Is there a chance to modify it and make it work for english texts instead of Chinese?
Ali-Nass opened this issue · 2 comments
Ali-Nass commented
I want to get a tf-idf python script that would get me keywords (by weight) from a text. Exactly what you're doing but for English text instead of Chinese.
Jasonnor commented
Hi, this will be simpler, because we can use blanks to separate words in English.
You can refer to other repo such as: https://github.com/hrs/python-tf-idf
Ali-Nass commented
Hi, Thank you for replying, but I want to extract keywords from a document (using tf Idf) rather than compare 2 documents (unless im missunderstanding something!)
Edit: I miss understood something (kinda big) about tf-idf, excuse me for the dumb request! Thanks for the help tho.