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

# Copyright 2020 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.

"""``ExcelDataSet`` loads/saves data from/to a Excel file using an underlying
filesystem (e.g.: local, S3, GCS). It uses pandas to handle the Excel file.
"""
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 (
    AbstractVersionedDataSet,
    DataSetError,
    Version,
    get_filepath_str,
    get_protocol_and_path,
)


[docs]class ExcelDataSet(AbstractVersionedDataSet): """``ExcelDataSet`` loads/saves data from/to a Excel file using an underlying filesystem (e.g.: local, S3, GCS). It uses pandas to handle the Excel file. Example: :: >>> from kedro.extras.datasets.pandas import ExcelDataSet >>> import pandas as pd >>> >>> data = pd.DataFrame({'col1': [1, 2], 'col2': [4, 5], >>> 'col3': [5, 6]}) >>> >>> # data_set = ExcelDataSet(filepath="gcs://bucket/test.xlsx") >>> data_set = ExcelDataSet(filepath="test.xlsx") >>> data_set.save(data) >>> reloaded = data_set.load() >>> assert data.equals(reloaded) """ DEFAULT_LOAD_ARGS = {"engine": "xlrd"} DEFAULT_SAVE_ARGS = {"index": False} # pylint: disable=too-many-arguments
[docs] def __init__( self, filepath: str, engine: str = "xlsxwriter", 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 ``ExcelDataSet`` pointing to a concrete Excel file on a specific filesystem. Args: filepath: Filepath in POSIX format to a Excel 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. engine: The engine used to write to excel files. The default engine is 'xlsxwriter'. load_args: Pandas options for loading Excel files. Here you can find all available arguments: https://pandas.pydata.org/pandas-docs/stable/generated/pandas.read_excel.html All defaults are preserved, but "engine", which is set to "xlrd". save_args: Pandas options for saving Excel files. Here you can find all available arguments: https://pandas.pydata.org/pandas-docs/stable/generated/pandas.DataFrame.to_excel.html All defaults are preserved, but "index", which is set to False. If you would like to specify options for the `ExcelWriter`, you can include them under "writer" key. Here you can find all available arguments: https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.ExcelWriter.html 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``), 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`: https://filesystem-spec.readthedocs.io/en/latest/api.html#fsspec.spec.AbstractFileSystem.open All defaults are preserved, except `mode`, which is set to `wb` 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) 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 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) self._writer_args = {"engine": engine} # type: Dict[str, Any] if save_args is not None: writer_args = save_args.pop("writer", {}) # type: Dict[str, Any] self._writer_args.update(writer_args) self._save_args.update(save_args) _fs_open_args_save.setdefault("mode", "wb") 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, load_args=self._load_args, save_args=self._save_args, writer_args=self._writer_args, version=self._version, ) def _load(self) -> pd.DataFrame: load_path = get_filepath_str(self._get_load_path(), self._protocol) with self._fs.open(load_path, **self._fs_open_args_load) as fs_file: return pd.read_excel(fs_file, **self._load_args) def _save(self, data: pd.DataFrame) -> None: output = BytesIO() save_path = get_filepath_str(self._get_save_path(), self._protocol) # pylint: disable=abstract-class-instantiated with pd.ExcelWriter(output, **self._writer_args) as writer: data.to_excel(writer, **self._save_args) with self._fs.open(save_path, **self._fs_open_args_save) as fs_file: fs_file.write(output.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)