1 | #region License Information
|
---|
2 | /* HeuristicLab
|
---|
3 | * Copyright (C) 2002-2011 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 | using System.Linq;
|
---|
22 | using HeuristicLab.Common;
|
---|
23 | using HeuristicLab.Core;
|
---|
24 | using HeuristicLab.Parameters;
|
---|
25 | using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
|
---|
26 |
|
---|
27 | namespace HeuristicLab.Problems.DataAnalysis.Symbolic.Classification {
|
---|
28 | [Item("Symbolic Classification Problem (single objective)", "Represents a single objective symbolic classfication problem.")]
|
---|
29 | [StorableClass]
|
---|
30 | [Creatable("Problems")]
|
---|
31 | public class SymbolicClassificationSingleObjectiveProblem : SymbolicDataAnalysisSingleObjectiveProblem<IClassificationProblemData, ISymbolicClassificationSingleObjectiveEvaluator, ISymbolicDataAnalysisSolutionCreator>, IClassificationProblem {
|
---|
32 | private const double PunishmentFactor = 10;
|
---|
33 | private const int InitialMaximumTreeDepth = 8;
|
---|
34 | private const int InitialMaximumTreeLength = 25;
|
---|
35 | private const string EstimationLimitsParameterName = "EstimationLimits";
|
---|
36 | private const string EstimationLimitsParameterDescription = "The lower and upper limit for the estimated value that can be returned by the symbolic classification model.";
|
---|
37 |
|
---|
38 | #region parameter properties
|
---|
39 | public IFixedValueParameter<DoubleLimit> EstimationLimitsParameter {
|
---|
40 | get { return (IFixedValueParameter<DoubleLimit>)Parameters[EstimationLimitsParameterName]; }
|
---|
41 | }
|
---|
42 | #endregion
|
---|
43 | #region properties
|
---|
44 | public DoubleLimit EstimationLimits {
|
---|
45 | get { return EstimationLimitsParameter.Value; }
|
---|
46 | }
|
---|
47 | #endregion
|
---|
48 | [StorableConstructor]
|
---|
49 | protected SymbolicClassificationSingleObjectiveProblem(bool deserializing) : base(deserializing) { }
|
---|
50 | protected SymbolicClassificationSingleObjectiveProblem(SymbolicClassificationSingleObjectiveProblem original, Cloner cloner) : base(original, cloner) { }
|
---|
51 | public override IDeepCloneable Clone(Cloner cloner) { return new SymbolicClassificationSingleObjectiveProblem(this, cloner); }
|
---|
52 |
|
---|
53 | public SymbolicClassificationSingleObjectiveProblem()
|
---|
54 | : base(new ClassificationProblemData(), new SymbolicClassificationSingleObjectiveMeanSquaredErrorEvaluator(), new SymbolicDataAnalysisExpressionTreeCreator()) {
|
---|
55 | Parameters.Add(new FixedValueParameter<DoubleLimit>(EstimationLimitsParameterName, EstimationLimitsParameterDescription, new DoubleLimit()));
|
---|
56 |
|
---|
57 | MaximumSymbolicExpressionTreeDepth.Value = InitialMaximumTreeDepth;
|
---|
58 | MaximumSymbolicExpressionTreeLength.Value = InitialMaximumTreeLength;
|
---|
59 |
|
---|
60 | InitializeOperators();
|
---|
61 | UpdateEstimationLimits();
|
---|
62 | }
|
---|
63 |
|
---|
64 | private void InitializeOperators() {
|
---|
65 | Operators.Add(new SymbolicClassificationSingleObjectiveTrainingBestSolutionAnalyzer());
|
---|
66 | Operators.Add(new SymbolicClassificationSingleObjectiveValidationBestSolutionAnalyzer());
|
---|
67 | Operators.Add(new SymbolicClassificationSingleObjectiveOverfittingAnalyzer());
|
---|
68 | ParameterizeOperators();
|
---|
69 | }
|
---|
70 |
|
---|
71 | private void UpdateEstimationLimits() {
|
---|
72 | if (ProblemData.TrainingPartition.Start < ProblemData.TrainingPartition.End) {
|
---|
73 | var targetValues = ProblemData.Dataset.GetVariableValues(ProblemData.TargetVariable, ProblemData.TrainingPartition.Start, ProblemData.TrainingPartition.End);
|
---|
74 | var mean = targetValues.Average();
|
---|
75 | var range = targetValues.Max() - targetValues.Min();
|
---|
76 | EstimationLimits.Upper = mean + PunishmentFactor * range;
|
---|
77 | EstimationLimits.Lower = mean - PunishmentFactor * range;
|
---|
78 | }
|
---|
79 | }
|
---|
80 |
|
---|
81 | protected override void OnProblemDataChanged() {
|
---|
82 | base.OnProblemDataChanged();
|
---|
83 | UpdateEstimationLimits();
|
---|
84 | }
|
---|
85 |
|
---|
86 | protected override void ParameterizeOperators() {
|
---|
87 | base.ParameterizeOperators();
|
---|
88 | if (Parameters.ContainsKey(EstimationLimitsParameterName)) {
|
---|
89 | var operators = Parameters.OfType<IValueParameter>().Select(p => p.Value).OfType<IOperator>().Union(Operators);
|
---|
90 | foreach (var op in operators.OfType<ISymbolicDataAnalysisBoundedOperator>()) {
|
---|
91 | op.EstimationLimitsParameter.ActualName = EstimationLimitsParameter.Name;
|
---|
92 | }
|
---|
93 | }
|
---|
94 | }
|
---|
95 |
|
---|
96 | public override void ImportProblemDataFromFile(string fileName) {
|
---|
97 | ClassificationProblemData problemData = ClassificationProblemData.ImportFromFile(fileName);
|
---|
98 | ProblemData = problemData;
|
---|
99 | }
|
---|
100 | }
|
---|
101 | }
|
---|