Skip to content

Commit

Permalink
removed one comment from utils
Browse files Browse the repository at this point in the history
  • Loading branch information
gicraveiro committed Feb 6, 2022
1 parent 32af629 commit 9998271
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion utils.py
Original file line number Diff line number Diff line change
Expand Up @@ -56,7 +56,7 @@ def clean_corpus(corpus):
corpus = re.sub("(\s+\-)", r" - ", corpus)
corpus = re.sub("([a-zA-Z]+)([0-9]+)", r"\1 \2", corpus)
corpus = re.sub("([0-9]+)([a-zA-Z]+)", r"\1 \2", corpus)
corpus = re.sub("([()!,;:\.\?\[\]\|])", r" \1 ", corpus) # including : afterwards didnt change result
corpus = re.sub("([()!,;:\.\?\[\]\|])", r" \1 ", corpus)
corpus = re.sub(" +", " ", corpus)

return corpus
Expand Down

0 comments on commit 9998271

Please sign in to comment.