fixup! fixup! fixup! fixup! fixup! fixup! Issue #114/#141 convert inline GeoJSON in aggregate_spatial to VectorCube

Author: soxofaan

openeo_driver/ProcessGraphDeserializer.py

@@ -740,32 +740,24 @@ def fit_class_random_forest(args: dict, env: EvalEnv) -> DriverMlModel:
         return DriverMlModel()
 
     predictors = extract_arg(args, 'predictors')
-    if not isinstance(predictors, AggregatePolygonSpatialResult):
-        # TODO #114 EP-3981 add support for real vector cubes.
+    if not isinstance(predictors, (AggregatePolygonSpatialResult, DriverVectorCube)):
+        # TODO #114 EP-3981 drop AggregatePolygonSpatialResult support.
         raise ProcessParameterInvalidException(
-            parameter="predictors", process="fit_class_random_forest",
-            reason=f"should be non-temporal vector-cube (got `{type(predictors)}`)."
-            )
-    target = extract_arg(args, 'target')
-    if not (
-            isinstance(target, dict)
-            and target.get("type") == "FeatureCollection"
-            and isinstance(target.get("features"), list)
-    ):
-        # TODO #114 EP-3981 vector cube support
-        raise ProcessParameterInvalidException(
-            parameter="target", process="fit_class_random_forest",
-            reason='only GeoJSON FeatureCollection is currently supported.',
+            parameter="predictors",
+            process="fit_class_random_forest",
+            reason=f"should be non-temporal vector-cube, got {type(predictors)}.",
         )
-    if any(
-        # TODO: allow string based target labels too?
-        not isinstance(deep_get(f, "properties", "target", default=None), int)
-        for f in target.get("features", [])
-    ):
+
+    target = extract_arg(args, "target")
+    if isinstance(target, DriverVectorCube):
+        pass
+    elif isinstance(target, dict) and target.get("type") == "FeatureCollection":
+        target = env.backend_implementation.DriverVectorCube.from_geojson(target)
+    else:
         raise ProcessParameterInvalidException(
             parameter="target",
             process="fit_class_random_forest",
-            reason="Each feature (from target feature collection) should have an integer 'target' property.",
+            reason=f"expected vector-cube like value but got {type(target)}.",
         )
 
     # TODO: get defaults from process spec?
@@ -1056,7 +1048,7 @@ def aggregate_spatial(args: dict, env: EvalEnv) -> DriverDataCube:
     if isinstance(geoms, DriverVectorCube):
         geoms = geoms
     elif isinstance(geoms, dict):
-        geoms = DriverVectorCube.from_geojson(geoms)
+        geoms = env.backend_implementation.DriverVectorCube.from_geojson(geoms)
     elif isinstance(geoms, DelayedVector):
         geoms = geoms.path
     else:
@@ -1559,7 +1551,7 @@ def to_vector_cube(args: Dict, env: EvalEnv):
     # TODO: standardization of something like this? https://github.com/Open-EO/openeo-processes/issues/346
     data = extract_arg(args, "data", process_id="to_vector_cube")
     if isinstance(data, dict) and data.get("type") in {"Polygon", "MultiPolygon", "Feature", "FeatureCollection"}:
-        return DriverVectorCube.from_geojson(data)
+        return env.backend_implementation.DriverVectorCube.from_geojson(data)
     # TODO: support more inputs: string with geojson, string with WKT, list of WKT, string with URL to GeoJSON, ...
     raise FeatureUnsupportedException(f"Converting {type(data)} to vector cube is not supported")
 

openeo_driver/_version.py

@@ -1 +1 @@
-__version__ = '0.20.4a1'
+__version__ = "0.21.0a1"

openeo_driver/backend.py

@@ -23,7 +23,7 @@
 from openeo.capabilities import ComparableVersion
 from openeo.internal.process_graph_visitor import ProcessGraphVisitor
 from openeo.util import rfc3339, dict_no_none
-from openeo_driver.datacube import DriverDataCube, DriverMlModel
+from openeo_driver.datacube import DriverDataCube, DriverMlModel, DriverVectorCube
 from openeo_driver.datastructs import SarBackscatterArgs
 from openeo_driver.dry_run import SourceConstraint
 from openeo_driver.errors import CollectionNotFoundException, ServiceUnsupportedException, FeatureUnsupportedException
@@ -570,6 +570,9 @@ class OpenEoBackendImplementation:
     enable_basic_auth = True
     enable_oidc_auth = True
 
+    # Overridable vector cube implementation
+    DriverVectorCube = DriverVectorCube
+
     def __init__(
             self,
             secondary_services: Optional[SecondaryServices] = None,

openeo_driver/datacube.py

@@ -177,7 +177,9 @@ def __init__(
     def with_cube(self, cube: xarray.DataArray, flatten_prefix: str = FLATTEN_PREFIX) -> "DriverVectorCube":
         """Create new vector cube with same geometries but new cube"""
         log.info(f"Creating vector cube with new cube {cube.name!r}")
-        return DriverVectorCube(geometries=self._geometries, cube=cube, flatten_prefix=flatten_prefix)
+        return type(self)(
+            geometries=self._geometries, cube=cube, flatten_prefix=flatten_prefix
+        )
 
