for idx in range(0, len(y_test)):
current_price = y_test[idx] # 重要
buy_sell_num_flag = [
1.0, 0.0, abs(buy_sell_count)
] if buy_sell_count >= 1 else [0.0, 1.0, abs(buy_sell_count)]
state_data = np.array(X_test[idx] + buy_sell_num_flag, dtype='f')
#state_data = state_data.reshape(state_data.shape[0], 1)
action = agent.act(state_data) # 教師が入力に入らないように。
tradecl.update_trading_view(current_price, action)
buy_sell_count, pass_count, money, ethereum, total_money = \
action_if(action, buy_sell_count, pass_count, money, ethereum, total_money, current_price)
# before_money = total_money
print("pass_count：" + str(pass_count))
print("buy_sell_count(at the end of TEST):" + str(buy_sell_count))
print("buy_sell_fee:" + str(buy_sell_fee))
print("====================TEST======================")
print("Initial MONEY:" + str(first_total_money))
print("Final Total MONEY:" + str(total_money))
print("TESTにおいて、Passは" + str(pass_count) + "回")
print("TESTにおいて、buy_sell_countは" + str(buy_sell_count) + "回" +
"(買いの回数が多い)" if buy_sell_count > 0 else "(売りの回数が多い)")
try:
tradecl.draw_trading_view()
except:
pass
print(os.path.basename(__file__))
class FxEnv(gym.Env):
def __init__(self):
self.price_idx = 0
self.trade = TradeClass()
training_set = self.trade.read_bitflyer_json()
print("price_data idx 0-10" + str(training_set[0:10]))
print("price_data idx last 10" + str(training_set[-1]))
self.input_len = 400
self.n_actions = 3
self.obs_size = self.input_len + self.n_actions #env.observation_space.shape[0]
self.X_train = []
self.y_train = []
for i in range(self.input_len, len(training_set) - 1001):
# X_train.append(np.flipud(training_set_scaled[i-60:i]))
self.X_train.append(training_set[i - self.input_len:i])
self.y_train.append(training_set[i])
self.price = self.y_train
self.money = 300
self.before_money = copy.deepcopy(self.money)
self.cripto = 0.1
self.total_money = self.money + np.float64(self.price[0] * self.cripto)
self.first_total_money = self.total_money
self.pass_count = 0
self.buy_sell_count = 0 # buy+ sell -
self.pass_renzoku_count = 0
self.buy_sell_fee = 0.00001
def _reset(self):
self.price_idx = 0
return self.X_train[self.price_idx]
def _seed(self, seed=None):
pass
def buy_simple(self, money, cripto, total_money, current_price):
first_money, first_cripto, first_total_money = money, cripto, total_money
spend = money * 0.1
money -= spend * (1 + self.buy_sell_fee)
if money <= 0.0:
return first_money, first_cripto, first_total_money
cripto += float(spend / current_price)
total_money = money + cripto * current_price
return money, cripto, total_money
def sell_simple(self, money, cripto, total_money, current_price):
first_money, first_cripto, first_total_money = money, cripto, total_money
spend = cripto * 0.1
cripto -= spend * (1 + self.buy_sell_fee)
if cripto <= 0.0:
return first_money, first_cripto, first_total_money
money += float(spend * current_price)
total_money = money + float(cripto * current_price)
return money, cripto, total_money
def pass_simple(self, money, cripto, total_money, current_price):
total_money = money + float(cripto * current_price)
return money, cripto, total_money
def _step(self, action):
self.price_idx += 1
current_price = self.X_train[self.price_idx][-1]
buy_sell_num_array = [
1.0, 0.0, self.buy_sell_count
] if self.buy_sell_count >= 1 else [0.0, 1.0, self.buy_sell_count]
self.trade.update_trading_view(current_price, action)
pass_reward = 0
if action == 0:
print("buy")
self.buy_sell_count += 1
self.money, self.cripto, self.total_money = self.buy_simple(
self.money, self.cripto, self.total_money, current_price)
elif action == 1:
