def _create_wallet_source(wallet: 'Wallet', include_worth: bool = True) -> 'List[Stream[float]]':
"""Creates a list of streams to describe a `Wallet`.
Parameters
----------
wallet : `Wallet`
The wallet to make streams for.
include_worth : bool, default True
Whether or
Returns
-------
`List[Stream[float]]`
A list of streams to describe the `wallet`.
"""
exchange_name = wallet.exchange.name
symbol = wallet.instrument.symbol
streams = []
with NameSpace(exchange_name + ":/" + symbol):
free_balance = Stream.sensor(wallet, lambda w: w.balance.as_float(), dtype="float").rename("free")
locked_balance = Stream.sensor(wallet, lambda w: w.locked_balance.as_float(), dtype="float").rename("locked")
total_balance = Stream.sensor(wallet, lambda w: w.total_balance.as_float(), dtype="float").rename("total")
streams += [free_balance, locked_balance, total_balance]
if include_worth:
price = Stream.select(wallet.exchange.streams(), lambda node: node.name.endswith(symbol))
worth = price.mul(total_balance).rename('worth')
streams += [worth]
return streams
def __init__(self, price: 'Stream'):
super().__init__()
self.position = -1
r = Stream.sensor(price, lambda p: p.value, dtype="float").diff()
position = Stream.sensor(self, lambda rs: rs.position, dtype="float")
reward = (r * position).fillna(0).rename("reward")
self.feed = DataFeed([reward])
self.feed.compile()
def __init__(self, price: 'Stream') -> None:
super().__init__()
self.position = -1
self.executed = 0
r = (Stream.sensor(price, lambda p: p.value,
dtype="float").pct_change()) #.log10()).diff()
position = Stream.sensor(self, lambda rs: rs.position, dtype="float")
executed = Stream.sensor(self, lambda rs: rs.executed, dtype="float")
reward = (position * r - executed).fillna(0).rename("reward")
self.feed = DataFeed([reward])
self.feed.compile()
def __init__(self, price: 'Stream') -> None:
super().__init__()
self.position = -1
## PBR works when commissions are negligible.
## Need to modify the following line to make it work for cases where commissions are substantial:
###NOTE: the agent learns to hold its position when abs(r) < commission
#r = Stream.sensor(price, lambda p: p.value, dtype="float").diff()
r = Stream.sensor(price, lambda p: p.value, dtype="float").pct_change()
position = Stream.sensor(self, lambda rs: rs.position, dtype="float")
reward = ((position * r).fillna(0)).rename("reward")
self.feed = DataFeed([reward])
self.feed.compile()
def __init__(self, price: 'Stream') -> None:
super().__init__()
self.position = 0
self.price = 0
self.pre_networth = 0
r = Stream.sensor(price, lambda p: p.value, dtype="float").diff()
position = Stream.sensor(self, lambda rs: rs.position, dtype="float")
reward = (position * r).fillna(0).rename("reward")
self.feed = DataFeed([reward])
self.feed.compile()
def create_env_for_predicting(config):
t = price_history['Close']
p = Stream.source(t.tolist(), dtype="float").rename("USD-BTC")
bitfinex = Exchange("bitfinex", service=execute_order)(Stream.source(
price_history['Close'].tolist(), dtype="float").rename("USD-BTC"))
cash = Wallet(bitfinex, 100000 * USD)
asset = Wallet(bitfinex, 0 * BTC)
portfolio = Portfolio(USD, [cash, asset])
feed = DataFeed([
p,
p.rolling(window=10).mean().rename("fast"),
p.rolling(window=50).mean().rename("medium"),
p.rolling(window=100).mean().rename("slow"),
p.log().diff().fillna(0).rename("lr")
])
reward_scheme = PBR(price=p)
action_scheme = BSH(cash=cash, asset=asset).attach(reward_scheme)
renderer_feed = DataFeed([
