Changeset 2165 for trunk/sources/HeuristicLab.SupportVectorMachines

Timestamp:

07/16/09 11:34:22 (15 years ago)

Author:

gkronber

Message:

Removed variable AllowedFeatures in all modeling algorithms. #709

Location:

trunk/sources/HeuristicLab.SupportVectorMachines/3.2

Files:

• SVMHelper.cs (modified) (3 diffs)
• SupportVectorCreator.cs (modified) (3 diffs)
• SupportVectorEvaluator.cs (modified) (3 diffs)
• VariableEvaluationImpactCalculator.cs (modified) (1 diff)
• VariableQualityImpactCalculator.cs (modified) (1 diff)

trunk/sources/HeuristicLab.SupportVectorMachines/3.2/SVMHelper.cs

@@ -9 +9 @@
 namespace HeuristicLab.SupportVectorMachines {
   public class SVMHelper {
-    public static SVM.Problem CreateSVMProblem(Dataset dataset, ItemList<IntData> allowedFeatures, int targetVariable, int start, int end) {
+    public static SVM.Problem CreateSVMProblem(Dataset dataset, int targetVariable, int start, int end) {
       int rowCount = end - start;
-      double[] samples = dataset.Samples;
+      List<int> skippedFeatures = new List<int>();
+      for (int i = 0; i < dataset.Columns; i++) {
+        if (i != targetVariable) {
+          if (dataset.GetRange(i, start, end) == 0)
+            skippedFeatures.Add(i);
+        }
+      }
 
-      List<int> skippedFeatures = new List<int>();
-      for (int i = 0; i < allowedFeatures.Count; i++) {
-        if (dataset.GetRange(allowedFeatures[i].Data, start, end) == 0)
-          skippedFeatures.Add(i);
-      }
+      int maxColumns = dataset.Columns - skippedFeatures.Count();
 
       double[] targetVector = new double[rowCount];
       for (int i = 0; i < rowCount; i++) {
-        double value = samples[(start + i) * dataset.Columns + targetVariable];
+        double value = dataset.GetValue(start + i, targetVariable);
           targetVector[i] = value;
       }
@@ -31 +33 @@
       for (int row = 0; row < rowCount; row++) {
         tempRow = new List<SVM.Node>();
-        for (int col = 0; col < allowedFeatures.Count; col++) {
-          if (!skippedFeatures.Contains(col)) {
-            double value = samples[(start + row) * dataset.Columns + allowedFeatures[col].Data];
+        for (int col = 0; col < dataset.Columns; col++) {
+          if (!skippedFeatures.Contains(col) && col!=targetVariable) {
+            double value = dataset.GetValue(start + row, col);
             if (!double.IsNaN(value))
-              tempRow.Add(new SVM.Node(allowedFeatures[col].Data, value));
+              tempRow.Add(new SVM.Node(col, value));
           }
         }
-        if (!double.IsNaN(samples[(start + row) * dataset.Columns + targetVariable])) {
+        if (!double.IsNaN(dataset.GetValue(start + row, targetVariable))) {
           nodes[addedRows] = tempRow.ToArray();
           addedRows++;
@@ -44 +46 @@
       }
 
-      return new SVM.Problem(targetVector.Length, targetVector, nodes, allowedFeatures.Max(x => x.Data));
+      return new SVM.Problem(targetVector.Length, targetVector, nodes, maxColumns);
     }
   }

trunk/sources/HeuristicLab.SupportVectorMachines/3.2/SupportVectorCreator.cs

@@ -39 +39 @@
       //Dataset infos
       AddVariableInfo(new VariableInfo("Dataset", "Dataset with all samples on which to apply the function", typeof(Dataset), VariableKind.In));
-      AddVariableInfo(new VariableInfo("AllowedFeatures", "List of indexes of allowed features", typeof(ItemList<IntData>), VariableKind.In));
       AddVariableInfo(new VariableInfo("TargetVariable", "Index of the column of the dataset that holds the target variable", typeof(IntData), VariableKind.In));
       AddVariableInfo(new VariableInfo("SamplesStart", "Start index of samples in dataset to evaluate", typeof(IntData), VariableKind.In));
@@ -67 +66 @@
       abortRequested = false;
       Dataset dataset = GetVariableValue<Dataset>("Dataset", scope, true);
-      ItemList<IntData> allowedFeatures = GetVariableValue<ItemList<IntData>>("AllowedFeatures", scope, true);
       int targetVariable = GetVariableValue<IntData>("TargetVariable", scope, true).Data;
       int start = GetVariableValue<IntData>("SamplesStart", scope, true).Data;
@@ -83 +81 @@
       parameter.Gamma = GetVariableValue<DoubleData>("SVMGamma", scope, true).Data;
 
