Changeset 6666 for trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation

Timestamp:

08/17/11 14:37:34 (13 years ago)

Author:

mkommend

Message:

#1592: Enabled creation of empty ensemble solutions and problem data changes.

Location:

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation

Files:

• Classification/ClassificationEnsembleModel.cs (modified) (1 diff)
• Classification/ClassificationEnsembleProblemData.cs (modified) (3 diffs)
• Classification/ClassificationEnsembleSolution.cs (modified) (3 diffs)
• Classification/ClassificationProblemData.cs (modified) (4 diffs)
• DataAnalysisProblemData.cs (modified) (3 diffs)
• Regression/RegressionEnsembleModel.cs (modified) (1 diff)
• Regression/RegressionEnsembleProblemData.cs (modified) (3 diffs)
• Regression/RegressionEnsembleSolution.cs (modified) (4 diffs)
• Regression/RegressionProblemData.cs (modified) (4 diffs)

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

@@ -46 +46 @@
       this.models = original.Models.Select(m => cloner.Clone(m)).ToList();
     }
+
+    public ClassificationEnsembleModel() : this(Enumerable.Empty<IClassificationModel>()) { }
     public ClassificationEnsembleModel(IEnumerable<IClassificationModel> models)
       : base() {

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

@@ -20 +20 @@
 #endregion
 
-using System;
 using System.Collections.Generic;
-using System.IO;
 using System.Linq;
 using HeuristicLab.Common;
@@ -36 +34 @@
 
     public override IEnumerable<int> TrainingIndizes {
-      get {
-        return Enumerable.Range(TrainingPartition.Start, TrainingPartition.End - TrainingPartition.Start);
-      }
+      get { return Enumerable.Range(TrainingPartition.Start, TrainingPartition.End - TrainingPartition.Start); }
     }
     public override IEnumerable<int> TestIndizes {
-      get {
-        return Enumerable.Range(TestPartition.Start, TestPartition.End - TestPartition.Start);
-      }
+      get { return Enumerable.Range(TestPartition.Start, TestPartition.End - TestPartition.Start); }
+    }
+
+    private static ClassificationEnsembleProblemData emptyProblemData;
+    public static ClassificationEnsembleProblemData EmptyProblemData {
+      get { return emptyProblemData; }
+    }
+
+    static ClassificationEnsembleProblemData() {
+      var problemData = new ClassificationEnsembleProblemData();
+      problemData.Parameters.Clear();
+      problemData.Name = "Empty Classification 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>()));
+      problemData.Parameters.Add(new FixedValueParameter<StringMatrix>(ClassNamesParameterName, "", new StringMatrix(0, 0).AsReadOnly()));
+      problemData.Parameters.Add(new FixedValueParameter<DoubleMatrix>(ClassificationPenaltiesParameterName, "", (DoubleMatrix)new DoubleMatrix(0, 0).AsReadOnly()));
+      emptyProblemData = problemData;
     }
 
     [StorableConstructor]
     protected ClassificationEnsembleProblemData(bool deserializing) : base(deserializing) { }
+    protected ClassificationEnsembleProblemData(ClassificationEnsembleProblemData original, Cloner cloner) : base(original, cloner) { }
+    public override IDeepCloneable Clone(Cloner cloner) {
+      if (this == emptyProblemData) return emptyProblemData;
+      return new ClassificationEnsembleProblemData(this, cloner);
+    }
 
-    protected ClassificationEnsembleProblemData(ClassificationEnsembleProblemData original, Cloner cloner)
-      : base(original, cloner) {
-    }
-    public override IDeepCloneable Clone(Cloner cloner) { return new ClassificationEnsembleProblemData(this, cloner); }
-
+    public ClassificationEnsembleProblemData() : base() { }
     public ClassificationEnsembleProblemData(IClassificationProblemData classificationProblemData)
       : base(classificationProblemData.Dataset, classificationProblemData.AllowedInputVariables, classificationProblemData.TargetVariable) {
@@ -61 +78 @@
       this.TestPartition.End = classificationProblemData.TestPartition.End;
     }
+
+    public ClassificationEnsembleProblemData(Dataset dataset, IEnumerable<string> allowedInputVariables, string targetVariable)
+      : base(dataset, allowedInputVariables, targetVariable) {
+    }
   }
 }

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

@@ -35 +35 @@
   [StorableClass]
   [Item("Classification Ensemble Solution", "A classification solution that contains an ensemble of multiple classification models")]
-  // [Creatable("Data Analysis")]
+  [Creatable("Data Analysis - Ensembles")]
   public sealed class ClassificationEnsembleSolution : ClassificationSolution, IClassificationEnsembleSolution {
     public new IClassificationEnsembleModel Model {
       get { return (IClassificationEnsembleModel)base.Model; }
+    }
+    public new ClassificationEnsembleProblemData ProblemData {
+      get { return (ClassificationEnsembleProblemData)base.ProblemData; }
+      set { base.ProblemData = value; }
     }
 
@@ -82 +86 @@
 
       classificationSolutions = cloner.Clone(original.classificationSolutions);
+      RegisterClassificationSolutionsEventHandler();
+    }
+
+    public ClassificationEnsembleSolution()
+      : base(new ClassificationEnsembleModel(), ClassificationEnsembleProblemData.EmptyProblemData) {
+      trainingPartitions = new Dictionary<IClassificationModel, IntRange>();
+      testPartitions = new Dictionary<IClassificationModel, IntRange>();
+      classificationSolutions = new ItemCollection<IClassificationSolution>();
+
       RegisterClassificationSolutionsEventHandler();
     }
@@ -208 +221 @@
     #endregion
 
