Migrate to general data cube definition

CHANGELOG.md

@@ -4,11 +4,22 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## Changes for vector cubes
+
+- Update the processes based on `raster-cubes` to work with `datacube` instead
+- Renamed `create_raster_cube` to `create_data_cube`
+- `add_dimension`: Added new dimension type `vector`
+- New definition for `aggregate_spatial`:
+    - Allows more than 3 input dimensions
+    - Allow to not export statistics by changing the parameter `target_dimenaion`
+    - Clarified how the resulting vector cube looks like
+
 ## Unreleased / Draft
 
 ### Added
 
 - New processes in proposal state:
+    - `filter_vector`
     - `fit_class_random_forest`
     - `fit_regr_random_forest`
     - `flatten_dimensions`
@@ -29,8 +40,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Renamed `text_merge` to `text_concat` for better alignment with `array_concat` and existing implementations.
 - `apply_neighborhood`: Allow `null` as default value for units.
 - `run_udf`: Allow all data types instead of just objects in the `context` parameter. [#376](https://github.com/Open-EO/openeo-processes/issues/376)
-- `load_collection` and `load_result`: Require at least one band if not set to `null`. [#372](https://github.com/Open-EO/openeo-processes/issues/372)
-- `load_collection`: Added a `NoDataAvailable` exception
+- `load_collection` and `load_result`:
+    - Require at least one band if not set to `null`. [#372](https://github.com/Open-EO/openeo-processes/issues/372)
+    - Added a `NoDataAvailable` exception
 - `inspect`: The parameter `message` has been moved to be the second argument. [#369](https://github.com/Open-EO/openeo-processes/issues/369)
 - `save_result`: Added a more concrete `DataCubeEmpty` exception.
 

add_dimension.json

@@ -11,7 +11,7 @@
             "description": "A data cube to add the dimension to.",
             "schema": {
                 "type": "object",
-                "subtype": "raster-cube"
+                "subtype": "datacube"
             }
         },
         {
@@ -39,9 +39,10 @@
             "schema": {
                 "type": "string",
                 "enum": [
+                    "bands",
                     "spatial",
                     "temporal",
-                    "bands",
+                    "vector",
                     "other"
                 ]
             },
@@ -53,12 +54,12 @@
         "description": "The data cube with a newly added dimension. The new dimension has exactly one dimension label. All other dimensions remain unchanged.",
         "schema": {
             "type": "object",
-            "subtype": "raster-cube"
+            "subtype": "datacube"
         }
     },
     "exceptions": {
         "DimensionExists": {
             "message": "A dimension with the specified name already exists."
         }
     }
-}
+}

