Dear sirs,
I am a new user of NLTK and Gensim. I need it to Topic Modelling of some articles' abstract. Each of the abstracts need to be weighted, for example abstract1 weighted by 0.23, abstract2 weighted by 0.87, and so on.
How to implement the weighting factor into NLTK and Gensim in Python?
best regards,
Harry Achsan
Sir, the implementation of weighting factor easily available in Gensim already. The strength or weight of document(abstracts in your case) can be calculated using score of the document using lda bow or tf-idf present in Gensim.
For eg: This gives weights of document in sorted order.
for index, score in sorted(lda_model[bow_vector], key=lambda tup: -1*tup[1]): print("Score: ",score )
Dear Sir Pratik Sapkota ,
Thanks for your answer.
But, what I need is that I want to put a weighting factor to every document manually before running Gensim/NLTK. It means that Gensim/NLTK might treat a document more important then other documents depends on its weighting factor.
I need your help, please.
- Badges
- Science topic
- Similar topics
- Computer Science and Engineering
- Programming Languages
- Python