Update scripts/sentiment.py

issue with pulling tweets for certain accounts due to empty string after cleaning

scripts/sentiment.py

@@ -18,30 +18,16 @@ def tweet_cleaner(tweet: str) -> str:
     Returns:
         str: The cleaned tweet.
     """
-    # Remove @ mentions from the tweet
-    # tweet = re.sub("@[A-Za-z0-9]+", "", tweet)
-
-    # # Remove URLs from the tweet
-    # tweet = re.sub(r"(?:\@|http?\://|https?\://|www)\S+", "", tweet)
-
-    # # Remove extra whitespaces from the tweet
-    # tweet = " ".join(tweet.split())
-
-    # # Remove hashtag sign but keep the text
-    # tweet = tweet.replace("#", "").replace("_", " ")
-
-    # # Tokenize the tweet and keep only valid words
-    # tweet = " ".join(
-    #     w
-    #     for w in nltk.wordpunct_tokenize(tweet)
-    #     if w.lower() in words or not w.isalpha()
-    # )
-
-    # # Return the cleaned tweet
-    # return tweet
+    if not isinstance(tweet, str):
+        try:
+            tweet = str(tweet)
+        except Exception as e:
+            print(f"Error converting tweet to string: {e}")
+            return tweet
+        
     bad_start = ["http:", "https:"]
     for w in bad_start:
-        tweet = re.sub(f" {w}\\S+", "", tweet)  # removes white space before url
+        tweet = re.sub(f" {w}\\S+", "", tweet)  # remove white space before url
         tweet = re.sub(f"{w}\\S+ ", "", tweet)  # in case a tweet starts with a url
         tweet = re.sub(f"\n{w}\\S+ ", "", tweet)  # in case the url is on a new line
         tweet = re.sub(