def read_json(
paths: Union[str, List[str]],
*,
filesystem: Optional["pyarrow.fs.FileSystem"] = None,
parallelism: int = 200,
ray_remote_args: Dict[str, Any] = None,
arrow_open_stream_args: Optional[Dict[str, Any]] = None,
meta_provider: BaseFileMetadataProvider = DefaultFileMetadataProvider(),
partition_filter: Optional[
PathPartitionFilter
] = JSONDatasource.file_extension_filter(),
**arrow_json_args,
) -> Dataset[ArrowRow]:
"""Create an Arrow dataset from json files.
Examples:
>>> import ray
>>> # Read a directory of files in remote storage.
>>> ray.data.read_json("s3://bucket/path") # doctest: +SKIP
>>> # Read multiple local files.
>>> ray.data.read_json(["/path/to/file1", "/path/to/file2"]) # doctest: +SKIP
>>> # Read multiple directories.
>>> ray.data.read_json( # doctest: +SKIP
... ["s3://bucket/path1", "s3://bucket/path2"])
Args:
paths: A single file/directory path or a list of file/directory paths.
A list of paths can contain both files and directories.
filesystem: The filesystem implementation to read from.
parallelism: The requested parallelism of the read. Parallelism may be
limited by the number of files of the dataset.
ray_remote_args: kwargs passed to ray.remote in the read tasks.
arrow_open_stream_args: kwargs passed to
pyarrow.fs.FileSystem.open_input_stream
meta_provider: File metadata provider. Custom metadata providers may
be able to resolve file metadata more quickly and/or accurately.
partition_filter: Path-based partition filter, if any. Can be used
with a custom callback to read only selected partitions of a dataset.
By default, this filters out any file paths whose file extension does not
match "*.json*".
arrow_json_args: Other json read options to pass to pyarrow.
Returns:
Dataset holding Arrow records read from the specified paths.
"""
return read_datasource(
JSONDatasource(),
parallelism=parallelism,
paths=paths,
filesystem=filesystem,
ray_remote_args=ray_remote_args,
open_stream_args=arrow_open_stream_args,
meta_provider=meta_provider,
partition_filter=partition_filter,
**arrow_json_args,
)
def read_json(paths: Union[str, List[str]],
*,
filesystem: Optional["pyarrow.fs.FileSystem"] = None,
parallelism: int = 200,
ray_remote_args: Dict[str, Any] = None,
**arrow_json_args) -> Dataset[ArrowRow]:
"""Create an Arrow dataset from json files.
Examples:
>>> # Read a directory of files in remote storage.
>>> ray.data.read_json("s3://bucket/path")
>>> # Read multiple local files.
>>> ray.data.read_json(["/path/to/file1", "/path/to/file2"])
>>> # Read multiple directories.
>>> ray.data.read_json(["s3://bucket/path1", "s3://bucket/path2"])
Args:
paths: A single file/directory path or a list of file/directory paths.
A list of paths can contain both files and directories.
filesystem: The filesystem implementation to read from.
parallelism: The amount of parallelism to use for the dataset.
ray_remote_args: kwargs passed to ray.remote in the read tasks.
arrow_json_args: Other json read options to pass to pyarrow.
Returns:
Dataset holding Arrow records read from the specified paths.
"""
return read_datasource(JSONDatasource(),
parallelism=parallelism,
paths=paths,
filesystem=filesystem,
ray_remote_args=ray_remote_args,
**arrow_json_args)