[1806] | 1 | #region License Information
|
---|
| 2 | /* HeuristicLab
|
---|
| 3 | * Copyright (C) 2002-2009 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.Text;
|
---|
| 26 | using HeuristicLab.Core;
|
---|
| 27 | using HeuristicLab.Data;
|
---|
| 28 | using HeuristicLab.DataAnalysis;
|
---|
[1848] | 29 | using System.Threading;
|
---|
[1806] | 30 |
|
---|
| 31 | namespace HeuristicLab.SupportVectorMachines {
|
---|
| 32 | public class SupportVectorCreator : OperatorBase {
|
---|
[1848] | 33 | private Thread trainingThread;
|
---|
| 34 | private object locker = new object();
|
---|
| 35 | private bool abortRequested = false;
|
---|
[1806] | 36 |
|
---|
| 37 | public SupportVectorCreator()
|
---|
| 38 | : base() {
|
---|
| 39 | //Dataset infos
|
---|
| 40 | AddVariableInfo(new VariableInfo("Dataset", "Dataset with all samples on which to apply the function", typeof(Dataset), VariableKind.In));
|
---|
| 41 | AddVariableInfo(new VariableInfo("TargetVariable", "Index of the column of the dataset that holds the target variable", typeof(IntData), VariableKind.In));
|
---|
| 42 | AddVariableInfo(new VariableInfo("SamplesStart", "Start index of samples in dataset to evaluate", typeof(IntData), VariableKind.In));
|
---|
| 43 | AddVariableInfo(new VariableInfo("SamplesEnd", "End index of samples in dataset to evaluate", typeof(IntData), VariableKind.In));
|
---|
| 44 |
|
---|
| 45 | //SVM parameters
|
---|
| 46 | AddVariableInfo(new VariableInfo("SVMType", "String describing which SVM type is used. Valid inputs are: C_SVC, NU_SVC, ONE_CLASS, EPSILON_SVR, NU_SVR",
|
---|
| 47 | typeof(StringData), VariableKind.In));
|
---|
| 48 | AddVariableInfo(new VariableInfo("SVMKernelType", "String describing which SVM kernel is used. Valid inputs are: LINEAR, POLY, RBF, SIGMOID, PRECOMPUTED",
|
---|
| 49 | typeof(StringData), VariableKind.In));
|
---|
| 50 | AddVariableInfo(new VariableInfo("SVMCost", "Cost parameter (C) of C-SVC, epsilon-SVR and nu-SVR", typeof(DoubleData), VariableKind.In));
|
---|
| 51 | AddVariableInfo(new VariableInfo("SVMNu", "Nu parameter of nu-SVC, one-class SVM and nu-SVR", typeof(DoubleData), VariableKind.In));
|
---|
| 52 | AddVariableInfo(new VariableInfo("SVMGamma", "Gamma parameter in kernel function", typeof(DoubleData), VariableKind.In));
|
---|
[1837] | 53 | AddVariableInfo(new VariableInfo("SVMModel", "Represent the model learned by the SVM", typeof(SVMModel), VariableKind.New | VariableKind.Out));
|
---|
[1848] | 54 | }
|
---|
[1806] | 55 |
|
---|
[1848] | 56 | public override void Abort() {
|
---|
| 57 | abortRequested = true;
|
---|
| 58 | lock (locker) {
|
---|
| 59 | if (trainingThread != null && trainingThread.ThreadState == ThreadState.Running) {
|
---|
| 60 | trainingThread.Abort();
|
---|
| 61 | }
|
---|
| 62 | }
|
---|
[1806] | 63 | }
|
---|
| 64 |
|
---|
| 65 | public override IOperation Apply(IScope scope) {
|
---|
[1848] | 66 | abortRequested = false;
|
---|
[1806] | 67 | Dataset dataset = GetVariableValue<Dataset>("Dataset", scope, true);
|
---|
| 68 | int targetVariable = GetVariableValue<IntData>("TargetVariable", scope, true).Data;
|
---|
| 69 | int start = GetVariableValue<IntData>("SamplesStart", scope, true).Data;
|
---|
| 70 | int end = GetVariableValue<IntData>("SamplesEnd", scope, true).Data;
|
---|
| 71 |
|
---|
| 72 | string svmType = GetVariableValue<StringData>("SVMType", scope, true).Data;
|
---|
| 73 | string svmKernelType = GetVariableValue<StringData>("SVMKernelType", scope, true).Data;
|
---|
| 74 |
|
---|
| 75 | //extract SVM parameters from scope and set them
|
---|
| 76 | SVM.Parameter parameter = new SVM.Parameter();
|
---|
| 77 | parameter.SvmType = (SVM.SvmType)Enum.Parse(typeof(SVM.SvmType), svmType, true);
|
---|
| 78 | parameter.KernelType = (SVM.KernelType)Enum.Parse(typeof(SVM.KernelType), svmKernelType, true);
|
---|
| 79 | parameter.C = GetVariableValue<DoubleData>("SVMCost", scope, true).Data;
|
---|
| 80 | parameter.Nu = GetVariableValue<DoubleData>("SVMNu", scope, true).Data;
|
---|
| 81 | parameter.Gamma = GetVariableValue<DoubleData>("SVMGamma", scope, true).Data;
|
---|
| 82 |
|
---|
[2165] | 83 | SVM.Problem problem = SVMHelper.CreateSVMProblem(dataset, targetVariable, start, end);
|
---|
[1806] | 84 | SVM.RangeTransform rangeTransform = SVM.Scaling.DetermineRange(problem);
|
---|
| 85 | SVM.Problem scaledProblem = SVM.Scaling.Scale(problem, rangeTransform);
|
---|
| 86 |
|
---|
[1848] | 87 | SVM.Model model = StartTraining(scaledProblem, parameter);
|
---|
| 88 | if (!abortRequested) {
|
---|
| 89 | //persist variables in scope
|
---|
| 90 | SVMModel modelData = new SVMModel();
|
---|
[1906] | 91 | modelData.Model = model;
|
---|
| 92 | modelData.RangeTransform = rangeTransform;
|
---|
[1848] | 93 | scope.AddVariable(new Variable(scope.TranslateName("SVMModel"), modelData));
|
---|
[1851] | 94 | return null;
|
---|
| 95 | } else {
|
---|
| 96 | return new AtomicOperation(this, scope);
|
---|
[1848] | 97 | }
|
---|
[1806] | 98 | }
|
---|
| 99 |
|
---|
[1848] | 100 | private SVM.Model StartTraining(SVM.Problem scaledProblem, SVM.Parameter parameter) {
|
---|
| 101 | SVM.Model model = null;
|
---|
| 102 | lock (locker) {
|
---|
| 103 | if (!abortRequested) {
|
---|
| 104 | trainingThread = new Thread(() => {
|
---|
[2163] | 105 | model = SVM.Training.Train(scaledProblem, parameter);
|
---|
[1848] | 106 | });
|
---|
| 107 | trainingThread.Start();
|
---|
| 108 | }
|
---|
| 109 | }
|
---|
[2163] | 110 | if (!abortRequested) {
|
---|
| 111 | trainingThread.Join();
|
---|
| 112 | trainingThread = null;
|
---|
| 113 | }
|
---|
[1848] | 114 | return model;
|
---|
| 115 | }
|
---|
[1806] | 116 | }
|
---|
| 117 | }
|
---|