1  #region License Information


2  /* HeuristicLab


3  * Copyright (C) 20022012 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;


23  using System.Collections.Generic;


24  using System.Linq;


25  using HeuristicLab.Common;


26  using HeuristicLab.Core;


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


28 


29  namespace HeuristicLab.Algorithms.DataAnalysis {


30  [StorableClass]


31  [Item(Name = "CovarianceSEard", Description = "Squared exponential covariance function with automatic relevance determination for Gaussian processes.")]


32  public class CovarianceSEard : Item, ICovarianceFunction {


33  [Storable]


34  private double sf2;


35  public double Scale { get { return sf2; } }


36 


37  [Storable]


38  private double[] inverseLength;


39  public double[] Length {


40  get {


41  if (inverseLength == null) return new double[0];


42  var copy = new double[inverseLength.Length];


43  Array.Copy(inverseLength, copy, copy.Length);


44  return copy;


45  }


46  }


47 


48  public int GetNumberOfParameters(int numberOfVariables) {


49  return numberOfVariables + 1;


50  }


51  [StorableConstructor]


52  protected CovarianceSEard(bool deserializing) : base(deserializing) { }


53  protected CovarianceSEard(CovarianceSEard original, Cloner cloner)


54  : base(original, cloner) {


55  if (original.inverseLength != null) {


56  this.inverseLength = new double[original.inverseLength.Length];


57  Array.Copy(original.inverseLength, this.inverseLength, inverseLength.Length);


58  }


59  this.sf2 = original.sf2;


60  }


61  public CovarianceSEard()


62  : base() {


63  }


64 


65  public override IDeepCloneable Clone(Cloner cloner) {


66  return new CovarianceSEard(this, cloner);


67  }


68 


69  public void SetParameter(double[] hyp) {


70  this.inverseLength = hyp.Take(hyp.Length  1).Select(p => 1.0 / Math.Exp(p)).ToArray();


71  this.sf2 = Math.Exp(2 * hyp[hyp.Length  1]);


72  }


73 


74  public double GetCovariance(double[,] x, int i, int j) {


75  double d = i == j


76  ? 0.0


77  : Util.SqrDist(x, i, j, inverseLength);


78  return sf2 * Math.Exp(d / 2.0);


79  }


80 


81  public IEnumerable<double> GetGradient(double[,] x, int i, int j) {


82  double d = i == j


83  ? 0.0


84  : Util.SqrDist(x, i, j, inverseLength);


85 


86  for (int ii = 0; ii < inverseLength.Length; ii++) {


87  double sqrDist = Util.SqrDist(x[i, ii] * inverseLength[ii], x[j, ii] * inverseLength[ii]);


88  yield return sf2 * Math.Exp(d / 2.0) * sqrDist;


89  }


90  yield return 2.0 * sf2 * Math.Exp(d / 2.0);


91  }


92 


93  public double GetCrossCovariance(double[,] x, double[,] xt, int i, int j) {


94  double d = Util.SqrDist(x, i, xt, j, inverseLength);


95  return sf2 * Math.Exp(d / 2.0);


96  }


97  }


98  }

