Changeset 13948 for branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis

Timestamp:

06/29/16 10:36:52 (8 years ago)

Author:

pfleck

Message:

#2597

• Merged recent trunk changes.
• Adapted VariablesUsedForPrediction property for RegressionSolutionTargetResponseGradientView.
• Fixed a reference (.dll to project ref).

Location:

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis

Files:

• . (modified) (1 prop)
• 3.4/BaselineClassifiers/OneR.cs (modified) (1 diff)
• 3.4/BaselineClassifiers/OneRClassificationModel.cs (modified) (4 diffs)
• 3.4/GBM/GradientBoostingRegressionAlgorithm.cs (modified) (14 diffs)
• 3.4/GaussianProcess/CovarianceFunctions/CovarianceProduct.cs (modified) (1 diff)
• 3.4/GaussianProcess/CovarianceFunctions/CovarianceSum.cs (modified) (1 diff)
• 3.4/GaussianProcess/GaussianProcessModel.cs (modified) (7 diffs)
• 3.4/GaussianProcess/StudentTProcessModel.cs (modified) (6 diffs)
• 3.4/GradientBoostedTrees/GradientBoostedTreesModel.cs (modified) (5 diffs)
• 3.4/GradientBoostedTrees/GradientBoostedTreesModelSurrogate.cs (modified) (6 diffs)
• 3.4/GradientBoostedTrees/RegressionTreeBuilder.cs (modified) (2 diffs)
• 3.4/GradientBoostedTrees/RegressionTreeModel.cs (modified) (11 diffs)
• 3.4/Linear/LinearDiscriminantAnalysis.cs (modified) (1 diff)
• 3.4/Linear/LinearRegression.cs (modified) (1 diff)
• 3.4/Linear/MultinomialLogitClassification.cs (modified) (1 diff)
• 3.4/Linear/MultinomialLogitClassificationSolution.cs (modified) (1 diff)
• 3.4/Linear/MultinomialLogitModel.cs (modified) (6 diffs)
• 3.4/MctsSymbolicRegression/MctsSymbolicRegressionStatic.cs (modified) (2 diffs)
• 3.4/Nca/NcaClassificationSolution.cs (modified) (1 diff)
• 3.4/Nca/NcaModel.cs (modified) (6 diffs)
• 3.4/NearestNeighbour/NearestNeighbourClassification.cs (modified) (1 diff)
• 3.4/NearestNeighbour/NearestNeighbourClassificationSolution.cs (modified) (1 diff)
• 3.4/NearestNeighbour/NearestNeighbourModel.cs (modified) (5 diffs)
• 3.4/NearestNeighbour/NearestNeighbourRegression.cs (modified) (1 diff)
• 3.4/NearestNeighbour/NearestNeighbourRegressionSolution.cs (modified) (1 diff)
• 3.4/NeuralNetwork/NeuralNetworkClassification.cs (modified) (1 diff)
• 3.4/NeuralNetwork/NeuralNetworkClassificationSolution.cs (modified) (1 diff)
• 3.4/NeuralNetwork/NeuralNetworkEnsembleClassification.cs (modified) (1 diff)
• 3.4/NeuralNetwork/NeuralNetworkEnsembleClassificationSolution.cs (modified) (1 diff)
• 3.4/NeuralNetwork/NeuralNetworkEnsembleModel.cs (modified) (5 diffs)
• 3.4/NeuralNetwork/NeuralNetworkEnsembleRegression.cs (modified) (1 diff)
• 3.4/NeuralNetwork/NeuralNetworkEnsembleRegressionSolution.cs (modified) (1 diff)
• 3.4/NeuralNetwork/NeuralNetworkModel.cs (modified) (6 diffs)
• 3.4/NeuralNetwork/NeuralNetworkRegression.cs (modified) (1 diff)
• 3.4/NeuralNetwork/NeuralNetworkRegressionSolution.cs (modified) (1 diff)
• 3.4/RandomForest/RandomForestClassification.cs (modified) (1 diff)
• 3.4/RandomForest/RandomForestClassificationSolution.cs (modified) (1 diff)
• 3.4/RandomForest/RandomForestModel.cs (modified) (7 diffs)
• 3.4/RandomForest/RandomForestRegression.cs (modified) (2 diffs)
• 3.4/RandomForest/RandomForestRegressionSolution.cs (modified) (1 diff)
• 3.4/SupportVectorMachine/SupportVectorMachineModel.cs (modified) (6 diffs)
• 3.4/TimeSeries/AutoregressiveModeling.cs (modified) (1 diff)
• 3.4/kMeans/KMeansClusteringModel.cs (modified) (1 diff)

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/BaselineClassifiers/OneR.cs

@@ -139 +139 @@
       }
 
-      var model = new OneRClassificationModel(bestVariable, bestSplits.Select(s => s.thresholdValue).ToArray(), bestSplits.Select(s => s.classValue).ToArray(), bestMissingValuesClass);
+      var model = new OneRClassificationModel(problemData.TargetVariable, bestVariable, bestSplits.Select(s => s.thresholdValue).ToArray(), bestSplits.Select(s => s.classValue).ToArray(), bestMissingValuesClass);
       var solution = new OneRClassificationSolution(model, (IClassificationProblemData)problemData.Clone());
 

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/BaselineClassifiers/OneRClassificationModel.cs

@@ -31 +31 @@
   [StorableClass]
   [Item("OneR Classification Model", "A model that uses intervals for one variable to determine the class.")]
-  public class OneRClassificationModel : NamedItem, IClassificationModel {
+  public class OneRClassificationModel : ClassificationModel {
+    public override IEnumerable<string> VariablesUsedForPrediction {
+      get { return new[] { Variable }; }
+    }
+
     [Storable]
     protected string variable;
@@ -66 +70 @@
     public override IDeepCloneable Clone(Cloner cloner) { return new OneRClassificationModel(this, cloner); }
 
-    public OneRClassificationModel(string variable, double[] splits, double[] classes, double missingValuesClass = double.NaN)
-      : base() {
+    public OneRClassificationModel(string targetVariable, string variable, double[] splits, double[] classes, double missingValuesClass = double.NaN)
+      : base(targetVariable) {
       if (splits.Length != classes.Length) {
         throw new ArgumentException("Number of splits and classes has to be equal.");
@@ -84 +88 @@
     // uses sorting to return the values in the order of rows, instead of using nested for loops
     // to avoid O(n²) runtime
-    public IEnumerable<double> GetEstimatedClassValues(IDataset dataset, IEnumerable<int> rows) {
+    public override IEnumerable<double> GetEstimatedClassValues(IDataset dataset, IEnumerable<int> rows) {
       var values = dataset.GetDoubleValues(Variable, rows).ToArray();
       var rowsArray = rows.ToArray();
@@ -108 +112 @@
     }
 
-    public IClassificationSolution CreateClassificationSolution(IClassificationProblemData problemData) {
+    public override IClassificationSolution CreateClassificationSolution(IClassificationProblemData problemData) {
       return new OneRClassificationSolution(this, new ClassificationProblemData(problemData));
     }

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/GBM/GradientBoostingRegressionAlgorithm.cs

@@ -64 +64 @@
     private const string SetSeedRandomlyParameterName = "SetSeedRandomly";
     private const string CreateSolutionParameterName = "CreateSolution";
+    private const string StoreRunsParameterName = "StoreRuns";
     private const string RegressionAlgorithmSolutionResultParameterName = "RegressionAlgorithmResult";
 
@@ -106 +107 @@
       get { return (IFixedValueParameter<BoolValue>)Parameters[CreateSolutionParameterName]; }
     }
+    public IFixedValueParameter<BoolValue> StoreRunsParameter {
+      get { return (IFixedValueParameter<BoolValue>)Parameters[StoreRunsParameterName]; }
+    }
 
     #endregion
@@ -144 +148 @@
       get { return CreateSolutionParameter.Value.Value; }
       set { CreateSolutionParameter.Value.Value = value; }
+    }
+
+    public bool StoreRuns {
+      get { return StoreRunsParameter.Value.Value; }
+      set { StoreRunsParameter.Value.Value = value; }
     }
 
@@ -178 +187 @@
       var regressionAlgs = new ItemSet<IAlgorithm>(new IAlgorithm[] {
         new RandomForestRegression(),
-        sgp, 
+        sgp,
         mctsSymbReg
       });
@@ -206 +215 @@
         "Flag that indicates if a solution should be produced at the end of the run", new BoolValue(true)));
       Parameters[CreateSolutionParameterName].Hidden = true;
+      Parameters.Add(new FixedValueParameter<BoolValue>(StoreRunsParameterName,
+        "Flag that indicates if the results of the individual runs should be stored for detailed analysis", new BoolValue(false)));
+      Parameters[StoreRunsParameterName].Hidden = true;
     }
 
