Free cookie consent management tool by TermsFeed Policy Generator

source: trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/SupportVectorMachine/SupportVectorMachineUtil.cs @ 11171

Last change on this file since 11171 was 11171, checked in by ascheibe, 9 years ago

#2115 merged r11170 (copyright update) into trunk

File size: 2.8 KB
Line 
1#region License Information
2/* HeuristicLab
3 * Copyright (C) 2002-2014 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.Collections.Generic;
23using System.Linq;
24using HeuristicLab.Problems.DataAnalysis;
25using LibSVM;
26
27namespace HeuristicLab.Algorithms.DataAnalysis {
28  public class SupportVectorMachineUtil {
29    /// <summary>
30    /// Transforms <paramref name="problemData"/> into a data structure as needed by libSVM.
31    /// </summary>
32    /// <param name="problemData">The problem data to transform</param>
33    /// <param name="rowIndices">The rows of the dataset that should be contained in the resulting SVM-problem</param>
34    /// <returns>A problem data type that can be used to train a support vector machine.</returns>
35    public static svm_problem CreateSvmProblem(Dataset dataset, string targetVariable, IEnumerable<string> inputVariables, IEnumerable<int> rowIndices) {
36      double[] targetVector =
37        dataset.GetDoubleValues(targetVariable, rowIndices).ToArray();
38
39      svm_node[][] nodes = new svm_node[targetVector.Length][];
40      List<svm_node> tempRow;
41      int maxNodeIndex = 0;
42      int svmProblemRowIndex = 0;
43      List<string> inputVariablesList = inputVariables.ToList();
44      foreach (int row in rowIndices) {
45        tempRow = new List<svm_node>();
46        int colIndex = 1; // make sure the smallest node index for SVM = 1
47        foreach (var inputVariable in inputVariablesList) {
48          double value = dataset.GetDoubleValue(inputVariable, row);
49          // SVM also works with missing values
50          // => don't add NaN values in the dataset to the sparse SVM matrix representation
51          if (!double.IsNaN(value)) {
52            tempRow.Add(new svm_node() { index = colIndex, value = value }); // nodes must be sorted in ascending ordered by column index
53            if (colIndex > maxNodeIndex) maxNodeIndex = colIndex;
54          }
55          colIndex++;
56        }
57        nodes[svmProblemRowIndex++] = tempRow.ToArray();
58      }
59
60      return new svm_problem() { l = targetVector.Length, y = targetVector, x = nodes };
61    }
62  }
63}
Note: See TracBrowser for help on using the repository browser.