private AlpsGeneticAlgorithm CreateAlpsGaSymRegSample()
{
AlpsGeneticAlgorithm alpsGa = new AlpsGeneticAlgorithm();
#region Problem Configuration
var provider = new VladislavlevaInstanceProvider();
var instance = provider.GetDataDescriptors().Single(x => x.Name.StartsWith("Vladislavleva-5 F5"));
var symbRegProblem = new SymbolicRegressionSingleObjectiveProblem();
symbRegProblem.Load(provider.LoadData(instance));
symbRegProblem.MaximumSymbolicExpressionTreeDepth.Value = 35;
symbRegProblem.MaximumSymbolicExpressionTreeLength.Value = 35;
var grammar = (TypeCoherentExpressionGrammar)symbRegProblem.SymbolicExpressionTreeGrammar;
grammar.Symbols.OfType <Exponential>().Single().Enabled = false;
grammar.Symbols.OfType <Logarithm>().Single().Enabled = false;
#endregion
#region Algorithm Configuration
alpsGa.Name = "ALPS Genetic Programming - Symbolic Regression";
alpsGa.Description = "An ALPS-GP to solve a symbolic regression problem (Vladislavleva-5 dataset)";
alpsGa.Problem = symbRegProblem;
SamplesUtils.ConfigureAlpsGeneticAlgorithmParameters <GeneralizedRankSelector, SubtreeCrossover, MultiSymbolicExpressionTreeManipulator>(alpsGa,
numberOfLayers: 1000,
popSize: 100,
mutationRate: 0.25,
elites: 1,
plusSelection: false,
agingScheme: AgingScheme.Polynomial,
ageGap: 15,
ageInheritance: 1.0,
maxGens: 500);
#endregion
return(alpsGa);
}
public void SymbolicDataAnalysisExpressionContextAwareCrossoverPerformanceTest()
{
var problem = new SymbolicRegressionSingleObjectiveProblem();
var crossover = problem.OperatorsParameter.Value.OfType <SymbolicDataAnalysisExpressionContextAwareCrossover <IRegressionProblemData> >().First();
SymbolicDataAnalysisCrossoverPerformanceTest(crossover);
}
private static void SymbolicDataAnalysisCrossoverPerformanceTest(ISymbolicDataAnalysisExpressionCrossover <IRegressionProblemData> crossover)
{
var twister = new MersenneTwister(31415);
var dataset = Util.CreateRandomDataset(twister, Rows, Columns);
var grammar = new FullFunctionalExpressionGrammar();
var stopwatch = new Stopwatch();
grammar.MaximumFunctionArguments = 0;
grammar.MaximumFunctionDefinitions = 0;
grammar.MinimumFunctionArguments = 0;
grammar.MinimumFunctionDefinitions = 0;
var trees = Util.CreateRandomTrees(twister, dataset, grammar, PopulationSize, 1, MaxTreeLength, 0, 0);
foreach (ISymbolicExpressionTree tree in trees)
{
Util.InitTree(tree, twister, new List <string>(dataset.VariableNames));
}
var problemData = new RegressionProblemData(dataset, dataset.VariableNames, dataset.VariableNames.Last());
var problem = new SymbolicRegressionSingleObjectiveProblem();
problem.ProblemData = problemData;
var globalScope = new Scope("Global Scope");
globalScope.Variables.Add(new Core.Variable("Random", twister));
var context = new ExecutionContext(null, problem, globalScope);
context = new ExecutionContext(context, crossover, globalScope);
stopwatch.Start();
for (int i = 0; i != PopulationSize; ++i)
{
var parent0 = (ISymbolicExpressionTree)trees.SampleRandom(twister).Clone();
var scopeParent0 = new Scope();
scopeParent0.Variables.Add(new Core.Variable(crossover.ParentsParameter.ActualName, parent0));
context.Scope.SubScopes.Add(scopeParent0);
var parent1 = (ISymbolicExpressionTree)trees.SampleRandom(twister).Clone();
var scopeParent1 = new Scope();
scopeParent1.Variables.Add(new Core.Variable(crossover.ParentsParameter.ActualName, parent1));
context.Scope.SubScopes.Add(scopeParent1);
crossover.Execute(context, new CancellationToken());
