Changeset 7866 for branches/ClassificationEnsembleVoting/HeuristicLab.Problems.DataAnalysis/3.4/Implementation

Timestamp:

05/22/12 10:36:20 (13 years ago)

Author:

sforsten

Message:

#1776:

• merged r7454:7863 trunk into branch to make it compatible again
• adjusted GetConfidence of MajorityVoteWeightCalculator to be in an interval of [0, 1]

Location:

branches/ClassificationEnsembleVoting/HeuristicLab.Problems.DataAnalysis

Files:

• . (modified) (1 prop)
• 3.4/Implementation/Classification/ClassificationProblem.cs (modified) (1 diff)
• 3.4/Implementation/Classification/ClassificationProblemData.cs (modified) (2 diffs)
• 3.4/Implementation/Classification/WeightCalculators/MajorityVoteWeightCalculator.cs (modified) (1 diff)
• 3.4/Implementation/Clustering/ClusteringProblem.cs (modified) (1 diff)
• 3.4/Implementation/Clustering/ClusteringProblemData.cs (modified) (2 diffs)
• 3.4/Implementation/DataAnalysisProblem.cs (modified) (2 diffs)
• 3.4/Implementation/Regression/RegressionEnsembleSolution.cs (modified) (1 diff)
• 3.4/Implementation/Regression/RegressionProblem.cs (modified) (1 diff)
• 3.4/Implementation/Regression/RegressionProblemData.cs (modified) (2 diffs)
• 3.4/Implementation/Regression/RegressionSolution.cs (modified) (1 diff)
• 3.4/Implementation/Regression/RegressionSolutionBase.cs (modified) (2 diffs)

branches/ClassificationEnsembleVoting/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationProblem.cs

@@ -40 +40 @@
       ProblemData = new ClassificationProblemData();
     }
-
-    public override void ImportProblemDataFromFile(string fileName) {
-      ClassificationProblemData problemData = ClassificationProblemData.ImportFromFile(fileName);
-      ProblemData = problemData;
-    }
   }
 }

branches/ClassificationEnsembleVoting/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationProblemData.cs

@@ -22 +22 @@
 using System;
 using System.Collections.Generic;
-using System.IO;
 using System.Linq;
 using HeuristicLab.Common;
@@ -403 +402 @@
     }
     #endregion
-
-    #region Import from file
-    public static ClassificationProblemData ImportFromFile(string fileName) {
-      TableFileParser csvFileParser = new TableFileParser();
-      csvFileParser.Parse(fileName);
-
-      Dataset dataset = new Dataset(csvFileParser.VariableNames, csvFileParser.Values);
-      dataset.Name = Path.GetFileName(fileName);
-
-      ClassificationProblemData problemData = new ClassificationProblemData(dataset, dataset.DoubleVariables.Skip(1), dataset.DoubleVariables.First());
-      problemData.Name = "Data imported from " + Path.GetFileName(fileName);
-      return problemData;
-    }
-    #endregion
   }
 }

branches/ClassificationEnsembleVoting/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/WeightCalculators/MajorityVoteWeightCalculator.cs

@@ -51 +51 @@
       return Enumerable.Repeat<double>(1, classificationSolutions.Count());
     }
+
+    public override double GetConfidence(IEnumerable<IClassificationSolution> solutions, int index, double estimatedClassValue) {
+      if (solutions.Count() < 1)
+        return double.NaN;
+      Dataset dataset = solutions.First().ProblemData.Dataset;
+      int correctEstimated = solutions.Select(s => s.Model.GetEstimatedClassValues(dataset, Enumerable.Repeat(index, 1)).First())
+                                      .Where(x => x.Equals(estimatedClassValue))
+                                      .Count();
+      return ((double)correctEstimated / (double)solutions.Count() - 0.5) * 2;
+    }
   }
 }

branches/ClassificationEnsembleVoting/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Clustering/ClusteringProblem.cs

@@ -38 +38 @@
       ProblemData = new ClusteringProblemData();
     }
-
-    public override void ImportProblemDataFromFile(string fileName) {
-      ClusteringProblemData problemData = ClusteringProblemData.ImportFromFile(fileName);
-      ProblemData = problemData;
-    }
   }
 }

branches/ClassificationEnsembleVoting/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Clustering/ClusteringProblemData.cs

@@ -21 +21 @@
 
 using System.Collections.Generic;
-using System.IO;
 using HeuristicLab.Common;
 using HeuristicLab.Core;
@@ -90 +89 @@
       : base(dataset, allowedInputVariables) {
     }
-
-
-    #region Import from file
-    public static ClusteringProblemData ImportFromFile(string fileName) {
-      TableFileParser csvFileParser = new TableFileParser();
-      csvFileParser.Parse(fileName);
-
-      Dataset dataset = new Dataset(csvFileParser.VariableNames, csvFileParser.Values);
-      dataset.Name = Path.GetFileName(fileName);
-
-      ClusteringProblemData problemData = new ClusteringProblemData(dataset, dataset.DoubleVariables);
-      problemData.Name = "Data imported from " + Path.GetFileName(fileName);
-      return problemData;
-    }
-    #endregion
   }
 }

branches/ClassificationEnsembleVoting/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/DataAnalysisProblem.cs

