Free cookie consent management tool by TermsFeed Policy Generator

source: branches/PersistenceSpeedUp/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/LinearRegression.cs @ 6760

Last change on this file since 6760 was 6760, checked in by epitzer, 13 years ago

#1530 integrate changes from trunk

File size: 5.5 KB
Line 
1#region License Information
2/* HeuristicLab
3 * Copyright (C) 2002-2011 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", "Linear regression data analysis algorithm (wrapper for ALGLIB).")]
40  [Creatable("Data Analysis")]
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
55    public override IDeepCloneable Clone(Cloner cloner) {
56      return new LinearRegression(this, cloner);
57    }
58
59    #region linear regression
60    protected override void Run() {
61      double rmsError, cvRmsError;
62      var solution = CreateLinearRegressionSolution(Problem.ProblemData, out rmsError, out cvRmsError);
63      Results.Add(new Result(LinearRegressionModelResultName, "The linear regression solution.", solution));
64      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)));
65      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)));
66    }
67
68    public static ISymbolicRegressionSolution CreateLinearRegressionSolution(IRegressionProblemData problemData, out double rmsError, out double cvRmsError) {
69      Dataset dataset = problemData.Dataset;
70      string targetVariable = problemData.TargetVariable;
71      IEnumerable<string> allowedInputVariables = problemData.AllowedInputVariables;
72      IEnumerable<int> rows = problemData.TrainingIndizes;
73      double[,] inputMatrix = AlglibUtil.PrepareInputMatrix(dataset, allowedInputVariables.Concat(new string[] { targetVariable }), rows);
74      if (inputMatrix.Cast<double>().Any(x => double.IsNaN(x) || double.IsInfinity(x)))
75        throw new NotSupportedException("Linear regression does not support NaN or infinity values in the input dataset.");
76
77      alglib.linearmodel lm = new alglib.linearmodel();
78      alglib.lrreport ar = new alglib.lrreport();
79      int nRows = inputMatrix.GetLength(0);
80      int nFeatures = inputMatrix.GetLength(1) - 1;
81      double[] coefficients = new double[nFeatures + 1]; // last coefficient is for the constant
82
83      int retVal = 1;
84      alglib.lrbuild(inputMatrix, nRows, nFeatures, out retVal, out lm, out ar);
85      if (retVal != 1) throw new ArgumentException("Error in calculation of linear regression solution");
86      rmsError = ar.rmserror;
87      cvRmsError = ar.cvrmserror;
88
89      alglib.lrunpack(lm, out coefficients, out nFeatures);
90
91      ISymbolicExpressionTree tree = new SymbolicExpressionTree(new ProgramRootSymbol().CreateTreeNode());
92      ISymbolicExpressionTreeNode startNode = new StartSymbol().CreateTreeNode();
93      tree.Root.AddSubtree(startNode);
94      ISymbolicExpressionTreeNode addition = new Addition().CreateTreeNode();
95      startNode.AddSubtree(addition);
96
97      int col = 0;
98      foreach (string column in allowedInputVariables) {
99        VariableTreeNode vNode = (VariableTreeNode)new HeuristicLab.Problems.DataAnalysis.Symbolic.Variable().CreateTreeNode();
100        vNode.VariableName = column;
101        vNode.Weight = coefficients[col];
102        addition.AddSubtree(vNode);
103        col++;
104      }
105
106      ConstantTreeNode cNode = (ConstantTreeNode)new Constant().CreateTreeNode();
107      cNode.Value = coefficients[coefficients.Length - 1];
108      addition.AddSubtree(cNode);
109
110      SymbolicRegressionSolution solution = new SymbolicRegressionSolution(new SymbolicRegressionModel(tree, new SymbolicDataAnalysisExpressionTreeInterpreter()), (IRegressionProblemData)problemData.Clone());
111      solution.Model.Name = "Linear Regression Model";
112      return solution;
113    }
114    #endregion
115  }
116}
Note: See TracBrowser for help on using the repository browser.