2299d6fb7437903bf421884c0191c38d59d06f7b,src/gensim/corpora/bleicorpus.py,BleiCorpus,saveCorpus,#Any#Any#Any#,72

Before Change

            logging.info("no word id mapping provided; initializing from corpus")
            maxId = -1
            for document in corpus:
                maxId = max(maxId, max([-1] + [fieldId for fieldId, _ in document]))
            numTerms = 1 + maxId
            id2word = dict(zip(xrange(numTerms), xrange(numTerms))) // word id mapping will be identity
        else:
            numTerms = 1 + max([-1] + id2word.keys())
        

After Change

        if id2word is None:
            logging.info("no word id mapping provided; initializing from corpus")
            id2word = utils.dictFromCorpus(corpus)
            numTerms = len(id2word)
        else:
            numTerms = 1 + max([-1] + id2word.keys())
        
        logging.info("storing corpus in Blei"s LDA-C format: %s" % fname)

Instances