Changeset 6685 for branches/GeneralizedQAP/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification

Timestamp:

08/31/11 11:52:11 (13 years ago)

Author:

abeham

Message:

#1628

• Updated branch from trunk
• Changed ReferenceEqualityComparer<T> to become a non-generic class (generic implementation probably was only made because of lacking support for co- and contravariance in C# 3.5)
• Added finished experiment from sample algorithms to the tests
• Wrote a unit test to instantiate every IDeepCloneable type, clone it and compare the objects in the object graph for equal references
• Wrote a unit test to load the experiment, clone it and compare again the objects in the object graph
• Preliminary fix for a potential bug in ThreadSafeLog
• Preliminary fix for a potential bug in OperatorGraphVisualizationInfo
• Preliminary fix for a potential bug in Calculator (and added license headers)
• Preliminary fix for a potential bug in ScrambleMove

Location:

branches/GeneralizedQAP

Files:

• . (modified) (1 prop)
• HeuristicLab.Problems.DataAnalysis (modified) (1 prop)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationEnsembleModel.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationEnsembleProblemData.cs (modified) (3 diffs)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationEnsembleSolution.cs (modified) (3 diffs)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationProblemData.cs (modified) (7 diffs)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationSolutionBase.cs (modified) (1 diff)

branches/GeneralizedQAP/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() {

branches/GeneralizedQAP/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;
 using HeuristicLab.Core;
@@ -35 +32 @@
   public class ClassificationEnsembleProblemData : ClassificationProblemData {
 
-    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 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 +80 @@
       this.TestPartition.End = classificationProblemData.TestPartition.End;
     }
+
+    public ClassificationEnsembleProblemData(Dataset dataset, IEnumerable<string> allowedInputVariables, string targetVariable)
+      : base(dataset, allowedInputVariables, targetVariable) {
+    }
   }
 }

branches/GeneralizedQAP/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);

branches/GeneralizedQAP/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
@@ -171 +171 @@
      {1176881,7,5,3,7,4,10,7,5,5,4        }
 };
-    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 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) { }
@@ -267 +291 @@
     private static IEnumerable<string> CheckVariablesForPossibleTargetVariables(Dataset dataset) {
       int maxSamples = Math.Min(InspectedRowsToDetermineTargets, dataset.Rows);
-      var validTargetVariables = from v in dataset.VariableNames
-                                 let DistinctValues = dataset.GetVariableValues(v)
-                                   .Take(maxSamples)
-                                   .Distinct()
-                                   .Count()
-                                 where DistinctValues < MaximumNumberOfClasses
-                                 select v;
+      var validTargetVariables = (from v in dataset.VariableNames
+                                  let distinctValues = dataset.GetEnumeratedVariableValues(v)
+                                    .Take(maxSamples)
+                                    .Distinct()
+                                    .Count()
+                                  where distinctValues < MaximumNumberOfClasses
+                                  select v).ToArray();
 
       if (!validTargetVariables.Any())
@@ -283 +307 @@
 
     private void ResetTargetVariableDependentMembers() {
-      DergisterParameterEvents();
+      DeregisterParameterEvents();
 
       classNames = null;
@@ -357 +381 @@
       ClassificationPenaltiesParameter.Value.ItemChanged += new EventHandler<EventArgs<int, int>>(MatrixParameter_ItemChanged);
     }
-    private void DergisterParameterEvents() {
+    private void DeregisterParameterEvents() {
       TargetVariableParameter.ValueChanged -= new EventHandler(TargetVariableParameter_ValueChanged);
       ClassNamesParameter.Value.Reset -= new EventHandler(Parameter_ValueChanged);

branches/GeneralizedQAP/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationSolutionBase.cs

@@ -40 +40 @@
     public new IClassificationProblemData ProblemData {
       get { return (IClassificationProblemData)base.ProblemData; }
-      protected set { base.ProblemData = value; }
+      set { base.ProblemData = value; }
     }