context.Scope.SubScopes.Remove(scopeParent0); // clean the scope in preparation for the next iteration
context.Scope.SubScopes.Remove(scopeParent1); // clean the scope in preparation for the next iteration
}
stopwatch.Stop();
double msPerCrossover = 2 * stopwatch.ElapsedMilliseconds / (double)PopulationSize;
Console.WriteLine(crossover.Name + ": " + Environment.NewLine +
msPerCrossover + " ms per crossover (~" + Math.Round(1000.0 / (msPerCrossover)) + " crossover operations / s)");
foreach (var tree in trees)
{
HeuristicLab.Encodings.SymbolicExpressionTreeEncoding.Tests.Util.IsValid(tree);
}
}
public void SymbolicDataAnalysisExpressionDepthConstrainedCrossoverPerformanceTest()
{
var problem = new SymbolicRegressionSingleObjectiveProblem();
var crossover = problem.OperatorsParameter.Value.OfType <SymbolicDataAnalysisExpressionDepthConstrainedCrossover <IRegressionProblemData> >().First();
crossover.DepthRangeParameter.Value = crossover.DepthRangeParameter.ValidValues.First(s => s.Value == "HighLevel");
SymbolicDataAnalysisCrossoverPerformanceTest(crossover);
crossover.DepthRangeParameter.Value = crossover.DepthRangeParameter.ValidValues.First(s => s.Value == "Standard");
SymbolicDataAnalysisCrossoverPerformanceTest(crossover);
crossover.DepthRangeParameter.Value = crossover.DepthRangeParameter.ValidValues.First(s => s.Value == "LowLevel");
SymbolicDataAnalysisCrossoverPerformanceTest(crossover);
}
static void Main(string[] args)
{
var path = @"D:\Data\Sinus\SimpleSinusHeuristicLab.csv";
var parser = new TableFileParser();
parser.Parse(path, columnNamesInFirstLine: true);
var dataset = new Dataset(parser.VariableNames, parser.Values);
var problemData = new RegressionProblemData(dataset, dataset.DoubleVariables.Take(dataset.Columns - 1), dataset.DoubleVariables.Last());
var grammar = new TypeCoherentExpressionGrammar();
var add = new Addition();
// var sub = new Subtraction();
// var mul = new Multiplication();
// var div = new Division();
grammar.ConfigureAsDefaultRegressionGrammar();
var problem = new SymbolicRegressionSingleObjectiveProblem {
ProblemData = problemData,
SymbolicExpressionTreeInterpreter = new SymbolicDataAnalysisExpressionTreeLinearInterpreter(),
SymbolicExpressionTreeGrammar = grammar,
EvaluatorParameter = { Value = new SymbolicRegressionSingleObjectivePearsonRSquaredEvaluator() },
SolutionCreatorParameter = { Value = new SymbolicDataAnalysisExpressionTreeCreator() }
};
var ga = new GeneticAlgorithm {
PopulationSize = { Value = 1000 },
MaximumGenerations = { Value = 100 },
Problem = problem,
MutationProbability = new PercentValue(25),
Engine = new SequentialEngine()
};
var manipulator = new MultiSymbolicExpressionTreeManipulator();
ga.MutatorParameter.ValidValues.Add(manipulator);
ga.ExecutionStateChanged += OnExecutionStateChanged;
ga.ExecutionTimeChanged += OnExecutionTimeChanged;
ga.Prepare();
ga.Start();
mutex.WaitOne();
}
private IAlgorithm CreateOSGP()
{
// configure strict osgp
var alg = new OffspringSelectionGeneticAlgorithm.OffspringSelectionGeneticAlgorithm();
var prob = new SymbolicRegressionSingleObjectiveProblem();
prob.MaximumSymbolicExpressionTreeDepth.Value = 7;
prob.MaximumSymbolicExpressionTreeLength.Value = 15;
alg.Problem = prob;
alg.SuccessRatio.Value = 1.0;
alg.ComparisonFactorLowerBound.Value = 1.0;
alg.ComparisonFactorUpperBound.Value = 1.0;
alg.MutationProbability.Value = 0.15;
alg.PopulationSize.Value = 200;
alg.MaximumSelectionPressure.Value = 100;
alg.MaximumEvaluatedSolutions.Value = 20000;
