# In[197]:
print("==============Get Backtest Results===========")
perf_stats_all = backtest_stats(account_value=df_account_value, value_col_name = 'total_assets')
# <a id='6.2'></a>
# ## 7.2 BackTestPlot
# In[198]:
print("==============Compare to DJIA===========")
get_ipython().run_line_magic('matplotlib', 'inline')
# S&P 500: ^GSPC
# Dow Jones Index: ^DJI
# NASDAQ 100: ^NDX
backtest_plot(df_account_value,
baseline_ticker = '^DJI',
baseline_start = '2019-01-01',
baseline_end = '2021-01-01', value_col_name = 'total_assets')
# In[ ]:
df_account_value, df_actions = DRLAgent.DRL_prediction(model=trained_a2c,
environment=e_trade_gym)
df_account_value.shape
df_account_value.tail()
############# BACKTEST #############
print("==============Get Backtest Results===========")
now = datetime.datetime.now().strftime('%Y%m%d-%Hh%M')
perf_stats_all = backtest_stats(account_value=df_account_value)
perf_stats_all = pd.DataFrame(perf_stats_all)
#baseline stats
print("==============Get Baseline Stats===========")
baseline_df = get_baseline(ticker="^DJI", start='2019-01-01', end='2021-01-01')
stats = backtest_stats(baseline_df, value_col_name='close')
print("==============Compare to DJIA===========")
# S&P 500: ^GSPC
# Dow Jones Index: ^DJI
# NASDAQ 100: ^NDX
backtest_plot(df_account_value,
baseline_ticker='^DJI',
baseline_start='2019-01-01',
baseline_end='2021-01-01')
df_account_value.date
def main():
if not os.path.exists("./" + config.DATA_SAVE_DIR):
os.makedirs("./" + config.DATA_SAVE_DIR)
if not os.path.exists("./" + config.TRAINED_MODEL_DIR):
os.makedirs("./" + config.TRAINED_MODEL_DIR)
if not os.path.exists("./" + config.TENSORBOARD_LOG_DIR):
os.makedirs("./" + config.TENSORBOARD_LOG_DIR)
if not os.path.exists("./" + config.RESULTS_DIR):
os.makedirs("./" + config.RESULTS_DIR)
print(config.START_DATE)
print(config.END_DATE)
print(config.PENNY_STOCKS)
df = YahooDownloader(start_date=config.START_DATE,
end_date=config.END_DATE,
ticker_list=config.PENNY_STOCKS).fetch_data()
fe = FeatureEngineer(use_technical_indicator=True,
tech_indicator_list=config.TECHNICAL_INDICATORS_LIST,
use_turbulence=True,
user_defined_feature=False)
processed = fe.preprocess_data(df)
information_cols = list(processed)
information_cols.remove('date')
information_cols.remove('tic')
stock_dimension = len(processed.tic.unique())
state_space = 1 + 2 * stock_dimension + len(
information_cols) * stock_dimension
print("Stock Dimension: {}, State Space: {}".format(
stock_dimension, state_space))
env_kwargs = {
"hmax": 100,
"initial_amount": 5000,
# Since in Indonesia the minimum number of shares per trx is 100, then we scaled the initial amount by dividing it with 100
"buy_cost_pct": 0.00, # IPOT has 0.19% buy cost
"sell_cost_pct": 0.00, # IPOT has 0.29% sell cost
"state_space": state_space,
"stock_dim": stock_dimension,
"tech_indicator_list": information_cols,
"action_space": stock_dimension,
"reward_scaling": 1e-4,
"print_verbosity": 5
}
rebalance_window = 63 # rebalance_window is the number of days to retrain the model
validation_window = 63 # validation_window is the number of days to do validation and trading (e.g. if validation_window=63, then both validation and trading period will be 63 days)
train_start = config.START_DATE
train_end = config.START_TRADE_DATE
val_test_start = config.START_TRADE_DATE
val_test_end = config.END_DATE
ensemble_agent = DRLEnsembleAgent(df=processed,
train_period=(train_start, train_end),
val_test_period=(val_test_start,
val_test_end),
rebalance_window=rebalance_window,
validation_window=validation_window,
**env_kwargs)
A2C_model_kwargs = {
'n_steps': 5,
'ent_coef': 0.01,
'learning_rate': 0.0005
}
PPO_model_kwargs = {
"ent_coef": 0.01,
"n_steps": 2048,
"learning_rate": 0.00025,
"batch_size": 128
}
DDPG_model_kwargs = {
"action_noise": "ornstein_uhlenbeck",
"buffer_size": 50000,
"learning_rate": 0.000005,
"batch_size": 128
}
TD3_model_kwargs = {
"batch_size": 100,
"buffer_size": 1000000,
"learning_rate": 0.001
}
timesteps_dict = {'a2c': 4000, 'ppo': 4000, 'ddpg': 4000, 'td3': 4000}
df_summary = ensemble_agent.run_ensemble_strategy(A2C_model_kwargs,
PPO_model_kwargs,
DDPG_model_kwargs,
TD3_model_kwargs,
timesteps_dict)
print(df_summary)
unique_trade_date = processed[(processed.date > val_test_start) & (
processed.date <= val_test_end)].date.unique()
df_trade_date = pd.DataFrame({'datadate': unique_trade_date})
df_account_value = pd.DataFrame()
for i in range(rebalance_window + validation_window,
len(unique_trade_date) + 1, rebalance_window):
print(rebalance_window + validation_window)
print(len(unique_trade_date) + 1)
print(rebalance_window)
try:
temp = pd.read_csv('results/account_value_trade_{}_{}.csv'.format(
'ensemble', i))
df_account_value = df_account_value.append(temp, ignore_index=True)
