您可以从sklean使用TfidfVectorizer
from sklearn.feature_extraction.text import TfidfVectorizerimport numpy as npfrom scipy.sparse.csr import csr_matrix #need this if you want to save tfidf_matrixtf = TfidfVectorizer(input='filename', analyzer='word', ngram_range=(1,6), min_df = 0, stop_words = 'english', sublinear_tf=True)tfidf_matrix = tf.fit_transform(corpus)
上面的tfidf_matix具有语料库中所有文档的TF-IDF值。这是一个很大的稀疏矩阵。现在，
feature_names = tf.get_feature_names()
这将为您提供所有标记，n-gram或单词的列表。对于语料库中的第一个文档，
doc = 0feature_index = tfidf_matrix[doc,:].nonzero()[1]tfidf_scores = zip(feature_index, [tfidf_matrix[doc, x] for x in feature_index])
让我们打印出来
for w, s in [(feature_names[i], s) for (i, s) in tfidf_scores]: print w, s
