Changeset 8297 for branches/ClassificationEnsembleVoting/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/WeightCalculators/ClassificationWeightCalculator.cs

Timestamp:

07/17/12 15:30:04 (12 years ago)

Author:

sforsten

Message:

#1776:

• Corrected namespace of IClassificationEnsembleSolutionWeightCalculator interface
• Corrected calculation of confidence for test and training samples in ClassificationEnsembleSolutionEstimatedClassValuesView
• Added overload method GetConfidence to IClassificationEnsembleSolutionWeightCalculator to calculate more than one point at a time (maybe additional methods for training and test confidence could improve the performance remarkably)
• Added ClassificationEnsembleSolutionConfidenceAccuracyDependence to see how accuracy would behave, if only samples with high confidence would be classified

File:

• branches/ClassificationEnsembleVoting/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/WeightCalculators/ClassificationWeightCalculator.cs (modified) (2 diffs)

branches/ClassificationEnsembleVoting/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/WeightCalculators/ClassificationWeightCalculator.cs

@@ -26 +26 @@
 using HeuristicLab.Data;
 using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
-using HeuristicLab.Problems.DataAnalysis.Interfaces.Classification;
+using HeuristicLab.Problems.DataAnalysis.Interfaces;
 
 namespace HeuristicLab.Problems.DataAnalysis {
@@ -124 +124 @@
     }
 
+    public virtual IEnumerable<double> GetConfidence(IEnumerable<IClassificationSolution> solutions, IEnumerable<int> indices, IEnumerable<double> estimatedClassValue) {
+      if (solutions.Count() < 1)
+        return Enumerable.Repeat(double.NaN, indices.Count());
+
+      Dataset dataset = solutions.First().ProblemData.Dataset;
+      Dictionary<IClassificationSolution, double[]> solValues = solutions.ToDictionary(x => x, x => x.Model.GetEstimatedClassValues(dataset, indices).ToArray());
+      double[] estimatedClassValueArr = estimatedClassValue.ToArray();
+      double[] confidences = new double[indices.Count()];
+
+      for (int i = 0; i < indices.Count(); i++) {
+        var correctSolutions = solValues.Where(x => DoubleExtensions.IsAlmost(x.Value[i], estimatedClassValueArr[i]));
+        confidences[i] = (from sol in correctSolutions
+                          select weights[sol.Key]).Sum();
+      }
+
+      return confidences;
+    }
+
     #region Helper
     protected IEnumerable<double> GetValues(IList<double> targetValues, IEnumerable<int> indizes) {