source: branches/SymbolicExpressionTreeDiversityAnalyzers/HeuristicLab.Problems.DataAnalysis.Symbolic/3.4/TreeMatching/SymbolicExpressionTreePhenotypicSimilarityCalculator.cs @ 12055

#region License Information
/* HeuristicLab
 * Copyright (C) 2002-2015 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 HeuristicLab.Common;
using HeuristicLab.Core;
using HeuristicLab.Data;
using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
using HeuristicLab.Optimization.Operators;
using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;

namespace HeuristicLab.Problems.DataAnalysis.Symbolic {
  [Item("SymbolicExpressionTreePhenotypicSimilarityCalculator", "An operator that calculates the similarity betweeon two trees based on the correlation of their outputs.")]
  [StorableClass]
  public class SymbolicExpressionTreePhenotypicSimilarityCalculator : SingleObjectiveSolutionSimilarityCalculator {
    public IDataAnalysisProblemData ProblemData { get; set; }
    public ISymbolicDataAnalysisExpressionTreeInterpreter Interpreter { get; set; }

    [StorableConstructor]
    protected SymbolicExpressionTreePhenotypicSimilarityCalculator(bool deserializing) : base(deserializing) { }

    public SymbolicExpressionTreePhenotypicSimilarityCalculator(SymbolicExpressionTreePhenotypicSimilarityCalculator original, Cloner cloner)
      : base(original, cloner) {
      this.ProblemData = original.ProblemData;
      this.Interpreter = original.Interpreter;
    }

    public override IDeepCloneable Clone(Cloner cloner) {
      return new SymbolicExpressionTreePhenotypicSimilarityCalculator(this, cloner);
    }

    public SymbolicExpressionTreePhenotypicSimilarityCalculator() { }

    public double CalculateSimilarity(ISymbolicExpressionTree t1, ISymbolicExpressionTree t2) {
      var v1 = Interpreter.GetSymbolicExpressionTreeValues(t1, ProblemData.Dataset, ProblemData.TrainingIndices);
      var v2 = Interpreter.GetSymbolicExpressionTreeValues(t2, ProblemData.Dataset, ProblemData.TrainingIndices);

      OnlineCalculatorError error;
      var r2 = OnlinePearsonsRSquaredCalculator.Calculate(v1, v2, out error);

      if (r2 > 1.0)
        r2 = 1.0;

      return error == OnlineCalculatorError.None ? r2 : 0;
    }

    public override double CalculateSolutionSimilarity(IScope leftSolution, IScope rightSolution) {
      if (leftSolution == rightSolution)
        return 1.0;

      var leftValues = (DoubleArray)leftSolution.Variables["EstimatedValues"].Value;
      var rightValues = (DoubleArray)rightSolution.Variables["EstimatedValues"].Value;

      if (leftValues.Variance().IsAlmost(0) && rightValues.Variance().IsAlmost(0))
        return 1.0;

      OnlineCalculatorError error;
      var r2 = OnlinePearsonsRSquaredCalculator.Calculate(leftValues, rightValues, out error);

      if (r2 > 1.0)
        r2 = 1.0; // sometimes due to fp errors it can happen that the r2 is over 1 (like 1.0000000009)

      return error == OnlineCalculatorError.None ? r2 : 0;
    }
  }
}