[6567] | 1 | #region License Information
|
---|
| 2 | /* HeuristicLab
|
---|
[15583] | 3 | * Copyright (C) 2002-2018 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
|
---|
[6567] | 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;
|
---|
[14523] | 25 | using System.Threading;
|
---|
[6567] | 26 | using HeuristicLab.Common;
|
---|
| 27 | using HeuristicLab.Core;
|
---|
| 28 | using HeuristicLab.Data;
|
---|
| 29 | using HeuristicLab.Optimization;
|
---|
| 30 | using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
|
---|
| 31 | using HeuristicLab.Problems.DataAnalysis;
|
---|
| 32 |
|
---|
| 33 | namespace HeuristicLab.Algorithms.DataAnalysis {
|
---|
| 34 | /// <summary>
|
---|
| 35 | /// Multinomial logit regression data analysis algorithm.
|
---|
| 36 | /// </summary>
|
---|
[13238] | 37 | [Item("Multinomial Logit Classification (MNL)", "Multinomial logit classification data analysis algorithm (wrapper for ALGLIB).")]
|
---|
[12622] | 38 | [Creatable(CreatableAttribute.Categories.DataAnalysisClassification, Priority = 180)]
|
---|
[6567] | 39 | [StorableClass]
|
---|
| 40 | public sealed class MultiNomialLogitClassification : FixedDataAnalysisAlgorithm<IClassificationProblem> {
|
---|
| 41 | private const string LogitClassificationModelResultName = "Logit classification solution";
|
---|
| 42 |
|
---|
| 43 | [StorableConstructor]
|
---|
| 44 | private MultiNomialLogitClassification(bool deserializing) : base(deserializing) { }
|
---|
| 45 | private MultiNomialLogitClassification(MultiNomialLogitClassification original, Cloner cloner)
|
---|
| 46 | : base(original, cloner) {
|
---|
| 47 | }
|
---|
| 48 | public MultiNomialLogitClassification()
|
---|
| 49 | : base() {
|
---|
| 50 | Problem = new ClassificationProblem();
|
---|
| 51 | }
|
---|
| 52 | [StorableHook(HookType.AfterDeserialization)]
|
---|
| 53 | private void AfterDeserialization() { }
|
---|
| 54 |
|
---|
| 55 | public override IDeepCloneable Clone(Cloner cloner) {
|
---|
| 56 | return new MultiNomialLogitClassification(this, cloner);
|
---|
| 57 | }
|
---|
| 58 |
|
---|
[6633] | 59 | #region logit classification
|
---|
[14523] | 60 | protected override void Run(CancellationToken cancellationToken) {
|
---|
[6567] | 61 | double rmsError, relClassError;
|
---|
| 62 | var solution = CreateLogitClassificationSolution(Problem.ProblemData, out rmsError, out relClassError);
|
---|
[6633] | 63 | Results.Add(new Result(LogitClassificationModelResultName, "The logit classification solution.", solution));
|
---|
| 64 | Results.Add(new Result("Root mean squared error", "The root of the mean of squared errors of the logit regression solution on the training set.", new DoubleValue(rmsError)));
|
---|
[6567] | 65 | Results.Add(new Result("Relative classification error", "Relative classification error on the training set (percentage of misclassified cases).", new PercentValue(relClassError)));
|
---|
| 66 | }
|
---|
| 67 |
|
---|
| 68 | public static IClassificationSolution CreateLogitClassificationSolution(IClassificationProblemData problemData, out double rmsError, out double relClassError) {
|
---|
[12509] | 69 | var dataset = problemData.Dataset;
|
---|
[6567] | 70 | string targetVariable = problemData.TargetVariable;
|
---|
[14826] | 71 | var doubleVariableNames = problemData.AllowedInputVariables.Where(dataset.VariableHasType<double>);
|
---|
| 72 | var factorVariableNames = problemData.AllowedInputVariables.Where(dataset.VariableHasType<string>);
|
---|
[8139] | 73 | IEnumerable<int> rows = problemData.TrainingIndices;
|
---|
[14843] | 74 | double[,] inputMatrix = dataset.ToArray(doubleVariableNames.Concat(new string[] { targetVariable }), rows);
|
---|
[14826] | 75 |
|
---|
[14843] | 76 | var factorVariableValues = dataset.GetFactorVariableValues(factorVariableNames, rows);
|
---|
| 77 | var factorMatrix = dataset.ToArray(factorVariableValues, rows);
|
---|
[14826] | 78 | inputMatrix = factorMatrix.HorzCat(inputMatrix);
|
---|
| 79 |
|
---|
[15786] | 80 | if (inputMatrix.ContainsNanOrInfinity())
|
---|
[6567] | 81 | throw new NotSupportedException("Multinomial logit classification does not support NaN or infinity values in the input dataset.");
|
---|
| 82 |
|
---|
[12817] | 83 | alglib.logitmodel lm = new alglib.logitmodel();
|
---|
| 84 | alglib.mnlreport rep = new alglib.mnlreport();
|
---|
[6567] | 85 | int nRows = inputMatrix.GetLength(0);
|
---|
| 86 | int nFeatures = inputMatrix.GetLength(1) - 1;
|
---|
[6740] | 87 | double[] classValues = dataset.GetDoubleValues(targetVariable).Distinct().OrderBy(x => x).ToArray();
|
---|
[6567] | 88 | int nClasses = classValues.Count();
|
---|
| 89 | // map original class values to values [0..nClasses-1]
|
---|
[8139] | 90 | Dictionary<double, double> classIndices = new Dictionary<double, double>();
|
---|
[6567] | 91 | for (int i = 0; i < nClasses; i++) {
|
---|
[8139] | 92 | classIndices[classValues[i]] = i;
|
---|
[6567] | 93 | }
|
---|
| 94 | for (int row = 0; row < nRows; row++) {
|
---|
[8139] | 95 | inputMatrix[row, nFeatures] = classIndices[inputMatrix[row, nFeatures]];
|
---|
[6567] | 96 | }
|
---|
| 97 | int info;
|
---|
| 98 | alglib.mnltrainh(inputMatrix, nRows, nFeatures, nClasses, out info, out lm, out rep);
|
---|
| 99 | if (info != 1) throw new ArgumentException("Error in calculation of logit classification solution");
|
---|
| 100 |
|
---|
| 101 | rmsError = alglib.mnlrmserror(lm, inputMatrix, nRows);
|
---|
| 102 | relClassError = alglib.mnlrelclserror(lm, inputMatrix, nRows);
|
---|
| 103 |
|
---|
[14826] | 104 | MultinomialLogitClassificationSolution solution = new MultinomialLogitClassificationSolution(new MultinomialLogitModel(lm, targetVariable, doubleVariableNames, factorVariableValues, classValues), (IClassificationProblemData)problemData.Clone());
|
---|
[6567] | 105 | return solution;
|
---|
| 106 | }
|
---|
| 107 | #endregion
|
---|
| 108 | }
|
---|
| 109 | }
|
---|