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 static class LinearRegressionUtil {
|
---|
28 | public static double[,] PrepareInputMatrix(Dataset dataset, string targetVariable, IEnumerable<string> allowedInputVariables, int start, int end) {
|
---|
29 | List<int> allowedRows = CalculateAllowedRows(dataset, targetVariable, allowedInputVariables, start, end);
|
---|
30 |
|
---|
31 | double[,] matrix = new double[allowedRows.Count, allowedInputVariables.Count() + 1];
|
---|
32 | for (int row = 0; row < allowedRows.Count; row++) {
|
---|
33 | int col = 0;
|
---|
34 | foreach (string column in allowedInputVariables) {
|
---|
35 | matrix[row, col] = dataset[column, row];
|
---|
36 | col++;
|
---|
37 | }
|
---|
38 | matrix[row, allowedInputVariables.Count()] = dataset[targetVariable, row];
|
---|
39 | }
|
---|
40 | return matrix;
|
---|
41 | }
|
---|
42 |
|
---|
43 | private static List<int> CalculateAllowedRows(Dataset dataset, string targetVariable, IEnumerable<string> allowedInputVariables, int start, int end) {
|
---|
44 | List<int> allowedRows = new List<int>();
|
---|
45 | bool add = false;
|
---|
46 |
|
---|
47 | for (int row = start; row < end; row++) {
|
---|
48 | add = true;
|
---|
49 | foreach (string column in allowedInputVariables) {
|
---|
50 | double value = dataset[column, row];
|
---|
51 | if (double.IsInfinity(value) ||
|
---|
52 | double.IsNaN(value))
|
---|
53 | add = false;
|
---|
54 | }
|
---|
55 | if (double.IsNaN(dataset[targetVariable, row]))
|
---|
56 | add = false;
|
---|
57 | if (add)
|
---|
58 | allowedRows.Add(row);
|
---|
59 | add = true;
|
---|
60 | }
|
---|
61 | return allowedRows;
|
---|
62 | }
|
---|
63 | }
|
---|
64 | }
|
---|