word2vec.py 文件源码

def train(self, sentences, total_words=None, word_count=0,
              total_examples=None, queue_factor=2, report_delay=1.0):
        """
        Update the model's neural weights from a sequence of sentences (can be a once-only generator stream).
        For Word2Vec, each sentence must be a list of unicode strings. (Subclasses may accept other examples.)

        To support linear learning-rate decay from (initial) alpha to min_alpha, either total_examples
        (count of sentences) or total_words (count of raw words in sentences) should be provided, unless the
        sentences are the same as those that were used to initially build the vocabulary.

        """
        if self.bucket > 0:
            sentences = HashIter(sentences, self.bucket, with_labels=True)
        if (self.model_trimmed_post_training):
            raise RuntimeError("Parameters for training were discarded using model_trimmed_post_training method")
        if FAST_VERSION < 0:
            import warnings
            warnings.warn("C extension not loaded for Word2Vec, training will be slow. "
                          "Install a C compiler and reinstall gensim for fast training.")
            self.neg_labels = []
            if self.negative > 0:
                # precompute negative labels optimization for pure-python training
                self.neg_labels = zeros(self.negative + 1)
                self.neg_labels[0] = 1.
        return super(LabeledWord2Vec, self).train(sentences, total_words, word_count,
                                                  total_examples, queue_factor, report_delay)