source: branches/ClassificationEnsembleVoting/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/WeightCalculators/DiscriminantClassificationWeightCalculator.cs @ 8814

#region License Information
/* HeuristicLab
 * Copyright (C) 2002-2012 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.Collections.Generic;
using System.Linq;
using HeuristicLab.Common;
using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;

namespace HeuristicLab.Problems.DataAnalysis {
  /// <summary>
  /// Base class for weight calculators for classification solutions in an ensemble.
  /// </summary>
  [StorableClass]
  public abstract class DiscriminantClassificationWeightCalculator : ClassificationWeightCalculator {
    [StorableConstructor]
    protected DiscriminantClassificationWeightCalculator(bool deserializing) : base(deserializing) { }
    protected DiscriminantClassificationWeightCalculator(DiscriminantClassificationWeightCalculator original, Cloner cloner)
      : base(original, cloner) {
    }
    public DiscriminantClassificationWeightCalculator()
      : base() {
    }

    protected override IEnumerable<double> CalculateWeights(IEnumerable<IClassificationSolution> classificationSolutions) {
      if (!classificationSolutions.All(x => x is IDiscriminantFunctionClassificationSolution))
        return Enumerable.Repeat<double>(1.0, classificationSolutions.Count());

      IEnumerable<IDiscriminantFunctionClassificationSolution> discriminantSolutions = classificationSolutions.Cast<IDiscriminantFunctionClassificationSolution>();

      return DiscriminantCalculateWeights(discriminantSolutions);
    }

    protected abstract IEnumerable<double> DiscriminantCalculateWeights(IEnumerable<IDiscriminantFunctionClassificationSolution> discriminantSolutions);

    public override IEnumerable<double> AggregateEstimatedClassValues(IEnumerable<IClassificationSolution> solutions, Dataset dataset, IEnumerable<int> rows, CheckPoint handler) {
      if (!solutions.All(x => x is IDiscriminantFunctionClassificationSolution))
        return Enumerable.Repeat<double>(double.NaN, rows.Count());

      IEnumerable<IDiscriminantFunctionClassificationSolution> discriminantSolutions = solutions.Cast<IDiscriminantFunctionClassificationSolution>();

      IEnumerable<IDictionary<IClassificationSolution, double>> estimatedClassValues = GetEstimatedClassValues(solutions, dataset, rows, handler);
      IEnumerable<IDictionary<IDiscriminantFunctionClassificationSolution, double>> estimatedValues = GetEstimatedValues(discriminantSolutions, dataset, rows, handler);

      return from zip in estimatedClassValues.Zip(estimatedValues, (classValues, values) => new { ClassValues = classValues, Values = values })
             select DiscriminantAggregateEstimatedClassValues(zip.ClassValues, zip.Values);
    }

    protected virtual double DiscriminantAggregateEstimatedClassValues(IDictionary<IClassificationSolution, double> estimatedClassValues, IDictionary<IDiscriminantFunctionClassificationSolution, double> estimatedValues) {
      return base.AggregateEstimatedClassValues(estimatedClassValues);
    }

    protected IEnumerable<IDictionary<IDiscriminantFunctionClassificationSolution, double>> GetEstimatedValues(IEnumerable<IDiscriminantFunctionClassificationSolution> solutions, Dataset dataset, IEnumerable<int> rows, CheckPoint handler) {
      var estimatedValuesEnumerators = (from solution in solutions
                                        select new { Solution = solution, EstimatedValuesEnumerator = solution.Model.GetEstimatedValues(dataset, rows).GetEnumerator() })
                                        .ToList();

      var rowEnumerator = rows.GetEnumerator();
      while (rowEnumerator.MoveNext() && estimatedValuesEnumerators.All(x => x.EstimatedValuesEnumerator.MoveNext())) {
        yield return (from enumerator in estimatedValuesEnumerators
                      where handler(enumerator.Solution.ProblemData, rowEnumerator.Current)
                      select enumerator)
                      .ToDictionary(x => x.Solution, x => x.EstimatedValuesEnumerator.Current);
      }
    }

    public sealed override double GetConfidence(IEnumerable<IClassificationSolution> solutions, int index, double estimatedClassValue, CheckPoint handler) {
      if (solutions.Count() < 1 || !solutions.All(x => x is IDiscriminantFunctionClassificationSolution))
        return double.NaN;

      IEnumerable<IDiscriminantFunctionClassificationSolution> discriminantSolutions = solutions.Cast<IDiscriminantFunctionClassificationSolution>();

      return GetDiscriminantConfidence(discriminantSolutions, index, estimatedClassValue, handler);
    }

    protected virtual double GetDiscriminantConfidence(IEnumerable<IDiscriminantFunctionClassificationSolution> solutions, int index, double estimatedClassValue, CheckPoint handler) {
      return base.GetConfidence(solutions, index, estimatedClassValue, handler);
    }

    public sealed override IEnumerable<double> GetConfidence(IEnumerable<IClassificationSolution> solutions, IEnumerable<int> indices, IEnumerable<double> estimatedClassValue, CheckPoint handler) {
      if (solutions.Count() < 1 || !solutions.All(x => x is IDiscriminantFunctionClassificationSolution))
        return Enumerable.Repeat(double.NaN, indices.Count());

      IEnumerable<IDiscriminantFunctionClassificationSolution> discriminantSolutions = solutions.Cast<IDiscriminantFunctionClassificationSolution>();

      return GetDiscriminantConfidence(discriminantSolutions, indices, estimatedClassValue, handler);
    }

    public virtual IEnumerable<double> GetDiscriminantConfidence(IEnumerable<IDiscriminantFunctionClassificationSolution> solutions, IEnumerable<int> indices, IEnumerable<double> estimatedClassValue, CheckPoint handler) {
      return base.GetConfidence(solutions, indices, estimatedClassValue, handler);
    }
  }
}