def _build_backtest_algo_and_data(exchanges, bundle, env, environ,
bundle_timestamp, open_calendar, start, end,
namespace, choose_loader, sim_params,
algorithm_class_kwargs):
if exchanges:
# Removed the existing Poloniex fork to keep things simple
# We can add back the complexity if required.
# I don't think that we should have arbitrary price data bundles
# Instead, we should center this data around exchanges.
# We still need to support bundles for other misc data, but we
# can handle this later.
data = DataPortalExchangeBacktest(
exchange_names=[exchange_name for exchange_name in exchanges],
asset_finder=None,
trading_calendar=open_calendar,
first_trading_day=start,
last_available_session=end)
algorithm_class = partial(ExchangeTradingAlgorithmBacktest,
exchanges=exchanges)
elif bundle is not None:
# TODO This branch should probably be removed or fixed: it doesn't even
# build `algorithm_class`, so it will break when trying to instantiate
# it.
bundle_data = load(bundle, environ, bundle_timestamp)
env = _bundle_trading_environment(bundle_data, environ)
first_trading_day = \
bundle_data.equity_minute_bar_reader.first_trading_day
data = DataPortal(
env.asset_finder,
open_calendar,
first_trading_day=first_trading_day,
equity_minute_reader=bundle_data.equity_minute_bar_reader,
equity_daily_reader=bundle_data.equity_daily_bar_reader,
adjustment_reader=bundle_data.adjustment_reader)
return data, algorithm_class(namespace=namespace,
env=env,
get_pipeline_loader=choose_loader,
sim_params=sim_params,
**algorithm_class_kwargs)
def _run(handle_data,
initialize,
before_trading_start,
analyze,
algofile,
algotext,
defines,
data_frequency,
capital_base,
data,
bundle,
bundle_timestamp,
start,
end,
output,
print_algo,
local_namespace,
environ,
live,
exchange,
algo_namespace,
quote_currency,
live_graph,
analyze_live,
simulate_orders,
auth_aliases,
stats_output):
"""Run a backtest for the given algorithm.
This is shared between the cli and :func:`catalyst.run_algo`.
"""
# TODO: refactor for more granularity
if algotext is not None:
if local_namespace:
ip = get_ipython() # noqa
namespace = ip.user_ns
else:
namespace = {}
for assign in defines:
try:
name, value = assign.split('=', 2)
except ValueError:
raise ValueError(
'invalid define %r, should be of the form name=value' %
assign,
)
try:
# evaluate in the same namespace so names may refer to
# eachother
namespace[name] = eval(value, namespace)
except Exception as e:
raise ValueError(
'failed to execute definition for name %r: %s' % (name, e),
)
elif defines:
raise _RunAlgoError(
'cannot pass define without `algotext`',
"cannot pass '-D' / '--define' without '-t' / '--algotext'",
)
else:
namespace = {}
if algofile is not None:
algotext = algofile.read()
if print_algo:
if PYGMENTS:
highlight(
algotext,
PythonLexer(),
TerminalFormatter(),
outfile=sys.stdout,
)
else:
click.echo(algotext)
log.info('Catalyst version {}'.format(catalyst.__version__))
if not DISABLE_ALPHA_WARNING:
log.warn(ALPHA_WARNING_MESSAGE)
# sleep(3)
if live:
if simulate_orders:
mode = 'paper-trading'
else:
mode = 'live-trading'
else:
mode = 'backtest'
log.info('running algo in {mode} mode'.format(mode=mode))
exchange_name = exchange
if exchange_name is None:
raise ValueError('Please specify at least one exchange.')
if isinstance(auth_aliases, string_types):
aliases = auth_aliases.split(',')
if len(aliases) < 2 or len(aliases) % 2 != 0:
raise ValueError(
'the `auth_aliases` parameter must contain an even list '
'of comma-delimited values. For example, '
'"binance,auth2" or "binance,auth2,bittrex,auth2".'
