Changeset 6760 for branches/PersistenceSpeedUp/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification

Timestamp:

09/14/11 13:59:25 (13 years ago)

Author:

epitzer

Message:

#1530 integrate changes from trunk

Location:

branches/PersistenceSpeedUp

Files:

• . (modified) (2 props)
• HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/HeuristicLabProblemsDataAnalysisSymbolicClassificationPlugin.cs.frame (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/MultiObjective/SymbolicClassificationMultiObjectiveMeanSquaredErrorTreeSizeEvaluator.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/MultiObjective/SymbolicClassificationMultiObjectivePearsonRSquaredTreeSizeEvaluator.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/MultiObjective/SymbolicClassificationMultiObjectiveProblem.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/Properties/AssemblyInfo.frame (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SingleObjective/SymbolicClassificationSingleObjectiveBoundedMeanSquaredErrorEvaluator.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SingleObjective/SymbolicClassificationSingleObjectiveMeanSquaredErrorEvaluator.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SingleObjective/SymbolicClassificationSingleObjectiveOverfittingAnalyzer.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SingleObjective/SymbolicClassificationSingleObjectivePearsonRSquaredEvaluator.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SingleObjective/SymbolicClassificationSingleObjectiveProblem.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SymbolicClassificationModel.cs (modified) (2 diffs)
• HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SymbolicClassificationSolution.cs (modified) (2 diffs)
• HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SymbolicDiscriminantFunctionClassificationModel.cs (modified) (6 diffs)
• HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SymbolicDiscriminantFunctionClassificationSolution.cs (modified) (2 diffs)

branches/PersistenceSpeedUp

@@ -12 +12 @@
 *.psess
 *.vsp
+*.docstates

@@ -12 +12 @@
 *.psess
 *.vsp
+*.docstates

branches/PersistenceSpeedUp/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/HeuristicLabProblemsDataAnalysisSymbolicClassificationPlugin.cs.frame

@@ -26 +26 @@
 
 namespace HeuristicLab.Problems.DataAnalysis.Symbolic.Classification {
-  [Plugin("HeuristicLab.Problems.DataAnalysis.Symbolic.Classification","Provides classes to perform symbolic classification (single- or multiobjective).", "3.4.0.$WCREV$")]
+  [Plugin("HeuristicLab.Problems.DataAnalysis.Symbolic.Classification","Provides classes to perform symbolic classification (single- or multiobjective).", "3.4.1.$WCREV$")]
   [PluginFile("HeuristicLab.Problems.DataAnalysis.Symbolic.Classification-3.4.dll", PluginFileType.Assembly)]
   [PluginDependency("HeuristicLab.ALGLIB", "3.1")]

branches/PersistenceSpeedUp/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/MultiObjective/SymbolicClassificationMultiObjectiveMeanSquaredErrorTreeSizeEvaluator.cs

@@ -54 +54 @@
     public static double[] Calculate(ISymbolicDataAnalysisExpressionTreeInterpreter interpreter, ISymbolicExpressionTree solution, double lowerEstimationLimit, double upperEstimationLimit, IClassificationProblemData problemData, IEnumerable<int> rows) {
       IEnumerable<double> estimatedValues = interpreter.GetSymbolicExpressionTreeValues(solution, problemData.Dataset, rows);
-      IEnumerable<double> originalValues = problemData.Dataset.GetEnumeratedVariableValues(problemData.TargetVariable, rows);
+      IEnumerable<double> originalValues = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, rows);
       IEnumerable<double> boundedEstimationValues = estimatedValues.LimitToRange(lowerEstimationLimit, upperEstimationLimit);
       OnlineCalculatorError errorState;

branches/PersistenceSpeedUp/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/MultiObjective/SymbolicClassificationMultiObjectivePearsonRSquaredTreeSizeEvaluator.cs

@@ -33 +33 @@
     public static double[] Calculate(ISymbolicDataAnalysisExpressionTreeInterpreter interpreter, ISymbolicExpressionTree solution, double lowerEstimationLimit, double upperEstimationLimit, IClassificationProblemData problemData, IEnumerable<int> rows) {
       IEnumerable<double> estimatedValues = interpreter.GetSymbolicExpressionTreeValues(solution, problemData.Dataset, rows);
-      IEnumerable<double> originalValues = problemData.Dataset.GetEnumeratedVariableValues(problemData.TargetVariable, rows);
+      IEnumerable<double> originalValues = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, rows);
       OnlineCalculatorError errorState;
       double r2 = OnlinePearsonsRSquaredCalculator.Calculate(estimatedValues, originalValues, out errorState);

branches/PersistenceSpeedUp/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/MultiObjective/SymbolicClassificationMultiObjectiveProblem.cs

