[8375] | 1 | #region License Information
|
---|
| 2 | /* HeuristicLab
|
---|
[11594] | 3 | * Copyright (C) 2002-2014 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
|
---|
[8375] | 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 HeuristicLab.Common;
|
---|
| 23 | using HeuristicLab.Core;
|
---|
| 24 | using HeuristicLab.Data;
|
---|
| 25 | using HeuristicLab.Operators;
|
---|
| 26 | using HeuristicLab.Optimization;
|
---|
| 27 | using HeuristicLab.Parameters;
|
---|
| 28 | using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
|
---|
| 29 | using HeuristicLab.Problems.DataAnalysis;
|
---|
| 30 |
|
---|
| 31 | namespace HeuristicLab.Algorithms.DataAnalysis {
|
---|
| 32 | [StorableClass]
|
---|
| 33 | [Item(Name = "GaussianProcessRegressionSolutionCreator",
|
---|
| 34 | Description = "Creates a Gaussian process solution from a trained model.")]
|
---|
| 35 | public sealed class GaussianProcessRegressionSolutionCreator : SingleSuccessorOperator {
|
---|
| 36 | private const string ProblemDataParameterName = "ProblemData";
|
---|
| 37 | private const string ModelParameterName = "GaussianProcessRegressionModel";
|
---|
| 38 | private const string SolutionParameterName = "Solution";
|
---|
| 39 | private const string ResultsParameterName = "Results";
|
---|
| 40 | private const string TrainingRSquaredResultName = "Training R²";
|
---|
| 41 | private const string TestRSquaredResultName = "Test R²";
|
---|
| 42 |
|
---|
| 43 | #region Parameter Properties
|
---|
| 44 | public ILookupParameter<IRegressionProblemData> ProblemDataParameter {
|
---|
| 45 | get { return (ILookupParameter<IRegressionProblemData>)Parameters[ProblemDataParameterName]; }
|
---|
| 46 | }
|
---|
| 47 | public ILookupParameter<IGaussianProcessSolution> SolutionParameter {
|
---|
| 48 | get { return (ILookupParameter<IGaussianProcessSolution>)Parameters[SolutionParameterName]; }
|
---|
| 49 | }
|
---|
| 50 | public ILookupParameter<IGaussianProcessModel> ModelParameter {
|
---|
| 51 | get { return (ILookupParameter<IGaussianProcessModel>)Parameters[ModelParameterName]; }
|
---|
| 52 | }
|
---|
| 53 | public ILookupParameter<ResultCollection> ResultsParameter {
|
---|
| 54 | get { return (ILookupParameter<ResultCollection>)Parameters[ResultsParameterName]; }
|
---|
| 55 | }
|
---|
| 56 | #endregion
|
---|
| 57 |
|
---|
| 58 | [StorableConstructor]
|
---|
| 59 | private GaussianProcessRegressionSolutionCreator(bool deserializing) : base(deserializing) { }
|
---|
| 60 | private GaussianProcessRegressionSolutionCreator(GaussianProcessRegressionSolutionCreator original, Cloner cloner) : base(original, cloner) { }
|
---|
| 61 | public GaussianProcessRegressionSolutionCreator()
|
---|
| 62 | : base() {
|
---|
| 63 | // in
|
---|
| 64 | Parameters.Add(new LookupParameter<IRegressionProblemData>(ProblemDataParameterName, "The regression problem data for the Gaussian process solution."));
|
---|
| 65 | Parameters.Add(new LookupParameter<IGaussianProcessModel>(ModelParameterName, "The Gaussian process regression model to use for the solution."));
|
---|
| 66 | // in & out
|
---|
| 67 | Parameters.Add(new LookupParameter<ResultCollection>(ResultsParameterName, "The result collection of the algorithm."));
|
---|
| 68 | // out
|
---|
| 69 | Parameters.Add(new LookupParameter<IGaussianProcessSolution>(SolutionParameterName, "The produced Gaussian process solution."));
|
---|
| 70 | }
|
---|
| 71 |
|
---|
| 72 | public override IDeepCloneable Clone(Cloner cloner) {
|
---|
| 73 | return new GaussianProcessRegressionSolutionCreator(this, cloner);
|
---|
| 74 | }
|
---|
| 75 |
|
---|
| 76 | public override IOperation Apply() {
|
---|
[8494] | 77 | if (ModelParameter.ActualValue != null) {
|
---|
| 78 | var m = (IGaussianProcessModel)ModelParameter.ActualValue.Clone();
|
---|
[8982] | 79 | m.FixParameters();
|
---|
[8494] | 80 | var data = (IRegressionProblemData)ProblemDataParameter.ActualValue.Clone();
|
---|
| 81 | var s = new GaussianProcessRegressionSolution(m, data);
|
---|
[8375] | 82 |
|
---|
| 83 |
|
---|
[8494] | 84 | SolutionParameter.ActualValue = s;
|
---|
| 85 | var results = ResultsParameter.ActualValue;
|
---|
| 86 | if (!results.ContainsKey(SolutionParameterName)) {
|
---|
| 87 | results.Add(new Result(SolutionParameterName, "The Gaussian process regression solution", s));
|
---|
| 88 | results.Add(new Result(TrainingRSquaredResultName,
|
---|
| 89 | "The Pearson's R² of the Gaussian process solution on the training partition.",
|
---|
| 90 | new DoubleValue(s.TrainingRSquared)));
|
---|
| 91 | results.Add(new Result(TestRSquaredResultName,
|
---|
| 92 | "The Pearson's R² of the Gaussian process solution on the test partition.",
|
---|
| 93 | new DoubleValue(s.TestRSquared)));
|
---|
| 94 | } else {
|
---|
| 95 | results[SolutionParameterName].Value = s;
|
---|
| 96 | results[TrainingRSquaredResultName].Value = new DoubleValue(s.TrainingRSquared);
|
---|
| 97 | results[TestRSquaredResultName].Value = new DoubleValue(s.TestRSquared);
|
---|
| 98 | }
|
---|
[8375] | 99 | }
|
---|
| 100 | return base.Apply();
|
---|
| 101 | }
|
---|
| 102 | }
|
---|
| 103 | }
|
---|