Changeset 6184 for trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression

Timestamp:

05/11/11 15:56:17 (14 years ago)

Author:

gkronber

Message:

#1450: merged r5816 from the branch and implemented first version of ensemble solutions for regression. The ensembles are only produced by cross validation.

Location:

trunk/sources

Files:

• . (modified) (1 prop)
• HeuristicLab.Problems.DataAnalysis (modified) (1 prop)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionEnsembleSolution.cs (copied) (copied from branches/DataAnalysis SolutionEnsembles/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionEnsembleSolution.cs) (3 diffs)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionSolution.cs (modified) (4 diffs)

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionEnsembleSolution.cs

@@ -75 +75 @@
         throw new ArgumentException();
       }
+
+      RecalculateResults();
+    }
+
+    private void RecalculateResults() {
+      double[] estimatedTrainingValues = EstimatedTrainingValues.ToArray(); // cache values
+      var trainingIndizes = Enumerable.Range(ProblemData.TrainingPartition.Start,
+        ProblemData.TrainingPartition.End - ProblemData.TrainingPartition.Start);
+      IEnumerable<double> originalTrainingValues = ProblemData.Dataset.GetEnumeratedVariableValues(ProblemData.TargetVariable, trainingIndizes);
+      double[] estimatedTestValues = EstimatedTestValues.ToArray(); // cache values
+      IEnumerable<double> originalTestValues = ProblemData.Dataset.GetEnumeratedVariableValues(ProblemData.TargetVariable, ProblemData.TestIndizes);
+
+      OnlineCalculatorError errorState;
+      double trainingMSE = OnlineMeanSquaredErrorCalculator.Calculate(estimatedTrainingValues, originalTrainingValues, out errorState);
+      TrainingMeanSquaredError = errorState == OnlineCalculatorError.None ? trainingMSE : double.NaN;
+      double testMSE = OnlineMeanSquaredErrorCalculator.Calculate(estimatedTestValues, originalTestValues, out errorState);
+      TestMeanSquaredError = errorState == OnlineCalculatorError.None ? testMSE : double.NaN;
+
+      double trainingR2 = OnlinePearsonsRSquaredCalculator.Calculate(estimatedTrainingValues, originalTrainingValues, out errorState);
+      TrainingRSquared = errorState == OnlineCalculatorError.None ? trainingR2 : double.NaN;
+      double testR2 = OnlinePearsonsRSquaredCalculator.Calculate(estimatedTestValues, originalTestValues, out errorState);
+      TestRSquared = errorState == OnlineCalculatorError.None ? testR2 : double.NaN;
+
+      double trainingRelError = OnlineMeanAbsolutePercentageErrorCalculator.Calculate(estimatedTrainingValues, originalTrainingValues, out errorState);
+      TrainingRelativeError = errorState == OnlineCalculatorError.None ? trainingRelError : double.NaN;
+      double testRelError = OnlineMeanAbsolutePercentageErrorCalculator.Calculate(estimatedTestValues, originalTestValues, out errorState);
+      TestRelativeError = errorState == OnlineCalculatorError.None ? testRelError : double.NaN;
+
+      double trainingNMSE = OnlineNormalizedMeanSquaredErrorCalculator.Calculate(estimatedTrainingValues, originalTrainingValues, out errorState);
+      TrainingNormalizedMeanSquaredError = errorState == OnlineCalculatorError.None ? trainingNMSE : double.NaN;
+      double testNMSE = OnlineNormalizedMeanSquaredErrorCalculator.Calculate(estimatedTestValues, originalTestValues, out errorState);
+      TestNormalizedMeanSquaredError = errorState == OnlineCalculatorError.None ? testNMSE : double.NaN;
     }
 
@@ -83 +115 @@
     public override IEnumerable<double> EstimatedTrainingValues {
       get {
+        var rows = Enumerable.Range(ProblemData.TrainingPartition.Start, ProblemData.TrainingPartition.End - ProblemData.TrainingPartition.Start);
         var estimatedValuesEnumerators = (from model in Model.Models
-                                          select new { Model = model, EstimatedValuesEnumerator = model.GetEstimatedValues(ProblemData.Dataset, ProblemData.TestIndizes).GetEnumerator() })
+                                          select new { Model = model, EstimatedValuesEnumerator = model.GetEstimatedValues(ProblemData.Dataset, rows).GetEnumerator() })
                                          .ToList();
-        var rowsEnumerator = ProblemData.TestIndizes.GetEnumerator();
-        while (rowsEnumerator.MoveNext() & estimatedValuesEnumerators.All(en => en.EstimatedValuesEnumerator.MoveNext())) {
+        var rowsEnumerator = rows.GetEnumerator();
+        while (rowsEnumerator.MoveNext() & estimatedValuesEnumerators.Select(en => en.EstimatedValuesEnumerator.MoveNext()).Aggregate(true, (acc, b) => acc & b)) {
           int currentRow = rowsEnumerator.Current;
 
