Source code for kedro.extras.datasets.yaml.yaml_dataset

"""``YAMLDataSet`` loads/saves data from/to a YAML file using an underlying
filesystem (e.g.: local, S3, GCS). It uses PyYAML to handle the YAML file.
from copy import deepcopy
from pathlib import PurePosixPath
from typing import Any, Dict, Union

import fsspec
import pandas as pd
import yaml

from import (

[docs]class YAMLDataSet(AbstractVersionedDataSet): """``YAMLDataSet`` loads/saves data from/to a YAML file using an underlying filesystem (e.g.: local, S3, GCS). It uses PyYAML to handle the YAML file. Example: :: >>> from kedro.extras.datasets.yaml import YAMLDataSet >>> >>> data = {'col1': [1, 2], 'col2': [4, 5], 'col3': [5, 6]} >>> >>> # data_set = YAMLDataSet(filepath="gcs://bucket/test.yaml") >>> data_set = YAMLDataSet(filepath="test.yaml") >>> >>> reloaded = data_set.load() >>> assert data == reloaded """ DEFAULT_SAVE_ARGS = {"default_flow_style": False} # type: Dict[str, Any] # pylint: disable=too-many-arguments
[docs] def __init__( self, filepath: str, 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 ``YAMLDataSet`` pointing to a concrete YAML file on a specific filesystem. Args: filepath: Filepath in POSIX format to a YAML 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. save_args: PyYAML options for saving YAML files (arguments passed into ```yaml.dump``). Here you can find all available arguments: All defaults are preserved, but "default_flow_style", which is set to False. version: If specified, should be an instance of ````. 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``), as well as to pass to the filesystem's `open` method through nested keys `open_args_load` and `open_args_save`. Here you can find all available arguments for `open`: All defaults are preserved, except `mode`, which is set to `r` when loading and to `w` when saving. """ _fs_args = deepcopy(fs_args) or {} _fs_open_args_load = _fs_args.pop("open_args_load", {}) _fs_open_args_save = _fs_args.pop("open_args_save", {}) _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._fs = fsspec.filesystem(self._protocol, **_credentials, **_fs_args) super().__init__( filepath=PurePosixPath(path), version=version, exists_function=self._fs.exists, glob_function=self._fs.glob, ) # Handle default save arguments self._save_args = deepcopy(self.DEFAULT_SAVE_ARGS) if save_args is not None: self._save_args.update(save_args) _fs_open_args_save.setdefault("mode", "w") self._fs_open_args_load = _fs_open_args_load self._fs_open_args_save = _fs_open_args_save
def _describe(self) -> Dict[str, Any]: return dict( filepath=self._filepath, protocol=self._protocol, save_args=self._save_args, version=self._version, ) def _load(self) -> Dict: load_path = get_filepath_str(self._get_load_path(), self._protocol) with, **self._fs_open_args_load) as fs_file: return yaml.safe_load(fs_file) def _save(self, data: Union[Dict, pd.DataFrame]) -> None: save_path = get_filepath_str(self._get_save_path(), self._protocol) if isinstance(data, pd.DataFrame): data = data.to_dict() with, **self._fs_open_args_save) as fs_file: yaml.dump(data, fs_file, **self._save_args) 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)