[5624] | 1 | #region License Information
|
---|
| 2 | /* HeuristicLab
|
---|
| 3 | * Copyright (C) 2002-2011 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 |
|
---|
| 22 | using System.Collections.Generic;
|
---|
| 23 | using System.Linq;
|
---|
| 24 | using HeuristicLab.Problems.DataAnalysis;
|
---|
| 25 |
|
---|
| 26 | namespace HeuristicLab.Algorithms.DataAnalysis {
|
---|
| 27 | public class SupportVectorMachineUtil {
|
---|
| 28 | /// <summary>
|
---|
| 29 | /// Transforms <paramref name="problemData"/> into a data structure as needed by libSVM.
|
---|
| 30 | /// </summary>
|
---|
| 31 | /// <param name="problemData">The problem data to transform</param>
|
---|
| 32 | /// <param name="rowIndices">The rows of the dataset that should be contained in the resulting SVM-problem</param>
|
---|
| 33 | /// <returns>A problem data type that can be used to train a support vector machine.</returns>
|
---|
| 34 | public static SVM.Problem CreateSvmProblem(Dataset dataset, string targetVariable, IEnumerable<string> inputVariables, IEnumerable<int> rowIndices) {
|
---|
| 35 | double[] targetVector =
|
---|
| 36 | dataset.GetEnumeratedVariableValues(targetVariable, rowIndices)
|
---|
| 37 | .ToArray();
|
---|
| 38 |
|
---|
| 39 | SVM.Node[][] nodes = new SVM.Node[targetVector.Length][];
|
---|
| 40 | List<SVM.Node> tempRow;
|
---|
| 41 | int maxNodeIndex = 0;
|
---|
| 42 | int svmProblemRowIndex = 0;
|
---|
[6002] | 43 | List<string> inputVariablesList = inputVariables.ToList();
|
---|
[5624] | 44 | foreach (int row in rowIndices) {
|
---|
| 45 | tempRow = new List<SVM.Node>();
|
---|
[6002] | 46 | int colIndex = 1; // make sure the smallest node index for SVM = 1
|
---|
| 47 | foreach (var inputVariable in inputVariablesList) {
|
---|
| 48 | double value = dataset[row, dataset.GetVariableIndex(inputVariable)];
|
---|
| 49 | // SVM also works with missing values
|
---|
| 50 | // => don't add NaN values in the dataset to the sparse SVM matrix representation
|
---|
[5624] | 51 | if (!double.IsNaN(value)) {
|
---|
[6002] | 52 | tempRow.Add(new SVM.Node(colIndex, value)); // nodes must be sorted in ascending ordered by column index
|
---|
| 53 | if (colIndex > maxNodeIndex) maxNodeIndex = colIndex;
|
---|
[5624] | 54 | }
|
---|
[6002] | 55 | colIndex++;
|
---|
[5624] | 56 | }
|
---|
[6002] | 57 | nodes[svmProblemRowIndex++] = tempRow.ToArray();
|
---|
[5624] | 58 | }
|
---|
| 59 |
|
---|
| 60 | return new SVM.Problem(targetVector.Length, targetVector, nodes, maxNodeIndex);
|
---|
| 61 | }
|
---|
| 62 | }
|
---|
| 63 | }
|
---|