Changeset 6606 for trunk/sources/HeuristicLab.Problems.DataAnalysis

Timestamp:

07/28/11 13:57:05 (13 years ago)

Author:

mkommend

Message:

#1604: Enabled caching of evaluation results in data analysis solutions.

Location:

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

Files:

• Classification/ClassificationSolution.cs (modified) (2 diffs)
• Classification/DiscriminantFunctionClassificationSolution.cs (modified) (3 diffs)
• Classification/DiscriminantFunctionClassificationSolutionBase.cs (modified) (3 diffs)
• DataAnalysisSolution.cs (modified) (3 diffs)
• Regression/RegressionSolution.cs (modified) (2 diffs)

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

@@ -31 +31 @@
   [StorableClass]
   public abstract class ClassificationSolution : ClassificationSolutionBase {
+    protected readonly Dictionary<int, double> evaluationCache;
+
     [StorableConstructor]
-    protected ClassificationSolution(bool deserializing) : base(deserializing) { }
+    protected ClassificationSolution(bool deserializing)
+      : base(deserializing) {
+      evaluationCache = new Dictionary<int, double>();
+    }
     protected ClassificationSolution(ClassificationSolution original, Cloner cloner)
       : base(original, cloner) {
+      evaluationCache = new Dictionary<int, double>(original.evaluationCache);
     }
     public ClassificationSolution(IClassificationModel model, IClassificationProblemData problemData)
       : base(model, problemData) {
+      evaluationCache = new Dictionary<int, double>();
     }
 
@@ -51 +58 @@
 
     public override IEnumerable<double> GetEstimatedClassValues(IEnumerable<int> rows) {
-      return Model.GetEstimatedClassValues(ProblemData.Dataset, rows);
+      var rowsToEvaluate = rows.Except(evaluationCache.Keys);
+      var rowsEnumerator = rowsToEvaluate.GetEnumerator();
+      var valuesEnumerator = Model.GetEstimatedClassValues(ProblemData.Dataset, rowsToEvaluate).GetEnumerator();
+
+      while (rowsEnumerator.MoveNext() & valuesEnumerator.MoveNext()) {
+        evaluationCache.Add(rowsEnumerator.Current, valuesEnumerator.Current);
+      }
+
+      return rows.Select(row => evaluationCache[row]);
+    }
+
+    protected override void OnProblemDataChanged() {
+      evaluationCache.Clear();
+      base.OnProblemDataChanged();
+    }
+
+    protected override void OnModelChanged() {
+      evaluationCache.Clear();
+      base.OnModelChanged();
     }
   }

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

@@ -33 +33 @@
   [Item("DiscriminantFunctionClassificationSolution", "Represents a classification solution that uses a discriminant function and classification thresholds.")]
   public abstract class DiscriminantFunctionClassificationSolution : DiscriminantFunctionClassificationSolutionBase {
+    protected readonly Dictionary<int, double> valueEvaluationCache;
+    protected readonly Dictionary<int, double> classValueEvaluationCache;
 
     [StorableConstructor]
-    protected DiscriminantFunctionClassificationSolution(bool deserializing) : base(deserializing) { }
+    protected DiscriminantFunctionClassificationSolution(bool deserializing)
+      : base(deserializing) {
+      valueEvaluationCache = new Dictionary<int, double>();
+      classValueEvaluationCache = new Dictionary<int, double>();
+    }
     protected DiscriminantFunctionClassificationSolution(DiscriminantFunctionClassificationSolution original, Cloner cloner)
       : base(original, cloner) {
+      valueEvaluationCache = new Dictionary<int, double>(original.valueEvaluationCache);
+      classValueEvaluationCache = new Dictionary<int, double>(original.classValueEvaluationCache);
     }
     protected DiscriminantFunctionClassificationSolution(IDiscriminantFunctionClassificationModel model, IClassificationProblemData problemData)
       : base(model, problemData) {
+      valueEvaluationCache = new Dictionary<int, double>();
+      classValueEvaluationCache = new Dictionary<int, double>();
+
+      SetAccuracyMaximizingThresholds();
     }
 
@@ -54 +66 @@
 
     public override IEnumerable<double> GetEstimatedClassValues(IEnumerable<int> rows) {
-      return Model.GetEstimatedClassValues(ProblemData.Dataset, rows);
+      var rowsToEvaluate = rows.Except(classValueEvaluationCache.Keys);
+      var rowsEnumerator = rowsToEvaluate.GetEnumerator();
+      var valuesEnumerator = Model.GetEstimatedClassValues(ProblemData.Dataset, rowsToEvaluate).GetEnumerator();
+
+      while (rowsEnumerator.MoveNext() & valuesEnumerator.MoveNext()) {
+        classValueEvaluationCache.Add(rowsEnumerator.Current, valuesEnumerator.Current);
+      }
+
+      return rows.Select(row => classValueEvaluationCache[row]);
     }
 