)
auth_aliases = dict(zip(aliases[::2], aliases[1::2]))
exchange_list = [x.strip().lower() for x in exchange.split(',')]
exchanges = dict()
for name in exchange_list:
if auth_aliases is not None and name in auth_aliases:
auth_alias = auth_aliases[name]
else:
auth_alias = None
exchanges[name] = get_exchange(
exchange_name=name,
quote_currency=quote_currency,
must_authenticate=(live and not simulate_orders),
skip_init=True,
auth_alias=auth_alias,
)
open_calendar = get_calendar('OPEN')
env = TradingEnvironment(
load=partial(
load_crypto_market_data,
environ=environ,
start_dt=start,
end_dt=end
),
environ=environ,
exchange_tz='UTC',
asset_db_path=None # We don't need an asset db, we have exchanges
)
env.asset_finder = ExchangeAssetFinder(exchanges=exchanges)
def choose_loader(column):
bound_cols = TradingPairPricing.columns
if column in bound_cols:
return ExchangePricingLoader(data_frequency)
raise ValueError(
"No PipelineLoader registered for column %s." % column
)
if live:
# TODO: fix the start data.
# is_start checks if a start date was specified by user
# needed for live clock
is_start = True
if start is None:
start = pd.Timestamp.utcnow()
is_start = False
elif start:
assert pd.Timestamp.utcnow() <= start, \
"specified start date is in the past."
elif start and end:
assert start < end, "start date is later than end date."
# TODO: fix the end data.
# is_end checks if an end date was specified by user
# needed for live clock
is_end = True
if end is None:
end = start + timedelta(hours=8760)
is_end = False
data = DataPortalExchangeLive(
exchanges=exchanges,
asset_finder=env.asset_finder,
trading_calendar=open_calendar,
first_trading_day=pd.to_datetime('today', utc=True)
)
sim_params = create_simulation_parameters(
start=start,
end=end,
capital_base=capital_base,
emission_rate='minute',
data_frequency='minute'
)
# TODO: use the constructor instead
sim_params._arena = 'live'
algorithm_class = partial(
ExchangeTradingAlgorithmLive,
exchanges=exchanges,
algo_namespace=algo_namespace,
live_graph=live_graph,
simulate_orders=simulate_orders,
stats_output=stats_output,
analyze_live=analyze_live,
start=start,
is_start=is_start,
end=end,
is_end=is_end,
)
elif exchanges:
# Removed the existing Poloniex fork to keep things simple
# We can add back the complexity if required.
# I don't think that we should have arbitrary price data bundles
# Instead, we should center this data around exchanges.
# We still need to support bundles for other misc data, but we
# can handle this later.
if (start and start != pd.tslib.normalize_date(start)) or \
(end and end != pd.tslib.normalize_date(end)):
# todo: add to Sim_Params the option to
# start & end at specific times
log.warn(
"Catalyst currently starts and ends on the start and "
"end of the dates specified, respectively. We hope to "
"Modify this and support specific times in a future release."
)
data = DataPortalExchangeBacktest(
exchange_names=[ex_name for ex_name in exchanges],
asset_finder=None,
trading_calendar=open_calendar,
first_trading_day=start,
last_available_session=end
)
sim_params = create_simulation_parameters(
start=start,
end=end,
capital_base=capital_base,
data_frequency=data_frequency,
emission_rate=data_frequency,
)
algorithm_class = partial(
ExchangeTradingAlgorithmBacktest,
exchanges=exchanges
)
elif bundle is not None:
bundle_data = load(
bundle,
environ,
bundle_timestamp,
)
prefix, connstr = re.split(
r'sqlite:///',
str(bundle_data.asset_finder.engine.url),
maxsplit=1,
)
if prefix:
raise ValueError(
"invalid url %r, must begin with 'sqlite:///'" %
str(bundle_data.asset_finder.engine.url),
)
env = TradingEnvironment(asset_db_path=connstr, environ=environ)
first_trading_day = \
bundle_data.equity_minute_bar_reader.first_trading_day
data = DataPortal(
env.asset_finder, open_calendar,
first_trading_day=first_trading_day,
equity_minute_reader=bundle_data.equity_minute_bar_reader,
equity_daily_reader=bundle_data.equity_daily_bar_reader,
adjustment_reader=bundle_data.adjustment_reader,
)
perf = algorithm_class(
namespace=namespace,
env=env,
get_pipeline_loader=choose_loader,
sim_params=sim_params,
**{
'initialize': initialize,
'handle_data': handle_data,
'before_trading_start': before_trading_start,
'analyze': analyze,
} if algotext is None else {
'algo_filename': getattr(algofile, 'name', '<algorithm>'),
'script': algotext,
}
).run(
data,
overwrite_sim_params=False,
)
if output == '-':
click.echo(str(perf))
elif output != os.devnull: # make the catalyst magic not write any data
perf.to_pickle(output)
return perf
def _run(handle_data, initialize, before_trading_start, analyze, algofile,
algotext, defines, data_frequency, capital_base, data, bundle,
bundle_timestamp, start, end, output, print_algo, local_namespace,
environ, live, exchange, algo_namespace, base_currency, live_graph,
simulate_orders, stats_output):
"""Run a backtest for the given algorithm.
