def main():
for trial in range(cf.get_trial()):
np.random.seed(trial)
results_list = [] # fitness list
de_list = []
"""Generate Initial Population"""
for p in range(cf.get_population_size()):
de_list.append(id.Individual())
"""Sort Array"""
de_list = sorted(de_list, key=lambda ID: ID.get_fitness())
"""Find Initial Best"""
BestPosition = de_list[0].get_position() # Best Solution
BestFitness = fn.calculation(BestPosition, 0)
"""↓↓↓Main Loop↓↓↓"""
for iteration in range(cf.get_iteration()):
"""list copy"""
candidate_de_list = copy.deepcopy(de_list)
"""Generate New Solutions"""
for i in range(len(de_list)):
candidate = copy.deepcopy(de_list[i])
"""select three points (a, b, c)"""
a = np.random.randint(0, cf.get_population_size())
while (a == i):
a = np.random.randint(0, cf.get_population_size())
b = np.random.randint(0, cf.get_population_size())
while (b == i or a == b):
b = np.random.randint(0, cf.get_population_size())
c = np.random.randint(0, cf.get_population_size())
while (c == i or c == a or c == b):
c = np.random.randint(0, cf.get_population_size())
"""Select Random Index (R)"""
R = np.random.randint(0, cf.get_dimension())
candidate.generate(a=de_list[a],
b=de_list[b],
c=de_list[c],
R=R)
candidate.set_fitness(
fn.calculation(candidate.get_position(), iteration))
if candidate.get_fitness() < de_list[i].get_fitness():
candidate_de_list[i] = copy.deepcopy(candidate)
"""Sort Array"""
de_list = sorted(candidate_de_list,
key=lambda ID: ID.get_fitness())
"""Rank and Find the Current Best"""
if de_list[0].get_fitness() < BestFitness:
BestPosition = de_list[0].get_position()
BestFitness = fn.calculation(BestPosition, iteration)
sys.stdout.write("\r Trial:%3d , Iteration:%7d, BestFitness:%.4f" %
(trial, iteration, BestFitness))
results_list.append(str(BestFitness))
results_writer.writerow(results_list)
def main():
result_list = np.zeros(cf.get_iteration())
for trial in range(cf.get_trial()):
# np.random.seed(trial)
np.random.seed()
cs_list = []
"""Generate Initial Population"""
for p in range(cf.get_population_size()):
cs_list.append(id.Individual())
"""Sort List"""
cs_list = sorted(cs_list, key=lambda ID: ID.get_fitness())
"""Find Initial Best"""
BestPosition = cs_list[0].get_position()
BestFitness = fn.calculation(cs_list[0].get_position(), 0)
"""↓↓↓Main Loop↓↓↓"""
for iteration in range(cf.get_iteration()):
"""Generate New Solutions"""
for i in range(len(cs_list)):
cs_list[i].get_cuckoo_dynamic_adaptive(iteration)
cs_list[i].set_fitness(
fn.calculation(cs_list[i].get_position(), iteration))
"""random choice (say j)"""
j = np.random.randint(low=0, high=cf.get_population_size())
while j == i: #random id[say j] ≠ i
j = np.random.randint(0, cf.get_population_size())
# for minimize problem
if (cs_list[i].get_fitness() < cs_list[j].get_fitness()):
cs_list[j].set_position(cs_list[i].get_position())
cs_list[j].set_fitness(cs_list[i].get_fitness())
"""Sort (to Keep Best)"""
cs_list = sorted(cs_list, key=lambda ID: ID.get_fitness())
"""Abandon Solutions (exclude the best)"""
for a in range(1, len(cs_list)):
r = np.random.rand()
if (r < cf.get_Pa()):
cs_list[a].abandon_dynamic(iteration)
cs_list[a].set_fitness(
fn.calculation(cs_list[a].get_position(), iteration))
"""Sort to Find the Best"""
cs_list = sorted(cs_list, key=lambda ID: ID.get_fitness())
if cs_list[0].get_fitness() < BestFitness:
BestFitness = cs_list[0].get_fitness()
BestPosition = cs_list[0].get_position()
sys.stdout.write(
