[5617] | 1 | #region License Information
|
---|
| 2 | /* HeuristicLab
|
---|
[12012] | 3 | * Copyright (C) 2002-2015 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
|
---|
[5617] | 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;
|
---|
[5777] | 23 | using System.Collections.Generic;
|
---|
[5617] | 24 | using System.Linq;
|
---|
| 25 | using HeuristicLab.Common;
|
---|
| 26 | using HeuristicLab.Core;
|
---|
| 27 | using HeuristicLab.Data;
|
---|
[5777] | 28 | using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
|
---|
[5617] | 29 | using HeuristicLab.Optimization;
|
---|
| 30 | using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
|
---|
| 31 | using HeuristicLab.Problems.DataAnalysis;
|
---|
| 32 | using HeuristicLab.Problems.DataAnalysis.Symbolic;
|
---|
[5624] | 33 | using HeuristicLab.Problems.DataAnalysis.Symbolic.Regression;
|
---|
[5617] | 34 |
|
---|
| 35 | namespace HeuristicLab.Algorithms.DataAnalysis {
|
---|
| 36 | /// <summary>
|
---|
| 37 | /// Linear regression data analysis algorithm.
|
---|
| 38 | /// </summary>
|
---|
[6240] | 39 | [Item("Linear Regression", "Linear regression data analysis algorithm (wrapper for ALGLIB).")]
|
---|
[12504] | 40 | [Creatable(CreatableAttribute.Categories.DataAnalysisRegression, Priority = 100)]
|
---|
[5617] | 41 | [StorableClass]
|
---|
| 42 | public sealed class LinearRegression : FixedDataAnalysisAlgorithm<IRegressionProblem> {
|
---|
[5649] | 43 | private const string LinearRegressionModelResultName = "Linear regression solution";
|
---|
[5617] | 44 |
|
---|
| 45 | [StorableConstructor]
|
---|
| 46 | private LinearRegression(bool deserializing) : base(deserializing) { }
|
---|
| 47 | private LinearRegression(LinearRegression original, Cloner cloner)
|
---|
| 48 | : base(original, cloner) {
|
---|
[12792] | 49 |
|
---|
[5617] | 50 | }
|
---|
| 51 | public LinearRegression()
|
---|
| 52 | : base() {
|
---|
[5649] | 53 | Problem = new RegressionProblem();
|
---|
[5617] | 54 | }
|
---|
| 55 | [StorableHook(HookType.AfterDeserialization)]
|
---|
| 56 | private void AfterDeserialization() { }
|
---|
| 57 |
|
---|
| 58 | public override IDeepCloneable Clone(Cloner cloner) {
|
---|
| 59 | return new LinearRegression(this, cloner);
|
---|
| 60 | }
|
---|
| 61 |
|
---|
| 62 | #region linear regression
|
---|
| 63 | protected override void Run() {
|
---|
| 64 | double rmsError, cvRmsError;
|
---|
[5624] | 65 | var solution = CreateLinearRegressionSolution(Problem.ProblemData, out rmsError, out cvRmsError);
|
---|
[5649] | 66 | Results.Add(new Result(LinearRegressionModelResultName, "The linear regression solution.", solution));
|
---|
| 67 | Results.Add(new Result("Root mean square error", "The root of the mean of squared errors of the linear regression solution on the training set.", new DoubleValue(rmsError)));
|
---|
| 68 | Results.Add(new Result("Estimated root mean square error (cross-validation)", "The estimated root of the mean of squared errors of the linear regression solution via cross validation.", new DoubleValue(cvRmsError)));
|
---|
[5617] | 69 | }
|
---|
| 70 |
|
---|
