Changeset 15870 for branches/2906_Transformations/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/DataAnalysisTransformationModel.cs

Timestamp:

03/28/18 17:17:31 (6 years ago)

Author:

pfleck

Message:

#2906

• Implemented for classification, clustering, etc.
• Simplified Transformation interfaces (read-only, ...).
• Started moving transformation logic out of ProblemData.

File:

• branches/2906_Transformations/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/DataAnalysisTransformationModel.cs (moved) (moved from branches/2906_Transformations/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/TransformedRegressionModel.cs) (3 diffs)

branches/2906_Transformations/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/DataAnalysisTransformationModel.cs

@@ -20 +20 @@
 #endregion
 
+using System;
 using System.Collections.Generic;
 using System.Linq;
@@ -27 +28 @@
 
 namespace HeuristicLab.Problems.DataAnalysis {
-  [Item("Transformed Regression Model", "A model that was transformed back to match the original variables after the training was performed on transformed variables.")]
+  [Item("Data Analysis Transformation Model", "A model that was transformed back to match the original variables after the training was performed on transformed variables.")]
   [StorableClass]
-  public class TransformedRegressionModel : RegressionModel, ITransformedRegressionModel {
+  public abstract class DataAnalysisTransformationModel : DataAnalysisModel, IDataAnalysisTransformationModel {
 
     [Storable]
-    public IRegressionModel OriginalModel { get; private set; }
+    public IDataAnalysisModel OriginalModel { get; protected set; }
 
     [Storable]
-    public ItemList<IDataAnalysisTransformation> Transformations { get; private set; }
+    public ReadOnlyItemList<IDataAnalysisTransformation> InputTransformations { get; protected set; }
+
+    [Storable]
+    public ReadOnlyItemList<IDataAnalysisTransformation> TargetTransformations { get; protected set; }
+
+    // Usually, the TargetVariable is usually only implemented for Regression and Classification.
+    // However, we implement it in the base class for reducing code duplication and to avoid quasi-identical views.
+    [Storable]
+    private string targetVariable;
+    public string TargetVariable {
+      get { return targetVariable; }
+      set {
+        if (string.IsNullOrEmpty(value) || targetVariable == value) return;
+        targetVariable = value;
+        OnTargetVariableChanged(this, EventArgs.Empty);
+      }
+    }
 
     public override IEnumerable<string> VariablesUsedForPrediction {
-      get { return OriginalModel.VariablesUsedForPrediction; }
+      get { return OriginalModel.VariablesUsedForPrediction; /* TODO: reduce extend-inputs */}
     }
 
     #region Constructor, Cloning & Persistence
-    public TransformedRegressionModel(IRegressionModel originalModel, IEnumerable<IDataAnalysisTransformation> transformations)
-      : base(RegressionProblemData.GetOriginalTragetVariable(originalModel.TargetVariable, transformations)) {
-      Name = "Transformed " + originalModel.Name;
+    protected DataAnalysisTransformationModel(IDataAnalysisModel originalModel, IEnumerable<IDataAnalysisTransformation> transformations)
+      : base(originalModel.Name) {
       OriginalModel = originalModel;
-      Transformations = new ItemList<IDataAnalysisTransformation>(transformations);
+      var transitiveInputs = CalculateTransitiveVariables(originalModel.VariablesUsedForPrediction, transformations);
+      InputTransformations = new ItemList<IDataAnalysisTransformation>(transformations.Where(t => transitiveInputs.Contains(t.OriginalVariable))).AsReadOnly();
+      TargetTransformations = new ReadOnlyItemList<IDataAnalysisTransformation>();
     }
 
-    protected TransformedRegressionModel(TransformedRegressionModel original, Cloner cloner)
+    protected DataAnalysisTransformationModel(DataAnalysisTransformationModel original, Cloner cloner)
       : base(original, cloner) {
       OriginalModel = cloner.Clone(original.OriginalModel);
-      Transformations = cloner.Clone(original.Transformations);
-    }
-
-    public override IDeepCloneable Clone(Cloner cloner) {
-      return new TransformedRegressionModel(this, cloner);
+      InputTransformations = cloner.Clone(original.InputTransformations);
+      TargetTransformations = cloner.Clone(original.TargetTransformations);
+      targetVariable = original.targetVariable;
     }
 