@@ -26 +26 @@
 using HeuristicLab.Parameters;
 using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
+using HeuristicLab.Problems.Instances;
 
 namespace HeuristicLab.Problems.DataAnalysis {
   [StorableClass]
-  public abstract class DataAnalysisProblem<T> : Problem,
-    IDataAnalysisProblem<T>
+  public abstract class DataAnalysisProblem<T> : Problem, IDataAnalysisProblem<T>,
+    IProblemInstanceConsumer<T>, IProblemInstanceExporter<T>
     where T : class, IDataAnalysisProblemData {
     private const string ProblemDataParameterName = "ProblemData";
@@ -91 +92 @@
     }
 
-    public abstract void ImportProblemDataFromFile(string fileName);
+    #region Import & Export
+    public void Load(T data) {
+      Name = data.Name;
+      Description = data.Description;
+      ProblemData = data;
+      OnReset();
+    }
+
+    public T Export() {
+      return ProblemData;
+    }
+    #endregion
   }
 }

branches/ClassificationEnsembleVoting/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionEnsembleSolution.cs

@@ -97 +97 @@
 
       RegisterRegressionSolutionsEventHandler();
+    }
+
+    public RegressionEnsembleSolution(IRegressionProblemData problemData)
+      : this(Enumerable.Empty<IRegressionModel>(), problemData) {
     }
 

branches/ClassificationEnsembleVoting/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionProblem.cs

@@ -40 +40 @@
       ProblemData = new RegressionProblemData();
     }
-
-    public override void ImportProblemDataFromFile(string fileName) {
-      RegressionProblemData problemData = RegressionProblemData.ImportFromFile(fileName);
-      ProblemData = problemData;
-    }
   }
 }

branches/ClassificationEnsembleVoting/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionProblemData.cs

@@ -22 +22 @@
 using System;
 using System.Collections.Generic;
-using System.IO;
 using System.Linq;
 using HeuristicLab.Common;
@@ -136 +135 @@
       OnChanged();
     }
-
-    #region Import from file
-    public static RegressionProblemData ImportFromFile(string fileName) {
-      TableFileParser csvFileParser = new TableFileParser();
-      csvFileParser.Parse(fileName);
-
-      Dataset dataset = new Dataset(csvFileParser.VariableNames, csvFileParser.Values);
-      dataset.Name = Path.GetFileName(fileName);
-
-      RegressionProblemData problemData = new RegressionProblemData(dataset, dataset.DoubleVariables.Skip(1), dataset.DoubleVariables.First());
-      problemData.Name = "Data imported from " + Path.GetFileName(fileName);
-      return problemData;
-    }
-    #endregion
   }
 }

branches/ClassificationEnsembleVoting/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionSolution.cs

@@ -44 +44 @@
     protected RegressionSolution(IRegressionModel model, IRegressionProblemData problemData)
       : base(model, problemData) {
-      evaluationCache = new Dictionary<int, double>();
+      evaluationCache = new Dictionary<int, double>(problemData.Dataset.Rows);
     }
 

branches/ClassificationEnsembleVoting/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionSolutionBase.cs

@@ -21 +21 @@
 
 using System.Collections.Generic;
-using System.Linq;
 using HeuristicLab.Common;
 using HeuristicLab.Data;
@@ -166 +165 @@
 
     protected void CalculateResults() {
-      double[] estimatedTrainingValues = EstimatedTrainingValues.ToArray(); // cache values
-      double[] originalTrainingValues = ProblemData.Dataset.GetDoubleValues(ProblemData.TargetVariable, ProblemData.TrainingIndizes).ToArray();
-      double[] estimatedTestValues = EstimatedTestValues.ToArray(); // cache values
-      double[] originalTestValues = ProblemData.Dataset.GetDoubleValues(ProblemData.TargetVariable, ProblemData.TestIndizes).ToArray();
+      IEnumerable<double> estimatedTrainingValues = EstimatedTrainingValues; // cache values
+      IEnumerable<double> originalTrainingValues = ProblemData.Dataset.GetDoubleValues(ProblemData.TargetVariable, ProblemData.TrainingIndizes);
+      IEnumerable<double> estimatedTestValues = EstimatedTestValues; // cache values
+      IEnumerable<double> originalTestValues = ProblemData.Dataset.GetDoubleValues(ProblemData.TargetVariable, ProblemData.TestIndizes);
 
       OnlineCalculatorError errorState;