Fix cleaner by removing #

behrouzbakhtiari · Mar 1, 2020 · f9e96db · f9e96db
1 parent 88bf952
commit f9e96db
Showing 1 changed file with 1 addition and 0 deletions.
diff --git a/twc.py b/twc.py
@@ -70,6 +70,7 @@ def remove_emoji(tweet):
 def clean_tweet(tweet):
     tweet = str(tweet)
     tweet = tweet.lower()
+    tweet = tweet.replace("#", "") # remove # so we preserve hashtags for the cloud
     tweet = tp.clean(tweet)
     tweet = remove_emoji(tweet)
     normalizer = Normalizer()