Changeset 11571 for branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Algorithms.DataAnalysis

Timestamp:

11/24/14 15:16:59 (10 years ago)

Author:

bburlacu

Message:

#2276: Commit initial version of IDataset interface and code refactoring.

Location:

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Algorithms.DataAnalysis/3.4

Files:

• GaussianProcess/GaussianProcessModel.cs (modified) (5 diffs)
• HeuristicLab.Algorithms.DataAnalysis-3.4.csproj (modified) (1 diff)
• Interfaces/IGaussianProcessModel.cs (modified) (1 diff)
• Interfaces/INcaModel.cs (modified) (1 diff)
• Linear/AlglibUtil.cs (modified) (2 diffs)
• Linear/LinearDiscriminantAnalysis.cs (modified) (1 diff)
• Linear/LinearRegression.cs (modified) (1 diff)
• Linear/MultinomialLogitClassification.cs (modified) (1 diff)
• Linear/MultinomialLogitModel.cs (modified) (1 diff)
• Linear/Scaling.cs (modified) (2 diffs)
• Nca/NcaModel.cs (modified) (4 diffs)
• NearestNeighbour/NearestNeighbourModel.cs (modified) (3 diffs)
• NeuralNetwork/NeuralNetworkClassification.cs (modified) (1 diff)
• NeuralNetwork/NeuralNetworkEnsembleClassification.cs (modified) (2 diffs)
• NeuralNetwork/NeuralNetworkEnsembleModel.cs (modified) (2 diffs)
• NeuralNetwork/NeuralNetworkEnsembleRegression.cs (modified) (2 diffs)
• NeuralNetwork/NeuralNetworkModel.cs (modified) (2 diffs)
• NeuralNetwork/NeuralNetworkRegression.cs (modified) (1 diff)
• RandomForest/RandomForestModel.cs (modified) (4 diffs)
• RandomForest/RandomForestUtil.cs (modified) (9 diffs)
• SupportVectorMachine/SupportVectorClassification.cs (modified) (1 diff)
• SupportVectorMachine/SupportVectorMachineModel.cs (modified) (3 diffs)
• SupportVectorMachine/SupportVectorMachineUtil.cs (modified) (1 diff)
• SupportVectorMachine/SupportVectorParameterTuningEvaluator.cs (added)
• SupportVectorMachine/SupportVectorParameterTuningProblem.cs (added)
• SupportVectorMachine/SupportVectorRegression.cs (modified) (1 diff)
• kMeans/KMeansClustering.cs (modified) (1 diff)
• kMeans/KMeansClusteringModel.cs (modified) (1 diff)
• kMeans/KMeansClusteringUtil.cs (modified) (2 diffs)

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/GaussianProcess/GaussianProcessModel.cs

@@ -117 +117 @@
       this.x = original.x;
     }
-    public GaussianProcessModel(Dataset ds, string targetVariable, IEnumerable<string> allowedInputVariables, IEnumerable<int> rows,
+    public GaussianProcessModel(IDataset ds, string targetVariable, IEnumerable<string> allowedInputVariables, IEnumerable<int> rows,
       IEnumerable<double> hyp, IMeanFunction meanFunction, ICovarianceFunction covarianceFunction)
       : base() {
@@ -141 +141 @@
     }
 
-    private void CalculateModel(Dataset ds, IEnumerable<int> rows) {
+    private void CalculateModel(IDataset ds, IEnumerable<int> rows) {
       inputScaling = new Scaling(ds, allowedInputVariables, rows);
       x = AlglibUtil.PrepareAndScaleInputMatrix(ds, allowedInputVariables, rows, inputScaling);
@@ -245 +245 @@
 
     #region IRegressionModel Members
-    public IEnumerable<double> GetEstimatedValues(Dataset dataset, IEnumerable<int> rows) {
+    public IEnumerable<double> GetEstimatedValues(IDataset dataset, IEnumerable<int> rows) {
       return GetEstimatedValuesHelper(dataset, rows);
     }
@@ -257 +257 @@
 
