word2vec.py 文件源码

def doesnt_match(self, words):
        """
        Which word from the given list doesn't go with the others?

        Example::
          >>> trained_model.doesnt_match("breakfast cereal dinner lunch".split())
          'cereal'
        """
        words = [word for word in words if word in self.vocab]  # filter out OOV words
        logger.debug("using words %s" % words)
        if not words:
            raise ValueError("cannot select a word from an empty list")
        # which word vector representation is furthest away from the mean?
        selection = self.syn0norm[[self.vocab[word].index for word in words]]
        mean = np.mean(selection, axis=0)
        sim = np.dot(selection, mean / np.linalg.norm(mean))
        return words[np.argmin(sim)]