Add BERTopic model
Browse files- .gitattributes +1 -0
- README.md +166 -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 +1,166 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
tags:
|
| 4 |
+
- bertopic
|
| 5 |
+
library_name: bertopic
|
| 6 |
+
pipeline_tag: text-classification
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
# BERTopic_all
|
| 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("karinegabsschon/BERTopic_all")
|
| 27 |
+
|
| 28 |
+
topic_model.get_topic_info()
|
| 29 |
+
```
|
| 30 |
+
|
| 31 |
+
## Topic overview
|
| 32 |
+
|
| 33 |
+
* Number of topics: 97
|
| 34 |
+
* Number of training documents: 3514
|
| 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 | electric - vehicles - ev - cars - charging | 10 | electric cars | electric vehicles | electric car |
|
| 42 |
+
| 0 | government - zero - uk - mandate - targets | 692 | electric cars | electric vehicles | emission vehicles |
|
| 43 |
+
| 1 | charging - abstract - stations - fast - ev charging | 100 | ev charging | fast charging | fast chargers |
|
| 44 |
+
| 2 | spain - moves - aid - iii - moves iii | 92 | electric vehicles | electric car | electric cars |
|
| 45 |
+
| 3 | byd - charging - minutes - fast - han | 77 | charging speeds | megawatt charging | fast charging |
|
| 46 |
+
| 4 | tax - car tax - pay - car - ved | 76 | car tax | electric vehicles | ev owners |
|
| 47 |
+
| 5 | new - used - year - new car - sales | 74 | ev sales | electric cars | electric car |
|
| 48 |
+
| 6 | charging - ev charging - ev - solutions - energy | 74 | ev infrastructure | ev charging | ev charger |
|
| 49 |
+
| 7 | spd - purchase - coalition - funding - tax | 66 | purchase incentives | purchase premium | purchase premiums |
|
| 50 |
+
| 8 | tesla - sales - musk - europe - tesla sales | 65 | tesla sales | tesla market | tesla sold |
|
| 51 |
+
| 9 | percent - german - volkswagen - group - bmw | 61 | tesla | bmw group | german car |
|
| 52 |
+
| 10 | india - tata - ev - indian - manufacturing | 59 | tata motors | ev manufacturing | electric vehicles |
|
| 53 |
+
| 11 | id - every1 - volkswagen - id every1 - vw | 57 | volkswagen id | electric car | vw wants |
|
| 54 |
+
| 12 | charging - stations - charging points - charging stations - points | 53 | charging infrastructure | charging stations | charging cars |
|
| 55 |
+
| 13 | chargers - public - uk - charging - points | 51 | charging infrastructure | ev charging | ev chargers |
|
| 56 |
+
| 14 | tesla - musk - tsla - robotaxi - gerber | 48 | tesla stock | tesla | tesla nasdaq |
|
| 57 |
+
| 15 | skoda - range - ford - volvo - new | 48 | ev | skoda elroq | electric car |
|
| 58 |
+
| 16 | battery - recycling - plant - batteries - ford | 45 | ev battery | ev batteries | battery recycling |
|
| 59 |
+
| 17 | units - ukraine - region - used - kyiv | 44 | vehicles ukraine | electric vehicles | electric cars |
|
| 60 |
+
| 18 | xiaomi - yu7 - su7 - li - li auto | 41 | xiaomi electric | xiaomi ev | xiaomi yu7 |
|
| 61 |
+
| 19 | million - sales - global - iea - china | 39 | electric cars | electric car | electric vehicles |
|
| 62 |
+
| 20 | battery - batteries - solid - lithium - cells | 38 | ev battery | ev batteries | battery technology |
|
| 63 |
+
| 21 | fires - safety - battery - burn - flames | 36 | ev fires | vehicle fires | car fires |
|
| 64 |
+
| 22 | byd - chinese - tesla - billion - china | 36 | china byd | electric cars | chinese electric |