@@ -218 +230 @@
 
       var table = new DataTable("Qualities");
-      table.Rows.Add(new DataRow("Loss (train)"));
-      table.Rows.Add(new DataRow("Loss (test)"));
+      table.Rows.Add(new DataRow("R² (train)"));
+      table.Rows.Add(new DataRow("R² (test)"));
       Results.Add(new Result("Qualities", table));
       var curLoss = new DoubleValue();
       var curTestLoss = new DoubleValue();
-      Results.Add(new Result("Loss (train)", curLoss));
-      Results.Add(new Result("Loss (test)", curTestLoss));
+      Results.Add(new Result("R² (train)", curLoss));
+      Results.Add(new Result("R² (test)", curTestLoss));
       var runCollection = new RunCollection();
-      Results.Add(new Result("Runs", runCollection));
+      if (StoreRuns)
+        Results.Add(new Result("Runs", runCollection));
 
       // init
       var problemData = Problem.ProblemData;
-      var targetVarName = Problem.ProblemData.TargetVariable;
+      var targetVarName = problemData.TargetVariable;
       var activeVariables = problemData.AllowedInputVariables.Concat(new string[] { problemData.TargetVariable });
       var modifiableDataset = new ModifiableDataset(
@@ -273 +286 @@
           IRegressionModel model;
           IRun run;
+
           // try to find a model. The algorithm might fail to produce a model. In this case we just retry until the iterations are exhausted
-          if (TryExecute(alg, RegressionAlgorithmResult, out model, out run)) {
+          if (TryExecute(alg, rand.Next(), RegressionAlgorithmResult, out model, out run)) {
             int row = 0;
             // update predictions for training and test
@@ -303 +317 @@
           }
 
-          runCollection.Add(run);
-          table.Rows["Loss (train)"].Values.Add(curLoss.Value);
-          table.Rows["Loss (test)"].Values.Add(curTestLoss.Value);
+          if (StoreRuns)
+            runCollection.Add(run);
+          table.Rows["R² (train)"].Values.Add(curLoss.Value);
+          table.Rows["R² (test)"].Values.Add(curTestLoss.Value);
           iterations.Value = i + 1;
         }
@@ -317 +332 @@
           // just produce an ensemble solution for now (TODO: correct scaling or linear regression for ensemble model weights)
 
-          var ensembleModel = new RegressionEnsembleModel(models) { AverageModelEstimates = false };
-          var ensembleSolution = ensembleModel.CreateRegressionSolution((IRegressionProblemData)problemData.Clone());
+          var ensembleSolution = CreateEnsembleSolution(models, (IRegressionProblemData)problemData.Clone());
           Results.Add(new Result("EnsembleSolution", ensembleSolution));
         }
@@ -326 +340 @@
         alg.Prepare(true);
       }
+    }
+
+    private static IRegressionEnsembleSolution CreateEnsembleSolution(List<IRegressionModel> models,
+      IRegressionProblemData problemData) {
+      var rows = problemData.TrainingPartition.Size;
+      var features = models.Count;
+      double[,] inputMatrix = new double[rows, features + 1];
+      //add model estimates
+      for (int m = 0; m < models.Count; m++) {
+        var model = models[m];
+        var estimates = model.GetEstimatedValues(problemData.Dataset, problemData.TrainingIndices);
+        int estimatesCounter = 0;
+        foreach (var estimate in estimates) {
+          inputMatrix[estimatesCounter, m] = estimate;
+          estimatesCounter++;
+        }
+      }
+
+      //add target
+      var targets = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, problemData.TrainingIndices);
+      int targetCounter = 0;
+      foreach (var target in targets) {
+        inputMatrix[targetCounter, models.Count] = target;
+        targetCounter++;
+      }
+
+      alglib.linearmodel lm = new alglib.linearmodel();
+      alglib.lrreport ar = new alglib.lrreport();
+      double[] coefficients;
+      int retVal = 1;
+      alglib.lrbuildz(inputMatrix, rows, features, out retVal, out lm, out ar);
+      if (retVal != 1) throw new ArgumentException("Error in calculation of linear regression solution");
+
+      alglib.lrunpack(lm, out coefficients, out features);
+
+      var ensembleModel = new RegressionEnsembleModel(models, coefficients.Take(models.Count)) { AverageModelEstimates = false };
+      var ensembleSolution = (IRegressionEnsembleSolution)ensembleModel.CreateRegressionSolution(problemData);
+      return ensembleSolution;
     }
 
@@ -391 +443 @@
       progRootNode.AddSubtree(startNode);
       var t = new SymbolicExpressionTree(progRootNode);
-      var combinedModel = new SymbolicRegressionModel(t, interpreter, lowerLimit, upperLimit);
+      var combinedModel = new SymbolicRegressionModel(problemData.TargetVariable, t, interpreter, lowerLimit, upperLimit);
       var sol = new SymbolicRegressionSolution(combinedModel, problemData);
       return sol;
@@ -405 +457 @@
     }
 
-    private static bool TryExecute(IAlgorithm alg, string regressionAlgorithmResultName, out IRegressionModel model, out IRun run) {
+    private static bool TryExecute(IAlgorithm alg, int seed, string regressionAlgorithmResultName, out IRegressionModel model, out IRun run) {
       model = null;
+      SetSeed(alg, seed);
       using (var wh = new AutoResetEvent(false)) {
-        EventHandler<EventArgs<Exception>> handler = (sender, args) => wh.Set();
+        Exception ex = null;
+        EventHandler<EventArgs<Exception>> handler = (sender, args) => {
+          ex = args.Value;
+          wh.Set();
+        };
         EventHandler handler2 = (sender, args) => wh.Set();
         alg.ExceptionOccurred += handler;
@@ -417 +474 @@
           wh.WaitOne();
 
+          if (ex != null) throw new AggregateException(ex);
           run = alg.Runs.Last();
+          alg.Runs.Clear();
           var sols = alg.Results.Select(r => r.Value).OfType<IRegressionSolution>();
           if (!sols.Any()) return false;
@@ -444 +503 @@
       return model != null;
     }
+
+    private static void SetSeed(IAlgorithm alg, int seed) {
+      // no common interface for algs that use a PRNG -> use naming convention to set seed
+      var paramItem = alg as IParameterizedItem;
+
+      if (paramItem.Parameters.ContainsKey("SetSeedRandomly")) {
+        ((BoolValue)paramItem.Parameters["SetSeedRandomly"].ActualValue).Value = false;
+        ((IntValue)paramItem.Parameters["Seed"].ActualValue).Value = seed;
+      } else {
+        throw new ArgumentException("Base learner does not have a seed parameter (algorithm {0})", alg.Name);
+      }
+
+    }
   }
 }

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/GaussianProcess/CovarianceFunctions/CovarianceProduct.cs

@@ -94 +94 @@
     public static IList<double> GetGradient(double[,] x, int i, int j, List<ParameterizedCovarianceFunction> factorFunctions) {
       var covariances = factorFunctions.Select(f => f.Covariance(x, i, j)).ToArray();
-      var gr = new List<double>(factorFunctions.Sum(f => f.CovarianceGradient(x, i, j).Count));
+      var gr = new List<double>();
       for (int ii = 0; ii < factorFunctions.Count; ii++) {
         foreach (var g in factorFunctions[ii].CovarianceGradient(x, i, j)) {

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/GaussianProcess/CovarianceFunctions/CovarianceSum.cs

@@ -88 +88 @@
       sum.CrossCovariance = (x, xt, i, j) => functions.Select(e => e.CrossCovariance(x, xt, i, j)).Sum();
       sum.CovarianceGradient = (x, i, j) => {
-        var g = new List<double>(functions.Sum(e => e.CovarianceGradient(x, i, j).Count));
+        var g = new List<double>();
         foreach (var e in functions)
           g.AddRange(e.CovarianceGradient(x, i, j));

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/GaussianProcess/GaussianProcessModel.cs

@@ -34 +34 @@
   [StorableClass]
   [Item("GaussianProcessModel", "Represents a Gaussian process posterior.")]
-  public sealed class GaussianProcessModel : NamedItem, IGaussianProcessModel {
+  public sealed class GaussianProcessModel : RegressionModel, IGaussianProcessModel {
+    public override IEnumerable<string> VariablesUsedForPrediction {
+      get { return allowedInputVariables; }
+    }
+
     [Storable]
     private double negativeLogLikelihood;
@@ -61 +65 @@
       get { return meanFunction; }
     }
-    [Storable]
-    private string targetVariable;
-    public string TargetVariable {
-      get { return targetVariable; }
-    }
+
     [Storable]
     private string[] allowedInputVariables;
@@ -128 +128 @@
       this.trainingDataset = cloner.Clone(original.trainingDataset);
       this.negativeLogLikelihood = original.negativeLogLikelihood;
-      this.targetVariable = original.targetVariable;
       this.sqrSigmaNoise = original.sqrSigmaNoise;
       if (original.meanParameter != null) {
@@ -147 +146 @@
       IEnumerable<double> hyp, IMeanFunction meanFunction, ICovarianceFunction covarianceFunction,
       bool scaleInputs = true)
-      : base() {
+      : base(targetVariable) {
       this.name = ItemName;
       this.description = ItemDescription;
       this.meanFunction = (IMeanFunction)meanFunction.Clone();
       this.covarianceFunction = (ICovarianceFunction)covarianceFunction.Clone();
-      this.targetVariable = targetVariable;
       this.allowedInputVariables = allowedInputVariables.ToArray();
 
