Changeset 11114 for trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation

Timestamp:

07/07/14 15:33:56 (11 years ago)

Author:

mkommend

Message:

#2206: Merged data preprocessing into the trunk.

Location:

trunk/sources

Files:

• . (modified) (1 prop)
• HeuristicLab.Problems.DataAnalysis (modified) (1 prop)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationProblemData.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Clustering/ClusteringProblemData.cs (modified) (2 diffs)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/DataAnalysisProblemData.cs (modified) (7 diffs)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionProblemData.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/TimeSeriesPrognosis/TimeSeriesPrognosisProblemData.cs (modified) (2 diffs)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Transformations (copied) (copied from branches/DataPreprocessing/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Transformations)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Transformations/ExponentialTransformation.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Transformations/LinearTransformation.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Transformations/LogarithmicTransformation.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Transformations/PowerTransformation.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Transformations/ReciprocalTransformation.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Transformations/ShiftStandardDistributionTransformation.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Transformations/ShiftToRangeTransformation.cs (modified) (1 diff)

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

@@ -300 +300 @@
     }
 
-    public ClassificationProblemData(Dataset dataset, IEnumerable<string> allowedInputVariables, string targetVariable)
-      : base(dataset, allowedInputVariables) {
+    public ClassificationProblemData(Dataset 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();
       var target = validTargetVariableValues.Where(x => x.Value == targetVariable).DefaultIfEmpty(validTargetVariableValues.First()).First();

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Clustering/ClusteringProblemData.cs

@@ -21 +21 @@
 
 using System.Collections.Generic;
+using System.Linq;
 using HeuristicLab.Common;
 using HeuristicLab.Core;
@@ -86 +87 @@
     }
 
-    public ClusteringProblemData(Dataset dataset, IEnumerable<string> allowedInputVariables)
-      : base(dataset, allowedInputVariables) {
+    public ClusteringProblemData(Dataset dataset, IEnumerable<string> allowedInputVariables, IEnumerable<ITransformation> transformations = null)
+      : base(dataset, allowedInputVariables, transformations ?? Enumerable.Empty<ITransformation>()) {
     }
   }

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

@@ -38 +38 @@
     protected const string TrainingPartitionParameterName = "TrainingPartition";
     protected const string TestPartitionParameterName = "TestPartition";
+    protected const string TransformationsParameterName = "Transformations";
 
     #region parameter properites
@@ -51 +52 @@
     public IFixedValueParameter<IntRange> TestPartitionParameter {
       get { return (IFixedValueParameter<IntRange>)Parameters[TestPartitionParameterName]; }
+    }
+    public IFixedValueParameter<ReadOnlyItemList<ITransformation>> TransformationsParameter {
+      get { return (IFixedValueParameter<ReadOnlyItemList<ITransformation>>)Parameters[TransformationsParameterName]; }
     }
     #endregion
@@ -89 +93 @@
     }
 
+    public IEnumerable<ITransformation> Transformations {
+      get { return TransformationsParameter.Value; }
+    }
+
     public virtual bool IsTrainingSample(int index) {
       return index >= 0 && index < Dataset.Rows &&
@@ -111 +119 @@
     [StorableHook(HookType.AfterDeserialization)]
     private void AfterDeserialization() {
+      if (!Parameters.ContainsKey(TransformationsParameterName)) {
+        Parameters.Add(new FixedValueParameter<ReadOnlyItemList<ITransformation>>(TransformationsParameterName, "", new ItemList<ITransformation>().AsReadOnly()));
+        TransformationsParameter.Hidden = true;
+      }
       RegisterEventHandlers();
     }
 
-    protected DataAnalysisProblemData(Dataset dataset, IEnumerable<string> allowedInputVariables) {
+    protected DataAnalysisProblemData(Dataset dataset, IEnumerable<string> allowedInputVariables, IEnumerable<ITransformation> transformations) {
       if (dataset == null) throw new ArgumentNullException("The dataset must not be null.");
       if (allowedInputVariables == null) throw new ArgumentNullException("The allowedInputVariables must not be null.");
@@ -120 +132 @@
       if (allowedInputVariables.Except(dataset.DoubleVariables).Any())
         throw new ArgumentException("All allowed input variables must be present in the dataset and of type double.");
+
+      if (transformations == null) throw new ArgumentNullException("The transformations must not be null.");
 
       var inputVariables = new CheckedItemList<StringValue>(dataset.DoubleVariables.Select(x => new StringValue(x)));
@@ -130 +144 @@
       int testPartitionEnd = dataset.Rows;
 
