debugging preprocess

This commit is contained in:
Grégoire Mureau 2025-07-16 11:28:25 +02:00
parent d3b0af6126
commit 98f9dd1729

View file

@ -47,7 +47,7 @@ def preprocess_tweet(tweet):
tweet = re.sub(r'[^\w\s<>@#!?]', '', tweet)
# Remove non-printable/control characters (e.g., \n, \t, emojis, corrupted unicode)
tweet = re.sub(r'[^\x20-\x7E]', '', tweet)
# tweet = re.sub(r'[^\x20-\x7E]', '', tweet)
# Tokenize the tweet into individual words
tokens = word_tokenize(tweet)