 
-    private IEnumerable<double> GetEstimatedValuesHelper(Dataset dataset, IEnumerable<int> rows) {
+    private IEnumerable<double> GetEstimatedValuesHelper(IDataset dataset, IEnumerable<int> rows) {
       var newX = AlglibUtil.PrepareAndScaleInputMatrix(dataset, allowedInputVariables, rows, inputScaling);
       int newN = newX.GetLength(0);
@@ -277 +277 @@
     }
 
-    public IEnumerable<double> GetEstimatedVariance(Dataset dataset, IEnumerable<int> rows) {
+    public IEnumerable<double> GetEstimatedVariance(IDataset dataset, IEnumerable<int> rows) {
       var newX = AlglibUtil.PrepareAndScaleInputMatrix(dataset, allowedInputVariables, rows, inputScaling);
       int newN = newX.GetLength(0);

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/HeuristicLab.Algorithms.DataAnalysis-3.4.csproj

@@ -263 +263 @@
     <Compile Include="RandomForest\RandomForestRegressionSolution.cs" />
     <Compile Include="RandomForest\RandomForestUtil.cs" />
+    <Compile Include="SupportVectorMachine\SupportVectorParameterTuningEvaluator.cs" />
+    <Compile Include="SupportVectorMachine\SupportVectorParameterTuningProblem.cs" />
     <Compile Include="SupportVectorMachine\SupportVectorClassification.cs" />
     <Compile Include="SupportVectorMachine\SupportVectorClassificationSolution.cs" />

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/Interfaces/IGaussianProcessModel.cs

@@ -34 +34 @@
     double[] HyperparameterGradients { get; }
 
-    IEnumerable<double> GetEstimatedVariance(Dataset ds, IEnumerable<int> rows);
+    IEnumerable<double> GetEstimatedVariance(IDataset ds, IEnumerable<int> rows);
     void FixParameters();
   }

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/Interfaces/INcaModel.cs

@@ -27 +27 @@
     new INcaClassificationSolution CreateClassificationSolution(IClassificationProblemData problemData);
 
-    double[,] Reduce(Dataset dataset, IEnumerable<int> rows);
+    double[,] Reduce(IDataset dataset, IEnumerable<int> rows);
   }
 }

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/AlglibUtil.cs

@@ -26 +26 @@
 namespace HeuristicLab.Algorithms.DataAnalysis {
   public static class AlglibUtil {
-    public static double[,] PrepareInputMatrix(Dataset dataset, IEnumerable<string> variables, IEnumerable<int> rows) {
+    public static double[,] PrepareInputMatrix(IDataset dataset, IEnumerable<string> variables, IEnumerable<int> rows) {
       List<string> variablesList = variables.ToList();
       List<int> rowsList = rows.ToList();
@@ -45 +45 @@
       return matrix;
     }
-    public static double[,] PrepareAndScaleInputMatrix(Dataset dataset, IEnumerable<string> variables, IEnumerable<int> rows, Scaling scaling) {
+    public static double[,] PrepareAndScaleInputMatrix(IDataset dataset, IEnumerable<string> variables, IEnumerable<int> rows, Scaling scaling) {
       List<string> variablesList = variables.ToList();
       List<int> rowsList = rows.ToList();

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/LinearDiscriminantAnalysis.cs

@@ -65 +65 @@
 
     public static IClassificationSolution CreateLinearDiscriminantAnalysisSolution(IClassificationProblemData problemData) {
-      Dataset dataset = problemData.Dataset;
+      var dataset = problemData.Dataset;
       string targetVariable = problemData.TargetVariable;
       IEnumerable<string> allowedInputVariables = problemData.AllowedInputVariables;

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/LinearRegression.cs

@@ -69 +69 @@
 
     public static ISymbolicRegressionSolution CreateLinearRegressionSolution(IRegressionProblemData problemData, out double rmsError, out double cvRmsError) {
-      Dataset dataset = problemData.Dataset;
+      var dataset = problemData.Dataset;
       string targetVariable = problemData.TargetVariable;
       IEnumerable<string> allowedInputVariables = problemData.AllowedInputVariables;

