1 | #region License Information
|
---|
2 | /* HeuristicLab
|
---|
3 | * Copyright (C) 2002-2016 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 HeuristicLab.Common;
|
---|
23 | using HeuristicLab.Core;
|
---|
24 | using HeuristicLab.Data;
|
---|
25 | using HeuristicLab.Encodings.RealVectorEncoding;
|
---|
26 | using HeuristicLab.Operators;
|
---|
27 | using HeuristicLab.Parameters;
|
---|
28 | using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
|
---|
29 |
|
---|
30 | namespace HeuristicLab.Algorithms.DataAnalysis {
|
---|
31 | [StorableClass]
|
---|
32 | // base class for GaussianProcessModelCreators (specific for classification and regression)
|
---|
33 | public abstract class GaussianProcessModelCreator : SingleSuccessorOperator {
|
---|
34 | private const string HyperparameterParameterName = "Hyperparameter";
|
---|
35 | private const string MeanFunctionParameterName = "MeanFunction";
|
---|
36 | private const string CovarianceFunctionParameterName = "CovarianceFunction";
|
---|
37 | private const string ModelParameterName = "Model";
|
---|
38 | private const string NegativeLogLikelihoodParameterName = "NegativeLogLikelihood";
|
---|
39 | private const string NegativeLogPredictiveProbabilityParameterName = "NegativeLogPredictiveProbability (LOOCV)";
|
---|
40 | private const string HyperparameterGradientsParameterName = "HyperparameterGradients";
|
---|
41 | protected const string ScaleInputValuesParameterName = "ScaleInputValues";
|
---|
42 |
|
---|
43 | #region Parameter Properties
|
---|
44 | // in
|
---|
45 | public ILookupParameter<RealVector> HyperparameterParameter {
|
---|
46 | get { return (ILookupParameter<RealVector>)Parameters[HyperparameterParameterName]; }
|
---|
47 | }
|
---|
48 | public ILookupParameter<IMeanFunction> MeanFunctionParameter {
|
---|
49 | get { return (ILookupParameter<IMeanFunction>)Parameters[MeanFunctionParameterName]; }
|
---|
50 | }
|
---|
51 | public ILookupParameter<ICovarianceFunction> CovarianceFunctionParameter {
|
---|
52 | get { return (ILookupParameter<ICovarianceFunction>)Parameters[CovarianceFunctionParameterName]; }
|
---|
53 | }
|
---|
54 | // out
|
---|
55 | public ILookupParameter<IGaussianProcessModel> ModelParameter {
|
---|
56 | get { return (ILookupParameter<IGaussianProcessModel>)Parameters[ModelParameterName]; }
|
---|
57 | }
|
---|
58 | public ILookupParameter<RealVector> HyperparameterGradientsParameter {
|
---|
59 | get { return (ILookupParameter<RealVector>)Parameters[HyperparameterGradientsParameterName]; }
|
---|
60 | }
|
---|
61 | public ILookupParameter<DoubleValue> NegativeLogLikelihoodParameter {
|
---|
62 | get { return (ILookupParameter<DoubleValue>)Parameters[NegativeLogLikelihoodParameterName]; }
|
---|
63 | }
|
---|
64 | public ILookupParameter<DoubleValue> NegativeLogPredictiveProbabilityParameter {
|
---|
65 | get { return (ILookupParameter<DoubleValue>)Parameters[NegativeLogPredictiveProbabilityParameterName]; }
|
---|
66 | }
|
---|
67 | public ILookupParameter<BoolValue> ScaleInputValuesParameter {
|
---|
68 | get { return (ILookupParameter<BoolValue>)Parameters[ScaleInputValuesParameterName]; }
|
---|
69 | }
|
---|
70 | #endregion
|
---|
71 |
|
---|
72 | #region Properties
|
---|
73 | protected RealVector Hyperparameter { get { return HyperparameterParameter.ActualValue; } }
|
---|
74 | protected IMeanFunction MeanFunction { get { return MeanFunctionParameter.ActualValue; } }
|
---|
75 | protected ICovarianceFunction CovarianceFunction { get { return CovarianceFunctionParameter.ActualValue; } }
|
---|
76 | public bool ScaleInputValues { get { return ScaleInputValuesParameter.ActualValue.Value; } }
|
---|
77 | #endregion
|
---|
78 |
|
---|
79 | [StorableConstructor]
|
---|
80 | protected GaussianProcessModelCreator(bool deserializing) : base(deserializing) { }
|
---|
81 | protected GaussianProcessModelCreator(GaussianProcessModelCreator original, Cloner cloner) : base(original, cloner) { }
|
---|
82 | protected GaussianProcessModelCreator()
|
---|
83 | : base() {
|
---|
84 | // in
|
---|
85 | Parameters.Add(new LookupParameter<RealVector>(HyperparameterParameterName, "The hyperparameters for the Gaussian process model."));
|
---|
86 | Parameters.Add(new LookupParameter<IMeanFunction>(MeanFunctionParameterName, "The mean function for the Gaussian process model."));
|
---|
87 | Parameters.Add(new LookupParameter<ICovarianceFunction>(CovarianceFunctionParameterName, "The covariance function for the Gaussian process model."));
|
---|
88 | // out
|
---|
89 | Parameters.Add(new LookupParameter<IGaussianProcessModel>(ModelParameterName, "The resulting Gaussian process model"));
|
---|
90 | Parameters.Add(new LookupParameter<RealVector>(HyperparameterGradientsParameterName, "The gradients of the hyperparameters for the produced Gaussian process model (necessary for hyperparameter optimization)"));
|
---|
91 | Parameters.Add(new LookupParameter<DoubleValue>(NegativeLogLikelihoodParameterName, "The negative log-likelihood of the produced Gaussian process model given the data."));
|
---|
92 | Parameters.Add(new LookupParameter<DoubleValue>(NegativeLogPredictiveProbabilityParameterName, "The leave-one-out-cross-validation negative log predictive probability of the produced Gaussian process model given the data."));
|
---|
93 |
|
---|
94 |
|
---|
95 | Parameters.Add(new LookupParameter<BoolValue>(ScaleInputValuesParameterName,
|
---|
96 | "Determines if the input variable values are scaled to the range [0..1] for training."));
|
---|
97 | Parameters[ScaleInputValuesParameterName].Hidden = true;
|
---|
98 | }
|
---|
99 |
|
---|
100 | [StorableHook(HookType.AfterDeserialization)]
|
---|
101 | private void AfterDeserialization() {
|
---|
102 | if (!Parameters.ContainsKey(ScaleInputValuesParameterName)) {
|
---|
103 | Parameters.Add(new LookupParameter<BoolValue>(ScaleInputValuesParameterName,
|
---|
104 | "Determines if the input variable values are scaled to the range [0..1] for training."));
|
---|
105 | Parameters[ScaleInputValuesParameterName].Hidden = true;
|
---|
106 | }
|
---|
107 | if (!Parameters.ContainsKey(NegativeLogPredictiveProbabilityParameterName)) {
|
---|
108 | Parameters.Add(new LookupParameter<DoubleValue>(NegativeLogPredictiveProbabilityParameterName,
|
---|
109 | "The leave-one-out-cross-validation negative log predictive probability of the produced Gaussian process model given the data."));
|
---|
110 | }
|
---|
111 | }
|
---|
112 | }
|
---|
113 | }
|
---|