alg.SelectorParameter.Value = alg.SelectorParameter.ValidValues.OfType <GenderSpecificSelector>().First();
alg.MutatorParameter.Value = alg.MutatorParameter.ValidValues.OfType <MultiSymbolicExpressionTreeManipulator>().First();
alg.StoreAlgorithmInEachRun = false;
return(alg);
}
private AlpsGeneticAlgorithm CreateAlpsGaSymRegSample() {
AlpsGeneticAlgorithm alpsGa = new AlpsGeneticAlgorithm();
#region Problem Configuration
var provider = new VladislavlevaInstanceProvider();
var instance = provider.GetDataDescriptors().Single(x => x.Name.StartsWith("Vladislavleva-5 F5"));
var symbRegProblem = new SymbolicRegressionSingleObjectiveProblem();
symbRegProblem.Load(provider.LoadData(instance));
symbRegProblem.MaximumSymbolicExpressionTreeDepth.Value = 35;
symbRegProblem.MaximumSymbolicExpressionTreeLength.Value = 35;
var grammar = (TypeCoherentExpressionGrammar)symbRegProblem.SymbolicExpressionTreeGrammar;
grammar.Symbols.OfType<Exponential>().Single().Enabled = false;
grammar.Symbols.OfType<Logarithm>().Single().Enabled = false;
#endregion
#region Algorithm Configuration
alpsGa.Name = "ALPS Genetic Programming - Symbolic Regression";
alpsGa.Description = "An ALPS-GP to solve a symbolic regression problem (Vladislavleva-5 dataset)";
alpsGa.Problem = symbRegProblem;
SamplesUtils.ConfigureAlpsGeneticAlgorithmParameters<GeneralizedRankSelector, SubtreeCrossover, MultiSymbolicExpressionTreeManipulator>(alpsGa,
numberOfLayers: 1000,
popSize: 100,
mutationRate: 0.25,
elites: 1,
plusSelection: false,
agingScheme: AgingScheme.Polynomial,
ageGap: 15,
ageInheritance: 1.0,
maxGens: 500);
#endregion
return alpsGa;
}
private IAlgorithm CreateOSGP() {
// configure strict osgp
var alg = new OffspringSelectionGeneticAlgorithm.OffspringSelectionGeneticAlgorithm();
var prob = new SymbolicRegressionSingleObjectiveProblem();
prob.MaximumSymbolicExpressionTreeDepth.Value = 7;
prob.MaximumSymbolicExpressionTreeLength.Value = 15;
alg.Problem = prob;
alg.SuccessRatio.Value = 1.0;
alg.ComparisonFactorLowerBound.Value = 1.0;
alg.ComparisonFactorUpperBound.Value = 1.0;
alg.MutationProbability.Value = 0.15;
alg.PopulationSize.Value = 200;
alg.MaximumSelectionPressure.Value = 100;
alg.MaximumEvaluatedSolutions.Value = 20000;
alg.SelectorParameter.Value = alg.SelectorParameter.ValidValues.OfType<GenderSpecificSelector>().First();
alg.MutatorParameter.Value = alg.MutatorParameter.ValidValues.OfType<MultiSymbolicExpressionTreeManipulator>().First();
alg.StoreAlgorithmInEachRun = false;
return alg;
}
private GeneticAlgorithm CreateGpSymbolicRegressionSample()
{
GeneticAlgorithm ga = new GeneticAlgorithm();
#region Problem Configuration
SymbolicRegressionSingleObjectiveProblem symbRegProblem = new SymbolicRegressionSingleObjectiveProblem();
symbRegProblem.Name = "Tower Symbolic Regression Problem";
symbRegProblem.Description = "Tower Dataset (downloaded from: http://www.symbolicregression.com/?q=towerProblem)";
RegressionRealWorldInstanceProvider provider = new RegressionRealWorldInstanceProvider();
var instance = provider.GetDataDescriptors().Where(x => x.Name.Equals("Tower")).Single();
var towerProblemData = (RegressionProblemData)provider.LoadData(instance);
towerProblemData.TargetVariableParameter.Value = towerProblemData.TargetVariableParameter.ValidValues
.First(v => v.Value == "towerResponse");
towerProblemData.InputVariables.SetItemCheckedState(
towerProblemData.InputVariables.Single(x => x.Value == "x1"), true);
