[5626] | 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 |
|
---|
| 22 | using System;
|
---|
[5759] | 23 | using System.Collections.Generic;
|
---|
[5626] | 24 | using System.Linq;
|
---|
| 25 | using HeuristicLab.Common;
|
---|
| 26 | using HeuristicLab.Core;
|
---|
| 27 | using HeuristicLab.Data;
|
---|
| 28 | using HeuristicLab.Optimization;
|
---|
| 29 | using HeuristicLab.Parameters;
|
---|
| 30 | using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
|
---|
| 31 | using HeuristicLab.Problems.DataAnalysis;
|
---|
| 32 |
|
---|
| 33 | namespace HeuristicLab.Algorithms.DataAnalysis {
|
---|
| 34 | /// <summary>
|
---|
| 35 | /// Support vector machine classification data analysis algorithm.
|
---|
| 36 | /// </summary>
|
---|
[6240] | 37 | [Item("Support Vector Classification", "Support vector machine classification data analysis algorithm (wrapper for libSVM).")]
|
---|
[5626] | 38 | [Creatable("Data Analysis")]
|
---|
| 39 | [StorableClass]
|
---|
| 40 | public sealed class SupportVectorClassification : FixedDataAnalysisAlgorithm<IClassificationProblem> {
|
---|
| 41 | private const string SvmTypeParameterName = "SvmType";
|
---|
| 42 | private const string KernelTypeParameterName = "KernelType";
|
---|
| 43 | private const string CostParameterName = "Cost";
|
---|
| 44 | private const string NuParameterName = "Nu";
|
---|
| 45 | private const string GammaParameterName = "Gamma";
|
---|
| 46 |
|
---|
| 47 | #region parameter properties
|
---|
| 48 | public IValueParameter<StringValue> SvmTypeParameter {
|
---|
| 49 | get { return (IValueParameter<StringValue>)Parameters[SvmTypeParameterName]; }
|
---|
| 50 | }
|
---|
| 51 | public IValueParameter<StringValue> KernelTypeParameter {
|
---|
| 52 | get { return (IValueParameter<StringValue>)Parameters[KernelTypeParameterName]; }
|
---|
| 53 | }
|
---|
| 54 | public IValueParameter<DoubleValue> NuParameter {
|
---|
| 55 | get { return (IValueParameter<DoubleValue>)Parameters[NuParameterName]; }
|
---|
| 56 | }
|
---|
| 57 | public IValueParameter<DoubleValue> CostParameter {
|
---|
| 58 | get { return (IValueParameter<DoubleValue>)Parameters[CostParameterName]; }
|
---|
| 59 | }
|
---|
| 60 | public IValueParameter<DoubleValue> GammaParameter {
|
---|
| 61 | get { return (IValueParameter<DoubleValue>)Parameters[GammaParameterName]; }
|
---|
| 62 | }
|
---|
| 63 | #endregion
|
---|
| 64 | #region properties
|
---|
| 65 | public StringValue SvmType {
|
---|
| 66 | get { return SvmTypeParameter.Value; }
|
---|
| 67 | }
|
---|
| 68 | public StringValue KernelType {
|
---|
| 69 | get { return KernelTypeParameter.Value; }
|
---|
| 70 | }
|
---|
| 71 | public DoubleValue Nu {
|
---|
| 72 | get { return NuParameter.Value; }
|
---|
| 73 | }
|
---|
| 74 | public DoubleValue Cost {
|
---|
| 75 | get { return CostParameter.Value; }
|
---|
| 76 | }
|
---|
| 77 | public DoubleValue Gamma {
|
---|
| 78 | get { return GammaParameter.Value; }
|
---|
| 79 | }
|
---|
| 80 | #endregion
|
---|
| 81 | [StorableConstructor]
|
---|
| 82 | private SupportVectorClassification(bool deserializing) : base(deserializing) { }
|
---|
| 83 | private SupportVectorClassification(SupportVectorClassification original, Cloner cloner)
|
---|
| 84 | : base(original, cloner) {
|
---|
| 85 | }
|
---|
| 86 | public SupportVectorClassification()
|
---|
| 87 | : base() {
|
---|
[5649] | 88 | Problem = new ClassificationProblem();
|
---|
| 89 |
|
---|
[5626] | 90 | List<StringValue> svrTypes = (from type in new List<string> { "NU_SVC", "EPSILON_SVC" }
|
---|
| 91 | select new StringValue(type).AsReadOnly())
|
---|
| 92 | .ToList();
|
---|
| 93 | ItemSet<StringValue> svrTypeSet = new ItemSet<StringValue>(svrTypes);
|
---|
| 94 | List<StringValue> kernelTypes = (from type in new List<string> { "LINEAR", "POLY", "SIGMOID", "RBF" }
