|
|
|
|
|
--- |
|
|
tags: |
|
|
- bertopic |
|
|
library_name: bertopic |
|
|
pipeline_tag: text-classification |
|
|
--- |
|
|
|
|
|
# bertopic_ready_labeled |
|
|
|
|
|
This is a [BERTopic](https://github.com/MaartenGr/BERTopic) model. |
|
|
BERTopic is a flexible and modular topic modeling framework that allows for the generation of easily interpretable topics from large datasets. |
|
|
|
|
|
## Usage |
|
|
|
|
|
To use this model, please install BERTopic: |
|
|
|
|
|
``` |
|
|
pip install -U bertopic |
|
|
``` |
|
|
|
|
|
You can use the model as follows: |
|
|
|
|
|
```python |
|
|
from bertopic import BERTopic |
|
|
topic_model = BERTopic.load("DobreMihai/bertopic_ready_labeled") |
|
|
|
|
|
topic_model.get_topic_info() |
|
|
``` |
|
|
|
|
|
## Topic overview |
|
|
|
|
|
* Number of topics: 16 |
|
|
* Number of training documents: 24020 |
|
|
|
|
|
<details> |
|
|
<summary>Click here for an overview of all topics.</summary> |
|
|
|
|
|
| Topic ID | Topic Keywords | Topic Frequency | Label | |
|
|
|----------|----------------|-----------------|-------| |
|
|
| -1 | be - it - the - to - alarm | 11 | -1_be_it_the_to | |
|
|
| 0 | math - app - up - to - wake | 9581 | Math | |
|
|
| 1 | not - the - alarm - it - off | 4179 | Sometimes not Ringing | |
|
|
| 2 | snooze - - - - | 2294 | Good App | |
|
|
| 3 | loud - - - - | 2279 | Premium Subscription | |
|
|
| 4 | be - premium - the - to - pay | 1866 | Loud | |
|
|
| 5 | camera - - - - | 1753 | Take Photo | |
|
|
| 6 | snooze - the - to - be - button | 603 | Snooze | |
|
|
| 7 | easy - use - simple - and - to | 381 | Easy to Use | |
|
|
| 8 | barcode - scan - the - code - to | 294 | Barcode Scanner | |
|
|
| 9 | ring - not - it - do - work | 282 | Update | |
|
|
| 10 | shake - it - the - phone - to | 263 | Shake Mission | |
|
|
| 11 | horoscope - be - it - and - news | 99 | Horoscope/News | |
|
|
| 12 | hot - phone - overheat - my - heat | 93 | Overheating | |
|
|
| 13 | mb - space - storage - app - be | 21 | Storage Size | |
|
|
| 14 | challenge - solve - purpose - fun - winner | 21 | Challenges | |
|
|
|
|
|
</details> |
|
|
|
|
|
## Training hyperparameters |
|
|
|
|
|
* calculate_probabilities: False |
|
|
* language: english |
|
|
* low_memory: False |
|
|
* min_topic_size: 10 |
|
|
* n_gram_range: (1, 1) |
|
|
* nr_topics: 50 |
|
|
* seed_topic_list: None |
|
|
* top_n_words: 10 |
|
|
* verbose: False |
|
|
* zeroshot_min_similarity: 0.85 |
|
|
* zeroshot_topic_list: ['android', 'premium*', 'ads', 'math', 'subscription', 'update', 'camera', 'shake', 'weather', 'snooze', 'loud', 'doesn', 'off'] |
|
|
|
|
|
## Framework versions |
|
|
|
|
|
* Numpy: 1.26.4 |
|
|
* HDBSCAN: 0.8.38.post1 |
|
|
* UMAP: 0.5.6 |
|
|
* Pandas: 2.2.1 |
|
|
* Scikit-Learn: 1.5.2 |
|
|
* Sentence-transformers: 3.1.0 |
|
|
* Transformers: 4.44.2 |
|
|
* Numba: 0.60.0 |
|
|
* Plotly: 5.24.1 |
|
|
* Python: 3.10.15 |
|
|
|