@@ -182 +180 @@
 
       IEnumerable<double> y;
-      y = ds.GetDoubleValues(targetVariable, rows);
+      y = ds.GetDoubleValues(TargetVariable, rows);
 
       int n = x.GetLength(0);
@@ -301 +299 @@
 
     #region IRegressionModel Members
-    public IEnumerable<double> GetEstimatedValues(IDataset dataset, IEnumerable<int> rows) {
+    public override IEnumerable<double> GetEstimatedValues(IDataset dataset, IEnumerable<int> rows) {
       return GetEstimatedValuesHelper(dataset, rows);
     }
-    public GaussianProcessRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData) {
+    public override IRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData) {
       return new GaussianProcessRegressionSolution(this, new RegressionProblemData(problemData));
-    }
-    IRegressionSolution IRegressionModel.CreateRegressionSolution(IRegressionProblemData problemData) {
-      return CreateRegressionSolution(problemData);
     }
     #endregion
@@ -392 +387 @@
       }
     }
+
   }
 }

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/GaussianProcess/StudentTProcessModel.cs

@@ -34 +34 @@
   [StorableClass]
   [Item("StudentTProcessModel", "Represents a Student-t process posterior.")]
-  public sealed class StudentTProcessModel : NamedItem, IGaussianProcessModel {
+  public sealed class StudentTProcessModel : RegressionModel, IGaussianProcessModel {
+    public override IEnumerable<string> VariablesUsedForPrediction {
+      get { return allowedInputVariables; }
+    }
+
     [Storable]
     private double negativeLogLikelihood;
@@ -61 +65 @@
       get { return meanFunction; }
     }
-    [Storable]
-    private string targetVariable;
-    public string TargetVariable {
-      get { return targetVariable; }
-    }
+
     [Storable]
     private string[] allowedInputVariables;
@@ -131 +131 @@
       this.trainingDataset = cloner.Clone(original.trainingDataset);
       this.negativeLogLikelihood = original.negativeLogLikelihood;
-      this.targetVariable = original.targetVariable;
       if (original.meanParameter != null) {
         this.meanParameter = (double[])original.meanParameter.Clone();
@@ -151 +150 @@
       IEnumerable<double> hyp, IMeanFunction meanFunction, ICovarianceFunction covarianceFunction,
       bool scaleInputs = true)
-      : base() {
+      : base(targetVariable) {
       this.name = ItemName;
       this.description = ItemDescription;
       this.meanFunction = (IMeanFunction)meanFunction.Clone();
       this.covarianceFunction = (ICovarianceFunction)covarianceFunction.Clone();
-      this.targetVariable = targetVariable;
       this.allowedInputVariables = allowedInputVariables.ToArray();
 
@@ -186 +184 @@
 
       IEnumerable<double> y;
-      y = ds.GetDoubleValues(targetVariable, rows);
+      y = ds.GetDoubleValues(TargetVariable, rows);
 
       int n = x.GetLength(0);
@@ -318 +316 @@
 
     #region IRegressionModel Members
-    public IEnumerable<double> GetEstimatedValues(IDataset dataset, IEnumerable<int> rows) {
+    public override IEnumerable<double> GetEstimatedValues(IDataset dataset, IEnumerable<int> rows) {
       return GetEstimatedValuesHelper(dataset, rows);
     }
-    public GaussianProcessRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData) {
+    public override IRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData) {
       return new GaussianProcessRegressionSolution(this, new RegressionProblemData(problemData));
-    }
-    IRegressionSolution IRegressionModel.CreateRegressionSolution(IRegressionProblemData problemData) {
-      return CreateRegressionSolution(problemData);
     }
     #endregion

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/GradientBoostedTreesModel.cs

@@ -33 +33 @@
   [Item("Gradient boosted tree model", "")]
   // this is essentially a collection of weighted regression models
-  public sealed class GradientBoostedTreesModel : NamedItem, IGradientBoostedTreesModel {
+  public sealed class GradientBoostedTreesModel : RegressionModel, IGradientBoostedTreesModel {
     // BackwardsCompatibility3.4 for allowing deserialization & serialization of old models
     #region Backwards compatible code, remove with 3.5
@@ -58 +58 @@
     #endregion
 
+    public override IEnumerable<string> VariablesUsedForPrediction {
+      get { return models.SelectMany(x => x.VariablesUsedForPrediction).Distinct().OrderBy(x => x); }
+    }
+
     private readonly IList<IRegressionModel> models;
     public IEnumerable<IRegressionModel> Models { get { return models; } }
@@ -77 +81 @@
     }
     [Obsolete("The constructor of GBTModel should not be used directly anymore (use GBTModelSurrogate instead)")]
-    public GradientBoostedTreesModel(IEnumerable<IRegressionModel> models, IEnumerable<double> weights)
-      : base("Gradient boosted tree model", string.Empty) {
+    internal GradientBoostedTreesModel(IEnumerable<IRegressionModel> models, IEnumerable<double> weights)
+      : base(string.Empty, "Gradient boosted tree model", string.Empty) {
       this.models = new List<IRegressionModel>(models);
       this.weights = new List<double>(weights);
@@ -89 +93 @@
     }
 
-    public IEnumerable<double> GetEstimatedValues(IDataset dataset, IEnumerable<int> rows) {
+    public override IEnumerable<double> GetEstimatedValues(IDataset dataset, IEnumerable<int> rows) {
       // allocate target array go over all models and add up weighted estimation for each row
       if (!rows.Any()) return Enumerable.Empty<double>(); // return immediately if rows is empty. This prevents multiple iteration over lazy rows enumerable.
@@ -105 +109 @@
     }
 
-    public IRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData) {
+    public override IRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData) {
       return new RegressionSolution(this, (IRegressionProblemData)problemData.Clone());
     }
+
   }
 }

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/GradientBoostedTreesModelSurrogate.cs

@@ -22 +22 @@
 
 using System.Collections.Generic;
+using System.Linq;
 using HeuristicLab.Common;
 using HeuristicLab.Core;
@@ -33 +34 @@
   // recalculate the actual GBT model on demand
   [Item("Gradient boosted tree model", "")]
-  public sealed class GradientBoostedTreesModelSurrogate : NamedItem, IGradientBoostedTreesModel {
+  public sealed class GradientBoostedTreesModelSurrogate : RegressionModel, IGradientBoostedTreesModel {
     // don't store the actual model!
     private IGradientBoostedTreesModel actualModel; // the actual model is only recalculated when necessary
@@ -55 +56 @@
 
 
+    public override IEnumerable<string> VariablesUsedForPrediction {
+      get { return actualModel.Models.SelectMany(x => x.VariablesUsedForPrediction).Distinct().OrderBy(x => x); }
+    }
+
     [StorableConstructor]
     private GradientBoostedTreesModelSurrogate(bool deserializing) : base(deserializing) { }
@@ -73 +78 @@
 
     // create only the surrogate model without an actual model
-    public GradientBoostedTreesModelSurrogate(IRegressionProblemData trainingProblemData, uint seed, ILossFunction lossFunction, int iterations, int maxSize, double r, double m, double nu)
-      : base("Gradient boosted tree model", string.Empty) {
+    public GradientBoostedTreesModelSurrogate(IRegressionProblemData trainingProblemData, uint seed,
+      ILossFunction lossFunction, int iterations, int maxSize, double r, double m, double nu)
+      : base(trainingProblemData.TargetVariable, "Gradient boosted tree model", string.Empty) {
       this.trainingProblemData = trainingProblemData;
       this.seed = seed;
@@ -86 +92 @@
 
     // wrap an actual model in a surrograte
-    public GradientBoostedTreesModelSurrogate(IRegressionProblemData trainingProblemData, uint seed, ILossFunction lossFunction, int iterations, int maxSize, double r, double m, double nu, IGradientBoostedTreesModel model)
+    public GradientBoostedTreesModelSurrogate(IRegressionProblemData trainingProblemData, uint seed,
+      ILossFunction lossFunction, int iterations, int maxSize, double r, double m, double nu,
+      IGradientBoostedTreesModel model)
       : this(trainingProblemData, seed, lossFunction, iterations, maxSize, r, m, nu) {
       this.actualModel = model;
@@ -96 +104 @@
 
     // forward message to actual model (recalculate model first if necessary)
-    public IEnumerable<double> GetEstimatedValues(IDataset dataset, IEnumerable<int> rows) {
+    public override IEnumerable<double> GetEstimatedValues(IDataset dataset, IEnumerable<int> rows) {
       if (actualModel == null) actualModel = RecalculateModel();
       return actualModel.GetEstimatedValues(dataset, rows);
     }
 
