Changeset 13103

Timestamp:

11/03/15 07:12:27 (9 years ago)

Author:

gkronber

Message:

#1998: code simplification of ConfusionMatrixCalculator

Location:

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/OnlineCalculators

Files:

• ConfusionMatrixCalculator.cs (modified) (2 diffs)
• FOneScoreCalculator.cs (modified) (1 diff)

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/OnlineCalculators/ConfusionMatrixCalculator.cs

@@ -27 +27 @@
   public class ConfusionMatrixCalculator {
     public static double[,] Calculate(IEnumerable<double> originalValues, IEnumerable<double> estimatedValues, out OnlineCalculatorError errorState) {
-      if (originalValues.Count() != estimatedValues.Count()) {
-        throw new ArgumentException("Number of elements in originalValues and estimatedValues enumerations doesn't match.");
-      }
-
-      var  classValues = originalValues.Distinct().ToList();
-      var estimatedClassValues = estimatedValues.Distinct().ToList();
-
-      if (!estimatedClassValues.All(x => classValues.Contains(x))) {
-        errorState = OnlineCalculatorError.InvalidValueAdded;
-        return null;
-      }
-
-      int classes = classValues.Count;
-      double[,] confusionMatrix = new double[classes, classes];
 
       Dictionary<double, int> classValueIndexMapping = new Dictionary<double, int>();
       int index = 0;
-      foreach (double classValue in classValues.OrderBy(x => x)) {
-        classValueIndexMapping.Add(classValue, index);
-        index++;
+      foreach (double classValue in originalValues.OrderBy(x => x)) {
+        if (!classValueIndexMapping.ContainsKey(classValue)) {
+          classValueIndexMapping.Add(classValue, index);
+          index++;
+        }
       }
+
+      int classes = classValueIndexMapping.Count;
+      double[,] confusionMatrix = new double[classes, classes];
+
 
       IEnumerator<double> originalEnumerator = originalValues.GetEnumerator();
@@ -66 +58 @@
       }
 
+      if (originalEnumerator.MoveNext() || estimatedEnumerator.MoveNext()) {
+        throw new ArgumentException("Number of elements in originalValues and estimatedValues enumerations doesn't match.");
+
+      }
+
       errorState = OnlineCalculatorError.None;
       return confusionMatrix;

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/OnlineCalculators/FOneScoreCalculator.cs

@@ -28 +28 @@
     public static double Calculate(IEnumerable<double> originalValues, IEnumerable<double> estimatedValues, out OnlineCalculatorError errorState) {
       if (originalValues.Distinct().Skip(2).Any()) {
+        // TODO: we could use ClassificationPerformanceMeasuresCalculator instead of the ConfusionMatrixCalculator below to handle multi-class problems
         throw new ArgumentException("F1 score can only be calculated for binary classification.");
       }