           var selectedEnumerators = from pair in estimatedValuesEnumerators
                                     where trainingPartitions == null || !trainingPartitions.ContainsKey(pair.Model) ||
-                                         (trainingPartitions[pair.Model].Start >= currentRow && trainingPartitions[pair.Model].End < currentRow)
+                                         (trainingPartitions[pair.Model].Start <= currentRow && currentRow < trainingPartitions[pair.Model].End)
                                     select pair.EstimatedValuesEnumerator;
           yield return AggregateEstimatedValues(selectedEnumerators.Select(x => x.Current));
@@ -105 +138 @@
                                          .ToList();
         var rowsEnumerator = ProblemData.TestIndizes.GetEnumerator();
-        while (rowsEnumerator.MoveNext() & estimatedValuesEnumerators.All(en => en.EstimatedValuesEnumerator.MoveNext())) {
+        while (rowsEnumerator.MoveNext() & estimatedValuesEnumerators.Select(en => en.EstimatedValuesEnumerator.MoveNext()).Aggregate(true, (acc, b) => acc & b)) {
           int currentRow = rowsEnumerator.Current;
 
           var selectedEnumerators = from pair in estimatedValuesEnumerators
                                     where testPartitions == null || !testPartitions.ContainsKey(pair.Model) ||
-                                      (testPartitions[pair.Model].Start >= currentRow && testPartitions[pair.Model].End < currentRow)
+                                      (testPartitions[pair.Model].Start <= currentRow && currentRow < testPartitions[pair.Model].End)
                                     select pair.EstimatedValuesEnumerator;
 

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionSolution.cs

@@ -30 +30 @@
 namespace HeuristicLab.Problems.DataAnalysis {
   /// <summary>
-  /// Abstract base class for regression data analysis solutions
+  /// Represents a regression data analysis solution
   /// </summary>
   [StorableClass]
-  public abstract class RegressionSolution : DataAnalysisSolution, IRegressionSolution {
+  public class RegressionSolution : DataAnalysisSolution, IRegressionSolution {
     private const string TrainingMeanSquaredErrorResultName = "Mean squared error (training)";
     private const string TestMeanSquaredErrorResultName = "Mean squared error (test)";
@@ -55 +55 @@
     public double TrainingMeanSquaredError {
       get { return ((DoubleValue)this[TrainingMeanSquaredErrorResultName].Value).Value; }
-      private set { ((DoubleValue)this[TrainingMeanSquaredErrorResultName].Value).Value = value; }
+      protected set { ((DoubleValue)this[TrainingMeanSquaredErrorResultName].Value).Value = value; }
     }
 
     public double TestMeanSquaredError {
       get { return ((DoubleValue)this[TestMeanSquaredErrorResultName].Value).Value; }
-      private set { ((DoubleValue)this[TestMeanSquaredErrorResultName].Value).Value = value; }
+      protected set { ((DoubleValue)this[TestMeanSquaredErrorResultName].Value).Value = value; }
     }
 
     public double TrainingRSquared {
       get { return ((DoubleValue)this[TrainingSquaredCorrelationResultName].Value).Value; }
-      private set { ((DoubleValue)this[TrainingSquaredCorrelationResultName].Value).Value = value; }
+      protected set { ((DoubleValue)this[TrainingSquaredCorrelationResultName].Value).Value = value; }
     }
 
     public double TestRSquared {
       get { return ((DoubleValue)this[TestSquaredCorrelationResultName].Value).Value; }
-      private set { ((DoubleValue)this[TestSquaredCorrelationResultName].Value).Value = value; }
+      protected set { ((DoubleValue)this[TestSquaredCorrelationResultName].Value).Value = value; }
     }
 
     public double TrainingRelativeError {
       get { return ((DoubleValue)this[TrainingRelativeErrorResultName].Value).Value; }
-      private set { ((DoubleValue)this[TrainingRelativeErrorResultName].Value).Value = value; }
+      protected set { ((DoubleValue)this[TrainingRelativeErrorResultName].Value).Value = value; }
     }
 
     public double TestRelativeError {
       get { return ((DoubleValue)this[TestRelativeErrorResultName].Value).Value; }
-      private set { ((DoubleValue)this[TestRelativeErrorResultName].Value).Value = value; }
+      protected set { ((DoubleValue)this[TestRelativeErrorResultName].Value).Value = value; }
     }
 
     public double TrainingNormalizedMeanSquaredError {
       get { return ((DoubleValue)this[TrainingNormalizedMeanSquaredErrorResultName].Value).Value; }
-      private set { ((DoubleValue)this[TrainingNormalizedMeanSquaredErrorResultName].Value).Value = value; }
+      protected set { ((DoubleValue)this[TrainingNormalizedMeanSquaredErrorResultName].Value).Value = value; }
     }
 
     public double TestNormalizedMeanSquaredError {
       get { return ((DoubleValue)this[TestNormalizedMeanSquaredErrorResultName].Value).Value; }
-      private set { ((DoubleValue)this[TestNormalizedMeanSquaredErrorResultName].Value).Value = value; }
+      protected set { ((DoubleValue)this[TestNormalizedMeanSquaredErrorResultName].Value).Value = value; }
     }
 
@@ -113 +113 @@
     }
 
+    public override IDeepCloneable Clone(Cloner cloner) {
+      return new RegressionSolution(this, cloner);
+    }
+
     protected override void OnProblemDataChanged(EventArgs e) {
       base.OnProblemDataChanged(e);
@@ -122 +126 @@
     }
 
-    protected void RecalculateResults() {
+    private void RecalculateResults() {
       double[] estimatedTrainingValues = EstimatedTrainingValues.ToArray(); // cache values
       IEnumerable<double> originalTrainingValues = ProblemData.Dataset.GetEnumeratedVariableValues(ProblemData.TargetVariable, ProblemData.TrainingIndizes);