1  #region License Information


2  /* HeuristicLab


3  * Copyright (C) 20022016 Heuristic and Evolutionary Algorithms Laboratory (HEAL)


4  *


5  * This file is part of HeuristicLab.


6  *


7  * HeuristicLab is free software: you can redistribute it and/or modify


8  * it under the terms of the GNU General Public License as published by


9  * the Free Software Foundation, either version 3 of the License, or


10  * (at your option) any later version.


11  *


12  * HeuristicLab is distributed in the hope that it will be useful,


13  * but WITHOUT ANY WARRANTY; without even the implied warranty of


14  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the


15  * GNU General Public License for more details.


16  *


17  * You should have received a copy of the GNU General Public License


18  * along with HeuristicLab. If not, see <http://www.gnu.org/licenses/>.


19  */


20  #endregion


21 


22  using System.Linq;


23  using HeuristicLab.Common;


24  using HeuristicLab.Core;


25  using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;


26  using HeuristicLab.Problems.DataAnalysis;


27 


28  namespace HeuristicLab.Algorithms.DataAnalysis {


29  [Item("LDA", "Initializes the matrix by performing a linear discriminant analysis.")]


30  [StorableClass]


31  public class LdaInitializer : NcaInitializer {


32 


33  [StorableConstructor]


34  protected LdaInitializer(bool deserializing) : base(deserializing) { }


35  protected LdaInitializer(LdaInitializer original, Cloner cloner) : base(original, cloner) { }


36  public LdaInitializer() : base() { }


37 


38  public override IDeepCloneable Clone(Cloner cloner) {


39  return new LdaInitializer(this, cloner);


40  }


41 


42  public override double[,] Initialize(IClassificationProblemData data, int dimensions) {


43  var instances = data.TrainingIndices.Count();


44  var attributes = data.AllowedInputVariables.Count();


45 


46  var ldaDs = AlglibUtil.PrepareInputMatrix(data.Dataset,


47  data.AllowedInputVariables.Concat(data.TargetVariable.ToEnumerable()),


48  data.TrainingIndices);


49 


50  // map class values to sequential natural numbers (required by alglib)


51  var uniqueClasses = data.Dataset.GetDoubleValues(data.TargetVariable, data.TrainingIndices)


52  .Distinct()


53  .Select((v, i) => new { v, i })


54  .ToDictionary(x => x.v, x => x.i);


55 


56  for (int row = 0; row < instances; row++)


57  ldaDs[row, attributes] = uniqueClasses[ldaDs[row, attributes]];


58 


59  int info;


60  double[,] matrix;


61  alglib.fisherldan(ldaDs, instances, attributes, uniqueClasses.Count, out info, out matrix);


62 


63  return matrix;


64  }


65 


66  }


67  }

