Update fit_class_random_forest.json to official spec

fixes openEOPlatform/architecture-docs#220

Author: soxofaan

openeo_driver/specs/openeo-processes/experimental/fit_class_random_forest.json

@@ -1,7 +1,7 @@
 {
     "id": "fit_class_random_forest",
     "summary": "Train a random forest classification model",
-    "description": "Executes the fit of a random forest classification based on the user input of target and predictors. The Random Forest classification model is based on the approach by Breiman (2001).",
+    "description": "Executes the fit of a random forest classification based on training data. The process does not include a separate split of the data in test, validation and training data. The Random Forest classification model is based on the approach by Breiman (2001).",
     "categories": [
         "machine learning"
     ],
@@ -24,13 +24,23 @@
             }
         },
         {
-            "name": "training",
-            "description": "The amount of training data to be used in the classification, given as a fraction. The sampling will be chosen randomly through the data object. The remaining data will be used as test data for the validation.",
-            "schema": {
-                "type": "number",
-                "exclusiveMinimum": 0,
-                "maximum": 1
-            }
+            "name": "max_variables",
+            "description": "Specifies how many split variables will be used at a node.\n\nThe following options are available:\n\n- *integer*: The given number of variables are considered for each split.\n- `all`: All variables are considered for each split.\n- `log2`: The logarithm with base 2 of the number of variables are considered for each split.\n- `onethird`: A third of the number of variables are considered for each split.\n- `sqrt`: The square root of the number of variables are considered for each split. This is often the default for classification.",
+            "schema": [
+                {
+                    "type": "integer",
+                    "minimum": 1
+                },
+                {
+                    "type": "string",
+                    "enum": [
+                        "all",
+                        "log2",
+                        "onethird",
+                        "sqrt"
+                    ]
+                }
+            ]
         },
         {
             "name": "num_trees",
@@ -42,21 +52,6 @@
                 "minimum": 1
             }
         },
-        {
-            "name": "mtry",
-            "description": "Specifies how many split variables will be used at a node. Default value is `null`, which corresponds to the number of predictors divided by 3.",
-            "optional": true,
-            "default": null,
-            "schema": [
-                {
-                    "type": "integer",
-                    "minimum": 1
-                },
-                {
-                    "type": "null"
-                }
-            ]
-        },
         {
             "name": "seed",
             "description": "A randomization seed to use for the random sampling in training. If not given or `null`, no seed is used and results may differ on subsequent use.",
@@ -85,4 +80,4 @@
             "rel": "about"
         }
     ]
-}
+}