"\r Trial:%3d , Iteration:%7d, BestFitness:%.10f" %
(trial, iteration, BestFitness))
result_list[iteration] += BestFitness
""" export avg result"""
result_list /= cf.get_trial()
for iteration in range(cf.get_iteration()):
result.write('{} {}\n'.format(iteration, result_list[iteration]))
def main():
for trial in range(cf.get_trial()):
np.random.seed(trial)
results_list = [] # fitness list
cs_list = []
"""Generate Initial Population"""
for p in range(cf.get_population_size()):
cs_list.append(id.Individual())
"""Sort List"""
cs_list = sorted(cs_list, key=lambda ID: ID.get_fitness())
"""Find Initial Best"""
BestPosition = cs_list[0].get_position()
BestFitness = fn.calculation(cs_list[0].get_position(), 0)
"""↓↓↓Main Loop↓↓↓"""
for iteration in range(cf.get_iteration()):
"""Generate New Solutions"""
for i in range(len(cs_list)):
cs_list[i].get_cuckoo()
cs_list[i].set_fitness(
fn.calculation(cs_list[i].get_position(), iteration))
"""random choice (say j)"""
j = np.random.randint(low=0, high=cf.get_population_size())
while j == i: # random id[say j] ≠ i
j = np.random.randint(0, cf.get_population_size())
# for minimize problem
if cs_list[i].get_fitness() < cs_list[j].get_fitness():
cs_list[j].set_position(cs_list[i].get_position())
cs_list[j].set_fitness(cs_list[i].get_fitness())
"""Sort (to Keep Best)"""
cs_list = sorted(cs_list, key=lambda ID: ID.get_fitness())
"""Abandon Solutions (exclude the best)"""
for a in range(1, len(cs_list)):
r = np.random.rand()
if r < cf.get_Pa():
cs_list[a].abandon()
cs_list[a].set_fitness(
fn.calculation(cs_list[a].get_position(), iteration))
"""Sort to Find the Best"""
cs_list = sorted(cs_list, key=lambda ID: ID.get_fitness())
if cs_list[0].get_fitness() < BestFitness:
BestFitness = cs_list[0].get_fitness()
BestPosition = cs_list[0].get_position()
sys.stdout.write("\r Trial:%3d , Iteration:%7d, BestFitness:%.4f" %
(trial, iteration, BestFitness))
results_list.append(str(BestFitness))
results_writer.writerow(results_list)
def reset(self, t):
self.__position = np.random.rand(cf.get_dimension()) * (
cf.get_max_domain() -
cf.get_min_domain()) + cf.get_min_domain() #位置座標
self.__velocity = np.random.rand(cf.get_dimension()) * (
cf.get_max_domain() -
cf.get_min_domain()) + cf.get_min_domain() #速度ベクトル
self.__fitness = fn.calculation(self.__position, 0) #評価値
def __init__(self):
self.__position = np.random.rand(cf.get_dimension()) * (
cf.get_max_domain() - cf.get_min_domain()) + cf.get_min_domain()
self.__velocity = np.random.rand(cf.get_dimension()) * (
cf.get_max_domain() - cf.get_min_domain()) + cf.get_min_domain()
self.__fitness = fn.calculation(self.__position, 0) # iteration = 0
self.__p_best_position = self.__position
self.__p_best_fitness = self.__fitness
def main():
for trial in range(cf.get_trial()):
np.random.seed(trial)
results_list = [] # fitness list
pso_list = []
"""Generate Initial Population"""
for p in range(cf.get_population_size()):
pso_list.append(id.Individual())
"""Sort Array"""
pso_list = sorted(pso_list, key=lambda ID: ID.get_fitness())
"""Find Initial Best"""
BestPosition = pso_list[0].get_position() # Best Solution
BestFitness = fn.calculation(BestPosition, 0)
"""↓↓↓Main Loop↓↓↓"""
for iteration in range(cf.get_iteration()):
"""Generate New Solutions"""
for i in range(len(pso_list)):
"""Update Position"""
pso_list[i].update_position()
"""Calculate Fitness"""
pso_list[i].set_fitness(
fn.calculation(pso_list[i].get_position(), t=iteration))
"""if f_x < f_(p_best) # for minimize optimization"""
