Free cookie consent management tool by TermsFeed Policy Generator

source: branches/3040_VectorBasedGP/HeuristicLab.Problems.Instances.DataAnalysis/3.3/Regression/ResourceRegressionInstanceProvider.cs @ 17541

Last change on this file since 17541 was 17418, checked in by pfleck, 5 years ago

#3040

  • (partially) enabled data preprocessing for vectorial data
  • use flat zip-files for large benchmarks instead of embedded resources (faster build times)
  • added multiple variants of vector benchmark I (vector lengh constraints)
File size: 2.8 KB
Line 
1#region License Information
2/* HeuristicLab
3 * Copyright (C) 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.Globalization;
24using System.IO;
25using System.IO.Compression;
26using System.Linq;
27using System.Text.RegularExpressions;
28using HeuristicLab.Problems.DataAnalysis;
29
30namespace HeuristicLab.Problems.Instances.DataAnalysis {
31  public abstract class ResourceRegressionInstanceProvider : RegressionInstanceProvider {
32
33    protected abstract string FileName { get; }
34
35    public override IRegressionProblemData LoadData(IDataDescriptor id) {
36      var descriptor = (ResourceRegressionDataDescriptor)id;
37
38      using (var instancesZipFile = new ZipArchive(OpenResourceStream(FileName), ZipArchiveMode.Read)) {
39        var entry = instancesZipFile.GetEntry(descriptor.ResourceName);
40        var formatOptions = GetFormatOptions(entry);
41
42        TableFileParser csvFileParser = new TableFileParser();
43        using (Stream stream = entry.Open()) {
44          csvFileParser.Parse(stream, formatOptions, true);
45        }
46
47        Dataset dataset = new Dataset(csvFileParser.VariableNames, csvFileParser.Values);
48        if (!descriptor.CheckVariableNames(csvFileParser.VariableNames)) {
49          throw new ArgumentException("Parsed file contains variables which are not in the descriptor.");
50        }
51
52        return descriptor.GenerateRegressionData(dataset);
53      }
54    }
55
56    protected virtual string GetResourceName(string fileName) {
57      return GetType().Assembly.GetManifestResourceNames()
58              .Where(x => Regex.Match(x, @".*\.Data\." + fileName).Success).SingleOrDefault();
59    }
60
61    protected virtual Stream OpenResourceStream(string fileName) {
62      var instanceArchiveName = GetResourceName(FileName + @"\.zip");
63      return GetType().Assembly.GetManifestResourceStream(instanceArchiveName);
64    }
65
66    protected virtual TableFileFormatOptions GetFormatOptions(ZipArchiveEntry entry) {
67      using (Stream stream = entry.Open()) {
68        return TableFileParser.DetermineFileFormat(stream);
69      }
70    }
71  }
72}
Note: See TracBrowser for help on using the repository browser.