Add BERTopic model
Browse files- README.md +126 -0
- config.json +16 -0
- ctfidf.safetensors +3 -0
- ctfidf_config.json +0 -0
- topic_embeddings.safetensors +3 -0
- topics.json +0 -0
README.md
ADDED
@@ -0,0 +1,126 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- bertopic
|
5 |
+
library_name: bertopic
|
6 |
+
pipeline_tag: text-classification
|
7 |
+
---
|
8 |
+
|
9 |
+
# WGNEWS_APR20
|
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("tyrealqian/WGNEWS_APR20")
|
27 |
+
|
28 |
+
topic_model.get_topic_info()
|
29 |
+
```
|
30 |
+
|
31 |
+
## Topic overview
|
32 |
+
|
33 |
+
* Number of topics: 57
|
34 |
+
* Number of training documents: 6094
|
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 | media - athletes - ceremony - opening - opening ceremony | 20 | -1_media_athletes_ceremony_opening |
|
42 |
+
| 0 | covid - cases - pandemic - omicron - covid cases | 2071 | 0_covid_cases_pandemic_omicron |
|
43 |
+
| 1 | teamcanada - curling - canada - hockey - canadas | 438 | 1_teamcanada_curling_canada_hockey |
|
44 |
+
| 2 | kamila - valieva - kamila valieva - russian figure - skater kamila | 268 | 2_kamila_valieva_kamila valieva_russian figure |
|
45 |
+
| 3 | winter sports - sports - ice snow - globalink - passion | 199 | 3_winter sports_sports_ice snow_globalink |
|
46 |
+
| 4 | spokesperson - globalink - ambassador - turkish - said globalink | 197 | 4_spokesperson_globalink_ambassador_turkish |
|
47 |
+
| 5 | dwen - mascot - bing dwen - dwen dwen - bing | 182 | 5_dwen_mascot_bing dwen_dwen dwen |
|
48 |
+
| 6 | speed - short track - speed skating - track speed - track | 173 | 6_speed_short track_speed skating_track speed |
|
49 |
+
| 7 | gu - eileen - womens freeski - eileen gu - gu ailing | 145 | 7_gu_eileen_womens freeski_eileen gu |
|
50 |
+
| 8 | torch - flame - torch relay - relay - olympic flame | 139 | 8_torch_flame_torch relay_relay |
|
51 |
+
| 9 | australia - diplomatic boycott - diplomatic - boycott - join diplomatic | 127 | 9_australia_diplomatic boycott_diplomatic_boycott |
|
52 |
+
| 10 | traditional - chinese new - new year - papercutting - culture | 107 | 10_traditional_chinese new_new year_papercutting |
|
53 |
+
| 11 | carbon - green - pollution - air quality - climate | 105 | 11_carbon_green_pollution_air quality |
|
54 |
+
| 12 | biden - diplomatic boycott - diplomatic - white house - joe | 79 | 12_biden_diplomatic boycott_diplomatic_white house |
|
55 |
+
| 13 | oval - skating oval - national speed - venue - ice | 73 | 13_oval_skating oval_national speed_venue |
|
56 |
+
| 14 | mikaela - shiffrin - mikaela shiffrin - slalom - race | 71 | 14_mikaela_shiffrin_mikaela shiffrin_slalom |
|
57 |
+
| 15 | socalled - boycott beijing - boycott - politicians - opposes | 69 | 15_socalled_boycott beijing_boycott_politicians |
|
58 |
+
| 16 | robot - robots - food - serving - served | 68 | 16_robot_robots_food_serving |
|
59 |
+
| 17 | putin - vladimir - vladimir putin - russian president - president vladimir | 66 | 17_putin_vladimir_vladimir putin_russian president |
|
60 |
+
| 18 | kiara reddingius - kiara - reddingius - australian - australias | 65 | 18_kiara reddingius_kiara_reddingius_australian |
