source: branches/DataAnalysis/HeuristicLab.Problems.DataAnalysis/3.3/Operators/CovariantParsimonyPressure.cs @ 4233

#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 System.Linq;
using alglib;
using HeuristicLab.Core;
using HeuristicLab.Data;
using HeuristicLab.Operators;
using HeuristicLab.Optimization;
using HeuristicLab.Parameters;
using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
using System.Collections.Generic;
using HeuristicLab.Problems.DataAnalysis.Evaluators;

namespace HeuristicLab.Problems.DataAnalysis.Operators {
  [Item("Covariant Parsimony Pressure", "Covariant Parsimony Pressure.")]
  [StorableClass]
  public class CovariantParsimonyPressure : SingleSuccessorOperator {
    public IScopeTreeLookupParameter<SymbolicExpressionTree> SymbolicExpressionTreeParameter {
      get { return (IScopeTreeLookupParameter<SymbolicExpressionTree>)Parameters["SymbolicExpressionTree"]; }
    }
    public IScopeTreeLookupParameter<DoubleValue> QualityParameter {
      get { return (IScopeTreeLookupParameter<DoubleValue>)Parameters["Quality"]; }
    }
    public ILookupParameter<BoolValue> MaximizationParameter {
      get { return (ILookupParameter<BoolValue>)Parameters["Maximization"]; }
    }
    public IValueLookupParameter<DoubleValue> KParameter {
      get { return (IValueLookupParameter<DoubleValue>)Parameters["K"]; }
    }


    public CovariantParsimonyPressure(bool deserializing) : base(deserializing) { }
    public CovariantParsimonyPressure()
      : base() {
      Parameters.Add(new ScopeTreeLookupParameter<SymbolicExpressionTree>("SymbolicExpressionTree"));
      Parameters.Add(new ScopeTreeLookupParameter<DoubleValue>("Quality"));
      Parameters.Add(new LookupParameter<BoolValue>("Maximization"));
      Parameters.Add(new ValueLookupParameter<DoubleValue>("K", new DoubleValue(1.0)));
    }

    [StorableHook(Persistence.Default.CompositeSerializers.Storable.HookType.AfterDeserialization)]
    private void AfterDeserialization() {
      if (!Parameters.ContainsKey("Maximization"))
        Parameters.Add(new LookupParameter<BoolValue>("Maximization"));
      if (!Parameters.ContainsKey("K"))
        Parameters.Add(new ValueLookupParameter<DoubleValue>("K", new DoubleValue(1.0)));
    }

    public override IOperation Apply() {
      var trees = SymbolicExpressionTreeParameter.ActualValue;
      var qualities = QualityParameter.ActualValue;
      var lengths = from tree in trees
                    select tree.Size;
      double k = KParameter.ActualValue.Value;

      // calculate cov(f, l) and cov(l, l^k)
      OnlineCovarianceEvaluator lengthFitnessCovEvaluator = new OnlineCovarianceEvaluator();
      OnlineCovarianceEvaluator lengthAdjLengthCovEvaluator = new OnlineCovarianceEvaluator();
      var lengthEnumerator = lengths.GetEnumerator();
      var qualityEnumerator = qualities.GetEnumerator();
      while (lengthEnumerator.MoveNext() & qualityEnumerator.MoveNext()) {
        double fitness = qualityEnumerator.Current.Value;
        if (!MaximizationParameter.ActualValue.Value) {
          // use f = 1 / (1 + quality) for minimization problems
          fitness = 1.0 / (1.0 + fitness);
        }
        lengthFitnessCovEvaluator.Add(lengthEnumerator.Current, fitness);
        lengthAdjLengthCovEvaluator.Add(lengthEnumerator.Current, Math.Pow(lengthEnumerator.Current, k));
      }

      // c = cov(l, f) / cov(l, l^k)
      double c = lengthFitnessCovEvaluator.Covariance / lengthAdjLengthCovEvaluator.Covariance;

      // adjust fitness
      bool maximization = MaximizationParameter.ActualValue.Value;

      lengthEnumerator = lengths.GetEnumerator();
      qualityEnumerator = qualities.GetEnumerator();
      while (lengthEnumerator.MoveNext() & qualityEnumerator.MoveNext()) {
        qualityEnumerator.Current.Value = qualityEnumerator.Current.Value - c * Math.Pow(lengthEnumerator.Current, k);
      }

      return base.Apply();
    }
  }
}