except:
break
sharpe = (252**0.5) * df_account_value.account_value.pct_change(
1).mean() / df_account_value.account_value.pct_change(1).std()
print('Sharpe Ratio: ', sharpe)
df_account_value = df_account_value.join(
df_trade_date[validation_window:].reset_index(drop=True))
df_account_value.account_value.plot()
print("==============Get Backtest Results===========")
now = datetime.datetime.now().strftime('%Y%m%d-%Hh%M')
perf_stats_all = backtest_stats(account_value=df_account_value)
perf_stats_all = pd.DataFrame(perf_stats_all)
print("==============Compare to IHSG===========")
backtest_plot(df_account_value,
baseline_ticker='^DJI',
baseline_start=df_account_value.loc[0, 'date'],
baseline_end=df_account_value.loc[len(df_account_value) - 1,
'date'])
environment = e_trade_gym)
df_account_value.shape
df_account_value.head()
df_actions.head()
print("==============Get Backtest Results===========")
now = datetime.datetime.now().strftime('%Y%m%d-%Hh%M')
perf_stats_all = backtest_stats(account_value=df_account_value)
perf_stats_all = pd.DataFrame(perf_stats_all)
perf_stats_all.to_csv("./"+config.RESULTS_DIR+"/perf_stats_all_"+now+'.csv')
print("==============Compare to DJIA===========")
# %matplotlib inline
# S&P 500: ^GSPC
# Dow Jones Index: ^DJI
# NASDAQ 100: ^NDX
backtest_plot(df_account_value, config,
baseline_start = '2019-01-01',
baseline_end = '2021-01-01')
print("==============Get Baseline Stats===========")
baseline_df = get_baseline(
ticker="^DJI", start = '2019-01-01',
end = '2021-01-01')
stats = backtest_stats(baseline_df, value_col_name = 'close')
def train_one(fetch=False):
"""
train an agent
"""
if fetch:
df = fetch_and_store()
else:
df = load()
counts = df[['date', 'tic']].groupby(['date']).count().tic
assert counts.min() == counts.max()
print("==============Start Feature Engineering===========")
fe = FeatureEngineer(
use_technical_indicator=True,
tech_indicator_list=config.TECHNICAL_INDICATORS_LIST,
use_turbulence=True,
# use_turbulence=False,
user_defined_feature=False,
)
processed = fe.preprocess_data(df)
# Training & Trading data split
start_date, trade_date, end_date = calculate_split(df,
start=config.START_DATE)
print(start_date, trade_date, end_date)
train = data_split(processed, start_date, trade_date)
trade = data_split(processed, trade_date, end_date)
print(
f'\n******\nRunning from {start_date} to {end_date} for:\n{", ".join(config.CRYPTO_TICKER)}\n******\n'
)
# calculate state action space
stock_dimension = len(train.tic.unique())
state_space = (1 + (2 * stock_dimension) +
(len(config.TECHNICAL_INDICATORS_LIST) * stock_dimension))
env_kwargs = {
"hmax": 100,
"initial_amount": 100000,
"buy_cost_pct": 0.0026,
"sell_cost_pct": 0.0026,
"state_space": state_space,
"stock_dim": stock_dimension,
"tech_indicator_list": config.TECHNICAL_INDICATORS_LIST,
"action_space": stock_dimension,
"reward_scaling": 1e-4
}
e_train_gym = StockTradingEnv(df=train, **env_kwargs)
e_trade_gym = StockTradingEnv(df=trade,
turbulence_threshold=250,
make_plots=True,
**env_kwargs)
env_train, _ = e_train_gym.get_sb_env()
env_trade, obs_trade = e_trade_gym.get_sb_env()
agent = DRLAgent(env=env_train)
print("==============Model Training===========")
now = datetime.datetime.now().strftime(config.DATETIME_FMT)
model_sac = agent.get_model("sac")
trained_sac = agent.train_model(
model=model_sac,
tb_log_name="sac",
# total_timesteps=100
total_timesteps=80000)
print("==============Start Trading===========")
df_account_value, df_actions = DRLAgent.DRL_prediction(
# model=trained_sac, test_data=trade, test_env=env_trade, test_obs=obs_trade
trained_sac,
e_trade_gym)
df_account_value.to_csv(
f"./{config.RESULTS_DIR}/df_account_value_{now}.csv")
df_actions.to_csv(f"./{config.RESULTS_DIR}/df_actions_{now}.csv")
df_txns = pd.DataFrame(e_trade_gym.transactions,
columns=['date', 'amount', 'price', 'symbol'])
df_txns = df_txns.set_index(pd.DatetimeIndex(df_txns['date'], tz=pytz.utc))
df_txns.to_csv(f'./{config.RESULTS_DIR}/df_txns_{now}.csv')
df_positions = pd.DataFrame(e_trade_gym.positions,
columns=['date', 'cash'] +
config.CRYPTO_TICKER)
df_positions = df_positions.set_index(
pd.DatetimeIndex(df_positions['date'],
tz=pytz.utc)).drop(columns=['date'])
df_positions['cash'] = df_positions.astype(
{col: np.float64
for col in df_positions.columns})
df_positions.to_csv(f'./{config.RESULTS_DIR}/df_positions_{now}.csv')
print("==============Get Backtest Results===========")
perf_stats_all = backtest_stats(df_account_value,
transactions=df_txns,
positions=df_positions)
perf_stats_all = pd.DataFrame(perf_stats_all)
perf_stats_all.to_csv(f"./{config.RESULTS_DIR}/perf_stats_all_{now}.csv")
backtest_plot(df_account_value,
baseline_start=trade_date,
baseline_end=end_date,
positions=df_positions,
transactions=df_txns)