Changeset 16053 for branches/2886_SymRegGrammarEnumeration/HeuristicLab.Algorithms.DataAnalysis.SymRegGrammarEnumeration/GrammarEnumeration/GrammarEnumerationAlgorithm.cs

Timestamp:

08/06/18 16:54:14 (6 years ago)

Author:

bburlacu

Message:

#2886: Refactor RSquaredEvaluator as a standalone ParameterizedNamedItem which is a parameter of the algorithm. Implement BestSolutionAnalyzer analyzer for quality statistics. Add license headers where missing.

File:

• branches/2886_SymRegGrammarEnumeration/HeuristicLab.Algorithms.DataAnalysis.SymRegGrammarEnumeration/GrammarEnumeration/GrammarEnumerationAlgorithm.cs (modified) (13 diffs)

branches/2886_SymRegGrammarEnumeration/HeuristicLab.Algorithms.DataAnalysis.SymRegGrammarEnumeration/GrammarEnumeration/GrammarEnumerationAlgorithm.cs

@@ -1 @@
-using System;
+#region License Information
+/* HeuristicLab
+ * Copyright (C) 2002-2018 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ *
+ * This file is part of HeuristicLab.
+ *
+ * HeuristicLab is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * HeuristicLab is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with HeuristicLab. If not, see <http://www.gnu.org/licenses/>.
+ */
+#endregion
+
+using System;
 using System.Collections.Generic;
 using System.Linq;
 using System.Threading;
-using HeuristicLab.Algorithms.DataAnalysis.SymRegGrammarEnumeration.GrammarEnumeration;
 using HeuristicLab.Collections;
 using HeuristicLab.Common;
@@ -31 +51 @@
     private readonly string ExpansionsPerSecondName = "Expansions per second";
 
-    private readonly string OptimizeConstantsParameterName = "Optimize Constants";
-    private readonly string ConstantOptimizationIterationsParameterName = "Constant Optimization Iterations";
+    private readonly string EvaluatorParameterName = "Evaluator";
+
     private readonly string ErrorWeightParameterName = "Error Weight";
     private readonly string SearchDataStructureParameterName = "Search Data Structure";
@@ -47 +67 @@
     public override bool SupportsPause { get { return true; } }
 
-    protected IFixedValueParameter<BoolValue> OptimizeConstantsParameter {
-      get { return (IFixedValueParameter<BoolValue>)Parameters[OptimizeConstantsParameterName]; }
-    }
-
-    public bool OptimizeConstants {
-      get { return OptimizeConstantsParameter.Value.Value; }
-      set { OptimizeConstantsParameter.Value.Value = value; }
-    }
-
-    public int ConstantOptimizationIterations {
-      get { return ConstantOptimizationIterationsParameter.Value.Value; }
-      set { ConstantOptimizationIterationsParameter.Value.Value = value; }
-    }
-
-    public IFixedValueParameter<IntValue> ConstantOptimizationIterationsParameter {
-      get { return (IFixedValueParameter<IntValue>)Parameters[ConstantOptimizationIterationsParameterName]; }
+    public IFixedValueParameter<RSquaredEvaluator> EvaluatorParameter {
+      get { return (IFixedValueParameter<RSquaredEvaluator>)Parameters[EvaluatorParameterName]; }
+    }
+
+    public RSquaredEvaluator Evaluator {
+      get { return EvaluatorParameter.Value; }
     }
 
@@ -102 +112 @@
     public int SearchDataStructureSize {
       get { return SearchDataStructureSizeParameter.Value.Value; }
+      set { SearchDataStructureSizeParameter.Value.Value = value; }
     }
 
@@ -189 +200 @@
 
     public GrammarEnumerationAlgorithm() {
-      Parameters.Add(new FixedValueParameter<BoolValue>(OptimizeConstantsParameterName, "Run constant optimization in sentence evaluation.", new BoolValue(false)));
       Parameters.Add(new FixedValueParameter<DoubleValue>(ErrorWeightParameterName, "Defines, how much weight is put on a phrase's r² value when priorizing phrases during search.", new DoubleValue(0.8)));
       Parameters.Add(new FixedValueParameter<IntValue>(MaxComplexityParameterName, "The maximum number of variable symbols in a sentence.", new IntValue(12)));
@@ -195 +205 @@
       Parameters.Add(new FixedValueParameter<IntValue>(SearchDataStructureSizeParameterName, "The size of the search data structure.", new IntValue((int)1e5)));
       Parameters.Add(new FixedValueParameter<EnumValue<StorageType>>(SearchDataStructureParameterName, new EnumValue<StorageType>(StorageType.SortedSet)));
-      Parameters.Add(new FixedValueParameter<IntValue>(ConstantOptimizationIterationsParameterName, new IntValue(10)));
+      Parameters.Add(new FixedValueParameter<RSquaredEvaluator>(EvaluatorParameterName, new RSquaredEvaluator()));
 