-    public IRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData) {
+    public override IRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData) {
       return new RegressionSolution(this, (IRegressionProblemData)problemData.Clone());
     }
-
 
     private IGradientBoostedTreesModel RecalculateModel() {

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/RegressionTreeBuilder.cs

@@ -180 +180 @@
 
 
-    // processes potential splits from the queue as long as splits are left and the maximum size of the tree is not reached
+    // processes potential splits from the queue as long as splits are remaining and the maximum size of the tree is not reached
     private void CreateRegressionTreeFromQueue(int maxNodes, ILossFunction lossFunction) {
       while (queue.Any() && curTreeNodeIdx + 1 < maxNodes) { // two nodes are created in each loop
@@ -204 +204 @@
 
         // overwrite existing leaf node with an internal node
-        tree[f.ParentNodeIdx] = new RegressionTreeModel.TreeNode(f.SplittingVariable, f.SplittingThreshold, leftTreeIdx, rightTreeIdx);
+        tree[f.ParentNodeIdx] = new RegressionTreeModel.TreeNode(f.SplittingVariable, f.SplittingThreshold, leftTreeIdx, rightTreeIdx, weightLeft: (splitIdx - startIdx + 1) / (double)(endIdx - startIdx + 1));
       }
     }

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/RegressionTreeModel.cs

@@ -34 +34 @@
   [StorableClass]
   [Item("RegressionTreeModel", "Represents a decision tree for regression.")]
-  public sealed class RegressionTreeModel : NamedItem, IRegressionModel {
+  public sealed class RegressionTreeModel : RegressionModel {
+    public override IEnumerable<string> VariablesUsedForPrediction {
+      get { return tree.Select(t => t.VarName).Where(v => v != TreeNode.NO_VARIABLE); }
+    }
 
     // trees are represented as a flat array    
@@ -40 +43 @@
       public readonly static string NO_VARIABLE = null;
 
-      public TreeNode(string varName, double val, int leftIdx = -1, int rightIdx = -1)
+      public TreeNode(string varName, double val, int leftIdx = -1, int rightIdx = -1, double weightLeft = -1.0)
         : this() {
         VarName = varName;
@@ -46 +49 @@
         LeftIdx = leftIdx;
         RightIdx = rightIdx;
-      }
-
-      public string VarName { get; private set; } // name of the variable for splitting or NO_VARIABLE if terminal node
-      public double Val { get; private set; } // threshold
-      public int LeftIdx { get; private set; }
-      public int RightIdx { get; private set; }
+        WeightLeft = weightLeft;
+      }
+
+      public string VarName { get; internal set; } // name of the variable for splitting or NO_VARIABLE if terminal node
+      public double Val { get; internal set; } // threshold
+      public int LeftIdx { get; internal set; }
+      public int RightIdx { get; internal set; }
+      public double WeightLeft { get; internal set; } // for partial dependence plots (value in range [0..1] describes the fraction of training samples for the left sub-tree
+
 
       // necessary because the default implementation of GetHashCode for structs in .NET would only return the hashcode of val here
@@ -64 +70 @@
             LeftIdx.Equals(other.LeftIdx) &&
             RightIdx.Equals(other.RightIdx) &&
+            WeightLeft.Equals(other.WeightLeft) &&
             EqualStrings(VarName, other.VarName);
         } else {
@@ -79 +86 @@
     private TreeNode[] tree;
 
-    [Storable]
+    #region old storable format
+    // remove with HL 3.4
+    [Storable(AllowOneWay = true)]
     // to prevent storing the references to data caches in nodes
-    // TODO seemingly it is bad (performance-wise) to persist tuples (tuples are used as keys in a dictionary)
+    // seemingly, it is bad (performance-wise) to persist tuples (tuples are used as keys in a dictionary)
     private Tuple<string, double, int, int>[] SerializedTree {
-      get { return tree.Select(t => Tuple.Create(t.VarName, t.Val, t.LeftIdx, t.RightIdx)).ToArray(); }
-      set { this.tree = value.Select(t => new TreeNode(t.Item1, t.Item2, t.Item3, t.Item4)).ToArray(); }
-    }
+      // get { return tree.Select(t => Tuple.Create(t.VarName, t.Val, t.LeftIdx, t.RightIdx)).ToArray(); }
+      set { this.tree = value.Select(t => new TreeNode(t.Item1, t.Item2, t.Item3, t.Item4, -1.0)).ToArray(); } // use a weight of -1.0 to indicate that partial dependence cannot be calculated for old models 
+    }
+    #endregion
+    #region new storable format
+    [Storable]
+    private string[] SerializedTreeVarNames {
+      get { return tree.Select(t => t.VarName).ToArray(); }
+      set {
+        if (tree == null) tree = new TreeNode[value.Length];
+        for (int i = 0; i < value.Length; i++) {
+          tree[i].VarName = value[i];
+        }
+      }
+    }
+    [Storable]
+    private double[] SerializedTreeValues {
+      get { return tree.Select(t => t.Val).ToArray(); }
+      set {
+        if (tree == null) tree = new TreeNode[value.Length];
+        for (int i = 0; i < value.Length; i++) {
+          tree[i].Val = value[i];
+        }
+      }
+    }
+    [Storable]
+    private int[] SerializedTreeLeftIdx {
+      get { return tree.Select(t => t.LeftIdx).ToArray(); }
+      set {
+        if (tree == null) tree = new TreeNode[value.Length];
+        for (int i = 0; i < value.Length; i++) {
+          tree[i].LeftIdx = value[i];
+        }
+      }
+    }
+    [Storable]
+    private int[] SerializedTreeRightIdx {
+      get { return tree.Select(t => t.RightIdx).ToArray(); }
+      set {
+        if (tree == null) tree = new TreeNode[value.Length];
+        for (int i = 0; i < value.Length; i++) {
+          tree[i].RightIdx = value[i];
+        }
+      }
+    }
+    [Storable]
+    private double[] SerializedTreeWeightLeft {
+      get { return tree.Select(t => t.WeightLeft).ToArray(); }
+      set {
+        if (tree == null) tree = new TreeNode[value.Length];
+        for (int i = 0; i < value.Length; i++) {
+          tree[i].WeightLeft = value[i];
+        }
+      }
+    }
+    #endregion
+
+
+
 
     [StorableConstructor]
@@ -98 +163 @@
     }
 
-    internal RegressionTreeModel(TreeNode[] tree)
-      : base("RegressionTreeModel", "Represents a decision tree for regression.") {
+    internal RegressionTreeModel(TreeNode[] tree, string target = "Target")
+      : base(target, "RegressionTreeModel", "Represents a decision tree for regression.") {
       this.tree = tree;
     }
@@ -108 +173 @@
         if (node.VarName == TreeNode.NO_VARIABLE)
           return node.Val;
-
-        if (columnCache[nodeIdx][row] <= node.Val)
+        if (columnCache[nodeIdx] == null) {
+          if (node.WeightLeft.IsAlmost(-1.0)) throw new InvalidOperationException("Cannot calculate partial dependence for trees loaded from older versions of HeuristicLab.");
+          // weighted average for partial dependence plot (recursive here because we need to calculate both sub-trees)
+          return node.WeightLeft * GetPredictionForRow(t, columnCache, node.LeftIdx, row) +
+                 (1.0 - node.WeightLeft) * GetPredictionForRow(t, columnCache, node.RightIdx, row);
+        } else if (columnCache[nodeIdx][row] <= node.Val)
           nodeIdx = node.LeftIdx;
         else
@@ -121 +190 @@
     }
 
-    public IEnumerable<double> GetEstimatedValues(IDataset ds, IEnumerable<int> rows) {
+    public override IEnumerable<double> GetEstimatedValues(IDataset ds, IEnumerable<int> rows) {
       // lookup columns for variableNames in one pass over the tree to speed up evaluation later on
       ReadOnlyCollection<double>[] columnCache = new ReadOnlyCollection<double>[tree.Length];
@@ -127 +196 @@
       for (int i = 0; i < tree.Length; i++) {
         if (tree[i].VarName != TreeNode.NO_VARIABLE) {
-          columnCache[i] = ds.GetReadOnlyDoubleValues(tree[i].VarName);
+          // tree models also support calculating estimations if not all variables used for training are available in the dataset
+          if (ds.ColumnNames.Contains(tree[i].VarName))
+            columnCache[i] = ds.GetReadOnlyDoubleValues(tree[i].VarName);
         }
       }
@@ -133 +204 @@
     }
 
