dataio.py 文件源码

def question_batches(data_file):
    """Iterates over a dataset returning batches composed by a single question
    and its candidate answers.

    :data_file: a HDF5 file object holding the dataset
    :returns: a DataSet namedtuple of arrays (questions, sentences, labels).
    """
    n_questions = np.asscalar(data_file['metadata/questions/count'][...])
    questions_ds = data_file['data/questions']
    sentences_ds = data_file['data/sentences']

    for i in range(n_questions):
        row_labels = data_file['data/labels/q%d' % i][...]
        labels = row_labels[:, 1]
        rows = row_labels[:, 0]
        questions = questions_ds[rows, ...]
        sentences = sentences_ds[rows, ...]
        yield DataSet(questions, sentences, labels)