Changeset 5197

Timestamp:

01/03/11 14:48:11 (14 years ago)

Author:

gkronber

Message:

Introduced base class for operators that evaluate symbolic regression models on a validation set. #1356

Location:

trunk/sources/HeuristicLab.Problems.DataAnalysis.Regression/3.3

Files:

• HeuristicLab.Problems.DataAnalysis.Regression-3.3.csproj (modified) (1 diff)
• Symbolic/Analyzers/SymbolicRegressionOverfittingAnalyzer.cs (modified) (6 diffs)
• Symbolic/Analyzers/SymbolicRegressionValidationAnalyzer.cs (added)

trunk/sources/HeuristicLab.Problems.DataAnalysis.Regression/3.3/HeuristicLab.Problems.DataAnalysis.Regression-3.3.csproj

@@ -121 +121 @@
     <Compile Include="SupportVectorRegression\SupportVectorRegressionSolution.cs" />
     <Compile Include="Symbolic\Analyzers\BestSymbolicRegressionSolutionAnalyzer.cs" />
+    <Compile Include="Symbolic\Analyzers\SymbolicRegressionValidationAnalyzer.cs" />
     <Compile Include="Symbolic\Analyzers\FixedValidationBestScaledSymbolicRegressionSolutionAnalyzer.cs" />
     <Compile Include="Symbolic\Analyzers\ISymbolicRegressionAnalyzer.cs" />

trunk/sources/HeuristicLab.Problems.DataAnalysis.Regression/3.3/Symbolic/Analyzers/SymbolicRegressionOverfittingAnalyzer.cs

@@ -38 +38 @@
   [Item("SymbolicRegressionOverfittingAnalyzer", "Calculates and tracks correlation of training and validation fitness of symbolic regression models.")]
   [StorableClass]
-  public sealed class SymbolicRegressionOverfittingAnalyzer : SingleSuccessorOperator, ISymbolicRegressionAnalyzer {
-    private const string RandomParameterName = "Random";
-    private const string SymbolicExpressionTreeParameterName = "SymbolicExpressionTree";
+  public sealed class SymbolicRegressionOverfittingAnalyzer : SymbolicRegressionValidationAnalyzer, ISymbolicRegressionAnalyzer {
     private const string MaximizationParameterName = "Maximization";
     private const string QualityParameterName = "Quality";
-    private const string ValidationQualityParameterName = "ValidationQuality";
     private const string TrainingValidationCorrelationParameterName = "TrainingValidationCorrelation";
     private const string TrainingValidationCorrelationTableParameterName = "TrainingValidationCorrelationTable";
@@ -50 +47 @@
     private const string OverfittingParameterName = "IsOverfitting";
     private const string ResultsParameterName = "Results";
-    private const string EvaluatorParameterName = "Evaluator";
-    private const string SymbolicExpressionTreeInterpreterParameterName = "SymbolicExpressionTreeInterpreter";
-    private const string ProblemDataParameterName = "ProblemData";
-    private const string ValidationSamplesStartParameterName = "ValidationSamplesStart";
-    private const string ValidationSamplesEndParameterName = "ValidationSamplesEnd";
-    private const string RelativeNumberOfEvaluatedSamplesParameterName = "RelativeNumberOfEvaluatedSamples";
-    private const string UpperEstimationLimitParameterName = "UpperEstimationLimit";
-    private const string LowerEstimationLimitParameterName = "LowerEstimationLimit";
 
     #region parameter properties
-    public ILookupParameter<IRandom> RandomParameter {
-      get { return (ILookupParameter<IRandom>)Parameters[RandomParameterName]; }
-    }
-    public ScopeTreeLookupParameter<SymbolicExpressionTree> SymbolicExpressionTreeParameter {
-      get { return (ScopeTreeLookupParameter<SymbolicExpressionTree>)Parameters[SymbolicExpressionTreeParameterName]; }
-    }
     public ScopeTreeLookupParameter<DoubleValue> QualityParameter {
       get { return (ScopeTreeLookupParameter<DoubleValue>)Parameters[QualityParameterName]; }
     }
-    public ScopeTreeLookupParameter<DoubleValue> ValidationQualityParameter {
-      get { return (ScopeTreeLookupParameter<DoubleValue>)Parameters[ValidationQualityParameterName]; }
-    }
     public ILookupParameter<BoolValue> MaximizationParameter {
       get { return (ILookupParameter<BoolValue>)Parameters[MaximizationParameterName]; }
-    }
-    public IValueLookupParameter<ISymbolicExpressionTreeInterpreter> SymbolicExpressionTreeInterpreterParameter {
-      get { return (IValueLookupParameter<ISymbolicExpressionTreeInterpreter>)Parameters[SymbolicExpressionTreeInterpreterParameterName]; }
-    }
-    public ILookupParameter<ISymbolicRegressionEvaluator> EvaluatorParameter {
-      get { return (ILookupParameter<ISymbolicRegressionEvaluator>)Parameters[EvaluatorParameterName]; }
-    }
-    public IValueLookupParameter<DataAnalysisProblemData> ProblemDataParameter {
-      get { return (IValueLookupParameter<DataAnalysisProblemData>)Parameters[ProblemDataParameterName]; }
-    }
-    public IValueLookupParameter<IntValue> ValidationSamplesStartParameter {
-      get { return (IValueLookupParameter<IntValue>)Parameters[ValidationSamplesStartParameterName]; }
-    }
-    public IValueLookupParameter<IntValue> ValidationSamplesEndParameter {
-      get { return (IValueLookupParameter<IntValue>)Parameters[ValidationSamplesEndParameterName]; }
-    }
-    public IValueParameter<PercentValue> RelativeNumberOfEvaluatedSamplesParameter {
-      get { return (IValueParameter<PercentValue>)Parameters[RelativeNumberOfEvaluatedSamplesParameterName]; }
-    }
-    public IValueLookupParameter<DoubleValue> UpperEstimationLimitParameter {
-      get { return (IValueLookupParameter<DoubleValue>)Parameters[UpperEstimationLimitParameterName]; }
-    }
-    public IValueLookupParameter<DoubleValue> LowerEstimationLimitParameter {
-      get { return (IValueLookupParameter<DoubleValue>)Parameters[LowerEstimationLimitParameterName]; }
     }
     public ILookupParameter<DoubleValue> TrainingValidationQualityCorrelationParameter {
@@ -119 +75 @@
     #endregion
     #region properties
-    public IRandom Random {
-      get { return RandomParameter.ActualValue; }
-    }
     public BoolValue Maximization {
       get { return MaximizationParameter.ActualValue; }
-    }
-    public ISymbolicExpressionTreeInterpreter SymbolicExpressionTreeInterpreter {
-      get { return SymbolicExpressionTreeInterpreterParameter.ActualValue; }
-    }
-    public ISymbolicRegressionEvaluator Evaluator {
-      get { return EvaluatorParameter.ActualValue; }
-    }
-    public DataAnalysisProblemData ProblemData {
-      get { return ProblemDataParameter.ActualValue; }
-    }
-    public IntValue ValidiationSamplesStart {
-      get { return ValidationSamplesStartParameter.ActualValue; }
-    }
-    public IntValue ValidationSamplesEnd {
-      get { return ValidationSamplesEndParameter.ActualValue; }
-    }
-    public PercentValue RelativeNumberOfEvaluatedSamples {
-      get { return RelativeNumberOfEvaluatedSamplesParameter.Value; }
-    }
-
-    public DoubleValue UpperEstimationLimit {
-      get { return UpperEstimationLimitParameter.ActualValue; }
-    }
-    public DoubleValue LowerEstimationLimit {
-      get { return LowerEstimationLimitParameter.ActualValue; }
     }
     #endregion
@@ -157 +85 @@
     public SymbolicRegressionOverfittingAnalyzer()
       : base() {
-      Parameters.Add(new LookupParameter<IRandom>(RandomParameterName, "The random generator to use.")); 
       Parameters.Add(new ScopeTreeLookupParameter<DoubleValue>(QualityParameterName, "Training fitness"));
       Parameters.Add(new LookupParameter<BoolValue>(MaximizationParameterName, "The direction of optimization."));
-
-      Parameters.Add(new ScopeTreeLookupParameter<SymbolicExpressionTree>(SymbolicExpressionTreeParameterName, "The symbolic expression trees to analyze."));
-      Parameters.Add(new LookupParameter<ISymbolicRegressionEvaluator>(EvaluatorParameterName, "The evaluator which should be used to evaluate the solution on the validation set."));
-      Parameters.Add(new ValueLookupParameter<ISymbolicExpressionTreeInterpreter>(SymbolicExpressionTreeInterpreterParameterName, "The interpreter that should be used for the analysis of symbolic expression trees."));
-      Parameters.Add(new ValueLookupParameter<DataAnalysisProblemData>(ProblemDataParameterName, "The problem data for which the symbolic expression tree is a solution."));
-      Parameters.Add(new ValueLookupParameter<IntValue>(ValidationSamplesStartParameterName, "The first index of the validation partition of the data set."));
-      Parameters.Add(new ValueLookupParameter<IntValue>(ValidationSamplesEndParameterName, "The last index of the validation partition of the data set."));
-      Parameters.Add(new ValueParameter<PercentValue>(RelativeNumberOfEvaluatedSamplesParameterName, "The relative number of samples of the dataset partition, which should be randomly chosen for evaluation between the start and end index.", new PercentValue(1)));
-      Parameters.Add(new ValueLookupParameter<DoubleValue>(UpperEstimationLimitParameterName, "The upper estimation limit that was set for the evaluation of the symbolic expression trees."));
-      Parameters.Add(new ValueLookupParameter<DoubleValue>(LowerEstimationLimitParameterName, "The lower estimation limit that was set for the evaluation of the symbolic expression trees."));
-
       Parameters.Add(new LookupParameter<DoubleValue>(TrainingValidationCorrelationParameterName, "Correlation of training and validation fitnesses"));
       Parameters.Add(new LookupParameter<DataTable>(TrainingValidationCorrelationTableParameterName, "Data table of training and validation fitness correlation values over the whole run."));
@@ -187 +103 @@
     }
 
-    public override IOperation Apply() {
-      ItemArray<DoubleValue> qualities = QualityParameter.ActualValue;
-      double[] trainingArr = qualities.Select(x => x.Value).ToArray();
-      double[] validationArr = new double[trainingArr.Length];
+    protected override void Analyze(SymbolicExpressionTree[] trees, double[] validationQuality) {
+      double[] trainingQuality = QualityParameter.ActualValue.Select(x => x.Value).ToArray();
 
-      #region calculate validation fitness
-      string targetVariable = ProblemData.TargetVariable.Value;
-
-      // select a random subset of rows in the validation set
-      int validationStart = ValidiationSamplesStart.Value;
-      int validationEnd = ValidationSamplesEnd.Value;
-      int seed = Random.Next();
-      int count = (int)((validationEnd - validationStart) * RelativeNumberOfEvaluatedSamples.Value);
-      if (count == 0) count = 1;
-      IEnumerable<int> rows = RandomEnumerable.SampleRandomNumbers(seed, validationStart, validationEnd, count)
-        .Where(row => row < ProblemData.TestSamplesStart.Value || ProblemData.TestSamplesEnd.Value <= row);
-
-      double upperEstimationLimit = UpperEstimationLimit != null ? UpperEstimationLimit.Value : double.PositiveInfinity;
-      double lowerEstimationLimit = LowerEstimationLimit != null ? LowerEstimationLimit.Value : double.NegativeInfinity;
-
-      var trees = SymbolicExpressionTreeParameter.ActualValue;
-
-      for (int i = 0; i < validationArr.Length; i++) {
-        var tree = trees[i];
-        double quality = Evaluator.Evaluate(SymbolicExpressionTreeInterpreter, tree,
-            lowerEstimationLimit, upperEstimationLimit,
-            ProblemData.Dataset, targetVariable,
-           rows);
-        validationArr[i] = quality;
-      }
-      
-      #endregion
-
-
-      double r = alglib.spearmancorr2(trainingArr, validationArr);
+      double r = alglib.spearmancorr2(trainingQuality, validationQuality);
 
       TrainingValidationQualityCorrelationParameter.ActualValue = new DoubleValue(r);
@@ -245 +130 @@
 
       OverfittingParameter.ActualValue = new BoolValue(overfitting);
-
-      return base.Apply();
     }
   }