Changeset 17401 for branches/3040_VectorBasedGP/HeuristicLab.Problems.Instances.DataAnalysis/3.3/Classification

Timestamp:

01/16/20 12:34:45 (5 years ago)

Author:

pfleck

Message:

#3040 Added parser for new benchmark data but did not commit the data yet (too large)

Location:

branches/3040_VectorBasedGP/HeuristicLab.Problems.Instances.DataAnalysis/3.3/Classification/TimeSeries

Files:

• . (added)
• TimeSeriesDataDescriptor.cs (copied) (copied from branches/3040_VectorBasedGP/HeuristicLab.Problems.Instances.DataAnalysis/3.3/Classification/UCI/UCIDataDescriptor.cs) (1 diff)
• TimeSeriesInstanceProvider.cs (copied) (copied from branches/3040_VectorBasedGP/HeuristicLab.Problems.Instances.DataAnalysis/3.3/Classification/UCI/UCIInstanceProvider.cs) (1 diff)
• TimeSeriesMultivariateInstanceProvider.cs (copied) (copied from branches/3040_VectorBasedGP/HeuristicLab.Problems.Instances.DataAnalysis/3.3/Classification/UCI/UCIInstanceProvider.cs) (1 diff)
• TimeSeriesUnivariateInstanceProvider.cs (copied) (copied from branches/3040_VectorBasedGP/HeuristicLab.Problems.Instances.DataAnalysis/3.3/Classification/UCI/UCIInstanceProvider.cs) (1 diff)

branches/3040_VectorBasedGP/HeuristicLab.Problems.Instances.DataAnalysis/3.3/Classification/TimeSeries/TimeSeriesDataDescriptor.cs

@@ -20 +20 @@
 #endregion
 
-using System;
+namespace HeuristicLab.Problems.Instances.DataAnalysis {
+  public class TimeSeriesDataDescriptor : IDataDescriptor {
+    public string Name { get; }
+    public string Description { get { return string.Empty; } }
 
-namespace HeuristicLab.Problems.Instances.DataAnalysis {
-  public abstract class UCIDataDescriptor : ResourceClassificationDataDescriptor {
-    public override string Name { get { return String.Format("{0}, {1}, {2}", Filename, Donor, Year); } }
-    public abstract string Filename { get; }
-    public abstract string Donor { get; }
-    public abstract int Year { get; }
+    internal string TrainingEntryName { get; }
+    internal string TestEntryName { get; }
+
+    public TimeSeriesDataDescriptor(string name, string trainingEntryName, string testEntryName) {
+      Name = name;
+      TrainingEntryName = trainingEntryName;
+      TestEntryName = testEntryName;
+    }
   }
 }

branches/3040_VectorBasedGP/HeuristicLab.Problems.Instances.DataAnalysis/3.3/Classification/TimeSeries/TimeSeriesInstanceProvider.cs

@@ -21 +21 @@
 
 using System;
+using System.Collections;
 using System.Collections.Generic;
+using System.Collections.ObjectModel;
+using System.Diagnostics;
+using System.Globalization;
 using System.IO;
 using System.IO.Compression;
 using System.Linq;
+using HeuristicLab.Problems.DataAnalysis;
 
 namespace HeuristicLab.Problems.Instances.DataAnalysis {
-  public class UCIInstanceProvider : ResourceClassificationInstanceProvider {
-    public override string Name {
-      get { return "UCI Problems"; }
-    }
+  public abstract class TimeSeriesInstanceProvider : ResourceClassificationInstanceProvider {
+    //public override string Name {
+    //  get { return "TimeSeries (Univariate) Problems"; }
+    //}
     public override string Description {
-      get {
-        return "";
-      }
+      get { return "UEA & UCR TimeSeries Problems"; }
     }
     public override Uri WebLink {
-      get { return new Uri("http://archive.ics.uci.edu/ml/datasets.html"); }
+      get { return new Uri("http://www.timeseriesclassification.com/"); }
     }
     public override string ReferencePublication {
-      get { return ""; }
+      get { return "Anthony Bagnall, Jason Lines, William Vickers and Eamonn Keogh, The UEA & UCR Time Series Classification Repository, www.timeseriesclassification.com"; }
     }
 