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/MultinomialLogitClassification.cs

@@ -66 +66 @@
 
     public static IClassificationSolution CreateLogitClassificationSolution(IClassificationProblemData problemData, out double rmsError, out double relClassError) {
-      Dataset dataset = problemData.Dataset;
+      var dataset = problemData.Dataset;
       string targetVariable = problemData.TargetVariable;
       IEnumerable<string> allowedInputVariables = problemData.AllowedInputVariables;

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/MultinomialLogitModel.cs

@@ -82 +82 @@
     }
 
-    public IEnumerable<double> GetEstimatedClassValues(Dataset dataset, IEnumerable<int> rows) {
+    public IEnumerable<double> GetEstimatedClassValues(IDataset dataset, IEnumerable<int> rows) {
       double[,] inputData = AlglibUtil.PrepareInputMatrix(dataset, allowedInputVariables, rows);
 

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/Scaling.cs

@@ -41 +41 @@
         scalingParameters.Add(pair.Key, Tuple.Create(pair.Value.Item1, pair.Value.Item2));
     }
-    public Scaling(Dataset ds, IEnumerable<string> variables, IEnumerable<int> rows) {
+    public Scaling(IDataset ds, IEnumerable<string> variables, IEnumerable<int> rows) {
       foreach (var variable in variables) {
         var values = ds.GetDoubleValues(variable, rows);
@@ -54 +54 @@
     }
 
-    public IEnumerable<double> GetScaledValues(Dataset ds, string variable, IEnumerable<int> rows) {
+    public IEnumerable<double> GetScaledValues(IDataset ds, string variable, IEnumerable<int> rows) {
       double min = scalingParameters[variable].Item1;
       double max = scalingParameters[variable].Item2;

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/Nca/NcaModel.cs

@@ -56 +56 @@
       this.classValues = (double[])original.classValues.Clone();
     }
-    public NcaModel(int k, double[,] transformationMatrix, Dataset 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) {
       Name = ItemName;
       Description = ItemDescription;
@@ -72 +72 @@
     }
 
-    public IEnumerable<double> GetEstimatedClassValues(Dataset dataset, IEnumerable<int> rows) {
+    public IEnumerable<double> GetEstimatedClassValues(IDataset dataset, IEnumerable<int> rows) {
       var ds = ReduceDataset(dataset, rows);
       return nnModel.GetEstimatedClassValues(ds, Enumerable.Range(0, ds.Rows));
@@ -85 +85 @@
     }
 
-    public double[,] Reduce(Dataset dataset, IEnumerable<int> rows) {
+    public double[,] Reduce(IDataset dataset, IEnumerable<int> rows) {
       var data = AlglibUtil.PrepareInputMatrix(dataset, allowedInputVariables, rows);
 
@@ -100 +100 @@
     }
 
-    public Dataset ReduceDataset(Dataset dataset, IEnumerable<int> rows) {
+    public Dataset ReduceDataset(IDataset dataset, IEnumerable<int> rows) {
       return new Dataset(Enumerable
           .Range(0, transformationMatrix.GetLength(1))

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour/NearestNeighbourModel.cs

@@ -96 +96 @@
         this.classValues = (double[])original.classValues.Clone();
     }
-    public NearestNeighbourModel(Dataset 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) {
       Name = ItemName;
       Description = ItemDescription;
@@ -135 +135 @@
     }
 
-    public IEnumerable<double> GetEstimatedValues(Dataset dataset, IEnumerable<int> rows) {
+    public IEnumerable<double> GetEstimatedValues(IDataset dataset, IEnumerable<int> rows) {
       double[,] inputData = AlglibUtil.PrepareInputMatrix(dataset, allowedInputVariables, rows);
 
@@ -163 +163 @@
     }
 
-    public IEnumerable<double> GetEstimatedClassValues(Dataset dataset, IEnumerable<int> rows) {
+    public 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);

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/NeuralNetwork/NeuralNetworkClassification.cs

