clusters.py 文件源码

def __init__(self, lang, tokenizer=None, load=True):
        self.lang = lang
        self.tokenizer = tokenizer or Tokenizer(lang)
        dirname = join(nlp_data, lang)
        dict_fname = join(dirname, DICTIONARY_FNAME)
        phrase_fname = join(dirname, PHRASES_FNAME)
        if load and exists(phrase_fname):
            self.phrases = gmodels.Phrases.load(phrase_fname)
        else:
            self.phrases = gmodels.Phrases()
        if load and exists(dict_fname):
            self.dictionary = corpora.Dictionary.load(dict_fname)
        else:
            self.dictionary = corpora.Dictionary()