-    public IRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData) {
+    public override IRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData) {
       return new RegressionSolution(this, new RegressionProblemData(problemData));
     }
@@ -148 +219 @@
       } else {
         return
-          TreeToString(n.LeftIdx, string.Format(CultureInfo.InvariantCulture, "{0}{1}{2} <= {3:F}", part, string.IsNullOrEmpty(part) ? "" : " and ", n.VarName, n.Val))
-        + TreeToString(n.RightIdx, string.Format(CultureInfo.InvariantCulture, "{0}{1}{2} >  {3:F}", part, string.IsNullOrEmpty(part) ? "" : " and ", n.VarName, n.Val));
-      }
-    }
+          TreeToString(n.LeftIdx, string.Format(CultureInfo.InvariantCulture, "{0}{1}{2} <= {3:F} ({4:N3})", part, string.IsNullOrEmpty(part) ? "" : " and ", n.VarName, n.Val, n.WeightLeft))
+        + TreeToString(n.RightIdx, string.Format(CultureInfo.InvariantCulture, "{0}{1}{2}  >  {3:F} ({4:N3}))", part, string.IsNullOrEmpty(part) ? "" : " and ", n.VarName, n.Val, 1.0 - n.WeightLeft));
+      }
+    }
+
   }
 }

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/LinearDiscriminantAnalysis.cs

@@ -111 +111 @@
       IClassificationProblemData problemData,
       IEnumerable<int> rows) {
-      var model = new SymbolicDiscriminantFunctionClassificationModel(tree, interpreter, new AccuracyMaximizationThresholdCalculator());
+      var model = new SymbolicDiscriminantFunctionClassificationModel(problemData.TargetVariable, tree, interpreter, new AccuracyMaximizationThresholdCalculator());
       model.RecalculateModelParameters(problemData, rows);
       return model;

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/LinearRegression.cs

@@ -110 +110 @@
       addition.AddSubtree(cNode);
 
-      SymbolicRegressionSolution solution = new SymbolicRegressionSolution(new SymbolicRegressionModel(tree, new SymbolicDataAnalysisExpressionTreeInterpreter()), (IRegressionProblemData)problemData.Clone());
+      SymbolicRegressionSolution solution = new SymbolicRegressionSolution(new SymbolicRegressionModel(problemData.TargetVariable, tree, new SymbolicDataAnalysisExpressionTreeInterpreter()), (IRegressionProblemData)problemData.Clone());
       solution.Model.Name = "Linear Regression Model";
       solution.Name = "Linear Regression Solution";

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/MultinomialLogitClassification.cs

@@ -95 +95 @@
       relClassError = alglib.mnlrelclserror(lm, inputMatrix, nRows);
 
-      MultinomialLogitClassificationSolution solution = new MultinomialLogitClassificationSolution((IClassificationProblemData)problemData.Clone(), new MultinomialLogitModel(lm, targetVariable, allowedInputVariables, classValues));
+      MultinomialLogitClassificationSolution solution = new MultinomialLogitClassificationSolution(new MultinomialLogitModel(lm, targetVariable, allowedInputVariables, classValues), (IClassificationProblemData)problemData.Clone());
       return solution;
     }

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/MultinomialLogitClassificationSolution.cs

@@ -43 +43 @@
       : base(original, cloner) {
     }
-    public MultinomialLogitClassificationSolution(IClassificationProblemData problemData, MultinomialLogitModel logitModel)
+    public MultinomialLogitClassificationSolution( MultinomialLogitModel logitModel,IClassificationProblemData problemData)
       : base(logitModel, problemData) {
     }

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/MultinomialLogitModel.cs

@@ -34 +34 @@
   [StorableClass]
   [Item("Multinomial Logit Model", "Represents a multinomial logit model for classification.")]
-  public sealed class MultinomialLogitModel : NamedItem, IClassificationModel {
+  public sealed class MultinomialLogitModel : ClassificationModel {
 
     private alglib.logitmodel logitModel;
@@ -48 +48 @@
     }
 
-    [Storable]
-    private string targetVariable;
+    public override IEnumerable<string> VariablesUsedForPrediction {
+      get { return allowedInputVariables; }
+    }
+
     [Storable]
     private string[] allowedInputVariables;
@@ -64 +66 @@
       logitModel = new alglib.logitmodel();
       logitModel.innerobj.w = (double[])original.logitModel.innerobj.w.Clone();
-      targetVariable = original.targetVariable;
       allowedInputVariables = (string[])original.allowedInputVariables.Clone();
       classValues = (double[])original.classValues.Clone();
     }
     public MultinomialLogitModel(alglib.logitmodel logitModel, string targetVariable, IEnumerable<string> allowedInputVariables, double[] classValues)
-      : base() {
+      : base(targetVariable) {
       this.name = ItemName;
       this.description = ItemDescription;
       this.logitModel = logitModel;
-      this.targetVariable = targetVariable;
       this.allowedInputVariables = allowedInputVariables.ToArray();
       this.classValues = (double[])classValues.Clone();
@@ -82 +82 @@
     }
 
-    public IEnumerable<double> GetEstimatedClassValues(IDataset dataset, IEnumerable<int> rows) {
+    public override IEnumerable<double> GetEstimatedClassValues(IDataset dataset, IEnumerable<int> rows) {
       double[,] inputData = AlglibUtil.PrepareInputMatrix(dataset, allowedInputVariables, rows);
 
@@ -108 +108 @@
     }
 
-    public MultinomialLogitClassificationSolution CreateClassificationSolution(IClassificationProblemData problemData) {
-      return new MultinomialLogitClassificationSolution(new ClassificationProblemData(problemData), this);
-    }
-    IClassificationSolution IClassificationModel.CreateClassificationSolution(IClassificationProblemData problemData) {
-      return CreateClassificationSolution(problemData);
+    public override IClassificationSolution CreateClassificationSolution(IClassificationProblemData problemData) {
+      return new MultinomialLogitClassificationSolution(this, new ClassificationProblemData(problemData));
     }
 
@@ -135 +132 @@
     }
     #endregion
+
   }
 }

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/MctsSymbolicRegression/MctsSymbolicRegressionStatic.cs

@@ -25 +25 @@
 using System.Linq;
 using HeuristicLab.Algorithms.DataAnalysis.MctsSymbolicRegression.Policies;
-using HeuristicLab.Common;
 using HeuristicLab.Core;
 using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
@@ -177 +176 @@
 
           var t = new SymbolicExpressionTree(treeGen.Exec(bestCode, bestConsts, bestNParams, scalingFactor, scalingOffset));
-          var model = new SymbolicRegressionModel(t, interpreter, lowerEstimationLimit, upperEstimationLimit);
+          var model = new SymbolicRegressionModel(problemData.TargetVariable, t, interpreter, lowerEstimationLimit, upperEstimationLimit);
 
           // model has already been scaled linearly in Eval

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/Nca/NcaClassificationSolution.cs

@@ -40 +40 @@
       : base(original, cloner) {
     }
-    public NcaClassificationSolution(IClassificationProblemData problemData, INcaModel ncaModel)
+    public NcaClassificationSolution(INcaModel ncaModel, IClassificationProblemData problemData)
       : base(ncaModel, problemData) {
     }

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/Nca/NcaModel.cs

@@ -30 +30 @@
   [Item("NCA Model", "")]
   [StorableClass]
-  public class NcaModel : NamedItem, INcaModel {
+  public class NcaModel : ClassificationModel, INcaModel {
+    public override IEnumerable<string> VariablesUsedForPrediction {
+      get { return allowedInputVariables; }
+    }
 
     [Storable]
@@ -39 +42 @@
     [Storable]
     private string[] allowedInputVariables;
-    [Storable]
-    private string targetVariable;
     [Storable]
     private INearestNeighbourModel nnModel;
@@ -52 +53 @@
       this.transformationMatrix = (double[,])original.transformationMatrix.Clone();
       this.allowedInputVariables = (string[])original.allowedInputVariables.Clone();
-      this.targetVariable = original.targetVariable;
       this.nnModel = cloner.Clone(original.nnModel);
       this.classValues = (double[])original.classValues.Clone();
     }
-    public NcaModel(int k, double[,] transformationMatrix, IDataset dataset, IEnumerable<int> rows, string targetVariable, IEnumerable<string> allowedInputVariables, double[] classValues) {
+    public NcaModel(int k, double[,] transformationMatrix, IDataset dataset, IEnumerable<int> rows, string targetVariable, IEnumerable<string> allowedInputVariables, double[] classValues)
+      : base(targetVariable) {
       Name = ItemName;
       Description = ItemDescription;
       this.transformationMatrix = (double[,])transformationMatrix.Clone();
       this.allowedInputVariables = allowedInputVariables.ToArray();
-      this.targetVariable = targetVariable;
       this.classValues = (double[])classValues.Clone();
 
@@ -72 +72 @@
     }
 
-    public IEnumerable<double> GetEstimatedClassValues(IDataset dataset, IEnumerable<int> rows) {
+    public override IEnumerable<double> GetEstimatedClassValues(IDataset dataset, IEnumerable<int> rows) {
       var ds = ReduceDataset(dataset, rows);
       return nnModel.GetEstimatedClassValues(ds, Enumerable.Range(0, ds.Rows));
     }
 
