Free cookie consent management tool by TermsFeed Policy Generator

source: trunk/sources/HeuristicLab.Problems.Instances.DataAnalysis/3.3/Classification/ResourceClassificationInstanceProvider.cs @ 9456

Last change on this file since 9456 was 9456, checked in by swagner, 11 years ago

Updated copyright year and added some missing license headers (#1889)

File size: 2.8 KB
Line 
1#region License Information
2/* HeuristicLab
3 * Copyright (C) 2002-2013 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.Linq;
26using System.Reflection;
27using System.Text.RegularExpressions;
28using HeuristicLab.Problems.DataAnalysis;
29using ICSharpCode.SharpZipLib.Zip;
30
31namespace HeuristicLab.Problems.Instances.DataAnalysis {
32  public abstract class ResourceClassificationInstanceProvider : ClassificationInstanceProvider {
33
34    protected abstract string FileName { get; }
35
36    public override IClassificationProblemData LoadData(IDataDescriptor id) {
37      var descriptor = (ResourceClassificationDataDescriptor)id;
38
39      var instanceArchiveName = GetResourceName(FileName + @"\.zip");
40      using (var instancesZipFile = new ZipFile(GetType().Assembly.GetManifestResourceStream(instanceArchiveName))) {
41        var entry = instancesZipFile.GetEntry(descriptor.ResourceName);
42        NumberFormatInfo numberFormat;
43        DateTimeFormatInfo dateFormat;
44        char separator;
45        using (Stream stream = instancesZipFile.GetInputStream(entry)) {
46          TableFileParser.DetermineFileFormat(stream, out numberFormat, out dateFormat, out separator);
47        }
48
49        TableFileParser csvFileParser = new TableFileParser();
50        using (Stream stream = instancesZipFile.GetInputStream(entry)) {
51          csvFileParser.Parse(stream, numberFormat, dateFormat, separator);
52        }
53
54        Dataset dataset = new Dataset(csvFileParser.VariableNames, csvFileParser.Values);
55        if (!descriptor.CheckVariableNames(csvFileParser.VariableNames)) {
56          throw new ArgumentException("Parsed file contains variables which are not in the descriptor.");
57        }
58
59        return descriptor.GenerateClassificationData(dataset);
60      }
61    }
62
63    protected virtual string GetResourceName(string fileName) {
64      return Assembly.GetExecutingAssembly().GetManifestResourceNames()
65              .Where(x => Regex.Match(x, @".*\.Data\." + fileName).Success).SingleOrDefault();
66    }
67  }
68}
Note: See TracBrowser for help on using the repository browser.