def _test_pipeline_output_after_initialize(self):
"""
Assert that calling pipeline_output after initialize raises correctly.
"""
def initialize(context):
attach_pipeline(Pipeline(), 'test')
pipeline_output('test')
raise AssertionError("Shouldn't make it past pipeline_output()")
def handle_data(context, data):
raise AssertionError("Shouldn't make it past initialize!")
def before_trading_start(context, data):
raise AssertionError("Shouldn't make it past initialize!")
algo = TradingAlgorithm(
initialize=initialize,
handle_data=handle_data,
before_trading_start=before_trading_start,
data_frequency='daily',
get_pipeline_loader=lambda column: self.pipeline_loader,
start=self.first_asset_start - self.trading_day,
end=self.last_asset_end + self.trading_day,
env=self.env,
)
with self.assertRaises(PipelineOutputDuringInitialize):
algo.run(self.data_portal)
def _test_get_output_nonexistent_pipeline(self):
"""
Assert that calling add_pipeline after initialize raises appropriately.
"""
def initialize(context):
attach_pipeline(Pipeline(), 'test')
def handle_data(context, data):
raise AssertionError("Shouldn't make it past before_trading_start")
def before_trading_start(context, data):
pipeline_output('not_test')
raise AssertionError("Shouldn't make it past pipeline_output!")
algo = TradingAlgorithm(
initialize=initialize,
handle_data=handle_data,
before_trading_start=before_trading_start,
data_frequency='daily',
get_pipeline_loader=lambda column: self.pipeline_loader,
start=self.first_asset_start - self.trading_day,
end=self.last_asset_end + self.trading_day,
env=self.env,
)
with self.assertRaises(NoSuchPipeline):
algo.run(self.data_portal)
def test_get_output_nonexistent_pipeline(self):
"""
Assert that calling add_pipeline after initialize raises appropriately.
"""
def initialize(context):
attach_pipeline(Pipeline(), 'test')
def handle_data(context, data):
raise AssertionError("Shouldn't make it past before_trading_start")
def before_trading_start(context, data):
pipeline_output('not_test')
raise AssertionError("Shouldn't make it past pipeline_output!")
algo = TradingAlgorithm(
initialize=initialize,
handle_data=handle_data,
before_trading_start=before_trading_start,
data_frequency='daily',
get_pipeline_loader=lambda column: self.pipeline_loader,
start=self.first_asset_start - self.trading_day,
end=self.last_asset_end + self.trading_day,
env=self.env,
)
with self.assertRaises(NoSuchPipeline):
algo.run(self.data_portal)
def test_pipeline_output_after_initialize(self):
"""
Assert that calling pipeline_output after initialize raises correctly.
"""
def initialize(context):
attach_pipeline(Pipeline(), 'test')
pipeline_output('test')
raise AssertionError("Shouldn't make it past pipeline_output()")
def handle_data(context, data):
raise AssertionError("Shouldn't make it past initialize!")
def before_trading_start(context, data):
raise AssertionError("Shouldn't make it past initialize!")
algo = TradingAlgorithm(
initialize=initialize,
handle_data=handle_data,
before_trading_start=before_trading_start,
data_frequency='daily',
get_pipeline_loader=lambda column: self.pipeline_loader,
start=self.first_asset_start - self.trading_day,
end=self.last_asset_end + self.trading_day,
env=self.env,
)
with self.assertRaises(PipelineOutputDuringInitialize):
algo.run(self.data_portal)
def test_assets_appear_on_correct_days(self, test_name, chunks):
"""
Assert that assets appear at correct times during a backtest, with
correctly-adjusted close price values.
