Ignore URLs by ignoring strings with .

Changes

1 changed files (+1/-1)

• data.py
  • @@ -24,7 +24,7 @@ # Extract all words from statuses
    words = [word for message in text for word in message.split()] # Remove URLs and special characters and convert to lowercase words = [sub(r'[^a-z0-9]', '', word.lower()) - for word in words if word.find('://') == -1] + for word in words if word.find('.') == -1] # Remove empty strings words = [word for word in words if word != '']