Changeset 11763 for trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification

Timestamp:

01/15/15 11:37:49 (10 years ago)

Author:

mkommend

Message:

#2278: Merged changes in HL.Problems.DataAnalysis into the trunk.

Location:

trunk/sources/HeuristicLab.Problems.DataAnalysis

Files:

• . (modified) (1 prop)
• 3.4/Implementation/Classification/ClassificationPerformanceMeasures.cs (copied) (copied from branches/Classification-Extensions/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationPerformanceMeasures.cs)
• 3.4/Implementation/Classification/ClassificationProblemData.cs (modified) (9 diffs)
• 3.4/Implementation/Classification/ClassificationSolutionBase.cs (modified) (6 diffs)

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationProblemData.cs

@@ -36 +36 @@
     protected const string ClassNamesParameterName = "ClassNames";
     protected const string ClassificationPenaltiesParameterName = "ClassificationPenalties";
+    protected const string PositiveClassNameParameterName = "PositiveClass";
     protected const int MaximumNumberOfClasses = 100;
     protected const int InspectedRowsToDetermineTargets = 2000;
@@ -213 +214 @@
       get { return (IFixedValueParameter<StringMatrix>)Parameters[ClassNamesParameterName]; }
     }
+    public IConstrainedValueParameter<StringValue> PositiveClassNameParameter {
+      get { return (IConstrainedValueParameter<StringValue>)Parameters[PositiveClassNameParameterName]; }
+    }
     public IFixedValueParameter<DoubleMatrix> ClassificationPenaltiesParameter {
       get { return (IFixedValueParameter<DoubleMatrix>)Parameters[ClassificationPenaltiesParameterName]; }
@@ -262 +266 @@
       get { return ClassNamesCache; }
     }
+
+    public string PositiveClassName {
+      get { return PositiveClassNameParameter.Value.Value; }
+      set {
+        var matchingValue = PositiveClassNameParameter.ValidValues.SingleOrDefault(x => x.Value == value);
+        if (matchingValue == null) throw new ArgumentException(string.Format("{0} cannot be set as positive class.", value));
+        PositiveClassNameParameter.Value = matchingValue;
+      }
+    }
     #endregion
 
@@ -270 +283 @@
     private void AfterDeserialization() {
       RegisterParameterEvents();
+      // BackwardsCompatibility3.4
+      #region Backwards compatible code, remove with 3.5
+      if (!Parameters.ContainsKey(PositiveClassNameParameterName)) {
+        var validValues = new ItemSet<StringValue>(ClassNames.Select(s => new StringValue(s).AsReadOnly()));
+        Parameters.Add(new ConstrainedValueParameter<StringValue>(PositiveClassNameParameterName,
+          "The positive class which is used for quality measure calculation (e.g., specifity, sensitivity,...)", validValues, validValues.First()));
+      }
+      #endregion
+
     }
 
@@ -307 +329 @@
       Parameters.Add(new ConstrainedValueParameter<StringValue>(TargetVariableParameterName, new ItemSet<StringValue>(validTargetVariableValues), target));
       Parameters.Add(new FixedValueParameter<StringMatrix>(ClassNamesParameterName, ""));
+      Parameters.Add(new ConstrainedValueParameter<StringValue>(PositiveClassNameParameterName, "The positive class which is used for quality measure calculation (e.g., specifity, sensitivity,...)"));
       Parameters.Add(new FixedValueParameter<DoubleMatrix>(ClassificationPenaltiesParameterName, ""));
 
@@ -340 +363 @@
       ClassNamesParameter.Value.RowNames = ClassValues.Select(s => "ClassValue: " + s);
 
+      PositiveClassNameParameter.ValidValues.Clear();
+      foreach (var className in ClassNames) {
+        PositiveClassNameParameter.ValidValues.Add(new StringValue(className).AsReadOnly());
+      }
+
       ((IStringConvertibleMatrix)ClassificationPenaltiesParameter.Value).Rows = Classes;
       ((IStringConvertibleMatrix)ClassificationPenaltiesParameter.Value).Columns = Classes;
@@ -411 +439 @@
     }
     private void Parameter_ValueChanged(object sender, EventArgs e) {
+      var oldPositiveClass = PositiveClassName;
+      var oldClassNames = classNamesCache;
+      var index = oldClassNames.IndexOf(oldPositiveClass);
+
       classNamesCache = null;
       ClassificationPenaltiesParameter.Value.RowNames = ClassNames.Select(name => "Actual " + name);
       ClassificationPenaltiesParameter.Value.ColumnNames = ClassNames.Select(name => "Estimated " + name);
+
+      PositiveClassNameParameter.ValidValues.Clear();
+      foreach (var className in ClassNames) {
+        PositiveClassNameParameter.ValidValues.Add(new StringValue(className).AsReadOnly());
+      }
+      PositiveClassNameParameter.Value = PositiveClassNameParameter.ValidValues.ElementAt(index);
+
       OnChanged();
     }
@@ -435 +474 @@
       if (!newClassValues.SequenceEqual(ClassValues)) {
         errorMessage = errorMessage + string.Format("The class values differ in the provided classification problem data.");
-        return false;
+        returnValue = false;
+      }
+
+      var newPositivieClassName = classificationProblemData.PositiveClassName;
+      if (newPositivieClassName != PositiveClassName) {
+        errorMessage = errorMessage + string.Format("The positive class differs in the provided classification problem data.");
+        returnValue = false;
       }
 