"""
if chunks == 'all_but_one_day':
chunks = (
self.dates.get_loc(self.last_asset_end) -
self.dates.get_loc(self.first_asset_start)
) - 1
elif chunks == 'custom_iter':
chunks = []
st = np.random.RandomState(12345)
remaining = (
self.dates.get_loc(self.last_asset_end) -
self.dates.get_loc(self.first_asset_start)
)
while remaining > 0:
chunk = st.randint(3)
chunks.append(chunk)
remaining -= chunk
def initialize(context):
p = attach_pipeline(Pipeline(), 'test', chunks=chunks)
p.add(USEquityPricing.close.latest, 'close')
def handle_data(context, data):
results = pipeline_output('test')
date = get_datetime().normalize()
for asset in self.assets:
# Assets should appear iff they exist today and yesterday.
exists_today = self.exists(date, asset)
existed_yesterday = self.exists(date - self.trading_day, asset)
if exists_today and existed_yesterday:
latest = results.loc[asset, 'close']
self.assertEqual(latest, self.expected_close(date, asset))
else:
self.assertNotIn(asset, results.index)
before_trading_start = handle_data
algo = TradingAlgorithm(
initialize=initialize,
handle_data=handle_data,
before_trading_start=before_trading_start,
data_frequency='daily',
get_pipeline_loader=lambda column: self.pipeline_loader,
start=self.first_asset_start,
end=self.last_asset_end,
env=self.env,
)
# Run for a week in the middle of our data.
algo.run(self.data_portal)
def _test_assets_appear_on_correct_days(self, test_name, chunks):
"""
Assert that assets appear at correct times during a backtest, with
correctly-adjusted close price values.
"""
if chunks == 'all_but_one_day':
chunks = (self.dates.get_loc(self.last_asset_end) -
self.dates.get_loc(self.first_asset_start)) - 1
elif chunks == 'custom_iter':
chunks = []
st = np.random.RandomState(12345)
remaining = (self.dates.get_loc(self.last_asset_end) -
self.dates.get_loc(self.first_asset_start))
while remaining > 0:
chunk = st.randint(3)
chunks.append(chunk)
remaining -= chunk
def initialize(context):
p = attach_pipeline(Pipeline(), 'test', chunks=chunks)
p.add(USEquityPricing.close.latest, 'close')
def handle_data(context, data):
results = pipeline_output('test')
date = get_datetime().normalize()
for asset in self.assets:
# Assets should appear iff they exist today and yesterday.
exists_today = self.exists(date, asset)
existed_yesterday = self.exists(date - self.trading_day, asset)
if exists_today and existed_yesterday:
latest = results.loc[asset, 'close']
self.assertEqual(latest, self.expected_close(date, asset))
else:
self.assertNotIn(asset, results.index)
before_trading_start = handle_data
algo = TradingAlgorithm(
initialize=initialize,
handle_data=handle_data,
before_trading_start=before_trading_start,
data_frequency='daily',
get_pipeline_loader=lambda column: self.pipeline_loader,
start=self.first_asset_start,
end=self.last_asset_end,
env=self.env,
)
# Run for a week in the middle of our data.
algo.run(self.data_portal)
def test_pipeline_beyond_daily_bars(self):
"""
Ensure that we can run an algo with pipeline beyond the max date
of the daily bars.
"""
# For ensuring we call before_trading_start.
count = [0]
current_day = self.trading_calendar.next_session_label(
self.pipeline_loader.raw_price_loader.last_available_dt,
)
def initialize(context):
pipeline = attach_pipeline(Pipeline(), 'test')
vwap = VWAP(window_length=10)
pipeline.add(vwap, 'vwap')
# Nothing should have prices less than 0.
pipeline.set_screen(vwap < 0)
def handle_data(context, data):
pass
def before_trading_start(context, data):
context.results = pipeline_output('test')
self.assertTrue(context.results.empty)
count[0] += 1
algo = TradingAlgorithm(
initialize=initialize,
handle_data=handle_data,
before_trading_start=before_trading_start,
data_frequency='daily',
get_pipeline_loader=lambda column: self.pipeline_loader,
start=self.dates[0],
end=current_day,
env=self.env,
)
algo.run(
FakeDataPortal(self.env),
overwrite_sim_params=False,
)
self.assertTrue(count[0] > 0)
def test_pipeline_beyond_daily_bars(self):
"""
Ensure that we can run an algo with pipeline beyond the max date
of the daily bars.
