source: branches/MCTS-SymbReg-2796/Tests/HeuristicLab.Algorithms.DataAnalysis-3.4/MctsSymbolicRegressionTest.cs @ 15420

using System;
using System.Collections.Generic;
using System.Linq;
using System.Threading;
using HeuristicLab.Algorithms.DataAnalysis.MctsSymbolicRegression.Policies;
using HeuristicLab.Data;
using HeuristicLab.Optimization;
using HeuristicLab.Problems.DataAnalysis;
using HeuristicLab.Problems.Instances.DataAnalysis;
using HeuristicLab.Random;
using Microsoft.VisualStudio.TestTools.UnitTesting;

namespace HeuristicLab.Algorithms.DataAnalysis.MctsSymbolicRegression {
  [TestClass()]
  public class MctsSymbolicRegressionTest {
    #region expression hashing
    [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "short")]
    public void ExprHashTest() {
      int nParams;
      byte[] code;

      {
        // addition of variables
        var codeGen = new CodeGenerator();
        codeGen.Emit2(MctsSymbolicRegression.OpCodes.LoadVar, 1);
        codeGen.Emit2(MctsSymbolicRegression.OpCodes.LoadVar, 2);
        codeGen.Emit1(OpCodes.Add);
        codeGen.Emit1(OpCodes.Exit);
        codeGen.GetCode(out code, out nParams);
        var h1 = ExprHash.GetHash(code, nParams);

        codeGen = new CodeGenerator();
        codeGen.Emit2(MctsSymbolicRegression.OpCodes.LoadVar, 2);
        codeGen.Emit2(MctsSymbolicRegression.OpCodes.LoadVar, 1);
        codeGen.Emit1(OpCodes.Add);
        codeGen.Emit1(OpCodes.Exit);
        codeGen.GetCode(out code, out nParams);
        var h2 = ExprHash.GetHash(code, nParams);

        Assert.AreEqual(h1, h2);
      }

      {
        // multiplication of variables
        var codeGen = new CodeGenerator();
        codeGen.Emit2(MctsSymbolicRegression.OpCodes.LoadVar, 1);
        codeGen.Emit2(MctsSymbolicRegression.OpCodes.LoadVar, 2);
        codeGen.Emit1(OpCodes.Mul);
        codeGen.Emit1(OpCodes.Exit);
        codeGen.GetCode(out code, out nParams);
        var h1 = ExprHash.GetHash(code, nParams);

        codeGen = new CodeGenerator();
        codeGen.Emit2(MctsSymbolicRegression.OpCodes.LoadVar, 2);
        codeGen.Emit2(MctsSymbolicRegression.OpCodes.LoadVar, 1);
        codeGen.Emit1(OpCodes.Mul);
        codeGen.Emit1(OpCodes.Exit);
        codeGen.GetCode(out code, out nParams);
        var h2 = ExprHash.GetHash(code, nParams);

        Assert.AreEqual(h1, h2);
      }

      {
        // distributivity 
        var codeGen = new CodeGenerator();
        codeGen.Emit2(MctsSymbolicRegression.OpCodes.LoadVar, 1);
        codeGen.Emit2(MctsSymbolicRegression.OpCodes.LoadVar, 2);
        codeGen.Emit1(OpCodes.Add);
        codeGen.Emit2(OpCodes.LoadVar, 3);
        codeGen.Emit1(OpCodes.Mul);
        codeGen.Emit1(OpCodes.Exit);
        codeGen.GetCode(out code, out nParams);
        var h1 = ExprHash.GetHash(code, nParams);

        codeGen = new CodeGenerator();
        codeGen.Emit2(MctsSymbolicRegression.OpCodes.LoadVar, 2);
        codeGen.Emit2(MctsSymbolicRegression.OpCodes.LoadVar, 3);
        codeGen.Emit1(OpCodes.Mul);
        codeGen.Emit2(MctsSymbolicRegression.OpCodes.LoadVar, 1);
        codeGen.Emit2(OpCodes.LoadVar, 3);
        codeGen.Emit1(OpCodes.Mul);
        codeGen.Emit1(OpCodes.Add);
        codeGen.Emit1(OpCodes.Exit);
        codeGen.GetCode(out code, out nParams);
        var h2 = ExprHash.GetHash(code, nParams);

        Assert.AreEqual(h1, h2);
      }


      {
        // div 
        var codeGen = new CodeGenerator();
        codeGen.Emit2(MctsSymbolicRegression.OpCodes.LoadVar, 1);
        codeGen.Emit2(MctsSymbolicRegression.OpCodes.LoadVar, 2);
        codeGen.Emit1(MctsSymbolicRegression.OpCodes.Mul);
        codeGen.Emit1(OpCodes.Inv);
        codeGen.Emit1(OpCodes.Exit);
        codeGen.GetCode(out code, out nParams);
        var h1 = ExprHash.GetHash(code, nParams);

        codeGen = new CodeGenerator();
        codeGen.Emit2(MctsSymbolicRegression.OpCodes.LoadVar, 1);
        codeGen.Emit1(OpCodes.Inv);
        codeGen.Emit2(MctsSymbolicRegression.OpCodes.LoadVar, 2);
        codeGen.Emit1(OpCodes.Inv);
        codeGen.Emit1(MctsSymbolicRegression.OpCodes.Mul);
        codeGen.Emit1(OpCodes.Exit);
        codeGen.GetCode(out code, out nParams);
        var h2 = ExprHash.GetHash(code, nParams);

        Assert.AreEqual(h1, h2);
      }
      {
        // exp
        var codeGen = new CodeGenerator();
        codeGen.Emit2(MctsSymbolicRegression.OpCodes.LoadVar, 1);
        codeGen.Emit2(MctsSymbolicRegression.OpCodes.LoadVar, 2);
        codeGen.Emit1(MctsSymbolicRegression.OpCodes.Add);
        codeGen.Emit1(OpCodes.Exp);
        codeGen.Emit1(OpCodes.Exit);
        codeGen.GetCode(out code, out nParams);
        var h1 = ExprHash.GetHash(code, nParams);

        codeGen = new CodeGenerator();
        codeGen.Emit2(MctsSymbolicRegression.OpCodes.LoadVar, 1);
        codeGen.Emit1(OpCodes.Exp);
        codeGen.Emit2(MctsSymbolicRegression.OpCodes.LoadVar, 2);
        codeGen.Emit1(OpCodes.Exp);
        codeGen.Emit1(MctsSymbolicRegression.OpCodes.Mul);
        codeGen.GetCode(out code, out nParams);
        codeGen.Emit1(OpCodes.Exit);
        var h2 = ExprHash.GetHash(code, nParams);

        Assert.AreEqual(h1, h2);
      }
      {
        // log
        var codeGen = new CodeGenerator();
        codeGen.Emit2(MctsSymbolicRegression.OpCodes.LoadVar, 1);
        codeGen.Emit2(MctsSymbolicRegression.OpCodes.LoadVar, 2);
        codeGen.Emit1(MctsSymbolicRegression.OpCodes.Mul);
        codeGen.Emit1(OpCodes.Log);
        codeGen.Emit1(OpCodes.Exit);
        codeGen.GetCode(out code, out nParams);
        var h1 = ExprHash.GetHash(code, nParams);

        codeGen = new CodeGenerator();
        codeGen.Emit2(MctsSymbolicRegression.OpCodes.LoadVar, 1);
        codeGen.Emit1(OpCodes.Log);
        codeGen.Emit2(MctsSymbolicRegression.OpCodes.LoadVar, 2);
        codeGen.Emit1(OpCodes.Log);
        codeGen.Emit1(MctsSymbolicRegression.OpCodes.Add);
        codeGen.Emit1(OpCodes.Exit);
        codeGen.GetCode(out code, out nParams);
        var h2 = ExprHash.GetHash(code, nParams);

        Assert.AreEqual(h1, h2);
      }

      {
        // x1 + x1 is equivalent to x1
        var codeGen = new CodeGenerator();
        codeGen.Emit2(MctsSymbolicRegression.OpCodes.LoadVar, 1);
        codeGen.Emit2(MctsSymbolicRegression.OpCodes.LoadVar, 1);
        codeGen.Emit1(OpCodes.Add);
        codeGen.Emit1(OpCodes.Exit);
        codeGen.GetCode(out code, out nParams);
        var h1 = ExprHash.GetHash(code, nParams);

        codeGen = new CodeGenerator();
        codeGen.Emit2(MctsSymbolicRegression.OpCodes.LoadVar, 1);
        codeGen.Emit1(OpCodes.Exit);
        codeGen.GetCode(out code, out nParams);
        var h2 = ExprHash.GetHash(code, nParams);

        Assert.AreEqual(h1, h2);
      }
      {
        // c1*x1 + c2*x1 is equivalent to c3*x1
        var codeGen = new CodeGenerator();
        codeGen.Emit1(MctsSymbolicRegression.OpCodes.LoadParamN);
        codeGen.Emit2(MctsSymbolicRegression.OpCodes.LoadVar, 1);
        codeGen.Emit1(MctsSymbolicRegression.OpCodes.Mul);

        codeGen.Emit1(MctsSymbolicRegression.OpCodes.LoadParamN);
        codeGen.Emit2(MctsSymbolicRegression.OpCodes.LoadVar, 1);
        codeGen.Emit1(MctsSymbolicRegression.OpCodes.Mul);

        codeGen.Emit1(OpCodes.Add);
        codeGen.Emit1(OpCodes.Exit);
        codeGen.GetCode(out code, out nParams);
        var h1 = ExprHash.GetHash(code, nParams);

        codeGen = new CodeGenerator();
        codeGen.Emit1(MctsSymbolicRegression.OpCodes.LoadParamN);
        codeGen.Emit2(MctsSymbolicRegression.OpCodes.LoadVar, 1);
        codeGen.Emit1(MctsSymbolicRegression.OpCodes.Mul);
        codeGen.Emit1(OpCodes.Exit);
        codeGen.GetCode(out code, out nParams);
        var h2 = ExprHash.GetHash(code, nParams);

        Assert.AreEqual(h1, h2);
      }

      {
        var codeGen = new CodeGenerator();
        codeGen.Emit1(MctsSymbolicRegression.OpCodes.LoadConst0);
        codeGen.Emit1(MctsSymbolicRegression.OpCodes.LoadConst1);
        codeGen.Emit1(MctsSymbolicRegression.OpCodes.LoadParamN);
        codeGen.Emit2(MctsSymbolicRegression.OpCodes.LoadVar, 1);
        codeGen.Emit1(MctsSymbolicRegression.OpCodes.Mul);

        codeGen.Emit1(MctsSymbolicRegression.OpCodes.LoadParamN);
        codeGen.Emit2(MctsSymbolicRegression.OpCodes.LoadVar, 1);
        codeGen.Emit1(MctsSymbolicRegression.OpCodes.Mul);

        codeGen.Emit1(OpCodes.Add);

        codeGen.Emit1(MctsSymbolicRegression.OpCodes.Mul);
        codeGen.Emit1(MctsSymbolicRegression.OpCodes.Add);

        codeGen.Emit1(OpCodes.Exit);
        codeGen.GetCode(out code, out nParams);
        var h1 = ExprHash.GetHash(code, nParams);

        codeGen = new CodeGenerator();
        codeGen.Emit1(MctsSymbolicRegression.OpCodes.LoadConst0);
        codeGen.Emit1(MctsSymbolicRegression.OpCodes.LoadConst1);
        codeGen.Emit1(MctsSymbolicRegression.OpCodes.LoadParamN);
        codeGen.Emit2(MctsSymbolicRegression.OpCodes.LoadVar, 1);
        codeGen.Emit1(MctsSymbolicRegression.OpCodes.Mul);
        codeGen.Emit1(MctsSymbolicRegression.OpCodes.Mul);
        codeGen.Emit1(MctsSymbolicRegression.OpCodes.Add);
        codeGen.Emit1(OpCodes.Exit);
        codeGen.GetCode(out code, out nParams);
        var h2 = ExprHash.GetHash(code, nParams);

        Assert.AreEqual(h1, h2);
      }
    }
    #endregion

    #region number of solutions
    // the algorithm should visits each solution only once
    [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "short")]
    public void MctsSymbRegNumberOfSolutionsOneVariable() {
      // this problem has only one variable
      var provider = new NguyenInstanceProvider();
      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("F1 ")));
      {
        // possible solutions with max one variable reference:
        // x
        // log(x)
        // exp(x)
        // 1/x
        TestMctsNumberOfSolutions(regProblem, 1, 4);
      }
      {
        // possible solutions with max two variable references:
        // TODO: equal terms should not be allowed (see ConstraintHandler)
        // x
        // log(x)
        // exp(x)
        // 1/x
        //              -- 4
        // x * x
        // x * log(x)
        // x * exp(x)
        // x * 1/x
        // x + x                                        ?
        // x + log(x)
        // x + exp(x)
        // x + 1/x
        //              -- 8
        // log(x) * log(x)
        // log(x) * exp(x)
        // log(x) * 1/x
        // log(x) + log(x)                              ?
        // log(x) + exp(x)                              ?
        // log(x) + 1/x
        //              -- 6
        // exp(x) * exp(x)
        // exp(x) * 1/x
        // exp(x) + exp(x)                              ?
        // exp(x) + 1/x
        //              -- 4
        // 1/x * 1/x
        // 1/x + 1/x                                    ?
        //              -- 2
        // log(x+x)                                     ?
        // log(x*x)
        // exp(x*x)
        // 1/(x+x)                                      ?
        // 1/(x*x)
        //              -- 5


        TestMctsNumberOfSolutions(regProblem, 2, 29);
      }
      {
        // possible solutions with max three variable references:
        // without log and inv
        // x
        // exp(x)
        //              -- 2
        // x * x
        // x + x                                            ?
        // x * exp(x)
        // x + exp(x)
        // exp(x) * exp(x)
        // exp(x) + exp(x)                                  ?
        // exp(x*x)
        //              -- 7
        // x * x * x
        // x + x * x                                       
        // x + x + x                                        ?
        // x * x * exp(x)
        // x + x * exp(x)                                   
        // x + x + exp(x)                                   ?
        // exp(x) + x*x
        // exp(x) + x*exp(x)                                
        // x + exp(x) * exp(x)                              
        // x + exp(x) + exp(x)                              ?
        // x * exp(x) * exp(x)
        // x * exp(x*x)
        // x + exp(x*x)
        //              -- 13

        // exp(x) * exp(x) * exp(x)
        // exp(x) + exp(x) * exp(x)                         
        // exp(x) + exp(x) + exp(x)                         ?
        //              -- 3

        // exp(x)   * exp(x*x)
        // exp(x)   + exp(x*x)
        //              -- 2
        // exp(x*x*x)
        //              -- 1
        TestMctsNumberOfSolutions(regProblem, 3, 2 + 7 + 13 + 3 + 2 + 1, allowLog: false, allowInv: false);
      }
      {
        // possible solutions with max 4 variable references:
        // without exp, log and inv
        // x       
        // x*x
        // x+x                                             ?
        // x*x*x
        // x+x*x
        // x+x+x                                           ?
        // x*x*x*x
        // x+x*x*x
        // x*x+x*x                                         ?
        // x+x+x*x                                         ?
        // x+x+x+x                                         ?

        TestMctsNumberOfSolutions(regProblem, 4, 11, allowLog: false, allowInv: false, allowExp: false);
      }
      {
        // possible solutions with max 5 variable references:
        // without exp, log and inv
        // x       
        // xx
        // x+x                                             ?
        // xxx
        // x+xx
        // x+x+x                                           ?
        // xxxx
        // x+xxx
        // xx+xx                                           ?
        // x+x+xx                                          ?
        // x+x+x+x                                         ?
        // xxxxx 
        // x+xxxx
        // xx+xxx
        // x+x+xxx                                         ?
        // x+xx+xx                                         ?
        // x+x+x+xx                                        ?
        // x+x+x+x+x                                       ?
        TestMctsNumberOfSolutions(regProblem, 5, 18, allowLog: false, allowInv: false, allowExp: false);
      }
    }

    [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "short")]
    public void MctsSymbRegNumberOfSolutionsTwoVariables() {
      // this problem has only two input variables
      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.NguyenInstanceProvider();
      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("F9 ")));
      {
        // possible solutions with max one variable reference:
        // x
        // log(x)
        // exp(x)
        // 1/x
        // y
        // log(y)
        // exp(y)
        // 1/y
        TestMctsNumberOfSolutions(regProblem, 1, 8);
      }
      {
        // possible solutions with max one variable reference:
        // without log and inv

        // x
        // exp(x)
        // y
        // exp(y)
        TestMctsNumberOfSolutions(regProblem, 1, 4, allowLog: false, allowInv: false);
      }
      {
        // possible solutions with max two variable references:
        // without log and inv

        // x
        // y
        // exp(x)
        // exp(y)
        //                  -- 4
        // x (*|+) x
        // x (*|+) exp(x)
        // x (*|+) y
        // x (*|+) exp(y)
        //                  -- 8
        // exp(x) (*|+) exp(x)
        // exp(x) (*|+) exp(y)
        //                  -- 4
        // y (*|+) y
        // y (*|+) exp(x)
        // y (*|+) exp(y)
        //                  -- 6
        // exp(y) (*|+) exp(y)
        //                  -- 2
        //
        // exp(x*x)
        // exp(x*y)
        // exp(y*y)
        //                  -- 3

        TestMctsNumberOfSolutions(regProblem, 2, 4 + 8 + 4 + 6 + 2 + 3, allowLog: false, allowInv: false);
      }

      {
        // possible solutions with max two variable references:
        // without exp and sum
        // x
        // y
        // log(x)
        // log(y)
        // inv(x)
        // inv(y)
        //              -- 6
        // x * x
        // x * y
        // x * log(x)
        // x * log(y)
        // x * inv(x)
        // x * inv(y)
        //              -- 6
        // log(x) * log(x)
        // log(x) * log(y)
        // log(x) * inv(x)
        // log(x) * inv(y)
        //              -- 4
        // inv(x) * inv(x)
        // inv(x) * inv(y)
        //              -- 2
        // y * y
        // y * log(x)
        // y * log(y)
        // y * inv(x)
        // y * inv(y)
        //              -- 5
        // log(y) * log(y)
        // log(y) * inv(x)
        // log(y) * inv(y)
        //              -- 3
        // inv(y) * inv(y)
        //              -- 1
        // log(x*x)
        // log(x*y)
        // log(y*y)

        // inv(x*x)
        // inv(x*y)
        // inv(y*y)
        //             -- 6
        // log(x+x)
        // log(x+y)
        // log(y+y)

        // inv(x+x)
        // inv(x+y)
        // inv(y+y)
        //             -- 6
        TestMctsNumberOfSolutions(regProblem, 2, 6 + 6 + 4 + 2 + 5 + 3 + 1 + 6 + 6, allowExp: false, allowSum: false);
      }
    }
    #endregion


    #region test structure search (no constants)
    [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "short")]
    public void MctsSymbReg_NoConstants_Nguyen1() {
      // x³ + x² + x
      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.NguyenInstanceProvider(seed: 1234);
      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("F1 ")));
      TestMctsWithoutConstants(regProblem, nVarRefs: 10, allowExp: false, allowLog: false, allowInv: false);
    }
    [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "short")]
    public void MctsSymbReg_NoConstants_Nguyen2() {
      // x^4 + x³ + x² + x
      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.NguyenInstanceProvider(seed: 1234);
      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("F2 ")));
      TestMctsWithoutConstants(regProblem, allowExp: false, allowLog: false, allowInv: false);
    }
    [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "short")]
    public void MctsSymbReg_NoConstants_Nguyen3() {
      // x^5 + x^4 + x³ + x² + x
      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.NguyenInstanceProvider(seed: 1234);
      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("F3 ")));
      TestMctsWithoutConstants(regProblem, nVarRefs: 15, iterations: 1000000, allowExp: false, allowLog: false, allowInv: false);
    }
    [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "short")]
    public void MctsSymbReg_NoConstants_Nguyen4() {
      // x^6 + x^5 + x^4 + x³ + x² + x
      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.NguyenInstanceProvider(seed: 1234);
      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("F4 ")));
      TestMctsWithoutConstants(regProblem, nVarRefs: 25, iterations: 1000000, allowExp: false, allowLog: false, allowInv: false);
    }

    [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "short")]
    public void MctsSymbReg_NoConstants_Nguyen7() {
      // log(x + 1) + log(x² + 1)
      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.NguyenInstanceProvider(seed: 1234);
      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("F7 ")));
      TestMctsWithoutConstants(regProblem, nVarRefs: 10, iterations: 100000, allowExp: false, allowLog: true, allowInv: false);
    }

    [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "short")]
    public void MctsSymbReg_NoConstants_Poly10_Part1() {
      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.VariousInstanceProvider(seed: 1234);
      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("Poly-10")));

      //  Y = X1*X2 + X3*X4 + X5*X6 + X1*X7*X9 + X3*X6*X10
      //  Y' = X1*X2 + X3*X4 + X5*X6
      // simplify problem by changing target
      var ds = ((Dataset)regProblem.Dataset).ToModifiable();
      var ys = ds.GetDoubleValues("Y").ToArray();
      var x1 = ds.GetDoubleValues("X1").ToArray();
      var x2 = ds.GetDoubleValues("X2").ToArray();
      var x3 = ds.GetDoubleValues("X3").ToArray();
      var x4 = ds.GetDoubleValues("X4").ToArray();
      var x5 = ds.GetDoubleValues("X5").ToArray();
      var x6 = ds.GetDoubleValues("X6").ToArray();
      var x7 = ds.GetDoubleValues("X7").ToArray();
      var x8 = ds.GetDoubleValues("X8").ToArray();
      var x9 = ds.GetDoubleValues("X9").ToArray();
      var x10 = ds.GetDoubleValues("X10").ToArray();
      for (int i = 0; i < ys.Length; i++) {
        ys[i] -= x1[i] * x7[i] * x9[i];
        ys[i] -= x3[i] * x6[i] * x10[i];
      }
      ds.ReplaceVariable("Y", ys.ToList());

      var modifiedProblemData = new RegressionProblemData(ds, regProblem.AllowedInputVariables, regProblem.TargetVariable);


      TestMctsWithoutConstants(modifiedProblemData, nVarRefs: 15, iterations: 100000, allowExp: false, allowLog: false, allowInv: false);
    }

    [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "short")]
    public void MctsSymbReg_NoConstants_Poly10_Part2() {
      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.VariousInstanceProvider(seed: 1234);
      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("Poly-10")));

      //  Y = X1*X2 + X3*X4 + X5*X6 + X1*X7*X9 + X3*X6*X10
      //  Y' = X1*X7*X9 + X3*X6*X10
      // simplify problem by changing target
      var ds = ((Dataset)regProblem.Dataset).ToModifiable();
      var ys = ds.GetDoubleValues("Y").ToArray();
      var x1 = ds.GetDoubleValues("X1").ToArray();
      var x2 = ds.GetDoubleValues("X2").ToArray();
      var x3 = ds.GetDoubleValues("X3").ToArray();
      var x4 = ds.GetDoubleValues("X4").ToArray();
      var x5 = ds.GetDoubleValues("X5").ToArray();
      var x6 = ds.GetDoubleValues("X6").ToArray();
      var x7 = ds.GetDoubleValues("X7").ToArray();
      var x8 = ds.GetDoubleValues("X8").ToArray();
      var x9 = ds.GetDoubleValues("X9").ToArray();
      var x10 = ds.GetDoubleValues("X10").ToArray();
      for (int i = 0; i < ys.Length; i++) {
        ys[i] -= x1[i] * x2[i];
        ys[i] -= x3[i] * x4[i];
        ys[i] -= x5[i] * x6[i];
      }
      ds.ReplaceVariable("Y", ys.ToList());

      var modifiedProblemData = new RegressionProblemData(ds, regProblem.AllowedInputVariables, regProblem.TargetVariable);


      TestMctsWithoutConstants(modifiedProblemData, nVarRefs: 15, iterations: 100000, allowExp: false, allowLog: false, allowInv: false);
    }

    [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "short")]
    public void MctsSymbReg_NoConstants_Poly10_Part3() {
      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.VariousInstanceProvider(seed: 1234);
      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("Poly-10")));

      //  Y = X1*X2 + X3*X4 + X5*X6 + X1*X7*X9 + X3*X6*X10
      //  Y' = X1*X2 + X1*X7*X9
      // simplify problem by changing target
      var ds = ((Dataset)regProblem.Dataset).ToModifiable();
      var ys = ds.GetDoubleValues("Y").ToArray();
      var x1 = ds.GetDoubleValues("X1").ToArray();
      var x2 = ds.GetDoubleValues("X2").ToArray();
      var x3 = ds.GetDoubleValues("X3").ToArray();
      var x4 = ds.GetDoubleValues("X4").ToArray();
      var x5 = ds.GetDoubleValues("X5").ToArray();
      var x6 = ds.GetDoubleValues("X6").ToArray();
      var x7 = ds.GetDoubleValues("X7").ToArray();
      var x8 = ds.GetDoubleValues("X8").ToArray();
      var x9 = ds.GetDoubleValues("X9").ToArray();
      var x10 = ds.GetDoubleValues("X10").ToArray();
      for (int i = 0; i < ys.Length; i++) {
        ys[i] -= x3[i] * x4[i];
        ys[i] -= x5[i] * x6[i];
        ys[i] -= x3[i] * x6[i] * x10[i];
      }
      ds.ReplaceVariable("Y", ys.ToList());

      var modifiedProblemData = new RegressionProblemData(ds, regProblem.AllowedInputVariables, regProblem.TargetVariable);


      TestMctsWithoutConstants(modifiedProblemData, nVarRefs: 15, iterations: 100000, allowExp: false, allowLog: false, allowInv: false);
    }

    [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "short")]
    public void MctsSymbReg_NoConstants_Poly10_Part4() {
      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.VariousInstanceProvider(seed: 1234);
      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("Poly-10")));

      //  Y = X1*X2 + X3*X4 + X5*X6 + X1*X7*X9 + X3*X6*X10
      //  Y' = X3*X4 + X5*X6 + X3*X6*X10
      // simplify problem by changing target
      var ds = ((Dataset)regProblem.Dataset).ToModifiable();
      var ys = ds.GetDoubleValues("Y").ToArray();
      var x1 = ds.GetDoubleValues("X1").ToArray();
      var x2 = ds.GetDoubleValues("X2").ToArray();
      var x3 = ds.GetDoubleValues("X3").ToArray();
      var x4 = ds.GetDoubleValues("X4").ToArray();
      var x5 = ds.GetDoubleValues("X5").ToArray();
      var x6 = ds.GetDoubleValues("X6").ToArray();
      var x7 = ds.GetDoubleValues("X7").ToArray();
      var x8 = ds.GetDoubleValues("X8").ToArray();
      var x9 = ds.GetDoubleValues("X9").ToArray();
      var x10 = ds.GetDoubleValues("X10").ToArray();
      for (int i = 0; i < ys.Length; i++) {
        ys[i] -= x1[i] * x2[i];
        ys[i] -= x1[i] * x7[i] * x9[i];
      }
      ds.ReplaceVariable("Y", ys.ToList());
      var modifiedProblemData = new RegressionProblemData(ds, regProblem.AllowedInputVariables, regProblem.TargetVariable);


      TestMctsWithoutConstants(modifiedProblemData, nVarRefs: 15, iterations: 100000, allowExp: false, allowLog: false, allowInv: false);
    }

    [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "short")]
    public void MctsSymbReg_NoConstants_Poly10_Part5() {
      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.VariousInstanceProvider(seed: 1234);
      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("Poly-10")));

      //  Y = X1*X2 + X3*X4 + X5*X6 + X1*X7*X9 + X3*X6*X10
      //  Y' = X1*X2 + X3*X4 + X5*X6 + X1*X7*X9
      // simplify problem by changing target
      var ds = ((Dataset)regProblem.Dataset).ToModifiable();
      var ys = ds.GetDoubleValues("Y").ToArray();
      var x1 = ds.GetDoubleValues("X1").ToArray();
      var x2 = ds.GetDoubleValues("X2").ToArray();
      var x3 = ds.GetDoubleValues("X3").ToArray();
      var x4 = ds.GetDoubleValues("X4").ToArray();
      var x5 = ds.GetDoubleValues("X5").ToArray();
      var x6 = ds.GetDoubleValues("X6").ToArray();
      var x7 = ds.GetDoubleValues("X7").ToArray();
      var x8 = ds.GetDoubleValues("X8").ToArray();
      var x9 = ds.GetDoubleValues("X9").ToArray();
      var x10 = ds.GetDoubleValues("X10").ToArray();
      for (int i = 0; i < ys.Length; i++) {
        ys[i] -= x3[i] * x6[i] * x10[i];
      }
      ds.ReplaceVariable("Y", ys.ToList());
      var modifiedProblemData = new RegressionProblemData(ds, regProblem.AllowedInputVariables, regProblem.TargetVariable);


      TestMctsWithoutConstants(modifiedProblemData, nVarRefs: 15, iterations: 100000, allowExp: false, allowLog: false, allowInv: false);
    }

    [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "short")]
    public void MctsSymbReg_NoConstants_Poly10_Part6() {
      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.VariousInstanceProvider(seed: 1234);
      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("Poly-10")));

      //  Y = X1*X2 + X3*X4 + X5*X6 + X1*X7*X9 + X3*X6*X10
      //  Y' = X1*X2 + X3*X4 + X5*X6 + X3*X6*X10
      // simplify problem by changing target
      var ds = ((Dataset)regProblem.Dataset).ToModifiable();
      var ys = ds.GetDoubleValues("Y").ToArray();
      var x1 = ds.GetDoubleValues("X1").ToArray();
      var x2 = ds.GetDoubleValues("X2").ToArray();
      var x3 = ds.GetDoubleValues("X3").ToArray();
      var x4 = ds.GetDoubleValues("X4").ToArray();
      var x5 = ds.GetDoubleValues("X5").ToArray();
      var x6 = ds.GetDoubleValues("X6").ToArray();
      var x7 = ds.GetDoubleValues("X7").ToArray();
      var x8 = ds.GetDoubleValues("X8").ToArray();
      var x9 = ds.GetDoubleValues("X9").ToArray();
      var x10 = ds.GetDoubleValues("X10").ToArray();
      for (int i = 0; i < ys.Length; i++) {
        ys[i] -= x1[i] * x7[i] * x9[i];
      }
      ds.ReplaceVariable("Y", ys.ToList());
      var modifiedProblemData = new RegressionProblemData(ds, regProblem.AllowedInputVariables, regProblem.TargetVariable);


      TestMctsWithoutConstants(modifiedProblemData, nVarRefs: 9, iterations: 100000, allowExp: false, allowLog: false, allowInv: false);
    }


    [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "long")]
    public void MctsSymbReg_NoConstants_Poly10_250rows() {
      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.VariousInstanceProvider(seed: 1234);
      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("Poly-10")));
      regProblem.TrainingPartition.Start = 0;
      regProblem.TrainingPartition.End = regProblem.Dataset.Rows;
      regProblem.TestPartition.Start = 0;
      regProblem.TestPartition.End = 2;
      TestMctsWithoutConstants(regProblem, nVarRefs: 15, iterations: 200000, allowExp: false, allowLog: false, allowInv: false);
    }
    [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "long")]
    public void MctsSymbReg_NoConstants_Poly10_10000rows() {
      // as poly-10 but more rows
      var rand = new FastRandom(1234);
      var x1 = Enumerable.Range(0, 10000).Select(_ => rand.NextDouble()).ToList();
      var x2 = Enumerable.Range(0, 10000).Select(_ => rand.NextDouble()).ToList();
      var x3 = Enumerable.Range(0, 10000).Select(_ => rand.NextDouble()).ToList();
      var x4 = Enumerable.Range(0, 10000).Select(_ => rand.NextDouble()).ToList();
      var x5 = Enumerable.Range(0, 10000).Select(_ => rand.NextDouble()).ToList();
      var x6 = Enumerable.Range(0, 10000).Select(_ => rand.NextDouble()).ToList();
      var x7 = Enumerable.Range(0, 10000).Select(_ => rand.NextDouble()).ToList();
      var x8 = Enumerable.Range(0, 10000).Select(_ => rand.NextDouble()).ToList();
      var x9 = Enumerable.Range(0, 10000).Select(_ => rand.NextDouble()).ToList();
      var x10 = Enumerable.Range(0, 10000).Select(_ => rand.NextDouble()).ToList();
      var ys = new List<double>();
      for (int i = 0; i < x1.Count; i++) {
        ys.Add(x1[i] * x2[i] + x3[i] * x4[i] + x5[i] * x6[i] + x1[i] * x7[i] * x9[i] + x3[i] * x6[i] * x10[i]);
      }

      var ds = new Dataset(new string[] { "a", "b", "c", "d", "e", "f", "g", "h", "i", "j", "y" }, 
        new[] { x1, x2, x3, x4, x5, x6, x7, x8, x9, x10, ys });


      var problemData = new RegressionProblemData(ds, new string[] { "a", "b", "c", "d", "e", "f", "g", "h", "i", "j"}, "y");

      problemData.TrainingPartition.Start = 0;
      problemData.TrainingPartition.End = problemData.Dataset.Rows;
      problemData.TestPartition.Start = 0;
      problemData.TestPartition.End = 2; // must not be empty


      TestMctsWithoutConstants(problemData, nVarRefs: 15, iterations: 100000, allowExp: false, allowLog: false, allowInv: false);
    }

    [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "short")]
    public void MctsSymbReg_NoConstants_TwoVars() {

      // y = x1 + x2 + x1*x2 + x1*x2*x2 + x1*x1*x2
      var rand = new FastRandom(1234);
      var x1 = Enumerable.Range(0, 100).Select(_ => rand.NextDouble()).ToList();
      var x2 = Enumerable.Range(0, 100).Select(_ => rand.NextDouble()).ToList();
      var ys = x1.Zip(x2, (x1i, x2i) => x1i + x2i + x1i * x2i + x1i * x2i * x2i + x1i * x1i * x2i).ToList();

      var ds = new Dataset(new string[] { "a", "b", "y" }, new[] { x1, x2, ys });

      var problemData = new RegressionProblemData(ds, new string[] { "a", "b" }, "y");


      TestMctsWithoutConstants(problemData, nVarRefs: 10, iterations: 10000, allowExp: false, allowLog: false, allowInv: false);
    }

    [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "short")]
    public void MctsSymbReg_NoConstants_Misleading() {

      // y = a + baaaaa (the effect of the second term should be very small)
      // the alg will quickly find that a has big effect and will search below a
      // since we prevent a + a... the algorithm must find the correct expression via a + b...
      // however b has a small effect so the branch might not be identified as relevant

      var rand = new FastRandom(1234);
      var @as = Enumerable.Range(0, 100).Select(_ => rand.NextDouble()).ToList();
      var bs = Enumerable.Range(0, 100).Select(_ => rand.NextDouble()).ToList();
      var cs = Enumerable.Range(0, 100).Select(_ => rand.NextDouble() * 1.0e-3).ToList();
      var ds = Enumerable.Range(0, 100).Select(_ => rand.NextDouble()).ToList();
      var es = Enumerable.Range(0, 100).Select(_ => rand.NextDouble()).ToList();
      var ys = new double[@as.Count];
      for (int i = 0; i < ys.Length; i++)
        ys[i] = @as[i] + bs[i] + @as[i] * bs[i] * cs[i];

      var dataset = new Dataset(new string[] { "a", "b", "c", "d", "e", "y" }, new[] { @as, bs, cs, ds, es, ys.ToList() });

      var problemData = new RegressionProblemData(dataset, new string[] { "a", "b", "c", "d", "e" }, "y");


      TestMctsWithoutConstants(problemData, nVarRefs: 10, iterations: 10000, allowExp: false, allowLog: false, allowInv: false);
    }
    #endregion

    #region restricted structure but including numeric constants

    [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "short")]
    public void MctsSymbRegKeijzer7() {
      // ln(x)
      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.KeijzerInstanceProvider(seed: 1234);
      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("Keijzer 7 f(")));
      // some Keijzer problem instances have very large test partitions (here we are not concerened about test performance)
      if (regProblem.TestPartition.End - regProblem.TestPartition.Start > 1000) regProblem.TestPartition.End = regProblem.TestPartition.Start + 1000;
      TestMcts(regProblem, allowExp: false, allowLog: true, allowInv: false);
    }

    /*
    // [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "short")]
    public void MctsSymbRegBenchmarkNguyen5() {
      // sin(x²)cos(x) - 1
      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.NguyenInstanceProvider();
      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("F5 ")));
      TestMcts(regProblem);
    }
    // [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "short")]
    public void MctsSymbRegBenchmarkNguyen6() {
      // sin(x) + sin(x + x²)
      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.NguyenInstanceProvider();
      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("F6 ")));
      TestMcts(regProblem);
    }
    */
    [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "short")]
    public void MctsSymbRegBenchmarkNguyen7() {
      //  log(x + 1) + log(x² + 1)
      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.NguyenInstanceProvider(seed: 1234);
      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("F7 ")));
      TestMcts(regProblem, maxVariableReferences: 5, allowExp: false, allowLog: true, allowInv: false);
    }
    [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "short")]
    public void MctsSymbRegBenchmarkNguyen8() {
      // Sqrt(x)
      // = x ^ 0.5
      // = exp(0.5 * log(x))
      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.NguyenInstanceProvider(seed: 1234);
      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("F8 ")));
      TestMcts(regProblem, maxVariableReferences: 5, allowExp: true, allowLog: true, allowInv: false);
    }
    /*
    // [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "short")]
    public void MctsSymbRegBenchmarkNguyen9() {
      //  sin(x) + sin(y²)
      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.NguyenInstanceProvider();
      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("F9 ")));
      TestMcts(regProblem);
    }
    // [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "short")]
    public void MctsSymbRegBenchmarkNguyen10() {
      // 2sin(x)cos(y)
      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.NguyenInstanceProvider();
      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("F10 ")));
      TestMcts(regProblem);
    }
    */
    [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "short")]
    public void MctsSymbRegBenchmarkNguyen11() {
      // x ^ y  , x > 0, y > 0   
      // = exp(y * log(x))
      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.NguyenInstanceProvider(seed: 1234);
      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("F11 ")));
      TestMcts(regProblem, maxVariableReferences: 5, allowExp: true, allowLog: true, allowInv: false);
    }
    [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "short")]
    public void MctsSymbRegBenchmarkNguyen12() {
      // x^4 - x³ + y²/2 - y
      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.NguyenInstanceProvider(seed: 1234);
      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("F12 ")));
      TestMcts(regProblem, maxVariableReferences: 20, allowExp: false, allowLog: false, allowInv: false);
    }

    #endregion

    #region keijzer
    [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "long")]
    public void MctsSymbRegBenchmarkKeijzer5() {
      // (30 * x * z) / ((x - 10)  * y²)
      // = 30 x z / (xy² - y²)
      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.KeijzerInstanceProvider(seed: 1234);
      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("Keijzer 5 f(")));
      // some Keijzer problem instances have very large test partitions (here we are not concerened about test performance)
      if (regProblem.TestPartition.End - regProblem.TestPartition.Start > 1000) regProblem.TestPartition.End = regProblem.TestPartition.Start + 1000;
      TestMcts(regProblem, maxVariableReferences: 20, allowExp: false, allowLog: false, allowInv: true);
    }

    [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "short")]
    public void MctsSymbRegBenchmarkKeijzer6() {
      // Keijzer 6 f(x) = Sum(1 / i) From 1 to X  , x \in [0..120]
      // we can only approximate this
      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.KeijzerInstanceProvider(seed: 1234);
      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("Keijzer 6 f(")));
      // some Keijzer problem instances have very large test partitions (here we are not concerened about test performance)
      if (regProblem.TestPartition.End - regProblem.TestPartition.Start > 1000) regProblem.TestPartition.End = regProblem.TestPartition.Start + 1000;
      TestMcts(regProblem, maxVariableReferences: 20, allowExp: false, allowLog: false, allowInv: true);
    }


    [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "short")]
    public void MctsSymbRegBenchmarkKeijzer8() {
      // sqrt(x)
      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.KeijzerInstanceProvider(seed: 1234);
      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("Keijzer 8 f(")));
      // some Keijzer problem instances have very large test partitions (here we are not concerened about test performance)
      if (regProblem.TestPartition.End - regProblem.TestPartition.Start > 1000) regProblem.TestPartition.End = regProblem.TestPartition.Start + 1000;
      TestMcts(regProblem, maxVariableReferences: 5, allowExp: true, allowLog: true, allowInv: false);
    }

    [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "short")]
    public void MctsSymbRegBenchmarkKeijzer9() {
      // arcsinh(x)  i.e. ln(x + sqrt(x² + 1))
      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.KeijzerInstanceProvider(seed: 1234);
      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("Keijzer 9 f(")));
      // some Keijzer problem instances have very large test partitions (here we are not concerened about test performance)
      if (regProblem.TestPartition.End - regProblem.TestPartition.Start > 1000) regProblem.TestPartition.End = regProblem.TestPartition.Start + 1000;
      TestMcts(regProblem, maxVariableReferences: 5, allowExp: true, allowLog: true, allowInv: false);
    }

    /* 
    [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "short")]
    public void MctsSymbRegBenchmarkKeijzer11() {
      // xy + sin( (x-1) (y-1) )
      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.KeijzerInstanceProvider();
      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("Keijzer 11 f(")));
      // some Keijzer problem instances have very large test partitions (here we are not concerened about test performance)
      if (regProblem.TestPartition.End - regProblem.TestPartition.Start > 1000) regProblem.TestPartition.End = regProblem.TestPartition.Start + 1000;
      TestMcts(regProblem, successThreshold: 0.99); // cannot solve this yet
    }
     */
    [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "short")]
    public void MctsSymbRegBenchmarkKeijzer12() {
      // x^4 - x³ + y² / 2 - y,  same as Nguyen 12             
      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.KeijzerInstanceProvider(seed: 1234);
      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("Keijzer 12 f(")));
      // some Keijzer problem instances have very large test partitions (here we are not concerened about test performance)
      if (regProblem.TestPartition.End - regProblem.TestPartition.Start > 1000) regProblem.TestPartition.End = regProblem.TestPartition.Start + 1000;
      TestMcts(regProblem, maxVariableReferences: 15, allowExp: false, allowLog: false, allowInv: false);
    }
    [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "short")]
    public void MctsSymbRegBenchmarkKeijzer14() {
      // 8 / (2 + x² + y²)
      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.KeijzerInstanceProvider(seed: 1234);
      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("Keijzer 14 f(")));
      // some Keijzer problem instances have very large test partitions (here we are not concerened about test performance)
      if (regProblem.TestPartition.End - regProblem.TestPartition.Start > 1000) regProblem.TestPartition.End = regProblem.TestPartition.Start + 1000;
      TestMcts(regProblem, maxVariableReferences: 10, allowExp: false, allowLog: false, allowInv: true);
    }
    [TestMethod]
    [TestCategory("Algorithms.DataAnalysis")]
    [TestProperty("Time", "short")]
    public void MctsSymbRegBenchmarkKeijzer15() {
      // x³ / 5 + y³ / 2 - y - x
      var provider = new HeuristicLab.Problems.Instances.DataAnalysis.KeijzerInstanceProvider(seed: 1234);
      var regProblem = provider.LoadData(provider.GetDataDescriptors().Single(x => x.Name.Contains("Keijzer 15 f(")));
      // some Keijzer problem instances have very large test partitions (here we are not concerened about test performance)
      if (regProblem.TestPartition.End - regProblem.TestPartition.Start > 1000) regProblem.TestPartition.End = regProblem.TestPartition.Start + 1000;
      TestMcts(regProblem, maxVariableReferences: 10, allowExp: false, allowLog: false, allowInv: false);
    }
    #endregion

    private void TestMcts(IRegressionProblemData problemData,
      int iterations = 20000,
      double successThreshold = 0.99999,
      int maxVariableReferences = 5,
      bool allowExp = true,
      bool allowLog = true,
      bool allowInv = true,
      bool allowSum = true
      ) {
      var mctsSymbReg = new MctsSymbolicRegressionAlgorithm();
      var regProblem = new RegressionProblem();
      regProblem.ProblemDataParameter.Value = problemData;
      #region Algorithm Configuration
      mctsSymbReg.Problem = regProblem;
      mctsSymbReg.Iterations = iterations;
      mctsSymbReg.MaxVariableReferences = maxVariableReferences;

      mctsSymbReg.SetSeedRandomly = false;
      mctsSymbReg.Seed = 1234;
      mctsSymbReg.AllowedFactors.SetItemCheckedState(mctsSymbReg.AllowedFactors.Single(s => s.Value.Contains("exp")), allowExp);
      mctsSymbReg.AllowedFactors.SetItemCheckedState(mctsSymbReg.AllowedFactors.Single(s => s.Value.Contains("log")), allowLog);
      mctsSymbReg.AllowedFactors.SetItemCheckedState(mctsSymbReg.AllowedFactors.Single(s => s.Value.Contains("1 /")), allowInv);
      mctsSymbReg.AllowedFactors.SetItemCheckedState(mctsSymbReg.AllowedFactors.Single(s => s.Value.Contains("t1(x) + t2(x) + ... ")), allowSum);

      mctsSymbReg.ScaleVariables = true;
      mctsSymbReg.ConstantOptimizationIterations = 0;

      #endregion
      RunAlgorithm(mctsSymbReg);

      Console.WriteLine(mctsSymbReg.ExecutionTime);
      var eps = 1.0 - successThreshold;
      Assert.AreEqual(1.0, ((DoubleValue)mctsSymbReg.Results["Best solution quality (train)"].Value).Value, eps);
      Assert.AreEqual(1.0, ((DoubleValue)mctsSymbReg.Results["Best solution quality (test)"].Value).Value, eps);
    }


    private void TestMctsWithoutConstants(IRegressionProblemData problemData,
      int nVarRefs = 10,
      int iterations = 200000, double successThreshold = 0.99999,
      bool allowExp = true,
      bool allowLog = true,
      bool allowInv = true,
      bool allowSum = true
      ) {
      var mctsSymbReg = new MctsSymbolicRegressionAlgorithm();
      var regProblem = new RegressionProblem();
      regProblem.ProblemDataParameter.Value = problemData;
      #region Algorithm Configuration
      mctsSymbReg.Problem = regProblem;
      mctsSymbReg.Iterations = iterations;
      mctsSymbReg.MaxVariableReferences = nVarRefs;
      mctsSymbReg.SetSeedRandomly = false;
      mctsSymbReg.Seed = 1234;
      mctsSymbReg.AllowedFactors.SetItemCheckedState(mctsSymbReg.AllowedFactors.Single(s => s.Value.Contains("exp")), allowExp);
      mctsSymbReg.AllowedFactors.SetItemCheckedState(mctsSymbReg.AllowedFactors.Single(s => s.Value.Contains("log")), allowLog);
      mctsSymbReg.AllowedFactors.SetItemCheckedState(mctsSymbReg.AllowedFactors.Single(s => s.Value.Contains("1 /")), allowInv);
      mctsSymbReg.AllowedFactors.SetItemCheckedState(mctsSymbReg.AllowedFactors.Single(s => s.Value.Contains("t1(x) + t2(x) + ... ")), allowSum);

      // no constants
      mctsSymbReg.ScaleVariables = false;
      mctsSymbReg.ConstantOptimizationIterations = -1;

      // random policy
      // var epsPolicy = new EpsilonGreedy();
      // epsPolicy.Eps = 1.0;
      // mctsSymbReg.Policy = epsPolicy;

      // UCB tuned
      // var ucbTuned = new UcbTuned();
      // ucbTuned.C = 1.5; 
      // mctsSymbReg.Policy = ucbTuned;


      #endregion
      RunAlgorithm(mctsSymbReg);

      Console.WriteLine(mctsSymbReg.ExecutionTime);
      var eps = 1.0 - successThreshold;
      Assert.AreEqual(1.0, ((DoubleValue)mctsSymbReg.Results["Best solution quality (train)"].Value).Value, eps);
      Assert.AreEqual(1.0, ((DoubleValue)mctsSymbReg.Results["Best solution quality (test)"].Value).Value, eps);
    }

    private void TestMctsNumberOfSolutions(IRegressionProblemData problemData, int maxNumberOfVariables, int expectedNumberOfSolutions,
      bool allowProd = true,
      bool allowExp = true,
      bool allowLog = true,
      bool allowInv = true,
      bool allowSum = true
  ) {
      var mctsSymbReg = new MctsSymbolicRegressionAlgorithm();
      var regProblem = new RegressionProblem();
      regProblem.ProblemDataParameter.Value = problemData;
      #region Algorithm Configuration

      mctsSymbReg.SetSeedRandomly = false;
      mctsSymbReg.Seed = 1234;
      mctsSymbReg.Problem = regProblem;
      mctsSymbReg.Iterations = int.MaxValue; // stopping when all solutions have been enumerated
      mctsSymbReg.MaxVariableReferences = maxNumberOfVariables;
      var ucbPolicy = new Ucb();
      ucbPolicy.C = 1000; // essentially breadth first search
      mctsSymbReg.Policy = ucbPolicy;
      mctsSymbReg.AllowedFactors.SetItemCheckedState(mctsSymbReg.AllowedFactors.Single(s => s.Value.StartsWith("x * y * ...")), allowProd);
      mctsSymbReg.AllowedFactors.SetItemCheckedState(mctsSymbReg.AllowedFactors.Single(s => s.Value.Contains("exp(c * x * y ...)")), allowExp);
      mctsSymbReg.AllowedFactors.SetItemCheckedState(mctsSymbReg.AllowedFactors.Single(s => s.Value.Contains("log(c + c1 x + c2 x + ...)")), allowLog);
      mctsSymbReg.AllowedFactors.SetItemCheckedState(mctsSymbReg.AllowedFactors.Single(s => s.Value.Contains("1 / (1 + c1 x + c2 x + ...)")), allowInv);
      mctsSymbReg.AllowedFactors.SetItemCheckedState(mctsSymbReg.AllowedFactors.Single(s => s.Value.Contains("t1(x) + t2(x) + ... ")), allowSum);
      #endregion
      RunAlgorithm(mctsSymbReg);

      Console.WriteLine(mctsSymbReg.ExecutionTime);
      Assert.AreEqual(expectedNumberOfSolutions, ((IntValue)mctsSymbReg.Results["Iterations"].Value).Value);
    }


    // same as in SamplesUtil
    private void RunAlgorithm(IAlgorithm a) {
      var trigger = new EventWaitHandle(false, EventResetMode.ManualReset);
      Exception ex = null;
      a.Stopped += (src, e) => { trigger.Set(); };
      a.ExceptionOccurred += (src, e) => { ex = e.Value; trigger.Set(); };
      a.Prepare();
      a.Start();
      trigger.WaitOne();

      Assert.AreEqual(ex, null);
    }

  }
}