Add BERTopic model
Browse files- .gitattributes +1 -0
- README.md +101 -0
- config.json +17 -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 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- bertopic
|
5 |
+
library_name: bertopic
|
6 |
+
pipeline_tag: text-classification
|
7 |
+
---
|
8 |
+
|
9 |
+
# ISSR_Dark_Web_31Topics_White_Nation
|
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("D0men1c0/ISSR_Dark_Web_31Topics_White_Nation")
|
27 |
+
|
28 |
+
topic_model.get_topic_info()
|
29 |
+
```
|
30 |
+
|
31 |
+
## Topic overview
|
32 |
+
|
33 |
+
* Number of topics: 32
|
34 |
+
* Number of training documents: 52310
|
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 | the - trump - to - of - in | 340 | outliers |
|
42 |
+
| 0 | socialism - lesson - applied socialism - practical - practical lesson applied | 16801 | Applied Socialism |
|
43 |
+
| 1 | trump - democrats - pelosi - biden - election | 10136 | 2020 Election Fraud Impeachment |
|
44 |
+
| 2 | border - illegal - wall - trump - mexico | 2606 | Border Wall Debate |
|
45 |
+
| 3 | israel - iran - syria - us - israeli | 1802 | Middle East Tensions Wars |
|
46 |
+
| 4 | brexit - eu - farage - europe - yellow | 1740 | EU Elections and Brexit Leaders |
|
47 |
+
| 5 | thread - re - you - pictures - pictures thread | 1184 | Funny Pictures Threads |
|
48 |
+
| 6 | climate - climate change - change - warming - global warming | 1067 | Climate Change Funding |
|
49 |
+
| 7 | the - fed - market - bank - banks | 915 | Global Central Banks |
|
50 |
+
| 8 | sgt - sgt report - report - appeared first - appeared first sgt | 1227 | SGT Report Articles |
|
51 |
+
| 9 | mueller - fbi - trump - clinton - obama | 832 | Trump Deep State |
|
52 |
+
| 10 | gun - guns - gun control - shooting - control | 3596 | Gun control and police shootings |
|
53 |
+
| 11 | facebook - google - tech - twitter - social media | 828 | Big Tech Censorship |
|
54 |
+
| 12 | china - trade - chinese - trump - tariffs | 818 | US Trade War |
|
55 |
+
| 13 | gold - silver - report - the post - sgt report | 642 | Gold Silver Ratio |
|
56 |
+
| 14 | epstein - jeffrey epstein - jeffrey - sex - maxwell | 750 | Epstein Maxwell Sex Scandal |
|
57 |
+
| 15 | women - men - transgender - gender - feminism | 569 | Transgender Rights and Feminism |
|
58 |
+
| 16 | jews - jewish - jew - holocaust - the jews | 485 | 20th Century Jewish History |
|
59 |
+
| 17 | kavanaugh - ford - christine - brett - brett kavanaugh | 590 | Kavanaugh Accuser |
|
60 |
+
| 18 | white - racist - white people - race - black | 442 | White Racism Follow |
|
61 |
+
| 19 | youtube - music - favorite - what favorite - what favorite music | 571 | Favorite Music Youtube |
|
62 |
+
| 20 | vaccine - vaccines - measles - vaccination - flu | 398 | Vaccine Lawsuit Losses |
|
63 |
+
| 21 | cancer - monsanto - pharma - drug - big pharma | 400 | Diabetes and Health |
|
64 |
+
| 22 | america - the - world - empire - globalists | 645 | Global Empire War |
|
65 |
+
| 23 | abortion - planned parenthood - parenthood - planned - babies | 332 | Planned Parenthood Abortion |
|
66 |
+
| 24 | christians - christianity - pope - christian - church | 281 | Christianity & Religion |
|
67 |
+
| 25 | media - news - cnn - fake news - fake | 551 | Mainstream Media and Fake News |
|
68 |
+
| 26 | antifa - portland - police - violence - protesters | 662 | Antifa Portland Attacks Journalist |
|
69 |
+
| 27 | college - school - students - schools - education | 337 | Education Politics |
|
70 |
+
| 28 | stormfront - stormfront sucks - re stormfront sucks - re stormfront - sucks | 374 | Stormfront Criticism |
|
71 |
+
| 29 | assange - julian - julian assange - wikileaks - us | 197 | Julian Assange Expulsion |
|
72 |
+
| 30 | coronavirus - virus - pandemic - outbreak - wuhan | 192 | Coronavirus Pandemic |
|
73 |
+
|
74 |
+
</details>
|
75 |
+
|
76 |
+
## Training hyperparameters
|
77 |
+
|
78 |
+
* calculate_probabilities: True
|
79 |
+
* language: None
|
80 |
+
* low_memory: False
|
81 |
+
* min_topic_size: 10
|
82 |
+
* n_gram_range: (1, 3)
|
83 |
+
* nr_topics: 32
|
84 |
+
* seed_topic_list: None
|
85 |
+
* top_n_words: 10
|
86 |
+
* verbose: True
|
87 |
+
* zeroshot_min_similarity: 0.7
|
88 |
+
* zeroshot_topic_list: None
|
89 |
+
|
90 |
+
## Framework versions
|
91 |
+
|
92 |
+
* Numpy: 1.26.4
|
93 |
+
* HDBSCAN: 0.8.36
|
94 |
+
* UMAP: 0.5.6
|
95 |
+
* Pandas: 2.2.1
|
96 |
+
* Scikit-Learn: 1.4.1.post1
|
97 |
+
* Sentence-transformers: 3.0.1
|
98 |
+
* Transformers: 4.39.3
|
99 |
+
* Numba: 0.60.0
|
100 |
+
* Plotly: 5.22.0
|
101 |
+
* Python: 3.12.2
|
config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"calculate_probabilities": true,
|
3 |
+
"language": null,
|
4 |
+
"low_memory": false,
|
5 |
+
"min_topic_size": 10,
|
6 |
+
"n_gram_range": [
|
7 |
+
1,
|
8 |
+
3
|
9 |
+
],
|
10 |
+
"nr_topics": 32,
|
11 |
+
"seed_topic_list": null,
|
12 |
+
"top_n_words": 10,
|
13 |
+
"verbose": true,
|
14 |
+
"zeroshot_min_similarity": 0.7,
|
15 |
+
"zeroshot_topic_list": null,
|
16 |
+
"embedding_model": "all-MiniLM-L6-v2"
|
17 |
+
}
|
ctfidf.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d887f7bda90422a03a8d12269fba005a5b47800a998a479b7e1de9794810ea3
|
3 |
+
size 21386092
|
ctfidf_config.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:201181018c7ccb67b98b78b6c31fb96240fea9b3ac7555a6d178a6d741d2f477
|
3 |
+
size 33880722
|
topic_embeddings.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a881f87103d7cd85ed1a8cfe9a5eca1776e8b4dc3ac67b1df4beb555053fdc10
|
3 |
+
size 49240
|
topics.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|