Changeset 11571 for branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Problems.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.Problems.DataAnalysis/3.4

Files:

• Dataset.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis-3.4.csproj (modified) (2 diffs)
• Implementation/Classification/ClassificationEnsembleModel.cs (modified) (2 diffs)
• Implementation/Classification/ClassificationEnsembleSolution.cs (modified) (1 diff)
• Implementation/Classification/ClassificationProblemData.cs (modified) (2 diffs)
• Implementation/Classification/DiscriminantFunctionClassificationModel.cs (modified) (1 diff)
• Implementation/DataAnalysisProblemData.cs (modified) (3 diffs)
• Implementation/Regression/ConstantRegressionModel.cs (modified) (1 diff)
• Implementation/Regression/RegressionEnsembleModel.cs (modified) (2 diffs)
• Implementation/Regression/RegressionEnsembleSolution.cs (modified) (1 diff)
• Implementation/Regression/RegressionProblemData.cs (modified) (1 diff)
• Implementation/TimeSeriesPrognosis/Models/ConstantTimeSeriesPrognosisModel.cs (modified) (1 diff)
• Implementation/TimeSeriesPrognosis/Models/TimeSeriesPrognosisAutoRegressiveModel.cs (modified) (2 diffs)
• Implementation/TimeSeriesPrognosis/TimeSeriesPrognosisProblemData.cs (modified) (1 diff)
• Interfaces/Classification/IClassificationEnsembleModel.cs (modified) (1 diff)
• Interfaces/Classification/IClassificationEnsembleSolution.cs (modified) (1 diff)
• Interfaces/Classification/IClassificationModel.cs (modified) (1 diff)
• Interfaces/Classification/IDiscriminantFunctionClassificationModel.cs (modified) (1 diff)
• Interfaces/Clustering/IClusteringModel.cs (modified) (1 diff)
• Interfaces/IDataAnalysisProblemData.cs (modified) (1 diff)
• Interfaces/IDataset.cs (added)
• Interfaces/Regression/IRegressionEnsembleModel.cs (modified) (1 diff)
• Interfaces/Regression/IRegressionEnsembleSolution.cs (modified) (1 diff)
• Interfaces/Regression/IRegressionModel.cs (modified) (1 diff)
• Interfaces/TimeSeriesPrognosis/ITimeSeriesPrognosisModel.cs (modified) (1 diff)
• SimpleDataset.cs (added)

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Problems.DataAnalysis/3.4/Dataset.cs

@@ -33 +33 @@
   [Item("Dataset", "Represents a dataset containing data that should be analyzed.")]
   [StorableClass]
-  public sealed class Dataset : NamedItem, IStringConvertibleMatrix {
+  public sealed class Dataset : NamedItem, IDataset {
     [StorableConstructor]
     private Dataset(bool deserializing) : base(deserializing) { }

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

@@ -158 +158 @@
     <Compile Include="Interfaces\Classification\IDiscriminantFunctionThresholdCalculator.cs" />
     <Compile Include="Interfaces\IDataAnalysisSolutionExporter.cs" />
+    <Compile Include="Interfaces\IDataset.cs" />
     <Compile Include="Interfaces\IDependencyCalculator.cs" />
     <Compile Include="Interfaces\ITransformation.cs" />
@@ -222 +223 @@
     <Compile Include="Implementation\Classification\ThresholdCalculators\NormalDistributionCutPointsThresholdCalculator.cs" />
     <Compile Include="Implementation\Classification\ThresholdCalculators\ThresholdCalculator.cs" />
+    <Compile Include="SimpleDataset.cs" />
     <None Include="HeuristicLab.snk" />
     <None Include="Plugin.cs.frame" />

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationEnsembleModel.cs

@@ -67 +67 @@
     }
 
-    public IEnumerable<IEnumerable<double>> GetEstimatedClassValueVectors(Dataset dataset, IEnumerable<int> rows) {
+    public IEnumerable<IEnumerable<double>> GetEstimatedClassValueVectors(IDataset dataset, IEnumerable<int> rows) {
       var estimatedValuesEnumerators = (from model in models
                                         select model.GetEstimatedClassValues(dataset, rows).GetEnumerator())
@@ -82 +82 @@
     #region IClassificationModel Members
 
-    public IEnumerable<double> GetEstimatedClassValues(Dataset dataset, IEnumerable<int> rows) {
+    public IEnumerable<double> GetEstimatedClassValues(IDataset dataset, IEnumerable<int> rows) {
       foreach (var estimatedValuesVector in GetEstimatedClassValueVectors(dataset, rows)) {
         // return the class which is most often occuring

