preprocessing.py 文件源码

def tiny_tokenize(text, stem=False, stop_words=[]):
    words = []
    for token in wordpunct_tokenize(re.sub('[%s]' % re.escape(string.punctuation), ' ', \
            text.decode(encoding='UTF-8', errors='ignore'))):
        if not token.isdigit() and not token in stop_words:
            if stem:
                try:
                    w = EnglishStemmer().stem(token)
                except Exception as e:
                    w = token
            else:
                w = token
            words.append(w)

    return words

    # return [EnglishStemmer().stem(token) if stem else token for token in wordpunct_tokenize(
    #                     re.sub('[%s]' % re.escape(string.punctuation), ' ', text.decode(encoding='UTF-8', errors='ignore'))) if
    #                     not token.isdigit() and not token in stop_words]