Free cookie consent management tool by TermsFeed Policy Generator

source: trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/LinearRegression.cs @ 14843

Last change on this file since 14843 was 14843, checked in by gkronber, 7 years ago

#2697: applied r14390, r14391, r14393, r14394, r14396 again (resolving conflicts)

File size: 5.6 KB
RevLine 
[5617]1#region License Information
2/* HeuristicLab
[14185]3 * Copyright (C) 2002-2016 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
22using System;
[5777]23using System.Collections.Generic;
[5617]24using System.Linq;
[14523]25using System.Threading;
[5617]26using HeuristicLab.Common;
27using HeuristicLab.Core;
28using HeuristicLab.Data;
[5777]29using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
[5617]30using HeuristicLab.Optimization;
31using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
32using HeuristicLab.Problems.DataAnalysis;
33using HeuristicLab.Problems.DataAnalysis.Symbolic;
[5624]34using HeuristicLab.Problems.DataAnalysis.Symbolic.Regression;
[5617]35
36namespace HeuristicLab.Algorithms.DataAnalysis {
37  /// <summary>
38  /// Linear regression data analysis algorithm.
39  /// </summary>
[13238]40  [Item("Linear Regression (LR)", "Linear regression data analysis algorithm (wrapper for ALGLIB).")]
[12504]41  [Creatable(CreatableAttribute.Categories.DataAnalysisRegression, Priority = 100)]
[5617]42  [StorableClass]
43  public sealed class LinearRegression : FixedDataAnalysisAlgorithm<IRegressionProblem> {
[5649]44    private const string LinearRegressionModelResultName = "Linear regression solution";
[5617]45
46    [StorableConstructor]
47    private LinearRegression(bool deserializing) : base(deserializing) { }
48    private LinearRegression(LinearRegression original, Cloner cloner)
49      : base(original, cloner) {
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
[14523]63    protected override void Run(CancellationToken cancellationToken) {
[5617]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;
[14826]76      var doubleVariables = allowedInputVariables.Where(dataset.VariableHasType<double>);
77      var factorVariableNames = allowedInputVariables.Where(dataset.VariableHasType<string>);
[14843]78      var factorVariables = dataset.GetFactorVariableValues(factorVariableNames, rows);
79      double[,] binaryMatrix = dataset.ToArray(factorVariables, rows);
80      double[,] doubleVarMatrix = dataset.ToArray(doubleVariables.Concat(new string[] { targetVariable }), rows);
[14826]81      var inputMatrix = binaryMatrix.HorzCat(doubleVarMatrix);
82
[6002]83      if (inputMatrix.Cast<double>().Any(x => double.IsNaN(x) || double.IsInfinity(x)))
84        throw new NotSupportedException("Linear regression does not support NaN or infinity values in the input dataset.");
[5617]85
[12817]86      alglib.linearmodel lm = new alglib.linearmodel();
87      alglib.lrreport ar = new alglib.lrreport();
[5617]88      int nRows = inputMatrix.GetLength(0);
89      int nFeatures = inputMatrix.GetLength(1) - 1;
[14400]90      double[] coefficients = new double[nFeatures + 1]; // last coefficient is for the constant
[5617]91
92      int retVal = 1;
93      alglib.lrbuild(inputMatrix, nRows, nFeatures, out retVal, out lm, out ar);
[5649]94      if (retVal != 1) throw new ArgumentException("Error in calculation of linear regression solution");
[5617]95      rmsError = ar.rmserror;
96      cvRmsError = ar.cvrmserror;
97
98      alglib.lrunpack(lm, out coefficients, out nFeatures);
99
[14843]100      int nFactorCoeff = binaryMatrix.GetLength(1);
101      int nVarCoeff = doubleVariables.Count();
102      var tree = LinearModelToTreeConverter.CreateTree(factorVariables, coefficients.Take(nFactorCoeff).ToArray(),
103        doubleVariables.ToArray(), coefficients.Skip(nFactorCoeff).Take(nVarCoeff).ToArray(),
104        @const: coefficients[nFeatures]);
105     
[14685]106      SymbolicRegressionSolution solution = new SymbolicRegressionSolution(new SymbolicRegressionModel(problemData.TargetVariable, tree, new SymbolicDataAnalysisExpressionTreeLinearInterpreter()), (IRegressionProblemData)problemData.Clone());
[6555]107      solution.Model.Name = "Linear Regression Model";
[7588]108      solution.Name = "Linear Regression Solution";
[5624]109      return solution;
[5617]110    }
111    #endregion
112  }
113}
Note: See TracBrowser for help on using the repository browser.