Extend geojson dataset to support more file types

Signed-off-by: Harm Matthias Harms <[email protected]>

kedro-datasets/RELEASE.md

@@ -1,10 +1,7 @@
 # Upcoming Release
 ## Major features and improvements
 
-- Added the following new datasets:
-  | Type | Description | Location |
-  | ---- | ----------- | -------- |
-  | `geopandas.ParquetDataset` | A dataset for loading and saving geopandas dataframe. | `kedro_datasets.geopandas` |
+- Add `file_format` to `geopandas.GeoJSONDataSet` to support parquet and feather file formats.
 
 ## Bug fixes and other changes
 ## Breaking Changes

kedro-datasets/kedro_datasets/geopandas/geojson_dataset.py

@@ -2,6 +2,7 @@
 underlying functionality is supported by geopandas, so it supports all
 allowed geopandas (pandas) options for loading and saving geosjon files.
 """
+
 from __future__ import annotations
 
 import copy
@@ -18,6 +19,8 @@
     get_protocol_and_path,
 )
 
+NON_FILE_SYSTEM_TARGETS = ["postgis"]
+
 
 class GeoJSONDataset(
     AbstractVersionedDataset[
@@ -41,7 +44,7 @@ class GeoJSONDataset(
         ...     {"col1": [1, 2], "col2": [4, 5], "col3": [5, 6]},
         ...     geometry=[Point(1, 1), Point(2, 4)],
         ... )
-        >>> dataset = GeoJSONDataset(filepath=tmp_path / "test.geojson", save_args=None)
+        >>> dataset = GeoJSONDataset(filepath=tmp_path / "test.geojson")
         >>> dataset.save(data)
         >>> reloaded = dataset.load()
         >>>
@@ -50,12 +53,13 @@ class GeoJSONDataset(
     """
 
     DEFAULT_LOAD_ARGS: dict[str, Any] = {}
-    DEFAULT_SAVE_ARGS = {"driver": "GeoJSON"}
+    DEFAULT_SAVE_ARGS: dict[str, Any] = {}
 
     def __init__(  # noqa: PLR0913
         self,
         *,
         filepath: str,
+        file_format: str = "file",
         load_args: dict[str, Any] | None = None,
         save_args: dict[str, Any] | None = None,
         version: Version | None = None,
@@ -72,6 +76,11 @@ def __init__(  # noqa: PLR0913
                 `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.
+            file_format: String which is used to match the appropriate load/save method on a best
+                effort basis. For example if 'parquet' is passed in the `geopandas.read_parquet` and
+                `geopandas.DataFrame.to_parquet` will be identified. An error will be raised unless
+                at least one matching `read_{file_format}` or `to_{file_format}` method is
+                identified. Defaults to 'file'.
             load_args: GeoPandas options for loading GeoJSON files.
                 Here you can find all available arguments:
                 https://geopandas.org/en/stable/docs/reference/api/geopandas.read_file.html
@@ -94,6 +103,9 @@ def __init__(  # noqa: PLR0913
             metadata: Any arbitrary metadata.
                 This is ignored by Kedro, but may be consumed by users or external plugins.
         """
+
+        self._file_format = file_format.lower()
+
         _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", {})
@@ -126,16 +138,45 @@ def __init__(  # noqa: PLR0913
         self._fs_open_args_load = _fs_open_args_load
         self._fs_open_args_save = _fs_open_args_save
 
+    def _ensure_file_system_target(self) -> None:
+        # Fail fast if provided a known non-filesystem target
+        if self._file_format in NON_FILE_SYSTEM_TARGETS:
+            raise DatasetError(
+                f"Cannot create a dataset of file_format '{self._file_format}' as it "
+                f"does not support a filepath target/source."
+            )
+
     def _load(self) -> gpd.GeoDataFrame | dict[str, gpd.GeoDataFrame]:
+        self._ensure_file_system_target()
+
         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 gpd.read_file(fs_file, **self._load_args)
+        load_method = getattr(gpd, f"read_{self._file_format}", None)
+        if load_method:
+            with self._fs.open(load_path, **self._fs_open_args_load) as fs_file:
+                return load_method(fs_file, **self._load_args)
+        raise DatasetError(
+            f"Unable to retrieve 'geopandas.read_{self._file_format}' method, please ensure that your "
+            "'file_format' parameter has been defined correctly as per the GeoPandas API "
+            "https://geopandas.org/en/stable/docs/reference/io.html"
+        )
 
     def _save(self, data: gpd.GeoDataFrame) -> None:
+        self._ensure_file_system_target()
+
         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_file(fs_file, **self._save_args)
-        self.invalidate_cache()
+        save_method = getattr(data, f"to_{self._file_format}", None)
+        if save_method:
+            with self._fs.open(save_path, **self._fs_open_args_save) as fs_file:
+                # KEY ASSUMPTION - first argument is path/buffer/io
+                save_method(fs_file, **self._save_args)
+                self.invalidate_cache()
+        else:
+            raise DatasetError(
+                f"Unable to retrieve 'geopandas.DataFrame.to_{self._file_format}' method, please "
+                "ensure that your 'file_format' parameter has been defined correctly as "
+                "per the GeoPandas API "
+                "https://geopandas.org/en/stable/docs/reference/io.html"
+            )
 
     def _exists(self) -> bool:
         try:
@@ -147,6 +188,7 @@ def _exists(self) -> bool:
     def _describe(self) -> dict[str, Any]:
         return {
             "filepath": self._filepath,
+            "file_format": self._file_format,
             "protocol": self._protocol,
             "load_args": self._load_args,
             "save_args": self._save_args,