aggregate_spatial.json

@@ -1,27 +1,47 @@
 {
     "id": "aggregate_spatial",
     "summary": "Zonal statistics for geometries",
-    "description": "Aggregates statistics for one or more geometries (e.g. zonal statistics for polygons) over the spatial dimensions. The number of total and valid pixels is returned together with the calculated values.\n\nAn 'unbounded' aggregation over the full extent of the horizontal spatial dimensions can be computed with the process ``reduce_spatial()``.\n\nThis process passes a list of values to the reducer. The list of values has an undefined order, therefore processes such as ``last()`` and ``first()`` that depend on the order of the values will lead to unpredictable results.",
+    "description": "Aggregates statistics for one or more geometries (e.g. zonal statistics for polygons) over the spatial dimensions. The given data cube can have multiple additional dimension and for all these dimensions results will be computed individually.\n\nAn 'unbounded' aggregation over the full extent of the horizontal spatial dimensions can be computed with the process ``reduce_spatial()``.\n\nThis process passes a list of values to the reducer. The list of values has an undefined order, therefore processes such as ``last()`` and ``first()`` that depend on the order of the values will lead to unpredictable results.",
     "categories": [
         "cubes",
         "aggregate & resample"
     ],
     "parameters": [
         {
             "name": "data",
-            "description": "A raster data cube.\n\nThe data cube must have been reduced to only contain two spatial dimensions and a third dimension the values are aggregated for, for example the temporal dimension to get a time series. Otherwise, this process fails with the `TooManyDimensions` exception.\n\nThe data cube implicitly gets restricted to the bounds of the geometries as if ``filter_spatial()`` would have been used with the same values for the corresponding parameters immediately before this process.",
+            "description": "A raster data cube with at least two spatial dimensions.\n\nThe data cube implicitly gets restricted to the bounds of the geometries as if ``filter_spatial()`` would have been used with the same values for the corresponding parameters immediately before this process.",
             "schema": {
                 "type": "object",
-                "subtype": "raster-cube"
+                "subtype": "datacube",
+                "dimensions": [
+                    {
+                        "type": "spatial",
+                        "axis": [
+                            "x",
+                            "y"
+                        ]
+                    }
+                ]
             }
         },
         {
             "name": "geometries",
-            "description": "Geometries as GeoJSON on which the aggregation will be based. Vector properties are preserved for vector data cubes and all GeoJSON Features.\n\nOne value will be computed per GeoJSON `Feature`, `Geometry` or `GeometryCollection`. For a `FeatureCollection` multiple values will be computed, one value per contained `Feature`. For example, a single value will be computed for a `MultiPolygon`, but two values will be computed for a `FeatureCollection` containing two polygons.\n\n- For **polygons**, the process considers all pixels for which the point at the pixel center intersects with the corresponding polygon (as defined in the Simple Features standard by the OGC).\n- For **points**, the process considers the closest pixel center.\n- For **lines** (line strings), the process considers all the pixels whose centers are closest to at least one point on the line.\n\nThus, pixels may be part of multiple geometries and be part of multiple aggregations.\n\nTo maximize interoperability, a nested `GeometryCollection` should be avoided. Furthermore, a `GeometryCollection` composed of a single type of geometries should be avoided in favour of the corresponding multi-part type (e.g. `MultiPolygon`).",
-            "schema": {
-                "type": "object",
-                "subtype": "geojson"
-            }
+            "description": "Geometries for which the aggregation will be computed. Vector properties are preserved for vector data cubes and all GeoJSON Features.\n\nOne value will be computed per label in the dimension of type `vector`, GeoJSON `Feature`, `Geometry` or `GeometryCollection`. For a `FeatureCollection` multiple values will be computed, one value per contained `Feature`. For example, a single value will be computed for a `MultiPolygon`, but two values will be computed for a `FeatureCollection` containing two polygons.\n\n- For **polygons**, the process considers all pixels for which the point at the pixel center intersects with the corresponding polygon (as defined in the Simple Features standard by the OGC).\n- For **points**, the process considers the closest pixel center.\n- For **lines** (line strings), the process considers all the pixels whose centers are closest to at least one point on the line.\n\nThus, pixels may be part of multiple geometries and be part of multiple aggregations.\n\nTo maximize interoperability, a nested `GeometryCollection` should be avoided. Furthermore, a `GeometryCollection` composed of a single type of geometries should be avoided in favour of the corresponding multi-part type (e.g. `MultiPolygon`).",
+            "schema": [
+                {
+                    "type": "object",
+                    "subtype": "geojson"
+                },
+                {
+                    "type": "object",
+                    "subtype": "datacube",
+                    "dimensions": [
+                        {
+                            "type": "vector"
+                        }
+                    ]
+                }
+            ]
         },
         {
             "name": "reducer",
@@ -60,11 +80,14 @@
         },
         {
             "name": "target_dimension",
-            "description": "The name of a new dimensions that is used to store the results. A new dimension will be created with the given name and type `other` (see ``add_dimension()``). Defaults to the dimension name `result`. Fails with a `TargetDimensionExists` exception if a dimension with the specified name exists.",
+            "description": "By default (which is `null`), the process only computes the results and doesn't add a new dimension. If this parameter contains a new dimension name, the computation also stores information about the total count of pixels (valid + invalid pixels) and the number of valid pixels (see ``is_valid()``) for each computed value. These values are added as a new dimension. The new dimension of type `other` has the dimension labels `value`, `total_count` and `valid_count`.",
             "schema": {
-                "type": "string"
+                "type": [
+                    "string",
+                    "null"
+                ]
             },
-            "default": "result",
+            "default": null,
             "optional": true
         },
         {
@@ -78,16 +101,18 @@
         }
     ],
     "returns": {
-        "description": "A vector data cube with the computed results and restricted to the bounds of the geometries.\n\nThe computed value is used for the dimension with the name that was specified in the parameter `target_dimension`.\n\nThe computation also stores information about the total count of pixels (valid + invalid pixels) and the number of valid pixels (see ``is_valid()``) for each geometry. These values are added as a new dimension with a dimension name derived from `target_dimension` by adding the suffix `_meta`. The new dimension has the dimension labels `total_count` and `valid_count`.",
+        "description": "A vector data cube with the computed results and restricted to the bounds of the geometries. The spatial dimensions is replaced by a vector dimension and if `target_dimension` is not `null`, a new dimension is added.",
         "schema": {
             "type": "object",
-            "subtype": "vector-cube"
+            "subtype": "datacube",
+            "dimensions": [
+                {
+                    "type": "vector"
+                }
+            ]
         }
     },
     "exceptions": {
-        "TooManyDimensions": {
-            "message": "The number of dimensions must be reduced to three for `aggregate_spatial`."
-        },
         "TargetDimensionExists": {
             "message": "A dimension with the specified target dimension name already exists."
         }

