e0ddcc6bc5fff33824ecde2c6abba3ed2bfcecf8,src/gensim/models/tfidfmodel.py,TfidfModel,initialize,#TfidfModel#Any#,54

Before Change

        
        if self.id2word is None:
            logging.info("no word id mapping provided; initializing from corpus, assuming identity")
            maxId = 0
            for document in corpus:
                maxId = max(maxId, max([-1] + [fieldId for fieldId, _ in document]))
            self.numTerms = 1 + maxId
            self.id2word = dict(zip(xrange(self.numTerms), xrange(self.numTerms)))
        else:
            self.numTerms = 1 + max([-1] + self.id2word.keys())
        

After Change

        
        if self.id2word is None:
            logging.info("no word id mapping provided; initializing from corpus, assuming identity")
            self.id2word = utils.dictFromCorpus(corpus)
            self.numTerms = len(self.id2word)
        else:
            self.numTerms = 1 + max([-1] + self.id2word.keys())
        

Instances