#region License Information /* HeuristicLab * Copyright (C) 2002-2014 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 . */ #endregion using HeuristicLab.Common; using HeuristicLab.Core; using HeuristicLab.Data; using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding; using HeuristicLab.Operators; using HeuristicLab.Parameters; using HeuristicLab.Persistence.Default.CompositeSerializers.Storable; namespace HeuristicLab.Problems.DataAnalysis.Symbolic { [StorableClass] public class SymbolicDataAnalysisExpressionTreeSimilarityCalculator : SingleSuccessorOperator { private const string SymbolicExpressionTreeParameterName = "SymbolicExpressionTree"; private const string CurrentSymbolicExpressionTreeParameterName = "CurrentSymbolicExpressionTree"; private const string SimilarityValuesParmeterName = "Similarity"; // comparer parameters private const string MatchVariablesParameterName = "MatchVariableNames"; private const string MatchVariableWeightsParameterName = "MatchVariableWeights"; private const string MatchConstantValuesParameterName = "MatchConstantValues"; public IScopeTreeLookupParameter SymbolicExpressionTreeParameter { get { return (IScopeTreeLookupParameter)Parameters[SymbolicExpressionTreeParameterName]; } } public IValueParameter CurrentSymbolicExpressionTreeParameter { get { return (IValueParameter)Parameters[CurrentSymbolicExpressionTreeParameterName]; } } public ILookupParameter MatchVariableNamesParameter { get { return (ILookupParameter)Parameters[MatchVariablesParameterName]; } } public ILookupParameter MatchVariableWeightsParameter { get { return (ILookupParameter)Parameters[MatchVariableWeightsParameterName]; } } public ILookupParameter MatchConstantValuesParameter { get { return (ILookupParameter)Parameters[MatchConstantValuesParameterName]; } } public ILookupParameter SimilarityParameter { get { return (ILookupParameter)Parameters[SimilarityValuesParmeterName]; } } public ISymbolicExpressionTree CurrentSymbolicExpressionTree { get { return CurrentSymbolicExpressionTreeParameter.Value; } set { CurrentSymbolicExpressionTreeParameter.Value = value; } } public SymbolicExpressionTreeNodeSimilarityComparer SimilarityComparer { get; set; } public int MaximumTreeDepth { get; set; } protected SymbolicDataAnalysisExpressionTreeSimilarityCalculator( SymbolicDataAnalysisExpressionTreeSimilarityCalculator original, Cloner cloner) : base(original, cloner) { } public override IDeepCloneable Clone(Cloner cloner) { return new SymbolicDataAnalysisExpressionTreeSimilarityCalculator(this, cloner); } [StorableConstructor] protected SymbolicDataAnalysisExpressionTreeSimilarityCalculator(bool deserializing) : base(deserializing) { } public SymbolicDataAnalysisExpressionTreeSimilarityCalculator() : base() { Parameters.Add(new ScopeTreeLookupParameter(SymbolicExpressionTreeParameterName, "The symbolic expression trees to analyze.")); Parameters.Add(new ValueParameter(CurrentSymbolicExpressionTreeParameterName, "")); Parameters.Add(new LookupParameter(MatchVariablesParameterName, "Specify if the symbolic expression tree comparer should match variable names.")); Parameters.Add(new LookupParameter(MatchVariableWeightsParameterName, "Specify if the symbolic expression tree comparer should match variable weghts.")); Parameters.Add(new LookupParameter(MatchConstantValuesParameterName, "Specify if the symbolic expression tree comparer should match constant values.")); Parameters.Add(new LookupParameter(SimilarityValuesParmeterName, "")); } public override IOperation Apply() { var trees = SymbolicExpressionTreeParameter.ActualValue; double similarity = 0.0; var current = CurrentSymbolicExpressionTree; bool found = false; foreach (var tree in trees) { if (tree == current) { found = true; continue; } if (found) { similarity += MaxCommonSubtreeSimilarity(current, tree, SimilarityComparer); } } lock (SimilarityParameter.ActualValue) { SimilarityParameter.ActualValue.Value += similarity; } return base.Apply(); } public static double CalculateSimilarity(ISymbolicExpressionTreeNode a, ISymbolicExpressionTreeNode b, SymbolicExpressionTreeNodeSimilarityComparer comparer) { return 2.0 * SymbolicExpressionTreeMatching.Match(a, b, comparer) / (a.GetLength() + b.GetLength()); } /// /// Try to match each pair of nodes from trees a and b and return a similarity value based on the maximum number of matched node pairs. /// /// /// /// /// A similarity value computed as 2.0 * MaxNumberOfMatchedPairs / (Sum of both tree sizes) public static double MaxCommonSubtreeSimilarity(ISymbolicExpressionTree a, ISymbolicExpressionTree b, SymbolicExpressionTreeNodeSimilarityComparer comparer) { int max = 0; var rootA = a.Root.GetSubtree(0).GetSubtree(0); var rootB = b.Root.GetSubtree(0).GetSubtree(0); foreach (var aa in rootA.IterateNodesBreadth()) { int lenA = aa.GetLength(); if (lenA <= max) continue; foreach (var bb in rootB.IterateNodesBreadth()) { int lenB = bb.GetLength(); if (lenB <= max) continue; int matches = SymbolicExpressionTreeMatching.Match(aa, bb, comparer); if (max < matches) max = matches; } } return 2.0 * max / (rootA.GetLength() + rootB.GetLength()); } // returns true if both nodes are variables, or both are constants, or both are functions private static bool SameType(ISymbolicExpressionTreeNode a, ISymbolicExpressionTreeNode b) { if (a is VariableTreeNode) { return b is VariableTreeNode; } if (a is ConstantTreeNode) { return b is ConstantTreeNode; } return true; } } }