"""
# For ensuring we call before_trading_start.
count = [0]
current_day = self.trading_calendar.next_session_label(
self.pipeline_loader.raw_price_loader.last_available_dt, )
def initialize(context):
pipeline = attach_pipeline(Pipeline(), 'test')
vwap = VWAP(window_length=10)
pipeline.add(vwap, 'vwap')
# Nothing should have prices less than 0.
pipeline.set_screen(vwap < 0)
def handle_data(context, data):
pass
def before_trading_start(context, data):
context.results = pipeline_output('test')
self.assertTrue(context.results.empty)
count[0] += 1
algo = TradingAlgorithm(
initialize=initialize,
handle_data=handle_data,
before_trading_start=before_trading_start,
data_frequency='daily',
get_pipeline_loader=lambda column: self.pipeline_loader,
start=self.dates[0],
end=current_day,
env=self.env,
)
algo.run(
FakeDataPortal(self.env),
overwrite_sim_params=False,
)
self.assertTrue(count[0] > 0)
def _create_generator(self, sim_params):
if self.perf_tracker is None:
self.perf_tracker = get_algo_object(algo_name=self.algo_namespace,
key='perf_tracker')
# Call the simulation trading algorithm for side-effects:
# it creates the perf tracker
TradingAlgorithm._create_generator(self, sim_params)
self.trading_client = ExchangeAlgorithmExecutor(
self,
sim_params,
self.data_portal,
self._create_clock(),
self._create_benchmark_source(),
self.restrictions,
universe_func=self._calculate_universe)
return self.trading_client.transform()
def test_empty_pipeline(self):
# For ensuring we call before_trading_start.
count = [0]
def initialize(context):
pipeline = attach_pipeline(Pipeline(), 'test')
vwap = VWAP(window_length=10)
pipeline.add(vwap, 'vwap')
# Nothing should have prices less than 0.
pipeline.set_screen(vwap < 0)
def handle_data(context, data):
pass
def before_trading_start(context, data):
context.results = pipeline_output('test')
self.assertTrue(context.results.empty)
count[0] += 1
algo = TradingAlgorithm(
initialize=initialize,
handle_data=handle_data,
before_trading_start=before_trading_start,
data_frequency='daily',
get_pipeline_loader=lambda column: self.pipeline_loader,
start=self.dates[0],
end=self.dates[-1],
env=self.env,
)
algo.run(
FakeDataPortal(self.env),
overwrite_sim_params=False,
)
self.assertTrue(count[0] > 0)
def test_empty_pipeline(self):
# For ensuring we call before_trading_start.
count = [0]
def initialize(context):
pipeline = attach_pipeline(Pipeline(), 'test')
vwap = VWAP(window_length=10)
pipeline.add(vwap, 'vwap')
# Nothing should have prices less than 0.
pipeline.set_screen(vwap < 0)
def handle_data(context, data):
pass
def before_trading_start(context, data):
context.results = pipeline_output('test')
self.assertTrue(context.results.empty)
count[0] += 1
algo = TradingAlgorithm(
initialize=initialize,
handle_data=handle_data,
before_trading_start=before_trading_start,
data_frequency='daily',
get_pipeline_loader=lambda column: self.pipeline_loader,
start=self.dates[0],
end=self.dates[-1],
env=self.env,
)
algo.run(
FakeDataPortal(self.env),
overwrite_sim_params=False,
)
self.assertTrue(count[0] > 0)
def _test_attach_pipeline_after_initialize(self):
"""
Assert that calling attach_pipeline after initialize raises correctly.