@@ -69 +89 @@
 
     public override IEnumerable<double> GetEstimatedValues(IEnumerable<int> rows) {
-      return Model.GetEstimatedValues(ProblemData.Dataset, rows);
+      var rowsToEvaluate = rows.Except(valueEvaluationCache.Keys);
+      var rowsEnumerator = rowsToEvaluate.GetEnumerator();
+      var valuesEnumerator = Model.GetEstimatedValues(ProblemData.Dataset, rowsToEvaluate).GetEnumerator();
+
+      while (rowsEnumerator.MoveNext() & valuesEnumerator.MoveNext()) {
+        valueEvaluationCache.Add(rowsEnumerator.Current, valuesEnumerator.Current);
+      }
+
+      return rows.Select(row => valueEvaluationCache[row]);
+    }
+
+    protected override void OnModelChanged() {
+      valueEvaluationCache.Clear();
+      classValueEvaluationCache.Clear();
+      base.OnModelChanged();
+    }
+    protected override void OnModelThresholdsChanged(System.EventArgs e) {
+      classValueEvaluationCache.Clear();
+      base.OnModelThresholdsChanged(e);
+    }
+    protected override void OnProblemDataChanged() {
+      valueEvaluationCache.Clear();
+      classValueEvaluationCache.Clear();
+      base.OnProblemDataChanged();
     }
   }

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

@@ -86 +86 @@
       Add(new Result(TestRSquaredResultName, "Squared Pearson's correlation coefficient of the model output and the actual values on the test partition", new DoubleValue()));
 
-      SetAccuracyMaximizingThresholds();
       RegisterEventHandler();
     }
@@ -95 +94 @@
     }
 
-    protected override void OnModelChanged(EventArgs e) {
+    protected override void OnModelChanged() {
       DeregisterEventHandler();
       SetAccuracyMaximizingThresholds();
       RegisterEventHandler();
-      base.OnModelChanged(e);
+      base.OnModelChanged();
     }
 
@@ -149 +148 @@
 
     protected virtual void OnModelThresholdsChanged(EventArgs e) {
-      RecalculateResults();
+      CalculateResults();
     }
 

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

@@ -48 +48 @@
           if (value != null) {
             this[ModelResultName].Value = value;
-            OnModelChanged(EventArgs.Empty);
+            OnModelChanged();
           }
         }
@@ -62 +62 @@
             this[ProblemDataResultName].Value = value;
             ProblemData.Changed += new EventHandler(ProblemData_Changed);
-            OnProblemDataChanged(EventArgs.Empty);
+            OnProblemDataChanged();
           }
         }
@@ -89 +89 @@
 
     private void ProblemData_Changed(object sender, EventArgs e) {
-      OnProblemDataChanged(e);
+      OnProblemDataChanged();
     }
 
     public event EventHandler ModelChanged;
-    protected virtual void OnModelChanged(EventArgs e) {
+    protected virtual void OnModelChanged() {
       RecalculateResults();
       var listeners = ModelChanged;
-      if (listeners != null) listeners(this, e);
+      if (listeners != null) listeners(this, EventArgs.Empty);
     }
 
     public event EventHandler ProblemDataChanged;
-    protected virtual void OnProblemDataChanged(EventArgs e) {
+    protected virtual void OnProblemDataChanged() {
       RecalculateResults();
       var listeners = ProblemDataChanged;
-      if (listeners != null) listeners(this, e);
+      if (listeners != null) listeners(this, EventArgs.Empty);
     }
 

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

@@ -31 +31 @@
   [StorableClass]
   public abstract class RegressionSolution : RegressionSolutionBase {
+    protected readonly Dictionary<int, double> evaluationCache;
+
     [StorableConstructor]
-    protected RegressionSolution(bool deserializing) : base(deserializing) { }
+    protected RegressionSolution(bool deserializing)
+      : base(deserializing) {
+      evaluationCache = new Dictionary<int, double>();
+    }
     protected RegressionSolution(RegressionSolution original, Cloner cloner)
       : base(original, cloner) {
+      evaluationCache = new Dictionary<int, double>(original.evaluationCache);
     }
     protected RegressionSolution(IRegressionModel model, IRegressionProblemData problemData)
       : base(model, problemData) {
+      evaluationCache = new Dictionary<int, double>();
     }
 
@@ -55 +62 @@
 
     public override IEnumerable<double> GetEstimatedValues(IEnumerable<int> rows) {
-      return Model.GetEstimatedValues(ProblemData.Dataset, rows);
+      var rowsToEvaluate = rows.Except(evaluationCache.Keys);
+      var rowsEnumerator = rowsToEvaluate.GetEnumerator();
+      var valuesEnumerator = Model.GetEstimatedValues(ProblemData.Dataset, rowsToEvaluate).GetEnumerator();
+
+      while (rowsEnumerator.MoveNext() & valuesEnumerator.MoveNext()) {
+        evaluationCache.Add(rowsEnumerator.Current, valuesEnumerator.Current);
+      }
+
+      return rows.Select(row => evaluationCache[row]);
+    }
+
+    protected override void OnProblemDataChanged() {
+      evaluationCache.Clear();
+      base.OnProblemDataChanged();
+    }
+
+    protected override void OnModelChanged() {
+      evaluationCache.Clear();
+      base.OnModelChanged();
     }
   }