Commit 2ecf839d authored by De Silva K.C.C.C's avatar De Silva K.C.C.C

keyword detection

parent 96671cee
...@@ -71,7 +71,7 @@ def get_nouns_multipartite(content): ...@@ -71,7 +71,7 @@ def get_nouns_multipartite(content):
extractor.load_document(input=content) extractor.load_document(input=content)
# not contain punctuation marks or stopwords as candidates. # not contain punctuation marks or stopwords as candidates.
pos = {'PROPN', 'NOUN'} pos = {'PROPN', 'NOUN'}
# pos = {'PROPN','NOUN'}
stoplist = list(string.punctuation) stoplist = list(string.punctuation)
stoplist += ['-lrb-', '-rrb-', '-lcb-', '-rcb-', '-lsb-', '-rsb-'] stoplist += ['-lrb-', '-rrb-', '-lcb-', '-rcb-', '-lsb-', '-rsb-']
stoplist += stopwords.words('english') stoplist += stopwords.words('english')
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment