Changeset 8430 for branches/HeuristicLab.TimeSeries/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationEnsembleSolution.cs

Timestamp:

08/08/12 14:04:17 (12 years ago)

Author:

mkommend

Message:

#1081: Intermediate commit of trunk updates - interpreter changes must be redone.

Location:

branches/HeuristicLab.TimeSeries

Files:

• . (modified) (1 prop)
• HeuristicLab.Problems.DataAnalysis (modified) (1 prop)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationEnsembleSolution.cs (modified) (10 diffs)

branches/HeuristicLab.TimeSeries

@@ -20 +20 @@
 bin
 protoc.exe
+_ReSharper.HeuristicLab.TimeSeries-3.3

@@ -20 +20 @@
 bin
 protoc.exe
+_ReSharper.HeuristicLab.TimeSeries-3.3

branches/HeuristicLab.TimeSeries/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationEnsembleSolution.cs

@@ -37 +37 @@
   [Creatable("Data Analysis - Ensembles")]
   public sealed class ClassificationEnsembleSolution : ClassificationSolution, IClassificationEnsembleSolution {
+    private readonly Dictionary<int, double> trainingEvaluationCache = new Dictionary<int, double>();
+    private readonly Dictionary<int, double> testEvaluationCache = new Dictionary<int, double>();
+
     public new IClassificationEnsembleModel Model {
       get { return (IClassificationEnsembleModel)base.Model; }
@@ -85 +88 @@
       }
 
+      trainingEvaluationCache = new Dictionary<int, double>(original.ProblemData.TrainingIndices.Count());
+      testEvaluationCache = new Dictionary<int, double>(original.ProblemData.TestIndices.Count());
+
       classificationSolutions = cloner.Clone(original.classificationSolutions);
       RegisterClassificationSolutionsEventHandler();
@@ -128 +134 @@
       }
 
+      trainingEvaluationCache = new Dictionary<int, double>(problemData.TrainingIndices.Count());
+      testEvaluationCache = new Dictionary<int, double>(problemData.TestIndices.Count());
+
       RegisterClassificationSolutionsEventHandler();
       classificationSolutions.AddRange(solutions);
@@ -148 +157 @@
     public override IEnumerable<double> EstimatedTrainingClassValues {
       get {
-        var rows = ProblemData.TrainingIndizes;
-        var estimatedValuesEnumerators = (from model in Model.Models
-                                          select new { Model = model, EstimatedValuesEnumerator = model.GetEstimatedClassValues(ProblemData.Dataset, rows).GetEnumerator() })
-                                         .ToList();
-        var rowsEnumerator = rows.GetEnumerator();
-        // aggregate to make sure that MoveNext is called for all enumerators 
-        while (rowsEnumerator.MoveNext() & estimatedValuesEnumerators.Select(en => en.EstimatedValuesEnumerator.MoveNext()).Aggregate(true, (acc, b) => acc & b)) {
-          int currentRow = rowsEnumerator.Current;
-
-          var selectedEnumerators = from pair in estimatedValuesEnumerators
-                                    where RowIsTrainingForModel(currentRow, pair.Model) && !RowIsTestForModel(currentRow, pair.Model)
-                                    select pair.EstimatedValuesEnumerator;
-          yield return AggregateEstimatedClassValues(selectedEnumerators.Select(x => x.Current));
+        var rows = ProblemData.TrainingIndices;
+        var rowsToEvaluate = rows.Except(trainingEvaluationCache.Keys);
+        var rowsEnumerator = rowsToEvaluate.GetEnumerator();
+        var valuesEnumerator = GetEstimatedValues(rowsToEvaluate, (r, m) => RowIsTrainingForModel(r, m) && !RowIsTestForModel(r, m)).GetEnumerator();
+
+        while (rowsEnumerator.MoveNext() & valuesEnumerator.MoveNext()) {
+          trainingEvaluationCache.Add(rowsEnumerator.Current, valuesEnumerator.Current);
         }
+
+        return rows.Select(row => trainingEvaluationCache[row]);
       }
     }
@@ -167 +172 @@
     public override IEnumerable<double> EstimatedTestClassValues {
       get {
-        var rows = ProblemData.TestIndizes;
-        var estimatedValuesEnumerators = (from model in Model.Models
-                                          select new { Model = model, EstimatedValuesEnumerator = model.GetEstimatedClassValues(ProblemData.Dataset, rows).GetEnumerator() })
-                                         .ToList();
-        var rowsEnumerator = ProblemData.TestIndizes.GetEnumerator();
-        // aggregate to make sure that MoveNext is called for all enumerators 
-        while (rowsEnumerator.MoveNext() & estimatedValuesEnumerators.Select(en => en.EstimatedValuesEnumerator.MoveNext()).Aggregate(true, (acc, b) => acc & b)) {
-          int currentRow = rowsEnumerator.Current;
-
-          var selectedEnumerators = from pair in estimatedValuesEnumerators
-                                    where RowIsTestForModel(currentRow, pair.Model)
-                                    select pair.EstimatedValuesEnumerator;
-
-          yield return AggregateEstimatedClassValues(selectedEnumerators.Select(x => x.Current));
+        var rows = ProblemData.TestIndices;
+        var rowsToEvaluate = rows.Except(testEvaluationCache.Keys);
+        var rowsEnumerator = rowsToEvaluate.GetEnumerator();
+        var valuesEnumerator = GetEstimatedValues(rowsToEvaluate, RowIsTestForModel).GetEnumerator();
+
+        while (rowsEnumerator.MoveNext() & valuesEnumerator.MoveNext()) {
+          testEvaluationCache.Add(rowsEnumerator.Current, valuesEnumerator.Current);
         }
+
+        return rows.Select(row => testEvaluationCache[row]);
+      }
+    }
+
+    private IEnumerable<double> GetEstimatedValues(IEnumerable<int> rows, Func<int, IClassificationModel, bool> modelSelectionPredicate) {
+      var estimatedValuesEnumerators = (from model in Model.Models
+                                        select new { Model = model, EstimatedValuesEnumerator = model.GetEstimatedClassValues(ProblemData.Dataset, rows).GetEnumerator() })
+                                       .ToList();
+      var rowsEnumerator = rows.GetEnumerator();
+      // aggregate to make sure that MoveNext is called for all enumerators 
+      while (rowsEnumerator.MoveNext() & estimatedValuesEnumerators.Select(en => en.EstimatedValuesEnumerator.MoveNext()).Aggregate(true, (acc, b) => acc & b)) {
+        int currentRow = rowsEnumerator.Current;
+
+        var selectedEnumerators = from pair in estimatedValuesEnumerators
+                                  where modelSelectionPredicate(currentRow, pair.Model)
+                                  select pair.EstimatedValuesEnumerator;
+
+        yield return AggregateEstimatedClassValues(selectedEnumerators.Select(x => x.Current));
       }
     }
@@ -196 +213 @@
 