if (pso_list[i].get_fitness() <
pso_list[i].get_p_best_fitness()):
pso_list[i].set_p_best_fitness(pso_list[i].get_fitness())
pso_list[i].set_p_best_position(pso_list[i].get_position())
"""if f_x < f_(g_best) # for minimize optimization"""
if (pso_list[i].get_fitness() < BestFitness):
BestFitness = pso_list[i].get_fitness()
BestPosition = pso_list[i].get_position()
"""Reload Velocity"""
pso_list[i].update_velocity(BestPosition)
"""Sort Array"""
pso_list = sorted(pso_list, key=lambda ID: ID.get_fitness())
"""Rank and Find the Current Best"""
if pso_list[0].get_fitness() < BestFitness:
BestPosition = pso_list[0].get_position()
BestFitness = fn.calculation(BestPosition, iteration)
sys.stdout.write("\r Trial:%3d , Iteration:%7d, BestFitness:%.4f" %
(trial, iteration, BestFitness))
results_list.append(str(BestFitness))
results_writer.writerow(results_list)
def __init__(self): #dim=次元数
self.__position = np.random.rand(cf.get_dimension()) * (
cf.get_max_domain() -
cf.get_min_domain()) + cf.get_min_domain() #位置座標
self.__velocity = np.random.rand(cf.get_dimension()) * (
cf.get_max_domain() -
cf.get_min_domain()) + cf.get_min_domain() #速度ベクトル
self.__fitness = fn.calculation(self.__position, 0) #評価値
self.__p_best_fitness = self.__fitness #各個体の最良値
self.__p_best_position = self.__position
def main():
result_list = np.zeros(cf.get_iteration())
for trial in range(cf.get_trial()):
np.random.seed(trial)
pos_list = []
v_list = []
pbest_list = []
gbest = None
"""Generate Initial Population"""
gbest = id.Individual()
for p in range(cf.get_population_size()):
pbest_list.append(id.Individual())
pos_list.append(id.Individual())
v_list.append(id.Individual())
""" Main Loop """
for iteration in range(cf.get_iteration()):
""" Update Partical position """
for i in range(cf.get_population_size()):
# move to new position
v_list[i].get_velocity(pos_list[i], pbest_list[i], gbest)
pos_list[i].get_newPos(v_list[i])
# update fitness
fitness = fn.calculation(pos_list[i].get_position(), 0)
pos_list[i].set_fitness(fitness)
# update pbest & gbest
if pos_list[i].get_fitness() < pbest_list[i].get_fitness():
pbest_list[i].set_position(pos_list[i].get_position())
pbest_list[i].set_fitness(pos_list[i].get_fitness())
if pos_list[i].get_fitness() < gbest.get_fitness():
gbest.set_position(pos_list[i].get_position())
gbest.set_fitness(pos_list[i].get_fitness())
# print([x.get_fitness() for x in pbest_list])
# print(gbest.get_fitness())
# sys.stdout.write("\r Trial:%3d , Iteration:%7d, BestFitness:%.10f" % (trial , iteration, gbest.get_fitness()))
result_list[iteration] += gbest.get_fitness()
""" export avg result"""
result_list /= cf.get_trial()
for iteration in range(cf.get_iteration()):
result.write('{} {}\n'.format(iteration, result_list[iteration]))
def run_cso(self, msg):
err_ = list(msg.error)
self.sum_err += (err_[5])
err = 0
if (self.status != 0):
return
self.status = 2
self.err = err
if (abs(self.int_err) > 20):
self.int_err = 0
else:
self.int_err += err
"""Assuming initial best values"""
FinalBestPosition = [-1 - 1 - 1]
FinalBestFitness = 0.00
for trial in range(self.Trial):
np.random.seed(trial)
results_list = [] # fitness list
cs_list = []
"""Generate Initial Population"""
for p in range(self.PopulationSize):
cs_list.append(id.Individual())
"""Sort List"""
cs_list = sorted(cs_list, key=lambda ID: ID.get_fitness())
"""Find Initial Best"""
TrialBestPosition = cs_list[0].get_position()
TrialBestFitness = fn.calculation(self.err, self.int_err,