     @classmethod
     def from_fiona(cls, paths: List[str], driver: str, options: dict) -> "DriverVectorCube":
@@ -333,6 +335,15 @@ def __eq__(self, other):
         return (isinstance(other, DriverVectorCube)
                 and np.array_equal(self._as_geopandas_df().values, other._as_geopandas_df().values))
 
+    def fit_class_random_forest(
+        self,
+        target: "DriverVectorCube",
+        num_trees: int = 100,
+        max_variables: Optional[Union[int, str]] = None,
+        seed: Optional[int] = None,
+    ) -> "DriverMlModel":
+        raise NotImplementedError
+
 
 class DriverMlModel:
     """Base class for driver-side 'ml-model' data structures"""

openeo_driver/dummy/dummy_backend.py

@@ -284,6 +284,25 @@ def fit_class_random_forest(
         )
 
 
+class DummyVectorCube(DriverVectorCube):
+    def fit_class_random_forest(
+        self,
+        target: DriverVectorCube,
+        num_trees: int = 100,
+        max_variables: Optional[Union[int, str]] = None,
+        seed: Optional[int] = None,
+    ) -> "DriverMlModel":
+        return DummyMlModel(
+            process_id="fit_class_random_forest",
+            # TODO: handle `to_geojson` in `DummyMlModel.write_assets` instead of here?
+            data=self.to_geojson(),
+            target=target.to_geojson(),
+            num_trees=num_trees,
+            max_variables=max_variables,
+            seed=seed,
+        )
+
+
 class DummyMlModel(DriverMlModel):
 
     def __init__(self, **kwargs):
@@ -608,6 +627,9 @@ def delete(self, user_id: str, process_id: str) -> None:
 
 
 class DummyBackendImplementation(OpenEoBackendImplementation):
+
+    DriverVectorCube = DummyVectorCube
+
     def __init__(self, processing: Optional[Processing] = None):
         super(DummyBackendImplementation, self).__init__(
             secondary_services=DummySecondaryServices(),

tests/test_views_execute.py

@@ -2699,17 +2699,84 @@ def test_chunk_polygon(api100):
 
 def test_fit_class_random_forest(api100):
     res = api100.check_result("fit_class_random_forest.json")
-    assert res.json == DictSubSet({
-        "type": "DummyMlModel",
-        "creation_data": {
-            "process_id": "fit_class_random_forest",
-            "data": [[100.0, 100.1, 100.2, 100.3], [101.0, 101.1, 101.2, 101.3]],
-            "target": DictSubSet({"type": "FeatureCollection"}),
-            "num_trees": 200,
-            "max_variables": None,
-            "seed": None,
+
+    geom1 = {
+        "type": "Polygon",
+        "coordinates": [[[3.0, 5.0], [4.0, 5.0], [4.0, 6.0], [3.0, 6.0], [3.0, 5.0]]],
+    }
+    geom2 = {
+        "type": "Polygon",
+        "coordinates": [[[8.0, 1.0], [9.0, 1.0], [9.0, 2.0], [8.0, 2.0], [8.0, 1.0]]],
+    }
+    assert res.json == DictSubSet(
+        {
+            "type": "DummyMlModel",
+            "creation_data": {
+                "process_id": "fit_class_random_forest",
+                "data": DictSubSet(
+                    {
+                        "type": "FeatureCollection",
+                        "features": [
+                            DictSubSet(
+                                {
+                                    "type": "Feature",
+                                    "id": "0",
+                                    "geometry": geom1,
+                                    "properties": {
+                                        "agg~B02": 2.345,
+                                        "agg~B03": None,
+                                        "agg~B04": 2.0,
+                                        "agg~B08": 3.0,
+                                        "target": 0,
+                                    },
+                                }
+                            ),
+                            DictSubSet(
+                                {
+                                    "type": "Feature",
+                                    "id": "1",
+                                    "geometry": geom2,
+                                    "properties": {
+                                        "agg~B02": 4.0,
+                                        "agg~B03": 5.0,
+                                        "agg~B04": 6.0,
+                                        "agg~B08": 7.0,
+                                        "target": 1,
+                                    },
+                                }
+                            ),
+                        ],
+                    }
+                ),
+                "target": DictSubSet(
+                    {
+                        "type": "FeatureCollection",
+                        "features": [
+                            DictSubSet(
+                                {
+                                    "type": "Feature",
+                                    "id": "0",
+                                    "geometry": geom1,
+                                    "properties": {"target": 0},
+                                }
+                            ),
+                            DictSubSet(
+                                {
+                                    "type": "Feature",
+                                    "id": "1",
+                                    "geometry": geom2,
+                                    "properties": {"target": 1},
+                                }
+                            ),
+                        ],
+                    }
+                ),
+                "max_variables": None,
+                "num_trees": 200,
+                "seed": None,
+            },
         }
-    })
+    )
 
 
 def test_if_merge_cubes(api100):