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationEnsembleSolution.cs

@@ -231 +231 @@
     }
 
-    public IEnumerable<IEnumerable<double>> GetEstimatedClassValueVectors(Dataset dataset, IEnumerable<int> rows) {
+    public IEnumerable<IEnumerable<double>> GetEstimatedClassValueVectors(IDataset dataset, IEnumerable<int> rows) {
       if (!Model.Models.Any()) yield break;
       var estimatedValuesEnumerators = (from model in Model.Models

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationProblemData.cs

@@ -300 +300 @@
     }
 
-    public ClassificationProblemData(Dataset dataset, IEnumerable<string> allowedInputVariables, string targetVariable, IEnumerable<ITransformation> transformations = null)
+    public ClassificationProblemData(IDataset dataset, IEnumerable<string> allowedInputVariables, string targetVariable, IEnumerable<ITransformation> transformations = null)
       : base(dataset, allowedInputVariables, transformations ?? Enumerable.Empty<ITransformation>()) {
       var validTargetVariableValues = CheckVariablesForPossibleTargetVariables(dataset).Select(x => new StringValue(x).AsReadOnly()).ToList();
@@ -313 +313 @@
     }
 
-    public static IEnumerable<string> CheckVariablesForPossibleTargetVariables(Dataset dataset) {
+    public static IEnumerable<string> CheckVariablesForPossibleTargetVariables(IDataset dataset) {
       int maxSamples = Math.Min(InspectedRowsToDetermineTargets, dataset.Rows);
       var validTargetVariables = (from v in dataset.DoubleVariables

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/DiscriminantFunctionClassificationModel.cs

@@ -111 +111 @@
 
 
-    public IEnumerable<double> GetEstimatedValues(Dataset dataset, IEnumerable<int> rows) {
+    public IEnumerable<double> GetEstimatedValues(IDataset dataset, IEnumerable<int> rows) {
       return model.GetEstimatedValues(dataset, rows);
     }
 
-    public IEnumerable<double> GetEstimatedClassValues(Dataset dataset, IEnumerable<int> rows) {
+    public IEnumerable<double> GetEstimatedClassValues(IDataset dataset, IEnumerable<int> rows) {
       if (!Thresholds.Any() && !ClassValues.Any()) throw new ArgumentException("No thresholds and class values were set for the current classification model.");
       foreach (var x in GetEstimatedValues(dataset, rows)) {

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/DataAnalysisProblemData.cs

@@ -63 +63 @@
       get { return isEmpty; }
     }
-    public Dataset Dataset {
+    public IDataset Dataset {
       get { return DatasetParameter.Value; }
     }
@@ -126 +126 @@
     }
 
-    protected DataAnalysisProblemData(Dataset dataset, IEnumerable<string> allowedInputVariables, IEnumerable<ITransformation> transformations = null) {
+    protected DataAnalysisProblemData(IDataset dataset, IEnumerable<string> allowedInputVariables, IEnumerable<ITransformation> transformations = null) {
       if (dataset == null) throw new ArgumentNullException("The dataset must not be null.");
       if (allowedInputVariables == null) throw new ArgumentNullException("The allowedInputVariables must not be null.");
@@ -144 +144 @@
       var transformationsList = new ItemList<ITransformation>(transformations ?? Enumerable.Empty<ITransformation>());
 
-      Parameters.Add(new FixedValueParameter<Dataset>(DatasetParameterName, "", dataset));
+      Parameters.Add(new FixedValueParameter<Dataset>(DatasetParameterName, "", (Dataset)dataset));
       Parameters.Add(new FixedValueParameter<ReadOnlyCheckedItemList<StringValue>>(InputVariablesParameterName, "", inputVariables.AsReadOnly()));
       Parameters.Add(new FixedValueParameter<IntRange>(TrainingPartitionParameterName, "", new IntRange(trainingPartitionStart, trainingPartitionEnd)));

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/ConstantRegressionModel.cs

@@ -51 +51 @@
     }
 
-    public IEnumerable<double> GetEstimatedValues(Dataset dataset, IEnumerable<int> rows) {
+    public IEnumerable<double> GetEstimatedValues(IDataset dataset, IEnumerable<int> rows) {
       return rows.Select(row => Constant);
     }

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionEnsembleModel.cs

@@ -80 +80 @@
     }
 
-    public IEnumerable<IEnumerable<double>> GetEstimatedValueVectors(Dataset dataset, IEnumerable<int> rows) {
+    public IEnumerable<IEnumerable<double>> GetEstimatedValueVectors(IDataset dataset, IEnumerable<int> rows) {
       var estimatedValuesEnumerators = (from model in models
                                         select model.GetEstimatedValues(dataset, rows).GetEnumerator())
@@ -95 +95 @@
     #region IRegressionModel Members
 
