some modification in preprocessing

src/data_utils.py

@@ -37,7 +37,7 @@ def clean_url(text):
     ## removing html tags
     text = re.sub('<.*?>', '', text)
     ## removing normal(without space urls)
-    text = re.sub(r'http\S+', "", text)
+    text = re.sub(r'(?:(?:http|https):\/\/)?([-a-zA-Z0-9.]{2,256}\.[a-z]{2,4})\b(?:\/[-a-zA-Z0-9@:%_\+.~#?&//=]*)?', "", text)
     ## removing urls that contains space
     result = ''
     for char in text: