source: branches/MathNetNumerics-Exploration-2789/Test/UnitTest1.cs @ 15529

using System;
using System.Diagnostics;
using System.Linq;
using HeuristicLab.Algorithms.DataAnalysis.Experimental;
using HeuristicLab.Algorithms.GeneticAlgorithm;
using HeuristicLab.Common;
using HeuristicLab.Problems.DataAnalysis;
using HeuristicLab.SequentialEngine;
using Microsoft.VisualStudio.TestTools.UnitTesting;

namespace Test {
  [TestClass]
  public class UnitTest1 {
    [TestMethod]
    public void TestMethod1() {
      var ga = new GeneticAlgorithm();
      var symbReg = new HeuristicLab.Problems.DataAnalysis.Symbolic.Regression.SymbolicRegressionSingleObjectiveProblem();
      var eval = new SymbolicRegressionConstantOptimizationEvaluator();
      symbReg.EvaluatorParameter.Value = eval;
      ga.Engine = new SequentialEngine();
      ga.Seed.Value = 1234;
      ga.Problem = symbReg;

      ga.Start();

    }
  }

  [TestClass]
  public class PenalizedRegressionSplineTests {
    [TestMethod]
    public void TestPenalizedRegressionSplinesCrossValidation() {
      var xs = HeuristicLab.Common.SequenceGenerator.GenerateSteps(-3.5, 3.5, 0.02, includeEnd: true).ToArray();
      var ys = xs.Select(xi => alglib.normaldistr.normaldistribution(xi)); // 1.0 / (Math.Sqrt(2 * Math.PI) * Math.Exp(-0.5 * xi * xi))).ToArray();

      alglib.hqrndstate state;
      alglib.hqrndseed(1234, 5678, out state);
      var ys_noise = ys.Select(yi => yi + alglib.hqrndnormal(state) * 0.01).ToArray();

      double bestRho = -15;
      double best_loo_rmse = double.PositiveInfinity;
      var clock = new Stopwatch();
      clock.Start();
      int iters = 0;
      for (int rho = -15; rho <= 15; rho++) {
        double loo_rmse;
        double avgTrainRmse;
        double[] predictions;
        Splines.CalculatePenalizedRegressionSpline(xs, ys_noise, rho, "y", new string[] { "x" }, out avgTrainRmse, out loo_rmse, out predictions);
        iters++;
        Console.WriteLine("{0} {1} {2}", rho, avgTrainRmse, loo_rmse);
        if (loo_rmse < best_loo_rmse) {
          best_loo_rmse = loo_rmse;
          bestRho = rho;
        }
      }
      clock.Stop();
      Console.WriteLine("Best rho {0}, RMSE (LOO): {1}, ms/run {2}", bestRho, best_loo_rmse, clock.ElapsedMilliseconds / (double)iters);
    }

    [TestMethod]
    public void TestReinschSplineCrossValidation() {
      var xs = HeuristicLab.Common.SequenceGenerator.GenerateSteps(-3.5, 3.5, 0.02, includeEnd: true).ToList();
      var ys = xs.Select(xi => alglib.normaldistr.normaldistribution(xi)); // 1.0 / (Math.Sqrt(2 * Math.PI) * Math.Exp(-0.5 * xi * xi))).ToArray();

      alglib.hqrndstate state;
      alglib.hqrndseed(1234, 5678, out state);
      var ys_noise = ys.Select(yi => yi + alglib.hqrndnormal(state) * 0.01).ToList();

      var tol = ys_noise.StandardDeviation();

      var ds = new Dataset(new string[] { "x", "y" }, new[] { xs, ys_noise });
      var rows = Enumerable.Range(0, xs.Count);

      var bestTol = double.PositiveInfinity;
      var bestLooRmse = double.PositiveInfinity;
      var clock = new Stopwatch();
      clock.Start();
      var iters = 0;
      while (tol > 0.0001) {
        double loo_rmse;
        double avgTrainRmse;
        var model = Splines.CalculateSmoothingSplineReinsch(
          xs.ToArray(), ys_noise.ToArray(), tol, "y", new string[] { "x" }, out avgTrainRmse, out loo_rmse);
        var y_pred = model.GetEstimatedValues(ds, rows);

        Console.WriteLine("{0} {1} {2}", tol, avgTrainRmse, loo_rmse);
        if (loo_rmse < bestLooRmse) {
          bestLooRmse = loo_rmse;
          bestTol = tol;
        }
        tol *= 0.8;
        iters++;
      }
      clock.Stop();
      Console.WriteLine("Best tolerance {0}, RMSE (LOO): {1}, ms/run {2}", bestTol, bestLooRmse, clock.ElapsedMilliseconds / (double)iters);
    }

    [TestMethod]
    public void TestReinschSplineAutomaticTolerance() {
      var xs = HeuristicLab.Common.SequenceGenerator.GenerateSteps(-3.5, 3.5, 0.02, includeEnd: true).ToList();
      var ys = xs.Select(xi => alglib.normaldistr.normaldistribution(xi)); // 1.0 / (Math.Sqrt(2 * Math.PI) * Math.Exp(-0.5 * xi * xi))).ToArray();

      alglib.hqrndstate state;
      alglib.hqrndseed(1234, 5678, out state);
      var ys_noise = ys.Select(yi => yi + alglib.hqrndnormal(state) * 0.01).ToList();

      double optTol;
      double looRMSE;
      Splines.CalculateSmoothingSplineReinsch(xs.ToArray(), ys_noise.ToArray(), new string[] { "x" }, "y", out optTol, out looRMSE);

      Console.WriteLine("Best tolerance {0}, RMSE (LOO): {1}", optTol, looRMSE);
    }

    [TestMethod]
    public void TestGAM() {
      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")));

      var gam = new GAM();
      gam.MaxIterations = 10;
      gam.MaxInteractions = 3;
      gam.Problem.ProblemData = problemData;
      gam.Start();

      var solution = (IRegressionSolution)gam.Results["Ensemble solution"].Value;

      Console.WriteLine("RMSE (train) {0}", solution.TrainingRootMeanSquaredError);
      Console.WriteLine("RMSE (test) {0}", solution.TestRootMeanSquaredError);
    }

  }
}