This is shared between the cli and :func:`catalyst.run_algo`.
"""
if algotext is not None:
if local_namespace:
ip = get_ipython() # noqa
namespace = ip.user_ns
else:
namespace = {}
for assign in defines:
try:
name, value = assign.split('=', 2)
except ValueError:
raise ValueError(
'invalid define %r, should be of the form name=value' %
assign, )
try:
# evaluate in the same namespace so names may refer to
# eachother
namespace[name] = eval(value, namespace)
except Exception as e:
raise ValueError(
'failed to execute definition for name %r: %s' %
(name, e), )
elif defines:
raise _RunAlgoError(
'cannot pass define without `algotext`',
"cannot pass '-D' / '--define' without '-t' / '--algotext'",
)
else:
namespace = {}
if algofile is not None:
algotext = algofile.read()
if print_algo:
if PYGMENTS:
highlight(
algotext,
PythonLexer(),
TerminalFormatter(),
outfile=sys.stdout,
)
else:
click.echo(algotext)
mode = 'paper-trading' if simulate_orders else 'live-trading' \
if live else 'backtest'
log.info('running algo in {mode} mode'.format(mode=mode))
exchange_name = exchange
if exchange_name is None:
raise ValueError('Please specify at least one exchange.')
exchange_list = [x.strip().lower() for x in exchange.split(',')]
exchanges = dict()
for exchange_name in exchange_list:
exchanges[exchange_name] = get_exchange(
exchange_name=exchange_name,
base_currency=base_currency,
must_authenticate=(live and not simulate_orders),
)
open_calendar = get_calendar('OPEN')
env = TradingEnvironment(
load=partial(load_crypto_market_data,
environ=environ,
start_dt=start,
end_dt=end),
environ=environ,
exchange_tz='UTC',
asset_db_path=None # We don't need an asset db, we have exchanges
)
env.asset_finder = AssetFinderExchange()
choose_loader = None # TODO: use the DataPortal in the algo class for this
if live:
start = pd.Timestamp.utcnow()
# TODO: fix the end data.
end = start + timedelta(hours=8760)
data = DataPortalExchangeLive(exchanges=exchanges,
asset_finder=env.asset_finder,
trading_calendar=open_calendar,
first_trading_day=pd.to_datetime(
'today', utc=True))
def fetch_capital_base(exchange, attempt_index=0):
"""
Fetch the base currency amount required to bootstrap
the algorithm against the exchange.
The algorithm cannot continue without this value.
