Changeset 18098 for branches/3040_VectorBasedGP/HeuristicLab.Problems.DataAnalysis.Symbolic/3.4/SegmentOptimization/SegmentOptimizationProblem.cs

Timestamp:

12/01/21 09:02:27 (3 years ago)

Author:

pfleck

Message:

#3040 Added support for multi-row data for SOP instances where the segment aggregation results are averaged over multiple rows.

File:

• branches/3040_VectorBasedGP/HeuristicLab.Problems.DataAnalysis.Symbolic/3.4/SegmentOptimization/SegmentOptimizationProblem.cs (modified) (10 diffs)

branches/3040_VectorBasedGP/HeuristicLab.Problems.DataAnalysis.Symbolic/3.4/SegmentOptimization/SegmentOptimizationProblem.cs

@@ -50 +50 @@
 
     [Storable]
-    private IValueParameter<DoubleArray> dataVectorParameter;
-    public IValueParameter<DoubleArray> DataVectorParameter {
-      get { return dataVectorParameter; }
+    private IValueParameter<DoubleMatrix> dataParameter;
+    public IValueParameter<DoubleMatrix> DataParameter {
+      get { return dataParameter; }
     }
     [Storable]
@@ -68 +68 @@
       Encoding = new IntegerVectorEncoding("bounds");
 
-      Parameters.Add(dataVectorParameter = new ValueParameter<DoubleArray>("Data Vector", ""));
+      Parameters.Add(dataParameter = new ValueParameter<DoubleMatrix>("Data", ""));
       Parameters.Add(knownBoundsParameter = new ValueParameter<IntRange>("Known Bounds", ""));
       Parameters.Add(aggregationParameter = new ValueParameter<EnumValue<Aggregation>>("Aggregation Function", ""));
@@ -76 +76 @@
       #region Default Instance
       Load(new SOPData() {
-        Values = Enumerable.Range(1, 50).Select(x => (double)x * x).ToArray(),
+        Data = ToNdimArray(Enumerable.Range(1, 50).Select(x => (double)x * x).ToArray()),
         Lower = 20, Upper = 30,
         Aggregation = "mean"
@@ -84 +84 @@
     private SegmentOptimizationProblem(SegmentOptimizationProblem original, Cloner cloner)
       : base(original, cloner) {
-      dataVectorParameter = cloner.Clone(original.dataVectorParameter);
+      dataParameter = cloner.Clone(original.dataParameter);
       knownBoundsParameter = cloner.Clone(original.knownBoundsParameter);
       aggregationParameter = cloner.Clone(original.aggregationParameter);
@@ -98 +98 @@
     [StorableHook(HookType.AfterDeserialization)]
     private void AfterDeserialization() {
+      if (Parameters.ContainsKey("Data Vector") && Parameters["Data Vector"] is ValueParameter<DoubleArray> arrayParameter) {
+        Parameters.Remove(arrayParameter);
+        var array = arrayParameter.Value;
+        var matrix = new DoubleMatrix(1, array.Length);
+        for (int i = 0; i < array.Length; i++) matrix[0, i] = array[i];
+        Parameters.Add(dataParameter = new ValueParameter<DoubleMatrix>("Data", "", matrix));
+      }
+
       RegisterEventHandlers();
     }
     
     private void RegisterEventHandlers() {
-      dataVectorParameter.ValueChanged += DataVectorChanged;
+      dataParameter.ValueChanged += DataChanged;
       knownBoundsParameter.ValueChanged += KnownBoundsChanged;
       aggregationParameter.Value.ValueChanged += AggregationFunctionChanged;
     }
-    private void DataVectorChanged(object sender, EventArgs eventArgs) {
-      Encoding.Bounds = new IntMatrix(new[,] { { 0, DataVectorParameter.Value.Length } });
+    private void DataChanged(object sender, EventArgs eventArgs) {
+      Encoding.Bounds = new IntMatrix(new[,] { { 0, DataParameter.Value.Columns } });
     }
     private void KnownBoundsChanged(object sender, EventArgs e) {
@@ -115 +123 @@
 
     public override double Evaluate(Individual individual, IRandom random) {
-      var data = DataVectorParameter.Value;
+      var data = DataParameter.Value;
       var knownBounds = KnownBoundsParameter.Value;
       var aggregation = aggregationParameter.Value.Value;
@@ -134 +142 @@
       var bounds = new IntRange(best.Min(), best.Max());
 
-      var data = DataVectorParameter.Value;
+      var data = DataParameter.Value;
       var knownBounds = KnownBoundsParameter.Value;
       var aggregation = aggregationParameter.Value.Value;
@@ -153 +161 @@
 
     private static double BoundedAggregation(DoubleArray data, IntRange bounds, Aggregation aggregation) {
+      var matrix = new DoubleMatrix(1, data.Length);
+      for (int i = 0; i < data.Length; i++) matrix[0, i] = data[i];
+      return BoundedAggregation(matrix, bounds, aggregation);
+    }
+
+    private static double BoundedAggregation(DoubleMatrix data, IntRange bounds, Aggregation aggregation) {
       if (bounds.Size == 0) {
         return 0;
       }
 
-      var vector = DoubleVector.Build.DenseOfEnumerable(data);
-      var segment = vector.SubVector(bounds.Start, bounds.Size);
-
-      switch (aggregation) {
-        case Aggregation.Sum:
-          return segment.Sum();
-        case Aggregation.Mean:
-         return segment.Average();
+      var resultValues = new double[data.Rows];
+      var array = new double[data.Columns];
+      for (int row = 0; row < data.Rows; row++) {
+        for (int i = 0; i < array.Length; i++) array[i] = data[row, i];
+
+        var vector = DoubleVector.Build.DenseOfArray(array);
+        var segment = vector.SubVector(bounds.Start, bounds.Size);
+
+        switch (aggregation) {
+          case Aggregation.Sum:
+            resultValues[row] = segment.Sum();
+            break;
+          case Aggregation.Mean:
+            resultValues[row] = segment.Average();
+            break;
           case Aggregation.StandardDeviation:
-          return segment.StandardDeviationPop();
-        default:
-          throw new NotImplementedException();
-      }
+            resultValues[row] = segment.StandardDeviationPop();
+            break;
+          default:
+            throw new NotImplementedException();
+        }
+      }
+
+      return resultValues.Average();
     }
 
     public void Load(SOPData data) {
-      DataVectorParameter.Value = new DoubleArray(data.Values);
+      DataParameter.Value = new DoubleMatrix(data.Data);
       KnownBoundsParameter.Value = new IntRange(data.Lower, data.Upper);
       switch (data.Aggregation.ToLower()) {
@@ -193 +218 @@
                                             
       Encoding.Length = 2;
-      Encoding.Bounds = new IntMatrix(new[,] { { 0, DataVectorParameter.Value.Length } });
+      Encoding.Bounds = new IntMatrix(new[,] { { 0, DataParameter.Value.Columns } });
 
       BestKnownQuality = 0;
@@ -200 +225 @@
       Description = data.Description;
     }
+
+    public static T[,] ToNdimArray<T>(T[] array) {
+      var matrix = new T[1, array.Length];
+      for (int i = 0; i < array.Length; i++)
+        matrix[0, i] = array[i];
+      return matrix;
+    }
   }
 }