|
| 65 |
+
| 23 | foxconn - mitsubishi - mitsubishi motors - japanese - nissan | 36 | japanese automaker | taiwanese electronics | electric vehicles |
|
| 66 |
+
| 24 | petrol - miles - car - ev - electric | 35 | electric car | electric cars | ev |
|
| 67 |
+
| 25 | study - combustion - cars - emissions - greenhouse | 35 | electric cars | electric car | emissions |
|
| 68 |
+
| 26 | ecological - bonus - euros - households - aid | 33 | financed energy | purchase electric | energy savings |
|
| 69 |
+
| 27 | musk - tesla - elon - elon musk - cybertruck | 32 | musk tesla | tesla musk | tesla denied |
|
| 70 |
+
| 28 | china - shanghai - chinese - manufacturers - german | 31 | chinese automotive | china roads | shanghai motor |
|
| 71 |
+
| 29 | rivian - r2 - scaringe - rivn - rivian automotive | 30 | rivian automotive | 2025 rivian | ceo rivian |
|
| 72 |
+
| 30 | inster - c3 - hyundai - hyundai inster - small | 30 | electric car | electric cars | small ev |
|
| 73 |
+
| 31 | indonesia - lg - nickel - battery - project | 29 | indonesia battery | ev battery | lg energy |
|
| 74 |
+
| 32 | percent - cars - registrations - previous year - previous | 29 | electric cars | cars newly | new cars |
|
| 75 |
+
| 33 | toyota - japanese - bz4x - suzuki - hybrid | 29 | electric car | electric cars | new toyota |
|
| 76 |
+
| 34 | byd - price war - price - war - china | 28 | chinese automakers | chinese car | china ev |
|
| 77 |
+
| 35 | renault - twingo - r5 - alpine - car | 28 | new renault | renault twingo | electric car |
|
| 78 |
+
| 36 | slate - truck - bezos - slate auto - pickup | 27 | electric vehicle | tesla | ev truck |
|
| 79 |
+
| 37 | hungary - huf - byd - chinese - european | 27 | chinese investments | chinese electric | china xplained |
|
| 80 |
+
| 38 | discounts - percent - dudenhöffer - euros - price | 27 | discounts cars | discounts electric | electric cars |
|
| 81 |
+
| 39 | tesla - quarter - year - musk - registrations | 26 | tesla sales | tesla registered | tesla nasdaq |
|
| 82 |
+
| 40 | vinfast - vf - vietnamese - vietnam - press release | 26 | vinfast auto | vinfast vf | vinfast |
|
| 83 |
+
| 41 | percent - huk - private - cars - car | 26 | electric cars | electric car | cars private |
|
| 84 |
+
| 42 | charging - stations - terminals - charging stations - france | 26 | electric vehicles | charging stations | electric mobility |
|
| 85 |
+
| 43 | nissan - leaf - micra - generation - new | 26 | nissan leaf | electric car | new nissan |
|
| 86 |
+
| 44 | ireland - transport - council - kerry - climate | 26 | ev charging | transport emissions | emissions reductions |
|
| 87 |
+
| 45 | tariffs - mexico - united states - united - states | 25 | additional tariffs | tariffs | tariffs product |
|
| 88 |
+
| 46 | changan - chinese - uk - deepal - omoda | 25 | chinese evs | changan automobile | chinese manufacturers |
|
| 89 |
+
| 47 | musk - tesla - protests - elon - police | 25 | tesla protests | tesla takedown | tesla supercharger |
|
| 90 |
+
| 48 | breakdown - barriers - breakdowns - adac - aa | 25 | electric cars | electric vehicles | cars break |
|
| 91 |
+
| 49 | byd - europe - tesla - jato - chinese | 24 | europe tesla | tesla sales | electric cars |
|
| 92 |
+
| 50 | catl - battery - sodium - swapping - batteries | 24 | batteries catl | naxtra battery | ev battery |
|
| 93 |
+
| 51 | honda - hyundai - yen - trillion yen - trillion | 24 | honda announced | ev investment | electric vehicles |
