Free cookie consent management tool by TermsFeed Policy Generator

source: branches/1888_OaaS/HeuristicLab.Problems.Instances.DataAnalysis/3.3/Classification/UCI/UCIInstanceProvider.cs

Last change on this file was 9208, checked in by sforsten, 12 years ago

#1941:

  • added wisconsin breast cancer problem instance
  • corrected iris dataset
  • changed classification data descriptors to be able to set training and test partition as well as input and target variables (in the same way as it is done in regression)
File size: 3.0 KB
Line 
1#region License Information
2/* HeuristicLab
3 * Copyright (C) 2002-2012 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.Collections.Generic;
24using System.IO;
25using System.Linq;
26using ICSharpCode.SharpZipLib.Zip;
27
28namespace HeuristicLab.Problems.Instances.DataAnalysis {
29  public class UCIInstanceProvider : ResourceClassificationInstanceProvider {
30    public override string Name {
31      get { return "UCI Problems"; }
32    }
33    public override string Description {
34      get {
35        return "";
36      }
37    }
38    public override Uri WebLink {
39      get { return new Uri("http://archive.ics.uci.edu/ml/datasets.html"); }
40    }
41    public override string ReferencePublication {
42      get { return ""; }
43    }
44
45    protected override string FileName { get { return "UCI"; } }
46
47    public override IEnumerable<IDataDescriptor> GetDataDescriptors() {
48      List<UCIDataDescriptor> descriptorList = new List<UCIDataDescriptor>();
49      descriptorList.Add(new Iris());
50      descriptorList.Add(new Mammography());
51      descriptorList.Add(new Parkinson());
52      descriptorList.Add(new Thyroid());
53      descriptorList.Add(new Vertebral_3C());
54      descriptorList.Add(new Wine());
55      descriptorList.Add(new WisconsinDiagnosticBreastCancer());
56      var solutionsArchiveName = GetResourceName(FileName + @"\.zip");
57      if (!String.IsNullOrEmpty(solutionsArchiveName)) {
58        using (var solutionsZipFile = new ZipInputStream(GetType().Assembly.GetManifestResourceStream(solutionsArchiveName))) {
59          IList<string> entries = new List<string>();
60          ZipEntry curEntry;
61          while ((curEntry = solutionsZipFile.GetNextEntry()) != null) {
62            entries.Add(curEntry.Name);
63          }
64          foreach (var entry in entries.OrderBy(x => x)) {
65            string filename = Path.GetFileNameWithoutExtension(entry);
66            UCIDataDescriptor desc = descriptorList.Where(x => x.Filename.Equals(filename)).FirstOrDefault();
67            if (desc != null) {
68              desc.ResourceName = entry;
69              yield return desc;
70            } else
71              throw new ArgumentNullException("No Descriptor could be found for this entry.");
72          }
73        }
74      }
75    }
76  }
77}
Note: See TracBrowser for help on using the repository browser.