towerProblemData.InputVariables.SetItemCheckedState(
towerProblemData.InputVariables.Single(x => x.Value == "x7"), false);
towerProblemData.InputVariables.SetItemCheckedState(
towerProblemData.InputVariables.Single(x => x.Value == "x11"), false);
towerProblemData.InputVariables.SetItemCheckedState(
towerProblemData.InputVariables.Single(x => x.Value == "x16"), false);
towerProblemData.InputVariables.SetItemCheckedState(
towerProblemData.InputVariables.Single(x => x.Value == "x21"), false);
towerProblemData.InputVariables.SetItemCheckedState(
towerProblemData.InputVariables.Single(x => x.Value == "x25"), false);
towerProblemData.InputVariables.SetItemCheckedState(
towerProblemData.InputVariables.Single(x => x.Value == "towerResponse"), false);
towerProblemData.TrainingPartition.Start = 0;
towerProblemData.TrainingPartition.End = 3136;
towerProblemData.TestPartition.Start = 3136;
towerProblemData.TestPartition.End = 4999;
towerProblemData.Name = "Data imported from towerData.txt";
towerProblemData.Description = "Chemical concentration at top of distillation tower, dataset downloaded from: http://vanillamodeling.com/realproblems.html, best R² achieved with nu-SVR = 0.97";
symbRegProblem.ProblemData = towerProblemData;
// configure grammar
var grammar = new TypeCoherentExpressionGrammar();
grammar.ConfigureAsDefaultRegressionGrammar();
grammar.Symbols.OfType <VariableCondition>().Single().InitialFrequency = 0.0;
var varSymbol = grammar.Symbols.OfType <Variable>().Where(x => !(x is LaggedVariable)).Single();
varSymbol.WeightMu = 1.0;
varSymbol.WeightSigma = 1.0;
varSymbol.WeightManipulatorMu = 0.0;
varSymbol.WeightManipulatorSigma = 0.05;
varSymbol.MultiplicativeWeightManipulatorSigma = 0.03;
var constSymbol = grammar.Symbols.OfType <Constant>().Single();
constSymbol.MaxValue = 20;
constSymbol.MinValue = -20;
constSymbol.ManipulatorMu = 0.0;
constSymbol.ManipulatorSigma = 1;
constSymbol.MultiplicativeManipulatorSigma = 0.03;
symbRegProblem.SymbolicExpressionTreeGrammar = grammar;
// configure remaining problem parameters
symbRegProblem.BestKnownQuality.Value = 0.97;
symbRegProblem.FitnessCalculationPartition.Start = 0;
symbRegProblem.FitnessCalculationPartition.End = 2300;
symbRegProblem.ValidationPartition.Start = 2300;
symbRegProblem.ValidationPartition.End = 3136;
symbRegProblem.RelativeNumberOfEvaluatedSamples.Value = 1;
symbRegProblem.MaximumSymbolicExpressionTreeLength.Value = 150;
symbRegProblem.MaximumSymbolicExpressionTreeDepth.Value = 12;
symbRegProblem.MaximumFunctionDefinitions.Value = 0;
symbRegProblem.MaximumFunctionArguments.Value = 0;
symbRegProblem.EvaluatorParameter.Value = new SymbolicRegressionSingleObjectivePearsonRSquaredEvaluator();
#endregion
#region Algorithm Configuration
ga.Problem = symbRegProblem;
ga.Name = "Genetic Programming - Symbolic Regression";
ga.Description = "A standard genetic programming algorithm to solve a symbolic regression problem (tower dataset)";
SamplesUtils.ConfigureGeneticAlgorithmParameters <TournamentSelector, SubtreeCrossover, MultiSymbolicExpressionTreeManipulator>(
ga, 1000, 1, 50, 0.15, 5);
var mutator = (MultiSymbolicExpressionTreeManipulator)ga.Mutator;
mutator.Operators.OfType <FullTreeShaker>().Single().ShakingFactor = 0.1;
mutator.Operators.OfType <OnePointShaker>().Single().ShakingFactor = 1.0;
ga.Analyzer.Operators.SetItemCheckedState(
ga.Analyzer.Operators
.OfType <SymbolicRegressionSingleObjectiveOverfittingAnalyzer>()
.Single(), false);
ga.Analyzer.Operators.SetItemCheckedState(
