feat(machine-learning): export the four advanced trainers

common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/machineLearning/sklearnAdvanced/KNNTrainer/SklearnAdvancedKNNParameters.java

@@ -22,24 +22,35 @@
 import org.apache.texera.amber.operator.machineLearning.sklearnAdvanced.base.ParamClass;
 
 public enum SklearnAdvancedKNNParameters implements ParamClass {
-    n_neighbors("n_neighbors", "int"),
-    p("p", "int"),
-    weights("weights", "str"),
-    algorithm("algorithm", "str"),
-    leaf_size("leaf_size", "int"),
-    // A metric is named, not measured: "minkowski" and the rest of the accepted
-    // set are words, so int() rejects every value scikit-learn would take.
-    metric("metric", "str"),
+    // Bounds are scikit-learn's own: a neighbour count and a leaf size start at one, and the
+    // Minkowski power is open at zero.
+    n_neighbors("n_neighbors", "int", "5") { @Override public String getMinimum() { return ">=1"; } },
+    p("p", "int", "2") { @Override public String getMinimum() { return ">0"; } },
+    weights("weights", "str", "", "uniform", "distance"),
+    algorithm("algorithm", "str", "", "auto", "ball_tree", "kd_tree", "brute"),
+    leaf_size("leaf_size", "int", "30") { @Override public String getMinimum() { return ">=1"; } },
+    // A metric is named, not measured: "minkowski" and the rest are words, so the
+    // int() this used to declare rejected every value scikit-learn would take. The
+    // set is the one every `algorithm` above accepts -- the tree algorithms take
+    // fewer metrics than brute force, and naming a brute-only metric here would
+    // break the moment the sibling knob is moved off `auto`.
+    metric("metric", "str", "minkowski", "minkowski", "euclidean", "manhattan",
+            "chebyshev", "cityblock", "l1", "l2"),
     // The only one that is not a scalar. scikit-learn wants a mapping of extra
     // keyword arguments for the metric, so the user's text is read as JSON.
-    metric_params("metric_params", "json.loads");
+    metric_params("metric_params", "json.loads", "{}");
 
     private final String name;
     private final String type;
+    private final String sampleValue;
+    private final String[] allowedValues;
 
-    SklearnAdvancedKNNParameters(String name, String type) {
+    SklearnAdvancedKNNParameters(
+            String name, String type, String sampleValue, String... allowedValues) {
         this.name = name;
         this.type = type;
+        this.sampleValue = sampleValue;
+        this.allowedValues = allowedValues;
     }
 
     public String getType() {
@@ -49,4 +60,12 @@ public String getType() {
     public String getName() {
         return this.name;
     }
+
+    public String getSampleValue() {
+        return this.sampleValue;
+    }
+
+    public String[] getAllowedValues() {
+        return this.allowedValues.clone();
+    }
 }

common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/machineLearning/sklearnAdvanced/SVCTrainer/SklearnAdvancedSVCParameters.java

@@ -22,20 +22,41 @@
 import org.apache.texera.amber.operator.machineLearning.sklearnAdvanced.base.ParamClass;
 
 public enum SklearnAdvancedSVCParameters implements ParamClass {
-    C("C", "float"),
-    kernel("kernel", "str"),
-    gamma("gamma", "float"),
-    degree("degree", "int"),
-    coef0("coef0", "float"),
-    tol("tol", "float"),
-    probability("probability", "(lambda value: value.lower() == \"true\")");
+    // Bounds are scikit-learn's own, whose ranges are open at zero for the two below and
+    // closed for degree.
+    C("C", "float", "1.0") { @Override public String getMinimum() { return ">0"; } },
+    kernel("kernel", "str", "", "rbf", "linear", "poly", "sigmoid", "precomputed"),
+    // gamma takes either of two words or a number, so no converter of a name covers it, and
+    // the pattern states what this one takes. Digits are [0-9] rather than \d so the browser
+    // and Python read it alike. It lets a negative through for the estimator to refuse, since
+    // excluding the sign would also exclude -0.0, which the estimator takes.
+    gamma(
+            "gamma",
+            "(lambda value: value.strip() if value.strip() in (\"scale\", \"auto\") else float(value))",
+            "scale") {
+        @Override
+        public String getPattern() {
+            return "^\\s*(?:scale|auto|[-+]?(?:(?:[0-9]+(?:_[0-9]+)*)?\\.(?:[0-9]+(?:_[0-9]+)*)"
+                    + "|(?:[0-9]+(?:_[0-9]+)*)\\.?)(?:[eE][-+]?[0-9]+(?:_[0-9]+)*)?)\\s*$";
+        }
+    },
+    degree("degree", "int", "3") { @Override public String getMinimum() { return ">=0"; } },
+    // coef0 is the one parameter here with no bound at either end.
+    coef0("coef0", "float", "0.0"),
+    tol("tol", "float", "0.001") { @Override public String getMinimum() { return ">0"; } },
+    probability("probability", "(lambda value: value.lower() == \"true\")", "", "false", "true");
 
     private final String name;
     private final String type;
+    private final String sampleValue;
+    private final String[] allowedValues;
 
