Changeset 8982 for trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/GaussianProcess/MeanFunctions/MeanConst.cs

Timestamp:

12/01/12 19:02:47 (11 years ago)

Author:

gkronber

Message:

#1902: removed class HyperParameter and changed implementations of covariance and mean functions to remove the parameter value caching and event handlers for parameter caching. Instead it is now possible to create the actual covariance and mean functions as Func from templates and specified parameter values. The instances of mean and covariance functions configured in the GUI are actually templates where the structure and fixed parameters can be specified.

File:

• trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/GaussianProcess/MeanFunctions/MeanConst.cs (modified) (5 diffs)

trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/GaussianProcess/MeanFunctions/MeanConst.cs

@@ -21 +21 @@
 
 using System;
+using System.Collections.Generic;
 using System.Linq;
 using HeuristicLab.Common;
 using HeuristicLab.Core;
 using HeuristicLab.Data;
+using HeuristicLab.Parameters;
 using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
 
@@ -31 +33 @@
   [Item(Name = "MeanConst", Description = "Constant mean function for Gaussian processes.")]
   public sealed class MeanConst : ParameterizedNamedItem, IMeanFunction {
-    [Storable]
-    private double c;
-    [Storable]
-    private readonly HyperParameter<DoubleValue> valueParameter;
-    public IValueParameter<DoubleValue> ValueParameter { get { return valueParameter; } }
+    public IValueParameter<DoubleValue> ValueParameter {
+      get { return (IValueParameter<DoubleValue>)Parameters["Value"]; }
+    }
 
     [StorableConstructor]
@@ -41 +41 @@
     private MeanConst(MeanConst original, Cloner cloner)
       : base(original, cloner) {
-      this.c = original.c;
-      this.valueParameter = cloner.Clone(original.valueParameter);
-      RegisterEvents();
     }
     public MeanConst()
@@ -50 +47 @@
       this.description = ItemDescription;
 
-      this.valueParameter = new HyperParameter<DoubleValue>("Value", "The constant value for the constant mean function.");
-      Parameters.Add(valueParameter);
-      RegisterEvents();
+      Parameters.Add(new OptionalValueParameter<DoubleValue>("Value", "The constant value for the constant mean function."));
     }
 
@@ -59 +54 @@
     }
 
-    [StorableHook(HookType.AfterDeserialization)]
-    private void AfterDeserialization() {
-      RegisterEvents();
+    public int GetNumberOfParameters(int numberOfVariables) {
+      return ValueParameter.Value != null ? 0 : 1;
     }
 
-    private void RegisterEvents() {
-      Util.AttachValueChangeHandler<DoubleValue, double>(valueParameter, () => { c = valueParameter.Value.Value; });
+    public void SetParameter(double[] p) {
+      double c;
+      GetParameters(p, out c);
+      ValueParameter.Value = new DoubleValue(c);
     }
 
-    public int GetNumberOfParameters(int numberOfVariables) {
-      return valueParameter.Fixed ? 0 : 1;
+    private void GetParameters(double[] p, out double c) {
+      if (ValueParameter.Value == null) {
+        c = p[0];
+      } else {
+        if (p.Length > 0)
+          throw new ArgumentException(
+            "The length of the parameter vector does not match the number of free parameters for the constant mean function.",
+            "p");
+        c = ValueParameter.Value.Value;
+      }
     }
 
-    public void SetParameter(double[] hyp) {
-      if (!valueParameter.Fixed) {
-        valueParameter.SetValue(new DoubleValue(hyp[0]));
-      } else if (hyp.Length > 0)
-        throw new ArgumentException("The length of the parameter vector does not match the number of free parameters for the constant mean function.", "hyp");
-    }
-
-    public double[] GetMean(double[,] x) {
-      return Enumerable.Repeat(c, x.GetLength(0)).ToArray();
-    }
-
-    public double[] GetGradients(int k, double[,] x) {
-      if (k > 0) throw new ArgumentException();
-      return Enumerable.Repeat(1.0, x.GetLength(0)).ToArray();
+    public ParameterizedMeanFunction GetParameterizedMeanFunction(double[] p, IEnumerable<int> columnIndices) {
+      double c;
+      GetParameters(p, out c);
+      var mf = new ParameterizedMeanFunction();
+      mf.Mean = (x, i) => c;
+      mf.Gradient = (x, i, k) => {
+        if (k > 0) throw new ArgumentException();
+        return 1.0;
+      };
+      return mf;
     }
   }