NLTKPreprocessor.py 文件源码

 复制代码def __init__(self, stopwords=None, punct=None,
                 lower=True, strip=True):
        self.lower = lower
        self.strip = strip
        #self.stopwords  = stopwords or set(sw.words('english'))
        self.punct = punct or set(string.punctuation)
        self.lemmatizer = WordNetLemmatizer()