def next(self, tick):
if crossover(self.sma1[:tick], self.sma2[:tick]):
self.buy()
elif crossover(self.sma2[:tick], self.sma1[:tick]):
self.sell()
else:
pass
def next(self, tick):
# 如果快线刚好越过慢线，买入全部
if crossover(self.sma1[:tick], self.sma1[:tick]):
self.buy()
# 如果慢线刚好越过快线，卖出全部
elif crossover(self.sma2[:tick], self.sma2[:tick]):
self.sell()
# 其他情况不进行操作
else:
pass
def next(self, tick):
# 如果此时快线刚好越过慢线，买入全部
if crossover(self.sma1[:tick], self.sma2[:tick]):
self.buy()
# 如果是慢线刚好越过快线，卖出全部
elif crossover(self.sma2[:tick], self.sma1[:tick]):
self.sell()
# 否则，这个时刻不执行任何操作
else:
pass
def next(self, tick):
# if fast line overtake slow line, buy all
if crossover(self.sma1[:tick], self.sma2[:tick]):
self.buy()
# if slow line overtake fast line, sell all
elif crossover(self.sma2[:tick], self.sma1[:tick]):
self.sell()
# otherwise，do nothing at this tick.
else:
pass
def next(self, tick):
# buy all, if fast passes slow
if crossover(self.sma1[:tick], self.sma2[:tick]):
self.buy()
# sell all, if flow passes fast
elif crossover(self.sma2[:tick], self.sma1[:tick]):
self.sell()
# do nothing
else:
pass
def get_single_offspring(args):
population, elitism_rate, datas, crossover, mutate = args
parent1 = elitism_selection(population, elitism_rate)
parent2 = elitism_selection(population, elitism_rate)
offspring = crossover(parent1[0], parent2[0])
offspring = mutate(offspring, datas)
return offspring
def LL_crossover_phase(x, x_prime, instance, implementation_choice,
chromossome_length, n_offsprings, crossover_bias):
y = copy(x_prime)
T = 0
if implementation_choice == 1: # original implementation
for i in range(n_offsprings):
offspring = utils.crossover(x, x_prime, crossover_bias)
if (offspring.chromossome == x.chromossome).all():
offspring.value = x.value
elif (offspring.chromossome == y.chromossome).all():
offspring.value = y.value
else:
offspring.value = getattr(evaluate, instance.name)(offspring,
instance)
T += 1
if offspring.value > y.value:
y = offspring
elif implementation_choice == 2: # new implementation: only consider bits where x and x_prime are different
D = np.arange(chromossome_length)[x != x_prime]
nD = len(D)
if nD >= 2: # no crossover if x and x_prime differ in less than two bits
for i in range(n_offsprings):
offspring = utils.crossover_different_bits(
x, x_prime, crossover_bias, D, nD)
offspring.value = getattr(evaluate, instance.name)(offspring,
instance)
T += 1
if offspring.value > y.value:
y = offspring
elif implementation_choice == 3: # same as crossover_implementation=1, but count evaluations even if offspring==parent
for i in range(n_offsprings):
offspring = utils.crossover(x, x_prime, crossover_bias)
offspring.value = getattr(evaluate, instance.name)(offspring,
instance)
T += 1
if offspring.value > y.value:
y = offspring
return y, T
def next(self, tick, t_stamp,*args):
side = ''
# 如果此时快线刚好越过慢线，买入全部
if crossover(self.sma1[:tick], self.sma2[:tick]):
self.buy(*args)
side = "buy"
# 如果是慢线刚好越过快线，卖出全部
elif crossover(self.sma2[:tick], self.sma1[:tick]):
self.sell(*args)
side = "sell"
# 否则，这个时刻不执行任何操作。
else:
pass
if not self._broker._test:
CrawlerToSql(symbol='BTCUSD', limit=5).save_to_sql(t_stamp)
save_strategy_value(self.data.Close[tick], t_stamp, side)
def main():
population = []
generation = 1
for i in range(INITIAL_POPULATION):
population.append(generate_individual(len(MASTER_SOLUTION)))
while generation < MAX_ITERATIONS:
print("Generation: {}, Population: {}".format(generation,
len(population)))
new_population = tournament_selection(population)
population = []
for x, y in new_population:
population.append(crossover(x, y))
population.append(crossover(y, x))
population = mutate_population(population)
generation += 1
while (generation < MAX_ITERATION):
selected_population = []
new_population = []
elitism_selecteds_size = POPULATION_SIZE - int(
(POPULATION_SIZE * SELECTION_PERCENT) / 100)
new_population.extend(get_bests(population, elitism_selecteds_size))
for i in range(int((POPULATION_SIZE * SELECTION_PERCENT) / 100)):
selected_population.append(roulette_selection(population))
selected_population = zip(
selected_population,
selected_population[int(len(selected_population) / 2):])
for x in selected_population:
sons = crossover(x[0].gene, x[1].gene)
new_population.extend(sons)
population_to_mutate = int((POPULATION_SIZE * MUTATION_PERCENT) / 100)
for i in range(population_to_mutate):
new_population[random.randint(0, POPULATION_SIZE - 1)] = mutate(
new_population[random.randint(0, POPULATION_SIZE - 1)].gene)
population = new_population
best_solution = best(population).fitness
generation += 1
print(best(population).gene)
population = gen_population(1000, accept, reject)
bestest = gen_individual(accept, reject)
for i in range(100):
best = ['fjkghdfkghdfkghsdkfhgksdfjhgksjdfhgkjsdhfgkjhsdfkghsdfkjghksdfhgkj', -9999]
print("\nGeneration:", i)
new_pop = []
for _ in range(800):
while True:
try:
m1 = utils.tournament_selection(population, 50)
m2 = utils.tournament_selection(population, 50)
child = utils.crossover(m1[0], m2[0])
child = [child, utils.calc_score(child, accept, reject)]
new_pop.append(child)
break
except:
pass
for _ in range(100):
new_pop.append(gen_individual(accept, reject))
for _ in range(100):
while True:
try:
a = random.choice(population)
b = utils.mutate(a[0])
b = [b, utils.calc_score(b, accept, reject)]