|
| 94 |
+
| 52 | lithium - rare - china - earths - rare earths | 24 | lithium production | domestic lithium | lithium |
|
| 95 |
+
| 53 | kia - ioniq - hyundai - ev2 - ev3 | 23 | kia ev | kia ev3 | kia ev4 |
|
| 96 |
+
| 54 | tesla - canadian - toronto - canada - reimbursement | 23 | incentives tesla | excluded tesla | tesla electric |
|
| 97 |
+
| 55 | mercedes - cla - amg - eq - new | 22 | mercedes ev | cla mercedes | mercedes cla |
|
| 98 |
+
| 56 | storage - electricity - energy - solar - batteries | 22 | energy storage | electric cars | solar power |
|
| 99 |
+
| 57 | eu - tariffs - china - chinese - minimum | 22 | tariffs chinese | tariffs china | car tariffs |
|
| 100 |
+
| 58 | russia - russian - neva - production - almaz | 21 | russia electric | russian electric | cars russia |
|
| 101 |
+
| 59 | lucid - nikola - rivian - lcid - lucid group | 21 | lucid motors | tesla | electric vehicle |
|
| 102 |
+
| 60 | california - trump - states - administration - resolution | 20 | cancel california | california electric | vehicles california |
|
| 103 |
+
| 61 | model - tesla - roadster - updated - performance | 20 | tesla model | tesla best | tesla |
|
| 104 |
+
| 62 | commission - european - eu - der - von der | 19 | european automotive | european car | electric vehicles |
|
| 105 |
+
| 63 | petrol - drivers - costs - mile - home | 19 | petrol prices | charge ev | fuel prices |
|
| 106 |
+
| 64 | audi - rs6 - döllner - tt - ingolstadt | 18 | audi plans | audi wants | audi |
|
| 107 |
+
| 65 | dolphin - surf - dolphin surf - byd - byd dolphin | 18 | byd dolphin | dolphin surf | budget ev |
|
| 108 |
+
| 66 | charge points - committee - points - charge - public | 18 | charging infrastructure | charging points | charge points |
|
| 109 |
+
| 67 | defence - security - chinese - military - spying | 18 | electric vehicles | chinese cars | chinese spying |
|
| 110 |
+
| 68 | belarus - ex5 - belgee - electric charging - gennady svidersky | 18 | belarus number | belarusian market | electric vehicles |
|
| 111 |
+
| 69 | mg - s5 - cyberster - mg4 - s5 ev | 17 | mgs5 ev | s5 ev | mg s5 |
|
| 112 |
+
| 70 | leapmotor - stellantis - c10 - t03 - chinese | 17 | manufacturer leapmotor | leapmotor evs | leapmotor uk |
|
| 113 |
+
| 71 | nio - firefly - onvo - chinese - china | 16 | chinese car | manufacturer nio | chinese ev |
|
| 114 |
+
| 72 | xpeng - p7 - ai - g6 - mona m03 | 16 | new xpeng | china xpeng | xpeng g6 |
|
| 115 |
+
| 73 | gm - cadillac - general motors - general - sales | 16 | tesla nasdaq | cadillac electric | tesla |
|
| 116 |
+
| 74 | trump - musk - president - white house - house | 16 | buying tesla | tesla | trump musk |
|
| 117 |
+
| 75 | cent - rental - drivers - evs - survey | 16 | electric vehicles | evs desirable | ev |
|
| 118 |
+
| 76 | london - congestion - congestion charge - tfl - charge | 16 | exemption evs | congestion charge | vehicle discount |
|
| 119 |
+
| 77 | ferrari - lamborghini - maserati - folgore - granturismo | 15 | maserati ev | electric car | ferrari |
|
| 120 |
+
| 78 | police - emergency - accident - essen - department | 15 | arson | accident | extinguishing |
|
| 121 |
+
| 79 | volvo - samuelsson - staff - jobs - company | 15 | volvo cars | volvo announced | volvo |
|
| 122 |
+
| 80 | xiaomi - su7 - accident - xiaomi su7 - su7 electric | 14 | xiaomi su7 | xiaomi plummeted | xiaomi electric |
|
| 123 |
+
