Changeset 10695 for branches/DataPreprocessing/HeuristicLab.Problems.DataAnalysis

Timestamp:

04/02/14 11:38:44 (11 years ago)

Author:

pfleck

Message:

• Added Transformations to PreprocessingData
• Added Transformations to DataAnalysisProblemData Parameters
• Removed SymbolicExpressionTree as inverse transformation.

Location:

branches/DataPreprocessing/HeuristicLab.Problems.DataAnalysis/3.4

Files:

• Implementation/Classification/ClassificationProblemData.cs (modified) (1 diff)
• Implementation/Clustering/ClusteringProblemData.cs (modified) (2 diffs)
• Implementation/DataAnalysisProblemData.cs (modified) (6 diffs)
• Implementation/Regression/RegressionProblemData.cs (modified) (1 diff)
• Interfaces/IDataAnalysisProblemData.cs (modified) (1 diff)
• Interfaces/ITransformation.cs (modified) (1 diff)

branches/DataPreprocessing/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationProblemData.cs

@@ -291 +291 @@
     }
 
-    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();

branches/DataPreprocessing/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>()) {
     }
   }

branches/DataPreprocessing/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/DataAnalysisProblemData.cs

@@ -37 +37 @@
     protected const string TrainingPartitionParameterName = "TrainingPartition";
     protected const string TestPartitionParameterName = "TestPartition";
+    protected const string TransformationsParameterName = "Transformations";
 
     #region parameter properites
@@ -50 +51 @@
     public IFixedValueParameter<IntRange> TestPartitionParameter {
       get { return (IFixedValueParameter<IntRange>)Parameters[TestPartitionParameterName]; }
+    }
+    public IFixedValueParameter<ReadOnlyItemCollection<ITransformation>> TransformationsParameter {
+      get { return (IFixedValueParameter<ReadOnlyItemCollection<ITransformation>>)Parameters[TransformationsParameterName]; }
     }
     #endregion
@@ -88 +92 @@
     }
 
+    public IEnumerable<ITransformation> Transformations {
+      get { return TransformationsParameter.Value; }
+    }
+
     public virtual bool IsTrainingSample(int index) {
       return index >= 0 && index < Dataset.Rows &&
@@ -111 +119 @@
     private void AfterDeserialization() {
       RegisterEventHandlers();
+
+      if (!Parameters.ContainsKey(TransformationsParameterName)) {
+        Parameters.Add(new FixedValueParameter<ReadOnlyItemCollection<ITransformation>>(TransformationsParameterName, "", new ItemCollection<ITransformation>().AsReadOnly()));
+      }
     }
 
-    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.");
@@ -119 +131 @@
       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)));
@@ -129 +143 @@
       int testPartitionEnd = dataset.Rows;
 
+      var transformationsCollection = new ItemCollection<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<ReadOnlyItemCollection<ITransformation>>(TransformationsParameterName, "", transformationsCollection.AsReadOnly()));
 
       ((ValueParameter<Dataset>)DatasetParameter).ReactOnValueToStringChangedAndValueItemImageChanged = false;

branches/DataPreprocessing/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionProblemData.cs

@@ -129 +129 @@
     }
 
-    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()));

branches/DataPreprocessing/HeuristicLab.Problems.DataAnalysis/3.4/Interfaces/IDataAnalysisProblemData.cs

@@ -39 +39 @@
     IEnumerable<int> TestIndices { get; }
 
+    IEnumerable<ITransformation> Transformations { get; }
+
     bool IsTrainingSample(int index);
     bool IsTestSample(int index);

branches/DataPreprocessing/HeuristicLab.Problems.DataAnalysis/3.4/Interfaces/ITransformation.cs

@@ -20 +20 @@
 #endregion
 
+using System.Collections;
 using System.Collections.Generic;
 using HeuristicLab.Core;
 
 namespace HeuristicLab.Problems.DataAnalysis {
-  public interface ITransformation<T> : IParameterizedItem {
+  public interface ITransformation : IParameterizedItem {
     string Column { get; }
+  }
+
+  public interface ITransformation<T> : ITransformation {
     IEnumerable<T> Apply(IEnumerable<T> data);
     IEnumerable<T> InverseApply(IEnumerable<T> data);