-    public IEnumerable<double> GetEstimatedValues(Dataset dataset, IEnumerable<int> rows) {
+    public IEnumerable<double> GetEstimatedValues(IDataset dataset, IEnumerable<int> rows) {
       foreach (var estimatedValuesVector in GetEstimatedValueVectors(dataset, rows)) {
         yield return estimatedValuesVector.Average();

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionEnsembleSolution.cs

@@ -232 +232 @@
     }
 
-    public IEnumerable<IEnumerable<double>> GetEstimatedValueVectors(Dataset dataset, IEnumerable<int> rows) {
+    public IEnumerable<IEnumerable<double>> GetEstimatedValueVectors(IDataset dataset, IEnumerable<int> rows) {
       if (!Model.Models.Any()) yield break;
       var estimatedValuesEnumerators = (from model in Model.Models

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionProblemData.cs

@@ -137 +137 @@
     }
 
-    public RegressionProblemData(Dataset dataset, IEnumerable<string> allowedInputVariables, string targetVariable, IEnumerable<ITransformation> transformations = null)
+    public RegressionProblemData(IDataset dataset, IEnumerable<string> allowedInputVariables, string targetVariable, IEnumerable<ITransformation> transformations = null)
       : base(dataset, allowedInputVariables, transformations ?? Enumerable.Empty<ITransformation>()) {
       var variables = InputVariables.Select(x => x.AsReadOnly()).ToList();

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/TimeSeriesPrognosis/Models/ConstantTimeSeriesPrognosisModel.cs

@@ -39 +39 @@
     public ConstantTimeSeriesPrognosisModel(double constant) : base(constant) { }
 
-    public IEnumerable<IEnumerable<double>> GetPrognosedValues(Dataset dataset, IEnumerable<int> rows, IEnumerable<int> horizons) {
+    public IEnumerable<IEnumerable<double>> GetPrognosedValues(IDataset dataset, IEnumerable<int> rows, IEnumerable<int> horizons) {
       return horizons.Select(horizon => Enumerable.Repeat(Constant, horizon));
     }

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/TimeSeriesPrognosis/Models/TimeSeriesPrognosisAutoRegressiveModel.cs

@@ -58 +58 @@
     }
 
-    public IEnumerable<IEnumerable<double>> GetPrognosedValues(Dataset dataset, IEnumerable<int> rows, IEnumerable<int> horizons) {
+    public IEnumerable<IEnumerable<double>> GetPrognosedValues(IDataset dataset, IEnumerable<int> rows, IEnumerable<int> horizons) {
       var rowsEnumerator = rows.GetEnumerator();
       var horizonsEnumerator = horizons.GetEnumerator();
@@ -91 +91 @@
     }
 
-    public IEnumerable<double> GetEstimatedValues(Dataset dataset, IEnumerable<int> rows) {
+    public IEnumerable<double> GetEstimatedValues(IDataset dataset, IEnumerable<int> rows) {
       var targetVariables = dataset.GetReadOnlyDoubleValues(TargetVariable);
       foreach (int row in rows) {

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/TimeSeriesPrognosis/TimeSeriesPrognosisProblemData.cs

@@ -1582 +1582 @@
       TrainingPartition.Start = 50;
     }
-    public TimeSeriesPrognosisProblemData(Dataset dataset, IEnumerable<string> allowedInputVariables, string targetVariable, IEnumerable<ITransformation> transformations = null)
+    public TimeSeriesPrognosisProblemData(IDataset dataset, IEnumerable<string> allowedInputVariables, string targetVariable, IEnumerable<ITransformation> transformations = null)
       : base(dataset, allowedInputVariables, targetVariable, transformations ?? Enumerable.Empty<ITransformation>()) {
       Parameters.Add(new FixedValueParameter<IntValue>(TrainingHorizonParameterName, "Specifies the horizon (how far the prognosis reaches in the future) for each training sample.", new IntValue(1)));

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Problems.DataAnalysis/3.4/Interfaces/Classification/IClassificationEnsembleModel.cs

@@ -26 +26 @@
     void Remove(IClassificationModel model);
     IEnumerable<IClassificationModel> Models { get; }
-    IEnumerable<IEnumerable<double>> GetEstimatedClassValueVectors(Dataset dataset, IEnumerable<int> rows);
+    IEnumerable<IEnumerable<double>> GetEstimatedClassValueVectors(IDataset dataset, IEnumerable<int> rows);
   }
 }

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Problems.DataAnalysis/3.4/Interfaces/Classification/IClassificationEnsembleSolution.cs

