# Copyright 2018-2019 QuantumBlack Visual Analytics Limited
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
# OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, AND
# NONINFRINGEMENT. IN NO EVENT WILL THE LICENSOR OR OTHER CONTRIBUTORS
# BE LIABLE FOR ANY CLAIM, DAMAGES, OR OTHER LIABILITY, WHETHER IN AN
# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF, OR IN
# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
#
# The QuantumBlack Visual Analytics Limited ("QuantumBlack") name and logo
# (either separately or in combination, "QuantumBlack Trademarks") are
# trademarks of QuantumBlack. The License does not grant you any right or
# license to the QuantumBlack Trademarks. You may not use the QuantumBlack
# Trademarks or any confusingly similar mark as a trademark for your product,
# or use the QuantumBlack Trademarks in any other manner that might cause
# confusion in the marketplace, including but not limited to in advertising,
# on websites, or on software.
#
# See the License for the specific language governing permissions and
# limitations under the License.
"""``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.
"""
from copy import deepcopy
from pathlib import PurePosixPath
from typing import Any, Dict
import fsspec
import pandas as pd
from fsspec.utils import infer_storage_options
from kedro.io.core import AbstractVersionedDataSet, DataSetError, Version
[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:
::
>>> from kedro.io.json_dataset 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 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`` except `http(s)`.
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.
https://cloud.google.com/resource-manager/docs/creating-managing-projects
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.
E.g. for ``GCSFileSystem`` class: `{project: 'my-project', ...}`
"""
_fs_args = deepcopy(fs_args) or {}
_credentials = deepcopy(credentials) or {}
options_dict = infer_storage_options(filepath)
self._protocol = options_dict["protocol"]
self._fs = fsspec.filesystem(self._protocol, **_credentials, **_fs_args)
super().__init__(
filepath=PurePosixPath(options_dict["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)
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 = self._get_load_path()
with self._fs.open(str(load_path), mode="r") as fs_file:
return pd.read_json(fs_file, **self._load_args)
def _save(self, data: pd.DataFrame) -> None:
save_path = self._get_save_path()
with self._fs.open(str(save_path), mode="w") as fs_file:
data.to_json(path_or_buf=fs_file, **self._save_args)
self.invalidate_cache()
def _exists(self) -> bool:
try:
load_path = self._get_load_path()
except DataSetError:
return False
return self._fs.exists(str(load_path))
def _release(self) -> None:
self.invalidate_cache()
[docs] def invalidate_cache(self) -> None:
"""Invalidate underlying filesystem caches."""
self._fs.invalidate_cache(str(self._filepath))