print("sell")
self.buy_sell_count -= 1
self.money, self.cripto, self.total_money = self.sell_simple(
self.money, self.cripto, self.total_money, current_price)
else:
print("PASS")
self.money, self.cripto, self.total_money = self.pass_simple(
self.money, self.cripto, self.total_money, current_price)
pass_reward = 0.0 # -0.001)#0.01 is default
self.pass_count += 1
reward = self.total_money - self.before_money + pass_reward
if self.buy_sell_count >= 5 and action == 0:
print("buy_sell" + str(self.buy_sell_count) + "回 action==" +
str(action))
reward -= (float(abs(self.buy_sell_count)**2))
print(reward)
elif self.buy_sell_count <= -5 and action == 1:
print("buy_sell" + str(self.buy_sell_count) + "回 action==" +
str(action))
reward -= (float(abs(self.buy_sell_count)**2))
print(reward)
else:
# reward 1.0がちょうど良い！
reward += 1.1
self.before_money = copy.deepcopy(self.total_money)
if self.price_idx % 2000 == 1000:
print("last action:" + str(action))
print("TOTAL MONEY" + str(self.total_money))
print("100回中passは" + str(self.pass_count) + "回")
# print("100回中buy_sell_countは" + str(self.buy_sell_count) + "回")
self.pass_count = 0
self.trade.draw_trading_view()
current_asset = [self.cripto, self.money]
# obs, reward, done, infoを返す
return [
self.X_train[self.price_idx], buy_sell_num_array, current_asset
], reward, False, None
class FxEnv(gym.Env):
def __init__(self):
self.price_idx = 0
self.trade = TradeClass()
training_set = self.trade.read_bitflyer_json()
print("price_data idx 0-10" + str(training_set[0:10]))
print("price_data idx last 10" + str(training_set[-1]))
self.length_data = len(training_set)
self.input_len = 400
self.n_actions = 3
self.asset_info_len = 2
self.buy_sell_count_len = 4
#TODO
self.observe_size = self.input_len + self.buy_sell_count_len #+self.asset_info_len #env.observation_space.shape[0]
self.data = []
self.y_train = []
for i in range(self.input_len, self.length_data - 1001):
# data.append(np.flipud(training_set_scaled[i-60:i]))
self.data.append(training_set[i - self.input_len:i])
self.y_train.append(training_set[i])
self.price = self.y_train
self.money = 500
self.before_money = copy.deepcopy(self.money)
self.cripto = 0.00001
self.total_money = self.money + np.float64(self.price[0] * self.cripto)
self.first_total_money = self.total_money
self.pass_count = 0
self.buy_sell_count = 0 # buy+ sell -
self.pass_renzoku_count = 0
self.buy_sell_fee = 0.00001
self.current_asset = [self.cripto, self.money]
self.action_space = gym.spaces.Discrete(3) # 東西南北
self.MAP = np.array([0 for idx in range(0, self.observe_size)])
self.inventory = []
self.observation_space = gym.spaces.Box(low=0,
high=3,
shape=self.MAP.shape)
self.begin_total_money = self.money + self.cripto * self.price[0]
print("LENGTH OF LOOP NUM:" + str(len(self.data)))
self.buy_inventory = []
self.sell_inventory = []
self.total_profit = 0
def _reset(self):
self.price_idx = 0
return self.data[self.price_idx] + [0, 0, 0, 0
] #TODO: +self.current_asset
def _seed(self, seed=None):
return self.length_data
def return_lenghth_steps(self):
return self.length_data
def _render(self, mode='', close=False):
#画面への表示 主にGUI
pass
def buy_simple(self, money, cripto, total_money, current_price):
first_money, first_cripto, first_total_money = money, cripto, total_money
spend = money * 0.1
money -= spend * (1 + self.buy_sell_fee)
if money <= 0.0:
return first_money, first_cripto, first_total_money
cripto += float(spend / current_price)
total_money = money + cripto * current_price
return money, cripto, total_money
def sell_simple(self, money, cripto, total_money, current_price):
