Changeset 8660 for branches/GP-MoveOperators/HeuristicLab.Algorithms.DataAnalysis/3.4/SupportVectorMachine/SupportVectorClassification.cs

Timestamp:

09/14/12 18:58:15 (12 years ago)

Author:

gkronber

Message:

#1847 merged r8205:8635 from trunk into branch

Location:

branches/GP-MoveOperators

Files:

• . (modified) (2 props)
• HeuristicLab.Algorithms.DataAnalysis/3.4 (modified) (1 prop)
• HeuristicLab.Algorithms.DataAnalysis/3.4/SupportVectorMachine/SupportVectorClassification.cs (modified) (8 diffs)

branches/GP-MoveOperators

@@ -21 +21 @@
 protoc.exe
 _ReSharper.HeuristicLab 3.3 Tests
+Google.ProtocolBuffers-2.4.1.473.dll

@@ -21 +21 @@
 protoc.exe
 _ReSharper.HeuristicLab 3.3 Tests
+Google.ProtocolBuffers-2.4.1.473.dll

branches/GP-MoveOperators/HeuristicLab.Algorithms.DataAnalysis/3.4

@@ -5 +5 @@
 *.vs10x
 Plugin.cs
+*.user

@@ -5 +5 @@
 *.vs10x
 Plugin.cs
+*.user

branches/GP-MoveOperators/HeuristicLab.Algorithms.DataAnalysis/3.4/SupportVectorMachine/SupportVectorClassification.cs

@@ -30 +30 @@
 using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
 using HeuristicLab.Problems.DataAnalysis;
+using LibSVM;
 
 namespace HeuristicLab.Algorithms.DataAnalysis {
@@ -44 +45 @@
     private const string NuParameterName = "Nu";
     private const string GammaParameterName = "Gamma";
+    private const string DegreeParameterName = "Degree";
 
     #region parameter properties
@@ -60 +62 @@
     public IValueParameter<DoubleValue> GammaParameter {
       get { return (IValueParameter<DoubleValue>)Parameters[GammaParameterName]; }
+    }
+    public IValueParameter<IntValue> DegreeParameter {
+      get { return (IValueParameter<IntValue>)Parameters[DegreeParameterName]; }
     }
     #endregion
@@ -79 +84 @@
     public DoubleValue Gamma {
       get { return GammaParameter.Value; }
+    }
+    public IntValue Degree {
+      get { return DegreeParameter.Value; }
     }
     #endregion
@@ -103 +111 @@
       Parameters.Add(new ValueParameter<DoubleValue>(CostParameterName, "The value of the C (cost) parameter of C-SVC.", new DoubleValue(1.0)));
       Parameters.Add(new ValueParameter<DoubleValue>(GammaParameterName, "The value of the gamma parameter in the kernel function.", new DoubleValue(1.0)));
+      Parameters.Add(new ValueParameter<IntValue>(DegreeParameterName, "The degree parameter for the polynomial kernel function.", new IntValue(3)));
     }
     [StorableHook(HookType.AfterDeserialization)]
-    private void AfterDeserialization() { }
+    private void AfterDeserialization() {
+      #region backwards compatibility (change with 3.4)
+      if (!Parameters.ContainsKey(DegreeParameterName))
+        Parameters.Add(new ValueParameter<IntValue>(DegreeParameterName, "The degree parameter for the polynomial kernel function.", new IntValue(3)));
+      #endregion
+    }
 
     public override IDeepCloneable Clone(Cloner cloner) {
@@ -118 +132 @@
       int nSv;
       var solution = CreateSupportVectorClassificationSolution(problemData, selectedInputVariables,
-        SvmType.Value, KernelType.Value, Cost.Value, Nu.Value, Gamma.Value,
+        SvmType.Value, KernelType.Value, Cost.Value, Nu.Value, Gamma.Value, Degree.Value,
         out trainingAccuracy, out testAccuracy, out nSv);
 
