def preprocess(text):

    """
    This function takes in a string, coverts it to lowercase, cleans
    it (remove special character and numbers), and tokenizes it.
    """

    #convert to lowercase
    text = text.lower()

    #remove special character and digits
    text = re.sub(r'd+', '', text)
    text = re.sub(r'[^ws]', '', text)

    #tokenize
    tokens = nltk.word_tokenize(text)

    return(tokens)