---

BERT, LDA, and TFIDF based keyword extraction in Python

Installation

pip install kwx

git clone https://github.com/andrewtavis/kwx.git
cd kwx
python setup.py install

import kwx

Contents:

• model
  • get_topic_words()
  • get_coherence()
  • _order_and_subset_by_coherence()
  • _select_kws()
  • extract_kws()
  • gen_files()
• topic_model
• TopicModel
  • TopicModel._vectorize()
  • TopicModel.fit()
• visuals
  • save_vis()
  • graph_topic_num_evals()
  • gen_word_cloud()
  • pyLDAvis_topics()
  • t_sne()
• languages
• lem_abbr_dict()
• stem_abbr_dict()
• sw_abbr_dict()
• utils
  • load_data()
  • _combine_texts_to_str()
  • _remove_unwanted()
  • _lemmatize()
  • clean()
  • prepare_data()
  • _prepare_corpus_path()
  • translate_output()
  • organize_by_pos()
  • prompt_for_word_removal()
• License
• Change log
  • Changelog
  • kwx 1.0.0 (December 28th, 2021)
  • kwx 0.1.8 (April 29th, 2021)
  • kwx 0.1.7.3 (March 30th, 2021)
  • kwx 0.1.5 (March 15th, 2021)
  • kwx 0.1.0 (Feb 17th, 2021)
  • kwx 0.0.2.2 (Jan 31st, 2021)

Project Indices

• Index