ga.Analyzer.Operators
.OfType <SymbolicDataAnalysisAlleleFrequencyAnalyzer>()
.First(), false);
#endregion
return(ga);
}
private OffspringSelectionGeneticAlgorithm CreateGpSymbolicRegressionSample()
{
var osga = new OffspringSelectionGeneticAlgorithm();
#region Problem Configuration
var provider = new VariousInstanceProvider(seed);
var instance = provider.GetDataDescriptors().First(x => x.Name.StartsWith("Spatial co-evolution"));
var problemData = (RegressionProblemData)provider.LoadData(instance);
var problem = new SymbolicRegressionSingleObjectiveProblem();
problem.ProblemData = problemData;
problem.Load(problemData);
problem.BestKnownQuality.Value = 1.0;
#region configure grammar
var grammar = (TypeCoherentExpressionGrammar)problem.SymbolicExpressionTreeGrammar;
grammar.ConfigureAsDefaultRegressionGrammar();
//symbols square, power, squareroot, root, log, exp, sine, cosine, tangent, variable
var square = grammar.Symbols.OfType <Square>().Single();
var power = grammar.Symbols.OfType <Power>().Single();
var squareroot = grammar.Symbols.OfType <SquareRoot>().Single();
var root = grammar.Symbols.OfType <Root>().Single();
var log = grammar.Symbols.OfType <Logarithm>().Single();
var exp = grammar.Symbols.OfType <Exponential>().Single();
var sine = grammar.Symbols.OfType <Sine>().Single();
var cosine = grammar.Symbols.OfType <Cosine>().Single();
var tangent = grammar.Symbols.OfType <Tangent>().Single();
var variable = grammar.Symbols.OfType <Variable>().Single();
var powerSymbols = grammar.Symbols.Single(s => s.Name == "Power Functions");
powerSymbols.Enabled = true;
square.Enabled = true;
square.InitialFrequency = 1.0;
foreach (var allowed in grammar.GetAllowedChildSymbols(square))
{
grammar.RemoveAllowedChildSymbol(square, allowed);
}
foreach (var allowed in grammar.GetAllowedChildSymbols(square, 0))
{
grammar.RemoveAllowedChildSymbol(square, allowed, 0);
}
grammar.AddAllowedChildSymbol(square, variable);
power.Enabled = false;
squareroot.Enabled = false;
foreach (var allowed in grammar.GetAllowedChildSymbols(squareroot))
{
grammar.RemoveAllowedChildSymbol(squareroot, allowed);
}
foreach (var allowed in grammar.GetAllowedChildSymbols(squareroot, 0))
{
grammar.RemoveAllowedChildSymbol(squareroot, allowed, 0);
}
grammar.AddAllowedChildSymbol(squareroot, variable);
root.Enabled = false;
log.Enabled = true;
log.InitialFrequency = 1.0;
foreach (var allowed in grammar.GetAllowedChildSymbols(log))
{
grammar.RemoveAllowedChildSymbol(log, allowed);
}
foreach (var allowed in grammar.GetAllowedChildSymbols(log, 0))
{
grammar.RemoveAllowedChildSymbol(log, allowed, 0);
}
grammar.AddAllowedChildSymbol(log, variable);
exp.Enabled = true;
exp.InitialFrequency = 1.0;
foreach (var allowed in grammar.GetAllowedChildSymbols(exp))
{
grammar.RemoveAllowedChildSymbol(exp, allowed);
}
foreach (var allowed in grammar.GetAllowedChildSymbols(exp, 0))
{
grammar.RemoveAllowedChildSymbol(exp, allowed, 0);
}
grammar.AddAllowedChildSymbol(exp, variable);
sine.Enabled = false;
foreach (var allowed in grammar.GetAllowedChildSymbols(sine))
{
grammar.RemoveAllowedChildSymbol(sine, allowed);
}
foreach (var allowed in grammar.GetAllowedChildSymbols(sine, 0))
{
grammar.RemoveAllowedChildSymbol(sine, allowed, 0);
}
grammar.AddAllowedChildSymbol(sine, variable);
cosine.Enabled = false;
foreach (var allowed in grammar.GetAllowedChildSymbols(cosine))
{
grammar.RemoveAllowedChildSymbol(cosine, allowed);
}
foreach (var allowed in grammar.GetAllowedChildSymbols(cosine, 0))