:param exchange: the targeted exchange
:param attempt_index:
:return capital_base: the amount of base currency available for
trading
"""
try:
log.debug('retrieving capital base in {} to bootstrap '
'exchange {}'.format(base_currency, exchange_name))
balances = exchange.get_balances()
except ExchangeRequestError as e:
if attempt_index < 20:
log.warn('could not retrieve balances on {}: {}'.format(
exchange.name, e))
sleep(5)
return fetch_capital_base(exchange, attempt_index + 1)
else:
raise ExchangeRequestErrorTooManyAttempts(
attempts=attempt_index, error=e)
if base_currency in balances:
base_currency_available = balances[base_currency]['free']
log.info(
'base currency available in the account: {} {}'.format(
base_currency_available, base_currency))
return base_currency_available
else:
raise BaseCurrencyNotFoundError(base_currency=base_currency,
exchange=exchange_name)
if not simulate_orders:
for exchange_name in exchanges:
exchange = exchanges[exchange_name]
balance = fetch_capital_base(exchange)
if balance < capital_base:
raise NotEnoughCapitalError(
exchange=exchange_name,
base_currency=base_currency,
balance=balance,
capital_base=capital_base,
)
sim_params = create_simulation_parameters(start=start,
end=end,
capital_base=capital_base,
emission_rate='minute',
data_frequency='minute')
# TODO: use the constructor instead
sim_params._arena = 'live'
algorithm_class = partial(
ExchangeTradingAlgorithmLive,
exchanges=exchanges,
algo_namespace=algo_namespace,
live_graph=live_graph,
simulate_orders=simulate_orders,
stats_output=stats_output,
)
elif exchanges:
# Removed the existing Poloniex fork to keep things simple
# We can add back the complexity if required.
# I don't think that we should have arbitrary price data bundles
# Instead, we should center this data around exchanges.
# We still need to support bundles for other misc data, but we
# can handle this later.
data = DataPortalExchangeBacktest(
exchange_names=[exchange_name for exchange_name in exchanges],
asset_finder=None,
trading_calendar=open_calendar,
first_trading_day=start,
last_available_session=end)
sim_params = create_simulation_parameters(
start=start,
end=end,
capital_base=capital_base,
data_frequency=data_frequency,
emission_rate=data_frequency,
)
algorithm_class = partial(ExchangeTradingAlgorithmBacktest,
exchanges=exchanges)
elif bundle is not None:
bundle_data = load(
bundle,
environ,
bundle_timestamp,
)
prefix, connstr = re.split(
r'sqlite:///',
str(bundle_data.asset_finder.engine.url),
maxsplit=1,
)
if prefix:
raise ValueError(
"invalid url %r, must begin with 'sqlite:///'" %
str(bundle_data.asset_finder.engine.url), )
env = TradingEnvironment(asset_db_path=connstr, environ=environ)
first_trading_day = \
bundle_data.equity_minute_bar_reader.first_trading_day
data = DataPortal(
env.asset_finder,
open_calendar,
first_trading_day=first_trading_day,
equity_minute_reader=bundle_data.equity_minute_bar_reader,
equity_daily_reader=bundle_data.equity_daily_bar_reader,
adjustment_reader=bundle_data.adjustment_reader,
)
perf = algorithm_class(
namespace=namespace,
env=env,
get_pipeline_loader=choose_loader,
sim_params=sim_params,
**{
'initialize': initialize,
'handle_data': handle_data,
'before_trading_start': before_trading_start,
'analyze': analyze,
} if algotext is None else {
'algo_filename': getattr(algofile, 'name', '<algorithm>'),
'script': algotext,
}).run(
data,
overwrite_sim_params=False,
)
if output == '-':
click.echo(str(perf))
elif output != os.devnull: # make the catalyst magic not write any data
perf.to_pickle(output)
return perf
def _run(handle_data,
initialize,
before_trading_start,
analyze,
algofile,
algotext,
defines,
data_frequency,
capital_base,
data,
bundle,
bundle_timestamp,
start,
end,
output,
print_algo,
local_namespace,
environ,
live,
exchange,
algo_namespace,
base_currency,
live_graph,
analyze_live,
simulate_orders,
stats_output):
"""Run a backtest for the given algorithm.
This is shared between the cli and :func:`catalyst.run_algo`.