aggregate_temporal.json

@@ -12,7 +12,12 @@
             "description": "A data cube.",
             "schema": {
                 "type": "object",
-                "subtype": "raster-cube"
+                "subtype": "datacube",
+                "dimensions": [
+                    {
+                        "type": "temporal"
+                    }
+                ]
             }
         },
         {
@@ -162,7 +167,12 @@
         "description": "A new data cube with the same dimensions. The dimension properties (name, type, labels, reference system and resolution) remain unchanged, except for the resolution and dimension labels of the given temporal dimension.",
         "schema": {
             "type": "object",
-            "subtype": "raster-cube"
+            "subtype": "datacube",
+            "dimensions": [
+                {
+                    "type": "temporal"
+                }
+            ]
         }
     },
     "examples": [
@@ -234,4 +244,4 @@
             "title": "Aggregation explained in the openEO documentation"
         }
     ]
-}
+}

aggregate_temporal_period.json

@@ -13,7 +13,12 @@
             "description": "The source data cube.",
             "schema": {
                 "type": "object",
-                "subtype": "raster-cube"
+                "subtype": "datacube",
+                "dimensions": [
+                    {
+                        "type": "temporal"
+                    }
+                ]
             }
         },
         {
@@ -97,7 +102,12 @@
         "description": "A new data cube with the same dimensions. The dimension properties (name, type, labels, reference system and resolution) remain unchanged, except for the resolution and dimension labels of the given temporal dimension. The specified temporal dimension has the following dimension labels (`YYYY` = four-digit year, `MM` = two-digit month, `DD` two-digit day of month):\n\n* `hour`: `YYYY-MM-DD-00` - `YYYY-MM-DD-23`\n* `day`: `YYYY-001` - `YYYY-365`\n* `week`: `YYYY-01` - `YYYY-52`\n* `dekad`: `YYYY-00` - `YYYY-36`\n* `month`: `YYYY-01` - `YYYY-12`\n* `season`: `YYYY-djf` (December - February), `YYYY-mam` (March - May), `YYYY-jja` (June - August), `YYYY-son` (September - November).\n* `tropical-season`: `YYYY-ndjfma` (November - April), `YYYY-mjjaso` (May - October).\n* `year`: `YYYY`\n* `decade`: `YYY0`\n* `decade-ad`: `YYY1`\n\nThe dimension labels in the new data cube are complete for the whole extent of the source data cube. For example, if `period` is set to `day` and the source data cube has two dimension labels at the beginning of the year (`2020-01-01`) and the end of a year (`2020-12-31`), the process returns a data cube with 365 dimension labels (`2020-001`, `2020-002`, ..., `2020-365`). In contrast, if `period` is set to `day` and the source data cube has just one dimension label `2020-01-05`, the process returns a data cube with just a single dimension label (`2020-005`).",
         "schema": {
             "type": "object",
-            "subtype": "raster-cube"
+            "subtype": "datacube",
+            "dimensions": [
+                {
+                    "type": "temporal"
+                }
+            ]
         }
     },
     "exceptions": {
@@ -118,4 +128,4 @@
             "title": "Aggregation explained in the openEO documentation"
         }
     ]
-}
+}

