def test_best_action(self):
q = QValue()
self.assertEqual(q.get_best_action(), 0)
q[ACTION.BUY] = 1
self.assertEqual(q.get_best_action(), ACTION.BUY)
print(q)
def create_q_sequence(self,
*,
start_time,
action,
start_price,
skip_time=1):
if (action == ACTION.BUY) or (action == ACTION.BUY_NOW):
peak_price = self.select_highest_price_time(start_time +
EXECUTE_TIME_MIN)
elif (action == ACTION.SELL) or (action == ACTION.SELL_NOW):
peak_price = self.select_lowest_price_time(start_time +
EXECUTE_TIME_MIN)
prices = self.list_price(start_time=start_time + skip_time,
end_time=peak_price.time,
desc=True)
nop_q = 0
old_q = QValue(start_time=start_time,
start_action=action,
start_price=start_price)
skip_count = 1
# print('creawteq_seq', start_time, action)
for price_rec in prices:
q = QValue(start_time=start_time,
start_action=action,
start_price=start_price)
q.set_price_record(price_rec)
nop_q *= Q_DISCOUNT_RATE
if q.is_same_q_except_nop(old_q):
skip_count += 1
continue
best_action = old_q.get_best_action()
# todo Ajudst Q values for negative values
if best_action == ACTION.BUY or action == ACTION.SELL:
new_q = old_q.max_q() * Q_FIRST_DISCOUNT_RATE * (
Q_DISCOUNT_RATE**skip_count)
else:
new_q = old_q.max_q() * (Q_DISCOUNT_RATE**skip_count)
if nop_q < new_q:
nop_q = new_q
q[ACTION.NOP] = nop_q
#if q.time != start_time:
self.insert_q(time=q.time,
start_time=start_time,
start_action=action,
q_value=q)
old_q = q
skip_count = 1
self.commit()
return old_q.max_q()