Free cookie consent management tool by TermsFeed Policy Generator

source: branches/1888_OaaS/HeuristicLab.Algorithms.DataAnalysis/3.4/GaussianProcess/MeanFunctions/MeanSum.cs @ 17915

Last change on this file since 17915 was 8982, checked in by gkronber, 12 years ago

#1902: removed class HyperParameter and changed implementations of covariance and mean functions to remove the parameter value caching and event handlers for parameter caching. Instead it is now possible to create the actual covariance and mean functions as Func from templates and specified parameter values. The instances of mean and covariance functions configured in the GUI are actually templates where the structure and fixed parameters can be specified.

File size: 3.8 KB
Line 
1#region License Information
2/* HeuristicLab
3 * Copyright (C) 2002-2012 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
22using System.Collections.Generic;
23using System.Linq;
24using HeuristicLab.Common;
25using HeuristicLab.Core;
26using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
27
28namespace HeuristicLab.Algorithms.DataAnalysis {
29  [StorableClass]
30  [Item(Name = "MeanSum", Description = "Sum of mean functions for Gaussian processes.")]
31  public sealed class MeanSum : Item, IMeanFunction {
32    [Storable]
33    private ItemList<IMeanFunction> terms;
34
35    [Storable]
36    private int numberOfVariables;
37    public ItemList<IMeanFunction> Terms {
38      get { return terms; }
39    }
40
41    [StorableConstructor]
42    private MeanSum(bool deserializing) : base(deserializing) { }
43    private MeanSum(MeanSum original, Cloner cloner)
44      : base(original, cloner) {
45      this.terms = cloner.Clone(original.terms);
46      this.numberOfVariables = original.numberOfVariables;
47    }
48    public MeanSum() {
49      this.terms = new ItemList<IMeanFunction>();
50    }
51
52    public override IDeepCloneable Clone(Cloner cloner) {
53      return new MeanSum(this, cloner);
54    }
55
56    public int GetNumberOfParameters(int numberOfVariables) {
57      this.numberOfVariables = numberOfVariables;
58      return terms.Select(t => t.GetNumberOfParameters(numberOfVariables)).Sum();
59    }
60
61    public void SetParameter(double[] p) {
62      int offset = 0;
63      foreach (var t in terms) {
64        var numberOfParameters = t.GetNumberOfParameters(numberOfVariables);
65        t.SetParameter(p.Skip(offset).Take(numberOfParameters).ToArray());
66        offset += numberOfParameters;
67      }
68    }
69
70    public ParameterizedMeanFunction GetParameterizedMeanFunction(double[] p, IEnumerable<int> columnIndices) {
71      var termMf = new List<ParameterizedMeanFunction>();
72      int totalNumberOfParameters = GetNumberOfParameters(numberOfVariables);
73      int[] termIndexMap = new int[totalNumberOfParameters]; // maps k-th parameter to the correct mean-term
74      int[] hyperParameterIndexMap = new int[totalNumberOfParameters]; // maps k-th parameter to the l-th parameter of the correct mean-term
75      int c = 0;
76      // get the parameterized mean function for each term
77      for (int termIndex = 0; termIndex < terms.Count; termIndex++) {
78        var numberOfParameters = terms[termIndex].GetNumberOfParameters(numberOfVariables);
79        termMf.Add(terms[termIndex].GetParameterizedMeanFunction(p.Take(numberOfParameters).ToArray(), columnIndices));
80        p = p.Skip(numberOfParameters).ToArray();
81
82        for (int hyperParameterIndex = 0; hyperParameterIndex < numberOfParameters; hyperParameterIndex++) {
83          termIndexMap[c] = termIndex;
84          hyperParameterIndexMap[c] = hyperParameterIndex;
85          c++;
86        }
87      }
88
89      var mf = new ParameterizedMeanFunction();
90      mf.Mean = (x, i) => termMf.Select(t => t.Mean(x, i)).Sum();
91      mf.Gradient = (x, i, k) => {
92        return termMf[termIndexMap[k]].Gradient(x, i, hyperParameterIndexMap[k]);
93      };
94      return mf;
95    }
96  }
97}
Note: See TracBrowser for help on using the repository browser.