Source code for kedro.io.excel_local

# 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.

"""``ExcelLocalDataSet`` loads and saves data to a local Excel file. The
underlying functionality is supported by pandas, so it supports all
allowed pandas options for loading and saving Excel files.
"""
from pathlib import Path
from typing import Any, Dict, Union

import pandas as pd

from kedro.io.core import AbstractDataSet, DataSetError, FilepathVersionMixIn, Version


[docs]class ExcelLocalDataSet(AbstractDataSet, FilepathVersionMixIn): """``ExcelLocalDataSet`` loads and saves data to a local Excel file. The underlying functionality is supported by pandas, so it supports all allowed pandas options for loading and saving Excel files. Example: :: >>> from kedro.io import ExcelLocalDataSet >>> import pandas as pd >>> >>> data = pd.DataFrame({'col1': [1, 2], 'col2': [4, 5], >>> 'col3': [5, 6]}) >>> data_set = ExcelLocalDataSet(filepath="test.xlsx", >>> load_args={'sheet_name':"Sheet1"}, >>> save_args=None) >>> data_set.save(data) >>> reloaded = data_set.load() >>> >>> assert data.equals(reloaded) """ def _describe(self) -> Dict[str, Any]: return dict( filepath=self._filepath, engine=self._engine, load_args=self._load_args, save_args=self._save_args, version=self._version, ) # 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, ) -> None: """Creates a new instance of ``ExcelLocalDataSet`` pointing to a concrete filepath. Args: engine: The engine used to write to excel files. The default engine is 'xlswriter'. filepath: path to an Excel file. 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 The default_load_arg engine is 'xlrd', all others preserved. 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. 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. """ self._filepath = filepath default_save_args = {"index": False} default_load_args = {"engine": "xlrd"} self._load_args = ( {**default_load_args, **load_args} if load_args is not None else default_load_args ) self._save_args = ( {**default_save_args, **save_args} if save_args is not None else default_save_args ) self._engine = engine self._version = version
def _load(self) -> Union[pd.DataFrame, Dict[str, pd.DataFrame]]: load_path = self._get_load_path(self._filepath, self._version) return pd.read_excel(load_path, **self._load_args) def _save(self, data: pd.DataFrame) -> None: save_path = Path(self._get_save_path(self._filepath, self._version)) save_path.parent.mkdir(parents=True, exist_ok=True) with pd.ExcelWriter(str(save_path), engine=self._engine) as writer: data.to_excel(writer, **self._save_args) load_path = Path(self._get_load_path(self._filepath, self._version)) self._check_paths_consistency( str(load_path.absolute()), str(save_path.absolute()) ) def _exists(self) -> bool: try: path = self._get_load_path(self._filepath, self._version) except DataSetError: return False return Path(path).is_file()