Changeset 9363 for branches/OaaS/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression

Timestamp:

04/16/13 13:13:41 (12 years ago)

Author:

spimming

Message:

#1888:

• Merged revisions from trunk

Location:

branches/OaaS

Files:

• . (modified) (2 props)
• HeuristicLab.Problems.DataAnalysis (modified) (1 prop)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/ConstantRegressionModel.cs (modified) (2 diffs)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/ConstantRegressionSolution.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionEnsembleModel.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionEnsembleSolution.cs (modified) (2 diffs)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionProblem.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionProblemData.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionSolution.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionSolutionBase.cs (modified) (3 diffs)

branches/OaaS

@@ -21 +21 @@
 protoc.exe
 _ReSharper.HeuristicLab 3.3 Tests
+Google.ProtocolBuffers-2.4.1.473.dll
 packages

@@ -21 +21 @@
 protoc.exe
 _ReSharper.HeuristicLab 3.3 Tests
+Google.ProtocolBuffers-2.4.1.473.dll
 packages

branches/OaaS/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/ConstantRegressionModel.cs

@@ -27 +27 @@
 
 namespace HeuristicLab.Problems.DataAnalysis {
+  [StorableClass]
   [Item("Constant Regression Model", "A model that always returns the same constant value regardless of the presented input data.")]
   public class ConstantRegressionModel : NamedItem, IRegressionModel {
     [Storable]
-    private double constant;
+    protected double constant;
     public double Constant {
       get { return constant; }
@@ -55 +56 @@
 
     public IRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData) {
-      return new ConstantRegressionSolution(this, problemData);
+      return new ConstantRegressionSolution(this, new RegressionProblemData(problemData));
     }
   }

branches/OaaS/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/ConstantRegressionSolution.cs

@@ -1 @@
-using HeuristicLab.Common;
+#region License Information
+/* HeuristicLab
+ * Copyright (C) 2002-2012 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ *
+ * This file is part of HeuristicLab.
+ *
+ * HeuristicLab is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * HeuristicLab is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with HeuristicLab. If not, see <http://www.gnu.org/licenses/>.
+ */
+#endregion
+
+using HeuristicLab.Common;
 using HeuristicLab.Core;
 using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;

branches/OaaS/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionEnsembleModel.cs

@@ -102 +102 @@
 
     public RegressionEnsembleSolution CreateRegressionSolution(IRegressionProblemData problemData) {
-      return new RegressionEnsembleSolution(this.Models, problemData);
+      return new RegressionEnsembleSolution(this.Models, new RegressionEnsembleProblemData(problemData));
     }
     IRegressionSolution IRegressionModel.CreateRegressionSolution(IRegressionProblemData problemData) {

branches/OaaS/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionEnsembleSolution.cs

@@ -36 +36 @@
   [Item("Regression Ensemble Solution", "A regression solution that contains an ensemble of multiple regression models")]
   [Creatable("Data Analysis - Ensembles")]
-  public sealed class RegressionEnsembleSolution : RegressionSolution, IRegressionEnsembleSolution {
+  public sealed class RegressionEnsembleSolution : RegressionSolutionBase, IRegressionEnsembleSolution {
     private readonly Dictionary<int, double> trainingEvaluationCache = new Dictionary<int, double>();
     private readonly Dictionary<int, double> testEvaluationCache = new Dictionary<int, double>();
+    private readonly Dictionary<int, double> evaluationCache = new Dictionary<int, double>();
 
     public new IRegressionEnsembleModel Model {
@@ -155 +156 @@
     }
 
-    protected override void RecalculateResults() {
-      CalculateResults();
-    }
-
     #region Evaluation
+    public override IEnumerable<double> EstimatedValues {
+      get { return GetEstimatedValues(Enumerable.Range(0, ProblemData.Dataset.Rows)); }
+    }
+
     public override IEnumerable<double> EstimatedTrainingValues {
       get {

branches/OaaS/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionProblem.cs

@@ -36 +36 @@
     public override IDeepCloneable Clone(Cloner cloner) { return new RegressionProblem(this, cloner); }
 
-    public RegressionProblem()
-      : base() {
-      ProblemData = new RegressionProblemData();
-    }
+    public RegressionProblem() : base(new RegressionProblemData()) { }
+
   }
 }

branches/OaaS/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionProblemData.cs

