source: branches/ClassificationEnsembleVoting/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/WeightCalculators/DiscriminantClassificationWeightCalculator.cs @ 7531

#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.Core;
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(ItemCollection<IClassificationSolution> classificationSolutions) {
      if (!classificationSolutions.All(x => x is IDiscriminantFunctionClassificationSolution))
        return Enumerable.Repeat<double>(1.0, classificationSolutions.Count);

      ItemCollection<IDiscriminantFunctionClassificationSolution> discriminantSolutions = new ItemCollection<IDiscriminantFunctionClassificationSolution>();
      foreach (var solution in classificationSolutions) {
        discriminantSolutions.Add((IDiscriminantFunctionClassificationSolution)solution);
      }

      return DiscriminantCalculateWeights(discriminantSolutions);
    }

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

    public override IEnumerable<double> AggregateEstimatedClassValues(IEnumerable<IClassificationModel> models, Dataset dataset, IEnumerable<int> rows) {
      if (!models.All(x => x is IDiscriminantFunctionClassificationModel))
        return Enumerable.Repeat<double>(0.0, rows.Count());

      IEnumerable<IDiscriminantFunctionClassificationModel> discriminantModels = models.Cast<IDiscriminantFunctionClassificationModel>();

      IEnumerable<IEnumerable<double>> estimatedClassValues = ClassificationWeightCalculator.GetEstimatedClassValues(models, dataset, rows);
      IEnumerable<IEnumerable<double>> estimatedValues = DiscriminantClassificationWeightCalculator.GetEstimatedValues(discriminantModels, dataset, rows);

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

    protected virtual double DiscriminantAggregateEstimatedClassValues(IEnumerable<double> estimatedClassValues, IEnumerable<double> estimatedValues) {
      return AggregateEstimatedClassValues(estimatedClassValues);
    }

    protected static IEnumerable<IEnumerable<double>> GetEstimatedValues(IEnumerable<IDiscriminantFunctionClassificationModel> models, Dataset dataset, IEnumerable<int> rows) {
      if (!models.Any()) yield break;
      var estimatedValuesEnumerators = (from model in models
                                        select model.GetEstimatedValues(dataset, rows).GetEnumerator())
                                       .ToList();

      while (estimatedValuesEnumerators.All(en => en.MoveNext())) {
        yield return from enumerator in estimatedValuesEnumerators
                     select enumerator.Current;
      }
    }
  }
}