@@ -179 +179 @@
     public static IClassificationSolution CreateNeuralNetworkClassificationSolution(IClassificationProblemData problemData, int nLayers, int nHiddenNodes1, int nHiddenNodes2, double decay, int restarts,
       out double rmsError, out double avgRelError, out double relClassError) {
-      Dataset dataset = problemData.Dataset;
+      var dataset = problemData.Dataset;
       string targetVariable = problemData.TargetVariable;
       IEnumerable<string> allowedInputVariables = problemData.AllowedInputVariables;

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/NeuralNetwork/NeuralNetworkEnsembleClassification.cs

@@ -124 +124 @@
     public NeuralNetworkEnsembleClassification()
       : base() {
-        var validHiddenLayerValues = new ItemSet<IntValue>(new IntValue[] { 
+      var validHiddenLayerValues = new ItemSet<IntValue>(new IntValue[] { 
         (IntValue)new IntValue(0).AsReadOnly(), 
         (IntValue)new IntValue(1).AsReadOnly(), 
@@ -165 +165 @@
     public static IClassificationSolution CreateNeuralNetworkEnsembleClassificationSolution(IClassificationProblemData problemData, int ensembleSize, int nLayers, int nHiddenNodes1, int nHiddenNodes2, double decay, int restarts,
       out double rmsError, out double avgRelError, out double relClassError) {
-      Dataset dataset = problemData.Dataset;
+      var dataset = problemData.Dataset;
       string targetVariable = problemData.TargetVariable;
       IEnumerable<string> allowedInputVariables = problemData.AllowedInputVariables;

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/NeuralNetwork/NeuralNetworkEnsembleModel.cs

@@ -86 +86 @@
     }
 
-    public IEnumerable<double> GetEstimatedValues(Dataset dataset, IEnumerable<int> rows) {
+    public IEnumerable<double> GetEstimatedValues(IDataset dataset, IEnumerable<int> rows) {
       double[,] inputData = AlglibUtil.PrepareInputMatrix(dataset, allowedInputVariables, rows);
 
@@ -103 +103 @@
     }
 
-    public IEnumerable<double> GetEstimatedClassValues(Dataset dataset, IEnumerable<int> rows) {
+    public IEnumerable<double> GetEstimatedClassValues(IDataset dataset, IEnumerable<int> rows) {
       double[,] inputData = AlglibUtil.PrepareInputMatrix(dataset, allowedInputVariables, rows);
 

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/NeuralNetwork/NeuralNetworkEnsembleRegression.cs

@@ -124 +124 @@
     public NeuralNetworkEnsembleRegression()
       : base() {
-        var validHiddenLayerValues = new ItemSet<IntValue>(new IntValue[] { 
+      var validHiddenLayerValues = new ItemSet<IntValue>(new IntValue[] { 
         (IntValue)new IntValue(0).AsReadOnly(), 
         (IntValue)new IntValue(1).AsReadOnly(), 
@@ -164 +164 @@
     public static IRegressionSolution CreateNeuralNetworkEnsembleRegressionSolution(IRegressionProblemData problemData, int ensembleSize, int nLayers, int nHiddenNodes1, int nHiddenNodes2, double decay, int restarts,
       out double rmsError, out double avgRelError) {
-      Dataset dataset = problemData.Dataset;
+      var dataset = problemData.Dataset;
       string targetVariable = problemData.TargetVariable;
       IEnumerable<string> allowedInputVariables = problemData.AllowedInputVariables;

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/NeuralNetwork/NeuralNetworkModel.cs

@@ -94 +94 @@
     }
 
-    public IEnumerable<double> GetEstimatedValues(Dataset dataset, IEnumerable<int> rows) {
+    public IEnumerable<double> GetEstimatedValues(IDataset dataset, IEnumerable<int> rows) {
       double[,] inputData = AlglibUtil.PrepareInputMatrix(dataset, allowedInputVariables, rows);
 
@@ -111 +111 @@
     }
 
-    public IEnumerable<double> GetEstimatedClassValues(Dataset dataset, IEnumerable<int> rows) {
+    public IEnumerable<double> GetEstimatedClassValues(IDataset dataset, IEnumerable<int> rows) {
       double[,] inputData = AlglibUtil.PrepareInputMatrix(dataset, allowedInputVariables, rows);
 

