pull_data.py 文件源码

def __init__(self):


        self.stemmer = LancasterStemmer()
        #Convert a collection of text documents to a matrix of token counts
        #Remove accents during the preprocessing step. 
        self.vectorizer = CountVectorizer(strip_accents='ascii') 
        self.tokenizer = self.vectorizer.build_tokenizer()
        self.preprocessor = self.vectorizer.build_preprocessor()
        self.spellchecker = enchant.DictWithPWL("en_US",
            pwl=path_config.PERSONAL_WORD_DICTIONARY_FILE)