@@ -26 +26 @@
     new IClassificationEnsembleModel Model { get; }
     IItemCollection<IClassificationSolution> ClassificationSolutions { get; }
-    IEnumerable<IEnumerable<double>> GetEstimatedClassValueVectors(Dataset dataset, IEnumerable<int> rows);
+    IEnumerable<IEnumerable<double>> GetEstimatedClassValueVectors(IDataset dataset, IEnumerable<int> rows);
   }
 }

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Problems.DataAnalysis/3.4/Interfaces/Classification/IClassificationModel.cs

@@ -23 +23 @@
 namespace HeuristicLab.Problems.DataAnalysis {
   public interface IClassificationModel : IDataAnalysisModel {
-    IEnumerable<double> GetEstimatedClassValues(Dataset dataset, IEnumerable<int> rows);
+    IEnumerable<double> GetEstimatedClassValues(IDataset dataset, IEnumerable<int> rows);
     IClassificationSolution CreateClassificationSolution(IClassificationProblemData problemData);
   }

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Problems.DataAnalysis/3.4/Interfaces/Classification/IDiscriminantFunctionClassificationModel.cs

@@ -30 +30 @@
     // class values and thresholds can only be assigned simultanously
     void SetThresholdsAndClassValues(IEnumerable<double> thresholds, IEnumerable<double> classValues);
-    IEnumerable<double> GetEstimatedValues(Dataset dataset, IEnumerable<int> rows);
+    IEnumerable<double> GetEstimatedValues(IDataset dataset, IEnumerable<int> rows);
 
     event EventHandler ThresholdsChanged;

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Problems.DataAnalysis/3.4/Interfaces/Clustering/IClusteringModel.cs

@@ -23 +23 @@
 namespace HeuristicLab.Problems.DataAnalysis {
   public interface IClusteringModel : IDataAnalysisModel {
-    IEnumerable<int> GetClusterValues(Dataset dataset, IEnumerable<int> rows);
+    IEnumerable<int> GetClusterValues(IDataset dataset, IEnumerable<int> rows);
   }
 }

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Problems.DataAnalysis/3.4/Interfaces/IDataAnalysisProblemData.cs

@@ -29 +29 @@
     bool IsEmpty { get; }
 
-    Dataset Dataset { get; }
+    IDataset Dataset { get; }
     ICheckedItemList<StringValue> InputVariables { get; }
     IEnumerable<string> AllowedInputVariables { get; }

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Problems.DataAnalysis/3.4/Interfaces/Regression/IRegressionEnsembleModel.cs

@@ -26 +26 @@
     void Remove(IRegressionModel model);
     IEnumerable<IRegressionModel> Models { get; }
-    IEnumerable<IEnumerable<double>> GetEstimatedValueVectors(Dataset dataset, IEnumerable<int> rows);
+    IEnumerable<IEnumerable<double>> GetEstimatedValueVectors(IDataset dataset, IEnumerable<int> rows);
   }
 }

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Problems.DataAnalysis/3.4/Interfaces/Regression/IRegressionEnsembleSolution.cs

@@ -27 +27 @@
     new RegressionEnsembleProblemData ProblemData { get; set; }
     IItemCollection<IRegressionSolution> RegressionSolutions { get; }
-    IEnumerable<IEnumerable<double>> GetEstimatedValueVectors(Dataset dataset, IEnumerable<int> rows);
+    IEnumerable<IEnumerable<double>> GetEstimatedValueVectors(IDataset dataset, IEnumerable<int> rows);
   }
 }

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Problems.DataAnalysis/3.4/Interfaces/Regression/IRegressionModel.cs

@@ -23 +23 @@
 namespace HeuristicLab.Problems.DataAnalysis {
   public interface IRegressionModel : IDataAnalysisModel {
-    IEnumerable<double> GetEstimatedValues(Dataset dataset, IEnumerable<int> rows);
+    IEnumerable<double> GetEstimatedValues(IDataset dataset, IEnumerable<int> rows);
     IRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData);
   }

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Problems.DataAnalysis/3.4/Interfaces/TimeSeriesPrognosis/ITimeSeriesPrognosisModel.cs

@@ -23 +23 @@
 namespace HeuristicLab.Problems.DataAnalysis {
   public interface ITimeSeriesPrognosisModel : IRegressionModel {
-    IEnumerable<IEnumerable<double>> GetPrognosedValues(Dataset dataset, IEnumerable<int> rows, IEnumerable<int> horizons);
+    IEnumerable<IEnumerable<double>> GetPrognosedValues(IDataset dataset, IEnumerable<int> rows, IEnumerable<int> horizons);
     ITimeSeriesPrognosisSolution CreateTimeSeriesPrognosisSolution(ITimeSeriesPrognosisProblemData problemData);
   }