Changeset 8636 for trunk/sources/HeuristicLab.Problems.DataAnalysis

Timestamp:

09/12/12 16:20:18 (12 years ago)

Author:

mkommend

Message:

#1924:

• Changed the accuracy threshold calculator to eliminate the necessity the the class values are ordered.
• Adapted the symbolic classification simplifier to work with all ISymbolicClassificationModels.
• Corrected ROCCurvesView to also work if the class values are not sorted.

File:

• trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ThresholdCalculators/AccuracyMaximizationThresholdCalculator.cs (modified) (2 diffs)

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ThresholdCalculators/AccuracyMaximizationThresholdCalculator.cs

@@ -53 +53 @@
 
     public static void CalculateThresholds(IClassificationProblemData problemData, IEnumerable<double> estimatedValues, IEnumerable<double> targetClassValues, out double[] classValues, out double[] thresholds) {
-      int slices = 100;
-      double minThresholdInc = 10e-5; // necessary to prevent infinite loop when maxEstimated - minEstimated is effectively zero (constant model)
+      const int slices = 100;
+      const double minThresholdInc = 10e-5; // necessary to prevent infinite loop when maxEstimated - minEstimated is effectively zero (constant model)
       List<double> estimatedValuesList = estimatedValues.ToList();
       double maxEstimatedValue = estimatedValuesList.Max();
@@ -61 +61 @@
       var estimatedAndTargetValuePairs =
         estimatedValuesList.Zip(targetClassValues, (x, y) => new { EstimatedValue = x, TargetClassValue = y })
-        .OrderBy(x => x.EstimatedValue)
-        .ToList();
+        .OrderBy(x => x.EstimatedValue).ToList();
 
-      classValues = problemData.ClassValues.OrderBy(x => x).ToArray();
+      classValues = estimatedAndTargetValuePairs.GroupBy(x => x.TargetClassValue)
+        .Select(x => new { Median = x.Select(y => y.EstimatedValue).Median(), Class = x.Key })
+        .OrderBy(x => x.Median).Select(x => x.Class).ToArray();
+
       int nClasses = classValues.Length;
       thresholds = new double[nClasses];
       thresholds[0] = double.NegativeInfinity;
-      // thresholds[thresholds.Length - 1] = double.PositiveInfinity;
 
       // incrementally calculate accuracy of all possible thresholds