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/NeuralNetwork/NeuralNetworkRegression.cs

@@ -180 +180 @@
     public static IRegressionSolution CreateNeuralNetworkRegressionSolution(IRegressionProblemData problemData, int nLayers, int nHiddenNodes1, int nHiddenNodes2, double decay, int restarts,
       out double rmsError, out double avgRelError) {
-      Dataset dataset = problemData.Dataset;
+      var dataset = problemData.Dataset;
       string targetVariable = problemData.TargetVariable;
       IEnumerable<string> allowedInputVariables = problemData.AllowedInputVariables;

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestModel.cs

@@ -129 +129 @@
     }
 
-    public IEnumerable<double> GetEstimatedValues(Dataset dataset, IEnumerable<int> rows) {
+    public IEnumerable<double> GetEstimatedValues(IDataset dataset, IEnumerable<int> rows) {
       double[,] inputData = AlglibUtil.PrepareInputMatrix(dataset, AllowedInputVariables, rows);
       AssertInputMatrix(inputData);
@@ -147 +147 @@
     }
 
-    public IEnumerable<double> GetEstimatedClassValues(Dataset dataset, IEnumerable<int> rows) {
+    public IEnumerable<double> GetEstimatedClassValues(IDataset dataset, IEnumerable<int> rows) {
       double[,] inputData = AlglibUtil.PrepareInputMatrix(dataset, AllowedInputVariables, rows);
       AssertInputMatrix(inputData);
@@ -205 +205 @@
       outOfBagRmsError = rep.oobrmserror;
 
-      return new RandomForestModel(dForest,seed, problemData,nTrees, r, m);
+      return new RandomForestModel(dForest, seed, problemData, nTrees, r, m);
     }
 
@@ -242 +242 @@
       outOfBagRelClassificationError = rep.oobrelclserror;
 
-      return new RandomForestModel(dForest,seed, problemData,nTrees, r, m, classValues);
+      return new RandomForestModel(dForest, seed, problemData, nTrees, r, m, classValues);
     }
 

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestUtil.cs

@@ -90 +90 @@
 
   public static class RandomForestUtil {
-    private static readonly object locker = new object();
-
     private static void CrossValidate(IRegressionProblemData problemData, Tuple<IEnumerable<int>, IEnumerable<int>>[] partitions, int nTrees, double r, double m, int seed, out double avgTestMse) {
       avgTestMse = 0;
@@ -132 +130 @@
     }
 
-    // grid search without cross-validation since in the case of random forests, the out-of-bag estimate is unbiased
+    /// <summary>
+    /// Grid search without crossvalidation (since for random forests the out-of-bag estimate is unbiased)
+    /// </summary>
+    /// <param name="problemData">The regression problem data</param>
+    /// <param name="parameterRanges">The ranges for each parameter in the grid search</param>
+    /// <param name="seed">The random seed (required by the random forest model)</param>
+    /// <param name="maxDegreeOfParallelism">The maximum allowed number of threads (to parallelize the grid search)</param>
     public static RFParameter GridSearch(IRegressionProblemData problemData, Dictionary<string, IEnumerable<double>> parameterRanges, int seed = 12345, int maxDegreeOfParallelism = 1) {
       var setters = parameterRanges.Keys.Select(GenerateSetter).ToList();
@@ -139 +143 @@
       RFParameter bestParameters = new RFParameter();
 
+      var locker = new object();
       Parallel.ForEach(crossProduct, new ParallelOptions { MaxDegreeOfParallelism = maxDegreeOfParallelism }, parameterCombination => {
         var parameterValues = parameterCombination.ToList();
@@ -156 +161 @@
     }
 
