Source code for kedro.io.csv_local

# 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.

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

import pandas as pd

from kedro.io.core import (
    AbstractVersionedDataSet,
    Version,
    deprecation_warning,
    is_remote_path,
)


[docs]class CSVLocalDataSet(AbstractVersionedDataSet): """``CSVLocalDataSet`` loads and saves data to a local csv file. The underlying functionality is supported by pandas, so it supports all allowed pandas options for loading and saving csv files. Example: :: >>> from kedro.io import CSVLocalDataSet >>> import pandas as pd >>> >>> data = pd.DataFrame({'col1': [1, 2], 'col2': [4, 5], >>> 'col3': [5, 6]}) >>> data_set = CSVLocalDataSet(filepath="test.csv", >>> load_args=None, >>> save_args={"index": False}) >>> data_set.save(data) >>> reloaded = data_set.load() >>> >>> assert data.equals(reloaded) """ DEFAULT_LOAD_ARGS = {} # type: Dict[str, Any] DEFAULT_SAVE_ARGS = {"index": False} # type: Dict[str, Any]
[docs] def __init__( self, filepath: str, load_args: Dict[str, Any] = None, save_args: Dict[str, Any] = None, version: Version = None, ) -> None: """Creates a new instance of ``CSVLocalDataSet`` pointing to a concrete filepath. Args: filepath: path to a csv file. load_args: Pandas options for loading csv files. Here you can find all available arguments: https://pandas.pydata.org/pandas-docs/stable/generated/pandas.read_csv.html All defaults are preserved. save_args: Pandas options for saving csv files. Here you can find all available arguments: https://pandas.pydata.org/pandas-docs/stable/generated/pandas.DataFrame.to_csv.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. Raises: ValueError: If 'filepath' looks like a remote path. """ deprecation_warning(self.__class__.__name__) super().__init__(Path(filepath), version) if is_remote_path(filepath): raise ValueError( "{} seems to be a remote file, which is not supported by {}".format( filepath, self.__class__.__name__ ) ) # Handle default load and save arguments self._load_args = copy.deepcopy(self.DEFAULT_LOAD_ARGS) if load_args is not None: self._load_args.update(load_args) self._save_args = copy.deepcopy(self.DEFAULT_SAVE_ARGS) if save_args is not None: self._save_args.update(save_args)
def _load(self) -> pd.DataFrame: load_path = Path(self._get_load_path()) return pd.read_csv(load_path, **self._load_args) def _save(self, data: pd.DataFrame) -> None: save_path = Path(self._get_save_path()) save_path.parent.mkdir(parents=True, exist_ok=True) data.to_csv(str(save_path), **self._save_args) def _exists(self) -> bool: path = self._get_load_path() return Path(path).is_file() def _describe(self) -> Dict[str, Any]: return dict( filepath=self._filepath, load_args=self._load_args, save_args=self._save_args, version=self._version, )