     public override IEnumerable<double> GetEstimatedClassValues(IEnumerable<int> rows) {
-      return from xs in GetEstimatedClassValueVectors(ProblemData.Dataset, rows)
-             select AggregateEstimatedClassValues(xs);
+      var rowsToEvaluate = rows.Except(evaluationCache.Keys);
+      var rowsEnumerator = rowsToEvaluate.GetEnumerator();
+      var valuesEnumerator = (from xs in GetEstimatedClassValueVectors(ProblemData.Dataset, rowsToEvaluate)
+                              select AggregateEstimatedClassValues(xs))
+                             .GetEnumerator();
+
+      while (rowsEnumerator.MoveNext() & valuesEnumerator.MoveNext()) {
+        evaluationCache.Add(rowsEnumerator.Current, valuesEnumerator.Current);
+      }
+
+      return rows.Select(row => evaluationCache[row]);
     }
 
@@ -223 +249 @@
 
     protected override void OnProblemDataChanged() {
+      trainingEvaluationCache.Clear();
+      testEvaluationCache.Clear();
+      evaluationCache.Clear();
+
       IClassificationProblemData problemData = new ClassificationProblemData(ProblemData.Dataset,
                                                                      ProblemData.AllowedInputVariables,
@@ -251 +281 @@
     public void AddClassificationSolutions(IEnumerable<IClassificationSolution> solutions) {
       classificationSolutions.AddRange(solutions);
+
+      trainingEvaluationCache.Clear();
+      testEvaluationCache.Clear();
+      evaluationCache.Clear();
     }
     public void RemoveClassificationSolutions(IEnumerable<IClassificationSolution> solutions) {
       classificationSolutions.RemoveRange(solutions);
+
+      trainingEvaluationCache.Clear();
+      testEvaluationCache.Clear();
+      evaluationCache.Clear();
     }
 
@@ -275 +313 @@
       trainingPartitions[solution.Model] = solution.ProblemData.TrainingPartition;
       testPartitions[solution.Model] = solution.ProblemData.TestPartition;
+
+      trainingEvaluationCache.Clear();
+      testEvaluationCache.Clear();
+      evaluationCache.Clear();
     }
 
@@ -282 +324 @@
       trainingPartitions.Remove(solution.Model);
       testPartitions.Remove(solution.Model);
+
+      trainingEvaluationCache.Clear();
+      testEvaluationCache.Clear();
+      evaluationCache.Clear();
     }
   }

@@ -20 +20 @@
 bin
 protoc.exe
+_ReSharper.HeuristicLab.TimeSeries-3.3