Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

remove stop words before calculating similarities #24

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

remove stop words before calculating similarities #24

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 14 additions & 1 deletion keyphrase_vectorizers/keyphrase_count_vectorizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -145,6 +145,11 @@ def __init__(self, spacy_pipeline: Union[str, spacy.Language] = 'en_core_web_sm'
self.binary = binary
self.dtype = dtype

def remove_stopwords(self, text):
text = ' '.join([word for word in text.split(' ') if word not in self.stop_words])

return text

def fit(self, raw_documents: List[str]) -> object:
"""
Learn the keyphrases that match the defined part-of-speech pattern from the list of raw documents.
Expand All @@ -170,7 +175,15 @@ def fit(self, raw_documents: List[str]) -> object:

# remove keyphrases that have more than 8 words, as they are probably no real keyphrases
# additionally this prevents memory issues during transformation to a document-keyphrase matrix
self.keyphrases = [keyphrase for keyphrase in self.keyphrases if len(keyphrase.split()) <= 8]
self.keyphrases = [keyphrase for keyphrase in self.keyphrases if len(keyphrase.split()) <= 5]


keys = ' | '.join([key for key in self.keyphrases])
if self.stop_words is not None:
keys = self.remove_stopwords(keys)
keys = keys.replace(' | | ', ' | ')
self.keyphrases = list(np.unique(keys.split(' | ')))


# compute document frequencies of keyphrases
if self.max_df or self.min_df:
Expand Down