     [StorableConstructor]
-    protected TransformedRegressionModel(bool deserializing)
+    protected DataAnalysisTransformationModel(bool deserializing)
       : base(deserializing) { }
     #endregion
 
+    public static ISet<string> CalculateTransitiveVariables(IEnumerable<string> inputVariables, IEnumerable<IDataAnalysisTransformation> transformations) {
+      var transitiveInputs = new HashSet<string>(inputVariables);
+
+      foreach (var transformation in transformations.Reverse()) {
+        if (transitiveInputs.Contains(transformation.TransformedVariable)) {
+          transitiveInputs.Add(transformation.OriginalVariable);
+        }
+      }
+
+      return transitiveInputs;
+    }
+
+    public static IDataset Transform(IDataset dataset, IEnumerable<IDataAnalysisTransformation> transformations) {
+      var modifiableDataset = ((Dataset)dataset).ToModifiable();
+
+      foreach (var transformation in transformations) {
+        var trans = (ITransformation<double>)transformation.Transformation;
+
+        var originalData = modifiableDataset.GetDoubleValues(transformation.OriginalVariable);
+        if (!trans.Check(originalData, out string errorMessage))
+          throw new InvalidOperationException($"Cannot estimate Values, Transformation is invalid: {errorMessage}");
+
+        var transformedData = trans.Apply(originalData).ToList();
+        if (modifiableDataset.VariableNames.Contains(transformation.TransformedVariable))
+          modifiableDataset.ReplaceVariable(transformation.TransformedVariable, transformedData);
+        else
+          modifiableDataset.AddVariable(transformation.TransformedVariable, transformedData);
+      }
+
+      return modifiableDataset;
+    }
+
+
+
+    #region Events
+    public event EventHandler TargetVariableChanged;
+    private void OnTargetVariableChanged(object sender, EventArgs args) {
+      var changed = TargetVariableChanged;
+      if (changed != null)
+        changed(sender, args);
+    }
+    #endregion
+
+
+
+
+
+
+    /*
     // dataset in original data range
     public override IEnumerable<double> GetEstimatedValues(IDataset dataset, IEnumerable<int> rows) {
-      var transformedDataset = TransformInputs(dataset, Transformations);
+      var transformedDataset = Transform(dataset, Transformations);
 
       var estimates = OriginalModel.GetEstimatedValues(transformedDataset, rows);
 
-      return InverseTransformEstimates(estimates, Transformations, OriginalModel.TargetVariable);
+      return InverseTransform(estimates, Transformations, OriginalModel.TargetVariable);
     }
 
@@ -76 +141 @@
     public override IRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData) {
       // TODO: specialized views for the original solution type are lost (RandomForestSolutionView, ...)
-      return new TransformedRegressionSolution(this, new RegressionProblemData(problemData));
-    }
-
-    private static IDataset TransformInputs(IDataset dataset, IEnumerable<IDataAnalysisTransformation> transformations) {
-      return DataAnalysisProblemData.Transform(dataset, transformations);
-    }
-
-    private static IEnumerable<double> InverseTransformEstimates(IEnumerable<double> data, IEnumerable<IDataAnalysisTransformation> transformations, string targetVariable) {
-      var estimates = data.ToList();
-
-      foreach (var transformation in transformations.Reverse()) {
-        if (transformation.TransformedVariable == targetVariable) {
-          var trans = (ITransformation<double>)transformation.Transformation;
-
-          estimates = trans.InverseApply(estimates).ToList();
-
-          // setup next iteration
-          targetVariable = transformation.OriginalVariable;
-        }
-      }
-
-      return estimates;
-    }
+      return new RegressionSolution(this, new RegressionProblemData(problemData));
+    } */
   }
 }