Changeset 14818 for branches/EfficientGlobalOptimization/HeuristicLab.Algorithms.EGO/EgoUtilities.cs

Timestamp:

04/04/17 12:37:52 (8 years ago)

Author:

bwerth

Message:

#2745 added several new InfillCriteria and moved Parameters from the InfillProblem to the Criteria themselves; added Sanitiy checks for GaussianProcessRegression

File:

• branches/EfficientGlobalOptimization/HeuristicLab.Algorithms.EGO/EgoUtilities.cs (modified) (2 diffs)

branches/EfficientGlobalOptimization/HeuristicLab.Algorithms.EGO/EgoUtilities.cs

@@ -94 +94 @@
 
     public static double GetEstimation(this IRegressionModel model, RealVector r) {
-      var dataset = GetDataSet(new[] { new Tuple<RealVector, double>(r, 0.0) });
+      var dataset = GetDataSet(new[] { new Tuple<RealVector, double>(r, 0.0) }, false);
       return model.GetEstimatedValues(dataset, new[] { 0 }).First();
     }
     public static double GetVariance(this IConfidenceRegressionModel model, RealVector r) {
-      var dataset = GetDataSet(new[] { new Tuple<RealVector, double>(r, 0.0) });
+      var dataset = GetDataSet(new[] { new Tuple<RealVector, double>(r, 0.0) }, false);
       return model.GetEstimatedVariances(dataset, new[] { 0 }).First();
     }
 
-    public static Dataset GetDataSet(IReadOnlyList<Tuple<RealVector, double>> samples) {
-      var n = samples[0].Item1.Length + 1;
-      var data = new double[samples.Count, n];
-      var names = new string[n - 1];
-      for (var i = 0; i < n; i++)
-        if (i < names.Length) {
-          names[i] = "input" + i;
-          for (var j = 0; j < samples.Count; j++) data[j, i] = samples[j].Item1[i];
-        } else
-          for (var j = 0; j < samples.Count; j++) data[j, n - 1] = samples[j].Item2;
+
+    public static double GetDoubleValue(this IDataset dataset, int i, int j) {
+      return dataset.GetDoubleValue("input" + j, i);
+    }
+    public static Dataset GetDataSet(IReadOnlyList<Tuple<RealVector, double>> samples, bool removeDuplicates) {
+      if (removeDuplicates)
+        samples = RemoveDuplicates(samples); //TODO duplicates require heteroskedasticity in Models
+
+
+      var dimensions = samples[0].Item1.Length + 1;
+      var data = new double[samples.Count, dimensions];
+      var names = new string[dimensions - 1];
+      for (var i = 0; i < names.Length; i++) names[i] = "input" + i;
+
+      for (var j = 0; j < samples.Count; j++) {
+        for (var i = 0; i < names.Length; i++) data[j, i] = samples[j].Item1[i];
+        data[j, dimensions - 1] = samples[j].Item2;
+
+      }
+
+
       return new Dataset(names.Concat(new[] { "output" }).ToArray(), data);
     }
+
+    private static IReadOnlyList<Tuple<RealVector, double>> RemoveDuplicates(IReadOnlyList<Tuple<RealVector, double>> samples) {
+      var res = new List<Tuple<RealVector, double, int>>();
+
+      foreach (var sample in samples) {
+        if (res.Count == 0) {
+          res.Add(new Tuple<RealVector, double, int>(sample.Item1, sample.Item2, 1));
+          continue;
+        }
+
+        var index = res.ArgMin(x => Euclidian(sample.Item1, x.Item1));
+        var d = Euclidian(res[index].Item1, sample.Item1);
+        if (d > 0.0001)
+          res.Add(new Tuple<RealVector, double, int>(sample.Item1, sample.Item2, 1));
+        else {
+          var t = res[index];
+          res.RemoveAt(index);
+          res.Add(new Tuple<RealVector, double, int>(t.Item1, t.Item2 + sample.Item2, t.Item3 + 1));
+        }
+      }
+      return res.Select(x => new Tuple<RealVector, double>(x.Item1, x.Item2 / x.Item3)).ToArray();
+    }
+
+    private static double Euclidian(IEnumerable<double> a, IEnumerable<double> b) {
+      return Math.Sqrt(a.Zip(b, (d, d1) => d - d1).Sum(d => d * d));
+    }
+
     public static DoubleMatrix GetBoundingBox(IEnumerable<RealVector> vectors) {
       DoubleMatrix res = null;
@@ -128 +166 @@
       return res;
     }
+
+
   }
 }