-    public INcaClassificationSolution CreateClassificationSolution(IClassificationProblemData problemData) {
-      return new NcaClassificationSolution(new ClassificationProblemData(problemData), this);
+    public override IClassificationSolution CreateClassificationSolution(IClassificationProblemData problemData) {
+      return new NcaClassificationSolution(this, new ClassificationProblemData(problemData));
     }
 
-    IClassificationSolution IClassificationModel.CreateClassificationSolution(IClassificationProblemData problemData) {
-      return CreateClassificationSolution(problemData);
+    INcaClassificationSolution INcaModel.CreateClassificationSolution(IClassificationProblemData problemData) {
+      return new NcaClassificationSolution(this, new ClassificationProblemData(problemData));
     }
 
@@ -88 +88 @@
       var data = AlglibUtil.PrepareInputMatrix(dataset, allowedInputVariables, rows);
 
-      var targets = dataset.GetDoubleValues(targetVariable, rows).ToArray();
+      var targets = dataset.GetDoubleValues(TargetVariable, rows).ToArray();
       var result = new double[data.GetLength(0), transformationMatrix.GetLength(1) + 1];
       for (int i = 0; i < data.GetLength(0); i++)
@@ -104 +104 @@
           .Range(0, transformationMatrix.GetLength(1))
           .Select(x => "X" + x.ToString())
-          .Concat(targetVariable.ToEnumerable()),
+          .Concat(TargetVariable.ToEnumerable()),
         Reduce(dataset, rows));
     }

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour/NearestNeighbourClassification.cs

@@ -81 +81 @@
     public static IClassificationSolution CreateNearestNeighbourClassificationSolution(IClassificationProblemData problemData, int k) {
       var problemDataClone = (IClassificationProblemData)problemData.Clone();
-      return new NearestNeighbourClassificationSolution(problemDataClone, Train(problemDataClone, k));
+      return new NearestNeighbourClassificationSolution(Train(problemDataClone, k), problemDataClone);
     }
 

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour/NearestNeighbourClassificationSolution.cs

@@ -43 +43 @@
       : base(original, cloner) {
     }
-    public NearestNeighbourClassificationSolution(IClassificationProblemData problemData, INearestNeighbourModel nnModel)
+    public NearestNeighbourClassificationSolution(INearestNeighbourModel nnModel, IClassificationProblemData problemData)
       : base(nnModel, problemData) {
     }

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour/NearestNeighbourModel.cs

@@ -34 +34 @@
   [StorableClass]
   [Item("NearestNeighbourModel", "Represents a nearest neighbour model for regression and classification.")]
-  public sealed class NearestNeighbourModel : NamedItem, INearestNeighbourModel {
+  public sealed class NearestNeighbourModel : ClassificationModel, INearestNeighbourModel {
 
     private alglib.nearestneighbor.kdtree kdTree;
@@ -48 +48 @@
     }
 
-    [Storable]
-    private string targetVariable;
+    public override IEnumerable<string> VariablesUsedForPrediction {
+      get { return allowedInputVariables; }
+    }
+
     [Storable]
     private string[] allowedInputVariables;
@@ -91 +93 @@
 
       k = original.k;
-      targetVariable = original.targetVariable;
       allowedInputVariables = (string[])original.allowedInputVariables.Clone();
       if (original.classValues != null)
         this.classValues = (double[])original.classValues.Clone();
     }
-    public NearestNeighbourModel(IDataset dataset, IEnumerable<int> rows, int k, string targetVariable, IEnumerable<string> allowedInputVariables, double[] classValues = null) {
+    public NearestNeighbourModel(IDataset dataset, IEnumerable<int> rows, int k, string targetVariable, IEnumerable<string> allowedInputVariables, double[] classValues = null)
+      : base(targetVariable) {
       Name = ItemName;
       Description = ItemDescription;
       this.k = k;
-      this.targetVariable = targetVariable;
       this.allowedInputVariables = allowedInputVariables.ToArray();
 
@@ -163 +164 @@
     }
 
-    public IEnumerable<double> GetEstimatedClassValues(IDataset dataset, IEnumerable<int> rows) {
+    public override IEnumerable<double> GetEstimatedClassValues(IDataset dataset, IEnumerable<int> rows) {
       if (classValues == null) throw new InvalidOperationException("No class values are defined.");
       double[,] inputData = AlglibUtil.PrepareInputMatrix(dataset, allowedInputVariables, rows);
@@ -201 +202 @@
     }
 
-    public INearestNeighbourRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData) {
-      return new NearestNeighbourRegressionSolution(new RegressionProblemData(problemData), this);
-    }
+
     IRegressionSolution IRegressionModel.CreateRegressionSolution(IRegressionProblemData problemData) {
-      return CreateRegressionSolution(problemData);
-    }
-    public INearestNeighbourClassificationSolution CreateClassificationSolution(IClassificationProblemData problemData) {
-      return new NearestNeighbourClassificationSolution(new ClassificationProblemData(problemData), this);
-    }
-    IClassificationSolution IClassificationModel.CreateClassificationSolution(IClassificationProblemData problemData) {
-      return CreateClassificationSolution(problemData);
+      return new NearestNeighbourRegressionSolution(this, new RegressionProblemData(problemData));
+    }
+    public override IClassificationSolution CreateClassificationSolution(IClassificationProblemData problemData) {
+      return new NearestNeighbourClassificationSolution(this, new ClassificationProblemData(problemData));
     }
 

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour/NearestNeighbourRegression.cs

@@ -80 +80 @@
     public static IRegressionSolution CreateNearestNeighbourRegressionSolution(IRegressionProblemData problemData, int k) {
       var clonedProblemData = (IRegressionProblemData)problemData.Clone();
-      return new NearestNeighbourRegressionSolution(clonedProblemData, Train(problemData, k));
+      return new NearestNeighbourRegressionSolution(Train(problemData, k), clonedProblemData);
     }
 

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour/NearestNeighbourRegressionSolution.cs

@@ -43 +43 @@
       : base(original, cloner) {
     }
-    public NearestNeighbourRegressionSolution(IRegressionProblemData problemData, INearestNeighbourModel nnModel)
+    public NearestNeighbourRegressionSolution(INearestNeighbourModel nnModel, IRegressionProblemData problemData)
       : base(nnModel, problemData) {
     }

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/NeuralNetwork/NeuralNetworkClassification.cs

@@ -220 +220 @@
 
       var problemDataClone = (IClassificationProblemData)problemData.Clone();
-      return new NeuralNetworkClassificationSolution(problemDataClone, new NeuralNetworkModel(multiLayerPerceptron, targetVariable, allowedInputVariables, problemDataClone.ClassValues.ToArray()));
+      return new NeuralNetworkClassificationSolution(new NeuralNetworkModel(multiLayerPerceptron, targetVariable, allowedInputVariables, problemDataClone.ClassValues.ToArray()), problemDataClone);
     }
     #endregion

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/NeuralNetwork/NeuralNetworkClassificationSolution.cs

@@ -43 +43 @@
       : base(original, cloner) {
     }
-    public NeuralNetworkClassificationSolution(IClassificationProblemData problemData, INeuralNetworkModel nnModel)
+    public NeuralNetworkClassificationSolution(INeuralNetworkModel nnModel, IClassificationProblemData problemData)
       : base(nnModel, problemData) {
     }

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/NeuralNetwork/NeuralNetworkEnsembleClassification.cs

@@ -204 +204 @@
       relClassError = alglib.mlperelclserror(mlpEnsemble, inputMatrix, nRows);
       var problemDataClone = (IClassificationProblemData)problemData.Clone();
-      return new NeuralNetworkEnsembleClassificationSolution(problemDataClone, new NeuralNetworkEnsembleModel(mlpEnsemble, targetVariable, allowedInputVariables, problemDataClone.ClassValues.ToArray()));
+      return new NeuralNetworkEnsembleClassificationSolution(new NeuralNetworkEnsembleModel(mlpEnsemble, targetVariable, allowedInputVariables, problemDataClone.ClassValues.ToArray()), problemDataClone);
     }
     #endregion

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/NeuralNetwork/NeuralNetworkEnsembleClassificationSolution.cs

@@ -43 +43 @@
       : base(original, cloner) {
     }
-    public NeuralNetworkEnsembleClassificationSolution(IClassificationProblemData problemData, INeuralNetworkEnsembleModel nnModel)
+    public NeuralNetworkEnsembleClassificationSolution(INeuralNetworkEnsembleModel nnModel, IClassificationProblemData problemData)
       : base(nnModel, problemData) {
     }

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/NeuralNetwork/NeuralNetworkEnsembleModel.cs