+      var transformationsList = new ItemList<ITransformation>(transformations);
+
       Parameters.Add(new FixedValueParameter<Dataset>(DatasetParameterName, "", dataset));
       Parameters.Add(new FixedValueParameter<ReadOnlyCheckedItemList<StringValue>>(InputVariablesParameterName, "", inputVariables.AsReadOnly()));
       Parameters.Add(new FixedValueParameter<IntRange>(TrainingPartitionParameterName, "", new IntRange(trainingPartitionStart, trainingPartitionEnd)));
       Parameters.Add(new FixedValueParameter<IntRange>(TestPartitionParameterName, "", new IntRange(testPartitionStart, testPartitionEnd)));
+      Parameters.Add(new FixedValueParameter<ReadOnlyItemList<ITransformation>>(TransformationsParameterName, "", transformationsList.AsReadOnly()));
+
+      TransformationsParameter.Hidden = true;
 
       ((ValueParameter<Dataset>)DatasetParameter).ReactOnValueToStringChangedAndValueItemImageChanged = false;
@@ -144 +163 @@
       TrainingPartition.ValueChanged += new EventHandler(Parameter_ValueChanged);
       TestPartition.ValueChanged += new EventHandler(Parameter_ValueChanged);
+      TransformationsParameter.ValueChanged += new EventHandler(Parameter_ValueChanged);
     }
 

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

@@ -137 +137 @@
     }
 
-    public RegressionProblemData(Dataset dataset, IEnumerable<string> allowedInputVariables, string targetVariable)
-      : base(dataset, allowedInputVariables) {
+    public RegressionProblemData(Dataset 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();
       Parameters.Add(new ConstrainedValueParameter<StringValue>(TargetVariableParameterName, new ItemSet<StringValue>(variables), variables.Where(x => x.Value == targetVariable).First()));

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)
-      : base(dataset, allowedInputVariables, targetVariable) {
+    public TimeSeriesPrognosisProblemData(Dataset 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)));
       Parameters.Add(new FixedValueParameter<IntValue>(TestHorizonParameterName, "Specifies the horizon (how far the prognosis reaches in the future) for each test sample.", new IntValue(1)));
@@ -1643 +1643 @@
 
       var trainingDataStart = TrainingIndices.First();
-      
+
       base.AdjustProblemDataProperties(problemData);
-      
+
       TestPartition.Start = trainingDataStart;
 

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Transformations/ExponentialTransformation.cs

@@ -29 +29 @@
     [StorableConstructor]
     protected ExponentialTransformation(bool deserializing) : base(deserializing) { }
-    protected ExponentialTransformation(Transformation<double> original, Cloner cloner)
+
+    protected ExponentialTransformation(ExponentialTransformation original, Cloner cloner)
       : base(original, cloner) {
     }
+
     public ExponentialTransformation(IEnumerable<string> allowedColumns)
       : base(allowedColumns) {

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Transformations/LinearTransformation.cs

@@ -66 +66 @@
     [StorableConstructor]
     protected LinearTransformation(bool deserializing) : base(deserializing) { }
-    protected LinearTransformation(Transformation<double> original, Cloner cloner)
+    protected LinearTransformation(LinearTransformation original, Cloner cloner)
       : base(original, cloner) {
     }

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Transformations/LogarithmicTransformation.cs

@@ -30 +30 @@
     [StorableConstructor]
     protected LogarithmicTransformation(bool deserializing) : base(deserializing) { }
-    protected LogarithmicTransformation(Transformation<double> original, Cloner cloner)
+    protected LogarithmicTransformation(LogarithmicTransformation original, Cloner cloner)
       : base(original, cloner) {
     }

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Transformations/PowerTransformation.cs

@@ -29 +29 @@
     [StorableConstructor]
     protected PowerTransformation(bool deserializing) : base(deserializing) { }
-    protected PowerTransformation(Transformation<double> original, Cloner cloner)
+    protected PowerTransformation(PowerTransformation original, Cloner cloner)
       : base(original, cloner) {
     }

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Transformations/ReciprocalTransformation.cs

@@ -19 +19 @@
     [StorableConstructor]
     protected ReciprocalTransformation(bool deserializing) : base(deserializing) { }
-    protected ReciprocalTransformation(Transformation<double> original, Cloner cloner)
+    protected ReciprocalTransformation(ReciprocalTransformation original, Cloner cloner)
       : base(original, cloner) {
     }

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Transformations/ShiftStandardDistributionTransformation.cs

@@ -52 +52 @@
     [StorableConstructor]
     protected ShiftStandardDistributionTransformation(bool deserializing) : base(deserializing) { }
-    protected ShiftStandardDistributionTransformation(Transformation<double> original, Cloner cloner)
+    protected ShiftStandardDistributionTransformation(ShiftStandardDistributionTransformation original, Cloner cloner)
       : base(original, cloner) {
     }

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Transformations/ShiftToRangeTransformation.cs

@@ -29 +29 @@
     [StorableConstructor]
     protected ShiftToRangeTransformation(bool deserializing) : base(deserializing) { }
-    protected ShiftToRangeTransformation(Transformation<double> original, Cloner cloner)
+    protected ShiftToRangeTransformation(ShiftToRangeTransformation original, Cloner cloner)
       : base(original, cloner) {
     }