1 | #region License Information
|
---|
2 | /* HeuristicLab
|
---|
3 | * Copyright (C) 2002-2017 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 System.Threading;
|
---|
26 | using HeuristicLab.Common;
|
---|
27 | using HeuristicLab.Data;
|
---|
28 | using HeuristicLab.Optimization;
|
---|
29 | using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
|
---|
30 | using HeuristicLab.Problems.DataAnalysis;
|
---|
31 |
|
---|
32 | namespace HeuristicLab.Algorithms.DataAnalysis {
|
---|
33 | [StorableClass]
|
---|
34 | public class M5TreeModel : RegressionModel, IM5MetaModel {
|
---|
35 | private const string NoCurrentLeafesResultName = "Number of current Leafs";
|
---|
36 | #region Properties
|
---|
37 | [Storable]
|
---|
38 | internal M5NodeModel Root { get; private set; }
|
---|
39 | //[Storable]
|
---|
40 | //private M5Parameters M5Params { get; set; }
|
---|
41 | #endregion
|
---|
42 |
|
---|
43 | #region HLConstructors & Cloning
|
---|
44 | [StorableConstructor]
|
---|
45 | protected M5TreeModel(bool deserializing) : base(deserializing) { }
|
---|
46 | protected M5TreeModel(M5TreeModel original, Cloner cloner) : base(original, cloner) {
|
---|
47 | Root = cloner.Clone(original.Root);
|
---|
48 | }
|
---|
49 | protected M5TreeModel(string targetVariable) : base(targetVariable) { }
|
---|
50 | public override IDeepCloneable Clone(Cloner cloner) {
|
---|
51 | return new M5TreeModel(this, cloner);
|
---|
52 | }
|
---|
53 | #endregion
|
---|
54 |
|
---|
55 | internal static M5TreeModel CreateTreeModel(string targetAttr, M5CreationParameters m5CreationParams) {
|
---|
56 | return m5CreationParams.LeafType is ILeafType<IConfidenceRegressionModel> ? new ConfidenceM5TreeModel(targetAttr) : new M5TreeModel(targetAttr);
|
---|
57 | }
|
---|
58 |
|
---|
59 | #region RegressionModel
|
---|
60 | public override IEnumerable<string> VariablesUsedForPrediction {
|
---|
61 | get { return Root.VariablesUsedForPrediction ?? new List<string>(); }
|
---|
62 | }
|
---|
63 | public override IEnumerable<double> GetEstimatedValues(IDataset dataset, IEnumerable<int> rows) {
|
---|
64 | if (Root == null) throw new NotSupportedException("The classifier has not been built yet");
|
---|
65 | return Root.GetEstimatedValues(dataset, rows);
|
---|
66 | }
|
---|
67 | public override IRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData) {
|
---|
68 | return new RegressionSolution(this, problemData);
|
---|
69 | }
|
---|
70 | #endregion
|
---|
71 |
|
---|
72 | #region IM5Component
|
---|
73 | void IM5MetaModel.BuildClassifier(IReadOnlyList<int> trainingRows, IReadOnlyList<int> holdoutRows, M5CreationParameters m5CreationParams, CancellationToken cancellation) {
|
---|
74 | Root = null;
|
---|
75 | var globalStdDev = m5CreationParams.Data.GetDoubleValues(m5CreationParams.TargetVariable, trainingRows).StandardDeviationPop();
|
---|
76 | Root = M5NodeModel.CreateNode(m5CreationParams.TargetVariable, m5CreationParams);
|
---|
77 | Root.Split(trainingRows, m5CreationParams, globalStdDev);
|
---|
78 | InitializeLeafCounter(m5CreationParams);
|
---|
79 | if (!(m5CreationParams.Pruningtype is NoPruning)) Root.Prune(trainingRows, holdoutRows, m5CreationParams, cancellation, globalStdDev);
|
---|
80 | Root.InstallModels(trainingRows.Union(holdoutRows).ToArray(), m5CreationParams.Random, m5CreationParams.Data, m5CreationParams.LeafType, cancellation);
|
---|
81 | }
|
---|
82 |
|
---|
83 | void IM5MetaModel.UpdateModel(IReadOnlyList<int> rows, M5UpdateParameters m5UpdateParameters, CancellationToken cancellation) {
|
---|
84 | Root.InstallModels(rows, m5UpdateParameters.Random, m5UpdateParameters.Data, m5UpdateParameters.LeafType, cancellation);
|
---|
85 | }
|
---|
86 | #endregion
|
---|
87 |
|
---|
88 | #region Helpers
|
---|
89 | private void InitializeLeafCounter(M5CreationParameters m5CreationParams) {
|
---|
90 | if (!m5CreationParams.Results.ContainsKey(NoCurrentLeafesResultName))
|
---|
91 | m5CreationParams.Results.Add(new Result(NoCurrentLeafesResultName, new IntValue(Root.EnumerateNodes().Count(x => x.IsLeaf))));
|
---|
92 | else ((IntValue) m5CreationParams.Results[NoCurrentLeafesResultName].Value).Value = Root.EnumerateNodes().Count(x => x.IsLeaf);
|
---|
93 | }
|
---|
94 | #endregion
|
---|
95 |
|
---|
96 | [StorableClass]
|
---|
97 | private class ConfidenceM5TreeModel : M5TreeModel, IConfidenceRegressionModel {
|
---|
98 | #region HLConstructors & Cloning
|
---|
99 | [StorableConstructor]
|
---|
100 | protected ConfidenceM5TreeModel(bool deserializing) : base(deserializing) { }
|
---|
101 | private ConfidenceM5TreeModel(ConfidenceM5TreeModel original, Cloner cloner) : base(original, cloner) { }
|
---|
102 | public ConfidenceM5TreeModel(string targetVariable) : base(targetVariable) { }
|
---|
103 | public override IDeepCloneable Clone(Cloner cloner) {
|
---|
104 | return new ConfidenceM5TreeModel(this, cloner);
|
---|
105 | }
|
---|
106 | #endregion
|
---|
107 |
|
---|
108 | public IEnumerable<double> GetEstimatedVariances(IDataset dataset, IEnumerable<int> rows) {
|
---|
109 | if (Root == null) throw new NotSupportedException("The classifier has not been built yet");
|
---|
110 | return ((IConfidenceRegressionModel) Root).GetEstimatedVariances(dataset, rows);
|
---|
111 | }
|
---|
112 | public override IRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData) {
|
---|
113 | return new ConfidenceRegressionSolution(this, problemData);
|
---|
114 | }
|
---|
115 | }
|
---|
116 | }
|
---|
117 | } |
---|