Train LDA model and infer top words

DataKind-BLR / PrathamBooks-Sprint-2018

Code and documentation for the collaboration with PrathamBooks during Sprint' 2018

MIT License

4 stars 7 forks source link

Train LDA model and infer top words #39

Closed goelakash closed 5 years ago

goelakash commented 5 years ago

Gets the 10 top-ranked keywords based on the probability of the topic for the test-documents and the probability of the words in topic. This results in the top 10 relevant words (aka tags) in decreasing order of relevance.