Changeset 6675 for branches/GP.Grammar.Editor/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression

Timestamp:

08/22/11 09:35:06 (13 years ago)

Author:

mkommend

Message:

#1479: Integrated trunk changes.

Location:

branches/GP.Grammar.Editor/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression

Files:

• RegressionEnsembleModel.cs (modified) (1 diff)
• RegressionEnsembleProblemData.cs (modified) (3 diffs)
• RegressionEnsembleSolution.cs (modified) (4 diffs)
• RegressionProblemData.cs (modified) (4 diffs)
• RegressionSolutionBase.cs (modified) (2 diffs)

branches/GP.Grammar.Editor/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionEnsembleModel.cs

@@ -58 +58 @@
       this.models = original.Models.Select(m => cloner.Clone(m)).ToList();
     }
+
+    public RegressionEnsembleModel() : this(Enumerable.Empty<IRegressionModel>()) { }
     public RegressionEnsembleModel(IEnumerable<IRegressionModel> models)
       : base() {

branches/GP.Grammar.Editor/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionEnsembleProblemData.cs

@@ -20 +20 @@
 #endregion
 
-using System;
 using System.Collections.Generic;
-using System.IO;
-using System.Linq;
 using HeuristicLab.Common;
 using HeuristicLab.Core;
@@ -35 +32 @@
   public sealed class RegressionEnsembleProblemData : RegressionProblemData {
 
-    public override IEnumerable<int> TrainingIndizes {
-      get {
-        return Enumerable.Range(TrainingPartition.Start, TrainingPartition.End - TrainingPartition.Start);
-      }
+    public override bool IsTrainingSample(int index) {
+      return index >= 0 && index < Dataset.Rows &&
+             TrainingPartition.Start <= index && index < TrainingPartition.End;
     }
 
-    public override IEnumerable<int> TestIndizes {
-      get {
-        return Enumerable.Range(TestPartition.Start, TestPartition.End - TestPartition.Start);
-      }
+    public override bool IsTestSample(int index) {
+      return index >= 0 && index < Dataset.Rows &&
+             TestPartition.Start <= index && index < TestPartition.End;
+    }
+
+    private static readonly RegressionEnsembleProblemData emptyProblemData;
+    public new static RegressionEnsembleProblemData EmptyProblemData {
+      get { return emptyProblemData; }
+    }
+    static RegressionEnsembleProblemData() {
+      var problemData = new RegressionEnsembleProblemData();
+      problemData.Parameters.Clear();
+      problemData.Name = "Empty Regression ProblemData";
+      problemData.Description = "This ProblemData acts as place holder before the correct problem data is loaded.";
+      problemData.isEmpty = true;
+
+      problemData.Parameters.Add(new FixedValueParameter<Dataset>(DatasetParameterName, "", new Dataset()));
+      problemData.Parameters.Add(new FixedValueParameter<ReadOnlyCheckedItemList<StringValue>>(InputVariablesParameterName, ""));
+      problemData.Parameters.Add(new FixedValueParameter<IntRange>(TrainingPartitionParameterName, "", (IntRange)new IntRange(0, 0).AsReadOnly()));
+      problemData.Parameters.Add(new FixedValueParameter<IntRange>(TestPartitionParameterName, "", (IntRange)new IntRange(0, 0).AsReadOnly()));
+      problemData.Parameters.Add(new ConstrainedValueParameter<StringValue>(TargetVariableParameterName, new ItemSet<StringValue>()));
+      emptyProblemData = problemData;
     }
 
     [StorableConstructor]
     private RegressionEnsembleProblemData(bool deserializing) : base(deserializing) { }
+    private RegressionEnsembleProblemData(RegressionEnsembleProblemData original, Cloner cloner) : base(original, cloner) { }
+    public override IDeepCloneable Clone(Cloner cloner) {
+      if (this == emptyProblemData) return emptyProblemData;
+      return new RegressionEnsembleProblemData(this, cloner);
+    }
 
