From 98f9dd1729e3a2d5dec6e251ac980a9368cd86e3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Gr=C3=A9goire=20MUREAU?= Date: Wed, 16 Jul 2025 11:28:25 +0200 Subject: [PATCH] debugging preprocess --- deployment/api/preprocessing.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/deployment/api/preprocessing.py b/deployment/api/preprocessing.py index 1bed0c2..31bb6b7 100644 --- a/deployment/api/preprocessing.py +++ b/deployment/api/preprocessing.py @@ -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)