def __init__(self, is_neigh_precomp=True, is_using_output_one_neigh=True): self.length = 100 self.epsilon = Fraction(2**-55) self.number_of_activations = 20 self.number_of_mutations_from_mutator = 50 self.population_size = 75 self.tolerance = ConjunctionTolerance(self.length, self.epsilon) self.tau = 0 # (self.epsilon / Decimal(self.length))**Decimal(3) * log(1/self.epsilon) self.representation_class = None if is_neigh_precomp: self.representation_class = get_set_of_all_representations_with_length( self.length) self.mutation_neighborhood = PrecompMonotoneConjunctionNeighborhood( self.representation_class) elif is_using_output_one_neigh: self.mutation_neighborhood = ConjunctionNeighborhoodOutputOne() else: self.mutation_neighborhood = MonotoneConjunctionNeighborhood() self.mutation_probability = ConjunctionMutationProbability( self.mutation_neighborhood) self.recombination_factor = 1
def learn_DNF__basic_model(): dnf = DNF() length = 58 epsilon = (2**-53) tau = (epsilon / length)**3 * log(1 / epsilon) tolerance = ConjunctionTolerance(length, epsilon) conjunction_performance_oracle = OneSidedPerformanceOracleWithTolerance( dnf, tau) performance_oracle = DNFOneSidePerformanceOracleWithTolerance( dnf, tau, epsilon, conjunction_performance_oracle) mutation_neighborhood = MonotoneConjunctionNeighborhood() mutation_probability = ConjunctionMutationProbability( mutation_neighborhood) mutator = Mutator(mutation_neighborhood, performance_oracle, tolerance, mutation_probability, epsilon) algorithm = ConjunctionEvolvabilityAlgorithm(mutator, length, epsilon, performance_oracle) print algorithm.learn_ideal_function_until_match()
def setUp(self): self.neighbors_finder = Mock() self.conjunction_mutation_probability = ConjunctionMutationProbability(self.neighbors_finder)