{
grammar.RemoveAllowedChildSymbol(cosine, allowed, 0);
}
grammar.AddAllowedChildSymbol(cosine, variable);
tangent.Enabled = false;
foreach (var allowed in grammar.GetAllowedChildSymbols(tangent))
{
grammar.RemoveAllowedChildSymbol(tangent, allowed);
}
foreach (var allowed in grammar.GetAllowedChildSymbols(tangent, 0))
{
grammar.RemoveAllowedChildSymbol(tangent, allowed, 0);
}
grammar.AddAllowedChildSymbol(tangent, variable);
#endregion
problem.SymbolicExpressionTreeGrammar = grammar;
// configure remaining problem parameters
problem.MaximumSymbolicExpressionTreeLength.Value = 50;
problem.MaximumSymbolicExpressionTreeDepth.Value = 12;
problem.MaximumFunctionDefinitions.Value = 0;
problem.MaximumFunctionArguments.Value = 0;
var evaluator = new SymbolicRegressionConstantOptimizationEvaluator();
evaluator.ConstantOptimizationIterations.Value = 5;
problem.EvaluatorParameter.Value = evaluator;
problem.RelativeNumberOfEvaluatedSamplesParameter.Hidden = true;
problem.SolutionCreatorParameter.Hidden = true;
#endregion
#region Algorithm Configuration
osga.Problem = problem;
osga.Name = "Offspring Selection Genetic Programming - Symbolic Regression";
osga.Description = "Genetic programming with strict offspring selection for solving a benchmark regression problem.";
SamplesUtils.ConfigureOsGeneticAlgorithmParameters <GenderSpecificSelector, SubtreeCrossover, MultiSymbolicExpressionTreeManipulator>(osga, 100, 1, 25, 0.2, 50);
var mutator = (MultiSymbolicExpressionTreeManipulator)osga.Mutator;
mutator.Operators.OfType <FullTreeShaker>().Single().ShakingFactor = 0.1;
mutator.Operators.OfType <OnePointShaker>().Single().ShakingFactor = 1.0;
osga.Analyzer.Operators.SetItemCheckedState(
osga.Analyzer.Operators
.OfType <SymbolicRegressionSingleObjectiveOverfittingAnalyzer>()
.Single(), false);
osga.Analyzer.Operators.SetItemCheckedState(
osga.Analyzer.Operators
.OfType <SymbolicDataAnalysisAlleleFrequencyAnalyzer>()
.First(), false);
osga.ComparisonFactorModifierParameter.Hidden = true;
osga.ComparisonFactorLowerBoundParameter.Hidden = true;
osga.ComparisonFactorUpperBoundParameter.Hidden = true;
osga.OffspringSelectionBeforeMutationParameter.Hidden = true;
osga.SuccessRatioParameter.Hidden = true;
osga.SelectedParentsParameter.Hidden = true;
osga.ElitesParameter.Hidden = true;
#endregion
return(osga);
}
public void SymbolicDataAnalysisExpressionDepthConstrainedCrossoverPerformanceTest() {
var problem = new SymbolicRegressionSingleObjectiveProblem();
var crossover = problem.OperatorsParameter.Value.OfType<SymbolicDataAnalysisExpressionDepthConstrainedCrossover<IRegressionProblemData>>().First();
crossover.DepthRangeParameter.Value = crossover.DepthRangeParameter.ValidValues.First(s => s.Value == "HighLevel");
SymbolicDataAnalysisCrossoverPerformanceTest(crossover);
crossover.DepthRangeParameter.Value = crossover.DepthRangeParameter.ValidValues.First(s => s.Value == "Standard");
SymbolicDataAnalysisCrossoverPerformanceTest(crossover);
crossover.DepthRangeParameter.Value = crossover.DepthRangeParameter.ValidValues.First(s => s.Value == "LowLevel");
SymbolicDataAnalysisCrossoverPerformanceTest(crossover);
}
public void SymbolicDataAnalysisExpressionContextAwareCrossoverPerformanceTest() {
var problem = new SymbolicRegressionSingleObjectiveProblem();
var crossover = problem.OperatorsParameter.Value.OfType<SymbolicDataAnalysisExpressionContextAwareCrossover<IRegressionProblemData>>().First();
