使用sklearn.feature_extraction.text.TfidfVectorizer的tf-idf特征权重

由于0.15版本，每个特征的TF-IDF评分可以通过属性来检索

idf_

TfidfVectorizer

from sklearn.feature_extraction.text import TfidfVectorizercorpus = ["This is very strange",          "This is very nice"]vectorizer = TfidfVectorizer(min_df=1)X = vectorizer.fit_transform(corpus)idf = vectorizer.idf_print dict(zip(vectorizer.get_feature_names(), idf))

输出：

{u'is': 1.0, u'nice': 1.4054651081081644, u'strange': 1.4054651081081644, u'this': 1.0, u'very': 1.0}

如评论中所述，在0.15版之前，一种解决方法是

idf_

_tfidf

TfidfTransformer

idf = vectorizer._tfidf.idf_print dict(zip(vectorizer.get_feature_names(), idf))

它应该提供与上述相同的输出。