1  #region License Information


2  /* HeuristicLab


3  * Copyright (C) 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.Data;


28  using HeuristicLab.Parameters;


29  using HEAL.Attic;


30 


31  namespace HeuristicLab.Algorithms.DataAnalysis {


32  [StorableType("A704FDF205664AB5B752D713831B016C")]


33  [Item(Name = "CovarianceLinearArd",


34  Description = "Linear covariance function with automatic relevance determination for Gaussian processes.")]


35  public sealed class CovarianceLinearArd : ParameterizedNamedItem, ICovarianceFunction {


36  public IValueParameter<DoubleArray> InverseLengthParameter {


37  get { return (IValueParameter<DoubleArray>)Parameters["InverseLength"]; }


38  }


39  private bool HasFixedInverseLengthParameter {


40  get { return InverseLengthParameter.Value != null; }


41  }


42 


43  [StorableConstructor]


44  private CovarianceLinearArd(StorableConstructorFlag _) : base(_) { }


45  private CovarianceLinearArd(CovarianceLinearArd original, Cloner cloner)


46  : base(original, cloner) {


47  }


48  public CovarianceLinearArd()


49  : base() {


50  Name = ItemName;


51  Description = ItemDescription;


52 


53  Parameters.Add(new OptionalValueParameter<DoubleArray>("InverseLength",


54  "The inverse length parameter for ARD."));


55  }


56 


57  public override IDeepCloneable Clone(Cloner cloner) {


58  return new CovarianceLinearArd(this, cloner);


59  }


60 


61  public int GetNumberOfParameters(int numberOfVariables) {


62  if (HasFixedInverseLengthParameter)


63  return 0;


64  else


65  return numberOfVariables;


66  }


67 


68  public void SetParameter(double[] p) {


69  double[] inverseLength;


70  GetParameterValues(p, out inverseLength);


71  InverseLengthParameter.Value = new DoubleArray(inverseLength);


72  }


73 


74  private void GetParameterValues(double[] p, out double[] inverseLength) {


75  // gather parameter values


76  if (HasFixedInverseLengthParameter) {


77  inverseLength = InverseLengthParameter.Value.ToArray();


78  } else {


79  inverseLength = p.Select(e => 1.0 / Math.Exp(e)).ToArray();


80  }


81  }


82 


83  public ParameterizedCovarianceFunction GetParameterizedCovarianceFunction(double[] p, int[] columnIndices) {


84  double[] inverseLength;


85  GetParameterValues(p, out inverseLength);


86  var fixedInverseLength = HasFixedInverseLengthParameter;


87  // create functions


88  var cov = new ParameterizedCovarianceFunction();


89  cov.Covariance = (x, i, j) => Util.ScalarProd(x, i, j, inverseLength, columnIndices);


90  cov.CrossCovariance = (x, xt, i, j) => Util.ScalarProd(x, i, xt, j, inverseLength, columnIndices);


91  if (fixedInverseLength)


92  cov.CovarianceGradient = (x, i, j) => new double[0];


93  else


94  cov.CovarianceGradient = (x, i, j) => GetGradient(x, i, j, inverseLength, columnIndices);


95  return cov;


96  }


97 


98  private static IList<double> GetGradient(double[,] x, int i, int j, double[] inverseLength, int[] columnIndices) {


99  int k = 0;


100  var g = new List<double>(columnIndices.Length);


101  for (int c = 0; c < columnIndices.Length; c++) {


102  var columnIndex = columnIndices[c];


103  g.Add(2.0 * x[i, columnIndex] * x[j, columnIndex] * inverseLength[k] * inverseLength[k]);


104  k++;


105  }


106  return g;


107  }


108  }


109  }

