Changeset 12515 for branches/HiveStatistics/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification

Timestamp:

06/25/15 18:21:19 (10 years ago)

Author:

dglaser

Message:

#2388: Merged trunk into HiveStatistics branch

Location:

branches/HiveStatistics/sources/HeuristicLab.Problems.DataAnalysis

Files:

• . (modified) (1 prop)
• 3.4/Implementation/Classification/ClassificationEnsembleModel.cs (modified) (2 diffs)
• 3.4/Implementation/Classification/ClassificationEnsembleSolution.cs (modified) (2 diffs)
• 3.4/Implementation/Classification/ClassificationProblem.cs (modified) (1 diff)
• 3.4/Implementation/Classification/ClassificationProblemData.cs (modified) (2 diffs)
• 3.4/Implementation/Classification/ClassificationSolution.cs (modified) (2 diffs)
• 3.4/Implementation/Classification/DiscriminantFunctionClassificationModel.cs (modified) (1 diff)

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

@@ -67 +67 @@
     }
 
-    public IEnumerable<IEnumerable<double>> GetEstimatedClassValueVectors(Dataset dataset, IEnumerable<int> rows) {
+    public IEnumerable<IEnumerable<double>> GetEstimatedClassValueVectors(IDataset dataset, IEnumerable<int> rows) {
       var estimatedValuesEnumerators = (from model in models
                                         select model.GetEstimatedClassValues(dataset, rows).GetEnumerator())
@@ -82 +82 @@
     #region IClassificationModel Members
 
-    public IEnumerable<double> GetEstimatedClassValues(Dataset dataset, IEnumerable<int> rows) {
+    public IEnumerable<double> GetEstimatedClassValues(IDataset dataset, IEnumerable<int> rows) {
       foreach (var estimatedValuesVector in GetEstimatedClassValueVectors(dataset, rows)) {
         // return the class which is most often occuring

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

@@ -35 +35 @@
   [StorableClass]
   [Item("Classification Ensemble Solution", "A classification solution that contains an ensemble of multiple classification models")]
-  [Creatable("Data Analysis - Ensembles")]
+  [Creatable(CreatableAttribute.Categories.DataAnalysisEnsembles, Priority = 110)]
   public sealed class ClassificationEnsembleSolution : ClassificationSolutionBase, IClassificationEnsembleSolution {
     private readonly Dictionary<int, double> trainingEvaluationCache = new Dictionary<int, double>();
@@ -231 +231 @@
     }
 
-    public IEnumerable<IEnumerable<double>> GetEstimatedClassValueVectors(Dataset dataset, IEnumerable<int> rows) {
+    public IEnumerable<IEnumerable<double>> GetEstimatedClassValueVectors(IDataset dataset, IEnumerable<int> rows) {
       if (!Model.Models.Any()) yield break;
       var estimatedValuesEnumerators = (from model in Model.Models

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

@@ -27 +27 @@
   [StorableClass]
   [Item("Classification Problem", "A general classification problem.")]
-  [Creatable("Problems")]
   public class ClassificationProblem : DataAnalysisProblem<IClassificationProblemData>, IClassificationProblem, IStorableContent {
     public string Filename { get; set; }

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

@@ -324 +324 @@
     }
 
-    public ClassificationProblemData(Dataset dataset, IEnumerable<string> allowedInputVariables, string targetVariable, IEnumerable<ITransformation> transformations = null)
+    public ClassificationProblemData(IDataset 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();
@@ -338 +338 @@
     }
 
-    public static IEnumerable<string> CheckVariablesForPossibleTargetVariables(Dataset dataset) {
+    public static IEnumerable<string> CheckVariablesForPossibleTargetVariables(IDataset dataset) {
       int maxSamples = Math.Min(InspectedRowsToDetermineTargets, dataset.Rows);
       var validTargetVariables = (from v in dataset.DoubleVariables

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

@@ -30 +30 @@
   /// </summary>
   [StorableClass]
-  public abstract class ClassificationSolution : ClassificationSolutionBase {
+  public class ClassificationSolution : ClassificationSolutionBase {
     protected readonly Dictionary<int, double> evaluationCache;
 
@@ -46 +46 @@
       evaluationCache = new Dictionary<int, double>(problemData.Dataset.Rows);
       CalculateClassificationResults();
+    }
+
+    public override IDeepCloneable Clone(Cloner cloner) {
+      return new ClassificationSolution(this, cloner);
     }
 

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

@@ -111 +111 @@
 
 
-    public IEnumerable<double> GetEstimatedValues(Dataset dataset, IEnumerable<int> rows) {
+    public IEnumerable<double> GetEstimatedValues(IDataset dataset, IEnumerable<int> rows) {
       return model.GetEstimatedValues(dataset, rows);
     }
 
-    public IEnumerable<double> GetEstimatedClassValues(Dataset dataset, IEnumerable<int> rows) {
+    public IEnumerable<double> GetEstimatedClassValues(IDataset dataset, IEnumerable<int> rows) {
       if (!Thresholds.Any() && !ClassValues.Any()) throw new ArgumentException("No thresholds and class values were set for the current classification model.");
       foreach (var x in GetEstimatedValues(dataset, rows)) {