-    protected override string FileName { get { return "UCI"; } }
+    public override IClassificationProblemData LoadData(IDataDescriptor id) {
+      var descriptor = (TimeSeriesDataDescriptor)id;
+      using (var instancesZipFile = OpenZipArchive()) {
+        var trainingEntry = instancesZipFile.GetEntry(descriptor.TrainingEntryName);
+        var testEntry = instancesZipFile.GetEntry(descriptor.TestEntryName);
 
-    public override IEnumerable<IDataDescriptor> GetDataDescriptors() {
-      List<UCIDataDescriptor> descriptorList = new List<UCIDataDescriptor>();
-      descriptorList.Add(new Iris());
-      descriptorList.Add(new Mammography());
-      descriptorList.Add(new Parkinsons());
-      descriptorList.Add(new Thyroid());
-      descriptorList.Add(new Vertebral_3C());
-      descriptorList.Add(new Wine());
-      descriptorList.Add(new WisconsinDiagnosticBreastCancer());
-      var solutionsArchiveName = GetResourceName(FileName + @"\.zip");
-      if (!String.IsNullOrEmpty(solutionsArchiveName)) {
-        using (var solutionsZipFile = new ZipArchive(GetType().Assembly.GetManifestResourceStream(solutionsArchiveName), ZipArchiveMode.Read)) {
-          IList<string> entries = new List<string>();
-          foreach (var curEntry in solutionsZipFile.Entries) {
-            entries.Add(curEntry.Name);
-          }
-          foreach (var entry in entries.OrderBy(x => x)) {
-            string filename = Path.GetFileNameWithoutExtension(entry);
-            UCIDataDescriptor desc = descriptorList.Where(x => x.Filename.Equals(filename)).FirstOrDefault();
-            if (desc != null) {
-              desc.ResourceName = entry;
-              yield return desc;
-            } else
-              throw new ArgumentNullException("No Descriptor could be found for this entry.");
-          }
+        if (trainingEntry == null || testEntry == null) {
+          throw new InvalidOperationException("The training or test entry could not be found in the archive.");
+        }
+
+        using (var trainingReader = new StreamReader(trainingEntry.Open()))
+        using (var testReader = new StreamReader(testEntry.Open())) {
+          ParseMetadata(trainingReader, out var inputVariables, out string targetVariable);
+          ParseMetadata(testReader, out _, out _); // ignore outputs
+
+          // Read data
+          var inputsData = new List<DoubleVector>[inputVariables.Count];
+          for (int i = 0; i < inputsData.Length; i++) inputsData[i] = new List<DoubleVector>();
+          var targetData = new List<double>();
+          ReadData(trainingReader, inputsData, targetData, out int numTrainingRows);
+          ReadData(testReader, inputsData, targetData, out int numTestRows);
+
+          // Build dataset
+          var dataset = new Dataset(
+            inputVariables.Concat(new[] { targetVariable }),
+            inputsData.Cast<IList>().Concat(new[] { targetData })
+          );
+          Debug.Assert(dataset.Rows == numTrainingRows + numTestRows);
+          Debug.Assert(dataset.Columns == inputVariables.Count + 1);
+
+          // Build problem data
+          var problemData = new ClassificationProblemData(dataset, inputVariables, targetVariable) {
+            Name = descriptor.Name
+          };
+          problemData.TrainingPartition.Start = 0;
+          problemData.TrainingPartition.End = numTrainingRows;
+          problemData.TestPartition.Start = numTrainingRows;
+          problemData.TestPartition.End = numTrainingRows + numTestRows;
+
+          return problemData;
         }
       }
     }
+