+    /// <summary>
+    /// Grid search without crossvalidation (since for random forests the out-of-bag estimate is unbiased)
+    /// </summary>
+    /// <param name="problemData">The classification problem data</param>
+    /// <param name="parameterRanges">The ranges for each parameter in the grid search</param>
+    /// <param name="seed">The random seed (required by the random forest model)</param>
+    /// <param name="maxDegreeOfParallelism">The maximum allowed number of threads (to parallelize the grid search)</param>
     public static RFParameter GridSearch(IClassificationProblemData problemData, Dictionary<string, IEnumerable<double>> parameterRanges, int seed = 12345, int maxDegreeOfParallelism = 1) {
       var setters = parameterRanges.Keys.Select(GenerateSetter).ToList();
@@ -163 +175 @@
       RFParameter bestParameters = new RFParameter();
 
+      var locker = new object();
       Parallel.ForEach(crossProduct, new ParallelOptions { MaxDegreeOfParallelism = maxDegreeOfParallelism }, parameterCombination => {
         var parameterValues = parameterCombination.ToList();
@@ -181 +194 @@
     }
 
+    /// <summary>
+    /// Grid search with crossvalidation
+    /// </summary>
+    /// <param name="problemData">The regression problem data</param>
+    /// <param name="numberOfFolds">The number of folds for crossvalidation</param>
+    /// <param name="shuffleFolds">Specifies whether the folds should be shuffled</param>
+    /// <param name="parameterRanges">The ranges for each parameter in the grid search</param>
+    /// <param name="seed">The random seed (required by the random forest model)</param>
+    /// <param name="maxDegreeOfParallelism">The maximum allowed number of threads (to parallelize the grid search)</param>
+    /// <returns>The best parameter values found by the grid search</returns>
     public static RFParameter GridSearch(IRegressionProblemData problemData, int numberOfFolds, bool shuffleFolds, Dictionary<string, IEnumerable<double>> parameterRanges, int seed = 12345, int maxDegreeOfParallelism = 1) {
       DoubleValue mse = new DoubleValue(Double.MaxValue);
@@ -189 +212 @@
       var crossProduct = parameterRanges.Values.CartesianProduct();
 
+      var locker = new object();
       Parallel.ForEach(crossProduct, new ParallelOptions { MaxDegreeOfParallelism = maxDegreeOfParallelism }, parameterCombination => {
         var parameterValues = parameterCombination.ToList();
@@ -208 +232 @@
     }
 
+    /// <summary>
+    /// Grid search with crossvalidation
+    /// </summary>
+    /// <param name="problemData">The classification problem data</param>
+    /// <param name="numberOfFolds">The number of folds for crossvalidation</param>
+    /// <param name="shuffleFolds">Specifies whether the folds should be shuffled</param>
+    /// <param name="parameterRanges">The ranges for each parameter in the grid search</param>
+    /// <param name="seed">The random seed (for shuffling)</param>
+    /// <param name="maxDegreeOfParallelism">The maximum allowed number of threads (to parallelize the grid search)</param>
     public static RFParameter GridSearch(IClassificationProblemData problemData, int numberOfFolds, bool shuffleFolds, Dictionary<string, IEnumerable<double>> parameterRanges, int seed = 12345, int maxDegreeOfParallelism = 1) {
       DoubleValue accuracy = new DoubleValue(0);
@@ -216 +249 @@
       var partitions = GenerateRandomForestPartitions(problemData, numberOfFolds, shuffleFolds);
 
+      var locker = new object();
       Parallel.ForEach(crossProduct, new ParallelOptions { MaxDegreeOfParallelism = maxDegreeOfParallelism }, parameterCombination => {
         var parameterValues = parameterCombination.ToList();

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/SupportVectorMachine/SupportVectorClassification.cs

@@ -149 +149 @@
     public static SupportVectorClassificationSolution CreateSupportVectorClassificationSolution(IClassificationProblemData problemData, IEnumerable<string> allowedInputVariables,
       int svmType, int kernelType, double cost, double nu, double gamma, int degree, out double trainingAccuracy, out double testAccuracy, out int nSv) {
-      Dataset dataset = problemData.Dataset;
+      var dataset = problemData.Dataset;
       string targetVariable = problemData.TargetVariable;
       IEnumerable<int> rows = problemData.TrainingIndices;