| 81 | tax - insurance - insurance tax - related insurance - related | 14 | vehicle tax | insurance tax | tax electric |
|
| 124 |
+
| 82 | credit - tax - house - republicans - republican | 13 | electric vehicles | electric vehicle | tax electric |
|
| 125 |
+
| 83 | power - blackout - spain - homes - power homes | 13 | evs power | power homes | electric car |
|
| 126 |
+
| 84 | french - centrale - la centrale - la - french people | 13 | electric cars | electric car | electric vehicles |
|
| 127 |
+
| 85 | ship - coast - vessel - coast guard - guard | 13 | fires ships | cargo ship | electric vehicles |
|
| 128 |
+
| 86 | byd - european - europe - seagull - dolphin | 12 | byd seagull | seagull company | chinese electric |
|
| 129 |
+
| 87 | pod - pod point - point - edf - energy giant | 12 | pod point | buy pod | companies pod |
|
| 130 |
+
| 88 | ocu - euros - savings - spain - combustion | 12 | electric car | electric cars | electric |
|
| 131 |
+
| 89 | stellantis - italy - elkann - europe italy - imparato | 12 | automotive groups | market stellantis | stellantis new |
|
| 132 |
+
| 90 | parking - tyresystem - solar - training - police | 12 | electric vehicles | electric cars | electric mobility |
|
| 133 |
+
| 91 | used - warranty - percent - battery - battery warranty | 12 | car battery | electric cars | battery warranty |
|
| 134 |
+
| 92 | percent - registrations - february - new registrations - eu | 12 | tesla cars | percent tesla | electric cars |
|
| 135 |
+
| 93 | tesla - china - model - sales - april | 11 | tesla china | china tesla | tesla sales |
|
| 136 |
+
| 94 | bmw - klasse - neue - neue klasse - ix3 | 11 | new bmw | bmw new | car bmw |
|
| 137 |
+
| 95 | ford - octopus - octopus energy - free - home | 11 | electric car | ev | ford power |
|
| 138 |
+
|
| 139 |
+
</details>
|
| 140 |
+
|
| 141 |
+
## Training hyperparameters
|
| 142 |
+
|
| 143 |
+
* calculate_probabilities: False
|
| 144 |
+
* language: None
|
| 145 |
+
* low_memory: False
|
| 146 |
+
* min_topic_size: 10
|
| 147 |
+
* n_gram_range: (1, 1)
|
| 148 |
+
* nr_topics: None
|
| 149 |
+
* seed_topic_list: None
|
| 150 |
+
* top_n_words: 10
|
| 151 |
+
* verbose: True
|
| 152 |
+
* zeroshot_min_similarity: 0.7
|
| 153 |
+
* zeroshot_topic_list: None
|
| 154 |
+
|
| 155 |
+
## Framework versions
|
| 156 |
+
|
| 157 |
+
* Numpy: 2.0.2
|
| 158 |
+
* HDBSCAN: 0.8.40
|
| 159 |
+
* UMAP: 0.5.9.post2
|
| 160 |
+
* Pandas: 2.2.2
|
| 161 |
+
* Scikit-Learn: 1.6.1
|
| 162 |
+
* Sentence-transformers: 4.1.0
|
| 163 |
+
* Transformers: 4.53.0
|
| 164 |
+
* Numba: 0.60.0
|
| 165 |
+
* Plotly: 5.24.1
|
| 166 |
+
* Python: 3.11.13
|
config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 10,
|
| 13 |
+
"verbose": true,
|
| 14 |
+
"zeroshot_min_similarity": 0.7,
|
| 15 |
+
"zeroshot_topic_list": null,
|
| 16 |
+
"embedding_model": "ibm-granite/granite-embedding-125m-english"
|
| 17 |
+
}
|
ctfidf.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33df94ec5b03624e5f92090b6631a257ce433d5641b3aaff4182346630506fa5
|
| 3 |
+
size 11259084
|
ctfidf_config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21663f34a159cd58ac811a91ae8b015a350774e909c1995b8002d57005dad3d2
|
| 3 |
+
size 12764597
|
topic_embeddings.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee936a9d6d98cbe00a287dbafd5bc6f71b74e83d8b6fa01bd998cac2de88cf21
|
| 3 |
+
size 298072
|
topics.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|