"""
if algotext is not None:
if local_namespace:
ip = get_ipython() # noqa
namespace = ip.user_ns
else:
namespace = {}
for assign in defines:
try:
name, value = assign.split('=', 2)
except ValueError:
raise ValueError(
'invalid define %r, should be of the form name=value' %
assign,
)
try:
# evaluate in the same namespace so names may refer to
# eachother
namespace[name] = eval(value, namespace)
except Exception as e:
raise ValueError(
'failed to execute definition for name %r: %s' % (name, e),
)
elif defines:
raise _RunAlgoError(
'cannot pass define without `algotext`',
"cannot pass '-D' / '--define' without '-t' / '--algotext'",
)
else:
namespace = {}
if algofile is not None:
algotext = algofile.read()
if print_algo:
if PYGMENTS:
highlight(
algotext,
PythonLexer(),
TerminalFormatter(),
outfile=sys.stdout,
)
else:
click.echo(algotext)
log.warn(
'Catalyst is currently in ALPHA. It is going through rapid '
'development and it is subject to errors. Please use carefully. '
'We encourage you to report any issue on GitHub: '
'https://github.com/enigmampc/catalyst/issues'
)
sleep(3)
if live:
if simulate_orders:
mode = 'paper-trading'
else:
mode = 'live-trading'
else:
mode = 'backtest'
log.info('running algo in {mode} mode'.format(mode=mode))
exchange_name = exchange
if exchange_name is None:
raise ValueError('Please specify at least one exchange.')
exchange_list = [x.strip().lower() for x in exchange.split(',')]
exchanges = dict()
for exchange_name in exchange_list:
exchanges[exchange_name] = get_exchange(
exchange_name=exchange_name,
base_currency=base_currency,
must_authenticate=(live and not simulate_orders),
skip_init=True,
)
open_calendar = get_calendar('OPEN')
env = TradingEnvironment(
load=partial(
load_crypto_market_data,
environ=environ,
start_dt=start,
end_dt=end
),
environ=environ,
exchange_tz='UTC',
asset_db_path=None # We don't need an asset db, we have exchanges
)
env.asset_finder = ExchangeAssetFinder(exchanges=exchanges)
def choose_loader(column):
bound_cols = TradingPairPricing.columns
if column in bound_cols:
return ExchangePricingLoader(data_frequency)
raise ValueError(
"No PipelineLoader registered for column %s." % column
)
if live:
start = pd.Timestamp.utcnow()
# TODO: fix the end data.
end = start + timedelta(hours=8760)
data = DataPortalExchangeLive(
exchanges=exchanges,
asset_finder=env.asset_finder,
trading_calendar=open_calendar,
first_trading_day=pd.to_datetime('today', utc=True)
)
sim_params = create_simulation_parameters(
start=start,
end=end,
capital_base=capital_base,
emission_rate='minute',
data_frequency='minute'
)
# TODO: use the constructor instead
sim_params._arena = 'live'
algorithm_class = partial(
ExchangeTradingAlgorithmLive,
exchanges=exchanges,
algo_namespace=algo_namespace,
live_graph=live_graph,
simulate_orders=simulate_orders,
stats_output=stats_output,
analyze_live=analyze_live,
)
elif exchanges:
# Removed the existing Poloniex fork to keep things simple
# We can add back the complexity if required.
# I don't think that we should have arbitrary price data bundles
# Instead, we should center this data around exchanges.
# We still need to support bundles for other misc data, but we
# can handle this later.
data = DataPortalExchangeBacktest(
exchange_names=[exchange_name for exchange_name in exchanges],
asset_finder=None,
trading_calendar=open_calendar,
first_trading_day=start,
last_available_session=end
)
sim_params = create_simulation_parameters(
start=start,
end=end,
capital_base=capital_base,
data_frequency=data_frequency,
emission_rate=data_frequency,
)
algorithm_class = partial(
ExchangeTradingAlgorithmBacktest,
exchanges=exchanges
)
elif bundle is not None:
bundle_data = load(
bundle,
environ,
bundle_timestamp,
)
prefix, connstr = re.split(
r'sqlite:///',
str(bundle_data.asset_finder.engine.url),
maxsplit=1,
)
if prefix:
raise ValueError(
"invalid url %r, must begin with 'sqlite:///'" %
