bucket_iterator.py 文件源码

def _sort_dataset_by_padding(dataset: Dataset,
                                 sorting_keys: List[Tuple[str, str]],  # pylint: disable=invalid-sequence-index
                                 padding_noise: float = 0.0) -> Dataset:
        """
        Sorts the ``Instances`` in this ``Dataset`` by their padding lengths, using the keys in
        ``sorting_keys`` (in the order in which they are provided).  ``sorting_keys`` is a list of
        ``(field_name, padding_key)`` tuples.
        """
        instances_with_lengths = []
        for instance in dataset.instances:
            padding_lengths = cast(Dict[str, Dict[str, float]], instance.get_padding_lengths())
            if padding_noise > 0.0:
                noisy_lengths = {}
                for field_name, field_lengths in padding_lengths.items():
                    noisy_lengths[field_name] = add_noise_to_dict_values(field_lengths, padding_noise)
                padding_lengths = noisy_lengths
            instance_with_lengths = ([padding_lengths[field_name][padding_key]
                                      for (field_name, padding_key) in sorting_keys],
                                     instance)
            instances_with_lengths.append(instance_with_lengths)
        instances_with_lengths.sort(key=lambda x: x[0])
        return Dataset([instance_with_lengths[-1] for instance_with_lengths in instances_with_lengths])