Changeset 5736 for branches/DataAnalysis Refactoring/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification.Views/3.4/InteractiveSymbolicDiscriminantFunctionClassificationSolutionSimplifierView.cs

Timestamp:

03/17/11 15:14:45 (13 years ago)

Author:

gkronber

Message:

#1418 implemented linear scaling for classification solutions, fixed bugs interactive simplifier view for classification solutions.

File:

• branches/DataAnalysis Refactoring/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification.Views/3.4/InteractiveSymbolicDiscriminantFunctionClassificationSolutionSimplifierView.cs (modified) (5 diffs)

branches/DataAnalysis Refactoring/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification.Views/3.4/InteractiveSymbolicDiscriminantFunctionClassificationSolutionSimplifierView.cs

@@ -48 +48 @@
       ISymbolicExpressionTreeNode root = new ProgramRootSymbol().CreateTreeNode();
       ISymbolicExpressionTreeNode start = new StartSymbol().CreateTreeNode();
-      root.AddSubTree(start);
+      root.AddSubtree(start);
       tempTree = new SymbolicExpressionTree(root);
     }
 
     protected override void UpdateModel(ISymbolicExpressionTree tree) {
-      var dataset = Content.ProblemData.Dataset;
-      var interpreter = Content.Model.Interpreter;
-      var rows = Content.ProblemData.TrainingIndizes;
-      string targetVariable = Content.ProblemData.TargetVariable;
-
-      var targetClassValues = dataset.GetEnumeratedVariableValues(targetVariable, rows);
-      var originalOutput = interpreter.GetSymbolicExpressionTreeValues(tree, dataset, rows)
-        .ToArray();
-      double[] classValues;
-      double[] thresholds;
-      NormalDistributionCutPointsThresholdCalculator.CalculateThresholds(Content.ProblemData, originalOutput, targetClassValues, out classValues, out thresholds);
-      Content.Model = new SymbolicDiscriminantFunctionClassificationModel(tree, Content.Model.Interpreter, classValues, thresholds);
+      Content.Model = new SymbolicDiscriminantFunctionClassificationModel(tree, Content.Model.Interpreter);
+      Content.SetClassDistibutionCutPointThresholds();
     }
 
@@ -83 +73 @@
       string targetVariable = Content.ProblemData.TargetVariable;
       Dictionary<ISymbolicExpressionTreeNode, double> impactValues = new Dictionary<ISymbolicExpressionTreeNode, double>();
-      List<ISymbolicExpressionTreeNode> nodes = tree.Root.GetSubTree(0).GetSubTree(0).IterateNodesPostfix().ToList();
+      List<ISymbolicExpressionTreeNode> nodes = tree.Root.GetSubtree(0).GetSubtree(0).IterateNodesPostfix().ToList();
 
       var targetClassValues = dataset.GetEnumeratedVariableValues(targetVariable, rows);
       var originalOutput = interpreter.GetSymbolicExpressionTreeValues(tree, dataset, rows)
+        .LimitToRange(Content.Model.LowerEstimationLimit, Content.Model.UpperEstimationLimit)
         .ToArray();
       double[] classValues;
       double[] thresholds;
       NormalDistributionCutPointsThresholdCalculator.CalculateThresholds(Content.ProblemData, originalOutput, targetClassValues, out classValues, out thresholds);
-      var classifier = new SymbolicDiscriminantFunctionClassificationModel(tree, interpreter, classValues, thresholds);
+      var classifier = new SymbolicDiscriminantFunctionClassificationModel(tree, interpreter);
+      classifier.SetThresholdsAndClassValues(thresholds, classValues);
       double originalAccuracy = OnlineAccuracyEvaluator.Calculate(targetClassValues, classifier.GetEstimatedClassValues(dataset, rows));
 
@@ -99 +91 @@
         ISymbolicExpressionTreeNode replacementNode = constantNode;
         SwitchNode(parent, node, replacementNode);
-        var newOutput = interpreter.GetSymbolicExpressionTreeValues(tree, dataset, rows);
+        var newOutput = interpreter.GetSymbolicExpressionTreeValues(tree, dataset, rows)
+          .LimitToRange(Content.Model.LowerEstimationLimit, Content.Model.UpperEstimationLimit)
+          .ToArray();
         NormalDistributionCutPointsThresholdCalculator.CalculateThresholds(Content.ProblemData, newOutput, targetClassValues, out classValues, out thresholds);
-        classifier = new SymbolicDiscriminantFunctionClassificationModel(tree, interpreter, classValues, thresholds);
+        classifier = new SymbolicDiscriminantFunctionClassificationModel(tree, interpreter);
+        classifier.SetThresholdsAndClassValues(thresholds, classValues);
         double newAccuracy = OnlineAccuracyEvaluator.Calculate(targetClassValues, classifier.GetEstimatedClassValues(dataset, rows));
 
@@ -114 +109 @@
 
     private double CalculateReplacementValue(ISymbolicExpressionTreeNode node) {
-      var start = tempTree.Root.GetSubTree(0);
-      while (start.SubTrees.Count() > 0) start.RemoveSubTree(0);
-      start.AddSubTree((ISymbolicExpressionTreeNode)node.Clone());
+      var start = tempTree.Root.GetSubtree(0);
+      while (start.SubtreesCount > 0) start.RemoveSubtree(0);
+      start.AddSubtree((ISymbolicExpressionTreeNode)node.Clone());
       var interpreter = Content.Model.Interpreter;
       var rows = Content.ProblemData.TrainingIndizes;
@@ -124 +119 @@
 
     private void SwitchNode(ISymbolicExpressionTreeNode root, ISymbolicExpressionTreeNode oldBranch, ISymbolicExpressionTreeNode newBranch) {
-      for (int i = 0; i < root.SubTrees.Count(); i++) {
-        if (root.GetSubTree(i) == oldBranch) {
-          root.RemoveSubTree(i);
-          root.InsertSubTree(i, newBranch);
+      for (int i = 0; i < root.SubtreesCount; i++) {
+        if (root.GetSubtree(i) == oldBranch) {
+          root.RemoveSubtree(i);
+          root.InsertSubtree(i, newBranch);
           return;
         }