+    protected override void OnProblemDataChanged() {
+      IClassificationProblemData problemData = new ClassificationProblemData(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 ClassificationSolutions) {
+        if (solution is ClassificationEnsembleSolution)
+          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 AddClassificationSolutions(IEnumerable<IClassificationSolution> solutions) {
       classificationSolutions.AddRange(solutions);

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

@@ -34 +34 @@
   [Item("ClassificationProblemData", "Represents an item containing all data defining a classification problem.")]
   public class ClassificationProblemData : DataAnalysisProblemData, IClassificationProblemData {
-    private const string TargetVariableParameterName = "TargetVariable";
-    private const string ClassNamesParameterName = "ClassNames";
-    private const string ClassificationPenaltiesParameterName = "ClassificationPenalties";
-    private const int MaximumNumberOfClasses = 20;
-    private const int InspectedRowsToDetermineTargets = 500;
+    protected const string TargetVariableParameterName = "TargetVariable";
+    protected const string ClassNamesParameterName = "ClassNames";
+    protected const string ClassificationPenaltiesParameterName = "ClassificationPenalties";
+    protected const int MaximumNumberOfClasses = 20;
+    protected const int InspectedRowsToDetermineTargets = 500;
 
     #region default data
@@ -174 +174 @@
     private static IEnumerable<string> defaultAllowedInputVariables;
     private static string defaultTargetVariable;
+
+    private static ClassificationProblemData emptyProblemData;
+    public static ClassificationProblemData EmptyProblemData {
+      get { return EmptyProblemData; }
+    }
+
     static ClassificationProblemData() {
       defaultDataset = new Dataset(defaultVariableNames, defaultData);
@@ -181 +187 @@
       defaultAllowedInputVariables = defaultVariableNames.Except(new List<string>() { "sample", "class" });
       defaultTargetVariable = "class";
+
+      var problemData = new ClassificationProblemData();
+      problemData.Parameters.Clear();
+      problemData.Name = "Empty Classification 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>()));
+      problemData.Parameters.Add(new FixedValueParameter<StringMatrix>(ClassNamesParameterName, "", new StringMatrix(0, 0).AsReadOnly()));
+      problemData.Parameters.Add(new FixedValueParameter<DoubleMatrix>(ClassificationPenaltiesParameterName, "", (DoubleMatrix)new DoubleMatrix(0, 0).AsReadOnly()));
+      emptyProblemData = problemData;
     }
     #endregion
@@ -249 +270 @@
       RegisterParameterEvents();
     }
-    public override IDeepCloneable Clone(Cloner cloner) { return new ClassificationProblemData(this, cloner); }
+    public override IDeepCloneable Clone(Cloner cloner) {
+      if (this == emptyProblemData) return emptyProblemData;
+      return new ClassificationProblemData(this, cloner);
+    }
 
     public ClassificationProblemData() : this(defaultDataset, defaultAllowedInputVariables, defaultTargetVariable) { }

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/DataAnalysisProblemData.cs

@@ -33 +33 @@
   [StorableClass]
   public abstract class DataAnalysisProblemData : ParameterizedNamedItem, IDataAnalysisProblemData {
-    private const string DatasetParameterName = "Dataset";
-    private const string InputVariablesParameterName = "InputVariables";
-    private const string TrainingPartitionParameterName = "TrainingPartition";
-    private const string TestPartitionParameterName = "TestPartition";
+    protected const string DatasetParameterName = "Dataset";
+    protected const string InputVariablesParameterName = "InputVariables";
+    protected const string TrainingPartitionParameterName = "TrainingPartition";
+    protected const string TestPartitionParameterName = "TestPartition";
 
     #region parameter properites
@@ -53 +53 @@
     #endregion
 
-    #region propeties
+    #region properties
+    protected bool isEmpty = false;
+    public bool IsEmpty {
+      get { return isEmpty; }
+    }
     public Dataset Dataset {
       get { return DatasetParameter.Value; }
@@ -87 +91 @@
     protected DataAnalysisProblemData(DataAnalysisProblemData original, Cloner cloner)
       : base(original, cloner) {
+      isEmpty = original.isEmpty;
       RegisterEventHandlers();
     }

trunk/sources/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() {

trunk/sources/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;
@@ -47 +45 @@
     }
 
+    private static 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 +80 @@
       TestPartition.End = regressionProblemData.TestPartition.End;
     }
+    public RegressionEnsembleProblemData(Dataset dataset, IEnumerable<string> allowedInputVariables, string targetVariable)
+      : base(dataset, allowedInputVariables, targetVariable) {
+    }
   }
 }

trunk/sources/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);
     }

trunk/sources/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
@@ -68 +68 @@
     private static string defaultTargetVariable;
 
+    private static RegressionProblemData emptyProblemData;
+    public static RegressionProblemData EmptyProblemData {
+      get { return emptyProblemData; }
+    }
+
     static RegressionProblemData() {
       defaultDataset = new Dataset(new string[] { "y", "x" }, kozaF1);
@@ -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()