def __init__()

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

• 25 lines of code
• 6 McCabe index (conditional complexity)

    def __init__(self, model=None, tokenizer=None, normalize=True,
                 embedding_file=None, num_workers=None):
        """
        Args:
            model: path to saved model file.
            tokenizer: option string to select tokenizer class.
            normalize: squash output score to 0-1 probabilities with a softmax.
            embedding_file: if provided, will expand dictionary to use all
              available pretrained vectors in this file.
            num_workers: number of CPU processes to use to preprocess batches.
        """
        logger.info('Initializing model...')
        self.model = DocReader.load(model or DEFAULTS['model'],
                                    normalize=normalize)

        if embedding_file:
            logger.info('Expanding dictionary...')
            words = utils.index_embedding_words(embedding_file)
            added = self.model.expand_dictionary(words)
            self.model.load_embeddings(added, embedding_file)

        logger.info('Initializing tokenizer...')
        annotators = tokenizers.get_annotators_for_model(self.model)
        if not tokenizer:
            tokenizer_class = DEFAULTS['tokenizer']
        else:
            tokenizer_class = tokenizers.get_class(tokenizer)

        if num_workers is None or num_workers > 0:
            self.workers = ProcessPool(
                num_workers,
                initializer=init,
                initargs=(tokenizer_class, annotators),
            )
        else:
            self.workers = None
            self.tokenizer = tokenizer_class(annotators=annotators)