str(bundle_data.asset_finder.engine.url),
)
env = TradingEnvironment(asset_db_path=connstr, environ=environ)
first_trading_day = \
bundle_data.equity_minute_bar_reader.first_trading_day
data = DataPortal(
env.asset_finder, open_calendar,
first_trading_day=first_trading_day,
equity_minute_reader=bundle_data.equity_minute_bar_reader,
equity_daily_reader=bundle_data.equity_daily_bar_reader,
adjustment_reader=bundle_data.adjustment_reader,
)
perf = algorithm_class(
namespace=namespace,
env=env,
get_pipeline_loader=choose_loader,
sim_params=sim_params,
**{
'initialize': initialize,
'handle_data': handle_data,
'before_trading_start': before_trading_start,
'analyze': analyze,
} if algotext is None else {
'algo_filename': getattr(algofile, 'name', '<algorithm>'),
'script': algotext,
}
).run(
data,
overwrite_sim_params=False,
)
if output == '-':
click.echo(str(perf))
elif output != os.devnull: # make the catalyst magic not write any data
perf.to_pickle(output)
return perf
def test_bundle(self):
url_map = merge(
{
format_wiki_url(
self.api_key,
symbol,
self.start_date,
self.end_date,
): test_resource_path('quandl_samples', symbol + '.csv.gz')
for symbol in self.symbols
},
{
format_metadata_url(self.api_key, n): test_resource_path(
'quandl_samples',
'metadata-%d.csv.gz' % n,
)
for n in (1, 2)
},
)
catalyst_root = self.enter_instance_context(tmp_dir()).path
environ = {
'ZIPLINE_ROOT': catalyst_root,
'QUANDL_API_KEY': self.api_key,
}
with patch_read_csv(url_map, strict=True):
ingest('quandl', environ=environ)
bundle = load('quandl', environ=environ)
sids = 0, 1, 2, 3
assert_equal(set(bundle.asset_finder.sids), set(sids))
for equity in bundle.asset_finder.retrieve_all(sids):
assert_equal(equity.start_date, self.asset_start, msg=equity)
assert_equal(equity.end_date, self.asset_end, msg=equity)
sessions = self.calendar.all_sessions
actual = bundle.equity_daily_bar_reader.load_raw_arrays(
self.columns,
sessions[sessions.get_loc(self.asset_start, 'bfill')],
sessions[sessions.get_loc(self.asset_end, 'ffill')],
sids,
)
expected_pricing, expected_adjustments = self._expected_data(
bundle.asset_finder, )
assert_equal(actual, expected_pricing, array_decimal=2)
adjustments_for_cols = bundle.adjustment_reader.load_adjustments(
self.columns,
sessions,
pd.Index(sids),
)
for column, adjustments, expected in zip(self.columns,
adjustments_for_cols,
expected_adjustments):
assert_equal(
adjustments,
expected,
msg=column,
)
def test_bundle(self):
url_map = merge(
{
format_wiki_url(
self.api_key,
symbol,
self.start_date,
self.end_date,
): test_resource_path('quandl_samples', symbol + '.csv.gz')
for symbol in self.symbols
},
{
format_metadata_url(self.api_key, n): test_resource_path(
'quandl_samples',
'metadata-%d.csv.gz' % n,
)
for n in (1, 2)
},
)
catalyst_root = self.enter_instance_context(tmp_dir()).path
environ = {
'ZIPLINE_ROOT': catalyst_root,
'QUANDL_API_KEY': self.api_key,
}
with patch_read_csv(url_map, strict=True):
ingest('quandl', environ=environ)
bundle = load('quandl', environ=environ)
sids = 0, 1, 2, 3
assert_equal(set(bundle.asset_finder.sids), set(sids))
for equity in bundle.asset_finder.retrieve_all(sids):
assert_equal(equity.start_date, self.asset_start, msg=equity)
assert_equal(equity.end_date, self.asset_end, msg=equity)
sessions = self.calendar.all_sessions
actual = bundle.equity_daily_bar_reader.load_raw_arrays(
self.columns,
sessions[sessions.get_loc(self.asset_start, 'bfill')],
sessions[sessions.get_loc(self.asset_end, 'ffill')],
sids,
)
expected_pricing, expected_adjustments = self._expected_data(
bundle.asset_finder,
)
assert_equal(actual, expected_pricing, array_decimal=2)
adjustments_for_cols = bundle.adjustment_reader.load_adjustments(
self.columns,
sessions,
pd.Index(sids),
)
for column, adjustments, expected in zip(self.columns,
adjustments_for_cols,
expected_adjustments):
assert_equal(
adjustments,
expected,
msg=column,
)