Changeset 11202 for branches/HiveStatistics/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification

Timestamp:

07/18/14 12:01:13 (10 years ago)

Author:

ascheibe

Message:

merged trunk into hive statistics branch

Location:

branches/HiveStatistics/sources

Files:

• . (modified) (2 props)
• HeuristicLab.Problems.DataAnalysis (modified) (1 prop)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationEnsembleModel.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationEnsembleProblemData.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationEnsembleSolution.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationProblem.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationProblemData.cs (modified) (5 diffs)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationSolution.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationSolutionBase.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/DiscriminantFunctionClassificationModel.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/DiscriminantFunctionClassificationSolution.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/DiscriminantFunctionClassificationSolutionBase.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ThresholdCalculators/AccuracyMaximizationThresholdCalculator.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ThresholdCalculators/NormalDistributionCutPointsThresholdCalculator.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ThresholdCalculators/ThresholdCalculator.cs (modified) (1 diff)

branches/HiveStatistics/sources

@@ -8 +8 @@
 FxCopResults.txt
 Google.ProtocolBuffers-0.9.1.dll
+Google.ProtocolBuffers-2.4.1.473.dll
 HeuristicLab 3.3.5.1.ReSharper.user
 HeuristicLab 3.3.6.0.ReSharper.user
 HeuristicLab.4.5.resharper.user
 HeuristicLab.ExtLibs.6.0.ReSharper.user
+HeuristicLab.Scripting.Development
 HeuristicLab.resharper.user
 ProtoGen.exe
@@ -17 +19 @@
 _ReSharper.HeuristicLab
 _ReSharper.HeuristicLab 3.3
+_ReSharper.HeuristicLab 3.3 Tests
 _ReSharper.HeuristicLab.ExtLibs
 bin
 protoc.exe
-_ReSharper.HeuristicLab 3.3 Tests
-Google.ProtocolBuffers-2.4.1.473.dll

@@ -8 +8 @@
 FxCopResults.txt
 Google.ProtocolBuffers-0.9.1.dll
+Google.ProtocolBuffers-2.4.1.473.dll
 HeuristicLab 3.3.5.1.ReSharper.user
 HeuristicLab 3.3.6.0.ReSharper.user
 HeuristicLab.4.5.resharper.user
 HeuristicLab.ExtLibs.6.0.ReSharper.user
+HeuristicLab.Scripting.Development
 HeuristicLab.resharper.user
 ProtoGen.exe
@@ -17 +19 @@
 _ReSharper.HeuristicLab
 _ReSharper.HeuristicLab 3.3
+_ReSharper.HeuristicLab 3.3 Tests
 _ReSharper.HeuristicLab.ExtLibs
 bin
 protoc.exe
-_ReSharper.HeuristicLab 3.3 Tests
-Google.ProtocolBuffers-2.4.1.473.dll

branches/HiveStatistics/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationEnsembleModel.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2012 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2014 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.

branches/HiveStatistics/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationEnsembleProblemData.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2012 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2014 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.

branches/HiveStatistics/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationEnsembleSolution.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2012 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2014 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.

branches/HiveStatistics/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationProblem.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2012 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2014 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.

branches/HiveStatistics/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationProblemData.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2012 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2014 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.
@@ -221 +221 @@
     public string TargetVariable {
       get { return TargetVariableParameter.Value.Value; }
+      set {
+        if (value == null) throw new ArgumentNullException("targetVariable", "The provided value for the targetVariable is null.");
+        if (value == TargetVariable) return;
+
+
+        var matchingParameterValue = TargetVariableParameter.ValidValues.FirstOrDefault(v => v.Value == value);
+        if (matchingParameterValue == null) throw new ArgumentException("The provided value is not valid as the targetVariable.", "targetVariable");
+        TargetVariableParameter.Value = matchingParameterValue;
+      }
     }
 
@@ -291 +300 @@
     }
 
-    public ClassificationProblemData(Dataset dataset, IEnumerable<string> allowedInputVariables, string targetVariable)
-      : base(dataset, allowedInputVariables) {
+    public ClassificationProblemData(Dataset dataset, IEnumerable<string> allowedInputVariables, string targetVariable, IEnumerable<ITransformation> transformations = null)
+      : base(dataset, allowedInputVariables, transformations ?? Enumerable.Empty<ITransformation>()) {
       var validTargetVariableValues = CheckVariablesForPossibleTargetVariables(dataset).Select(x => new StringValue(x).AsReadOnly()).ToList();
       var target = validTargetVariableValues.Where(x => x.Value == targetVariable).DefaultIfEmpty(validTargetVariableValues.First()).First();
@@ -311 +320 @@
                                     .Distinct()
                                     .Count()
-                                  where distinctValues < MaximumNumberOfClasses
+                                  where distinctValues <= MaximumNumberOfClasses
                                   select v).ToArray();
 
