def __init__(self,min_df=2,norm="l2"):
""" Constructor """
self.cv = CountVectorizer(min_df=min_df)
self.tfidf = TfidfTransformer(norm)
self.LOG_IDF = None
self.CORPUS_VOCAB = None
self.OOV_IDF_VAL = 0 #min idf value to assign for out-of-vocabulary terms
self.IDF_MODEL = dict()
评论列表
文章目录