[KED-2254] Add datatable csv dataset (#592)

kedro/extras/datasets/datatable/__init__.py

@@ -0,0 +1,38 @@
+# 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.
+
+"""``AbstractDataSet`` implementations that produce datatable Frames."""
+
+__all__ = [
+    "CSVDataSet",
+]
+
+from contextlib import suppress
+
+with suppress(ImportError):
+    from .csv_dataset import CSVDataSet  # NOQA

kedro/extras/datasets/datatable/csv_dataset.py

@@ -0,0 +1,185 @@
+# 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.
+
+"""``CSVDataSet`` loads/saves data from/to a CSV file using an underlying
+filesystem (e.g.: local, S3, GCS). It uses datatable to handle the CSV file.
+"""
+import copy
+from pathlib import PurePosixPath
+from typing import Any, Dict
+
+import datatable as dt
+import fsspec
+
+from kedro.io.core import (
+    AbstractVersionedDataSet,
+    DataSetError,
+    Version,
+    get_filepath_str,
+    get_protocol_and_path,
+)
+
+
+class CSVDataSet(AbstractVersionedDataSet):
+    """``CSVDataSet`` loads/saves data from/to a CSV file using an underlying
+    filesystem (e.g.: local, S3, GCS). It uses datatable to handle the CSV file.
+
+    The main differences with respect to the ``pandas`` implementation:
+
+    - speed-up of csv reading, as datatable allows multi-thread reading from csv;
+    - usage of data manipulation API that is familiar to R users,
+      who might not have experience with ``pandas``.
+
+    Note that ``pandas.DataFrame`` is used for writing out.
+
+    Example:
+    ::
+
+        >>> from kedro.extras.datasets.datatable import CSVDataSet
+        >>> import datatable as dt
+        >>>
+        >>> data = dt.Frame(A=range(5), B=[1.7, 3.4, 0, None, -dt.math.inf],
+        >>>                stypes={"A": dt.int64})
+        >>>
+        >>> data_set = CSVDataSet(filepath="test.csv")
+        >>> data_set.save(data)
+
+    """
+
+    DEFAULT_LOAD_ARGS = {}  # type: Dict[str, Any]
+    DEFAULT_SAVE_ARGS = {"index": False}  # type: Dict[str, Any]
+
+    # pylint: disable=too-many-arguments
+    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: Datatable options for loading CSV files.
+                Here you can find all available arguments:
+                https://datatable.readthedocs.io/en/latest/api/dt/fread.html
+                All defaults are preserved.
+            save_args: Datatable options for saving CSV files.
+                Saving is done via pandas.
+                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
+        """
+        _fs_args = copy.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 = copy.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 = 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)
+
+        _fs_open_args_save.setdefault("mode", "w")
+        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) -> dt.Frame:
+        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 dt.fread(file=fs_file, **self._load_args)
+
+    def _save(self, data: dt.Frame) -> 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:
+            # convert to pandas before saving as otherwise can not use fs_file
+            data.to_pandas().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)

test_requirements.txt

@@ -5,6 +5,7 @@ behave==1.2.6
 biopython~=1.73
 black==v19.10.b0
 dask[complete]~=2.6
+datatable>=0.11.1, <1.0
 flake8~=3.5
 gcsfs>=0.3.0, <0.7.0 # gcsfs 0.7.0 requires fsspec>=0.8.0, but we pin fsspec <0.7.0
 geopandas>=0.6.0, <1.0