+    private static void ParseMetadata(StreamReader reader, out List<string> inputVariables, out string targetVariable) {
+      int nrOfInputs = 0;
+      bool dataStart = false;
+      while (!reader.EndOfStream && !dataStart) {
+        var line = reader.ReadLine();
+        if (line.StartsWith("#")) {
+          // Comment
+        } else if (line.StartsWith("@")) {
+          var splits = line.Split(' ');
+          var type = splits.First();
+          var arguments = splits.Skip(1).ToList();
+          switch (type.ToLowerInvariant()) {
+            case "@univariate":
+              bool univariate = bool.Parse(arguments[0]);
+              if (univariate)
+                nrOfInputs = 1;
+              break;
+            case "@dimensions":
+              int dimensions = int.Parse(arguments[0]);
+              nrOfInputs = dimensions;
+              break;
+            case "@data":
+              dataStart = true;
+              break;
+          }
+        } else {
+          throw new InvalidOperationException("A data section already occurred within metadata section.");
+        }
+      }
+
+      int digits = Math.Max((int)Math.Log10(nrOfInputs - 1) + 1, 1);
+      inputVariables = Enumerable.Range(0, nrOfInputs)
+        .Select(i => "X" + i.ToString("D" + digits))
+        .ToList();
+
+      targetVariable = "Y";
+    }
+
+    private static void ReadData(StreamReader reader, List<DoubleVector>[] inputsData, List<double> targetData, out int count) {
+      count = 0;
+      while (!reader.EndOfStream) {
+        var line = reader.ReadLine();
+        var variables = line.Split(':');
+
+        // parse all except last, which is the non-vector target
+        for (int i = 0; i < variables.Length - 1; i++) {
+          var variable = variables[i];
+          var numbers = variable
+            .Split(',')
+            .Select(d => double.Parse(d, CultureInfo.InvariantCulture))
+            .ToList();
+          inputsData[i].Add(new DoubleVector(numbers));
+        }
+
+        var target = double.Parse(variables[variables.Length - 1], CultureInfo.InvariantCulture);
+        targetData.Add(target);
+
+        count++;
+      }
+    }
+
+    public override IEnumerable<IDataDescriptor> GetDataDescriptors() {
+      using (var instancesZipFile = OpenZipArchive()) {
+        var instances = GroupEntriesByInstance(instancesZipFile.Entries);
+        var descriptors = instances.Select(instance => CreateDescriptor(instance.Key, instance.Value));
+
+        return descriptors.ToList();
+      }
+    }
+
+    private ZipArchive OpenZipArchive() {
+      var instanceArchiveName = GetResourceName(FileName + @"\.zip");
+      return new ZipArchive(GetType().Assembly.GetManifestResourceStream(instanceArchiveName), ZipArchiveMode.Read);
+    }
+
+    private static IDictionary<string, List<ZipArchiveEntry>> GroupEntriesByInstance(ReadOnlyCollection<ZipArchiveEntry> entries) {
+      var topLevelEntries = entries.Where(entry => string.IsNullOrEmpty(entry.Name)).ToList();
+
+      return topLevelEntries.ToDictionary(
+        entry => Path.GetDirectoryName(entry.FullName),
+        entry => entries.Except(topLevelEntries).Where(subEntry => subEntry.FullName.StartsWith(entry.FullName)).ToList());
+    }
+
+    private static TimeSeriesDataDescriptor CreateDescriptor(string name, List<ZipArchiveEntry> subEntries) {
+      var trainingEntry = subEntries.Single(entry => entry.Name.EndsWith("_TRAIN.ts"));
+      var testEntry = subEntries.Single(entry => entry.Name.EndsWith("_TEST.ts"));
+      return new TimeSeriesDataDescriptor(name, trainingEntry.FullName, testEntry.FullName);
+    }
   }
 }

