Changeset 12247 for branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Problems.DataAnalysis.Symbolic

Timestamp:

03/24/15 11:17:08 (10 years ago)

Author:

mkommend

Message:

#2276: Merged trunk changes into dataset refactoring branch.

Location:

branches/HeuristicLab.DatasetRefactor/sources

Files:

• . (modified) (1 prop)
• HeuristicLab.Problems.DataAnalysis.Symbolic (modified) (1 prop)
• HeuristicLab.Problems.DataAnalysis.Symbolic/3.4/SymbolicDataAnalysisExpressionPruningOperator.cs (modified) (3 diffs)
• HeuristicLab.Problems.DataAnalysis.Symbolic/3.4/SymbolicDataAnalysisExpressionTreeSimplifier.cs (modified) (4 diffs)

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Problems.DataAnalysis.Symbolic/3.4/SymbolicDataAnalysisExpressionPruningOperator.cs

@@ -109 +109 @@
       : base(original, cloner) { }
 
-    protected SymbolicDataAnalysisExpressionPruningOperator() {
+    protected SymbolicDataAnalysisExpressionPruningOperator(ISymbolicDataAnalysisSolutionImpactValuesCalculator impactValuesCalculator) {
       #region add parameters
       Parameters.Add(new LookupParameter<IDataAnalysisProblemData>(ProblemDataParameterName));
@@ -122 +122 @@
       Parameters.Add(new LookupParameter<ISymbolicExpressionTree>(SymbolicExpressionTreeParameterName));
       Parameters.Add(new LookupParameter<DoubleValue>(QualityParameterName));
+      Parameters.Add(new ValueParameter<ISymbolicDataAnalysisSolutionImpactValuesCalculator>(ImpactValuesCalculatorParameterName, impactValuesCalculator));
       #endregion
     }
 
-    protected abstract ISymbolicDataAnalysisModel CreateModel();
+    protected abstract ISymbolicDataAnalysisModel CreateModel(ISymbolicExpressionTree tree, ISymbolicDataAnalysisExpressionTreeInterpreter interpreter, IDataAnalysisProblemData problemData, DoubleLimit estimationLimits);
 
     protected abstract double Evaluate(IDataAnalysisModel model);
 
     public override IOperation Apply() {
-      var model = CreateModel();
+      var model = CreateModel(SymbolicExpressionTree, Interpreter, ProblemData, EstimationLimits);
       var nodes = SymbolicExpressionTree.Root.GetSubtree(0).GetSubtree(0).IterateNodesPrefix().ToList();
       var rows = Enumerable.Range(FitnessCalculationPartition.Start, FitnessCalculationPartition.Size);
@@ -169 +170 @@
     }
 
-    private static void ReplaceWithConstant(ISymbolicExpressionTreeNode original, ISymbolicExpressionTreeNode replacement) {
+    public ISymbolicExpressionTree Prune(ISymbolicExpressionTree tree, ISymbolicDataAnalysisExpressionTreeInterpreter interpreter, IDataAnalysisProblemData problemData, DoubleLimit estimationLimits) {
+      var model = CreateModel((ISymbolicExpressionTree)tree.Clone(), Interpreter, ProblemData, EstimationLimits);
+      var nodes = SymbolicExpressionTree.Root.GetSubtree(0).GetSubtree(0).IterateNodesPrefix().ToList();
+      var rows = Enumerable.Range(FitnessCalculationPartition.Start, FitnessCalculationPartition.Size);
+
+      double quality = Evaluate(model);
+
+      for (int i = 0; i < nodes.Count; ++i) {
+        var node = nodes[i];
+        if (node is ConstantTreeNode) continue;
+
+        double impactValue, replacementValue;
+        ImpactValuesCalculator.CalculateImpactAndReplacementValues(model, node, ProblemData, rows, out impactValue, out replacementValue, quality);
+
+        if (PruneOnlyZeroImpactNodes) {
+          if (!impactValue.IsAlmost(0.0)) continue;
+        } else if (NodeImpactThreshold < impactValue) {
+          continue;
+        }
+
+        var constantNode = (ConstantTreeNode)node.Grammar.GetSymbol("Constant").CreateTreeNode();
+        constantNode.Value = replacementValue;
+
+        ReplaceWithConstant(node, constantNode);
+        i += node.GetLength() - 1; // skip subtrees under the node that was folded
+
+        quality -= impactValue;
+      }
+      return model.SymbolicExpressionTree;
+    }
+
+    protected static void ReplaceWithConstant(ISymbolicExpressionTreeNode original, ISymbolicExpressionTreeNode replacement) {
       var parent = original.Parent;
       var i = parent.IndexOfSubtree(original);

branches/HeuristicLab.DatasetRefactor/sources/HeuristicLab.Problems.DataAnalysis.Symbolic/3.4/SymbolicDataAnalysisExpressionTreeSimplifier.cs

@@ -299 +299 @@
         // simplify expressions x0..xn
         // make multiplication (x0 * 1/(x1 * x1 * .. * xn))
-        var simplifiedTrees = original.Subtrees.Select(x => GetSimplifiedTree(x));
+        var simplifiedTrees = original.Subtrees.Select(GetSimplifiedTree).ToArray();
         return
-          MakeProduct(simplifiedTrees.First(), Invert(simplifiedTrees.Skip(1).Aggregate((a, b) => MakeProduct(a, b))));
+          MakeProduct(simplifiedTrees.First(), Invert(simplifiedTrees.Skip(1).Aggregate(MakeProduct)));
       }
     }
@@ -310 +310 @@
       } else {
         return original.Subtrees
-          .Select(x => GetSimplifiedTree(x))
-          .Aggregate((a, b) => MakeProduct(a, b));
+          .Select(GetSimplifiedTree).ToArray()
+          .Aggregate(MakeProduct);
       }
     }
@@ -321 +321 @@
         // simplify expressions x0..xn
         // make addition (x0,-x1..-xn)
-        var simplifiedTrees = original.Subtrees.Select(x => GetSimplifiedTree(x));
+        var simplifiedTrees = original.Subtrees.Select(GetSimplifiedTree).ToArray();
         return simplifiedTrees.Take(1)
-          .Concat(simplifiedTrees.Skip(1).Select(x => Negate(x)))
-          .Aggregate((a, b) => MakeSum(a, b));
+          .Concat(simplifiedTrees.Skip(1).Select(Negate))
+          .Aggregate(MakeSum);
       }
     }
@@ -335 +335 @@
         // make addition (x0..xn)
         return original.Subtrees
-          .Select(x => GetSimplifiedTree(x))
-          .Aggregate((a, b) => MakeSum(a, b));
+          .Select(GetSimplifiedTree).ToArray()
+          .Aggregate(MakeSum);
       }
     }