-      SVM.Problem problem = SVMHelper.CreateSVMProblem(dataset, allowedFeatures, targetVariable, start, end);
+      SVM.Problem problem = SVMHelper.CreateSVMProblem(dataset, targetVariable, start, end);
       SVM.RangeTransform rangeTransform = SVM.Scaling.DetermineRange(problem);
       SVM.Problem scaledProblem = SVM.Scaling.Scale(problem, rangeTransform);

trunk/sources/HeuristicLab.SupportVectorMachines/3.2/SupportVectorEvaluator.cs

@@ -35 +35 @@
       //Dataset infos
       AddVariableInfo(new VariableInfo("Dataset", "Dataset with all samples on which to apply the function", typeof(Dataset), VariableKind.In));
-      AddVariableInfo(new VariableInfo("AllowedFeatures", "List of indexes of allowed features", typeof(ItemList<IntData>), VariableKind.In));
       AddVariableInfo(new VariableInfo("TargetVariable", "Index of the column of the dataset that holds the target variable", typeof(IntData), VariableKind.In));
       AddVariableInfo(new VariableInfo("SamplesStart", "Start index of samples in dataset to evaluate", typeof(IntData), VariableKind.In));
@@ -47 +46 @@
     public override IOperation Apply(IScope scope) {
       Dataset dataset = GetVariableValue<Dataset>("Dataset", scope, true);
-      ItemList<IntData> allowedFeatures = GetVariableValue<ItemList<IntData>>("AllowedFeatures", scope, true);
       int targetVariable = GetVariableValue<IntData>("TargetVariable", scope, true).Data;
       int start = GetVariableValue<IntData>("SamplesStart", scope, true).Data;
@@ -53 +51 @@
 
       SVMModel modelData = GetVariableValue<SVMModel>("SVMModel", scope, true);
-      SVM.Problem problem = SVMHelper.CreateSVMProblem(dataset, allowedFeatures, targetVariable, start, end);
+      SVM.Problem problem = SVMHelper.CreateSVMProblem(dataset, targetVariable, start, end);
       SVM.Problem scaledProblem = SVM.Scaling.Scale(problem, modelData.RangeTransform);
 

trunk/sources/HeuristicLab.SupportVectorMachines/3.2/VariableEvaluationImpactCalculator.cs

@@ -38 +38 @@
 
 
-    protected override double[] GetOutputs(IScope scope, Dataset dataset, int targetVariable, ItemList<IntData> allowedFeatures, int start, int end) {
+    protected override double[] GetOutputs(IScope scope, Dataset dataset, int targetVariable, int start, int end) {
       SVMModel model = GetVariableValue<SVMModel>("SVMModel", scope, true);
-      SVM.Problem problem = SVMHelper.CreateSVMProblem(dataset, allowedFeatures, targetVariable, start, end);
+      SVM.Problem problem = SVMHelper.CreateSVMProblem(dataset, targetVariable, start, end);
       SVM.Problem scaledProblem = SVM.Scaling.Scale(problem, model.RangeTransform);
 

trunk/sources/HeuristicLab.SupportVectorMachines/3.2/VariableQualityImpactCalculator.cs

@@ -37 +37 @@
     }
 
-    protected override double CalculateQuality(IScope scope, Dataset dataset, int targetVariable, ItemList<IntData> allowedFeatures, int start, int end) {
+    protected override double CalculateQuality(IScope scope, Dataset dataset, int targetVariable, int start, int end) {
       SVMModel model = GetVariableValue<SVMModel>("SVMModel", scope, true);
-      SVM.Problem problem = SVMHelper.CreateSVMProblem(dataset, allowedFeatures, targetVariable, start, end);
+      SVM.Problem problem = SVMHelper.CreateSVMProblem(dataset, targetVariable, start, end);
       SVM.Problem scaledProblem = SVM.Scaling.Scale(problem, model.RangeTransform);