ML Generic API

CHANGELOG.md

@@ -18,8 +18,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
     - `load_geojson`
     - `load_ml_model`
     - `load_url`
-    - `ml_fit_class_random_forest`
-    - `ml_fit_regr_random_forest`
+    - `ml_fit`
     - `ml_predict`
     - `save_ml_model`
     - `unflatten_dimension`

proposals/load_ml_model.json

@@ -1,7 +1,7 @@
 {
     "id": "load_ml_model",
     "summary": "Load a ML model",
-    "description": "Loads a machine learning model from a STAC Item.\n\nSuch a model could be trained and saved as part of a previous batch job with processes such as  ``ml_fit_regr_random_forest()`` and ``save_ml_model()``.",
+    "description": "Loads a machine learning model from a STAC Item.\n\nSuch a model could be trained and saved as part of a previous batch job with processes such as  ``ml_fit()`` and ``save_ml_model()``.",
     "categories": [
         "machine learning",
         "import"
@@ -43,4 +43,4 @@
             "rel": "about"
         }
     ]
-}
+}

proposals/ml_fit.json

@@ -0,0 +1,89 @@
+{
+    "id": "ml_fit",
+    "summary": "Train a machine learning or deep learning model",
+    "description": "Fit a machine learning or deep learning model to training data. It can be used for both classification and regression tasks, determined by the nature of the labels.",
+    "categories": [
+        "machine learning",
+        "deep learning"
+    ],
+    "experimental": true,
+    "parameters": [
+        {
+            "name": "predictors",
+            "description": "The predictors for the model as a vector data cube. These are the independent variables that the algorithm analyses to learn patterns and relationships within the data.",
+            "schema": [
+                {
+                    "type": "object",
+                    "subtype": "datacube",
+                    "dimensions": [
+                        {
+                            "type": "geometry"
+                        },
+                        {
+                            "type": "bands"
+                        }
+                    ]
+                },
+                {
+                    "type": "object",
+                    "subtype": "datacube",
+                    "dimensions": [
+                        {
+                            "type": "geometry"
+                        },
+                        {
+                            "type": "other"
+                        }
+                    ]
+                }
+            ]
+        },
+        {
+            "name": "target",
+            "description": "The dependent variable for the model. These are the labeled data, aligning with predictor values based on a shared geometry dimension. This ensures a clear connection between predictor rows and labels.",
+            "schema": {
+                "type": "object",
+                "subtype": "datacube",
+                "dimensions": [
+                    {
+                        "type": "geometry"
+                    }
+                ]
+            }
+        },
+        {
+            "name": "ml_method",
+            "description": "The machine learning method to be used for fitting the model.",
+            "schema": {
+                "type": "string",
+                "enum": [
+                    "cnn",
+                    "cnn_lstm",
+                    "mlp",
+                    "random_forest",
+                    "resnet",
+                    "svm",
+                    "tempcnn",
+                    "xgboost"
+                ],
+                "default": "random_forest"
+            }
+        },
+        {
+            "name": "parameters",
+            "description": "Additional parameters for the chosen machine learning method, passed as an object.",
+            "schema": {
+                "type": "object"
+            },
+            "default": null,
+            "optional": true
+        }
+    ],
+    "returns": {
+        "description": "A model object that can be saved with ``save_ml_model()`` and restored with ``load_ml_model()``.",
+        "schema": {
+            "type": "object",
+            "subtype": "ml-model"
+        }
+    }
+}

proposals/ml_predict.json

@@ -17,7 +17,7 @@
         },
         {
             "name": "model",
-            "description": "A ML model that was trained with one of the ML training processes such as ``ml_fit_regr_random_forest()``.",
+            "description": "A ML model that was trained with the ML training process ``ml_fit()``.",
             "schema": {
                 "type": "object",
                 "subtype": "ml-model"
@@ -46,4 +46,4 @@
             ]
         }
     }
-}
+}