@@ -408 +417 @@
     }
     #endregion
+
+    protected override bool IsProblemDataCompatible(IDataAnalysisProblemData problemData, out string errorMessage) {
+      if (problemData == null) throw new ArgumentNullException("problemData", "The provided problemData is null.");
+      IClassificationProblemData classificationProblemData = problemData as IClassificationProblemData;
+      if (classificationProblemData == null)
+        throw new ArgumentException("The problem data is no classification problem data. Instead a " + problemData.GetType().GetPrettyName() + " was provided.", "problemData");
+
+      var returnValue = base.IsProblemDataCompatible(classificationProblemData, out errorMessage);
+      //check targetVariable
+      if (classificationProblemData.InputVariables.All(var => var.Value != TargetVariable)) {
+        errorMessage = string.Format("The target variable {0} is not present in the new problem data.", TargetVariable)
+                       + Environment.NewLine + errorMessage;
+        return false;
+      }
+
+      var newClassValues = classificationProblemData.Dataset.GetDoubleValues(TargetVariable).Distinct().OrderBy(x => x);
+      if (!newClassValues.SequenceEqual(ClassValues)) {
+        errorMessage = errorMessage + string.Format("The class values differ in the provided classification problem data.");
+        return false;
+      }
+
+      return returnValue;
+    }
+
+    public override void AdjustProblemDataProperties(IDataAnalysisProblemData problemData) {
+      if (problemData == null) throw new ArgumentNullException("problemData", "The provided problemData is null.");
+      ClassificationProblemData classificationProblemData = problemData as ClassificationProblemData;
+      if (classificationProblemData == null)
+        throw new ArgumentException("The problem data is not a classification problem data. Instead a " + problemData.GetType().GetPrettyName() + " was provided.", "problemData");
+
+      base.AdjustProblemDataProperties(problemData);
+      TargetVariable = classificationProblemData.TargetVariable;
+      for (int i = 0; i < classificationProblemData.ClassNames.Count(); i++)
+        ClassNamesParameter.Value[i, 0] = classificationProblemData.ClassNames.ElementAt(i);
+
+      for (int i = 0; i < Classes; i++) {
+        for (int j = 0; j < Classes; j++) {
+          ClassificationPenaltiesParameter.Value[i, j] = classificationProblemData.GetClassificationPenalty(ClassValuesCache[i], ClassValuesCache[j]);
+        }
+      }
+    }
   }
 }

branches/HiveStatistics/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationSolution.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2012 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2014 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.

branches/HiveStatistics/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationSolutionBase.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2012 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2014 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.

branches/HiveStatistics/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/DiscriminantFunctionClassificationModel.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2012 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2014 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.

branches/HiveStatistics/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/DiscriminantFunctionClassificationSolution.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2012 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2014 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.

branches/HiveStatistics/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/DiscriminantFunctionClassificationSolutionBase.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2012 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2014 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.

branches/HiveStatistics/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ThresholdCalculators/AccuracyMaximizationThresholdCalculator.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2012 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2014 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.

branches/HiveStatistics/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ThresholdCalculators/NormalDistributionCutPointsThresholdCalculator.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2012 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2014 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.

branches/HiveStatistics/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ThresholdCalculators/ThresholdCalculator.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2012 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2014 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.

@@ -8 +8 @@
 FxCopResults.txt
 Google.ProtocolBuffers-0.9.1.dll
+Google.ProtocolBuffers-2.4.1.473.dll
 HeuristicLab 3.3.5.1.ReSharper.user
 HeuristicLab 3.3.6.0.ReSharper.user
 HeuristicLab.4.5.resharper.user
 HeuristicLab.ExtLibs.6.0.ReSharper.user
+HeuristicLab.Scripting.Development
 HeuristicLab.resharper.user
 ProtoGen.exe
@@ -17 +19 @@
 _ReSharper.HeuristicLab
 _ReSharper.HeuristicLab 3.3
+_ReSharper.HeuristicLab 3.3 Tests
 _ReSharper.HeuristicLab.ExtLibs
 bin
 protoc.exe
-_ReSharper.HeuristicLab 3.3 Tests
-Google.ProtocolBuffers-2.4.1.473.dll