first_money, first_cripto, first_total_money = money, cripto, total_money
spend = cripto * 0.1
cripto -= spend * (1 + self.buy_sell_fee)
if cripto <= 0.0:
return first_money, first_cripto, first_total_money
money += float(spend * current_price)
total_money = money + float(cripto * current_price)
return money, cripto, total_money
def pass_simple(self, money, cripto, total_money, current_price):
total_money = money + float(cripto * current_price)
return money, cripto, total_money
def buy_lot(self, money, cripto, total_money, current_price):
first_money, first_cripto, first_total_money = money, cripto, total_money
spend = current_price * 0.001
money -= spend * (1 + self.buy_sell_fee)
EMPTY_MONEY_FLAG = False
if money <= 0.0:
EMPTY_MONEY_FLAG = True
return first_money, first_cripto, first_total_money, EMPTY_MONEY_FLAG
cripto += float(spend / current_price)
total_money = money + cripto * current_price
return money, cripto, total_money, EMPTY_MONEY_FLAG
def sell_lot(self, money, cripto, total_money, current_price):
first_money, first_cripto, first_total_money = money, cripto, total_money
spend = cripto * 0.001
cripto -= spend * (1 + self.buy_sell_fee)
EMPTY_MONEY_FLAG = False
if cripto <= 0.0:
EMPTY_MONEY_FLAG = True
return first_money, first_cripto, first_total_money, EMPTY_MONEY_FLAG
money += float(spend * current_price)
total_money = money + float(cripto * current_price)
return money, cripto, total_money, EMPTY_MONEY_FLAG
def _step(self, action):
if type(action) is list or type(action) is np.ndarray:
action = action.tolist()
action = action.index(max(action))
else:
pass
self.price_idx += 1
current_price = self.data[self.price_idx][-1]
self.trade.update_trading_view(current_price, action)
len_buy = len(self.buy_inventory)
len_sell = len(self.sell_inventory)
if len_buy > 40:
buy_flag = 1
sell_flag = 0
elif len_sell > 40:
buy_flag = 0
sell_flag = 1
else:
buy_flag = 0
sell_flag = 0
buy_sell_array = [len_buy, len_sell, buy_flag, sell_flag]
#TODO idx + 1じゃなくて良いか？ バグの可能性あり。=>修正済み
#next_state = getStateFromCsvData(self.data, self.price_idx+1, window_size)
reward = 0
if action == 1 and len(self.sell_inventory) > 0: # sell
i = 0
for i in range(0, int(len(self.sell_inventory) / 10)):
sold_price = self.sell_inventory.pop(0)
profit = sold_price - current_price
reward = profit #max(profit, 0)
self.total_profit += profit
#print("Buy(空売りの決済): " + str(current_price) + " | Profit: " + str(profit))
reward = reward / (i + 1)
elif action == 1 and len(self.buy_inventory) < 50: # buy
self.buy_inventory.append(current_price)
#print("Buy: " + str(current_price))
elif action == 2 and len(self.buy_inventory) > 0: # sell
i = 0
for i in range(0, int(len(self.buy_inventory) / 10)):
bought_price = self.buy_inventory.pop(0)
profit = current_price - bought_price
reward = profit # max(profit, 0)
self.total_profit += profit
#print("Sell: " + str(current_price) + " | Profit: " + formatPrice(profit))
reward = reward / (i + 1)
elif action == 2 and len(self.sell_inventory) < 50:
self.sell_inventory.append(current_price)
#print("Sell(空売り): " + formatPrice(current_price))
#print("Reward: "+str(reward))
print("inventory(sell) : " + str(len(self.sell_inventory)) +
" inventory(buy) : " + str(len(self.buy_inventory)))
print("TOTAL PROFIT: " + str(self.total_profit))
if False: #self.price_idx % 10000 == 1000:
try:
print("TOTAL PROFIT: " + str(self.total_profit))
print("inventory(sell) : " + str(len(self.sell_inventory)) +
" inventory(buy) : " +
str(len(self.buy_inventory)))
self.trade.draw_trading_view()
except:
pass
done = True if self.price_idx == self.length_data - 1 else False
