Changeset 15450 for branches/MathNetNumerics-Exploration-2789/HeuristicLab.Algorithms.DataAnalysis.Experimental/GAM.cs

Timestamp:

11/06/17 13:12:41 (6 years ago)

Author:

gkronber

Message:

#2789 more tests with CV and automatic determination of smoothing parameter

File:

• branches/MathNetNumerics-Exploration-2789/HeuristicLab.Algorithms.DataAnalysis.Experimental/GAM.cs (modified) (4 diffs)

branches/MathNetNumerics-Exploration-2789/HeuristicLab.Algorithms.DataAnalysis.Experimental/GAM.cs

@@ -111 +111 @@
         nTerms += inputVars.Combinations(i).Count();
       }
+
       IRegressionModel[] f = new IRegressionModel[nTerms];
       for (int i = 0; i < f.Length; i++) {
@@ -130 +131 @@
       string[] terms = new string[f.Length];
       Results.Add(new Result("RSS Values", typeof(DoubleMatrix)));
+
+      var combinations = new List<string[]>();
+      for(int i=1;i<=maxInteractions;i++)
+        combinations.AddRange(HeuristicLab.Common.EnumerableExtensions.Combinations(inputVars, i).Select(c => c.ToArray()));
+      // combinations.Add(new string[] { "X1", "X2" });
+      // combinations.Add(new string[] { "X3", "X4" });
+      // combinations.Add(new string[] { "X5", "X6" });
+      // combinations.Add(new string[] { "X1", "X7", "X9" });
+      // combinations.Add(new string[] { "X3", "X6", "X10" });
+
+
 
       // until convergence
@@ -144 +156 @@
         //}
 
-        for (int interaction = 1; interaction <= maxInteractions; interaction++) {
-          var selectedVars = HeuristicLab.Common.EnumerableExtensions.Combinations(inputVars, interaction);
-
-          foreach (var element in selectedVars) {
-            var res = CalculateResiduals(problemData, f, j, avgY, problemData.TrainingIndices);
-            rss[j] = res.Variance();
-            terms[j] = string.Format("f({0})", string.Join(",", element));
-            f[j] = RegressSpline(problemData, element.ToArray(), res, lambda);
-            j++;
-          }
+
+
+        foreach (var element in combinations) {
+          var res = CalculateResiduals(problemData, f, j, avgY, problemData.TrainingIndices);
+          rss[j] = res.Variance();
+          terms[j] = string.Format("f({0})", string.Join(",", element));
+          f[j] = RegressSpline(problemData, element.ToArray(), res, lambda);
+          j++;
         }
 
@@ -218 +228 @@
           product = product.Zip(problemData.Dataset.GetDoubleValues(inputVars[i], problemData.TrainingIndices), (pi, vi) => pi * vi).ToArray();
         }
-        CubicSplineGCV.CubGcvReport report;
-        return CubicSplineGCV.CalculateCubicSpline(
-          product,
-          (double[])target.Clone(), 
-          problemData.TargetVariable, inputVars, out report
-          );
+        // CubicSplineGCV.CubGcvReport report;
+        // return CubicSplineGCV.CalculateCubicSpline(
+        //   product,
+        //   (double[])target.Clone(), 
+        //   problemData.TargetVariable, inputVars, out report
+        //   );
+
+        double optTolerance; double cvRMSE;
+        // find tolerance
+        // var ensemble = Splines.CalculateSmoothingSplineReinsch(product, (double[])target.Clone(), inputVars, problemData.TargetVariable, out optTolerance, out cvRMSE);
+        // // train on whole data
+        // return Splines.CalculateSmoothingSplineReinsch(product, (double[])target.Clone(), inputVars, optTolerance, product.Length - 1, problemData.TargetVariable); 
+
+
+        // find tolerance
+        var bestLambda = -5.0;
+        double bestCVRMSE = double.PositiveInfinity;
+        double avgTrainRMSE = double.PositiveInfinity;
+        for (double curLambda = -5.0; curLambda <= 6.0; curLambda += 1.0) {
+          var ensemble = Splines.CalculatePenalizedRegressionSpline(product, (double[])target.Clone(), curLambda, problemData.TargetVariable,  inputVars, out avgTrainRMSE, out cvRMSE);
+          Console.Write("{0} {1} {2}", curLambda, avgTrainRMSE, cvRMSE);
+          if (bestCVRMSE > cvRMSE) {
+            Console.Write(" *");
+            bestCVRMSE = cvRMSE;
+            bestLambda = curLambda;
+          }
+          Console.WriteLine();
+        }
+        // train on whole data
+       return Splines.CalculatePenalizedRegressionSpline(product, (double[])target.Clone(), bestLambda, problemData.TargetVariable, inputVars, out avgTrainRMSE, out cvRMSE);
+
       } else return new ConstantModel(target.Average(), problemData.TargetVariable);
     }