|
---|
| 95 | select new StringValue(type).AsReadOnly())
|
---|
| 96 | .ToList();
|
---|
[5649] | 97 | ItemSet<StringValue> kernelTypeSet = new ItemSet<StringValue>(kernelTypes);
|
---|
[5626] | 98 | Parameters.Add(new ConstrainedValueParameter<StringValue>(SvmTypeParameterName, "The type of SVM to use.", svrTypeSet, svrTypes[0]));
|
---|
| 99 | Parameters.Add(new ConstrainedValueParameter<StringValue>(KernelTypeParameterName, "The kernel type to use for the SVM.", kernelTypeSet, kernelTypes[3]));
|
---|
| 100 | Parameters.Add(new ValueParameter<DoubleValue>(NuParameterName, "The value of the nu parameter nu-SVC.", new DoubleValue(0.5)));
|
---|
| 101 | Parameters.Add(new ValueParameter<DoubleValue>(CostParameterName, "The value of the C (cost) parameter of C-SVC.", new DoubleValue(1.0)));
|
---|
| 102 | Parameters.Add(new ValueParameter<DoubleValue>(GammaParameterName, "The value of the gamma parameter in the kernel function.", new DoubleValue(1.0)));
|
---|
| 103 | }
|
---|
| 104 | [StorableHook(HookType.AfterDeserialization)]
|
---|
| 105 | private void AfterDeserialization() { }
|
---|
| 106 |
|
---|
| 107 | public override IDeepCloneable Clone(Cloner cloner) {
|
---|
| 108 | return new SupportVectorClassification(this, cloner);
|
---|
| 109 | }
|
---|
| 110 |
|
---|
| 111 | #region support vector classification
|
---|
| 112 | protected override void Run() {
|
---|
| 113 | IClassificationProblemData problemData = Problem.ProblemData;
|
---|
[5649] | 114 | IEnumerable<string> selectedInputVariables = problemData.AllowedInputVariables;
|
---|
[5626] | 115 | var solution = CreateSupportVectorClassificationSolution(problemData, selectedInputVariables, SvmType.Value, KernelType.Value, Cost.Value, Nu.Value, Gamma.Value);
|
---|
| 116 |
|
---|
| 117 | Results.Add(new Result("Support vector classification solution", "The support vector classification solution.", solution));
|
---|
| 118 | }
|
---|
| 119 |
|
---|
| 120 | public static SupportVectorClassificationSolution CreateSupportVectorClassificationSolution(IClassificationProblemData problemData, IEnumerable<string> allowedInputVariables,
|
---|
| 121 | string svmType, string kernelType, double cost, double nu, double gamma) {
|
---|
| 122 | Dataset dataset = problemData.Dataset;
|
---|
| 123 | string targetVariable = problemData.TargetVariable;
|
---|
[6182] | 124 | IEnumerable<int> rows = problemData.TrainingIndizes;
|
---|
[5626] | 125 |
|
---|
| 126 | //extract SVM parameters from scope and set them
|
---|
| 127 | SVM.Parameter parameter = new SVM.Parameter();
|
---|
| 128 | parameter.SvmType = (SVM.SvmType)Enum.Parse(typeof(SVM.SvmType), svmType, true);
|
---|
| 129 | parameter.KernelType = (SVM.KernelType)Enum.Parse(typeof(SVM.KernelType), kernelType, true);
|
---|
| 130 | parameter.C = cost;
|
---|
| 131 | parameter.Nu = nu;
|
---|
| 132 | parameter.Gamma = gamma;
|
---|
| 133 | parameter.CacheSize = 500;
|
---|
| 134 | parameter.Probability = false;
|
---|
| 135 |
|
---|
| 136 |
|
---|
| 137 | SVM.Problem problem = SupportVectorMachineUtil.CreateSvmProblem(dataset, targetVariable, allowedInputVariables, rows);
|
---|
| 138 | SVM.RangeTransform rangeTransform = SVM.RangeTransform.Compute(problem);
|
---|
| 139 | SVM.Problem scaledProblem = SVM.Scaling.Scale(rangeTransform, problem);
|
---|
[5690] | 140 | var model = new SupportVectorMachineModel(SVM.Training.Train(scaledProblem, parameter), rangeTransform, targetVariable, allowedInputVariables, problemData.ClassValues);
|
---|
[5626] | 141 |
|
---|
[5914] | 142 | return new SupportVectorClassificationSolution(model, (IClassificationProblemData)problemData.Clone());
|
---|
[5626] | 143 | }
|
---|
| 144 | #endregion
|
---|
| 145 | }
|
---|
| 146 | }
|
---|