Free cookie consent management tool by TermsFeed Policy Generator

source: trunk/HeuristicLab.Problems.Instances.DataAnalysis/3.3/TimeSeries/CSV/TimeSeriesPrognosisCSVInstanceProvider.cs @ 16565

Last change on this file since 16565 was 16565, checked in by gkronber, 5 years ago

#2520: merged changes from PersistenceOverhaul branch (r16451:16564) into trunk

File size: 4.6 KB
Line 
1#region License Information
2/* HeuristicLab
3 * Copyright (C) 2002-2019 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;
23using System.Collections.Generic;
24using System.IO;
25using System.Linq;
26using HeuristicLab.Common;
27using HeuristicLab.Problems.DataAnalysis;
28
29namespace HeuristicLab.Problems.Instances.DataAnalysis {
30  public class TimeSeriesPrognosisCSVInstanceProvider : TimeSeriesPrognosisInstanceProvider {
31    public override string Name {
32      get { return "CSV Problem Provider"; }
33    }
34    public override string Description {
35      get {
36        return "";
37      }
38    }
39    public override Uri WebLink {
40      get { return new Uri("http://dev.heuristiclab.com/trac.fcgi/wiki/Documentation/FAQ#DataAnalysisImportFileFormat"); }
41    }
42    public override string ReferencePublication {
43      get { return ""; }
44    }
45
46    public override IEnumerable<IDataDescriptor> GetDataDescriptors() {
47      return new List<IDataDescriptor>();
48    }
49
50    public override ITimeSeriesPrognosisProblemData LoadData(IDataDescriptor descriptor) {
51      throw new NotImplementedException();
52    }
53
54    public override bool CanImportData { get { return true; } }
55
56    public override ITimeSeriesPrognosisProblemData ImportData(string path) {
57      TableFileParser csvFileParser = new TableFileParser();
58      csvFileParser.Parse(path, csvFileParser.AreColumnNamesInFirstLine(path));
59
60      Dataset dataset = new Dataset(csvFileParser.VariableNames, csvFileParser.Values);
61      string targetVar = csvFileParser.VariableNames.Last();
62
63      IEnumerable<string> allowedInputVars = dataset.DoubleVariables.Where(x => !x.Equals(targetVar));
64
65      ITimeSeriesPrognosisProblemData timeSeriesPrognosisData = new TimeSeriesPrognosisProblemData(dataset, allowedInputVars, targetVar);
66
67      int trainingPartEnd = csvFileParser.Rows * 2 / 3;
68      timeSeriesPrognosisData.TrainingPartition.Start = 0;
69      timeSeriesPrognosisData.TrainingPartition.End = trainingPartEnd;
70      timeSeriesPrognosisData.TestPartition.Start = trainingPartEnd;
71      timeSeriesPrognosisData.TestPartition.End = csvFileParser.Rows;
72
73      int pos = path.LastIndexOf('\\');
74      if (pos < 0)
75        timeSeriesPrognosisData.Name = path;
76      else {
77        pos++;
78        timeSeriesPrognosisData.Name = path.Substring(pos, path.Length - pos);
79      }
80      return timeSeriesPrognosisData;
81    }
82
83    protected override ITimeSeriesPrognosisProblemData ImportData(string path, TimeSeriesPrognosisImportType type, TableFileParser csvFileParser) {
84      Dataset dataset = new Dataset(csvFileParser.VariableNames, csvFileParser.Values);
85
86      // turn of input variables that are constant in the training partition
87      var allowedInputVars = new List<string>();
88      int trainingPartEnd = (csvFileParser.Rows * type.TrainingPercentage) / 100;
89      trainingPartEnd = trainingPartEnd > 0 ? trainingPartEnd : 1;
90      var trainingIndizes = Enumerable.Range(0, trainingPartEnd);
91      if (trainingIndizes.Count() >= 2) {
92        foreach (var variableName in dataset.DoubleVariables) {
93          if (dataset.GetDoubleValues(variableName, trainingIndizes).Range() > 0 &&
94            variableName != type.TargetVariable)
95            allowedInputVars.Add(variableName);
96        }
97      } else {
98        allowedInputVars.AddRange(dataset.DoubleVariables.Where(x => !x.Equals(type.TargetVariable)));
99      }
100
101      TimeSeriesPrognosisProblemData timeSeriesPrognosisData = new TimeSeriesPrognosisProblemData(dataset, allowedInputVars, type.TargetVariable);
102
103      timeSeriesPrognosisData.TrainingPartition.Start = 0;
104      timeSeriesPrognosisData.TrainingPartition.End = trainingPartEnd;
105      timeSeriesPrognosisData.TestPartition.Start = trainingPartEnd;
106      timeSeriesPrognosisData.TestPartition.End = csvFileParser.Rows;
107
108      timeSeriesPrognosisData.Name = Path.GetFileName(path);
109
110      return timeSeriesPrognosisData;
111    }
112  }
113}
Note: See TracBrowser for help on using the repository browser.