Changeset 13697 for trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression

Timestamp:

03/14/16 17:16:12 (9 years ago)

Author:

mkommend

Message:

#2590: Extracted estimated values calculation from RegressionEnsembleSolution to the according model.

Location:

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

Files:

• RegressionEnsembleModel.cs (modified) (3 diffs)
• RegressionEnsembleSolution.cs (modified) (5 diffs)

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

@@ -20 +20 @@
 #endregion
 
+using System;
 using System.Collections.Generic;
 using System.Linq;
@@ -91 +92 @@
     }
 
+    public IEnumerable<double> GetEstimatedValues(IDataset dataset, IEnumerable<int> rows, Func<int, IRegressionModel, bool> modelSelectionPredicate) {
+      var estimatedValuesEnumerators = GetEstimatedValueVectors(dataset, rows).GetEnumerator();
+      var rowsEnumerator = rows.GetEnumerator();
+
+      // aggregate to make sure that MoveNext is called for all enumerators 
+      while (rowsEnumerator.MoveNext() & estimatedValuesEnumerators.MoveNext()) {
+        int currentRow = rowsEnumerator.Current;
+
+        var filteredEstimates = models.Zip(estimatedValuesEnumerators.Current,
+          (m, e) => new { Model = m, EstimatedValue = e }).Where(f => modelSelectionPredicate(currentRow, f.Model));
+
+        yield return filteredEstimates.Select(f => f.EstimatedValue).DefaultIfEmpty(double.NaN).Average();
+      }
+    }
+
     #endregion
 
     #region IRegressionModel Members
-
     public IEnumerable<double> GetEstimatedValues(IDataset dataset, IEnumerable<int> rows) {
       foreach (var estimatedValuesVector in GetEstimatedValueVectors(dataset, rows)) {
@@ -107 +122 @@
       return CreateRegressionSolution(problemData);
     }
-
     #endregion
   }

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

@@ -169 +169 @@
         var rowsToEvaluate = rows.Except(trainingEvaluationCache.Keys);
         var rowsEnumerator = rowsToEvaluate.GetEnumerator();
-        var valuesEnumerator = GetEstimatedValues(rowsToEvaluate, (r, m) => RowIsTrainingForModel(r, m) && !RowIsTestForModel(r, m)).GetEnumerator();
+        var valuesEnumerator = Model.GetEstimatedValues(ProblemData.Dataset, rowsToEvaluate, (r, m) => RowIsTrainingForModel(r, m) && !RowIsTestForModel(r, m)).GetEnumerator();
 
         while (rowsEnumerator.MoveNext() & valuesEnumerator.MoveNext()) {
@@ -184 +184 @@
         var rowsToEvaluate = rows.Except(testEvaluationCache.Keys);
         var rowsEnumerator = rowsToEvaluate.GetEnumerator();
-        var valuesEnumerator = GetEstimatedValues(rowsToEvaluate, RowIsTestForModel).GetEnumerator();
+        var valuesEnumerator = Model.GetEstimatedValues(ProblemData.Dataset, rowsToEvaluate, RowIsTestForModel).GetEnumerator();
 
         while (rowsEnumerator.MoveNext() & valuesEnumerator.MoveNext()) {
@@ -193 +193 @@
       }
     }
-
-    private IEnumerable<double> GetEstimatedValues(IEnumerable<int> rows, Func<int, IRegressionModel, bool> modelSelectionPredicate) {
-      var estimatedValuesEnumerators = (from model in Model.Models
-                                        select new { Model = model, EstimatedValuesEnumerator = model.GetEstimatedValues(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 AggregateEstimatedValues(selectedEnumerators.Select(x => x.Current));
-      }
-    }
-
     private bool RowIsTrainingForModel(int currentRow, IRegressionModel model) {
       return trainingPartitions == null || !trainingPartitions.ContainsKey(model) ||
               (trainingPartitions[model].Start <= currentRow && currentRow < trainingPartitions[model].End);
     }
-
     private bool RowIsTestForModel(int currentRow, IRegressionModel model) {
       return testPartitions == null || !testPartitions.ContainsKey(model) ||
@@ -224 +205 @@
       var rowsToEvaluate = rows.Except(evaluationCache.Keys);
       var rowsEnumerator = rowsToEvaluate.GetEnumerator();
-      var valuesEnumerator = (from xs in GetEstimatedValueVectors(ProblemData.Dataset, rowsToEvaluate)
-                              select AggregateEstimatedValues(xs))
-                             .GetEnumerator();
+      var valuesEnumerator = Model.GetEstimatedValues(ProblemData.Dataset, rowsToEvaluate).GetEnumerator();
 
       while (rowsEnumerator.MoveNext() & valuesEnumerator.MoveNext()) {
@@ -235 +214 @@
     }
 
-    public IEnumerable<IEnumerable<double>> GetEstimatedValueVectors(IDataset dataset, IEnumerable<int> rows) {
-      if (!Model.Models.Any()) yield break;
-      var estimatedValuesEnumerators = (from model in Model.Models
-                                        select model.GetEstimatedValues(dataset, rows).GetEnumerator())
-                                       .ToList();
-
-      while (estimatedValuesEnumerators.All(en => en.MoveNext())) {
-        yield return from enumerator in estimatedValuesEnumerators
-                     select enumerator.Current;
-      }
-    }
-
-    private double AggregateEstimatedValues(IEnumerable<double> estimatedValues) {
-      return estimatedValues.DefaultIfEmpty(double.NaN).Average();
+    public IEnumerable<IEnumerable<double>> GetEstimatedValueVectors(IEnumerable<int> rows) {
+      return Model.GetEstimatedValueVectors(ProblemData.Dataset, rows);
     }
     #endregion