Changeset 9363 for branches/OaaS/HeuristicLab.Problems.Instances.DataAnalysis/3.3/Clustering

Timestamp:

04/16/13 13:13:41 (12 years ago)

Author:

spimming

Message:

#1888:

• Merged revisions from trunk

Location:

branches/OaaS

Files:

• . (modified) (2 props)
• HeuristicLab.Problems.Instances.DataAnalysis (modified) (1 prop)
• HeuristicLab.Problems.Instances.DataAnalysis/3.3/Clustering/CSV/ClusteringCSVInstanceProvider.cs (modified) (2 diffs)
• HeuristicLab.Problems.Instances.DataAnalysis/3.3/Clustering/ClusteringInstanceProvider.cs (modified) (1 diff)

branches/OaaS

@@ -21 +21 @@
 protoc.exe
 _ReSharper.HeuristicLab 3.3 Tests
+Google.ProtocolBuffers-2.4.1.473.dll
 packages

@@ -21 +21 @@
 protoc.exe
 _ReSharper.HeuristicLab 3.3 Tests
+Google.ProtocolBuffers-2.4.1.473.dll
 packages

branches/OaaS/HeuristicLab.Problems.Instances.DataAnalysis/3.3/Clustering/CSV/ClusteringCSVInstanceProvider.cs

@@ -21 +21 @@
 
 using System;
+using System.Collections;
 using System.Collections.Generic;
 using System.IO;
-using System.Text;
+using System.Linq;
+using HeuristicLab.Common;
 using HeuristicLab.Problems.DataAnalysis;
 
@@ -56 +58 @@
     public override IClusteringProblemData ImportData(string path) {
       var csvFileParser = new TableFileParser();
-
       csvFileParser.Parse(path);
 
-      var dataset = new Dataset(csvFileParser.VariableNames, csvFileParser.Values);
-      var claData = new ClusteringProblemData(dataset, dataset.DoubleVariables);
+      Dataset dataset = new Dataset(csvFileParser.VariableNames, csvFileParser.Values);
+      string targetVar = dataset.DoubleVariables.Last();
 
-      int trainingPartEnd = csvFileParser.Rows * 2 / 3;
-      claData.TrainingPartition.Start = 0;
-      claData.TrainingPartition.End = trainingPartEnd;
-      claData.TestPartition.Start = trainingPartEnd;
-      claData.TestPartition.End = csvFileParser.Rows;
-      int pos = path.LastIndexOf('\\');
-      if (pos < 0)
-        claData.Name = path;
-      else {
-        pos++;
-        claData.Name = path.Substring(pos, path.Length - pos);
+      // turn of input variables that are constant in the training partition
+      var allowedInputVars = new List<string>();
+      var trainingIndizes = Enumerable.Range(0, (csvFileParser.Rows * 2) / 3);
+      if (trainingIndizes.Count() >= 2) {
+        foreach (var variableName in dataset.DoubleVariables) {
+          if (dataset.GetDoubleValues(variableName, trainingIndizes).Range() > 0 &&
+            variableName != targetVar)
+            allowedInputVars.Add(variableName);
+        }
+      } else {
+        allowedInputVars.AddRange(dataset.DoubleVariables.Where(x => !x.Equals(targetVar)));
       }
 
-      return claData;
+      ClusteringProblemData clusteringData = new ClusteringProblemData(dataset, allowedInputVars);
+
+      int trainingPartEnd = trainingIndizes.Last();
+      clusteringData.TrainingPartition.Start = trainingIndizes.First();
+      clusteringData.TrainingPartition.End = trainingPartEnd;
+      clusteringData.TestPartition.Start = trainingPartEnd;
+      clusteringData.TestPartition.End = csvFileParser.Rows;
+
+      clusteringData.Name = Path.GetFileName(path);
+
+      return clusteringData;
     }
 
-    public override bool CanExportData {
-      get { return true; }
-    }
-    public override void ExportData(IClusteringProblemData instance, string path) {
-      var strBuilder = new StringBuilder();
-
-      foreach (var variable in instance.InputVariables) {
-        strBuilder.Append(variable + ";");
-      }
-      strBuilder.Remove(strBuilder.Length - 1, 1);
-      strBuilder.AppendLine();
-
-      var dataset = instance.Dataset;
-
-      for (int i = 0; i < dataset.Rows; i++) {
-        for (int j = 0; j < dataset.Columns; j++) {
-          strBuilder.Append(dataset.GetValue(i, j) + ";");
-        }
-        strBuilder.Remove(strBuilder.Length - 1, 1);
-        strBuilder.AppendLine();
+    protected override IClusteringProblemData ImportData(string path, DataAnalysisImportType type, TableFileParser csvFileParser) {
+      List<IList> values = csvFileParser.Values;
+      if (type.Shuffle) {
+        values = Shuffle(values);
       }
 
-      using (var writer = new StreamWriter(path)) {
-        writer.Write(strBuilder);
+      Dataset dataset = new Dataset(csvFileParser.VariableNames, values);
+      string targetVar = dataset.DoubleVariables.Last();
+
+      // turn of input variables that are constant in the training partition
+      var allowedInputVars = new List<string>();
+      int trainingPartEnd = (csvFileParser.Rows * type.TrainingPercentage) / 100;
+      var trainingIndizes = Enumerable.Range(0, trainingPartEnd);
+      if (trainingIndizes.Count() >= 2) {
+        foreach (var variableName in dataset.DoubleVariables) {
+          if (dataset.GetDoubleValues(variableName, trainingIndizes).Range() > 0 &&
+            variableName != targetVar)
+            allowedInputVars.Add(variableName);
+        }
+      } else {
+        allowedInputVars.AddRange(dataset.DoubleVariables.Where(x => !x.Equals(targetVar)));
       }
+
+      ClusteringProblemData clusteringData = new ClusteringProblemData(dataset, allowedInputVars);
+
+      clusteringData.TrainingPartition.Start = 0;
+      clusteringData.TrainingPartition.End = trainingPartEnd;
+      clusteringData.TestPartition.Start = trainingPartEnd;
+      clusteringData.TestPartition.End = csvFileParser.Rows;
+
+      clusteringData.Name = Path.GetFileName(path);
+
+      return clusteringData;
     }
   }

branches/OaaS/HeuristicLab.Problems.Instances.DataAnalysis/3.3/Clustering/ClusteringInstanceProvider.cs

@@ -23 +23 @@
 
 namespace HeuristicLab.Problems.Instances.DataAnalysis {
-  public abstract class ClusteringInstanceProvider : ProblemInstanceProvider<IClusteringProblemData> {
+  public abstract class ClusteringInstanceProvider : DataAnalysisInstanceProvider<IClusteringProblemData, DataAnalysisImportType> {
   }
 }

@@ -21 +21 @@
 protoc.exe
 _ReSharper.HeuristicLab 3.3 Tests
+Google.ProtocolBuffers-2.4.1.473.dll
 packages