1 | #region License Information
|
---|
2 | /* HeuristicLab
|
---|
3 | * Copyright (C) 2002-2015 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
|
---|
4 | * and the BEACON Center for the Study of Evolution in Action.
|
---|
5 | *
|
---|
6 | * This file is part of HeuristicLab.
|
---|
7 | *
|
---|
8 | * HeuristicLab is free software: you can redistribute it and/or modify
|
---|
9 | * it under the terms of the GNU General Public License as published by
|
---|
10 | * the Free Software Foundation, either version 3 of the License, or
|
---|
11 | * (at your option) any later version.
|
---|
12 | *
|
---|
13 | * HeuristicLab is distributed in the hope that it will be useful,
|
---|
14 | * but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
15 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
16 | * GNU General Public License for more details.
|
---|
17 | *
|
---|
18 | * You should have received a copy of the GNU General Public License
|
---|
19 | * along with HeuristicLab. If not, see <http://www.gnu.org/licenses/>.
|
---|
20 | */
|
---|
21 | #endregion
|
---|
22 |
|
---|
23 | using System;
|
---|
24 | using System.Collections.Generic;
|
---|
25 | using System.Diagnostics;
|
---|
26 | using System.Linq;
|
---|
27 | using HeuristicLab.Common;
|
---|
28 | using HeuristicLab.Core;
|
---|
29 | using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
|
---|
30 |
|
---|
31 | namespace HeuristicLab.Algorithms.DataAnalysis {
|
---|
32 | // Greedy Function Approximation: A Gradient Boosting Machine (page 9)
|
---|
33 | [StorableType("89E2D6B3-2BDE-4FF2-98B5-236F4C3B3F69")]
|
---|
34 | [Item("Logistic regression loss", "")]
|
---|
35 | public sealed class LogisticRegressionLoss : Item, ILossFunction {
|
---|
36 | public LogisticRegressionLoss() { }
|
---|
37 |
|
---|
38 | public double GetLoss(IEnumerable<double> target, IEnumerable<double> pred) {
|
---|
39 | var targetEnum = target.GetEnumerator();
|
---|
40 | var predEnum = pred.GetEnumerator();
|
---|
41 |
|
---|
42 | double s = 0;
|
---|
43 | while (targetEnum.MoveNext() & predEnum.MoveNext()) {
|
---|
44 | Debug.Assert(targetEnum.Current.IsAlmost(0.0) || targetEnum.Current.IsAlmost(1.0), "labels must be 0 or 1 for logistic regression loss");
|
---|
45 |
|
---|
46 | var y = targetEnum.Current * 2 - 1; // y in {-1,1}
|
---|
47 | s += Math.Log(1 + Math.Exp(-2 * y * predEnum.Current));
|
---|
48 | }
|
---|
49 | if (targetEnum.MoveNext() | predEnum.MoveNext())
|
---|
50 | throw new ArgumentException("target and pred have different lengths");
|
---|
51 |
|
---|
52 | return s;
|
---|
53 | }
|
---|
54 |
|
---|
55 | public IEnumerable<double> GetLossGradient(IEnumerable<double> target, IEnumerable<double> pred) {
|
---|
56 | var targetEnum = target.GetEnumerator();
|
---|
57 | var predEnum = pred.GetEnumerator();
|
---|
58 |
|
---|
59 | while (targetEnum.MoveNext() & predEnum.MoveNext()) {
|
---|
60 | Debug.Assert(targetEnum.Current.IsAlmost(0.0) || targetEnum.Current.IsAlmost(1.0), "labels must be 0 or 1 for logistic regression loss");
|
---|
61 | var y = targetEnum.Current * 2 - 1; // y in {-1,1}
|
---|
62 |
|
---|
63 | yield return 2 * y / (1 + Math.Exp(2 * y * predEnum.Current));
|
---|
64 |
|
---|
65 | }
|
---|
66 | if (targetEnum.MoveNext() | predEnum.MoveNext())
|
---|
67 | throw new ArgumentException("target and pred have different lengths");
|
---|
68 | }
|
---|
69 |
|
---|
70 | // targetArr and predArr are not changed by LineSearch
|
---|
71 | public double LineSearch(double[] targetArr, double[] predArr, int[] idx, int startIdx, int endIdx) {
|
---|
72 | if (targetArr.Length != predArr.Length)
|
---|
73 | throw new ArgumentException("target and pred have different lengths");
|
---|
74 |
|
---|
75 | // "Simple Newton-Raphson step" of eqn. 23
|
---|
76 | double sumY = 0.0;
|
---|
77 | double sumDiff = 0.0;
|
---|
78 | for (int i = startIdx; i <= endIdx; i++) {
|
---|
79 | var row = idx[i];
|
---|
80 | var y = targetArr[row] * 2 - 1; // y in {-1,1}
|
---|
81 | var pseudoResponse = 2 * y / (1 + Math.Exp(2 * y * predArr[row]));
|
---|
82 |
|
---|
83 | sumY += pseudoResponse;
|
---|
84 | sumDiff += Math.Abs(pseudoResponse) * (2 - Math.Abs(pseudoResponse));
|
---|
85 | }
|
---|
86 | // prevent divByZero
|
---|
87 | sumDiff = Math.Max(1E-12, sumDiff);
|
---|
88 | return sumY / sumDiff;
|
---|
89 | }
|
---|
90 |
|
---|
91 | #region item implementation
|
---|
92 | [StorableConstructor]
|
---|
93 | private LogisticRegressionLoss(bool deserializing) : base(deserializing) { }
|
---|
94 |
|
---|
95 | private LogisticRegressionLoss(LogisticRegressionLoss original, Cloner cloner) : base(original, cloner) { }
|
---|
96 |
|
---|
97 | public override IDeepCloneable Clone(Cloner cloner) {
|
---|
98 | return new LogisticRegressionLoss(this, cloner);
|
---|
99 | }
|
---|
100 | #endregion
|
---|
101 |
|
---|
102 | }
|
---|
103 | }
|
---|