"""``CSVDataSet`` loads/saves data from/to a CSV file using an underlying
filesystem (e.g.: local, S3, GCS). It uses pandas to handle the CSV file.
"""
from copy import deepcopy
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 CSVDataSet(AbstractVersionedDataSet):
"""``CSVDataSet`` loads/saves data from/to a CSV file using an underlying
filesystem (e.g.: local, S3, GCS). It uses pandas to handle the CSV file.
Example adding a catalog entry with
`YAML API
<https://kedro.readthedocs.io/en/stable/05_data/\
01_data_catalog.html#using-the-data-catalog-with-the-yaml-api>`_:
.. code-block:: yaml
>>> cars:
>>> type: pandas.CSVDataSet
>>> filepath: data/01_raw/company/cars.csv
>>> load_args:
>>> sep: ","
>>> na_values: ["#NA", NA]
>>> save_args:
>>> index: False
>>> date_format: "%Y-%m-%d %H:%M"
>>> decimal: .
>>>
>>> motorbikes:
>>> type: pandas.CSVDataSet
>>> filepath: s3://your_bucket/data/02_intermediate/company/motorbikes.csv
>>> credentials: dev_s3
>>>
Example using Python API:
::
>>> from kedro.extras.datasets.pandas import CSVDataSet
>>> import pandas as pd
>>>
>>> data = pd.DataFrame({'col1': [1, 2], 'col2': [4, 5],
>>> 'col3': [5, 6]})
>>>
>>> # data_set = CSVDataSet(filepath="gcs://bucket/test.csv")
>>> data_set = CSVDataSet(filepath="test.csv")
>>> 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,
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 ``CSVDataSet`` pointing to a concrete CSV file
on a specific filesystem.
Args:
filepath: Filepath in POSIX format to a CSV 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.
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.
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 `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 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)
if save_args is not None:
self._save_args.update(save_args)
_fs_open_args_save.setdefault("mode", "w")
_fs_open_args_save.setdefault("newline", "")
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,
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_csv(fs_file, **self._load_args)
def _save(self, data: pd.DataFrame) -> None:
save_path = get_filepath_str(self._get_save_path(), self._protocol)
with self._fs.open(save_path, **self._fs_open_args_save) as fs_file:
data.to_csv(path_or_buf=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)