - owen farrell | 986 | England Rugby - England |
|
45 |
+
| 4 | champions cup - champions - european - challenge cup - challenge | 908 | European Cup - Europe |
|
46 |
+
| 5 | connacht - zebre - dragons - benetton - ulster | 837 | Pro14 - Various Countries |
|
47 |
+
| 6 | urc - united rugby - united rugby championship - hendrikse - bulls | 828 | United Rugby Championship - Various Countries |
|
48 |
+
| 7 | sexton - schmidt - ireland - johnny sexton - tadhg | 807 | Six Nations - Various Countries |
|
49 |
+
| 8 | rebels - melbourne - melbourne rebels - waratahs - brumbies | 798 | Super Rugby - Various Countries |
|
50 |
+
| 9 | saracens - premiership - rfu - wasps - worcester | 732 | Premiership - England |
|
51 |
+
| 10 | rennie - cheika - wallabies - hooper - cooper | 722 | Super Rugby - Australia |
|
52 |
+
| 11 | springboks - boks - rugby championship - championship - south africa | 717 | Rugby Championship - Various Countries |
|
53 |
+
| 12 | toulon - montpellier - french - agence france presse - agence france | 710 | Top 14 - France |
|
54 |
+
| 13 | urc - united rugby - united rugby championship - munster - dobson | 696 | United Rugby Championship - Various Countries |
|
55 |
+
| 14 | highlanders - dixon - ioane - lienert - lienert brown | 667 | Super Rugby - Various Countries |
|
56 |
+
| 15 | nienaber - springbok - boks - coetzee - marx | 638 | Rugby Championship - Various Countries |
|
57 |
+
| 16 | wales - wyn - wyn jones - biggar - alun wyn | 628 | Six Nations - Various Countries |
|
58 |
+
| 17 | jones - eddie - jones england - eddie jones - england | 627 | World Cup - Various Countries |
|
59 |
+
| 18 | currie cup - currie - province - western province - golden lions | 596 | Currie Cup - South Africa |
|
60 |
+
| 19 | clermont - rochelle - la rochelle - bordeaux - toulon | 591 | Top 14 - France |
|
61 |
+
| 20 | sevens - series - world series - dubai - powell | 591 | Sevens - Various Countries |
|
62 |
+
| 21 | reds - queensland - queensland reds - brumbies - waratahs | 579 | Super Rugby - Various Countries |
|
63 |
+
| 22 | scotland - russell - hogg - townsend - finn | 575 | Six Nations - Various Countries |
|
64 |
+
| 23 | crusaders - robertson - havili - scott barrett - codie | 565 | Super Rugby - Various Countries |
|
65 |
+
| 24 | griquas - province - western province - currie cup - currie | 560 | Currie Cup - South Africa |
|
66 |
+
| 25 | italy - tommaso - nations - scotland - italian | 551 | Six Nations - Various Countries |
|
67 |
+
| 26 | santiago - argentina - sanchez - matias - creevy | 551 | Rugby Championship - Various Countries |
|
68 |
+
| 27 | sanzaar - zealand rugby - new zealand rugby - nz - pacific | 538 | Super Rugby - New Zealand |
|
69 |
+
| 28 | brumbies - force - nsw - western force - waratahs | 530 | Super Rugby AU - Australia |
|
70 |
+
| 29 | bulls - van zyl - zyl - odendaal - visagie | 517 | Premiership - England |
|
71 |
+
| 30 | fleck - stormers - dobson - kolisi - newlands | 498 | Super Rugby - South Africa |
|
72 |
+
| 31 | hurricanes - canterbury - savea - wellington - laumape | 492 | Super Rugby - New Zealand |
|
73 |
+
| 32 | world rugby - rugby world - japan - world - rugby world cup | 480 | Rugby World Cup - Various Countries |
|
74 |
+
| 33 | whiteley - ackermann - lions - elton - elton jantjies | 477 | Currie Cup - South Africa |
|
75 |
+
| 34 | sharks - preez - du preez - bosch - du | 470 | Super Rugby - South Africa |
|
76 |
+
| 35 | dupont - les - romain - france - french | 454 | Six Nations - Various Countries |
|
77 |
+
| 36 | cardiff - munster - ospreys - ulster - academy | 450 | Pro14 - Various Countries |
|
78 |
+
| 37 | pumas - blue bulls - blue - griquas - currie cup | 423 | Currie Cup - South Africa |
|
79 |
+
| 38 | bledisloe - bledisloe cup - wallabies - blacks - cheika | 359 | Bledisloe Cup - Australia/New Zealand |
|
80 |
+
| 39 | fiji - kenya - canada - samoa - spain | 350 | Sevens - Various Countries |
|
81 |
+
| 40 | wales - gatland - owens - welsh - stadium | 317 | Six Nations - Various Countries |
|
82 |
+
| 41 | samoa - tonga - fiji - world cup - rugby world | 307 | Rugby World Cup - Various Countries |
|
83 |
+
| 42 | sunwolves - japanese - tokyo - rebels - waratahs | 282 | Super Rugby - Japan |
|
84 |
+
| 43 | wprfu - marais - saru - wp - newlands | 278 | Currie Cup - South Africa |
|
85 |
+
| 44 | sa rugby - saru - sa - roux - kings | 254 | Rugby Championship - Various Countries |
|
86 |
+
| 45 | gatland - lions - irish lions - british irish - british irish lions | 253 | British Irish Lions - Various Countries |
|
87 |
+
| 46 | hendrikse - stormers - bulls - jacobs - sharks | 110 | United Rugby Championship - Various Countries |
|
88 |
+
| 47 | folau - israel - rugby australia - million - australia | 104 | Rugby Championship - Various Countries |
|
89 |
+
| 48 | committee - sanzaar - weeks - nigel - player | 60 | SANZAAR - Various Countries |
|
90 |
+
| 49 | lyon - bulls - pretoria - burger - champions | 7 | Top 14 - France |
|
91 |
+
|
92 |
+
</details>
|
93 |
+
|
94 |
+
## Training hyperparameters
|
95 |
+
|
96 |
+
* calculate_probabilities: False
|
97 |
+
* language: None
|
98 |
+
* low_memory: False
|
99 |
+
* min_topic_size: 10
|
100 |
+
* n_gram_range: (1, 1)
|
101 |
+
* nr_topics: None
|
102 |
+
* seed_topic_list: None
|
103 |
+
* top_n_words: 20
|
104 |
+
* verbose: True
|
105 |
+
|
106 |
+
## Framework versions
|
107 |
+
|
108 |
+
* Numpy: 1.21.0
|
109 |
+
* HDBSCAN: 0.8.29
|
110 |
+
* UMAP: 0.5.3
|
111 |
+
* Pandas: 2.0.2
|
112 |
+
* Scikit-Learn: 1.2.2
|
113 |
+
* Sentence-transformers: 2.2.2
|
114 |
+
* Transformers: 4.29.2
|
115 |
+
* Numba: 0.57.0
|
116 |
+
* Plotly: 5.14.1
|
117 |
+
* Python: 3.9.6
|
config.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": null,
|
11 |
+
"seed_topic_list": null,
|
12 |
+
"top_n_words": 20,
|
13 |
+
"verbose": true,
|
14 |
+
"embedding_model": "distiluse-base-multilingual-cased-v1"
|
15 |
+
}
|
topic_embeddings.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:315443da0f29df8c4e2374a00b0184782e833f1cd23f0c2b895219eb2007ba3e
|
3 |
+
size 102488
|
topics.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|