-    private RegressionEnsembleProblemData(RegressionEnsembleProblemData original, Cloner cloner)
-      : base(original, cloner) {
-    }
-    public override IDeepCloneable Clone(Cloner cloner) { return new RegressionEnsembleProblemData(this, cloner); }
-
+    public RegressionEnsembleProblemData() : base() { }
     public RegressionEnsembleProblemData(IRegressionProblemData regressionProblemData)
       : base(regressionProblemData.Dataset, regressionProblemData.AllowedInputVariables, regressionProblemData.TargetVariable) {
@@ -62 +77 @@
       TestPartition.End = regressionProblemData.TestPartition.End;
     }
+    public RegressionEnsembleProblemData(Dataset dataset, IEnumerable<string> allowedInputVariables, string targetVariable)
+      : base(dataset, allowedInputVariables, targetVariable) {
+    }
   }
 }

branches/GP.Grammar.Editor/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionEnsembleSolution.cs

@@ -35 +35 @@
   [StorableClass]
   [Item("Regression Ensemble Solution", "A regression solution that contains an ensemble of multiple regression models")]
-  // [Creatable("Data Analysis")]
+  [Creatable("Data Analysis - Ensembles")]
   public sealed class RegressionEnsembleSolution : RegressionSolution, IRegressionEnsembleSolution {
     public new IRegressionEnsembleModel Model {
       get { return (IRegressionEnsembleModel)base.Model; }
+    }
+
+    public new RegressionEnsembleProblemData ProblemData {
+      get { return (RegressionEnsembleProblemData)base.ProblemData; }
+      set { base.ProblemData = value; }
     }
 
@@ -59 +64 @@
     private void AfterDeserialization() {
       foreach (var model in Model.Models) {
-        IRegressionProblemData problemData = (IRegressionProblemData)ProblemData.Clone();
+        IRegressionProblemData problemData = (IRegressionProblemData) ProblemData.Clone();
         problemData.TrainingPartition.Start = trainingPartitions[model].Start;
         problemData.TrainingPartition.End = trainingPartitions[model].End;
@@ -82 +87 @@
 
       regressionSolutions = cloner.Clone(original.regressionSolutions);
+      RegisterRegressionSolutionsEventHandler();
+    }
+
+    public RegressionEnsembleSolution()
+      : base(new RegressionEnsembleModel(), RegressionEnsembleProblemData.EmptyProblemData) {
+      trainingPartitions = new Dictionary<IRegressionModel, IntRange>();
+      testPartitions = new Dictionary<IRegressionModel, IntRange>();
+      regressionSolutions = new ItemCollection<IRegressionSolution>();
+
       RegisterRegressionSolutionsEventHandler();
     }
@@ -203 +217 @@
     #endregion
 
+    protected override void OnProblemDataChanged() {
+      IRegressionProblemData problemData = new RegressionProblemData(ProblemData.Dataset,
+                                                                     ProblemData.AllowedInputVariables,
+                                                                     ProblemData.TargetVariable);
+      problemData.TrainingPartition.Start = ProblemData.TrainingPartition.Start;
+      problemData.TrainingPartition.End = ProblemData.TrainingPartition.End;
+      problemData.TestPartition.Start = ProblemData.TestPartition.Start;
+      problemData.TestPartition.End = ProblemData.TestPartition.End;
+
+      foreach (var solution in RegressionSolutions) {
+        if (solution is RegressionEnsembleSolution)
+          solution.ProblemData = ProblemData;
+        else
+          solution.ProblemData = problemData;
+      }
+      foreach (var trainingPartition in trainingPartitions.Values) {
+        trainingPartition.Start = ProblemData.TrainingPartition.Start;
+        trainingPartition.End = ProblemData.TrainingPartition.End;
+      }
+      foreach (var testPartition in testPartitions.Values) {
+        testPartition.Start = ProblemData.TestPartition.Start;
+        testPartition.End = ProblemData.TestPartition.End;
+      }
+
+      base.OnProblemDataChanged();
+    }
+
     public void AddRegressionSolutions(IEnumerable<IRegressionSolution> solutions) {
-      solutions.OfType<RegressionEnsembleSolution>().SelectMany(ensemble => ensemble.RegressionSolutions);
       regressionSolutions.AddRange(solutions);
     }

branches/GP.Grammar.Editor/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionProblemData.cs

