# This method retrains the traders from scratch using training data from TRAINING and test data from TESTING
EPISODES = 5
if __name__ == "__main__":
# Create the training data and testing data
# Hint: You can crop the training data with training_data.deepcopy_first_n_items(n)
training_data = StockMarketData([Company.A, Company.B], [Period.TRAINING])
testing_data = StockMarketData([Company.A, Company.B], [Period.TESTING])
#training_data = training_data.deepcopy_first_n_items(6000)
# 12588
#print(f'training_data[Company.A].get_row_count(): {training_data[Company.A].get_row_count()}')
# Create the stock exchange and one traders to train the net
stock_exchange = stock_exchange.StockExchange(10000.0)
training_trader = DeepQLearningTrader(ObscureExpert(Company.A),
ObscureExpert(Company.B), False,
True)
# Save the final portfolio values per episode
final_values_training, final_values_test = [], []
for i in range(EPISODES):
logger.info(f"DQL Trader: Starting training episode {i}")
# train the net
stock_exchange.run(training_data, [training_trader])
training_trader.save_trained_model()
final_values_training.append(
stock_exchange.get_final_portfolio_value(training_trader))
final_portfolio_values = dict(train=[], test=[])
return_pct_per_day = dict(train=[], test=[])
traders = dict(train=[], test=[])
def get_last_portfolio_value(phase: str, run: int) -> float:
index = min(run * EPISODES + EPISODES - 1, len(final_portfolio_values[phase]) - 1)
return final_portfolio_values[phase][index]
def get_last_v_score(phase: str, run: int) -> float:
index = min(run * EPISODES + EPISODES - 1, len(return_pct_per_day[phase]) - 1)
return return_pct_per_day[phase][index]
for run in range(TRAINING_RUNS):
# Create the stock exchange and one traders to train the net
starting_cash = dict(train=10000.0, test=2000.0)
stock_exchanges = dict(train=stock_exchange.StockExchange(starting_cash["train"]),
test=stock_exchange.StockExchange(starting_cash["test"]))
traders['train'].append(DeepQLearningTrader(ObscureExpert(Company.A), ObscureExpert(Company.B), False, True))
for episode in range(EPISODES):
# logger.info(f"DQL Trader: Starting training episode {episode}")
for phase in ['train', 'test']:
if phase == 'test':
testing_trader = DeepQLearningTrader(ObscureExpert(Company.A), ObscureExpert(Company.B), True, False)
if episode == 0:
traders[phase].append(testing_trader)
else:
traders[phase][-1] = testing_trader # replace testing trader from previous episode
trader = traders[phase][-1]
stock_exchanges[phase].run(data[phase], [trader])