Stream.source(price_history['Close'].tolist(),
dtype="float").rename("price"),
Stream.sensor(action_scheme, lambda s: s.action,
dtype="float").rename("action")
])
environment = default.create(feed=feed,
portfolio=portfolio,
action_scheme=action_scheme,
reward_scheme=reward_scheme,
renderer_feed=renderer_feed,
renderer=PositionChangeChart(),
window_size=config["window_size"],
max_allowed_loss=0.6)
return environment
def create_env(config):
x = np.arange(0, 2 * np.pi, 2 * np.pi / 1001)
y = 50 * np.sin(3 * x) + 100
x = np.arange(0, 2 * np.pi, 2 * np.pi / 1000)
p = Stream.source(y, dtype="float").rename("USD-TTC")
coinbase = Exchange("coinbase", service=execute_order)(p)
cash = Wallet(coinbase, 100000 * USD)
asset = Wallet(coinbase, 0 * TTC)
portfolio = Portfolio(USD, [cash, asset])
feed = DataFeed([
p,
p.rolling(window=10).mean().rename("fast"),
p.rolling(window=50).mean().rename("medium"),
p.rolling(window=100).mean().rename("slow"),
p.log().diff().fillna(0).rename("lr")
])
reward_scheme = PBR(price=p)
action_scheme = BSH(cash=cash, asset=asset).attach(reward_scheme)
renderer_feed = DataFeed([
Stream.source(y, dtype="float").rename("price"),
Stream.sensor(action_scheme, lambda s: s.action,
dtype="float").rename("action")
])
chart_renderer = PlotlyTradingChart(
display=True, # show the chart on screen (default)
height=
800, # affects both displayed and saved file height. None for 100% height.
save_format="html", # save the chart to an HTML file
auto_open_html=True, # open the saved HTML chart in a new browser tab
)
import uuid
uid = uuid.uuid4()
callback = LoggingCallback(f'/Users/vkrot/callback-{uid}', chart_renderer)
environment = default.create(
feed=feed,
portfolio=portfolio,
action_scheme=action_scheme,
reward_scheme=reward_scheme,
renderer_feed=renderer_feed,
# renderer=PositionChangeChart(),
renderer=PositionChangeChart(),
window_size=config["window_size"],
max_allowed_loss=0.6,
callback=callback)
return environment
def create_env_sin(config):
x = np.arange(0, 2 * np.pi, 2 * np.pi / 1001)
y = 50 * np.sin(3 * x) + 100
x = np.arange(0, 2 * np.pi, 2 * np.pi / 1000)
p = Stream.source(y, dtype="float").rename("USD-TTC")
bitfinex = Exchange("bitfinex", service=execute_order)(p)
cash = Wallet(bitfinex, 10000 * USD)
asset = Wallet(bitfinex, 0 * TTC)
portfolio = Portfolio(USD, [cash, asset])
feed = DataFeed([
p,
p.rolling(window=10).mean().rename("fast"),
p.rolling(window=50).mean().rename("medium"),
p.rolling(window=100).mean().rename("slow"),
p.log().diff().fillna(0).rename("lr")
])
reward_scheme = default.rewards.PBREX(price=p)
#action_scheme = default.actions.BSHEX(
# cash=cash,
# asset=asset
#).attach(reward_scheme)
action_scheme = default.actions.SimpleOrders(
trade_sizes=3).attach(reward_scheme)
renderer_feed = DataFeed([
Stream.source(y, dtype="float").rename("price"),
Stream.sensor(action_scheme, lambda s: s.action,
dtype="float").rename("action")
])
environment = default.create(feed=feed,
portfolio=portfolio,
action_scheme=action_scheme,
reward_scheme=reward_scheme,
renderer_feed=renderer_feed,
renderer=PositionChangeChart(),
window_size=config["window_size"],
max_allowed_loss=0.6)
return environment
def create_env(config):
df = load_csv('btc_usdt_m5_history.csv')
y = df['close'].tolist()
p = Stream.source(y, dtype="float").rename("USD-TTC")
bitfinex = Exchange("bitfinex", service=execute_order)(p)
cash = Wallet(bitfinex, 100000 * USD)
asset = Wallet(bitfinex, 0 * TTC)
portfolio = Portfolio(USD, [cash, asset])
feed = DataFeed([
p,