"""
def initialize(context):
pass
def late_attach(context, data):
attach_pipeline(Pipeline(), 'test')
raise AssertionError("Shouldn't make it past attach_pipeline!")
algo = TradingAlgorithm(
initialize=initialize,
handle_data=late_attach,
data_frequency='daily',
get_pipeline_loader=lambda column: self.pipeline_loader,
start=self.first_asset_start - self.trading_day,
end=self.last_asset_end + self.trading_day,
env=self.env,
)
with self.assertRaises(AttachPipelineAfterInitialize):
algo.run(self.data_portal)
def barf(context, data):
raise AssertionError("Shouldn't make it past before_trading_start")
algo = TradingAlgorithm(
initialize=initialize,
before_trading_start=late_attach,
handle_data=barf,
data_frequency='daily',
get_pipeline_loader=lambda column: self.pipeline_loader,
start=self.first_asset_start - self.trading_day,
end=self.last_asset_end + self.trading_day,
env=self.env,
)
with self.assertRaises(AttachPipelineAfterInitialize):
algo.run(self.data_portal)
def test_attach_pipeline_after_initialize(self):
"""
Assert that calling attach_pipeline after initialize raises correctly.
"""
def initialize(context):
pass
def late_attach(context, data):
attach_pipeline(Pipeline(), 'test')
raise AssertionError("Shouldn't make it past attach_pipeline!")
algo = TradingAlgorithm(
initialize=initialize,
handle_data=late_attach,
data_frequency='daily',
get_pipeline_loader=lambda column: self.pipeline_loader,
start=self.first_asset_start - self.trading_day,
end=self.last_asset_end + self.trading_day,
env=self.env,
)
with self.assertRaises(AttachPipelineAfterInitialize):
algo.run(self.data_portal)
def barf(context, data):
raise AssertionError("Shouldn't make it past before_trading_start")
algo = TradingAlgorithm(
initialize=initialize,
before_trading_start=late_attach,
handle_data=barf,
data_frequency='daily',
get_pipeline_loader=lambda column: self.pipeline_loader,
start=self.first_asset_start - self.trading_day,
end=self.last_asset_end + self.trading_day,
env=self.env,
)
with self.assertRaises(AttachPipelineAfterInitialize):
algo.run(self.data_portal)
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):
"""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)
if bundle is not None:
bundles = bundle.split(',')
def get_trading_env_and_data(bundles):
env = data = None
b = 'poloniex'
if len(bundles) == 0:
return env, data
elif len(bundles) == 1:
b = bundles[0]
bundle_data = load(
b,
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), )
open_calendar = get_calendar('OPEN')
env = TradingEnvironment(
load=partial(load_crypto_market_data, environ=environ),
bm_symbol='USDT_BTC',
trading_calendar=open_calendar,
asset_db_path=connstr,
environ=environ,
)
first_trading_day = bundle_data.minute_bar_reader.first_trading_day
data = DataPortal(
env.asset_finder,
open_calendar,
first_trading_day=first_trading_day,
minute_reader=bundle_data.minute_bar_reader,
five_minute_reader=bundle_data.five_minute_bar_reader,
daily_reader=bundle_data.daily_bar_reader,
adjustment_reader=bundle_data.adjustment_reader,
)
return env, data
def get_loader_for_bundle(b):
bundle_data = load(
b,
environ,
bundle_timestamp,
)
if b == 'poloniex':
return CryptoPricingLoader(
bundle_data,
data_frequency,
CryptoPricing,
)
elif b == 'quandl':
return USEquityPricingLoader(
bundle_data,
data_frequency,
USEquityPricing,
)
raise ValueError("No PipelineLoader registered for bundle %s." % b)
loaders = [get_loader_for_bundle(b) for b in bundles]
env, data = get_trading_env_and_data(bundles)
def choose_loader(column):
for loader in loaders:
if column in loader.columns:
return loader
raise ValueError("No PipelineLoader registered for column %s." %
