source: trunk/sources/HeuristicLab.Problems.Instances.DataAnalysis/3.3/DataAnalysisInstanceProvider.cs @ 13414

Last change on this file since 13414 was 13414, checked in by gkronber, 5 years ago

#2071: added progress reporting when importing regression problem data from csv files.

File size: 4.0 KB
Line 
1#region License Information
2/* HeuristicLab
3 * Copyright (C) 2002-2015 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;
24using System.Collections.Generic;
25using System.ComponentModel;
26using System.Drawing;
27using System.Globalization;
28using System.IO;
29using System.Linq;
30using System.Text;
31using HeuristicLab.Problems.DataAnalysis;
32using HeuristicLab.Random;
33
34namespace HeuristicLab.Problems.Instances.DataAnalysis {
35  public abstract class DataAnalysisInstanceProvider<TData, ImportType> : ProblemInstanceProvider<TData>
36    where TData : class, IDataAnalysisProblemData
37    where ImportType : DataAnalysisImportType {
38
39    public event ProgressChangedEventHandler ProgressChanged;
40
41    public TData ImportData(string path, ImportType type, DataAnalysisCSVFormat csvFormat) {
42      TableFileParser csvFileParser = new TableFileParser();
43      long fileSize = new FileInfo(path).Length;
44      csvFileParser.ProgressChanged += (sender, e) => {
45        OnProgressChanged(e / (double)fileSize);
46      };
47      csvFileParser.Parse(path, csvFormat.NumberFormatInfo, csvFormat.DateTimeFormatInfo, csvFormat.Separator, csvFormat.VariableNamesAvailable);
48      return ImportData(path, type, csvFileParser);
49    }
50
51    protected virtual void OnProgressChanged(double d) {
52      var handler = ProgressChanged;
53      if (handler != null)
54        handler(this, new ProgressChangedEventArgs((int)(100*d), null));
55    }
56
57    protected virtual TData ImportData(string path, ImportType type, TableFileParser csvFileParser) {
58      throw new NotSupportedException();
59    }
60
61    protected List<IList> Shuffle(List<IList> values) {
62      int count = values.First().Count;
63      int[] indices = Enumerable.Range(0, count).Shuffle(new FastRandom()).ToArray();
64      List<IList> shuffled = new List<IList>(values.Count);
65      for (int col = 0; col < values.Count; col++) {
66
67        if (values[col] is List<double>)
68          shuffled.Add(new List<double>());
69        else if (values[col] is List<DateTime>)
70          shuffled.Add(new List<DateTime>());
71        else if (values[col] is List<string>)
72          shuffled.Add(new List<string>());
73        else
74          throw new InvalidOperationException();
75
76        for (int i = 0; i < count; i++) {
77          shuffled[col].Add(values[col][indices[i]]);
78        }
79      }
80      return shuffled;
81    }
82
83    public override bool CanExportData {
84      get { return true; }
85    }
86    public override void ExportData(TData instance, string path) {
87      var strBuilder = new StringBuilder();
88      var colSep = CultureInfo.CurrentCulture.TextInfo.ListSeparator;
89      foreach (var variable in instance.Dataset.VariableNames) {
90        strBuilder.Append(variable.Replace(colSep, String.Empty) + colSep);
91      }
92      strBuilder.Remove(strBuilder.Length - colSep.Length, colSep.Length);
93      strBuilder.AppendLine();
94
95      var dataset = instance.Dataset;
96
97      for (int i = 0; i < dataset.Rows; i++) {
98        for (int j = 0; j < dataset.Columns; j++) {
99          if (j > 0) strBuilder.Append(colSep);
100          strBuilder.Append(dataset.GetValue(i, j));
101        }
102        strBuilder.AppendLine();
103      }
104
105      using (var writer = new StreamWriter(path)) {
106        writer.Write(strBuilder);
107      }
108    }
109  }
110}
Note: See TracBrowser for help on using the repository browser.