|
61 |
+
| 19 | xi jinping - jinping - president xi - xi - chinese president | 65 | 19_xi jinping_jinping_president xi_xi |
|
62 |
+
| 20 | human rights - rights - human - chinas human - rights watch | 61 | 20_human rights_rights_human_chinas human |
|
63 |
+
| 21 | yanqing - paralympic - villages - winter paralympic - completed | 60 | 21_yanqing_paralympic_villages_winter paralympic |
|
64 |
+
| 22 | nest - birds nest - birds - rehearsal - fireworks | 59 | 22_nest_birds nest_birds_rehearsal |
|
65 |
+
| 23 | sadowskisynnott - new zealands - zealands - womens slopestyle - jakara | 59 | 23_sadowskisynnott_new zealands_zealands_womens slopestyle |
|
66 |
+
| 24 | shaun - shaun white - white - halfpipe - hirano | 58 | 24_shaun_shaun white_white_halfpipe |
|
67 |
+
| 25 | su - yiming - su yiming - mens snowboard - snowboarder su | 57 | 25_su_yiming_su yiming_mens snowboard |
|
68 |
+
| 26 | heres watch - opening ceremony - opening - cbc - watch opening | 51 | 26_heres watch_opening ceremony_opening_cbc |
|
69 |
+
| 27 | nhl - players - nhl players - send players - olympics nhl | 49 | 27_nhl_players_nhl players_send players |
|
70 |
+
| 28 | medals grabs - gold delegations - heres breakdown - breakdown - count stands | 47 | 28_medals grabs_gold delegations_heres breakdown_breakdown |
|
71 |
+
| 29 | president thomas - bach - thomas bach - thomas - ioc president | 47 | 29_president thomas_bach_thomas bach_thomas |
|
72 |
+
| 30 | nathan chen - chen - nathan - skater nathan - elton | 45 | 30_nathan chen_chen_nathan_skater nathan |
|
73 |
+
| 31 | snowfall - heavy - heavy snowfall - weather - snow | 43 | 31_snowfall_heavy_heavy snowfall_weather |
|
74 |
+
| 32 | jamaicas - jamaica - benjamin alexander - benjamin - alexander | 43 | 32_jamaicas_jamaica_benjamin alexander_benjamin |
|
75 |
+
| 33 | countdown - countdown beijing - day countdown - days - days beijing | 42 | 33_countdown_countdown beijing_day countdown_days |
|
76 |
+
| 34 | reuterspictures - pictures - day pictures - pictures beijing - olympics day | 40 | 34_reuterspictures_pictures_day pictures_pictures beijing |
|
77 |
+
| 35 | bank - commemorative - yuan - digital - coins | 40 | 35_bank_commemorative_yuan_digital |
|
78 |
+
| 36 | yuzuruhanyu - hanyu - yuzuru - japanese - yuzuru hanyu | 39 | 36_yuzuruhanyu_hanyu_yuzuru_japanese |
|
79 |
+
| 37 | xi - president xi - xi jinping - jinping - chinese president | 37 | 37_xi_president xi_xi jinping_jinping |
|
80 |
+
| 38 | aerials - xu mengtao - mengtao - xu - womens aerials | 34 | 38_aerials_xu mengtao_mengtao_xu |
|
81 |
+
| 39 | tickets - sell - sell tickets - sold - spectators | 33 | 39_tickets_sell_sell tickets_sold |
|
82 |
+
| 40 | technologies - aerospace - technology - technologies used - scitech | 33 | 40_technologies_aerospace_technology_technologies used |
|
83 |
+
| 41 | sui - cong - wenjing - sui wenjing - han cong | 32 | 41_sui_cong_wenjing_sui wenjing |
|
84 |
+
| 42 | erin - jackson - erin jackson - woman - black | 32 | 42_erin_jackson_erin jackson_woman |
|
85 |
+
