[7860] | 1 | #region License Information
|
---|
| 2 | /* HeuristicLab
|
---|
[9456] | 3 | * Copyright (C) 2002-2013 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
|
---|
[7860] | 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;
|
---|
[8598] | 23 | using System.Collections;
|
---|
[7860] | 24 | using System.Collections.Generic;
|
---|
[8180] | 25 | using System.IO;
|
---|
[8192] | 26 | using System.Linq;
|
---|
[8566] | 27 | using HeuristicLab.Common;
|
---|
[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();
|
---|
[9608] | 59 | csvFileParser.Parse(path, csvFileParser.AreColumnNamesInFirstLine(path));
|
---|
[8180] | 60 |
|
---|
[8192] | 61 | Dataset dataset = new Dataset(csvFileParser.VariableNames, csvFileParser.Values);
|
---|
[8566] | 62 | string targetVar = dataset.DoubleVariables.Last();
|
---|
[8192] | 63 |
|
---|
[9989] | 64 | // turn off input variables that are constant in the training partition
|
---|
[8566] | 65 | var allowedInputVars = new List<string>();
|
---|
| 66 | var trainingIndizes = Enumerable.Range(0, (csvFileParser.Rows * 2) / 3);
|
---|
[8877] | 67 | if (trainingIndizes.Count() >= 2) {
|
---|
| 68 | foreach (var variableName in dataset.DoubleVariables) {
|
---|
| 69 | if (dataset.GetDoubleValues(variableName, trainingIndizes).Range() > 0 &&
|
---|
| 70 | variableName != targetVar)
|
---|
| 71 | allowedInputVars.Add(variableName);
|
---|
| 72 | }
|
---|
| 73 | } else {
|
---|
| 74 | allowedInputVars.AddRange(dataset.DoubleVariables.Where(x => !x.Equals(targetVar)));
|
---|
[8566] | 75 | }
|
---|
[8192] | 76 |
|
---|
[8566] | 77 | IRegressionProblemData regressionData = new RegressionProblemData(dataset, allowedInputVars, targetVar);
|
---|
[8192] | 78 |
|
---|
[8566] | 79 | var trainingPartEnd = trainingIndizes.Last();
|
---|
| 80 | regressionData.TrainingPartition.Start = trainingIndizes.First();
|
---|
| 81 | regressionData.TrainingPartition.End = trainingPartEnd;
|
---|
| 82 | regressionData.TestPartition.Start = trainingPartEnd;
|
---|
| 83 | regressionData.TestPartition.End = csvFileParser.Rows;
|
---|
[8192] | 84 |
|
---|
[8566] | 85 | regressionData.Name = Path.GetFileName(path);
|
---|
| 86 |
|
---|
| 87 | return regressionData;
|
---|
[7860] | 88 | }
|
---|
| 89 |
|
---|
[8877] | 90 | protected override IRegressionProblemData ImportData(string path, RegressionImportType type, TableFileParser csvFileParser) {
|
---|
[8598] | 91 | List<IList> values = csvFileParser.Values;
|
---|
| 92 | if (type.Shuffle) {
|
---|
| 93 | values = Shuffle(values);
|
---|
| 94 | }
|
---|
| 95 | Dataset dataset = new Dataset(csvFileParser.VariableNames, values);
|
---|
| 96 |
|
---|
| 97 | // turn of input variables that are constant in the training partition
|
---|
| 98 | var allowedInputVars = new List<string>();
|
---|
[9021] | 99 | int trainingPartEnd = (csvFileParser.Rows * type.TrainingPercentage) / 100;
|
---|
[8601] | 100 | trainingPartEnd = trainingPartEnd > 0 ? trainingPartEnd : 1;
|
---|
[8599] | 101 | var trainingIndizes = Enumerable.Range(0, trainingPartEnd);
|
---|
[8601] | 102 | if (trainingIndizes.Count() >= 2) {
|
---|
| 103 | foreach (var variableName in dataset.DoubleVariables) {
|
---|
| 104 | if (dataset.GetDoubleValues(variableName, trainingIndizes).Range() > 0 &&
|
---|
[8877] | 105 | variableName != type.TargetVariable)
|
---|
[8601] | 106 | allowedInputVars.Add(variableName);
|
---|
| 107 | }
|
---|
| 108 | } else {
|
---|
[8877] | 109 | allowedInputVars.AddRange(dataset.DoubleVariables.Where(x => !x.Equals(type.TargetVariable)));
|
---|
[8598] | 110 | }
|
---|
| 111 |
|
---|
[8877] | 112 | RegressionProblemData regressionData = new RegressionProblemData(dataset, allowedInputVars, type.TargetVariable);
|
---|
[8598] | 113 |
|
---|
[8599] | 114 | regressionData.TrainingPartition.Start = 0;
|
---|
[8598] | 115 | regressionData.TrainingPartition.End = trainingPartEnd;
|
---|
| 116 | regressionData.TestPartition.Start = trainingPartEnd;
|
---|
| 117 | regressionData.TestPartition.End = csvFileParser.Rows;
|
---|
| 118 |
|
---|
| 119 | regressionData.Name = Path.GetFileName(path);
|
---|
| 120 |
|
---|
| 121 | return regressionData;
|
---|
| 122 | }
|
---|
[7860] | 123 | }
|
---|
| 124 | }
|
---|