[7849] | 1 | #region License Information
|
---|
| 2 | /* HeuristicLab
|
---|
[16453] | 3 | * Copyright (C) 2002-2019 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
|
---|
[7849] | 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.Globalization;
|
---|
| 24 | using System.IO;
|
---|
[11650] | 25 | using System.IO.Compression;
|
---|
[7849] | 26 | using System.Linq;
|
---|
| 27 | using System.Reflection;
|
---|
| 28 | using System.Text.RegularExpressions;
|
---|
| 29 | using HeuristicLab.Problems.DataAnalysis;
|
---|
| 30 |
|
---|
| 31 | namespace HeuristicLab.Problems.Instances.DataAnalysis {
|
---|
| 32 | public abstract class ResourceClassificationInstanceProvider : ClassificationInstanceProvider {
|
---|
| 33 |
|
---|
| 34 | protected abstract string FileName { get; }
|
---|
| 35 |
|
---|
| 36 | public override IClassificationProblemData LoadData(IDataDescriptor id) {
|
---|
| 37 | var descriptor = (ResourceClassificationDataDescriptor)id;
|
---|
| 38 |
|
---|
| 39 | var instanceArchiveName = GetResourceName(FileName + @"\.zip");
|
---|
[11650] | 40 | using (var instancesZipFile = new ZipArchive(GetType().Assembly.GetManifestResourceStream(instanceArchiveName), ZipArchiveMode.Read)) {
|
---|
[7849] | 41 | var entry = instancesZipFile.GetEntry(descriptor.ResourceName);
|
---|
| 42 | NumberFormatInfo numberFormat;
|
---|
| 43 | DateTimeFormatInfo dateFormat;
|
---|
| 44 | char separator;
|
---|
[11650] | 45 | using (Stream stream = entry.Open()) {
|
---|
[7849] | 46 | TableFileParser.DetermineFileFormat(stream, out numberFormat, out dateFormat, out separator);
|
---|
| 47 | }
|
---|
| 48 |
|
---|
[7851] | 49 | TableFileParser csvFileParser = new TableFileParser();
|
---|
[11650] | 50 | using (Stream stream = entry.Open()) {
|
---|
[9610] | 51 | csvFileParser.Parse(stream, numberFormat, dateFormat, separator, true);
|
---|
[7849] | 52 | }
|
---|
[7851] | 53 |
|
---|
| 54 | Dataset dataset = new Dataset(csvFileParser.VariableNames, csvFileParser.Values);
|
---|
[9208] | 55 | if (!descriptor.CheckVariableNames(csvFileParser.VariableNames)) {
|
---|
| 56 | throw new ArgumentException("Parsed file contains variables which are not in the descriptor.");
|
---|
| 57 | }
|
---|
[7851] | 58 |
|
---|
[9208] | 59 | return descriptor.GenerateClassificationData(dataset);
|
---|
[7849] | 60 | }
|
---|
| 61 | }
|
---|
| 62 |
|
---|
| 63 | protected virtual string GetResourceName(string fileName) {
|
---|
| 64 | return Assembly.GetExecutingAssembly().GetManifestResourceNames()
|
---|
| 65 | .Where(x => Regex.Match(x, @".*\.Data\." + fileName).Success).SingleOrDefault();
|
---|
| 66 | }
|
---|
| 67 | }
|
---|
| 68 | }
|
---|