Free cookie consent management tool by TermsFeed Policy Generator

source: stable/HeuristicLab.Tests/HeuristicLab.Algorithms.DataAnalysis-3.4/GaussianProcessModelTest.cs @ 17058

Last change on this file since 17058 was 15584, checked in by swagner, 7 years ago

#2640: Updated year of copyrights in license headers on stable

File size: 4.3 KB
Line 
1#region License Information
2/* HeuristicLab
3 * Copyright (C) 2002-2018 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.Linq;
23using HeuristicLab.Problems.Instances.DataAnalysis;
24using Microsoft.VisualStudio.TestTools.UnitTesting;
25
26namespace HeuristicLab.Algorithms.DataAnalysis.Tests {
27  [TestClass]
28
29  // reference values calculated with Rasmussen's GPML MATLAB package
30  public class GaussianProcessModelTest {
31    [TestMethod]
32    [TestCategory("General")]
33    [TestProperty("Time", "medium")]
34    public void GaussianProcessModelOutputTest() {
35      var provider = new RegressionCSVInstanceProvider();
36      var problemData = provider.ImportData(@"Test Resources\co2.txt");
37
38      var targetVariable = "interpolated";
39      var allowedInputVariables = new string[] { "decimal date" };
40      var rows = Enumerable.Range(0, 401);
41
42      var meanFunction = new MeanConst();
43      var covarianceFunction = new CovarianceSum();
44      covarianceFunction.Terms.Add(new CovarianceSquaredExponentialIso());
45      var prod = new CovarianceProduct();
46      prod.Factors.Add(new CovarianceSquaredExponentialIso());
47      prod.Factors.Add(new CovariancePeriodic());
48      covarianceFunction.Terms.Add(prod);
49
50      {
51        var hyp = new double[] { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 };
52        var model = new GaussianProcessModel(problemData.Dataset, targetVariable, allowedInputVariables, rows, hyp,
53                                             meanFunction,
54                                             covarianceFunction);
55        Assert.AreEqual(4.3170e+004, model.NegativeLogLikelihood, 1);
56
57        var dHyp = model.HyperparameterGradients;
58        Assert.AreEqual(-248.7932, dHyp[0], 1E-2);
59        var dHypCovExpected = new double[] { -0.5550e4, -5.5533e4, -0.2511e4, -2.7625e4, -1.3033e4, 0.0289e4, -2.7625e4 };
60        AssertEqual(dHypCovExpected, dHyp.Skip(1).Take(7).ToArray(), 1);
61        Assert.AreEqual(-2.0171e+003, dHyp.Last(), 1);
62
63
64        var predTrain = model.GetEstimatedValues(problemData.Dataset, new int[] { 0, 400 }).ToArray();
65        Assert.AreEqual(310.5930, predTrain[0], 1e-3);
66        Assert.AreEqual(347.9993, predTrain[1], 1e-3);
67
68        var predTrainVar = model.GetEstimatedVariances(problemData.Dataset, problemData.TrainingIndices).ToArray();
69      }
70
71      {
72        var hyp = new double[] { 0.029973094285941, 0.455535210579926, 3.438647883940457, 1.464114485889487, 3.001788584487478, 3.815289323309630, 4.374914122810222, 3.001788584487478, 0.716427415979145 };
73        var model = new GaussianProcessModel(problemData.Dataset, targetVariable, allowedInputVariables, rows, hyp,
74                                             meanFunction,
75                                             covarianceFunction);
76        Assert.AreEqual(872.8448, model.NegativeLogLikelihood, 1e-3);
77
78        var dHyp = model.HyperparameterGradients;
79        Assert.AreEqual(-0.0046, dHyp[0], 1e-3);
80        var dHypCovExpected = new double[] { 0.2652, -0.2386, 0.1706, -0.1744, 0.0000, 0.0000, -0.1744 };
81        AssertEqual(dHypCovExpected, dHyp.Skip(1).Take(7).ToArray(), 1e-3);
82        Assert.AreEqual(0.8621, dHyp.Last(), 1e-3);
83
84        var predTrain = model.GetEstimatedValues(problemData.Dataset, new int[] { 0, 400 }).ToArray();
85        Assert.AreEqual(315.3692, predTrain[0], 1e-3);
86        Assert.AreEqual(356.6076, predTrain[1], 1e-3);
87      }
88    }
89
90
91    private void AssertEqual(double[] expected, double[] actual, double delta = 1E-3) {
92      Assert.AreEqual(expected.Length, actual.Length);
93      for (int i = 0; i < expected.Length; i++)
94        Assert.AreEqual(expected[i], actual[i], delta);
95    }
96  }
97}
Note: See TracBrowser for help on using the repository browser.