p.rolling(window=10).mean().rename("fast"),
p.rolling(window=50).mean().rename("medium"),
p.rolling(window=100).mean().rename("slow"),
p.log().diff().fillna(0).rename("lr")
])
reward_scheme = SimpleProfit(window_size=12)
action_scheme = ManagedRiskOrders()
renderer_feed = DataFeed([
Stream.source(y, dtype="float").rename("price"),
Stream.sensor(action_scheme, lambda s: s.action,
dtype="float").rename("action")
])
environment = default.create(
feed=feed,
portfolio=portfolio,
action_scheme=action_scheme,
reward_scheme=reward_scheme,
renderer_feed=renderer_feed,
renderer=default.renderers.PlotlyTradingChart(),
window_size=config["window_size"],
max_allowed_loss=0.6)
return environment
def create_env(config):
x = np.arange(0, 2 * np.pi, 2 * np.pi / 1001)
y = 50 * np.sin(3 * x) + 100
p = Stream.source(y, dtype="float").rename("USD-TTC")
coinbase = Exchange("coinbase", service=execute_order)(p)
cash = Wallet(coinbase, 10000 * USD)
asset = Wallet(coinbase, 0 * TTC)
portfolio = Portfolio(USD, [cash, asset])
feed = DataFeed([
p,
p.ewm(span=10).mean().rename("fast"),
p.ewm(span=50).mean().rename("medium"),
p.ewm(span=100).mean().rename("slow"),
p.log().diff().fillna(0).rename("lr")
])
reward_scheme = PBR(price=p)
action_scheme = BSH(cash=cash, asset=asset).attach(reward_scheme)
renderer_feed = DataFeed([
Stream.source(y, dtype="float").rename("price"),
Stream.sensor(action_scheme, lambda s: s.action,
dtype="float").rename("action")
])
environment = default.create(feed=feed,
portfolio=portfolio,
action_scheme=action_scheme,
reward_scheme=reward_scheme,
renderer_feed=renderer_feed,
renderer=PositionChangeChart(),
window_size=config["window_size"],
max_allowed_loss=0.6)
return environment
def create_env(config, train="train"):
cdd = CryptoDataDownload()
data = cdd.fetch("Bitstamp", "USD", "BTC", "1h")
if False:
data.close = data.close / 20 + range(len(data))
print("genenrating fake increase")
if train == "train":
data = data[0:int(len(data) / 2)] # training
print("using first half for training")
elif train == "eval":
data = data[int(len(data) / 2):] # validation
print("using second half for eval")
else:
print("using all data")
pclose = Stream.source(list(data.close), dtype="float").rename("USD-BTC")
pmin = Stream.source(list(data.low), dtype="float").rename("USD-BTClow")
pmax = Stream.source(list(data.high), dtype="float").rename("USD-BTChigh")
pmin = Stream.source(list(data.low), dtype="float").rename("USD-BTClow")
pmax = Stream.source(list(data.high), dtype="float").rename("USD-BTChigh")
pmin3 = pmin.rolling(window=3).min()
pmin10 = pmin.rolling(window=10).min()
pmin20 = pmin.rolling(window=20).min()
pmax3 = pmax.rolling(window=3).max()
pmax10 = pmax.rolling(window=10).max()
pmax20 = pmax.rolling(window=20).max()
eo = ExchangeOptions(commission=0.002) #
coinbase = Exchange("coinbase", service=execute_order, options=eo)(
pclose
)
cash = Wallet(coinbase, 100000 * USD)
asset = Wallet(coinbase, 0 * BTC)
portfolio = Portfolio(USD, [
cash,
asset
])
feed = DataFeed([
(pclose.log() - pmin3.log()).fillna(0).rename("relmin3"),
(pclose.log() - pmin10.log()).fillna(0).rename("relmin10"),
(pclose.log() - pmin20.log()).fillna(0).rename("relmin20"),
(pclose.log() - pmax3.log()).fillna(0).rename("relmax3"),
(pclose.log() - pmax10.log()).fillna(0).rename("relmax10"),
(pclose.log() - pmax20.log()).fillna(0).rename("relmax20"),
])
action_scheme = BSH(cash=cash, asset=asset)
renderer_feed = DataFeed([
Stream.source(list(data.close), dtype="float").rename("price"),