SymbolicDataAnalysisCrossoverPerformanceTest(crossover);
}
private static void SymbolicDataAnalysisCrossoverPerformanceTest(ISymbolicDataAnalysisExpressionCrossover<IRegressionProblemData> crossover) {
var twister = new MersenneTwister(31415);
var dataset = Util.CreateRandomDataset(twister, Rows, Columns);
var grammar = new FullFunctionalExpressionGrammar();
var stopwatch = new Stopwatch();
grammar.MaximumFunctionArguments = 0;
grammar.MaximumFunctionDefinitions = 0;
grammar.MinimumFunctionArguments = 0;
grammar.MinimumFunctionDefinitions = 0;
var trees = Util.CreateRandomTrees(twister, dataset, grammar, PopulationSize, 1, MaxTreeLength, 0, 0);
foreach (ISymbolicExpressionTree tree in trees) {
Util.InitTree(tree, twister, new List<string>(dataset.VariableNames));
}
var problemData = new RegressionProblemData(dataset, dataset.VariableNames, dataset.VariableNames.Last());
var problem = new SymbolicRegressionSingleObjectiveProblem();
problem.ProblemData = problemData;
var globalScope = new Scope("Global Scope");
globalScope.Variables.Add(new Core.Variable("Random", twister));
var context = new ExecutionContext(null, problem, globalScope);
context = new ExecutionContext(context, crossover, globalScope);
stopwatch.Start();
for (int i = 0; i != PopulationSize; ++i) {
var parent0 = (ISymbolicExpressionTree)trees.SampleRandom(twister).Clone();
var scopeParent0 = new Scope();
scopeParent0.Variables.Add(new Core.Variable(crossover.ParentsParameter.ActualName, parent0));
context.Scope.SubScopes.Add(scopeParent0);
var parent1 = (ISymbolicExpressionTree)trees.SampleRandom(twister).Clone();
var scopeParent1 = new Scope();
scopeParent1.Variables.Add(new Core.Variable(crossover.ParentsParameter.ActualName, parent1));
context.Scope.SubScopes.Add(scopeParent1);
crossover.Execute(context, new CancellationToken());
context.Scope.SubScopes.Remove(scopeParent0); // clean the scope in preparation for the next iteration
context.Scope.SubScopes.Remove(scopeParent1); // clean the scope in preparation for the next iteration
}
stopwatch.Stop();
double msPerCrossover = 2 * stopwatch.ElapsedMilliseconds / (double)PopulationSize;
Console.WriteLine(crossover.Name + ": " + Environment.NewLine +
msPerCrossover + " ms per crossover (~" + Math.Round(1000.0 / (msPerCrossover)) + " crossover operations / s)");
foreach (var tree in trees)
HeuristicLab.Encodings.SymbolicExpressionTreeEncoding.Tests.Util.IsValid(tree);
}
private GeneticAlgorithm CreateGpSymbolicRegressionSample() {
GeneticAlgorithm ga = new GeneticAlgorithm();
#region Problem Configuration
SymbolicRegressionSingleObjectiveProblem symbRegProblem = new SymbolicRegressionSingleObjectiveProblem();
symbRegProblem.Name = "Tower Symbolic Regression Problem";
symbRegProblem.Description = "Tower Dataset (downloaded from: http://www.symbolicregression.com/?q=towerProblem)";
RegressionRealWorldInstanceProvider provider = new RegressionRealWorldInstanceProvider();
var instance = provider.GetDataDescriptors().Where(x => x.Name.Equals("Tower")).Single();
var towerProblemData = (RegressionProblemData)provider.LoadData(instance);
towerProblemData.TargetVariableParameter.Value = towerProblemData.TargetVariableParameter.ValidValues
.First(v => v.Value == "towerResponse");
towerProblemData.InputVariables.SetItemCheckedState(
towerProblemData.InputVariables.Single(x => x.Value == "x1"), true);
towerProblemData.InputVariables.SetItemCheckedState(
towerProblemData.InputVariables.Single(x => x.Value == "x7"), false);