self.prev_err,
cs_list[0].get_position(), 0)
"""↓↓↓Main Loop↓↓↓"""
for iteration in range(self.Iteration):
"""Generate New Solutions"""
for i in range(len(cs_list)):
cs_list[i].get_cuckoo()
cs_list[i].set_fitness(
fn.calculation(self.err, self.int_err, self.prev_err,
cs_list[i].get_position(), iteration))
"""random choice (say j)"""
j = np.random.randint(low=0, high=self.PopulationSize)
while j == i: #random id[say j] ≠ i
j = np.random.randint(0, self.PopulationSize)
if (cs_list[i].get_fitness() > cs_list[j].get_fitness()):
cs_list[j].set_position(cs_list[i].get_position())
cs_list[j].set_fitness(cs_list[i].get_fitness())
"""Sort (to Keep Best)"""
cs_list = sorted(cs_list, key=lambda ID: ID.get_fitness())
"""Abandon Solutions (exclude the best)"""
for a in range(1, len(cs_list)):
r = np.random.rand()
if (r < cf.get_Pa()):
cs_list[a].abandon()
cs_list[a].set_fitness(
fn.calculation(self.err, self.int_err,
self.prev_err,
cs_list[a].get_position(),
iteration))
"""Sort to Find the Best"""
cs_list = sorted(cs_list, key=lambda ID: ID.get_fitness())
if cs_list[0].get_fitness() > TrialBestFitness:
TrialBestFitness = cs_list[0].get_fitness()
TrialBestPosition = cs_list[0].get_position()
"""sys.stdout.write("\r Trial:%3d , Iteration:%7d, BestFitness:%.4f" % (trial , iteration, BestFitness))"""
"""results_list.append(str(TrialBestPosition))
results_writer.writerow(results_list)"""
FinalPIDvals = np.array(TrialBestPosition)
print(FinalPIDvals)
p_ = float(FinalPIDvals[0])
i_ = float(FinalPIDvals[1])
d_ = float(FinalPIDvals[2])
self.pid_vals_[0] = p_
self.pid_vals_[1] = i_
self.pid_vals_[2] = d_
self.prev_err = err
self.status = 1
def main():
for trial in range(cf.get_trial()): # seed = 試行回数
np.random.seed(trial)
if os.path.exists("results" + os.sep + "position" + os.sep +
str(trial)):
pass
else:
os.mkdir("results" + os.sep + "position" + os.sep + str(trial))
results_list = [] # fitness list
results_pso_list = []
results_cs_list = []
results_de_list = []
pso_list = [] # pso list
cs_list = [] # cs list
de_list = []
all_list = []
eval = 0
iteration = 0
BestFitness = 10000
improvement = []
"""Generate Initial Population"""
for p in range(int(args[7])):
pso_list.append(ind.Individual())
for c in range(int(args[8])):
cs_list.append(ind.Individual())
for d in range(int(args[9])):
de_list.append(ind.Individual())
"""Sort Array"""
pso_list = sorted(pso_list, key=lambda ID: ID.get_fitness())
cs_list = sorted(cs_list, key=lambda ID: ID.get_fitness())
de_list = sorted(de_list, key=lambda ID: ID.get_fitness())
for i in range(len(pso_list)):
all_list.append(pso_list[i])
# print(pso_list[i].get_position())
for i in range(len(cs_list)):
all_list.append(cs_list[i])
for i in range(len(de_list)):
all_list.append(de_list[i])
"""Find Initial Best"""
PSO_Best = Best(pso_list[0].get_fitness(), pso_list[0].get_position())
CS_Best = Best(cs_list[0].get_fitness(), cs_list[0].get_position())
DE_Best = Best(de_list[0].get_fitness(), de_list[0].get_position())
"""Find the Best"""
if PSO_Best.get_best_fitness() < CS_Best.get_best_fitness():
if (PSO_Best.get_best_fitness() < DE_Best.get_best_fitness()):
ALL_Best = Best(PSO_Best.get_best_fitness(),
PSO_Best.get_best_position())
else:
ALL_Best = Best(DE_Best.get_best_fitness(),
DE_Best.get_best_position())
else:
if (CS_Best.get_best_fitness() < DE_Best.get_best_fitness()):
ALL_Best = Best(CS_Best.get_best_fitness(),
CS_Best.get_best_position())
else:
ALL_Best = Best(DE_Best.get_best_fitness(),
