Changeset 6618 for branches/GP.Grammar.Editor/HeuristicLab.Algorithms.DataAnalysis/3.4/SupportVectorMachine

Timestamp:

08/01/11 17:48:53 (13 years ago)

Author:

mkommend

Message:

#1479: Integrated trunk changes.

Location:

branches/GP.Grammar.Editor/HeuristicLab.Algorithms.DataAnalysis/3.4/SupportVectorMachine

Files:

• SupportVectorClassificationSolution.cs (modified) (3 diffs)
• SupportVectorMachineModel.cs (modified) (3 diffs)
• SupportVectorRegressionSolution.cs (modified) (2 diffs)

branches/GP.Grammar.Editor/HeuristicLab.Algorithms.DataAnalysis/3.4/SupportVectorMachine/SupportVectorClassificationSolution.cs

@@ -20 +20 @@
 #endregion
 
-using System;
-using System.Collections.Generic;
-using System.Drawing;
-using System.Linq;
 using HeuristicLab.Common;
 using HeuristicLab.Core;
@@ -49 +45 @@
     public SupportVectorClassificationSolution(SupportVectorMachineModel model, IClassificationProblemData problemData)
       : base(model, problemData) {
+      RecalculateResults();
     }
 
@@ -54 +51 @@
       return new SupportVectorClassificationSolution(this, cloner);
     }
+
+    protected override void RecalculateResults() {
+      CalculateResults();
+    }
   }
 }

branches/GP.Grammar.Editor/HeuristicLab.Algorithms.DataAnalysis/3.4/SupportVectorMachine/SupportVectorMachineModel.cs

@@ -98 +98 @@
       this.targetVariable = original.targetVariable;
       this.allowedInputVariables = (string[])original.allowedInputVariables.Clone();
+      foreach (var dataset in original.cachedPredictions.Keys) {
+        this.cachedPredictions.Add(cloner.Clone(dataset), (double[])original.cachedPredictions[dataset].Clone());
+      }
       if (original.classValues != null)
         this.classValues = (double[])original.classValues.Clone();
@@ -123 +126 @@
       return GetEstimatedValuesHelper(dataset, rows);
     }
-    #endregion
+    public SupportVectorRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData) {
+      return new SupportVectorRegressionSolution(this, problemData);
+    }
+    IRegressionSolution IRegressionModel.CreateRegressionSolution(IRegressionProblemData problemData) {
+      return CreateRegressionSolution(problemData);
+    }
+    #endregion
+
     #region IClassificationModel Members
     public IEnumerable<double> GetEstimatedClassValues(Dataset dataset, IEnumerable<int> rows) {
@@ -144 +154 @@
       }
     }
-    #endregion
+
+    public SupportVectorClassificationSolution CreateClassificationSolution(IClassificationProblemData problemData) {
+      return new SupportVectorClassificationSolution(this, problemData);
+    }
+    IClassificationSolution IClassificationModel.CreateClassificationSolution(IClassificationProblemData problemData) {
+      return CreateClassificationSolution(problemData);
+    }
+    #endregion
+    // cache for predictions, which is cloned but not persisted, must be cleared when the model is changed
+    private Dictionary<Dataset, double[]> cachedPredictions = new Dictionary<Dataset, double[]>();
     private IEnumerable<double> GetEstimatedValuesHelper(Dataset dataset, IEnumerable<int> rows) {
+      if (!cachedPredictions.ContainsKey(dataset)) {
+        // create an array of cached predictions which is initially filled with NaNs
+        double[] predictions = Enumerable.Repeat(double.NaN, dataset.Rows).ToArray();
+        CalculatePredictions(dataset, rows, predictions);
+        cachedPredictions.Add(dataset, predictions);
+      }
+      // get the array of predictions and select the subset of requested rows
+      double[] p = cachedPredictions[dataset];
+      var requestedPredictions = from r in rows
+                                 select p[r];
+      // check if the requested predictions contain NaNs 
+      // (this means for the request rows some predictions have not been cached)
+      if (requestedPredictions.Any(x => double.IsNaN(x))) {
+        // updated the predictions for currently requested rows
+        CalculatePredictions(dataset, rows, p);
+        cachedPredictions[dataset] = p;
+        // now we can be sure that for the current rows all predictions are available
+        return from r in rows
+               select p[r];
+      } else {
+        // there were no NaNs => just return the cached predictions
+        return requestedPredictions;
+      }
+    }
+
+    private void CalculatePredictions(Dataset dataset, IEnumerable<int> rows, double[] predictions) {
+      // calculate and cache predictions for the currently requested rows
       SVM.Problem problem = SupportVectorMachineUtil.CreateSvmProblem(dataset, targetVariable, allowedInputVariables, rows);
       SVM.Problem scaledProblem = Scaling.Scale(RangeTransform, problem);
 
-      foreach (var row in Enumerable.Range(0, scaledProblem.Count)) {
-        yield return SVM.Prediction.Predict(Model, scaledProblem.X[row]);
-      }
-    }
+      // row is the index in the original dataset, 
+      // i is the index in the scaled dataset (containing only the necessary rows)
+      int i = 0;
+      foreach (var row in rows) {
+        predictions[row] = SVM.Prediction.Predict(Model, scaledProblem.X[i]);
+        i++;
+      }
+    }
+
     #region events
     public event EventHandler Changed;
     private void OnChanged(EventArgs e) {
+      cachedPredictions.Clear();
       var handlers = Changed;
       if (handlers != null)

branches/GP.Grammar.Editor/HeuristicLab.Algorithms.DataAnalysis/3.4/SupportVectorMachine/SupportVectorRegressionSolution.cs

@@ -20 +20 @@
 #endregion
 
-using System;
-using System.Collections.Generic;
-using System.Drawing;
-using System.Linq;
 using HeuristicLab.Common;
 using HeuristicLab.Core;
@@ -49 +45 @@
     public SupportVectorRegressionSolution(SupportVectorMachineModel model, IRegressionProblemData problemData)
       : base(model, problemData) {
+      RecalculateResults();
     }