From f9e96db25b9f2b43126b9f603f885ef752fc0252 Mon Sep 17 00:00:00 2001 From: Mostafa Ahangarha Date: Sun, 1 Mar 2020 16:53:23 +0430 Subject: [PATCH] Fix cleaner by removing # --- twc.py | 1 + 1 file changed, 1 insertion(+) diff --git a/twc.py b/twc.py index c49f4c8..353b316 100755 --- 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()