Changeset 12509 for trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation

Timestamp:

06/25/15 13:46:24 (9 years ago)

Author:

mkommend

Message:

#2276: Reintegrated branch for dataset refactoring.

Location:

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation

Files:

• Classification/ClassificationEnsembleModel.cs (modified) (2 diffs)
• Classification/ClassificationEnsembleSolution.cs (modified) (1 diff)
• Classification/ClassificationProblemData.cs (modified) (2 diffs)
• Classification/DiscriminantFunctionClassificationModel.cs (modified) (1 diff)
• DataAnalysisProblemData.cs (modified) (3 diffs)
• Regression/ConstantRegressionModel.cs (modified) (1 diff)
• Regression/RegressionEnsembleModel.cs (modified) (2 diffs)
• Regression/RegressionEnsembleSolution.cs (modified) (1 diff)
• Regression/RegressionProblemData.cs (modified) (1 diff)
• Regression/RegressionSolution.cs (modified) (1 diff)
• TimeSeriesPrognosis/Models/ConstantTimeSeriesPrognosisModel.cs (modified) (1 diff)
• TimeSeriesPrognosis/Models/TimeSeriesPrognosisAutoRegressiveModel.cs (modified) (2 diffs)
• TimeSeriesPrognosis/TimeSeriesPrognosisProblemData.cs (modified) (1 diff)

trunk/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

trunk/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

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationProblemData.cs

@@ -324 +324 @@
     }
 
-    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();
@@ -338 +338 @@
     }
 
-    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

trunk/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)) {

trunk/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)));

trunk/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);
     }

trunk/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();

trunk/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

trunk/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();

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionSolution.cs

@@ -63 +63 @@
 
     public override IEnumerable<double> GetEstimatedValues(IEnumerable<int> rows) {
-      var rowsToEvaluate = rows.Except(evaluationCache.Keys);
+      var rowsToEvaluate = rows.Where(row => !evaluationCache.ContainsKey(row));
       var rowsEnumerator = rowsToEvaluate.GetEnumerator();
       var valuesEnumerator = Model.GetEstimatedValues(ProblemData.Dataset, rowsToEvaluate).GetEnumerator();

trunk/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));
     }

trunk/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) {

trunk/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)));