import re import string def remove_articles(text): regex = re.compile(r"\b(a|an|the)\b", re.UNICODE) return re.sub(regex, " ", text) def white_space_fix(text): return " ".join(text.split()) def remove_punc(text): exclude = set(string.punctuation) return "".join(ch for ch in text if ch not in exclude) def lower(text): return text.lower()