[5624] | 71 | public static ISymbolicRegressionSolution CreateLinearRegressionSolution(IRegressionProblemData problemData, out double rmsError, out double cvRmsError) {
|
---|
[12509] | 72 | var dataset = problemData.Dataset;
|
---|
[5624] | 73 | string targetVariable = problemData.TargetVariable;
|
---|
[5649] | 74 | IEnumerable<string> allowedInputVariables = problemData.AllowedInputVariables;
|
---|
[8139] | 75 | IEnumerable<int> rows = problemData.TrainingIndices;
|
---|
[5658] | 76 | double[,] inputMatrix = AlglibUtil.PrepareInputMatrix(dataset, allowedInputVariables.Concat(new string[] { targetVariable }), rows);
|
---|
[6002] | 77 | if (inputMatrix.Cast<double>().Any(x => double.IsNaN(x) || double.IsInfinity(x)))
|
---|
| 78 | throw new NotSupportedException("Linear regression does not support NaN or infinity values in the input dataset.");
|
---|
[5617] | 79 |
|
---|
[12792] | 80 | alglib.linearmodel lm;
|
---|
| 81 | alglib.lrreport ar;
|
---|
[5617] | 82 | int nRows = inputMatrix.GetLength(0);
|
---|
| 83 | int nFeatures = inputMatrix.GetLength(1) - 1;
|
---|
[12792] | 84 | double[] coefficients;
|
---|
[5617] | 85 |
|
---|
| 86 | int retVal = 1;
|
---|
| 87 | alglib.lrbuild(inputMatrix, nRows, nFeatures, out retVal, out lm, out ar);
|
---|
[5649] | 88 | if (retVal != 1) throw new ArgumentException("Error in calculation of linear regression solution");
|
---|
[5617] | 89 | rmsError = ar.rmserror;
|
---|
| 90 | cvRmsError = ar.cvrmserror;
|
---|
| 91 |
|
---|
| 92 | alglib.lrunpack(lm, out coefficients, out nFeatures);
|
---|
| 93 |
|
---|
| 94 | ISymbolicExpressionTree tree = new SymbolicExpressionTree(new ProgramRootSymbol().CreateTreeNode());
|
---|
| 95 | ISymbolicExpressionTreeNode startNode = new StartSymbol().CreateTreeNode();
|
---|
[5733] | 96 | tree.Root.AddSubtree(startNode);
|
---|
[5617] | 97 | ISymbolicExpressionTreeNode addition = new Addition().CreateTreeNode();
|
---|
[5733] | 98 | startNode.AddSubtree(addition);
|
---|
[5617] | 99 |
|
---|
| 100 | int col = 0;
|
---|
| 101 | foreach (string column in allowedInputVariables) {
|
---|
| 102 | VariableTreeNode vNode = (VariableTreeNode)new HeuristicLab.Problems.DataAnalysis.Symbolic.Variable().CreateTreeNode();
|
---|
| 103 | vNode.VariableName = column;
|
---|
| 104 | vNode.Weight = coefficients[col];
|
---|
[5733] | 105 | addition.AddSubtree(vNode);
|
---|
[5617] | 106 | col++;
|
---|
| 107 | }
|
---|
| 108 |
|
---|
| 109 | ConstantTreeNode cNode = (ConstantTreeNode)new Constant().CreateTreeNode();
|
---|
| 110 | cNode.Value = coefficients[coefficients.Length - 1];
|
---|
[5733] | 111 | addition.AddSubtree(cNode);
|
---|
[5617] | 112 |
|
---|
[6649] | 113 | SymbolicRegressionSolution solution = new SymbolicRegressionSolution(new SymbolicRegressionModel(tree, new SymbolicDataAnalysisExpressionTreeInterpreter()), (IRegressionProblemData)problemData.Clone());
|
---|
[6555] | 114 | solution.Model.Name = "Linear Regression Model";
|
---|
[7588] | 115 | solution.Name = "Linear Regression Solution";
|
---|
[5624] | 116 | return solution;
|
---|
[5617] | 117 | }
|
---|
| 118 | #endregion
|
---|
| 119 | }
|
---|
| 120 | }
|
---|