| 43 | burner - personal - phones - apps smartphonelike - smartphonelike device | 31 | 43_burner_personal_phones_apps smartphonelike |
|
86 |
+
| 44 | leduc - nonbinary - openly - timothy leduc - timothy | 30 | 44_leduc_nonbinary_openly_timothy leduc |
|
87 |
+
| 45 | summer winter - host summer - city host - summer - city | 27 | 45_summer winter_host summer_city host_summer |
|
88 |
+
| 46 | ukraine - invasion - ukraines - ukraine beijing - invasion ukraine | 26 | 46_ukraine_invasion_ukraines_ukraine beijing |
|
89 |
+
| 47 | ralph lauren - lauren - uniforms - ralph - lauren unveiled | 26 | 47_ralph lauren_lauren_uniforms_ralph |
|
90 |
+
| 48 | argentine - fernandez - president alberto - argentine president - alberto fernandez | 25 | 48_argentine_fernandez_president alberto_argentine president |
|
91 |
+
| 49 | truce - olympic truce - antonio guterres - secretarygeneral antonio - guterres | 25 | 49_truce_olympic truce_antonio guterres_secretarygeneral antonio |
|
92 |
+
| 50 | peng - shuai - peng shuai - tennis - chinese tennis | 25 | 50_peng_shuai_peng shuai_tennis |
|
93 |
+
| 51 | zhangjiakou - chongli district - chongli - hebei - cohost | 23 | 51_zhangjiakou_chongli district_chongli_hebei |
|
94 |
+
| 52 | athletes watch - watch beijing - names - biggest names - look biggest | 23 | 52_athletes watch_watch beijing_names_biggest names |
|
95 |
+
| 53 | railway - highspeed - train - highspeed railway - beijingzhangjiakou highspeed | 23 | 53_railway_highspeed_train_highspeed railway |
|
96 |
+
| 54 | peel - laura peel - laura - kerry - aerial | 22 | 54_peel_laura peel_laura_kerry |
|
97 |
+
| 55 | shougang - shougang park - industrial - park - big air | 20 | 55_shougang_shougang park_industrial_park |
|
98 |
+
|
99 |
+
</details>
|
100 |
+
|
101 |
+
## Training hyperparameters
|
102 |
+
|
103 |
+
* calculate_probabilities: True
|
104 |
+
* language: None
|
105 |
+
* low_memory: False
|
106 |
+
* min_topic_size: 10
|
107 |
+
* n_gram_range: (1, 1)
|
108 |
+
* nr_topics: None
|
109 |
+
* seed_topic_list: None
|
110 |
+
* top_n_words: 10
|
111 |
+
* verbose: True
|
112 |
+
* zeroshot_min_similarity: 0.7
|
113 |
+
* zeroshot_topic_list: None
|
114 |
+
|
115 |
+
## Framework versions
|
116 |
+
|
117 |
+
* Numpy: 2.0.2
|
118 |
+
* HDBSCAN: 0.8.40
|
119 |
+
* UMAP: 0.5.7
|
120 |
+
* Pandas: 2.2.2
|
121 |
+
* Scikit-Learn: 1.6.1
|
122 |
+
* Sentence-transformers: 3.4.1
|
123 |
+
* Transformers: 4.51.3
|
124 |
+
* Numba: 0.60.0
|
125 |
+
* Plotly: 5.24.1
|
126 |
+
* Python: 3.11.12
|
config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"calculate_probabilities": true,
|
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": 10,
|
13 |
+
"verbose": true,
|
14 |
+
"zeroshot_min_similarity": 0.7,
|
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:f92ccecec69dd833e1fe8cf4cdeb9e4bb361c0300245ada590e5d57007768a30
|
3 |
+
size 1714220
|
ctfidf_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
topic_embeddings.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16ad085975d98db93f78e511137e23caa4c6b2d876ea1c8681e2d2688abdf3f3
|
3 |
+
size 233560
|
topics.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|