@@ -34 +34 @@
   [Item("RegressionProblemData", "Represents an item containing all data defining a regression problem.")]
   public class RegressionProblemData : DataAnalysisProblemData, IRegressionProblemData {
-    private const string TargetVariableParameterName = "TargetVariable";
+    protected const string TargetVariableParameterName = "TargetVariable";
 
     #region default data
@@ -64 +64 @@
           {0.83763905,  0.468046718}
     };
-    private static Dataset defaultDataset;
-    private static IEnumerable<string> defaultAllowedInputVariables;
-    private static string defaultTargetVariable;
+    private static readonly Dataset defaultDataset;
+    private static readonly IEnumerable<string> defaultAllowedInputVariables;
+    private static readonly string defaultTargetVariable;
+
+    private static readonly RegressionProblemData emptyProblemData;
+    public static RegressionProblemData EmptyProblemData {
+      get { return emptyProblemData; }
+    }
 
     static RegressionProblemData() {
@@ -74 +79 @@
       defaultAllowedInputVariables = new List<string>() { "x" };
       defaultTargetVariable = "y";
+
+      var problemData = new RegressionProblemData();
+      problemData.Parameters.Clear();
+      problemData.Name = "Empty Regression ProblemData";
+      problemData.Description = "This ProblemData acts as place holder before the correct problem data is loaded.";
+      problemData.isEmpty = true;
+
+      problemData.Parameters.Add(new FixedValueParameter<Dataset>(DatasetParameterName, "", new Dataset()));
+      problemData.Parameters.Add(new FixedValueParameter<ReadOnlyCheckedItemList<StringValue>>(InputVariablesParameterName, ""));
+      problemData.Parameters.Add(new FixedValueParameter<IntRange>(TrainingPartitionParameterName, "", (IntRange)new IntRange(0, 0).AsReadOnly()));
+      problemData.Parameters.Add(new FixedValueParameter<IntRange>(TestPartitionParameterName, "", (IntRange)new IntRange(0, 0).AsReadOnly()));
+      problemData.Parameters.Add(new ConstrainedValueParameter<StringValue>(TargetVariableParameterName, new ItemSet<StringValue>()));
+      emptyProblemData = problemData;
     }
     #endregion
@@ -91 +109 @@
     }
 
-
     protected RegressionProblemData(RegressionProblemData original, Cloner cloner)
       : base(original, cloner) {
       RegisterParameterEvents();
     }
-    public override IDeepCloneable Clone(Cloner cloner) { return new RegressionProblemData(this, cloner); }
+    public override IDeepCloneable Clone(Cloner cloner) {
+      if (this == emptyProblemData) return emptyProblemData;
+      return new RegressionProblemData(this, cloner);
+    }
 
     public RegressionProblemData()

branches/GP.Grammar.Editor/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionSolutionBase.cs

@@ -48 +48 @@
     public new IRegressionProblemData ProblemData {
       get { return (IRegressionProblemData)base.ProblemData; }
-      protected set { base.ProblemData = value; }
+      set { base.ProblemData = value; }
     }
 
@@ -127 +127 @@
         OnlineCalculatorError errorState;
         Add(new Result(TrainingMeanAbsoluteErrorResultName, "Mean of absolute errors of the model on the training partition", new DoubleValue()));
-        double trainingMAE = OnlineMeanSquaredErrorCalculator.Calculate(EstimatedTrainingValues, ProblemData.Dataset.GetEnumeratedVariableValues(ProblemData.TargetVariable, ProblemData.TrainingIndizes), out errorState);
+        double trainingMAE = OnlineMeanAbsoluteErrorCalculator.Calculate(EstimatedTrainingValues, ProblemData.Dataset.GetEnumeratedVariableValues(ProblemData.TargetVariable, ProblemData.TrainingIndizes), out errorState);
         TrainingMeanAbsoluteError = errorState == OnlineCalculatorError.None ? trainingMAE : double.NaN;
       }