source: branches/DataAnalysis.PopulationDiversityAnalysis/HeuristicLab.Problems.DataAnalysis.Regression/3.3/Symbolic/Analyzers/VariablesUsagePopulationDiversityAnalyzer.cs @ 4881

#region License Information
/* HeuristicLab
 * Copyright (C) 2002-2010 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 HeuristicLab.Analysis;
using HeuristicLab.Common;
using HeuristicLab.Core;
using HeuristicLab.Data;
using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
using HeuristicLab.Operators;
using HeuristicLab.Optimization;
using HeuristicLab.Optimization.Operators;
using HeuristicLab.Parameters;
using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
using HeuristicLab.Problems.DataAnalysis.Symbolic;
using System.Collections.Generic;
using HeuristicLab.Problems.DataAnalysis.Symbolic.Symbols;

namespace HeuristicLab.Problems.DataAnalysis.Regression.Symbolic.Analyzers {
  /// <summary>
  /// An operator that analyzes the population diversity with respect to the sets of used variables.
  /// </summary>
  [Item("VariablesUsagePopulationDiversityAnalysisOperator", "An operator that analyzes the population diversity with respect to the sets of used variables.")]
  [StorableClass]
  public sealed class VariablesUsagePopulationDiversityAnalyzer : PopulationDiversityAnalyzer<SymbolicExpressionTree>, ISymbolicRegressionAnalyzer {

    private const string ProblemDataParameterName = "ProblemData";

    public IValueLookupParameter<DataAnalysisProblemData> ProblemDataParameter {
      get { return (IValueLookupParameter<DataAnalysisProblemData>)Parameters[ProblemDataParameterName]; }
    }
    public DataAnalysisProblemData ProblemData {
      get { return ProblemDataParameter.ActualValue; }
    }

    #region ISymbolicRegressionAnalyzer Members

    public ScopeTreeLookupParameter<SymbolicExpressionTree> SymbolicExpressionTreeParameter {
      get { return base.SolutionParameter; }
    }

    public new ILookupParameter<ResultCollection> ResultsParameter {
      get { return base.ResultsParameter; }
    }

    #endregion

    [StorableConstructor]
    private VariablesUsagePopulationDiversityAnalyzer(bool deserializing) : base(deserializing) { }
    private VariablesUsagePopulationDiversityAnalyzer(VariablesUsagePopulationDiversityAnalyzer original, Cloner cloner) : base(original, cloner) { }
    public VariablesUsagePopulationDiversityAnalyzer() : base() {
      Parameters.Add(new ValueLookupParameter<DataAnalysisProblemData>(ProblemDataParameterName, "The problem data for which the symbolic expression tree is a solution."));
    }

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

    protected override double[,] CalculateSimilarities(SymbolicExpressionTree[] solutions) {
      int n = solutions.Length;
      List<string> variableNames = new List<string>() ;
      foreach (StringValue inputVariable in ProblemData.InputVariables)
        variableNames.Add(inputVariable.Value);
      List<int>[] usedVariables = new List<int>[n];
      for (int i = 0; i < n; i++) {
        usedVariables[i] = collectUsedVariables(solutions[i], variableNames);
      }
      double[,] result = new double[n, n];
      for (int i = 0; i < n; i++) {
        for (int j = 0; j < n; j++) {
          if (i == j)
            result[i, j] = 1;
          else
            result[i, j] = overlapRatio(usedVariables[i], usedVariables[j]);
        }
      }
      return result;
    }

    private List<int> collectUsedVariables(SymbolicExpressionTree tree, List<string> variableNames) {
      List<int> variables = new List<int>();
      collectUsedVariables(tree.Root, variables, variableNames);
      return variables;
    }

    private void collectUsedVariables(SymbolicExpressionTreeNode node, List<int> variables, List<string> variableNames) {
      if (node is VariableTreeNode) {
        string varName = (node as VariableTreeNode).VariableName;
        int varIndex = variableNames.IndexOf(varName);
        if (!variables.Contains(varIndex))
          variables.Add(varIndex);
      }
      foreach (SymbolicExpressionTreeNode subnode in node.SubTrees)
        collectUsedVariables(subnode, variables, variableNames);
    }

    private double overlapRatio(List<int> list1, List<int> list2) {
      int found = 0;
      foreach (int i in list1)
        if (list2.Contains(i))
          found++;
      return ((double)found) / list1.Count;
    }

  }
}