def add_multi_gen(self, pop, f_evals, opt_hv):
self.gen_num += 1
self.gens.append(None)
self.fevals.append(f_evals)
hv = multi_utils.hypervolume(pop)
os = GenStats(min=opt_hv - hv, max=opt_hv - hv, mean=opt_hv - hv)
fs = GenStats(min=hv, max=hv, mean=hv)
self.obj_stats.append(os)
self.fit_stats.append(fs)
if self.write_immediately:
with open(self.flog_name, 'a') as f:
f.write(f'{f_evals} {fs.max} {fs.mean} {fs.min}\n')
with open(self.olog_name, 'a') as f:
f.write(f'{f_evals} {os.max} {os.mean} {os.min}\n')
if self.gen_num % self.print_frequency == 0:
print(f'{f_evals:8} {os.min:8.2f} {os.mean:8.2f} {os.max:8.2f}')
fit = mf.get_function_by_name(fit_name)
opt_hv = mf.get_opt_hypervolume(fit_name)
mutate_ind = Mutation(step_size=MUT_STEP)
xover = functools.partial(crossover, cross=one_pt_cross, cx_prob=CX_PROB)
mut = functools.partial(mutation, mut_prob=MUT_PROB, mutate=mutate_ind)
# run the algorithm `REPEATS` times and remember the best solutions from
# last generations
best_inds = []
for run in range(REPEATS):
# initialize the log structure
log = utils.Log(OUT_DIR, EXP_ID + '.' + fit_name , run,
write_immediately=True, print_frequency=5)
# create population
pop = create_pop(POP_SIZE, cr_ind)
# run evolution - notice we use the pool.map as the map_fn
pop = evolutionary_algorithm(pop, MAX_GEN, fit, [xover, mut], tournament_selection_NSGA2, mutate_ind, map_fn=map, log=log, opt_hv=opt_hv)
# remember the best individual from last generation, save it to file
best_inds.append(mu.hypervolume(pop))
# if we used write_immediately = False, we would need to save the
# files now
# log.write_files()
# print an overview of the best individuals from each run
for i, bi in enumerate(best_inds):
print(f'Run {i}: objective = {opt_hv - bi}')
# write summary logs for the whole experiment
utils.summarize_experiment(OUT_DIR, EXP_ID + '.' + fit_name)