@@ -452 +497 @@
         ClassNamesParameter.Value[i, 0] = classificationProblemData.ClassNames.ElementAt(i);
 
+      PositiveClassName = classificationProblemData.PositiveClassName;
+
       for (int i = 0; i < Classes; i++) {
         for (int j = 0; j < Classes; j++) {

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationSolutionBase.cs

@@ -34 +34 @@
     private const string TrainingNormalizedGiniCoefficientResultName = "Normalized Gini Coefficient (training)";
     private const string TestNormalizedGiniCoefficientResultName = "Normalized Gini Coefficient (test)";
+    private const string ClassificationPerformanceMeasuresResultName = "Classification Performance Measures";
 
     public new IClassificationModel Model {
@@ -62 +63 @@
       protected set { ((DoubleValue)this[TestNormalizedGiniCoefficientResultName].Value).Value = value; }
     }
+    public ClassificationPerformanceMeasuresResultCollection ClassificationPerformanceMeasures {
+      get { return ((ClassificationPerformanceMeasuresResultCollection)this[ClassificationPerformanceMeasuresResultName].Value); }
+      protected set { (this[ClassificationPerformanceMeasuresResultName].Value) = value; }
+    }
     #endregion
 
@@ -75 +80 @@
       Add(new Result(TrainingNormalizedGiniCoefficientResultName, "Normalized Gini coefficient of the model on the training partition.", new DoubleValue()));
       Add(new Result(TestNormalizedGiniCoefficientResultName, "Normalized Gini coefficient of the model on the test partition.", new DoubleValue()));
+      Add(new Result(ClassificationPerformanceMeasuresResultName, @"Classification performance measures.\n
+                              In a multiclass classification all misclassifications of the negative class will be treated as true negatives except on positive class estimations.",
+                            new ClassificationPerformanceMeasuresResultCollection()));
     }
 
@@ -83 +91 @@
       if (!this.ContainsKey(TestNormalizedGiniCoefficientResultName))
         Add(new Result(TestNormalizedGiniCoefficientResultName, "Normalized Gini coefficient of the model on the test partition.", new DoubleValue()));
+      if (!this.ContainsKey(ClassificationPerformanceMeasuresResultName)) {
+        Add(new Result(ClassificationPerformanceMeasuresResultName, @"Classification performance measures.\n
+                              In a multiclass classification all misclassifications of the negative class will be treated as true negatives except on positive class estimations.",
+                              new ClassificationPerformanceMeasuresResultCollection()));
+        RecalculateResults();
+      }
     }
 
@@ -88 +102 @@
       double[] estimatedTrainingClassValues = EstimatedTrainingClassValues.ToArray(); // cache values
       double[] originalTrainingClassValues = ProblemData.Dataset.GetDoubleValues(ProblemData.TargetVariable, ProblemData.TrainingIndices).ToArray();
+
       double[] estimatedTestClassValues = EstimatedTestClassValues.ToArray(); // cache values
       double[] originalTestClassValues = ProblemData.Dataset.GetDoubleValues(ProblemData.TargetVariable, ProblemData.TestIndices).ToArray();
+
+      var positiveClassName = ProblemData.PositiveClassName;
+      double positiveClassValue = ProblemData.GetClassValue(positiveClassName);
+      ClassificationPerformanceMeasuresCalculator trainingPerformanceCalculator = new ClassificationPerformanceMeasuresCalculator(positiveClassName, positiveClassValue);
+      ClassificationPerformanceMeasuresCalculator testPerformanceCalculator = new ClassificationPerformanceMeasuresCalculator(positiveClassName, positiveClassValue);
 
       OnlineCalculatorError errorState;
@@ -107 +127 @@
       TrainingNormalizedGiniCoefficient = trainingNormalizedGini;
       TestNormalizedGiniCoefficient = testNormalizedGini;
+
+      trainingPerformanceCalculator.Calculate(originalTrainingClassValues, estimatedTrainingClassValues);
+      if (trainingPerformanceCalculator.ErrorState == OnlineCalculatorError.None)
+        ClassificationPerformanceMeasures.SetTrainingResults(trainingPerformanceCalculator);
+
+      testPerformanceCalculator.Calculate(originalTestClassValues, estimatedTestClassValues);
+      if (testPerformanceCalculator.ErrorState == OnlineCalculatorError.None)
+        ClassificationPerformanceMeasures.SetTestResults(testPerformanceCalculator);
     }