anomaly.json

@@ -13,15 +13,25 @@
             "description": "A data cube with exactly one temporal dimension and the following dimension labels for the given period (`YYYY` = four-digit year, `MM` = two-digit month, `DD` two-digit day of month):\n\n* `hour`: `YYYY-MM-DD-00` - `YYYY-MM-DD-23`\n* `day`: `YYYY-001` - `YYYY-365`\n* `week`: `YYYY-01` - `YYYY-52`\n* `dekad`: `YYYY-00` - `YYYY-36`\n* `month`: `YYYY-01` - `YYYY-12`\n* `season`: `YYYY-djf` (December - February), `YYYY-mam` (March - May), `YYYY-jja` (June - August), `YYYY-son` (September - November).\n* `tropical-season`: `YYYY-ndjfma` (November - April), `YYYY-mjjaso` (May - October).\n* `year`: `YYYY`\n* `decade`: `YYY0`\n* `decade-ad`: `YYY1`\n* `single-period` / `climatology-period`: Any\n\n``aggregate_temporal_period()`` can compute such a data cube.",
             "schema": {
                 "type": "object",
-                "subtype": "raster-cube"
+                "subtype": "datacube",
+                "dimensions": [
+                    {
+                        "type": "temporal"
+                    }
+                ]
             }
         },
         {
             "name": "normals",
             "description": "A data cube with normals, e.g. daily, monthly or yearly values computed from a process such as ``climatological_normal()``. Must contain exactly one temporal dimension with the following dimension labels for the given period:\n\n* `hour`: `00` - `23`\n* `day`: `001` - `365`\n* `week`: `01` - `52`\n* `dekad`: `00` - `36`\n* `month`: `01` - `12`\n* `season`: `djf` (December - February), `mam` (March - May), `jja` (June - August), `son` (September - November)\n* `tropical-season`: `ndjfma` (November - April), `mjjaso` (May - October)\n* `year`: Four-digit year numbers\n* `decade`: Four-digit year numbers, the last digit being a `0`\n* `decade-ad`: Four-digit year numbers, the last digit being a `1`\n* `single-period` / `climatology-period`: A single dimension label with any name is expected.",
             "schema": {
                 "type": "object",
-                "subtype": "raster-cube"
+                "subtype": "datacube",
+                "dimensions": [
+                    {
+                        "type": "temporal"
+                    }
+                ]
             }
         },
         {
@@ -50,7 +60,12 @@
         "description": "A data cube with the same dimensions. The dimension properties (name, type, labels, reference system and resolution) remain unchanged.",
         "schema": {
             "type": "object",
-            "subtype": "raster-cube"
+            "subtype": "datacube",
+            "dimensions": [
+                {
+                    "type": "temporal"
+                }
+            ]
         }
     }
 }

apply.json

@@ -1,7 +1,7 @@
 {
     "id": "apply",
-    "summary": "Apply a process to each pixel",
-    "description": "Applies a process to each pixel value in the data cube (i.e. a local operation). In contrast, the process ``apply_dimension()`` applies a process to all pixel values along a particular dimension.",
+    "summary": "Apply a process to each value",
+    "description": "Applies a process to each value in the data cube (i.e. a local operation). In contrast, the process ``apply_dimension()`` applies a process to all values along a particular dimension.",
     "categories": [
         "cubes"
     ],
@@ -11,7 +11,7 @@
             "description": "A data cube.",
             "schema": {
                 "type": "object",
-                "subtype": "raster-cube"
+                "subtype": "datacube"
             }
         },
         {
@@ -60,7 +60,7 @@
         "description": "A data cube with the newly computed values and the same dimensions. The dimension properties (name, type, labels, reference system and resolution) remain unchanged.",
         "schema": {
             "type": "object",
-            "subtype": "raster-cube"
+            "subtype": "datacube"
         }
     },
     "links": [