@@ -73 +73 @@
 
     private void UpdateEstimationLimits() {
-      if (ProblemData.TrainingPartition.Start < ProblemData.TrainingPartition.End) {
-        var targetValues = ProblemData.Dataset.GetVariableValues(ProblemData.TargetVariable, ProblemData.TrainingPartition.Start, ProblemData.TrainingPartition.End);
+      if (ProblemData.TrainingIndizes.Any()) {
+        var targetValues = ProblemData.Dataset.GetDoubleValues(ProblemData.TargetVariable, ProblemData.TrainingIndizes).ToList();
         var mean = targetValues.Average();
         var range = targetValues.Max() - targetValues.Min();
         EstimationLimits.Upper = mean + PunishmentFactor * range;
         EstimationLimits.Lower = mean - PunishmentFactor * range;
+      } else {
+        EstimationLimits.Upper = double.MaxValue;
+        EstimationLimits.Lower = double.MinValue;
       }
     }

branches/PersistenceSpeedUp/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/Properties/AssemblyInfo.frame

@@ -53 +53 @@
 // by using the '*' as shown below:
 [assembly: AssemblyVersion("3.4.0.0")]
-[assembly: AssemblyFileVersion("3.4.0.$WCREV$")]
+[assembly: AssemblyFileVersion("3.4.1.$WCREV$")]

branches/PersistenceSpeedUp/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SingleObjective/SymbolicClassificationSingleObjectiveBoundedMeanSquaredErrorEvaluator.cs

@@ -54 +54 @@
     public static double Calculate(ISymbolicDataAnalysisExpressionTreeInterpreter interpreter, ISymbolicExpressionTree solution, double lowerEstimationLimit, double upperEstimationLimit, IClassificationProblemData problemData, IEnumerable<int> rows) {
       IEnumerable<double> estimatedValues = interpreter.GetSymbolicExpressionTreeValues(solution, problemData.Dataset, rows);
-      IEnumerable<double> originalValues = problemData.Dataset.GetEnumeratedVariableValues(problemData.TargetVariable, rows);
+      IEnumerable<double> originalValues = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, rows);
       IEnumerable<double> boundedEstimationValues = estimatedValues.LimitToRange(lowerEstimationLimit, upperEstimationLimit);
 

branches/PersistenceSpeedUp/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SingleObjective/SymbolicClassificationSingleObjectiveMeanSquaredErrorEvaluator.cs

@@ -54 +54 @@
     public static double Calculate(ISymbolicDataAnalysisExpressionTreeInterpreter interpreter, ISymbolicExpressionTree solution, double lowerEstimationLimit, double upperEstimationLimit, IClassificationProblemData problemData, IEnumerable<int> rows) {
       IEnumerable<double> estimatedValues = interpreter.GetSymbolicExpressionTreeValues(solution, problemData.Dataset, rows);
-      IEnumerable<double> originalValues = problemData.Dataset.GetEnumeratedVariableValues(problemData.TargetVariable, rows);
+      IEnumerable<double> originalValues = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, rows);
       IEnumerable<double> boundedEstimationValues = estimatedValues.LimitToRange(lowerEstimationLimit, upperEstimationLimit);
       OnlineCalculatorError errorState;

branches/PersistenceSpeedUp/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SingleObjective/SymbolicClassificationSingleObjectiveOverfittingAnalyzer.cs

