Created
April 18, 2016 00:08
-
-
Save cxtadment/7815ab31f0ed129e55f725ddc0bff867 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| def seg_filter(self, word, tagging): | |
| # filter stop words including punctuation | |
| if word in self.stopwords: | |
| return False | |
| # filter element containing number | |
| if re.match('^(?=.*\\d)', word): | |
| return False | |
| # if the word is in the topics | |
| if word in self.topics: | |
| return False | |
| return True |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment