# 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.
"""``CSVS3DataSet`` loads and saves data to a file in S3. It uses s3fs
to read and write from S3 and pandas to handle the csv file.
"""
import copy
from pathlib import PurePosixPath
from typing import Any, Dict
import pandas as pd
from s3fs.core import S3FileSystem
from kedro.io.core import AbstractVersionedDataSet, Version, deprecation_warning
[docs]class CSVS3DataSet(AbstractVersionedDataSet):
"""``CSVS3DataSet`` loads and saves data to a file in S3. It uses s3fs
to read and write from S3 and pandas to handle the csv file.
Example:
::
>>> from kedro.io import CSVS3DataSet
>>> import pandas as pd
>>>
>>> data = pd.DataFrame({'col1': [1, 2], 'col2': [4, 5],
>>> 'col3': [5, 6]})
>>>
>>> data_set = CSVS3DataSet(filepath="test.csv",
>>> bucket_name="test_bucket",
>>> 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]
# pylint: disable=too-many-arguments
[docs] def __init__(
self,
filepath: str,
bucket_name: str = None,
credentials: Dict[str, Any] = None,
load_args: Dict[str, Any] = None,
save_args: Dict[str, Any] = None,
version: Version = None,
s3fs_args: Dict[str, Any] = None,
) -> None:
"""Creates a new instance of ``CSVS3DataSet`` pointing to a concrete
csv file on S3.
Args:
filepath: Path to a csv file. May contain the full path in S3
including bucket and protocol, e.g. `s3://bucket-name/path/to/file.csv`.
bucket_name: S3 bucket name. Must be specified **only** if not
present in ``filepath``.
credentials: Credentials to access the S3 bucket, such as
``aws_access_key_id``, ``aws_secret_access_key``.
load_args: Pandas options for loading csv files.
You can find all available arguments at:
https://pandas.pydata.org/pandas-docs/stable/generated/pandas.read_csv.html
All defaults are preserved.
save_args: Pandas options for saving csv files.
You can find all available arguments at:
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.
s3fs_args: S3FileSystem options. You can see all available arguments at:
https://s3fs.readthedocs.io/en/latest/api.html#s3fs.core.S3FileSystem
"""
deprecation_warning(self.__class__.__name__)
_credentials = copy.deepcopy(credentials) or {}
_s3fs_args = copy.deepcopy(s3fs_args) or {}
_s3 = S3FileSystem(client_kwargs=_credentials, **_s3fs_args)
path = _s3._strip_protocol(filepath)
path = PurePosixPath("{}/{}".format(bucket_name, path) if bucket_name else path)
super().__init__(
path, version, exists_function=_s3.exists, glob_function=_s3.glob
)
# 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)
self._s3 = _s3
def _describe(self) -> Dict[str, Any]:
return dict(
filepath=self._filepath,
load_args=self._load_args,
save_args=self._save_args,
version=self._version,
)
def _load(self) -> pd.DataFrame:
load_path = self._get_load_path()
with self._s3.open(str(load_path), mode="rb") as s3_file:
return pd.read_csv(s3_file, **self._load_args)
def _save(self, data: pd.DataFrame) -> None:
save_path = self._get_save_path()
with self._s3.open(str(save_path), mode="wb") as s3_file:
# Only binary read and write modes are implemented for S3Files
s3_file.write(data.to_csv(**self._save_args).encode("utf8"))
def _exists(self) -> bool:
load_path = str(self._get_load_path())
return self._s3.isfile(load_path)