@@ -34 +34 @@
   [StorableClass]
   [Item("NeuralNetworkEnsembleModel", "Represents a neural network ensemble for regression and classification.")]
-  public sealed class NeuralNetworkEnsembleModel : NamedItem, INeuralNetworkEnsembleModel {
+  public sealed class NeuralNetworkEnsembleModel : ClassificationModel, INeuralNetworkEnsembleModel {
 
     private alglib.mlpensemble mlpEnsemble;
@@ -46 +46 @@
         }
       }
+    }
+
+    public override IEnumerable<string> VariablesUsedForPrediction {
+      get { return allowedInputVariables; }
     }
 
@@ -72 +76 @@
     }
     public NeuralNetworkEnsembleModel(alglib.mlpensemble mlpEnsemble, string targetVariable, IEnumerable<string> allowedInputVariables, double[] classValues = null)
-      : base() {
+      : base(targetVariable) {
       this.name = ItemName;
       this.description = ItemDescription;
@@ -103 +107 @@
     }
 
-    public IEnumerable<double> GetEstimatedClassValues(IDataset dataset, IEnumerable<int> rows) {
+    public override IEnumerable<double> GetEstimatedClassValues(IDataset dataset, IEnumerable<int> rows) {
       double[,] inputData = AlglibUtil.PrepareInputMatrix(dataset, allowedInputVariables, rows);
 
@@ -129 +133 @@
     }
 
-    public INeuralNetworkEnsembleRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData) {
-      return new NeuralNetworkEnsembleRegressionSolution(new RegressionEnsembleProblemData(problemData), this);
-    }
-    IRegressionSolution IRegressionModel.CreateRegressionSolution(IRegressionProblemData problemData) {
-      return CreateRegressionSolution(problemData);
-    }
-    public INeuralNetworkEnsembleClassificationSolution CreateClassificationSolution(IClassificationProblemData problemData) {
-      return new NeuralNetworkEnsembleClassificationSolution(new ClassificationEnsembleProblemData(problemData), this);
-    }
-    IClassificationSolution IClassificationModel.CreateClassificationSolution(IClassificationProblemData problemData) {
-      return CreateClassificationSolution(problemData);
+    public IRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData) {
+      return new NeuralNetworkEnsembleRegressionSolution(this, new RegressionEnsembleProblemData(problemData));
+    }
+    public override IClassificationSolution CreateClassificationSolution(IClassificationProblemData problemData) {
+      return new NeuralNetworkEnsembleClassificationSolution(this, new ClassificationEnsembleProblemData(problemData));
     }
 

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/NeuralNetwork/NeuralNetworkEnsembleRegression.cs

@@ -190 +190 @@
       avgRelError = alglib.mlpeavgrelerror(mlpEnsemble, inputMatrix, nRows);
 
-      return new NeuralNetworkEnsembleRegressionSolution((IRegressionProblemData)problemData.Clone(), new NeuralNetworkEnsembleModel(mlpEnsemble, targetVariable, allowedInputVariables));
+      return new NeuralNetworkEnsembleRegressionSolution(new NeuralNetworkEnsembleModel(mlpEnsemble, targetVariable, allowedInputVariables), (IRegressionProblemData)problemData.Clone());
     }
     #endregion

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/NeuralNetwork/NeuralNetworkEnsembleRegressionSolution.cs

@@ -43 +43 @@
       : base(original, cloner) {
     }
-    public NeuralNetworkEnsembleRegressionSolution(IRegressionProblemData problemData, INeuralNetworkEnsembleModel nnModel)
+    public NeuralNetworkEnsembleRegressionSolution(INeuralNetworkEnsembleModel nnModel, IRegressionProblemData problemData)
       : base(nnModel, problemData) {
       RecalculateResults();

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/NeuralNetwork/NeuralNetworkModel.cs

@@ -34 +34 @@
   [StorableClass]
   [Item("NeuralNetworkModel", "Represents a neural network for regression and classification.")]
-  public sealed class NeuralNetworkModel : NamedItem, INeuralNetworkModel {
+  public sealed class NeuralNetworkModel : ClassificationModel, INeuralNetworkModel {
 
     private alglib.multilayerperceptron multiLayerPerceptron;
@@ -48 +48 @@
     }
 
-    [Storable]
-    private string targetVariable;
+    public override IEnumerable<string> VariablesUsedForPrediction {
+      get { return allowedInputVariables; }
+    }
+
     [Storable]
     private string[] allowedInputVariables;
@@ -74 +76 @@
       multiLayerPerceptron.innerobj.x = (double[])original.multiLayerPerceptron.innerobj.x.Clone();
       multiLayerPerceptron.innerobj.y = (double[])original.multiLayerPerceptron.innerobj.y.Clone();
-      targetVariable = original.targetVariable;
       allowedInputVariables = (string[])original.allowedInputVariables.Clone();
       if (original.classValues != null)
@@ -80 +81 @@
     }
     public NeuralNetworkModel(alglib.multilayerperceptron multiLayerPerceptron, string targetVariable, IEnumerable<string> allowedInputVariables, double[] classValues = null)
-      : base() {
+      : base(targetVariable) {
       this.name = ItemName;
       this.description = ItemDescription;
       this.multiLayerPerceptron = multiLayerPerceptron;
-      this.targetVariable = targetVariable;
       this.allowedInputVariables = allowedInputVariables.ToArray();
       if (classValues != null)
@@ -111 +111 @@
     }
 
-    public IEnumerable<double> GetEstimatedClassValues(IDataset dataset, IEnumerable<int> rows) {
+    public override IEnumerable<double> GetEstimatedClassValues(IDataset dataset, IEnumerable<int> rows) {
       double[,] inputData = AlglibUtil.PrepareInputMatrix(dataset, allowedInputVariables, rows);
 
@@ -137 +137 @@
     }
 
-    public INeuralNetworkRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData) {
-      return new NeuralNetworkRegressionSolution(new RegressionProblemData(problemData), this);
-    }
-    IRegressionSolution IRegressionModel.CreateRegressionSolution(IRegressionProblemData problemData) {
-      return CreateRegressionSolution(problemData);
-    }
-    public INeuralNetworkClassificationSolution CreateClassificationSolution(IClassificationProblemData problemData) {
-      return new NeuralNetworkClassificationSolution(new ClassificationProblemData(problemData), this);
-    }
-    IClassificationSolution IClassificationModel.CreateClassificationSolution(IClassificationProblemData problemData) {
-      return CreateClassificationSolution(problemData);
+    public IRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData) {
+      return new NeuralNetworkRegressionSolution(this, new RegressionProblemData(problemData));
+    }
+    public override IClassificationSolution CreateClassificationSolution(IClassificationProblemData problemData) {
+      return new NeuralNetworkClassificationSolution(this, new ClassificationProblemData(problemData));
     }
 

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/NeuralNetwork/NeuralNetworkRegression.cs

@@ -207 +207 @@
       avgRelError = alglib.mlpavgrelerror(multiLayerPerceptron, inputMatrix, nRows);
 
-      return new NeuralNetworkRegressionSolution((IRegressionProblemData)problemData.Clone(), new NeuralNetworkModel(multiLayerPerceptron, targetVariable, allowedInputVariables));
+      return new NeuralNetworkRegressionSolution(new NeuralNetworkModel(multiLayerPerceptron, targetVariable, allowedInputVariables), (IRegressionProblemData)problemData.Clone());
     }
     #endregion

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/NeuralNetwork/NeuralNetworkRegressionSolution.cs

@@ -43 +43 @@
       : base(original, cloner) {
     }
-    public NeuralNetworkRegressionSolution(IRegressionProblemData problemData, INeuralNetworkModel nnModel)
+    public NeuralNetworkRegressionSolution(INeuralNetworkModel nnModel, IRegressionProblemData problemData)
       : base(nnModel, problemData) {
     }

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestClassification.cs

@@ -143 +143 @@
 
       if (CreateSolution) {
-        var solution = new RandomForestClassificationSolution((IClassificationProblemData)Problem.ProblemData.Clone(), model);
+        var solution = new RandomForestClassificationSolution(model, (IClassificationProblemData)Problem.ProblemData.Clone());
         Results.Add(new Result(RandomForestClassificationModelResultName, "The random forest classification solution.", solution));
       }
     }
-    
+
     // keep for compatibility with old API
     public static RandomForestClassificationSolution CreateRandomForestClassificationSolution(IClassificationProblemData problemData, int nTrees, double r, double m, int seed,
       out double rmsError, out double relClassificationError, out double outOfBagRmsError, out double outOfBagRelClassificationError) {
       var model = CreateRandomForestClassificationModel(problemData, nTrees, r, m, seed, out rmsError, out relClassificationError, out outOfBagRmsError, out outOfBagRelClassificationError);
-      return new RandomForestClassificationSolution((IClassificationProblemData)problemData.Clone(), model);
+      return new RandomForestClassificationSolution(model, (IClassificationProblemData)problemData.Clone());
     }
 

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestClassificationSolution.cs

