1  #region License Information


2  /* HeuristicLab


3  * Copyright (C) 20022016 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 


22  using System;


23  using System.Collections.Generic;


24  using System.Linq;


25  using System.Threading;


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  using HeuristicLab.Problems.DataAnalysis.Symbolic;


33  using HeuristicLab.Problems.DataAnalysis.Symbolic.Regression;


34 


35  namespace 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(CancellationToken cancellationToken) {


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 (crossvalidation)", "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  var doubleVariables = allowedInputVariables.Where(dataset.VariableHasType<double>);


76  var factorVariableNames = allowedInputVariables.Where(dataset.VariableHasType<string>);


77  var factorVariables = dataset.GetFactorVariableValues(factorVariableNames, rows);


78  double[,] binaryMatrix = dataset.ToArray(factorVariables, rows);


79  double[,] doubleVarMatrix = dataset.ToArray(doubleVariables.Concat(new string[] { targetVariable }), rows);


80  var inputMatrix = binaryMatrix.HorzCat(doubleVarMatrix);


81 


82  if (inputMatrix.Cast<double>().Any(x => double.IsNaN(x)  double.IsInfinity(x)))


83  throw new NotSupportedException("Linear regression does not support NaN or infinity values in the input dataset.");


84 


85  alglib.linearmodel lm = new alglib.linearmodel();


86  alglib.lrreport ar = new alglib.lrreport();


87  int nRows = inputMatrix.GetLength(0);


88  int nFeatures = inputMatrix.GetLength(1)  1;


89  double[] coefficients = new double[nFeatures + 1]; // last coefficient is for the constant


90 


91  int retVal = 1;


92  alglib.lrbuild(inputMatrix, nRows, nFeatures, out retVal, out lm, out ar);


93  if (retVal != 1) throw new ArgumentException("Error in calculation of linear regression solution");


94  rmsError = ar.rmserror;


95  cvRmsError = ar.cvrmserror;


96 


97  alglib.lrunpack(lm, out coefficients, out nFeatures);


98 


99  int nFactorCoeff = binaryMatrix.GetLength(1);


100  int nVarCoeff = doubleVariables.Count();


101  var tree = LinearModelToTreeConverter.CreateTree(factorVariables, coefficients.Take(nFactorCoeff).ToArray(),


102  doubleVariables.ToArray(), coefficients.Skip(nFactorCoeff).Take(nVarCoeff).ToArray(),


103  @const: coefficients[nFeatures]);


104 


105  SymbolicRegressionSolution solution = new SymbolicRegressionSolution(new SymbolicRegressionModel(problemData.TargetVariable, tree, new SymbolicDataAnalysisExpressionTreeLinearInterpreter()), (IRegressionProblemData)problemData.Clone());


106  solution.Model.Name = "Linear Regression Model";


107  solution.Name = "Linear Regression Solution";


108  return solution;


109  }


110  #endregion


111  }


112  }