DE_Best.get_best_position())
for iteration in range(cf.get_iteration()):
# if iteration == 150:
# BestFitness = 10000
# cf.set_Rnd(np.random.randint(0,5000))
# if(cf.get_function() == "ex21"):
# if(iteration >= 0 and iteration < 3000):
# if(iteration % 50 == 0):
# cf.set_Radisu(cf.get_Radius() + 1)
# 環境変化後リセット用
#
# 記述
#
# if(iteration == 5000 or iteration == 10000):
# """Generate Initial Population"""
# for p in range(cf.get_population_size()):
# pso_list.append(ind.Individual())
# cs_list.append(ind.Individual())
# de_list.append(ind.Individual())
# 位置記録
pos = open(
"results" + os.sep + "position" + os.sep + str(trial) +
os.sep + str(iteration).zfill(6) + ".csv", "w")
pos_writer = csv.writer(pos, lineterminator="\n")
#
# """Write Moved Position"""
for i in range(len(all_list)):
pos_writer.writerow(all_list[i].get_position())
# print(all_list[i].get_position())
# input()
# 各群の解アップデート
""">>>> PSO Update """
for i in range(len(pso_list)):
"""Update Position"""
pso_list[i].update_position()
"""Calculate Fitness"""
pso_list[i].set_fitness(
fn.calculation(pso_list[i].get_position(), iteration))
"""Update Personal Best # for minimize optimization"""
if (pso_list[i].get_fitness() < fn.calculation(
pso_list[i].get_p_best_position(), iteration)):
pso_list[i].set_p_best_fitness(pso_list[i].get_fitness())
pso_list[i].set_p_best_position(pso_list[i].get_position())
"""Update Global Best # for minimize optimization"""
if (pso_list[i].get_fitness() < PSO_Best.get_best_fitness()):
PSO_Best.set_best_fitness(pso_list[i].get_fitness())
PSO_Best.set_best_position(pso_list[i].get_position())
eval += 1
BestFitness, improvement = fitness_update(
fn.calculation(pso_list[i].get_position(), iteration),
BestFitness, improvement)
"""<<<< End PSO """
""">>>> CS Update """
for i in range(len(cs_list)):
cs_list[i].get_cuckoo()
cs_list[i].set_fitness(
fn.calculation(cs_list[i].get_position(), iteration))
"""random choice (say j)"""
j = np.random.randint(low=0, high=len(cs_list)) # [say j]
while (i == j):
j = np.random.randint(low=0, high=len(cs_list)) # [say j]
# for minimize problem
if (cs_list[i].get_fitness() < fn.calculation(
cs_list[j].get_position(), iteration)):
cs_list[j].set_position(cs_list[i].get_position())
cs_list[j].set_fitness(cs_list[i].get_fitness())
eval += 1
BestFitness, improvement = fitness_update(
fn.calculation(cs_list[j].get_position(), iteration),
BestFitness, improvement)
"""Find the Best"""
best_id = 0
best_fitness = cs_list[0].get_fitness()
for b in range(len(cs_list)):
F = cs_list[b].get_fitness()
if (F < best_fitness):
best_id = b
best_fitness = F
"""Abandon Solutions (exclude the best)"""
for a in range(0, len(cs_list)):
if (a != best_id): # To Keep the Best
r = np.random.rand()
if (r < cf.get_Pa()):
cs_list[a].abandon()
cs_list[a].set_fitness(
fn.calculation(cs_list[a].get_position(),
iteration))
"""<<<< End CS """
""">>>> DE Update"""
"""Generate New Solutions"""
for i in range(len(de_list)):
candidate = copy.deepcopy(de_list[i])
"""select three points (a, b, c)"""
a = np.random.randint(0, len(de_list))
while (a == i):
a = np.random.randint(0, len(de_list))
b = np.random.randint(0, len(de_list))
while (b == i or a == b):
b = np.random.randint(0, len(de_list))
c = np.random.randint(0, len(de_list))
while (c == i or c == a or c == b):
c = np.random.randint(0, len(de_list))
"""Select Random Index (R)"""
R = np.random.randint(0, cf.get_dimension())
candidate.generate(a=de_list[a],
