Changeset 6760 for branches/PersistenceSpeedUp/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationProblemData.cs

Timestamp:

09/14/11 13:59:25 (13 years ago)

Author:

epitzer

Message:

#1530 integrate changes from trunk

Location:

branches/PersistenceSpeedUp

Files:

• . (modified) (2 props)
• HeuristicLab.Problems.DataAnalysis (modified) (1 prop)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationProblemData.cs (modified) (9 diffs)

branches/PersistenceSpeedUp

@@ -12 +12 @@
 *.psess
 *.vsp
+*.docstates

@@ -12 +12 @@
 *.psess
 *.vsp
+*.docstates

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

@@ -34 +34 @@
   [Item("ClassificationProblemData", "Represents an item containing all data defining a classification problem.")]
   public class ClassificationProblemData : DataAnalysisProblemData, IClassificationProblemData {
-    private const string TargetVariableParameterName = "TargetVariable";
-    private const string ClassNamesParameterName = "ClassNames";
-    private const string ClassificationPenaltiesParameterName = "ClassificationPenalties";
-    private const int MaximumNumberOfClasses = 20;
-    private const int InspectedRowsToDetermineTargets = 500;
+    protected const string TargetVariableParameterName = "TargetVariable";
+    protected const string ClassNamesParameterName = "ClassNames";
+    protected const string ClassificationPenaltiesParameterName = "ClassificationPenalties";
+    protected const int MaximumNumberOfClasses = 20;
+    protected const int InspectedRowsToDetermineTargets = 500;
 
     #region default data
@@ -171 +171 @@
      {1176881,7,5,3,7,4,10,7,5,5,4        }
 };
-    private static Dataset defaultDataset;
-    private static IEnumerable<string> defaultAllowedInputVariables;
-    private static string defaultTargetVariable;
+    private static readonly Dataset defaultDataset;
+    private static readonly IEnumerable<string> defaultAllowedInputVariables;
+    private static readonly string defaultTargetVariable;
+
+    private static readonly ClassificationProblemData emptyProblemData;
+    public static ClassificationProblemData EmptyProblemData {
+      get { return EmptyProblemData; }
+    }
+
     static ClassificationProblemData() {
       defaultDataset = new Dataset(defaultVariableNames, defaultData);
@@ -181 +187 @@
       defaultAllowedInputVariables = defaultVariableNames.Except(new List<string>() { "sample", "class" });
       defaultTargetVariable = "class";
+
+      var problemData = new ClassificationProblemData();
+      problemData.Parameters.Clear();
+      problemData.Name = "Empty Classification ProblemData";
+      problemData.Description = "This ProblemData acts as place holder before the correct problem data is loaded.";
+      problemData.isEmpty = true;
+
+      problemData.Parameters.Add(new FixedValueParameter<Dataset>(DatasetParameterName, "", new Dataset()));
+      problemData.Parameters.Add(new FixedValueParameter<ReadOnlyCheckedItemList<StringValue>>(InputVariablesParameterName, ""));
+      problemData.Parameters.Add(new FixedValueParameter<IntRange>(TrainingPartitionParameterName, "", (IntRange)new IntRange(0, 0).AsReadOnly()));
+      problemData.Parameters.Add(new FixedValueParameter<IntRange>(TestPartitionParameterName, "", (IntRange)new IntRange(0, 0).AsReadOnly()));
+      problemData.Parameters.Add(new ConstrainedValueParameter<StringValue>(TargetVariableParameterName, new ItemSet<StringValue>()));
+      problemData.Parameters.Add(new FixedValueParameter<StringMatrix>(ClassNamesParameterName, "", new StringMatrix(0, 0).AsReadOnly()));
+      problemData.Parameters.Add(new FixedValueParameter<DoubleMatrix>(ClassificationPenaltiesParameterName, "", (DoubleMatrix)new DoubleMatrix(0, 0).AsReadOnly()));
+      emptyProblemData = problemData;
     }
     #endregion
 
     #region parameter properties
-    public IValueParameter<StringValue> TargetVariableParameter {
-      get { return (IValueParameter<StringValue>)Parameters[TargetVariableParameterName]; }
+    public ConstrainedValueParameter<StringValue> TargetVariableParameter {
+      get { return (ConstrainedValueParameter<StringValue>)Parameters[TargetVariableParameterName]; }
     }
     public IFixedValueParameter<StringMatrix> ClassNamesParameter {
@@ -205 +226 @@
       get {
         if (classValues == null) {
-          classValues = Dataset.GetEnumeratedVariableValues(TargetVariableParameter.Value.Value).Distinct().ToList();
+          classValues = Dataset.GetDoubleValues(TargetVariableParameter.Value.Value).Distinct().ToList();
           classValues.Sort();
         }
@@ -249 +270 @@
       RegisterParameterEvents();
     }
-    public override IDeepCloneable Clone(Cloner cloner) { return new ClassificationProblemData(this, cloner); }
+    public override IDeepCloneable Clone(Cloner cloner) {
+      if (this == emptyProblemData) return emptyProblemData;
+      return new ClassificationProblemData(this, cloner);
+    }
 
     public ClassificationProblemData() : this(defaultDataset, defaultAllowedInputVariables, defaultTargetVariable) { }
@@ -267 +291 @@
     private static IEnumerable<string> CheckVariablesForPossibleTargetVariables(Dataset dataset) {
       int maxSamples = Math.Min(InspectedRowsToDetermineTargets, dataset.Rows);
-      var validTargetVariables = from v in dataset.VariableNames
-                                 let DistinctValues = dataset.GetVariableValues(v)
-                                   .Take(maxSamples)
-                                   .Distinct()
-                                   .Count()
-                                 where DistinctValues < MaximumNumberOfClasses
-                                 select v;
+      var validTargetVariables = (from v in dataset.DoubleVariables
+                                  let distinctValues = dataset.GetDoubleValues(v)
+                                    .Take(maxSamples)
+                                    .Distinct()
+                                    .Count()
+                                  where distinctValues < MaximumNumberOfClasses
+                                  select v).ToArray();
 
       if (!validTargetVariables.Any())
@@ -283 +307 @@
 
     private void ResetTargetVariableDependentMembers() {
-      DergisterParameterEvents();
+      DeregisterParameterEvents();
 
       classNames = null;
@@ -357 +381 @@
       ClassificationPenaltiesParameter.Value.ItemChanged += new EventHandler<EventArgs<int, int>>(MatrixParameter_ItemChanged);
     }
-    private void DergisterParameterEvents() {
+    private void DeregisterParameterEvents() {
       TargetVariableParameter.ValueChanged -= new EventHandler(TargetVariableParameter_ValueChanged);
       ClassNamesParameter.Value.Reset -= new EventHandler(Parameter_ValueChanged);
@@ -386 +410 @@
       dataset.Name = Path.GetFileName(fileName);
 
-      ClassificationProblemData problemData = new ClassificationProblemData(dataset, dataset.VariableNames.Skip(1), dataset.VariableNames.First());
+      ClassificationProblemData problemData = new ClassificationProblemData(dataset, dataset.DoubleVariables.Skip(1), dataset.DoubleVariables.First());
       problemData.Name = "Data imported from " + Path.GetFileName(fileName);
       return problemData;

@@ -12 +12 @@
 *.psess
 *.vsp
+*.docstates