@@ -121 +121 @@
       : this(defaultDataset, defaultAllowedInputVariables, defaultTargetVariable) {
     }
+    public RegressionProblemData(IRegressionProblemData regressionProblemData)
+      : this(regressionProblemData.Dataset, regressionProblemData.AllowedInputVariables, regressionProblemData.TargetVariable) {
+      TrainingPartition.Start = regressionProblemData.TrainingPartition.Start;
+      TrainingPartition.End = regressionProblemData.TrainingPartition.End;
+      TestPartition.Start = regressionProblemData.TestPartition.Start;
+      TestPartition.End = regressionProblemData.TestPartition.End;
+    }
 
     public RegressionProblemData(Dataset dataset, IEnumerable<string> allowedInputVariables, string targetVariable)

branches/OaaS/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionSolution.cs

@@ -45 +45 @@
       : base(model, problemData) {
       evaluationCache = new Dictionary<int, double>(problemData.Dataset.Rows);
+      CalculateRegressionResults();
     }
 
-    protected override void RecalculateResults() {
-      CalculateResults();
-    }
 
     public override IEnumerable<double> EstimatedValues {

branches/OaaS/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionSolutionBase.cs

@@ -29 +29 @@
   [StorableClass]
   public abstract class RegressionSolutionBase : DataAnalysisSolution, IRegressionSolution {
-    private const string TrainingMeanSquaredErrorResultName = "Mean squared error (training)";
-    private const string TestMeanSquaredErrorResultName = "Mean squared error (test)";
-    private const string TrainingMeanAbsoluteErrorResultName = "Mean absolute error (training)";
-    private const string TestMeanAbsoluteErrorResultName = "Mean absolute error (test)";
-    private const string TrainingSquaredCorrelationResultName = "Pearson's R² (training)";
-    private const string TestSquaredCorrelationResultName = "Pearson's R² (test)";
-    private const string TrainingRelativeErrorResultName = "Average relative error (training)";
-    private const string TestRelativeErrorResultName = "Average relative error (test)";
-    private const string TrainingNormalizedMeanSquaredErrorResultName = "Normalized mean squared error (training)";
-    private const string TestNormalizedMeanSquaredErrorResultName = "Normalized mean squared error (test)";
-    private const string TrainingMeanErrorResultName = "Mean error (training)";
-    private const string TestMeanErrorResultName = "Mean error (test)";
+    protected const string TrainingMeanSquaredErrorResultName = "Mean squared error (training)";
+    protected const string TestMeanSquaredErrorResultName = "Mean squared error (test)";
+    protected const string TrainingMeanAbsoluteErrorResultName = "Mean absolute error (training)";
+    protected const string TestMeanAbsoluteErrorResultName = "Mean absolute error (test)";
+    protected const string TrainingSquaredCorrelationResultName = "Pearson's R² (training)";
+    protected const string TestSquaredCorrelationResultName = "Pearson's R² (test)";
+    protected const string TrainingRelativeErrorResultName = "Average relative error (training)";
+    protected const string TestRelativeErrorResultName = "Average relative error (test)";
+    protected const string TrainingNormalizedMeanSquaredErrorResultName = "Normalized mean squared error (training)";
+    protected const string TestNormalizedMeanSquaredErrorResultName = "Normalized mean squared error (test)";
+    protected const string TrainingMeanErrorResultName = "Mean error (training)";
+    protected const string TestMeanErrorResultName = "Mean error (test)";
+
+    protected const string TrainingMeanSquaredErrorResultDescription = "Mean of squared errors of the model on the training partition";
+    protected const string TestMeanSquaredErrorResultDescription = "Mean of squared errors of the model on the test partition";
+    protected const string TrainingMeanAbsoluteErrorResultDescription = "Mean of absolute errors of the model on the training partition";
+    protected const string TestMeanAbsoluteErrorResultDescription = "Mean of absolute errors of the model on the test partition";
+    protected const string TrainingSquaredCorrelationResultDescription = "Squared Pearson's correlation coefficient of the model output and the actual values on the training partition";
+    protected const string TestSquaredCorrelationResultDescription = "Squared Pearson's correlation coefficient of the model output and the actual values on the test partition";
+    protected const string TrainingRelativeErrorResultDescription = "Average of the relative errors of the model output and the actual values on the training partition";
+    protected const string TestRelativeErrorResultDescription = "Average of the relative errors of the model output and the actual values on the test partition";
+    protected const string TrainingNormalizedMeanSquaredErrorResultDescription = "Normalized mean of squared errors of the model on the training partition";
+    protected const string TestNormalizedMeanSquaredErrorResultDescription = "Normalized mean of squared errors of the model on the test partition";
+    protected const string TrainingMeanErrorResultDescription = "Mean of errors of the model on the training partition";
+    protected const string TestMeanErrorResultDescription = "Mean of errors of the model on the test partition";
 
