Changeset 396 for trunk/sources/HeuristicLab.StructureIdentification

Timestamp:

07/28/08 18:46:02 (17 years ago)

Author:

gkronber

Message:

fixed ticket #205 by creating the function-specific evaluator in the evaluation operators.

Location:

trunk/sources/HeuristicLab.StructureIdentification/Evaluation

Files:

• CoefficientOfDeterminationEvaluator.cs (modified) (1 diff)
• EarlyStoppingMeanSquaredErrorEvaluator.cs (modified) (1 diff)
• GPEvaluatorBase.cs (modified) (2 diffs)
• MCCEvaluator.cs (modified) (1 diff)
• MeanAbsolutePercentageErrorEvaluator.cs (modified) (1 diff)
• MeanSquaredErrorEvaluator.cs (modified) (1 diff)
• SimpleEvaluator.cs (modified) (2 diffs)
• TheilInequalityCoefficientEvaluator.cs (modified) (1 diff)
• VarianceAccountedForEvaluator.cs (modified) (1 diff)

trunk/sources/HeuristicLab.StructureIdentification/Evaluation/CoefficientOfDeterminationEvaluator.cs ¶

@@ -49 +49 @@
       double originalDeviationTotalSumOfSquares = 0.0;
       double targetMean = dataset.GetMean(targetVariable, trainingStart, trainingEnd);
-      functionTree.PrepareEvaluation(dataset);
       for(int sample = trainingStart; sample < trainingEnd; sample++) {
-        double estimated = functionTree.Evaluate(sample);
+        double estimated = evaluator.Evaluate(sample);
         double original = dataset.GetValue(sample, targetVariable);
         if(!double.IsNaN(original) && !double.IsInfinity(original)) {

trunk/sources/HeuristicLab.StructureIdentification/Evaluation/EarlyStoppingMeanSquaredErrorEvaluator.cs ¶

@@ -60 +60 @@
       double errorsSquaredSum = 0;
       double targetMean = dataset.GetMean(targetVariable, trainingStart, trainingEnd);
-      functionTree.PrepareEvaluation(dataset);
       for(int sample = trainingStart; sample < trainingEnd; sample++) {
-        double estimated = functionTree.Evaluate(sample);
+        double estimated = evaluator.Evaluate(sample);
         double original = dataset.GetValue(sample, targetVariable);
         if(double.IsNaN(estimated) || double.IsInfinity(estimated)) {

trunk/sources/HeuristicLab.StructureIdentification/Evaluation/GPEvaluatorBase.cs ¶

@@ -35 +35 @@
     protected int treeSize;
     protected double totalEvaluatedNodes;
+    protected IEvaluator evaluator;
 
     public GPEvaluatorBase()
@@ -56 +57 @@
       this.treeSize = scope.GetVariableValue<IntData>("TreeSize", false).Data;
       this.totalEvaluatedNodes = scope.GetVariableValue<DoubleData>("TotalEvaluatedNodes", true).Data;
+      if(evaluator == null) evaluator = functionTree.CreateEvaluator(dataset);
+      evaluator.ResetEvaluator(functionTree);
       double result = Evaluate(scope, functionTree, targetVariable, dataset);
 

trunk/sources/HeuristicLab.StructureIdentification/Evaluation/MCCEvaluator.cs ¶

@@ -58 +58 @@
       double negative = 0;
       double targetMean = dataset.GetMean(targetVariable, trainingStart, trainingEnd);
-      functionTree.PrepareEvaluation(dataset);
       for(int sample = trainingStart; sample < trainingEnd; sample++) {
-        double est = functionTree.Evaluate(sample);
+        double est = evaluator.Evaluate(sample);
         double orig = dataset.GetValue(sample, targetVariable);
         if(double.IsNaN(est) || double.IsInfinity(est)) {

trunk/sources/HeuristicLab.StructureIdentification/Evaluation/MeanAbsolutePercentageErrorEvaluator.cs ¶

@@ -47 +47 @@
       int trainingEnd = GetVariableValue<IntData>("TrainingSamplesEnd", scope, true).Data;
       double errorsSum = 0.0;
-      functionTree.PrepareEvaluation(dataset);
       for(int sample = trainingStart; sample < trainingEnd; sample++) {
-        double estimated = functionTree.Evaluate(sample);
+        double estimated = evaluator.Evaluate(sample);
         double original = dataset.GetValue(sample, targetVariable);
         if(!double.IsNaN(original) && !double.IsInfinity(original)) {

trunk/sources/HeuristicLab.StructureIdentification/Evaluation/MeanSquaredErrorEvaluator.cs ¶

@@ -59 +59 @@
         }
       }
-
-      functionTree.PrepareEvaluation(dataset);
       for(int sample = trainingStart; sample < trainingEnd; sample++) {
-        double estimated = functionTree.Evaluate(sample);
+        double estimated = evaluator.Evaluate(sample);
         double original = dataset.GetValue(sample, targetVariable);
         if(double.IsNaN(estimated) || double.IsInfinity(estimated)) {

trunk/sources/HeuristicLab.StructureIdentification/Evaluation/SimpleEvaluator.cs ¶

@@ -34 +34 @@
     protected int treeSize;
     protected double totalEvaluatedNodes;
+    private IEvaluator evaluator;
 
     public SimpleEvaluator()
@@ -66 +67 @@
       }
       values.Clear();
-      functionTree.PrepareEvaluation(dataset);
+      if(evaluator == null) evaluator = functionTree.CreateEvaluator(dataset);
+      evaluator.ResetEvaluator(functionTree);
       for(int sample = trainingStart; sample < trainingEnd; sample++) {
         ItemList row = new ItemList();
-        row.Add(new DoubleData(functionTree.Evaluate(sample)));
+        row.Add(new DoubleData(evaluator.Evaluate(sample)));
         row.Add(new DoubleData(dataset.GetValue(sample, targetVariable)));
         values.Add(row);

trunk/sources/HeuristicLab.StructureIdentification/Evaluation/TheilInequalityCoefficientEvaluator.cs ¶

@@ -51 +51 @@
       double estimatedSquaredSum = 0.0;
       double originalSquaredSum = 0.0;
-      functionTree.PrepareEvaluation(dataset);
       for(int sample = trainingStart; sample < trainingEnd; sample++) {
         double prevValue = 0.0;
         if(difference) prevValue = dataset.GetValue(sample - 1, targetVariable);
-        double estimatedChange = functionTree.Evaluate(sample) - prevValue;
+        double estimatedChange = evaluator.Evaluate(sample) - prevValue;
         double originalChange = dataset.GetValue(sample, targetVariable) - prevValue;
         if(!double.IsNaN(originalChange) && !double.IsInfinity(originalChange)) {

trunk/sources/HeuristicLab.StructureIdentification/Evaluation/VarianceAccountedForEvaluator.cs ¶

@@ -59 +59 @@
       double[] originalTargetVariableValues = new double[trainingEnd-trainingStart];
       double targetMean = dataset.GetMean(targetVariable, trainingStart, trainingEnd);
-      functionTree.PrepareEvaluation(dataset);
       for(int sample = trainingStart; sample < trainingEnd; sample++) {
-        double estimated = functionTree.Evaluate(sample);
+        double estimated = evaluator.Evaluate(sample);
         double original = dataset.GetValue(sample, targetVariable);
         if(!double.IsNaN(original) && !double.IsInfinity(original)) {