Changeset 15450 for branches/MathNetNumerics-Exploration-2789/Main

Timestamp:

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

Author:

gkronber

Message:

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

Location:

branches/MathNetNumerics-Exploration-2789/Main

Files:

• Main.csproj (modified) (1 diff)
• Program.cs (modified) (1 diff)

branches/MathNetNumerics-Exploration-2789/Main/Main.csproj

@@ -38 +38 @@
       <HintPath>..\..\..\trunk\sources\bin\ALGLIB-3.7.0.dll</HintPath>
     </Reference>
+    <Reference Include="HeuristicLab.Algorithms.DataAnalysis-3.4, Version=3.4.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
+      <SpecificVersion>False</SpecificVersion>
+      <HintPath>..\..\..\trunk\sources\bin\HeuristicLab.Algorithms.DataAnalysis-3.4.dll</HintPath>
+    </Reference>
+    <Reference Include="HeuristicLab.Collections-3.3, Version=3.3.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec" />
     <Reference Include="HeuristicLab.Common-3.3">
       <HintPath>..\..\..\trunk\sources\bin\HeuristicLab.Common-3.3.dll</HintPath>
     </Reference>
     <Reference Include="HeuristicLab.Core-3.3, Version=3.3.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec" />
+    <Reference Include="HeuristicLab.Optimization-3.3, Version=3.3.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec" />
     <Reference Include="HeuristicLab.Problems.DataAnalysis-3.4, Version=3.4.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
       <SpecificVersion>False</SpecificVersion>
       <HintPath>..\..\..\trunk\sources\bin\HeuristicLab.Problems.DataAnalysis-3.4.dll</HintPath>
+    </Reference>
+    <Reference Include="HeuristicLab.Problems.Instances-3.3, Version=3.3.0.0, Culture=neutral, PublicKeyToken=ba48961d6f65dcec, processorArchitecture=MSIL">
+      <SpecificVersion>False</SpecificVersion>
+      <HintPath>..\..\..\trunk\sources\bin\HeuristicLab.Problems.Instances-3.3.dll</HintPath>
+    </Reference>
+    <Reference Include="HeuristicLab.Problems.Instances.DataAnalysis-3.3">
+      <HintPath>..\..\..\trunk\sources\bin\HeuristicLab.Problems.Instances.DataAnalysis-3.3.dll</HintPath>
     </Reference>
     <Reference Include="System" />

branches/MathNetNumerics-Exploration-2789/Main/Program.cs

@@ -12 +12 @@
   class Program {
     static void Main(string[] args) {
-      var xs = HeuristicLab.Common.SequenceGenerator.GenerateSteps(-3.5, 3.5, 0.1, includeEnd: true).ToList();
-      var ys = xs.Select(xi => 1.0 / Math.Sqrt(2 * Math.PI) * Math.Exp(-0.5 * xi * xi)).ToArray(); // 1.0 / (Math.Sqrt(2 * Math.PI) * Math.Exp(-0.5 * xi * xi))).ToArray();
+      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.VariousInstanceProvider();
+      var problemData = provider.LoadData(provider.GetDataDescriptors().First(dd => dd.Name.Contains("Poly")));
+      // var provider = new HeuristicLab.Problems.Instances.DataAnalysis.RegressionRealWorldInstanceProvider();
+      // var problemData = provider.LoadData(provider.GetDataDescriptors().First(dd => dd.Name.Contains("Chem")));
 
-      int n = xs.Count();
-      alglib.hqrndstate state;
-      alglib.hqrndseed(1234, 5678, out state);
-      var ys_noise = ys.Select(yi => yi + alglib.hqrndnormal(state) * 0.1).ToList();
+      var gam = new GAM();
+      gam.MaxIterations = 10;
+      gam.MaxInteractions = 3;
+      gam.Problem.ProblemData = problemData;
+      gam.Start();
 
-      CubicSplineGCV.CubGcvReport report;
-      var model = CubicSplineGCV.CalculateCubicSpline(
-        xs.ToArray(), ys_noise.ToArray(), "y", new string[] { "x" }, out report);
+      var solution = (IRegressionSolution)gam.Results["Ensemble solution"].Value;
 
-      Console.WriteLine("Smoothing Parameter (= RHO/(RHO + 1) {0}", report.smoothingParameter);
-      Console.WriteLine("Estimated DOF of RSS {0}", report.estimatedRSSDegreesOfFreedom);
-      Console.WriteLine("GCV {0}", report.generalizedCrossValidation);
-      Console.WriteLine("Mean squared residual {0}", report.meanSquareResiudal);
-      Console.WriteLine("Estimate of true MSE at data points {0}", report.estimatedTrueMeanSquaredErrorAtDataPoints);
-      Console.WriteLine("Estimate of error variance {0}", report.estimatedErrorVariance);
-      Console.WriteLine("Mean square value of DF(I) {0}", report.meanSquareOfDf);
-
-      OnlineCalculatorError error;
-      var ys_smoothed = xs.Select(xi => model.GetEstimatedValue(xi)).ToArray();
-      var mse = OnlineMeanSquaredErrorCalculator.Calculate(ys, ys_smoothed, out error);
-      Console.WriteLine("MSE(ys, ys_smooth) = {0}", mse);
-      mse = OnlineMeanSquaredErrorCalculator.Calculate(ys, ys_noise, out error);
-      Console.WriteLine("MSE(ys, ys_noise) = {0}", mse);
-
-      Thread.CurrentThread.CurrentCulture = CultureInfo.InvariantCulture;
-
-      for (int i = 0; i < n; i++) {
-        Console.WriteLine("{0}\t{1}\t{2}\t{3}\t{4}\t{5}",
-          xs[i], ys[i], ys_smoothed[i], ys_noise[i], ys_smoothed[i] + 1.96 * report.se[i], ys_smoothed[i] - 1.96 * report.se[i]);
-      }
+      Console.WriteLine("RMSE (train) {0}", solution.TrainingRootMeanSquaredError);
+      Console.WriteLine("RMSE (test) {0}", solution.TestRootMeanSquaredError);
     }
   }