b=de_list[b],
c=de_list[c],
R=R)
"""Calculate Solution"""
candidate.set_fitness(
fn.calculation(candidate.get_position(), iteration))
de_list[i].set_fitness(
fn.calculation(de_list[i].get_position(), iteration))
if candidate.get_fitness() < de_list[i].get_fitness():
de_list[i] = copy.deepcopy(candidate)
eval += 1
BestFitness, improvement = fitness_update(
fn.calculation(de_list[i].get_position(), iteration),
BestFitness, improvement)
de_list = copy.deepcopy(de_list)
"""<<<< End DE """
"""Sort Array"""
all_list = []
pso_list = sorted(pso_list, key=lambda ID: ID.get_fitness())
cs_list = sorted(cs_list, key=lambda ID: ID.get_fitness())
de_list = sorted(de_list, key=lambda ID: ID.get_fitness())
for i in range(len(pso_list)):
all_list.append(pso_list[i])
for i in range(len(cs_list)):
all_list.append(cs_list[i])
for i in range(len(de_list)):
all_list.append(de_list[i])
PSO_Best.set_best_fitness(
fn.calculation(PSO_Best.get_best_position(), iteration))
CS_Best.set_best_fitness(
fn.calculation(CS_Best.get_best_position(), iteration))
DE_Best.set_best_fitness(
fn.calculation(DE_Best.get_best_position(), iteration))
ALL_Best.set_best_fitness(
fn.calculation(ALL_Best.get_best_position(), iteration))
# print("rnd",cf.get_Rnd())
# print(fn.multimoving(PSO_Best.get_best_position(), cf.get_Rnd()))
# print("pso", PSO_Best.get_best_fitness())
# print("cs", CS_Best.get_best_fitness())
# print("de", DE_Best.get_best_fitness())
cs_list[0].set_fitness(
fn.calculation(cs_list[0].get_position(), iteration))
"""Update Best"""
UpdateBest(PSO_Best, pso_list[0])
UpdateBest(CS_Best, cs_list[0])
UpdateBest(DE_Best, de_list[0])
UpdateAllBest(ALL_Best, PSO_Best, CS_Best, DE_Best)
# 一番いいものを挿入
# if(iteration % 100 == 0):
pso_list[-1].set_position(ALL_Best.get_best_position())
cs_list[-1].set_position(ALL_Best.get_best_position())
de_list[-1].set_position(ALL_Best.get_best_position())
""">>>> Update PSO """
for i in range(len(pso_list)):
"""Reload Velocity"""
pso_list[i].update_velocity(PSO_Best.get_best_position())
"""<<<< End PSO """
# print("all_pos",ALL_Best.get_best_position())
# print(fn.multimoving(ALL_Best.get_best_position(), cf.get_Rnd()))
# print("all_fit",ALL_Best.get_best_fitness())
ALL_Best.set_best_fitness(
fn.calculation(ALL_Best.get_best_position(), iteration))
sys.stdout.write("\r Trial:%3d , Iteration:%7d, BestFitness:%.6f" %
(trial, iteration, ALL_Best.get_best_fitness()))
# print()
# input()
results_list.append(str(ALL_Best.get_best_fitness()))
# results_pso_list.append(str(PSO_Best.get_best_fitness()))
# results_cs_list.append(str(CS_Best.get_best_fitness()))
# results_de_list.append(str(DE_Best.get_best_fitness()))
results_writer.writerow(results_list)
# pso_results_writer.writerow(results_pso_list)
# cs_results_writer.writerow(results_cs_list)
# de_results_writer.writerow(results_de_list)
all = pd.DataFrame(improvement)
all.to_csv("./results/fitness_by_evaluation/trial" + str(trial) +
".csv")
"""File Close"""
FileClose()
def __init__(self):
self.__position = np.random.rand(cf.get_dimension()) * (
cf.get_max_domain() - cf.get_min_domain()) + cf.get_min_domain()
self.__fitness = fn.calculation(0, 0, 0, self.__position,
0) # iteration = 0
def __init__(self):
self.__position = np.random.rand(cf.get_dimension()) * (
cf.get_max_domain() - cf.get_min_domain()) + cf.get_min_domain()
self.__fitness = fn.calculation(self.__position, 0) # iteration = 0
self.__intensity = 1 / (1 + self.__fitness) # for minimize problem
