Changeset 5649 for branches/DataAnalysis Refactoring/HeuristicLab.Problems.DataAnalysis/3.4/ClassificationSolution.cs

Timestamp:

03/10/11 10:00:09 (13 years ago)

Author:

gkronber

Message:

#1418 Implemented classes for classification based on a discriminant function and thresholds and implemented interfaces and base classes for clustering.

File:

• branches/DataAnalysis Refactoring/HeuristicLab.Problems.DataAnalysis/3.4/ClassificationSolution.cs (modified) (6 diffs)

branches/DataAnalysis Refactoring/HeuristicLab.Problems.DataAnalysis/3.4/ClassificationSolution.cs

@@ -37 +37 @@
   [StorableClass]
   public abstract class ClassificationSolution : DataAnalysisSolution, IClassificationSolution {
-    private const string ThresholdsResultsName = "Thresholds";
+    private const string TrainingAccuracyResultName = "Accuracy (training)";
+    private const string TestAccuracyResultName = "Accuracy (test)";
     [StorableConstructor]
     protected ClassificationSolution(bool deserializing) : base(deserializing) { }
@@ -45 +46 @@
     public ClassificationSolution(IClassificationModel model, IClassificationProblemData problemData)
       : base(model, problemData) {
-      DoubleArray thresholds = new DoubleArray();
-      Add(new Result(ThresholdsResultsName, "The threshold values for class boundaries.", thresholds));
-      thresholds.Reset += new EventHandler(thresholds_Reset);
-      thresholds.ItemChanged += new EventHandler<EventArgs<int>>(thresholds_ItemChanged);
+      double[] estimatedTrainingClassValues = EstimatedTrainingClassValues.ToArray(); // cache values
+      IEnumerable<double> originalTrainingClassValues = ProblemData.Dataset.GetEnumeratedVariableValues(ProblemData.TargetVariable, ProblemData.TrainingIndizes);
+      double[] estimatedTestClassValues = EstimatedTestClassValues.ToArray(); // cache values
+      IEnumerable<double> originalTestClassValues = ProblemData.Dataset.GetEnumeratedVariableValues(ProblemData.TargetVariable, ProblemData.TestIndizes);
+
+      double trainingAccuracy = OnlineAccuracyEvaluator.Calculate(estimatedTrainingClassValues, originalTrainingClassValues);
+      double testAccuracy = OnlineAccuracyEvaluator.Calculate(estimatedTestClassValues, originalTestClassValues);
+
+      Add(new Result(TrainingAccuracyResultName, "Accuracy of the model on the training partition (percentage of correctly classified instances).", new PercentValue(trainingAccuracy)));
+      Add(new Result(TestAccuracyResultName, "Accuracy of the model on the test partition (percentage of correctly classified instances).", new PercentValue(testAccuracy)));
     }
 
@@ -61 +68 @@
     }
 
-    public virtual IEnumerable<double> EstimatedValues {
-      get {
-        return GetEstimatedValues(Enumerable.Range(0, ProblemData.Dataset.Rows));
-      }
-    }
-
-    public virtual IEnumerable<double> EstimatedTrainingValues {
-      get {
-        return GetEstimatedValues(ProblemData.TrainingIndizes);
-      }
-    }
-
-    public virtual IEnumerable<double> EstimatedTestValues {
-      get {
-        return GetEstimatedValues(ProblemData.TestIndizes);
-      }
-    }
-
-    public virtual IEnumerable<double> GetEstimatedValues(IEnumerable<int> rows) {
-      return Model.GetEstimatedValues(ProblemData, rows);
-    }
-
-    public IEnumerable<double> Thresholds {
-      get {
-        return (DoubleArray)this[ThresholdsResultsName].Value;
-      }
-    }
-
-    public IEnumerable<double> EstimatedClassValues {
+    public virtual IEnumerable<double> EstimatedClassValues {
       get {
         return GetEstimatedClassValues(Enumerable.Range(0, ProblemData.Dataset.Rows));
@@ -95 +74 @@
     }
 
-    public IEnumerable<double> EstimatedTrainingClassValues {
+    public virtual IEnumerable<double> EstimatedTrainingClassValues {
       get {
         return GetEstimatedClassValues(ProblemData.TrainingIndizes);
@@ -101 +80 @@
     }
 
-    public IEnumerable<double> EstimatedTestClassValues {
+    public virtual IEnumerable<double> EstimatedTestClassValues {
       get {
         return GetEstimatedClassValues(ProblemData.TestIndizes);
@@ -107 +86 @@
     }
 
-    public IEnumerable<double> GetEstimatedClassValues(IEnumerable<int> rows) {
-      return Model.GetEstimatedClassValues(ProblemData, rows);
-    }
-
-    #endregion
-    #region events
-    private void thresholds_ItemChanged(object sender, EventArgs<int> e) {
-      OnThresholdsChanged(EventArgs.Empty);
-    }
-
-    private void thresholds_Reset(object sender, EventArgs e) {
-      OnThresholdsChanged(EventArgs.Empty);
-    }
-
-    public event EventHandler ThresholdsChanged;
-    private void OnThresholdsChanged(EventArgs e) {
-      var listeners = ThresholdsChanged;
-      if (listeners != null) listeners(this, e);
+    public virtual IEnumerable<double> GetEstimatedClassValues(IEnumerable<int> rows) {
+      return Model.GetEstimatedClassValues(ProblemData.Dataset, rows);
     }
     #endregion