Changeset 15030 for branches/HeuristicLab.DatastreamAnalysis/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/DataAnalysisProblemData.cs

Timestamp:

06/08/17 17:02:13 (7 years ago)

Author:

jzenisek

Message:

#2719 merged with trunk (revision 15029)

Location:

branches/HeuristicLab.DatastreamAnalysis/HeuristicLab.Problems.DataAnalysis

Files:

• . (modified) (1 prop)
• 3.4/Implementation/DataAnalysisProblemData.cs (modified) (5 diffs)

branches/HeuristicLab.DatastreamAnalysis/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/DataAnalysisProblemData.cs

@@ -41 +41 @@
 
     #region parameter properites
+    //mkommend: inserted parameter caching due to performance reasons
+    private IFixedValueParameter<Dataset> datasetParameter;
     public IFixedValueParameter<Dataset> DatasetParameter {
-      get { return (IFixedValueParameter<Dataset>)Parameters[DatasetParameterName]; }
-    }
+      get {
+        if (datasetParameter == null) datasetParameter = (IFixedValueParameter<Dataset>)Parameters[DatasetParameterName];
+        return datasetParameter;
+      }
+    }
+
+    private IFixedValueParameter<ReadOnlyCheckedItemList<StringValue>> inputVariablesParameter;
     public IFixedValueParameter<ReadOnlyCheckedItemList<StringValue>> InputVariablesParameter {
-      get { return (IFixedValueParameter<ReadOnlyCheckedItemList<StringValue>>)Parameters[InputVariablesParameterName]; }
-    }
+      get {
+        if (inputVariablesParameter == null) inputVariablesParameter = (IFixedValueParameter<ReadOnlyCheckedItemList<StringValue>>)Parameters[InputVariablesParameterName];
+        return inputVariablesParameter;
+      }
+    }
+
+    private IFixedValueParameter<IntRange> trainingPartitionParameter;
     public IFixedValueParameter<IntRange> TrainingPartitionParameter {
-      get { return (IFixedValueParameter<IntRange>)Parameters[TrainingPartitionParameterName]; }
-    }
+      get {
+        if (trainingPartitionParameter == null) trainingPartitionParameter = (IFixedValueParameter<IntRange>)Parameters[TrainingPartitionParameterName];
+        return trainingPartitionParameter;
+      }
+    }
+
+    private IFixedValueParameter<IntRange> testPartitionParameter;
     public IFixedValueParameter<IntRange> TestPartitionParameter {
-      get { return (IFixedValueParameter<IntRange>)Parameters[TestPartitionParameterName]; }
-    }
+      get {
+        if (testPartitionParameter == null) testPartitionParameter = (IFixedValueParameter<IntRange>)Parameters[TestPartitionParameterName];
+        return testPartitionParameter;
+      }
+    }
+
     public IFixedValueParameter<ReadOnlyItemList<ITransformation>> TransformationsParameter {
       get { return (IFixedValueParameter<ReadOnlyItemList<ITransformation>>)Parameters[TransformationsParameterName]; }
@@ -73 +94 @@
     }
 
+    public double[,] AllowedInputsTrainingValues {
+      get { return Dataset.ToArray(AllowedInputVariables, TrainingIndices); }
+    }
+
+    public double[,] AllowedInputsTestValues { get { return Dataset.ToArray(AllowedInputVariables, TestIndices); } }
     public IntRange TrainingPartition {
       get { return TrainingPartitionParameter.Value; }
@@ -102 +128 @@
     public virtual bool IsTrainingSample(int index) {
       return index >= 0 && index < Dataset.Rows &&
-        TrainingPartition.Start <= index && index < TrainingPartition.End &&
-        (index < TestPartition.Start || TestPartition.End <= index);
+             TrainingPartition.Start <= index && index < TrainingPartition.End &&
+             (index < TestPartition.Start || TestPartition.End <= index);
     }
 
@@ -131 +157 @@
     protected DataAnalysisProblemData(IDataset dataset, IEnumerable<string> allowedInputVariables, IEnumerable<ITransformation> transformations = null) {
       if (dataset == null) throw new ArgumentNullException("The dataset must not be null.");
-      if (allowedInputVariables == null) throw new ArgumentNullException("The allowedInputVariables must not be null.");
-
-      if (allowedInputVariables.Except(dataset.DoubleVariables).Any())
-        throw new ArgumentException("All allowed input variables must be present in the dataset and of type double.");
-
-      var inputVariables = new CheckedItemList<StringValue>(dataset.DoubleVariables.Select(x => new StringValue(x)));
+      if (allowedInputVariables == null) throw new ArgumentNullException("The allowed input variables must not be null.");
+
+      if (allowedInputVariables.Except(dataset.DoubleVariables).Except(dataset.StringVariables).Any())
+        throw new ArgumentException("All allowed input variables must be present in the dataset and of type double or string.");
+
+      var variables = dataset.VariableNames.Where(variable => dataset.VariableHasType<double>(variable) || dataset.VariableHasType<string>(variable));
+      var inputVariables = new CheckedItemList<StringValue>(variables.Select(x => new StringValue(x)));
       foreach (StringValue x in inputVariables)
         inputVariables.SetItemCheckedState(x, allowedInputVariables.Contains(x.Value));
@@ -214 +241 @@
         InputVariables.SetItemCheckedState(inputVariable, variable != null && data.InputVariables.ItemChecked(variable));
       }
-
-      TrainingPartition.Start = TrainingPartition.End = 0;
-      TestPartition.Start = 0;
-      TestPartition.End = Dataset.Rows;
     }
   }