Stream.sensor(action_scheme, lambda s: s.action, dtype="float").rename("action") # only works for BSH
])
environment = default.create(
feed=feed,
portfolio=portfolio,
action_scheme=action_scheme,
reward_scheme="simple",
renderer_feed=renderer_feed,
renderer=PositionChangeChart(),
window_size=config["window_size"],
min_periods=20,
max_allowed_loss=0.6
)
return environment
def build_env(config):
worker_index = 1
if hasattr(config, 'worker_index'):
worker_index = config.worker_index
raw_data = pd.read_csv(btc_usd_file, sep=';')
raw_data['date'] = pd.to_datetime(raw_data['time'], unit='ms')
data = compute_features(raw_data)
features = []
for c in data.columns:
if c not in raw_data.columns:
s = Stream.source(list(data[c]),
dtype="float").rename(data[c].name)
features += [s]
comm = 0.00001
coinbase = Exchange("coinbase",
service=execute_order,
options=ExchangeOptions(commission=comm))(
Stream.source(list(data["close"]),
dtype="float").rename("USD-BTC"))
cash = Wallet(coinbase, 10000 * USD)
asset = Wallet(coinbase, 0 * BTC)
portfolio = Portfolio(USD, [cash, asset])
renderer_feed = DataFeed([
Stream.source(list(data["date"])).rename("date"),
Stream.source(list(data["open"]), dtype="float").rename("open"),
Stream.source(list(data["high"]), dtype="float").rename("high"),
Stream.source(list(data["low"]), dtype="float").rename("low"),
Stream.source(list(data["close"]), dtype="float").rename("close"),
Stream.source(list(data["volume"]), dtype="float").rename("volume")
])
# reward_scheme = rewards.SimpleProfit()
rsi = Stream.select(features, lambda x: x.name == "rsi")
reward_scheme = SparseReward(rsi=rsi, window_size=10)
action_scheme = BuySellHoldActionSchemes(cash, asset)
action_scheme.attach(reward_scheme)
plotly = PlotlyTradingChart(display=True, height=700, save_format="html")
class EpisodeStopper(Stopper):
def stop(self, env: 'TradingEnv') -> bool:
return env.clock.num_steps > 1000
open_position = Stream.sensor(asset,
lambda a: asset.total_balance.as_float() > 0)
# open_position = Stream.sensor(
# action_scheme, lambda action_scheme: action_scheme.has_asset
# )
features.append(open_position)
feed = DataFeed(features)
feed.compile()
env = default.create(
portfolio=portfolio,
action_scheme=action_scheme,
reward_scheme=reward_scheme,
feed=feed,
renderer_feed=renderer_feed,
renderer=plotly,
window_size=20,
max_allowed_loss=0.5,
stopper=EpisodeStopper(),
callback=(LoggingCallback('http://165.227.193.153:8050', plotly)
if worker_index == 1 else None))
import logging
import os
LOGGER = logging.getLogger(__name__)
logging.basicConfig(
level=logging.INFO,
format=
'%(asctime)s - %(name)s [%(threadName)s] - %(levelname)s - %(message)s',
)
LOGGER.info('env created logger')
LOGGER.info(f'env: {os.environ}')
print(f'env: {os.environ}')
print('env created')
return env
df.sort_values(by='date', ascending=True, inplace=True)
df.reset_index(drop=True, inplace=True)
# Format timestamps as you want them to appear on the chart buy/sell marks.
df['date'] = df['date'].dt.strftime('%Y-%m-%d %I:%M %p')
return df
df = load_csv('btc_usdt_m5_history.csv')
price = df['close']
position = 1.1
r = Stream.sensor(price, lambda p: p.value, dtype="float").diff()
position = Stream.sensor(position, lambda p: p, dtype="float")
reward = (position * r).fillna(0).rename("reward")
print(r)
print("Type: {}".format(type(r)))
print("--------------------------")
print(position)
print("Type: {}".format(type(position)))
print("--------------------------")
print(reward)