@@ -76 +76 @@
     public override IOperation Apply() {
       double[] trainingQuality = QualityParameter.ActualValue.Select(x => x.Value).ToArray();
+      var problemData = ProblemDataParameter.ActualValue;
+      var evaluator = EvaluatorParameter.ActualValue;
       // evaluate on validation partition
       IEnumerable<int> rows = GenerateRowsToEvaluate();
       if (!rows.Any()) return base.Apply();
-
-      IExecutionContext childContext = (IExecutionContext)ExecutionContext.CreateChildOperation(EvaluatorParameter.ActualValue);
-      double[] validationQuality = (from tree in SymbolicExpressionTree
-                                    select EvaluatorParameter.ActualValue.Evaluate(childContext, tree, ProblemDataParameter.ActualValue, rows))
-                                   .ToArray();
+      IExecutionContext childContext = (IExecutionContext)ExecutionContext.CreateChildOperation(evaluator);
+      double[] validationQuality = SymbolicExpressionTree
+        .AsParallel()
+        .Select(t => evaluator.Evaluate(childContext, t, problemData, rows))
+        .ToArray();
       double r = 0.0;
       try {

branches/PersistenceSpeedUp/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SingleObjective/SymbolicClassificationSingleObjectivePearsonRSquaredEvaluator.cs

@@ -54 +54 @@
     public static double Calculate(ISymbolicDataAnalysisExpressionTreeInterpreter interpreter, ISymbolicExpressionTree solution, double lowerEstimationLimit, double upperEstimationLimit, IClassificationProblemData problemData, IEnumerable<int> rows) {
       IEnumerable<double> estimatedValues = interpreter.GetSymbolicExpressionTreeValues(solution, problemData.Dataset, rows);
-      IEnumerable<double> originalValues = problemData.Dataset.GetEnumeratedVariableValues(problemData.TargetVariable, rows);
+      IEnumerable<double> originalValues = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, rows);
       OnlineCalculatorError errorState;
       double r2 = OnlinePearsonsRSquaredCalculator.Calculate(estimatedValues, originalValues, out errorState);

branches/PersistenceSpeedUp/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SingleObjective/SymbolicClassificationSingleObjectiveProblem.cs

@@ -72 +72 @@
 
     private void UpdateEstimationLimits() {
-      if (ProblemData.TrainingPartition.Start < ProblemData.TrainingPartition.End) {
-        var targetValues = ProblemData.Dataset.GetVariableValues(ProblemData.TargetVariable, ProblemData.TrainingPartition.Start, ProblemData.TrainingPartition.End);
+      if (ProblemData.TrainingIndizes.Any()) {
+        var targetValues = ProblemData.Dataset.GetDoubleValues(ProblemData.TargetVariable, ProblemData.TrainingIndizes).ToList();
         var mean = targetValues.Average();
         var range = targetValues.Max() - targetValues.Min();
         EstimationLimits.Upper = mean + PunishmentFactor * range;
         EstimationLimits.Lower = mean - PunishmentFactor * range;
+      } else {
+        EstimationLimits.Upper = double.MaxValue;
+        EstimationLimits.Lower = double.MinValue;
       }
     }

branches/PersistenceSpeedUp/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SymbolicClassificationModel.cs

@@ -21 +21 @@
 
 using System.Collections.Generic;
-using System.Linq;
 using HeuristicLab.Common;
 using HeuristicLab.Core;
-using HeuristicLab.Data;
 using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
-using HeuristicLab.Operators;
-using HeuristicLab.Parameters;
 using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
-using HeuristicLab.Optimization;
-using System;
 
 namespace HeuristicLab.Problems.DataAnalysis.Symbolic.Classification {
@@ -55 +49 @@
       return Interpreter.GetSymbolicExpressionTreeValues(SymbolicExpressionTree, dataset, rows);
     }
+
+    public ISymbolicClassificationSolution CreateClassificationSolution(IClassificationProblemData problemData) {
+      return new SymbolicClassificationSolution(this, problemData);
+    }
+    IClassificationSolution IClassificationModel.CreateClassificationSolution(IClassificationProblemData problemData) {
+      return CreateClassificationSolution(problemData);
+    }
+
+
   }
 }

branches/PersistenceSpeedUp/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SymbolicClassificationSolution.cs

@@ -20 +20 @@
 #endregion
 
-using System.Collections.Generic;
-using System.Linq;
 using HeuristicLab.Common;
 using HeuristicLab.Core;
 using HeuristicLab.Data;
-using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
-using HeuristicLab.Operators;
-using HeuristicLab.Parameters;
+using HeuristicLab.Optimization;
 using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
-using HeuristicLab.Optimization;
-using System;
 
 namespace HeuristicLab.Problems.DataAnalysis.Symbolic.Classification {
@@ -76 +70 @@
     }
 
