Bertopic_Keybert_Champions
This is a 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:
from bertopic import BERTopic
topic_model = BERTopic.load("Noibu/Bertopic_Keybert_Champions")
topic_model.get_topic_info()
Topic overview
- Number of topics: 10
- Number of training documents: 11678
<details> <summary>Click here for an overview of all topics.</summary>
| Topic ID | Topic Keywords | Topic Frequency | Label |
|---|---|---|---|
| -1 | short - powerblend - mesh short - shorts - big tall | 78 | -1_short_powerblend_mesh short_shorts |
| 0 | ny - york - new york - st - st apt | 2099 | 0_ny_york_new york_st |
| 1 | available color - color - color black - grey - white | 5852 | 1_available color_color_color black_grey |
| 2 | search result - search - short search - item search - pant search | 2210 | 2_search result_search_short search_item search |
| 3 | address close - shipping address - address - shipping - michael | 463 | 3_address close_shipping address_address_shipping |
| 4 | size xl - size guide - xl xl - xl available - xl | 403 | 4_size xl_size guide_xl xl_xl available |
| 5 | code - code order - apply - new premium - premium | 190 | 5_code_code order_apply_new premium |
| 6 | password - new password - login - account - enter | 140 | 6_password_new password_login_account |
| 7 | shipping address - address address - address - address order - new address | 131 | 7_shipping address_address address_address_address order |
| 8 | billing - credit card - card number - card - credit | 112 | 8_billing_credit card_card number_card |
</details>
Training hyperparameters
- calculate_probabilities: True
- language: None
- low_memory: False
- min_topic_size: 50
- n_gram_range: (1, 2)
- nr_topics: 10
- seed_topic_list: [['ship', 'address', 'location', 'destination', 'post', 'deliver', 'florida', 'texas', 'united states', 'europe', 'asia'], ['password', 'account', 'login', 'sign in', 'email', 'id', 'authentication', 'username'], ['select', 'choose', 'sort', 'next', 'more', 'back', 'scroll', 'previous', 'search', 'results', 'catalog', 'find', 'lookup', 'query', 'browse', 'explore', 'filter'], ['first', 'last', 'name', 'username', 'middlename', 'surname', 'given name', 'alias'], ['cart', 'basket', 'bag', 'add', 'remove', 'edit', 'cancel', 'update', 'delete', 'modify', 'change'], ['checkout', 'payment', 'pay', 'order', 'purchase', 'billing', 'transaction'], ['small', 'medium', 'large', 'extra large', 's', 'm', 'l', 'xl', 'xxl', 'slim fit', 'size', 'fit', 'quantity'], ['promo', 'code', 'apply', 'welcome', 'offer']]
- top_n_words: 10
- verbose: False
Framework versions
- Numpy: 1.23.5
- HDBSCAN: 0.8.33
- UMAP: 0.5.3
- Pandas: 1.5.3
- Scikit-Learn: 1.2.2
- Sentence-transformers: 2.2.2
- Transformers: 4.31.0
- Numba: 0.56.4
- Plotly: 5.15.0
- Python: 3.10.12
