Method encode_batch

src/datasets/features/features.py:2180–2197

Encode batch into a format for Arrow. Args: batch (`dict[str, list[Any]]`): Data in a Dataset batch. Returns: `dict[str, list[Any]]`

(self, batch)

        return [encode_nested_example(self[column_name], obj, level=1) for obj in column]

    def encode_batch(self, batch):
        """
        Encode batch into a format for Arrow.

        Args:
            batch (`dict[str, list[Any]]`):
                Data in a Dataset batch.

        Returns:
            `dict[str, list[Any]]`
        """
        encoded_batch = {}
        if set(batch) != set(self):
            raise ValueError(f"Column mismatch between batch {set(batch)} and features {set(self)}")
        for key, column in batch.items():
            column = cast_to_python_objects(column)
            encoded_batch[key] = [encode_nested_example(self[key], obj, level=1) for obj in column]
        return encoded_batch

    def decode_example(self, example: dict, token_per_repo_id: Optional[dict[str, Union[str, bool, None]]] = None):
        """Decode example with custom feature decoding.