branches/3040_VectorBasedGP/HeuristicLab.Problems.Instances.DataAnalysis/3.3/Classification/TimeSeries/TimeSeriesMultivariateInstanceProvider.cs

@@ -20 +20 @@
 #endregion
 
-using System;
-using System.Collections.Generic;
-using System.IO;
-using System.IO.Compression;
-using System.Linq;
 
 namespace HeuristicLab.Problems.Instances.DataAnalysis {
-  public class UCIInstanceProvider : ResourceClassificationInstanceProvider {
+  public class TimeSeriesMultivariateInstanceProvider : TimeSeriesInstanceProvider {
     public override string Name {
-      get { return "UCI Problems"; }
-    }
-    public override string Description {
-      get {
-        return "";
-      }
-    }
-    public override Uri WebLink {
-      get { return new Uri("http://archive.ics.uci.edu/ml/datasets.html"); }
-    }
-    public override string ReferencePublication {
-      get { return ""; }
+      get { return "TimeSeries (Multivariate)"; }
     }
 
-    protected override string FileName { get { return "UCI"; } }
-
-    public override IEnumerable<IDataDescriptor> GetDataDescriptors() {
-      List<UCIDataDescriptor> descriptorList = new List<UCIDataDescriptor>();
-      descriptorList.Add(new Iris());
-      descriptorList.Add(new Mammography());
-      descriptorList.Add(new Parkinsons());
-      descriptorList.Add(new Thyroid());
-      descriptorList.Add(new Vertebral_3C());
-      descriptorList.Add(new Wine());
-      descriptorList.Add(new WisconsinDiagnosticBreastCancer());
-      var solutionsArchiveName = GetResourceName(FileName + @"\.zip");
-      if (!String.IsNullOrEmpty(solutionsArchiveName)) {
-        using (var solutionsZipFile = new ZipArchive(GetType().Assembly.GetManifestResourceStream(solutionsArchiveName), ZipArchiveMode.Read)) {
-          IList<string> entries = new List<string>();
-          foreach (var curEntry in solutionsZipFile.Entries) {
-            entries.Add(curEntry.Name);
-          }
-          foreach (var entry in entries.OrderBy(x => x)) {
-            string filename = Path.GetFileNameWithoutExtension(entry);
-            UCIDataDescriptor desc = descriptorList.Where(x => x.Filename.Equals(filename)).FirstOrDefault();
-            if (desc != null) {
-              desc.ResourceName = entry;
-              yield return desc;
-            } else
-              throw new ArgumentNullException("No Descriptor could be found for this entry.");
-          }
-        }
-      }
-    }
+    protected override string FileName { get { return "TimeSeriesMultivariate"; } }
   }
 }

branches/3040_VectorBasedGP/HeuristicLab.Problems.Instances.DataAnalysis/3.3/Classification/TimeSeries/TimeSeriesUnivariateInstanceProvider.cs

@@ -20 +20 @@
 #endregion
 
-using System;
-using System.Collections.Generic;
-using System.IO;
-using System.IO.Compression;
-using System.Linq;
 
 namespace HeuristicLab.Problems.Instances.DataAnalysis {
-  public class UCIInstanceProvider : ResourceClassificationInstanceProvider {
+  public class TimeSeriesUnivariateInstanceProvider : TimeSeriesInstanceProvider {
     public override string Name {
-      get { return "UCI Problems"; }
-    }
-    public override string Description {
-      get {
-        return "";
-      }
-    }
-    public override Uri WebLink {
-      get { return new Uri("http://archive.ics.uci.edu/ml/datasets.html"); }
-    }
-    public override string ReferencePublication {
-      get { return ""; }
+      get { return "TimeSeries (Univariate)"; }
     }
 
-    protected override string FileName { get { return "UCI"; } }
-
-    public override IEnumerable<IDataDescriptor> GetDataDescriptors() {
-      List<UCIDataDescriptor> descriptorList = new List<UCIDataDescriptor>();
-      descriptorList.Add(new Iris());
-      descriptorList.Add(new Mammography());
-      descriptorList.Add(new Parkinsons());
-      descriptorList.Add(new Thyroid());
-      descriptorList.Add(new Vertebral_3C());
-      descriptorList.Add(new Wine());
-      descriptorList.Add(new WisconsinDiagnosticBreastCancer());
-      var solutionsArchiveName = GetResourceName(FileName + @"\.zip");
-      if (!String.IsNullOrEmpty(solutionsArchiveName)) {
-        using (var solutionsZipFile = new ZipArchive(GetType().Assembly.GetManifestResourceStream(solutionsArchiveName), ZipArchiveMode.Read)) {
-          IList<string> entries = new List<string>();
-          foreach (var curEntry in solutionsZipFile.Entries) {
-            entries.Add(curEntry.Name);
-          }
-          foreach (var entry in entries.OrderBy(x => x)) {
-            string filename = Path.GetFileNameWithoutExtension(entry);
-            UCIDataDescriptor desc = descriptorList.Where(x => x.Filename.Equals(filename)).FirstOrDefault();
-            if (desc != null) {
-              desc.ResourceName = entry;
-              yield return desc;
-            } else
-              throw new ArgumentNullException("No Descriptor could be found for this entry.");
-          }
-        }
-      }
-    }
+    protected override string FileName { get { return "TimeSeriesUnivariate"; } }
   }
 }