Changeset 8598 for trunk/sources/HeuristicLab.Problems.Instances.DataAnalysis/3.3/Clustering

Timestamp:

09/07/12 14:53:39 (12 years ago)

Author:

sforsten

Message:

#1942: csv files for data analysis problems can be shuffled when imported

Location:

trunk/sources/HeuristicLab.Problems.Instances.DataAnalysis/3.3/Clustering

Files:

• CSV/ClusteringCSVInstanceProvider.cs (modified) (3 diffs)
• ClusteringInstanceProvider.cs (modified) (1 diff)

trunk/sources/HeuristicLab.Problems.Instances.DataAnalysis/3.3/Clustering/CSV/ClusteringCSVInstanceProvider.cs

@@ -21 +21 @@
 
 using System;
+using System.Collections;
 using System.Collections.Generic;
 using System.Globalization;
@@ -59 +60 @@
     public override IClusteringProblemData ImportData(string path) {
       var csvFileParser = new TableFileParser();
-
       csvFileParser.Parse(path);
 
-      var dataset = new Dataset(csvFileParser.VariableNames, csvFileParser.Values);
+      Dataset dataset = new Dataset(csvFileParser.VariableNames, csvFileParser.Values);
+      string targetVar = dataset.DoubleVariables.Last();
 
       // turn of input variables that are constant in the training partition
@@ -68 +69 @@
       var trainingIndizes = Enumerable.Range(0, (csvFileParser.Rows * 2) / 3);
       foreach (var variableName in dataset.DoubleVariables) {
-        if (dataset.GetDoubleValues(variableName, trainingIndizes).Range() > 0)
+        if (dataset.GetDoubleValues(variableName, trainingIndizes).Range() > 0 &&
+          variableName != targetVar)
           allowedInputVars.Add(variableName);
       }
 
-      var clusteringData = new ClusteringProblemData(dataset, allowedInputVars);
+      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 IClusteringProblemData ImportData(string path, DataAnalysisImportType type) {
+      TableFileParser csvFileParser = new TableFileParser();
+      csvFileParser.Parse(path);
+
+      List<IList> values = csvFileParser.Values;
+      if (type.Shuffle) {
+        values = Shuffle(values);
+      }
+
+      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>();
+      var trainingIndizes = Enumerable.Range(0, (csvFileParser.Rows * 2) / 3);
+      foreach (var variableName in dataset.DoubleVariables) {
+        if (dataset.GetDoubleValues(variableName, trainingIndizes).Range() > 0 &&
+          variableName != targetVar)
+          allowedInputVars.Add(variableName);
+      }
+
+      ClusteringProblemData clusteringData = new ClusteringProblemData(dataset, allowedInputVars);
 
       int trainingPartEnd = trainingIndizes.Last();

trunk/sources/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> {
   }
 }