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/SupportVectorMachine/SupportVectorMachineModel.cs

@@ -120 +120 @@
 
     #region IRegressionModel Members
-    public IEnumerable<double> GetEstimatedValues(Dataset dataset, IEnumerable<int> rows) {
+    public IEnumerable<double> GetEstimatedValues(IDataset dataset, IEnumerable<int> rows) {
       return GetEstimatedValuesHelper(dataset, rows);
     }
@@ -132 +132 @@
 
     #region IClassificationModel Members
-    public IEnumerable<double> GetEstimatedClassValues(Dataset dataset, IEnumerable<int> rows) {
+    public 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
@@ -159 +159 @@
     }
     #endregion
-    private IEnumerable<double> GetEstimatedValuesHelper(Dataset dataset, IEnumerable<int> rows) {
+    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);

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/SupportVectorMachine/SupportVectorMachineUtil.cs

@@ -40 +40 @@
     /// <param name="rowIndices">The rows of the dataset that should be contained in the resulting SVM-problem</param>
     /// <returns>A problem data type that can be used to train a support vector machine.</returns>
-    public static svm_problem CreateSvmProblem(Dataset dataset, string targetVariable, IEnumerable<string> inputVariables, IEnumerable<int> rowIndices) {
+    public static svm_problem CreateSvmProblem(IDataset dataset, string targetVariable, IEnumerable<string> inputVariables, IEnumerable<int> rowIndices) {
       double[] targetVector = dataset.GetDoubleValues(targetVariable, rowIndices).ToArray();
       svm_node[][] nodes = new svm_node[targetVector.Length][];

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/SupportVectorMachine/SupportVectorRegression.cs

@@ -152 +152 @@
       string svmType, string kernelType, double cost, double nu, double gamma, double epsilon, int degree,
       out double trainingR2, out double testR2, out int nSv) {
-      Dataset dataset = problemData.Dataset;
+      var dataset = problemData.Dataset;
       string targetVariable = problemData.TargetVariable;
       IEnumerable<int> rows = problemData.TrainingIndices;

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/kMeans/KMeansClustering.cs

@@ -83 +83 @@
 
     public static KMeansClusteringSolution CreateKMeansSolution(IClusteringProblemData problemData, int k, int restarts) {
-      Dataset dataset = problemData.Dataset;
+      var dataset = problemData.Dataset;
       IEnumerable<string> allowedInputVariables = problemData.AllowedInputVariables;
       IEnumerable<int> rows = problemData.TrainingIndices;

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/kMeans/KMeansClusteringModel.cs

@@ -81 +81 @@
 
 
-    public IEnumerable<int> GetClusterValues(Dataset dataset, IEnumerable<int> rows) {
+    public IEnumerable<int> GetClusterValues(IDataset dataset, IEnumerable<int> rows) {
       return KMeansClusteringUtil.FindClosestCenters(centers, dataset, allowedInputVariables, rows);
     }

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/kMeans/KMeansClusteringUtil.cs

@@ -27 +27 @@
 namespace HeuristicLab.Algorithms.DataAnalysis {
   public static class KMeansClusteringUtil {
-    public static IEnumerable<int> FindClosestCenters(IEnumerable<double[]> centers, Dataset dataset, IEnumerable<string> allowedInputVariables, IEnumerable<int> rows) {
+    public static IEnumerable<int> FindClosestCenters(IEnumerable<double[]> centers, IDataset dataset, IEnumerable<string> allowedInputVariables, IEnumerable<int> rows) {
       int nRows = rows.Count();
       int nCols = allowedInputVariables.Count();
@@ -58 +58 @@
     }
 
-    public static double CalculateIntraClusterSumOfSquares(KMeansClusteringModel model, Dataset dataset, IEnumerable<int> rows) {
+    public static double CalculateIntraClusterSumOfSquares(KMeansClusteringModel model, IDataset dataset, IEnumerable<int> rows) {
       List<int> clusterValues = model.GetClusterValues(dataset, rows).ToList();
       List<string> allowedInputVariables = model.AllowedInputVariables.ToList();