def load_embeddings()

in drqa/reader/model.py [0:0]

• 29 lines of code
• 10 McCabe index (conditional complexity)

    def load_embeddings(self, words, embedding_file):
        """Load pretrained embeddings for a given list of words, if they exist.

        Args:
            words: iterable of tokens. Only those that are indexed in the
              dictionary are kept.
            embedding_file: path to text file of embeddings, space separated.
        """
        words = {w for w in words if w in self.word_dict}
        logger.info('Loading pre-trained embeddings for %d words from %s' %
                    (len(words), embedding_file))
        embedding = self.network.embedding.weight.data

        # When normalized, some words are duplicated. (Average the embeddings).
        vec_counts = {}
        with open(embedding_file) as f:
            # Skip first line if of form count/dim.
            line = f.readline().rstrip().split(' ')
            if len(line) != 2:
                f.seek(0)
            for line in f:
                parsed = line.rstrip().split(' ')
                assert(len(parsed) == embedding.size(1) + 1)
                w = self.word_dict.normalize(parsed[0])
                if w in words:
                    vec = torch.Tensor([float(i) for i in parsed[1:]])
                    if w not in vec_counts:
                        vec_counts[w] = 1
                        embedding[self.word_dict[w]].copy_(vec)
                    else:
                        logging.warning(
                            'WARN: Duplicate embedding found for %s' % w
                        )
                        vec_counts[w] = vec_counts[w] + 1
                        embedding[self.word_dict[w]].add_(vec)

        for w, c in vec_counts.items():
            embedding[self.word_dict[w]].div_(c)

        logger.info('Loaded %d embeddings (%.2f%%)' %
                    (len(vec_counts), 100 * len(vec_counts) / len(words)))