source: trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/LinearRegression.cs @ 14390

Last change on this file since 14390 was 14390, checked in by gkronber, 4 years ago

#2697:

  • renaming of folder "Transformation" to "Converters" to distinguish between transformations for variables (from data preprocessing) and classes for transformation of trees.
  • renamed SymbolicDataAnalysisExpressionTreeSimplifier -> TreeSimplifier
  • Implemented a converter to create a linar model as a symbolic expression tree
File size: 4.9 KB
Line 
1#region License Information
2/* HeuristicLab
3 * Copyright (C) 2002-2016 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
22using System;
23using System.Collections.Generic;
24using System.Linq;
25using HeuristicLab.Common;
26using HeuristicLab.Core;
27using HeuristicLab.Data;
28using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
29using HeuristicLab.Optimization;
30using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
31using HeuristicLab.Problems.DataAnalysis;
32using HeuristicLab.Problems.DataAnalysis.Symbolic;
33using HeuristicLab.Problems.DataAnalysis.Symbolic.Regression;
34
35namespace HeuristicLab.Algorithms.DataAnalysis {
36  /// <summary>
37  /// Linear regression data analysis algorithm.
38  /// </summary>
39  [Item("Linear Regression (LR)", "Linear regression data analysis algorithm (wrapper for ALGLIB).")]
40  [Creatable(CreatableAttribute.Categories.DataAnalysisRegression, Priority = 100)]
41  [StorableClass]
42  public sealed class LinearRegression : FixedDataAnalysisAlgorithm<IRegressionProblem> {
43    private const string LinearRegressionModelResultName = "Linear regression solution";
44
45    [StorableConstructor]
46    private LinearRegression(bool deserializing) : base(deserializing) { }
47    private LinearRegression(LinearRegression original, Cloner cloner)
48      : base(original, cloner) {
49    }
50    public LinearRegression()
51      : base() {
52      Problem = new RegressionProblem();
53    }
54    [StorableHook(HookType.AfterDeserialization)]
55    private void AfterDeserialization() { }
56
57    public override IDeepCloneable Clone(Cloner cloner) {
58      return new LinearRegression(this, cloner);
59    }
60
61    #region linear regression
62    protected override void Run() {
63      double rmsError, cvRmsError;
64      var solution = CreateLinearRegressionSolution(Problem.ProblemData, out rmsError, out cvRmsError);
65      Results.Add(new Result(LinearRegressionModelResultName, "The linear regression solution.", solution));
66      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)));
67      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)));
68    }
69
70    public static ISymbolicRegressionSolution CreateLinearRegressionSolution(IRegressionProblemData problemData, out double rmsError, out double cvRmsError) {
71      var dataset = problemData.Dataset;
72      string targetVariable = problemData.TargetVariable;
73      IEnumerable<string> allowedInputVariables = problemData.AllowedInputVariables;
74      IEnumerable<int> rows = problemData.TrainingIndices;
75      double[,] inputMatrix = AlglibUtil.PrepareInputMatrix(dataset, allowedInputVariables.Concat(new string[] { targetVariable }), rows);
76      if (inputMatrix.Cast<double>().Any(x => double.IsNaN(x) || double.IsInfinity(x)))
77        throw new NotSupportedException("Linear regression does not support NaN or infinity values in the input dataset.");
78
79      alglib.linearmodel lm = new alglib.linearmodel();
80      alglib.lrreport ar = new alglib.lrreport();
81      int nRows = inputMatrix.GetLength(0);
82      int nFeatures = inputMatrix.GetLength(1) - 1;
83      double[] coefficients;
84
85      int retVal = 1;
86      alglib.lrbuild(inputMatrix, nRows, nFeatures, out retVal, out lm, out ar);
87      if (retVal != 1) throw new ArgumentException("Error in calculation of linear regression solution");
88      rmsError = ar.rmserror;
89      cvRmsError = ar.cvrmserror;
90
91      alglib.lrunpack(lm, out coefficients, out nFeatures);
92
93      var tree = LinearModelToTreeConverter.CreateTree(allowedInputVariables.ToArray(),
94        coefficients.Take(nFeatures).ToArray(), @const: coefficients[nFeatures]);
95
96      SymbolicRegressionSolution solution = new SymbolicRegressionSolution(new SymbolicRegressionModel(problemData.TargetVariable, tree, new SymbolicDataAnalysisExpressionTreeInterpreter()), (IRegressionProblemData)problemData.Clone());
97      solution.Model.Name = "Linear Regression Model";
98      solution.Name = "Linear Regression Solution";
99      return solution;
100    }
101    #endregion
102  }
103}
Note: See TracBrowser for help on using the repository browser.