# obs, reward, done, infoを返す
return self.data[self.price_idx] + buy_sell_array, reward, done, {}
money, ethereum, total_money = pass_simple(money, ethereum,
total_money,
current_price)
reward += 0.00000
pass_count += 1
before_money = total_money
if idx % 10000 == 500:
print("BEGGINING MONEY:" + str(first_total_money))
print("FINAL MONEY:" + str(total_money))
print("1000回中passは" + str(pass_count) + "回")
print("1000回終わった後のbuy_sell_countは" + str(buy_sell_count) + "回")
print("total_reward:" + str(total_reward))
pass_count = 0
trade.draw_trading_view()
agent.save('chainerRLAgent')
#agent.stop_episode_and_train(X_train[-1], reward, True)
# Save an agent to the 'agent' directory
agent.save('chainerRLAgent')
print("START MONEY" + str(first_total_money))
#テスト
'''
for i in range(0,1):
reward=0
price = y_train
money = 300
class FxEnv(gym.Env):
def __init__(self):
self.price_idx = 0
self.trade = TradeClass()
training_set = self.trade.read_bitflyer_json()
print("price_data idx 0-10" + str(training_set[0:10]))
print("price_data idx last 10" + str(training_set[-1]))
self.input_len = 400
self.n_actions = 3
self.asset_info_len = 2
self.buy_sell_count_len = 4
self.observe_size = self.input_len + self.buy_sell_count_len + self.asset_info_len # env.observation_space.shape[0]
self.X_train = []
self.y_train = []
for i in range(self.input_len, len(training_set) - 1001):
# X_train.append(np.flipud(training_set_scaled[i-60:i]))
self.X_train.append(training_set[i - self.input_len:i])
self.y_train.append(training_set[i])
self.price = self.y_train
self.money = 500
self.before_money = copy.deepcopy(self.money)
self.cripto = 0.00001
self.total_money = self.money + np.float64(self.price[0] * self.cripto)
self.first_total_money = self.total_money
self.pass_count = 0
self.buy_sell_count = 0 # buy+ sell -
self.pass_renzoku_count = 0
self.buy_sell_fee = 0.00001
self.current_asset = [self.cripto, self.money]
self.action_space = gym.spaces.Discrete(3) # 東西南北
self.MAP = np.array([0 for idx in range(0, self.observe_size)])
self.inventory = []
self.observation_space = gym.spaces.Box(
low=0,
high=3,
shape=self.MAP.shape
)
self.begin_total_money = self.y_train[0]
print("LENGTH OF LOOP NUM:" + str(len(self.X_train)))
def _reset(self):
self.price_idx = 0
return self.X_train[self.price_idx] + [0, 0, 0, 0] + self.current_asset
def _seed(self, seed=None):
pass
def _render(self, mode='', close=False):
# 画面への表示 主にGUI
pass
def buy_simple(self, money, cripto, total_money, current_price):
first_money, first_cripto, first_total_money = money, cripto, total_money
spend = money * 0.1
money -= spend * (1 + self.buy_sell_fee)
if money <= 0.0:
return first_money, first_cripto, first_total_money
cripto += float(spend / current_price)
total_money = money + cripto * current_price
return money, cripto, total_money
def sell_simple(self, money, cripto, total_money, current_price):
first_money, first_cripto, first_total_money = money, cripto, total_money
spend = cripto * 0.1
cripto -= spend * (1 + self.buy_sell_fee)
if cripto <= 0.0:
return first_money, first_cripto, first_total_money
money += float(spend * current_price)
total_money = money + float(cripto * current_price)
return money, cripto, total_money
def pass_simple(self, money, cripto, total_money, current_price):
total_money = money + float(cripto * current_price)
return money, cripto, total_money
def buy_lot(self, money, cripto, total_money, current_price):
first_money, first_cripto, first_total_money = money, cripto, total_money
spend = current_price * 0.001
money -= spend * (1 + self.buy_sell_fee)
EMPTY_MONEY_FLAG = False
if money <= 0.0:
EMPTY_MONEY_FLAG = True
