shantanudave's picture
Add BERTopic model
c7ed6cc verified
metadata
tags:
  - bertopic
library_name: bertopic
pipeline_tag: text-classification

TopicModel_StoreReviews

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("shantanudave/TopicModel_StoreReviews")

topic_model.get_topic_info()

Topic overview

  • Number of topics: 10
  • Number of training documents: 14747
Click here for an overview of all topics.
Topic ID Topic Keywords Topic Frequency Label
0 clothing - clothes - fashion - clothe - clothing store 2672 Fashionable Clothing Selection
1 shopping - shop - price - cheap - store 1864 Diverse Shopping Experiences
2 tidy - clean - branch - range - renovation 1807 Clean Retail Space
3 quality - offer - use - stop - good 1793 Quality Offer Search
4 selection - choice - large - large selection - size 1459 Large Size Selection
5 advice - saleswoman - service - friendly - competent 1447 Friendly Saleswoman Service
6 staff - friendly staff - staff staff - staff friendly - friendly 1177 Friendly Staff Selection
7 wow - waw - oh - yeah - 1108 Expressive Words Discovery
8 voucher - money - return - exchange - cash 933 Customer Return Experience
9 super - friendly super - super friendly - pleasure - super service 487 super friendly service

Training hyperparameters

  • calculate_probabilities: True
  • language: None
  • low_memory: False
  • min_topic_size: 10
  • n_gram_range: (1, 1)
  • nr_topics: None
  • seed_topic_list: None
  • top_n_words: 10
  • verbose: True
  • zeroshot_min_similarity: 0.7
  • zeroshot_topic_list: None

Framework versions

  • Numpy: 1.23.5
  • HDBSCAN: 0.8.33
  • UMAP: 0.5.5
  • Pandas: 1.3.5
  • Scikit-Learn: 1.4.1.post1
  • Sentence-transformers: 2.6.1
  • Transformers: 4.39.3
  • Numba: 0.59.1
  • Plotly: 5.21.0
  • Python: 3.10.13