       Results.Add(new Result("Support vector classification solution", "The support vector classification solution.", solution));
       Results.Add(new Result("Training accuracy", "The accuracy of the SVR solution on the training partition.", new DoubleValue(trainingAccuracy)));
-      Results.Add(new Result("Test R²", "The accuracy of the SVR solution on the test partition.", new DoubleValue(testAccuracy)));
+      Results.Add(new Result("Test accuracy", "The accuracy of the SVR solution on the test partition.", new DoubleValue(testAccuracy)));
       Results.Add(new Result("Number of support vectors", "The number of support vectors of the SVR solution.", new IntValue(nSv)));
     }
 
     public static SupportVectorClassificationSolution CreateSupportVectorClassificationSolution(IClassificationProblemData problemData, IEnumerable<string> allowedInputVariables,
-      string svmType, string kernelType, double cost, double nu, double gamma,
+      string svmType, string kernelType, double cost, double nu, double gamma, int degree,
       out double trainingAccuracy, out double testAccuracy, out int nSv) {
       Dataset dataset = problemData.Dataset;
@@ -135 +149 @@
 
       //extract SVM parameters from scope and set them
-      SVM.Parameter parameter = new SVM.Parameter();
-      parameter.SvmType = (SVM.SvmType)Enum.Parse(typeof(SVM.SvmType), svmType, true);
-      parameter.KernelType = (SVM.KernelType)Enum.Parse(typeof(SVM.KernelType), kernelType, true);
+      svm_parameter parameter = new svm_parameter();
+      parameter.svm_type = GetSvmType(svmType);
+      parameter.kernel_type = GetKernelType(kernelType);
       parameter.C = cost;
-      parameter.Nu = nu;
-      parameter.Gamma = gamma;
-      parameter.CacheSize = 500;
-      parameter.Probability = false;
-
+      parameter.nu = nu;
+      parameter.gamma = gamma;
+      parameter.cache_size = 500;
+      parameter.probability = 0;
+      parameter.eps = 0.001;
+      parameter.degree = degree;
+      parameter.shrinking = 1;
+      parameter.coef0 = 0;
+
+
+      var weightLabels = new List<int>();
+      var weights = new List<double>();
       foreach (double c in problemData.ClassValues) {
         double wSum = 0.0;
@@ -151 +172 @@
           }
         }
-        parameter.Weights.Add((int)c, wSum);
+        weightLabels.Add((int)c);
+        weights.Add(wSum);
       }
-
-
-      SVM.Problem problem = SupportVectorMachineUtil.CreateSvmProblem(dataset, targetVariable, allowedInputVariables, rows);
-      SVM.RangeTransform rangeTransform = SVM.RangeTransform.Compute(problem);
-      SVM.Problem scaledProblem = SVM.Scaling.Scale(rangeTransform, problem);
-      var svmModel = SVM.Training.Train(scaledProblem, parameter);
+      parameter.weight_label = weightLabels.ToArray();
+      parameter.weight = weights.ToArray();
+
+
+      svm_problem problem = SupportVectorMachineUtil.CreateSvmProblem(dataset, targetVariable, allowedInputVariables, rows);
+      RangeTransform rangeTransform = RangeTransform.Compute(problem);
+      svm_problem scaledProblem = rangeTransform.Scale(problem);
+      var svmModel = svm.svm_train(scaledProblem, parameter);
       var model = new SupportVectorMachineModel(svmModel, rangeTransform, targetVariable, allowedInputVariables, problemData.ClassValues);
       var solution = new SupportVectorClassificationSolution(model, (IClassificationProblemData)problemData.Clone());
 
-      nSv = svmModel.SupportVectorCount;
+      nSv = svmModel.SV.Length;
       trainingAccuracy = solution.TrainingAccuracy;
       testAccuracy = solution.TestAccuracy;
 
       return solution;
+    }
+
+    private static int GetSvmType(string svmType) {
+      if (svmType == "NU_SVC") return svm_parameter.NU_SVC;
+      if (svmType == "C_SVC") return svm_parameter.C_SVC;
+      throw new ArgumentException("Unknown SVM type");
+    }
+
+    private static int GetKernelType(string kernelType) {
+      if (kernelType == "LINEAR") return svm_parameter.LINEAR;
+      if (kernelType == "POLY") return svm_parameter.POLY;
+      if (kernelType == "SIGMOID") return svm_parameter.SIGMOID;
+      if (kernelType == "RBF") return svm_parameter.RBF;
+      throw new ArgumentException("Unknown kernel type");
     }
     #endregion

@@ -21 +21 @@
 protoc.exe
 _ReSharper.HeuristicLab 3.3 Tests
+Google.ProtocolBuffers-2.4.1.473.dll

@@ -5 +5 @@
 *.vs10x
 Plugin.cs
+*.user