return first_money, first_cripto, first_total_money, EMPTY_MONEY_FLAG
cripto += float(spend / current_price)
total_money = money + cripto * current_price
return money, cripto, total_money, EMPTY_MONEY_FLAG
def sell_lot(self, money, cripto, total_money, current_price):
first_money, first_cripto, first_total_money = money, cripto, total_money
spend = cripto * 0.001
cripto -= spend * (1 + self.buy_sell_fee)
EMPTY_MONEY_FLAG = False
if cripto <= 0.0:
EMPTY_MONEY_FLAG = True
return first_money, first_cripto, first_total_money, EMPTY_MONEY_FLAG
money += float(spend * current_price)
total_money = money + float(cripto * current_price)
return money, cripto, total_money, EMPTY_MONEY_FLAG
def _step(self, action):
if type(action) is list or type(action) is np.ndarray:
action = action.tolist()
action = action.index(max(action))
else:
pass
self.price_idx += 1
current_price = self.X_train[self.price_idx][-1]
if abs(self.buy_sell_count) >= 10:
between_range = 0.0
else:
between_range = 1.0
buy_sell_num_array = [1.0, 0.0, abs(self.buy_sell_count), between_range] if self.buy_sell_count >= 0 else [0.0,
1.0,
abs(
self.buy_sell_count),
between_range]
self.trade.update_trading_view(current_price, action)
reward = 0
if action == 0:
print("buy")
self.buy_sell_count += 1
self.money, self.cripto, self.total_money = self.buy_simple(self.money, self.cripto, self.total_money,
current_price)
if self.buy_sell_count < 0:
reward += 0.01
else:
reward -= 0.01
elif action == 1 and len(self.inventory) > 0:
print("sell")
self.buy_sell_count -= 1
self.money, self.cripto, self.total_money = self.sell_simple(self.money, self.cripto, self.total_money,
current_price)
if self.buy_sell_count > 0:
reward += 0.01
else:
reward -= 0.01
else:
print("PASS")
self.money, self.cripto, self.total_money = self.pass_simple(self.money, self.cripto, self.total_money,
current_price)
reward += 0.000000 # -0.001)#0.01 is default
self.pass_count += 1
reward += 0.01 * (self.total_money - self.before_money)
print("buy_sell" + str(self.buy_sell_count) + "回 action==" + str(action))
self.before_money = self.total_money
if False: # self.price_idx % 50000 == 1000:
print("last action:" + str(action))
print("TOTAL MONEY" + str(self.total_money))
print("100回中passは" + str(self.pass_count) + "回")
# print("100回中buy_sell_countは" + str(self.buy_sell_count) + "回")
self.pass_count = 0
try:
self.trade.draw_trading_view()
except:
pass
print("begin MONEY: " + str(self.begin_total_money))
print("current MONEY: " + str(self.total_money))
print("price_IDX: " + str(self.price_idx))
print("Reward: " + str(reward))
self.current_asset = [self.cripto, self.money]
# obs, reward, done, infoを返す
return self.X_train[self.price_idx] + buy_sell_num_array + self.current_asset, reward, False, {}
pred = pred_array[idx][0]
if pred - before_pred > 0.00005:
action = 0
elif pred - before_pred < -0.00005:
action = 1
else:
action = 2
tradecl.update_trading_view(current_price, action)
buy_sell_count, pass_count, money, cripto, total_money = \
action_if(action,buy_sell_count,pass_count,money,cripto,total_money,current_price)
before_money = total_money
before_price = current_price
before_pred = pred
before_action = action
print("====================TEST======================")
print("START MONEY" + str(first_total_money))
print("FINAL MONEY:" + str(total_money))
print("pass_count：" + str(pass_count))
print("buy_sell_count(at the end of TEST):" + str(buy_sell_count))
#matploblibでトレードの結果をグラフで可視化
try:
tradecl.draw_trading_view("main_price_prediction.png")
except:
print(traceback.format_exc())
print("tradecl.draw_trading_view FAILED!!")