Changeset 8152 for trunk/sources

Timestamp:

06/28/12 16:15:16 (12 years ago)

Author:

gkronber

Message:

#1720 added estimated values caching to RegressionEnsembleSolution

File:

• trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionEnsembleSolution.cs (modified) (7 diffs)

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

@@ -56 +56 @@
 
     [Storable]
-    private Dictionary<IRegressionModel, IntRange> trainingPartitions;
+    private readonly Dictionary<IRegressionModel, IntRange> trainingPartitions;
     [Storable]
-    private Dictionary<IRegressionModel, IntRange> testPartitions;
+    private readonly Dictionary<IRegressionModel, IntRange> testPartitions;
 
     [StorableConstructor]
@@ -156 +156 @@
     #region Evaluation
     public override IEnumerable<double> EstimatedTrainingValues {
-      get { return GetEstimatedValues(ProblemData.TrainingIndices, (r, m) => RowIsTrainingForModel(r, m) && !RowIsTestForModel(r, m)); }
+      get {
+        var rows = ProblemData.TrainingIndices;
+        var rowsToEvaluate = rows.Except(trainingEstimatedValuesCache.Keys);
+        var rowsEnumerator = rowsToEvaluate.GetEnumerator();
+        var valuesEnumerator = GetEstimatedValues(rowsToEvaluate, (r, m) => RowIsTrainingForModel(r, m) && !RowIsTestForModel(r, m)).GetEnumerator();
+
+        while (rowsEnumerator.MoveNext() & valuesEnumerator.MoveNext()) {
+          trainingEstimatedValuesCache.Add(rowsEnumerator.Current, valuesEnumerator.Current);
+        }
+
+        return rows.Select(row => trainingEstimatedValuesCache[row]);
+      }
     }
 
     public override IEnumerable<double> EstimatedTestValues {
-      get { return GetEstimatedValues(ProblemData.TestIndices, RowIsTestForModel); }
+      get {
+        var rows = ProblemData.TestIndices;
+        var rowsToEvaluate = rows.Except(testEstimatedValuesCache.Keys);
+        var rowsEnumerator = rowsToEvaluate.GetEnumerator();
+        var valuesEnumerator = GetEstimatedValues(rowsToEvaluate, RowIsTestForModel).GetEnumerator();
+
+        while (rowsEnumerator.MoveNext() & valuesEnumerator.MoveNext()) {
+          testEstimatedValuesCache.Add(rowsEnumerator.Current, valuesEnumerator.Current);
+        }
+
+        return rows.Select(row => testEstimatedValuesCache[row]);
+      }
     }
 
@@ -191 +213 @@
 
     public override IEnumerable<double> GetEstimatedValues(IEnumerable<int> rows) {
-      return from xs in GetEstimatedValueVectors(ProblemData.Dataset, rows)
-             select AggregateEstimatedValues(xs);
+      var rowsToEvaluate = rows.Except(estimatedValuesCache.Keys);
+      var rowsEnumerator = rowsToEvaluate.GetEnumerator();
+      var valuesEnumerator = (from xs in GetEstimatedValueVectors(ProblemData.Dataset, rowsToEvaluate)
+                              select AggregateEstimatedValues(xs))
+                             .GetEnumerator();
+
+      while (rowsEnumerator.MoveNext() & valuesEnumerator.MoveNext()) {
+        estimatedValuesCache.Add(rowsEnumerator.Current, valuesEnumerator.Current);
+      }
+
+      return rows.Select(row => estimatedValuesCache[row]);
     }
 
@@ -213 +244 @@
 
     protected override void OnProblemDataChanged() {
+      trainingEstimatedValuesCache.Clear();
+      testEstimatedValuesCache.Clear();
+      estimatedValuesCache.Clear();
       IRegressionProblemData problemData = new RegressionProblemData(ProblemData.Dataset,
                                                                      ProblemData.AllowedInputVariables,
@@ -241 +275 @@
     public void AddRegressionSolutions(IEnumerable<IRegressionSolution> solutions) {
       regressionSolutions.AddRange(solutions);
+
+      trainingEstimatedValuesCache.Clear();
+      testEstimatedValuesCache.Clear();
+      estimatedValuesCache.Clear();
     }
     public void RemoveRegressionSolutions(IEnumerable<IRegressionSolution> solutions) {
       regressionSolutions.RemoveRange(solutions);
+
+      trainingEstimatedValuesCache.Clear();
+      testEstimatedValuesCache.Clear();
+      estimatedValuesCache.Clear();
     }
 
@@ -265 +307 @@
       trainingPartitions[solution.Model] = solution.ProblemData.TrainingPartition;
       testPartitions[solution.Model] = solution.ProblemData.TestPartition;
+
+      trainingEstimatedValuesCache.Clear();
+      testEstimatedValuesCache.Clear();
+      estimatedValuesCache.Clear();
     }
 
@@ -272 +318 @@
       trainingPartitions.Remove(solution.Model);
       testPartitions.Remove(solution.Model);
+
+      trainingEstimatedValuesCache.Clear();
+      testEstimatedValuesCache.Clear();
+      estimatedValuesCache.Clear();
     }
   }