       SearchDataStructureParameter.Value.ValueChanged += (o, e) => Prepare();
@@ -203 +213 @@
         new SearchGraphVisualizer(),
         new SentenceLogger(),
-        new RSquaredEvaluator()
+        new BestSolutionAnalyzer()
       };
 
@@ -215 +225 @@
         Analyzers.SetItemCheckedState(analyzer, false);
       }
-      Analyzers.SetItemCheckedState(Analyzers.First(analyzer => analyzer is RSquaredEvaluator), true);
+      Analyzers.SetItemCheckedState(Analyzers.First(analyzer => analyzer is BestSolutionAnalyzer), true);
 
       var grammarSymbols = Enum.GetValues(typeof(GrammarRule))
@@ -275 +285 @@
       MaxSentenceLength = Grammar.GetMaxSentenceLength(MaxComplexity);
       var errorWeight = ErrorWeight;
-      var optimizeConstants = OptimizeConstants; // cache value to avoid parameter lookup
-      var iterations = ConstantOptimizationIterations;
+      var evaluator = EvaluatorParameter.Value;
+      var problemData = Problem.ProblemData;
+
       // main search loop
       while (OpenPhrases.Count > 0) {
@@ -317 +328 @@
 
             // Is the best solution found? (only if RSquaredEvaluator is activated)
-            if (Results.ContainsKey(RSquaredEvaluator.BestTrainingQualityResultName)) {
-              double r2 = ((DoubleValue)Results[RSquaredEvaluator.BestTrainingQualityResultName].Value).Value;
-              if (r2.IsAlmost(1.0)) {
-                UpdateView(force: true);
-                return;
-              }
-            }
+            //if (Results.ContainsKey(RSquaredEvaluator.BestTrainingQualityResultName)) {
+            //  double r2 = ((DoubleValue)Results[RSquaredEvaluator.BestTrainingQualityResultName].Value).Value;
+            //  if (r2.IsAlmost(1.0)) {
+            //    UpdateView(force: true);
+            //    return;
+            //  }
+            //}
 
             if (!DistinctSentencesComplexity.ContainsKey(phraseHash) || DistinctSentencesComplexity[phraseHash] > newPhraseComplexity) {
@@ -334 +345 @@
 
           } else if (!OpenPhrases.Contains(phraseHash) && !ArchivedPhrases.Contains(phraseHash)) {
-
-            bool isCompleteSentence = IsCompleteSentence(newPhrase);
-            double r2 = isCompleteSentence ? Grammar.EvaluatePhrase(newPhrase, Problem.ProblemData, optimizeConstants, iterations) : fetchedSearchNode.R2;
+            double r2 = IsCompleteSentence(newPhrase) ? evaluator.Evaluate(problemData, Grammar, newPhrase) : fetchedSearchNode.R2;
             double phrasePriority = GetPriority(newPhrase, r2);
 
@@ -389 +398 @@
       var model = new SymbolicRegressionModel(Problem.ProblemData.TargetVariable, tree, interpreter);
 
+      var iterations = EvaluatorParameter.Value.ConstantOptimizationIterations;
+      var applyLinearScaling = EvaluatorParameter.Value.ApplyLinearScaling;
+
       SymbolicRegressionConstantOptimizationEvaluator.OptimizeConstants(
         interpreter,
@@ -394 +406 @@
         Problem.ProblemData,
         Problem.ProblemData.TrainingIndices,
-        applyLinearScaling: true,
-        maxIterations: ConstantOptimizationIterations,
+        applyLinearScaling: applyLinearScaling,
+        maxIterations: iterations,
         updateVariableWeights: false,
         updateConstantsInTree: true);