Method iter_rows

python/ray/data/iterator.py:315–343

Return a local row iterable over the dataset. If the dataset is a tabular dataset (Arrow/Pandas blocks), dicts are yielded for each row by the iterator. If the dataset is not tabular, the raw row is yielded. Examples: >>> import ray >>> datas

(self)

    @PublicAPI
    def iter_rows(self) -> Iterable[Dict[str, Any]]:
        """Return a local row iterable over the dataset.

        If the dataset is a tabular dataset (Arrow/Pandas blocks), dicts
        are yielded for each row by the iterator. If the dataset is not tabular,
        the raw row is yielded.

        Examples:
            >>> import ray
            >>> dataset = ray.data.range(10)
            >>> next(iter(dataset.iterator().iter_rows()))
            {'id': 0}

        Time complexity: O(1)

        Returns:
            An iterable over rows of the dataset.
        """
        batch_iterable = self._iter_batches(
            batch_size=None, batch_format=None, prefetch_batches=1
        )

        def _wrapped_iterator():
            for batch in batch_iterable:
                batch = BlockAccessor.for_block(BlockAccessor.batch_to_block(batch))
                for row in batch.iter_rows(public_row_format=True):
                    yield row

        return _IterableFromIterator(_wrapped_iterator)

    @abc.abstractmethod
    @PublicAPI