[15430] | 1 | #region License Information
|
---|
| 2 | /* HeuristicLab
|
---|
| 3 | * Copyright (C) 2002-2017 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 HeuristicLab.Common;
|
---|
| 26 | using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
|
---|
| 27 | using HeuristicLab.Problems.DataAnalysis;
|
---|
| 28 |
|
---|
| 29 | namespace HeuristicLab.Algorithms.DataAnalysis {
|
---|
| 30 | //mulitdimensional extension of http://www2.stat.duke.edu/~tjl13/s101/slides/unit6lec3H.pdf
|
---|
| 31 | [StorableClass]
|
---|
| 32 | internal sealed class PreconstructedLinearModel : RegressionModel, IConfidenceRegressionModel {
|
---|
| 33 | [Storable]
|
---|
| 34 | public Dictionary<string, double> Coefficients { get; private set; }
|
---|
| 35 | [Storable]
|
---|
| 36 | public double Intercept { get; private set; }
|
---|
| 37 | [Storable]
|
---|
| 38 | private Dictionary<string, double> Center { get; set; }
|
---|
| 39 | [Storable]
|
---|
| 40 | private Dictionary<string, double> Variances { get; set; }
|
---|
| 41 | [Storable]
|
---|
| 42 | private double ResidualVariance { get; set; }
|
---|
| 43 | [Storable]
|
---|
| 44 | private int SampleSize { get; set; }
|
---|
| 45 |
|
---|
| 46 | public override IEnumerable<string> VariablesUsedForPrediction {
|
---|
| 47 | get { return Coefficients.Keys; }
|
---|
| 48 | }
|
---|
| 49 | #region HLConstructors
|
---|
| 50 | [StorableConstructor]
|
---|
| 51 | private PreconstructedLinearModel(bool deserializing) : base(deserializing) { }
|
---|
| 52 | private PreconstructedLinearModel(PreconstructedLinearModel original, Cloner cloner) : base(original, cloner) {
|
---|
| 53 | if (original.Coefficients != null) Coefficients = original.Coefficients.ToDictionary(x => x.Key, x => x.Value);
|
---|
| 54 | Intercept = original.Intercept;
|
---|
| 55 | if (original.Center != null) Center = original.Center.ToDictionary(x => x.Key, x => x.Value);
|
---|
| 56 | if (original.Variances != null) Variances = original.Variances.ToDictionary(x => x.Key, x => x.Value);
|
---|
| 57 | ResidualVariance = original.ResidualVariance;
|
---|
| 58 | SampleSize = original.SampleSize;
|
---|
| 59 | }
|
---|
| 60 | private PreconstructedLinearModel(Dictionary<string, double> coefficients, double intercept, string targetvariable) : base(targetvariable) {
|
---|
| 61 | Coefficients = coefficients.ToDictionary(x => x.Key, x => x.Value);
|
---|
| 62 | Intercept = intercept;
|
---|
| 63 | Variances = new Dictionary<string, double>();
|
---|
| 64 | ResidualVariance = 0;
|
---|
| 65 | SampleSize = 0;
|
---|
| 66 | }
|
---|
| 67 | public PreconstructedLinearModel(double intercept, string targetvariable) : base(targetvariable) {
|
---|
| 68 | Coefficients = new Dictionary<string, double>();
|
---|
| 69 | Intercept = intercept;
|
---|
| 70 | Variances = new Dictionary<string, double>();
|
---|
| 71 | ResidualVariance = 0;
|
---|
| 72 | SampleSize = 0;
|
---|
| 73 | }
|
---|
| 74 | public override IDeepCloneable Clone(Cloner cloner) {
|
---|
| 75 | return new PreconstructedLinearModel(this, cloner);
|
---|
| 76 | }
|
---|
| 77 | #endregion
|
---|
| 78 |
|
---|
| 79 | public static PreconstructedLinearModel CreateConfidenceLinearModel(IRegressionProblemData pd, out double rmse, out double cvRmse) {
|
---|
| 80 | var inputMatrix = pd.Dataset.ToArray(pd.AllowedInputVariables.Concat(new[] {pd.TargetVariable}), pd.AllIndices);
|
---|
| 81 | alglib.linearmodel lm;
|
---|
| 82 | alglib.lrreport ar;
|
---|
| 83 | var nFeatures = inputMatrix.GetLength(1) - 1;
|
---|
| 84 | double[] coefficients; // last coefficient is for the constant
|
---|
| 85 |
|
---|
| 86 | int retVal;
|
---|
| 87 | alglib.lrbuild(inputMatrix, inputMatrix.GetLength(0), nFeatures, out retVal, out lm, out ar);
|
---|
| 88 | if (retVal != 1)
|
---|
| 89 | throw new ArgumentException("Error in calculation of linear regression solution");
|
---|
| 90 | rmse = ar.rmserror;
|
---|
| 91 | cvRmse = ar.cvrmserror;
|
---|
| 92 |
|
---|
| 93 | alglib.lrunpack(lm, out coefficients, out nFeatures);
|
---|
| 94 | return new PreconstructedLinearModel(pd.AllowedInputVariables.Zip(coefficients, (s, d) => new {s, d}).ToDictionary(x => x.s, x => x.d), coefficients[nFeatures], pd.TargetVariable);
|
---|
| 95 | }
|
---|
| 96 |
|
---|
| 97 | public override IEnumerable<double> GetEstimatedValues(IDataset dataset, IEnumerable<int> rows) {
|
---|
| 98 | return rows.Select(row => GetEstimatedValue(dataset, row));
|
---|
| 99 | }
|
---|
| 100 |
|
---|
| 101 | public override IRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData) {
|
---|
| 102 | return new RegressionSolution(this, problemData);
|
---|
| 103 | }
|
---|
| 104 |
|
---|
| 105 | public IEnumerable<double> GetEstimatedVariances(IDataset dataset, IEnumerable<int> rows) {
|
---|
| 106 | return rows.Select(i => GetEstimatedVariance(dataset, i));
|
---|
| 107 | }
|
---|
| 108 |
|
---|
| 109 | #region helpers
|
---|
| 110 | private double GetEstimatedValue(IDataset dataset, int row) {
|
---|
| 111 | return Intercept + (Coefficients.Count == 0 ? 0 : Coefficients.Sum(s => s.Value * dataset.GetDoubleValue(s.Key, row)));
|
---|
| 112 | }
|
---|
| 113 | private double GetEstimatedVariance(IDataset dataset, int row) {
|
---|
| 114 | if (SampleSize == 0) return 0.0;
|
---|
| 115 | var sum = (from var in Variances let d = dataset.GetDoubleValue(var.Key, row) - Center[var.Key] select d * d / var.Value).Sum();
|
---|
| 116 | return ResidualVariance * (1.0 / SampleSize + sum / (SampleSize - 1));
|
---|
| 117 | }
|
---|
| 118 | #endregion
|
---|
| 119 | }
|
---|
| 120 | } |
---|