     public new IRegressionModel Model {
@@ -115 +128 @@
     protected RegressionSolutionBase(IRegressionModel model, IRegressionProblemData problemData)
       : base(model, problemData) {
-      Add(new Result(TrainingMeanSquaredErrorResultName, "Mean of squared errors of the model on the training partition", new DoubleValue()));
-      Add(new Result(TestMeanSquaredErrorResultName, "Mean of squared errors of the model on the test partition", new DoubleValue()));
-      Add(new Result(TrainingMeanAbsoluteErrorResultName, "Mean of absolute errors of the model on the training partition", new DoubleValue()));
-      Add(new Result(TestMeanAbsoluteErrorResultName, "Mean of absolute errors of the model on the test partition", new DoubleValue()));
-      Add(new Result(TrainingSquaredCorrelationResultName, "Squared Pearson's correlation coefficient of the model output and the actual values on the training partition", new DoubleValue()));
-      Add(new Result(TestSquaredCorrelationResultName, "Squared Pearson's correlation coefficient of the model output and the actual values on the test partition", new DoubleValue()));
-      Add(new Result(TrainingRelativeErrorResultName, "Average of the relative errors of the model output and the actual values on the training partition", new PercentValue()));
-      Add(new Result(TestRelativeErrorResultName, "Average of the relative errors of the model output and the actual values on the test partition", new PercentValue()));
-      Add(new Result(TrainingNormalizedMeanSquaredErrorResultName, "Normalized mean of squared errors of the model on the training partition", new DoubleValue()));
-      Add(new Result(TestNormalizedMeanSquaredErrorResultName, "Normalized mean of squared errors of the model on the test partition", new DoubleValue()));
-      Add(new Result(TrainingMeanErrorResultName, "Mean of errors of the model on the training partition", new DoubleValue()));
-      Add(new Result(TestMeanErrorResultName, "Mean of errors of the model on the test partition", new DoubleValue()));
+      Add(new Result(TrainingMeanSquaredErrorResultName, TrainingMeanSquaredErrorResultDescription, new DoubleValue()));
+      Add(new Result(TestMeanSquaredErrorResultName, TestMeanSquaredErrorResultDescription, new DoubleValue()));
+      Add(new Result(TrainingMeanAbsoluteErrorResultName, TrainingMeanAbsoluteErrorResultDescription, new DoubleValue()));
+      Add(new Result(TestMeanAbsoluteErrorResultName, TestMeanAbsoluteErrorResultDescription, new DoubleValue()));
+      Add(new Result(TrainingSquaredCorrelationResultName, TrainingSquaredCorrelationResultDescription, new DoubleValue()));
+      Add(new Result(TestSquaredCorrelationResultName, TestSquaredCorrelationResultDescription, new DoubleValue()));
+      Add(new Result(TrainingRelativeErrorResultName, TrainingRelativeErrorResultDescription, new PercentValue()));
+      Add(new Result(TestRelativeErrorResultName, TestRelativeErrorResultDescription, new PercentValue()));
+      Add(new Result(TrainingNormalizedMeanSquaredErrorResultName, TrainingNormalizedMeanSquaredErrorResultDescription, new DoubleValue()));
+      Add(new Result(TestNormalizedMeanSquaredErrorResultName, TestNormalizedMeanSquaredErrorResultDescription, new DoubleValue()));
+      Add(new Result(TrainingMeanErrorResultName, TrainingMeanErrorResultDescription, new DoubleValue()));
+      Add(new Result(TestMeanErrorResultName, TestMeanErrorResultDescription, new DoubleValue()));
     }
 
@@ -164 +177 @@
     }
 
-    protected void CalculateResults() {
+    protected override void RecalculateResults() {
+      CalculateRegressionResults();
+    }
+
+    protected void CalculateRegressionResults() {
       IEnumerable<double> estimatedTrainingValues = EstimatedTrainingValues; // cache values
       IEnumerable<double> originalTrainingValues = ProblemData.Dataset.GetDoubleValues(ProblemData.TargetVariable, ProblemData.TrainingIndices);

@@ -21 +21 @@
 protoc.exe
 _ReSharper.HeuristicLab 3.3 Tests
+Google.ProtocolBuffers-2.4.1.473.dll
 packages