[7860] | 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 |
|
---|
| 22 | using System;
|
---|
| 23 | using System.Collections.Generic;
|
---|
[8530] | 24 | using System.Globalization;
|
---|
[8180] | 25 | using System.IO;
|
---|
[8192] | 26 | using System.Linq;
|
---|
[8180] | 27 | using System.Text;
|
---|
[7860] | 28 | using HeuristicLab.Problems.DataAnalysis;
|
---|
[8192] | 29 |
|
---|
[7860] | 30 | namespace HeuristicLab.Problems.Instances.DataAnalysis {
|
---|
| 31 | public class RegressionCSVInstanceProvider : RegressionInstanceProvider {
|
---|
| 32 | public override string Name {
|
---|
[8211] | 33 | get { return "CSV File"; }
|
---|
[7860] | 34 | }
|
---|
| 35 | public override string Description {
|
---|
| 36 | get {
|
---|
| 37 | return "";
|
---|
| 38 | }
|
---|
| 39 | }
|
---|
| 40 | public override Uri WebLink {
|
---|
| 41 | get { return new Uri("http://dev.heuristiclab.com/trac/hl/core/wiki/UsersFAQ#DataAnalysisImportFileFormat"); }
|
---|
| 42 | }
|
---|
| 43 | public override string ReferencePublication {
|
---|
| 44 | get { return ""; }
|
---|
| 45 | }
|
---|
| 46 |
|
---|
[8192] | 47 | public override IEnumerable<IDataDescriptor> GetDataDescriptors() {
|
---|
| 48 | return new List<IDataDescriptor>();
|
---|
| 49 | }
|
---|
| 50 | public override IRegressionProblemData LoadData(IDataDescriptor descriptor) {
|
---|
| 51 | throw new NotImplementedException();
|
---|
| 52 | }
|
---|
| 53 |
|
---|
| 54 | public override bool CanImportData {
|
---|
[8180] | 55 | get { return true; }
|
---|
| 56 | }
|
---|
[8192] | 57 | public override IRegressionProblemData ImportData(string path) {
|
---|
| 58 | TableFileParser csvFileParser = new TableFileParser();
|
---|
| 59 | csvFileParser.Parse(path);
|
---|
[8180] | 60 |
|
---|
[8192] | 61 | Dataset dataset = new Dataset(csvFileParser.VariableNames, csvFileParser.Values);
|
---|
| 62 | string targetVar = csvFileParser.VariableNames.Where(x => dataset.DoubleVariables.Contains(x)).Last();
|
---|
| 63 |
|
---|
| 64 | IEnumerable<string> allowedInputVars = dataset.DoubleVariables.Where(x => !x.Equals(targetVar));
|
---|
| 65 |
|
---|
| 66 | IRegressionProblemData regData = new RegressionProblemData(dataset, allowedInputVars, targetVar);
|
---|
| 67 |
|
---|
| 68 | int trainingPartEnd = csvFileParser.Rows * 2 / 3;
|
---|
| 69 | regData.TrainingPartition.Start = 0;
|
---|
| 70 | regData.TrainingPartition.End = trainingPartEnd;
|
---|
| 71 | regData.TestPartition.Start = trainingPartEnd;
|
---|
| 72 | regData.TestPartition.End = csvFileParser.Rows;
|
---|
| 73 |
|
---|
| 74 | int pos = path.LastIndexOf('\\');
|
---|
| 75 | if (pos < 0)
|
---|
| 76 | regData.Name = path;
|
---|
| 77 | else {
|
---|
| 78 | pos++;
|
---|
| 79 | regData.Name = path.Substring(pos, path.Length - pos);
|
---|
| 80 | }
|
---|
| 81 | return regData;
|
---|
[7860] | 82 | }
|
---|
| 83 |
|
---|
[8192] | 84 | public override bool CanExportData {
|
---|
| 85 | get { return true; }
|
---|
| 86 | }
|
---|
| 87 | public override void ExportData(IRegressionProblemData instance, string path) {
|
---|
[8530] | 88 | var strBuilder = new StringBuilder();
|
---|
[8180] | 89 |
|
---|
| 90 | foreach (var variable in instance.InputVariables) {
|
---|
[8530] | 91 | strBuilder.Append(variable + CultureInfo.CurrentCulture.TextInfo.ListSeparator);
|
---|
[8180] | 92 | }
|
---|
[8530] | 93 | strBuilder.Remove(strBuilder.Length - CultureInfo.CurrentCulture.TextInfo.ListSeparator.Length, CultureInfo.CurrentCulture.TextInfo.ListSeparator.Length);
|
---|
[8180] | 94 | strBuilder.AppendLine();
|
---|
| 95 |
|
---|
[8530] | 96 | var dataset = instance.Dataset;
|
---|
[8180] | 97 |
|
---|
| 98 | for (int i = 0; i < dataset.Rows; i++) {
|
---|
| 99 | for (int j = 0; j < dataset.Columns; j++) {
|
---|
[8530] | 100 | if (j > 0) strBuilder.Append(CultureInfo.CurrentCulture.TextInfo.ListSeparator);
|
---|
| 101 | strBuilder.Append(dataset.GetValue(i, j));
|
---|
[8180] | 102 | }
|
---|
| 103 | strBuilder.AppendLine();
|
---|
| 104 | }
|
---|
| 105 |
|
---|
[8530] | 106 | using (var writer = new StreamWriter(path)) {
|
---|
[8180] | 107 | writer.Write(strBuilder);
|
---|
| 108 | }
|
---|
| 109 | }
|
---|
[7860] | 110 | }
|
---|
| 111 | }
|
---|