towerProblemData.InputVariables.SetItemCheckedState(
towerProblemData.InputVariables.Single(x => x.Value == "x11"), false);
towerProblemData.InputVariables.SetItemCheckedState(
towerProblemData.InputVariables.Single(x => x.Value == "x16"), false);
towerProblemData.InputVariables.SetItemCheckedState(
towerProblemData.InputVariables.Single(x => x.Value == "x21"), false);
towerProblemData.InputVariables.SetItemCheckedState(
towerProblemData.InputVariables.Single(x => x.Value == "x25"), false);
towerProblemData.InputVariables.SetItemCheckedState(
towerProblemData.InputVariables.Single(x => x.Value == "towerResponse"), false);
towerProblemData.TrainingPartition.Start = 0;
towerProblemData.TrainingPartition.End = 3136;
towerProblemData.TestPartition.Start = 3136;
towerProblemData.TestPartition.End = 4999;
towerProblemData.Name = "Data imported from towerData.txt";
towerProblemData.Description = "Chemical concentration at top of distillation tower, dataset downloaded from: http://vanillamodeling.com/realproblems.html, best R² achieved with nu-SVR = 0.97";
symbRegProblem.ProblemData = towerProblemData;
// configure grammar
var grammar = new TypeCoherentExpressionGrammar();
grammar.ConfigureAsDefaultRegressionGrammar();
grammar.Symbols.OfType<VariableCondition>().Single().InitialFrequency = 0.0;
var varSymbol = grammar.Symbols.OfType<Variable>().Where(x => !(x is LaggedVariable)).Single();
varSymbol.WeightMu = 1.0;
varSymbol.WeightSigma = 1.0;
varSymbol.WeightManipulatorMu = 0.0;
varSymbol.WeightManipulatorSigma = 0.05;
varSymbol.MultiplicativeWeightManipulatorSigma = 0.03;
var constSymbol = grammar.Symbols.OfType<Constant>().Single();
constSymbol.MaxValue = 20;
constSymbol.MinValue = -20;
constSymbol.ManipulatorMu = 0.0;
constSymbol.ManipulatorSigma = 1;
constSymbol.MultiplicativeManipulatorSigma = 0.03;
symbRegProblem.SymbolicExpressionTreeGrammar = grammar;
// configure remaining problem parameters
symbRegProblem.BestKnownQuality.Value = 0.97;
symbRegProblem.FitnessCalculationPartition.Start = 0;
symbRegProblem.FitnessCalculationPartition.End = 2300;
symbRegProblem.ValidationPartition.Start = 2300;
symbRegProblem.ValidationPartition.End = 3136;
symbRegProblem.RelativeNumberOfEvaluatedSamples.Value = 1;
symbRegProblem.MaximumSymbolicExpressionTreeLength.Value = 150;
symbRegProblem.MaximumSymbolicExpressionTreeDepth.Value = 12;
symbRegProblem.MaximumFunctionDefinitions.Value = 0;
symbRegProblem.MaximumFunctionArguments.Value = 0;
symbRegProblem.EvaluatorParameter.Value = new SymbolicRegressionSingleObjectivePearsonRSquaredEvaluator();
#endregion
#region Algorithm Configuration
ga.Problem = symbRegProblem;
ga.Name = "Genetic Programming - Symbolic Regression";
ga.Description = "A standard genetic programming algorithm to solve a symbolic regression problem (tower dataset)";
SamplesUtils.ConfigureGeneticAlgorithmParameters<TournamentSelector, SubtreeCrossover, MultiSymbolicExpressionTreeManipulator>(
ga, 1000, 1, 50, 0.15, 5);
var mutator = (MultiSymbolicExpressionTreeManipulator)ga.Mutator;
mutator.Operators.OfType<FullTreeShaker>().Single().ShakingFactor = 0.1;
mutator.Operators.OfType<OnePointShaker>().Single().ShakingFactor = 1.0;
ga.Analyzer.Operators.SetItemCheckedState(
ga.Analyzer.Operators
.OfType<SymbolicRegressionSingleObjectiveOverfittingAnalyzer>()
.Single(), false);
ga.Analyzer.Operators.SetItemCheckedState(
ga.Analyzer.Operators
.OfType<SymbolicDataAnalysisAlleleFrequencyAnalyzer>()
.First(), false);
#endregion
return ga;
}