-    protected override void OnModelChanged(EventArgs e) {
-      base.OnModelChanged(e);
-      RecalculateResults();
-    }
-
-    private new void RecalculateResults() {
+    protected override void RecalculateResults() {
       ModelLength = Model.SymbolicExpressionTree.Length;
       ModelDepth = Model.SymbolicExpressionTree.Depth;
+      CalculateResults();
     }
   }

branches/PersistenceSpeedUp/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SymbolicDiscriminantFunctionClassificationModel.cs

@@ -20 +20 @@
 #endregion
 
+using System;
 using System.Collections.Generic;
 using System.Linq;
 using HeuristicLab.Common;
 using HeuristicLab.Core;
-using HeuristicLab.Data;
 using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
-using HeuristicLab.Operators;
-using HeuristicLab.Parameters;
 using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
-using HeuristicLab.Optimization;
-using System;
 
 namespace HeuristicLab.Problems.DataAnalysis.Symbolic.Classification {
@@ -108 +104 @@
     }
 
+    public SymbolicDiscriminantFunctionClassificationSolution CreateClassificationSolution(IClassificationProblemData problemData) {
+      return new SymbolicDiscriminantFunctionClassificationSolution(this, problemData);
+    }
+    IClassificationSolution IClassificationModel.CreateClassificationSolution(IClassificationProblemData problemData) {
+      return CreateClassificationSolution(problemData);
+    }
+    IDiscriminantFunctionClassificationSolution IDiscriminantFunctionClassificationModel.CreateDiscriminantFunctionClassificationSolution(IClassificationProblemData problemData) {
+      return CreateClassificationSolution(problemData);
+    }
+
     #region events
     public event EventHandler ThresholdsChanged;
@@ -121 +127 @@
       var rows = problemData.TrainingIndizes;
       var estimatedValues = model.Interpreter.GetSymbolicExpressionTreeValues(model.SymbolicExpressionTree, dataset, rows);
-      var targetValues = dataset.GetEnumeratedVariableValues(targetVariable, rows);
+      var targetValues = dataset.GetDoubleValues(targetVariable, rows);
       double alpha;
       double beta;
@@ -150 +156 @@
         var mainBranch = startNode.GetSubtree(0);
         startNode.RemoveSubtree(0);
-        var scaledMainBranch = MakeSum(MakeProduct(beta, mainBranch), alpha);
+        var scaledMainBranch = MakeSum(MakeProduct(mainBranch, beta), alpha);
         startNode.AddSubtree(scaledMainBranch);
       }
@@ -159 +165 @@
         return treeNode;
       } else {
-        var node = (new Addition()).CreateTreeNode();
+        var addition = new Addition();
+        var node = addition.CreateTreeNode();
         var alphaConst = MakeConstant(alpha);
         node.AddSubtree(treeNode);
@@ -167 +174 @@
     }
 
-    private static ISymbolicExpressionTreeNode MakeProduct(double beta, ISymbolicExpressionTreeNode treeNode) {
+    private static ISymbolicExpressionTreeNode MakeProduct(ISymbolicExpressionTreeNode treeNode, double beta) {
       if (beta.IsAlmost(1.0)) {
         return treeNode;
       } else {
-        var node = (new Multiplication()).CreateTreeNode();
+        var multipliciation = new Multiplication();
+        var node = multipliciation.CreateTreeNode();
         var betaConst = MakeConstant(beta);
         node.AddSubtree(treeNode);

branches/PersistenceSpeedUp/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SymbolicDiscriminantFunctionClassificationSolution.cs

@@ -20 +20 @@
 #endregion
 
-using System;
 using HeuristicLab.Common;
 using HeuristicLab.Core;
@@ -74 +73 @@
     }
 
-    protected override void OnModelChanged(EventArgs e) {
-      base.OnModelChanged(e);
-      RecalculateResults();
-    }
-
-    private new void RecalculateResults() {
+    protected override void RecalculateResults() {
+      CalculateResults();
+      CalculateRegressionResults();
       ModelLength = Model.SymbolicExpressionTree.Length;
       ModelDepth = Model.SymbolicExpressionTree.Depth;
     }
+
   }
 }

@@ -12 +12 @@
 *.psess
 *.vsp
+*.docstates