-    SklearnAdvancedSVCParameters(String name, String type) {
+    SklearnAdvancedSVCParameters(
+            String name, String type, String sampleValue, String... allowedValues) {
         this.name = name;
         this.type = type;
+        this.sampleValue = sampleValue;
+        this.allowedValues = allowedValues;
     }
 
     public String getType() {
@@ -45,4 +66,12 @@ public String getType() {
     public String getName() {
         return this.name;
     }
+
+    public String getSampleValue() {
+        return this.sampleValue;
+    }
+
+    public String[] getAllowedValues() {
+        return this.allowedValues.clone();
+    }
 }

common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/machineLearning/sklearnAdvanced/SVRTrainer/SklearnAdvancedSVRParameters.java

@@ -22,24 +22,42 @@
 import org.apache.texera.amber.operator.machineLearning.sklearnAdvanced.base.ParamClass;
 
 public enum SklearnAdvancedSVRParameters implements ParamClass {
-    C("C", "float"),
-    kernel("kernel", "str"),
-    gamma("gamma", "float"),
-    degree("degree", "int"),
-    coef0("coef0", "float"),
-    tol("tol", "float"),
-    shrinking("shrinking", "(lambda value: value.lower() == \"true\")"),
-    verbose("verbose", "(lambda value: value.lower() == \"true\")"),
-    epsilon("epsilon", "float"),
-    cache_size("cache_size", "int"),
-    max_iter("max_iter", "int");
+    // Bounds are scikit-learn's own; see SVC for the shared ones.
+    C("C", "float", "1.0") { @Override public String getMinimum() { return ">0"; } },
+    kernel("kernel", "str", "", "rbf", "linear", "poly", "sigmoid", "precomputed"),
+    // Same converter and shape as SVC's gamma -- see there for why each is spelled this way.
+    gamma(
+            "gamma",
+            "(lambda value: value.strip() if value.strip() in (\"scale\", \"auto\") else float(value))",
+            "scale") {
+        @Override
+        public String getPattern() {
+            return "^\\s*(?:scale|auto|[-+]?(?:(?:[0-9]+(?:_[0-9]+)*)?\\.(?:[0-9]+(?:_[0-9]+)*)"
+                    + "|(?:[0-9]+(?:_[0-9]+)*)\\.?)(?:[eE][-+]?[0-9]+(?:_[0-9]+)*)?)\\s*$";
+        }
+    },
+    degree("degree", "int", "3") { @Override public String getMinimum() { return ">=0"; } },
+    coef0("coef0", "float", "0.0"),
+    tol("tol", "float", "0.001") { @Override public String getMinimum() { return ">0"; } },
+    shrinking("shrinking", "(lambda value: value.lower() == \"true\")", "", "true", "false"),
+    verbose("verbose", "(lambda value: value.lower() == \"true\")", "", "false", "true"),
+    epsilon("epsilon", "float", "0.1") { @Override public String getMinimum() { return ">=0"; } },
+    cache_size("cache_size", "int", "200") { @Override public String getMinimum() { return ">0"; } },
+    // -1 is SVR's own value for no iteration limit, which is also why the bound is -1 and not
+    // zero: the sentinel has to remain reachable.
+    max_iter("max_iter", "int", "-1") { @Override public String getMinimum() { return ">=-1"; } };
 
     private final String name;
     private final String type;
+    private final String sampleValue;
+    private final String[] allowedValues;
 
-    SklearnAdvancedSVRParameters(String name, String type) {
+    SklearnAdvancedSVRParameters(
+            String name, String type, String sampleValue, String... allowedValues) {
         this.name = name;
         this.type = type;
+        this.sampleValue = sampleValue;
+        this.allowedValues = allowedValues;
     }
 
     public String getType() {
@@ -49,4 +67,12 @@ public String getType() {
     public String getName() {
         return this.name;
     }
+
+    public String getSampleValue() {
+        return this.sampleValue;
+    }
+
+    public String[] getAllowedValues() {
+        return this.allowedValues.clone();
+    }
 }

common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/machineLearning/sklearnAdvanced/base/HyperParameters.scala

@@ -27,8 +27,27 @@ import org.apache.texera.amber.operator.metadata.annotations.{
   HideAnnotation
 }
 
+/**
+  * One row of a trainer's parameter table. `parametersSource` decides which of the two inputs
+  * the row uses, and the hide rules below show only that one, so exactly one of them is needed
+  * and neither can be required outright.
+  */
+@JsonSchemaInject(json = """
+{
+  "allOf": [
+    {
+      "if": { "properties": { "parametersSource": { "const": true } } },
+      "then": { "required": ["attribute"] },
+      "else": { "required": ["value"] }
+    }
+  ]
+}
+""")
 class HyperParameters[T] {
 
+  // Two rows naming one parameter emit its keyword argument twice, which the generated
+  // Python will not compile, so the form warns on the row rather than letting it be added.
+  @JsonSchemaInject(json = """{ "uniqueAmongRows": true }""")
   @JsonProperty(required = true)
   @JsonSchemaTitle("Parameter")
   @JsonPropertyDescription("Choose the name of the parameter")