Source code for kedro.extras.datasets.pandas.json_dataset

"""``JSONDataSet`` loads/saves data from/to a JSON file using an underlying
filesystem (e.g.: local, S3, GCS). It uses pandas to handle the JSON file.
"""
import logging
from copy import deepcopy
from io import BytesIO
from pathlib import PurePosixPath
from typing import Any, Dict

import fsspec
import pandas as pd

from kedro.io.core import (
    PROTOCOL_DELIMITER,
    AbstractVersionedDataSet,
    DataSetError,
    Version,
    get_filepath_str,
    get_protocol_and_path,
)

logger = logging.getLogger(__name__)


[docs]class JSONDataSet(AbstractVersionedDataSet): """``JSONDataSet`` loads/saves data from/to a JSON file using an underlying filesystem (e.g.: local, S3, GCS). It uses pandas to handle the json file. Example adding a catalog entry with `YAML API <https://kedro.readthedocs.io/en/stable/data/\ data_catalog.html#using-the-data-catalog-with-the-yaml-api>`_: .. code-block:: yaml >>> clickstream_dataset: >>> type: pandas.JSONDataSet >>> filepath: abfs://landing_area/primary/click_stream.json >>> credentials: abfs_creds >>> >>> json_dataset: >>> type: pandas.JSONDataSet >>> filepath: data/01_raw/Video_Games.json >>> load_args: >>> lines: True Example using Python API: :: >>> from kedro.extras.datasets.pandas import JSONDataSet >>> import pandas as pd >>> >>> data = pd.DataFrame({'col1': [1, 2], 'col2': [4, 5], >>> 'col3': [5, 6]}) >>> >>> # data_set = JSONDataSet(filepath="gcs://bucket/test.json") >>> data_set = JSONDataSet(filepath="test.json") >>> data_set.save(data) >>> reloaded = data_set.load() >>> assert data.equals(reloaded) """ DEFAULT_LOAD_ARGS = {} # type: Dict[str, Any] DEFAULT_SAVE_ARGS = {} # type: Dict[str, Any] # pylint: disable=too-many-arguments
[docs] def __init__( self, filepath: str, load_args: Dict[str, Any] = None, save_args: Dict[str, Any] = None, version: Version = None, credentials: Dict[str, Any] = None, fs_args: Dict[str, Any] = None, ) -> None: """Creates a new instance of ``JSONDataSet`` pointing to a concrete JSON file on a specific filesystem. Args: filepath: Filepath in POSIX format to a JSON file prefixed with a protocol like `s3://`. If prefix is not provided `file` protocol (local filesystem) will be used. The prefix should be any protocol supported by ``fsspec``. Note: `http(s)` doesn't support versioning. load_args: Pandas options for loading JSON files. Here you can find all available arguments: https://pandas.pydata.org/pandas-docs/stable/generated/pandas.read_json.html All defaults are preserved. save_args: Pandas options for saving JSON files. Here you can find all available arguments: https://pandas.pydata.org/pandas-docs/stable/generated/pandas.DataFrame.to_json.html All defaults are preserved, but "index", which is set to False. version: If specified, should be an instance of ``kedro.io.core.Version``. If its ``load`` attribute is None, the latest version will be loaded. If its ``save`` attribute is None, save version will be autogenerated. credentials: Credentials required to get access to the underlying filesystem. E.g. for ``GCSFileSystem`` it should look like `{'token': None}`. fs_args: Extra arguments to pass into underlying filesystem class constructor (e.g. `{"project": "my-project"}` for ``GCSFileSystem``). """ _fs_args = deepcopy(fs_args) or {} _credentials = deepcopy(credentials) or {} protocol, path = get_protocol_and_path(filepath, version) if protocol == "file": _fs_args.setdefault("auto_mkdir", True) self._protocol = protocol self._storage_options = {**_credentials, **_fs_args} self._fs = fsspec.filesystem(self._protocol, **self._storage_options) super().__init__( filepath=PurePosixPath(path), version=version, exists_function=self._fs.exists, glob_function=self._fs.glob, ) # Handle default load and save arguments self._load_args = deepcopy(self.DEFAULT_LOAD_ARGS) if load_args is not None: self._load_args.update(load_args) self._save_args = deepcopy(self.DEFAULT_SAVE_ARGS) if save_args is not None: self._save_args.update(save_args) if "storage_options" in self._save_args or "storage_options" in self._load_args: logger.warning( "Dropping `storage_options` for %s, " "please specify them under `fs_args` or `credentials`.", self._filepath, ) self._save_args.pop("storage_options", None) self._load_args.pop("storage_options", None)
def _describe(self) -> Dict[str, Any]: return dict( filepath=self._filepath, protocol=self._protocol, load_args=self._load_args, save_args=self._save_args, version=self._version, ) def _load(self) -> Any: load_path = str(self._get_load_path()) if self._protocol == "file": # file:// protocol seems to misbehave on Windows # (<urlopen error file not on local host>), # so we don't join that back to the filepath; # storage_options also don't work with local paths return pd.read_json(load_path, **self._load_args) load_path = f"{self._protocol}{PROTOCOL_DELIMITER}{load_path}" return pd.read_json( load_path, storage_options=self._storage_options, **self._load_args ) def _save(self, data: pd.DataFrame) -> None: save_path = get_filepath_str(self._get_save_path(), self._protocol) buf = BytesIO() data.to_json(path_or_buf=buf, **self._save_args) with self._fs.open(save_path, mode="wb") as fs_file: fs_file.write(buf.getvalue()) self._invalidate_cache() def _exists(self) -> bool: try: load_path = get_filepath_str(self._get_load_path(), self._protocol) except DataSetError: return False return self._fs.exists(load_path) def _release(self) -> None: super()._release() self._invalidate_cache() def _invalidate_cache(self) -> None: """Invalidate underlying filesystem caches.""" filepath = get_filepath_str(self._filepath, self._protocol) self._fs.invalidate_cache(filepath)