Closed doori closed 10 years ago
Currently in apply_stoplist, the nltk_stop parameter takes a boolean and adds stoplist for English as default.
This could be changed to nltk_stop='english' as default and take other languages, list of languages or None for more flexible corpus cleanup.
Pushed in vsm/extensions/corpuscleanup.py in master branch.
Currently in apply_stoplist, the nltk_stop parameter takes a boolean and adds stoplist for English as default.
This could be changed to nltk_stop='english' as default and take other languages, list of languages or None for more flexible corpus cleanup.