def individual(self):
bounds = {'x0': [0.0, 20.0], 'x1': [0.0, 20.0]}
ind = Individual(bounds)
ind.position = np.array([10.0, 10.0])
return ind
def test_termination_check(self, ga):
bounds = {'x0': [0.0, 10.0], 'x1': [0.0, 10.0]}
best = Individual(bounds)
best.fitness = 0.0001
ga.best_individual = best
tm = ErrorTerminationManager(ga, 0.0, 1e-3)
ret_bool = tm.termination_check()
assert ret_bool
def population():
population = []
for i in range(1, 5 + 1):
bounds = {
'x0': [0.0, 10.0],
'x1': [0.0, 10.0]
}
_ind = Individual(bounds)
_ind.fitness = i
population.append(_ind)
return population
def parent_a():
bounds = {
'x0': [0.0, 10.0],
'x1': [0.0, 10.0]
}
return Individual(bounds)
def soga(self):
bounds = {'x0': [0.0, 10.0], 'x1': [0.0, 10.0]}
soga = SOGA(bounds, n_individuals=30, n_iterations=100)
soga.initialise_population()
soga.best_individual = Individual(bounds)
soga.best_individual.fitness = 0.5
for idx, individual in enumerate(soga.population):
individual.fitness = 5.0
return soga
def individual(self):
ind = Individual({'x0': [0.0, 10.0], 'x1': [0.0, 10.0]})
ind.position = np.array([2.0, 7.0])
return ind
def fully_populate_with_random_individuals(self):
while self.size < ga_configs.configs['max_population_size']:
g = create_random_genes()
i = Individual(g)
self._individuals.append(i)