| # Lowercasing the text | |
| training_queries['cleaned']=training_queries['query'].apply(lambda x:x.lower()) | |
| testing_queries['cleaned']=testing_queries['query'].apply(lambda x:x.lower()) | |
| # Expanding contractions | |
| training_queries['cleaned']=training_queries['cleaned'].apply(lambda x:expand_contractions(x)) | |
| testing_queries['cleaned']=testing_queries['cleaned'].apply(lambda x:expand_contractions(x)) | |
| # Cleaning queries using RegEx | |
| training_queries['cleaned']=training_queries['cleaned'].apply(lambda x: clean_text(x)) | |
| testing_queries['cleaned']=testing_queries['cleaned'].apply(lambda x: clean_text(x)) | |
| # Removing extra spaces | |
| training_queries['cleaned']=training_queries['cleaned'].apply(lambda x: re.sub(' +',' ',x)) | |
| testing_queries['cleaned']=testing_queries['cleaned'].apply(lambda x: re.sub(' +',' ',x)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment