def generateDictionary(self):
dictionary=corpora.Dictionary(self.wordProvider)
stop_ids=[]
once_ids = [tokenid for tokenid, docfreq in dictionary.dfs.items() if docfreq == 1]
dictionary.filter_tokens(stop_ids + once_ids)
dictionary.compactify()
self.dictionary=dictionary
return self.dictionary
评论列表
文章目录