def get_only_wti(doc,includew=None):
    words = set()
    wordstoret=set()
    for word in re.split('\\W+', doc):
        if 2 < len(word) < 20:
            words.add(word.lower())
    for word in words:
       if word in includew:
        wordstoret.add(word.lower())
    return wordstoret
def helper_fun(doc):
    return get_only_wti(doc,words_to_include)