@@ -43 +43 @@
       : base(original, cloner) {
     }
-    public RandomForestClassificationSolution(IClassificationProblemData problemData, IRandomForestModel randomForestModel)
+    public RandomForestClassificationSolution(IRandomForestModel randomForestModel, IClassificationProblemData problemData)
       : base(randomForestModel, problemData) {
     }

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestModel.cs

@@ -34 +34 @@
   [StorableClass]
   [Item("RandomForestModel", "Represents a random forest for regression and classification.")]
-  public sealed class RandomForestModel : NamedItem, IRandomForestModel {
+  public sealed class RandomForestModel : ClassificationModel, IRandomForestModel {
     // not persisted
     private alglib.decisionforest randomForest;
@@ -44 +44 @@
       }
     }
+
+    public override IEnumerable<string> VariablesUsedForPrediction {
+      get { return originalTrainingData.AllowedInputVariables; }
+    }
+
 
     // instead of storing the data of the model itself
@@ -91 +96 @@
 
     // random forest models can only be created through the static factory methods CreateRegressionModel and CreateClassificationModel
-    private RandomForestModel(alglib.decisionforest randomForest,
+    private RandomForestModel(string targetVariable, alglib.decisionforest randomForest,
       int seed, IDataAnalysisProblemData originalTrainingData,
       int nTrees, double r, double m, double[] classValues = null)
-      : base() {
+      : base(targetVariable) {
       this.name = ItemName;
       this.description = ItemDescription;
@@ -147 +152 @@
     }
 
-    public IEnumerable<double> GetEstimatedClassValues(IDataset dataset, IEnumerable<int> rows) {
+    public override IEnumerable<double> GetEstimatedClassValues(IDataset dataset, IEnumerable<int> rows) {
       double[,] inputData = AlglibUtil.PrepareInputMatrix(dataset, AllowedInputVariables, rows);
       AssertInputMatrix(inputData);
@@ -174 +179 @@
     }
 
-    public IRandomForestRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData) {
-      return new RandomForestRegressionSolution(new RegressionProblemData(problemData), this);
-    }
-    IRegressionSolution IRegressionModel.CreateRegressionSolution(IRegressionProblemData problemData) {
-      return CreateRegressionSolution(problemData);
-    }
-    public IRandomForestClassificationSolution CreateClassificationSolution(IClassificationProblemData problemData) {
-      return new RandomForestClassificationSolution(new ClassificationProblemData(problemData), this);
-    }
-    IClassificationSolution IClassificationModel.CreateClassificationSolution(IClassificationProblemData problemData) {
-      return CreateClassificationSolution(problemData);
+
+    public IRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData) {
+      return new RandomForestRegressionSolution(this, new RegressionProblemData(problemData));
+    }
+    public override IClassificationSolution CreateClassificationSolution(IClassificationProblemData problemData) {
+      return new RandomForestClassificationSolution(this, new ClassificationProblemData(problemData));
     }
 
@@ -205 +205 @@
       outOfBagRmsError = rep.oobrmserror;
 
-      return new RandomForestModel(dForest, seed, problemData, nTrees, r, m);
+      return new RandomForestModel(problemData.TargetVariable, dForest, seed, problemData, nTrees, r, m);
     }
 
@@ -242 +242 @@
       outOfBagRelClassificationError = rep.oobrelclserror;
 
-      return new RandomForestModel(dForest, seed, problemData, nTrees, r, m, classValues);
+      return new RandomForestModel(problemData.TargetVariable, dForest, seed, problemData, nTrees, r, m, classValues);
     }
 

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestRegression.cs

@@ -143 +143 @@
 
       if (CreateSolution) {
-        var solution = new RandomForestRegressionSolution((IRegressionProblemData)Problem.ProblemData.Clone(), model);
+        var solution = new RandomForestRegressionSolution(model, (IRegressionProblemData)Problem.ProblemData.Clone());
         Results.Add(new Result(RandomForestRegressionModelResultName, "The random forest regression solution.", solution));
       }
@@ -153 +153 @@
       var model = CreateRandomForestRegressionModel(problemData, nTrees, r, m, seed,
         out rmsError, out avgRelError, out outOfBagRmsError, out outOfBagAvgRelError);
-      return new RandomForestRegressionSolution((IRegressionProblemData)problemData.Clone(), model);
+      return new RandomForestRegressionSolution(model, (IRegressionProblemData)problemData.Clone());
     }
 

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestRegressionSolution.cs

@@ -43 +43 @@
       : base(original, cloner) {
     }
-    public RandomForestRegressionSolution(IRegressionProblemData problemData, IRandomForestModel randomForestModel)
+    public RandomForestRegressionSolution(IRandomForestModel randomForestModel, IRegressionProblemData problemData)
       : base(randomForestModel, problemData) {
     }

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/SupportVectorMachine/SupportVectorMachineModel.cs

@@ -37 +37 @@
   [StorableClass]
   [Item("SupportVectorMachineModel", "Represents a support vector machine model.")]
-  public sealed class SupportVectorMachineModel : NamedItem, ISupportVectorMachineModel {
+  public sealed class SupportVectorMachineModel : ClassificationModel, ISupportVectorMachineModel {
+    public override IEnumerable<string> VariablesUsedForPrediction {
+      get { return allowedInputVariables; }
+    }
+
 
     private svm_model model;
@@ -83 +87 @@
 
     [Storable]
-    private string targetVariable;
-    [Storable]
     private string[] allowedInputVariables;
     [Storable]
@@ -96 +98 @@
       this.model = original.model;
       this.rangeTransform = original.rangeTransform;
-      this.targetVariable = original.targetVariable;
       this.allowedInputVariables = (string[])original.allowedInputVariables.Clone();
       if (original.classValues != null)
@@ -106 +107 @@
     }
     public SupportVectorMachineModel(svm_model model, RangeTransform rangeTransform, string targetVariable, IEnumerable<string> allowedInputVariables)
-      : base() {
+      : base(targetVariable) {
       this.name = ItemName;
       this.description = ItemDescription;
       this.model = model;
       this.rangeTransform = rangeTransform;
-      this.targetVariable = targetVariable;
       this.allowedInputVariables = allowedInputVariables.ToArray();
     }
@@ -123 +123 @@
       return GetEstimatedValuesHelper(dataset, rows);
     }
-    public SupportVectorRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData) {
+    public IRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData) {
       return new SupportVectorRegressionSolution(this, new RegressionProblemData(problemData));
     }
-    IRegressionSolution IRegressionModel.CreateRegressionSolution(IRegressionProblemData problemData) {
-      return CreateRegressionSolution(problemData);
-    }
     #endregion
 
     #region IClassificationModel Members
-    public IEnumerable<double> GetEstimatedClassValues(IDataset dataset, IEnumerable<int> rows) {
+    public override IEnumerable<double> GetEstimatedClassValues(IDataset dataset, IEnumerable<int> rows) {
       if (classValues == null) throw new NotSupportedException();
       // return the original class value instead of the predicted value of the model
@@ -152 +149 @@
     }
 
-    public SupportVectorClassificationSolution CreateClassificationSolution(IClassificationProblemData problemData) {
+    public override IClassificationSolution CreateClassificationSolution(IClassificationProblemData problemData) {
       return new SupportVectorClassificationSolution(this, new ClassificationProblemData(problemData));
-    }
-    IClassificationSolution IClassificationModel.CreateClassificationSolution(IClassificationProblemData problemData) {
-      return CreateClassificationSolution(problemData);
     }
     #endregion
     private IEnumerable<double> GetEstimatedValuesHelper(IDataset dataset, IEnumerable<int> rows) {
       // calculate predictions for the currently requested rows
-      svm_problem problem = SupportVectorMachineUtil.CreateSvmProblem(dataset, targetVariable, allowedInputVariables, rows);
+      svm_problem problem = SupportVectorMachineUtil.CreateSvmProblem(dataset, TargetVariable, allowedInputVariables, rows);
       svm_problem scaledProblem = rangeTransform.Scale(problem);
 

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/TimeSeries/AutoregressiveModeling.cs

@@ -134 +134 @@
 
       var interpreter = new SymbolicTimeSeriesPrognosisExpressionTreeInterpreter(problemData.TargetVariable);
-      var model = new SymbolicTimeSeriesPrognosisModel(tree, interpreter);
+      var model = new SymbolicTimeSeriesPrognosisModel(problemData.TargetVariable, tree, interpreter);
       var solution = model.CreateTimeSeriesPrognosisSolution((ITimeSeriesPrognosisProblemData)problemData.Clone());
       return solution;

branches/HeuristicLab.RegressionSolutionGradientView/HeuristicLab.Algorithms.DataAnalysis/3.4/kMeans/KMeansClusteringModel.cs

@@ -37 +37 @@
     public static new Image StaticItemImage {
       get { return HeuristicLab.Common.Resources.VSImageLibrary.Function; }
+    }
+
+    public IEnumerable<string> VariablesUsedForPrediction {
+      get { return allowedInputVariables; }
     }