column)
else:
env = TradingEnvironment(environ=environ)
choose_loader = None
perf = TradingAlgorithm(
namespace=namespace,
env=env,
get_pipeline_loader=choose_loader,
sim_params=create_simulation_parameters(
start=start,
end=end,
capital_base=capital_base,
data_frequency=data_frequency,
emission_rate=data_frequency,
),
**{
'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_handle_adjustment(self, set_screen):
AAPL, MSFT, BRK_A = assets = self.assets
window_lengths = [1, 2, 5, 10]
vwaps = self.compute_expected_vwaps(window_lengths)
def vwap_key(length):
return "vwap_%d" % length
def initialize(context):
pipeline = Pipeline()
context.vwaps = []
for length in vwaps:
name = vwap_key(length)
factor = VWAP(window_length=length)
context.vwaps.append(factor)
pipeline.add(factor, name=name)
filter_ = (USEquityPricing.close.latest > 300)
pipeline.add(filter_, 'filter')
if set_screen:
pipeline.set_screen(filter_)
attach_pipeline(pipeline, 'test')
def handle_data(context, data):
today = normalize_date(get_datetime())
results = pipeline_output('test')
expect_over_300 = {
AAPL: today < self.AAPL_split_date,
MSFT: False,
BRK_A: True,
}
for asset in assets:
should_pass_filter = expect_over_300[asset]
if set_screen and not should_pass_filter:
self.assertNotIn(asset, results.index)
continue
asset_results = results.loc[asset]
self.assertEqual(asset_results['filter'], should_pass_filter)
for length in vwaps:
computed = results.loc[asset, vwap_key(length)]
expected = vwaps[length][asset].loc[today]
# Only having two places of precision here is a bit
# unfortunate.
assert_almost_equal(computed, expected, decimal=2)
# Do the same checks in before_trading_start
before_trading_start = handle_data
algo = TradingAlgorithm(
initialize=initialize,
handle_data=handle_data,
before_trading_start=before_trading_start,
data_frequency='daily',
get_pipeline_loader=lambda column: self.pipeline_loader,
start=self.dates[max(window_lengths)],
end=self.dates[-1],
env=self.env,
)
algo.run(
FakeDataPortal(self.env),
# Yes, I really do want to use the start and end dates I passed to
# TradingAlgorithm.
overwrite_sim_params=False,
)
def test_handle_adjustment(self, set_screen):
AAPL, MSFT, BRK_A = assets = self.assets
window_lengths = [1, 2, 5, 10]
vwaps = self.compute_expected_vwaps(window_lengths)
def vwap_key(length):
return "vwap_%d" % length
def initialize(context):
pipeline = Pipeline()
context.vwaps = []
for length in vwaps:
name = vwap_key(length)
factor = VWAP(window_length=length)
context.vwaps.append(factor)
pipeline.add(factor, name=name)
filter_ = (USEquityPricing.close.latest > 300)
pipeline.add(filter_, 'filter')
if set_screen:
pipeline.set_screen(filter_)
attach_pipeline(pipeline, 'test')
def handle_data(context, data):
today = normalize_date(get_datetime())
results = pipeline_output('test')
expect_over_300 = {
AAPL: today < self.AAPL_split_date,
MSFT: False,
BRK_A: True,
}
for asset in assets:
should_pass_filter = expect_over_300[asset]
if set_screen and not should_pass_filter:
self.assertNotIn(asset, results.index)
continue
asset_results = results.loc[asset]
self.assertEqual(asset_results['filter'], should_pass_filter)
for length in vwaps:
computed = results.loc[asset, vwap_key(length)]
expected = vwaps[length][asset].loc[today]
# Only having two places of precision here is a bit
# unfortunate.
assert_almost_equal(computed, expected, decimal=2)
# Do the same checks in before_trading_start
before_trading_start = handle_data
algo = TradingAlgorithm(
initialize=initialize,
handle_data=handle_data,
before_trading_start=before_trading_start,
data_frequency='daily',
get_pipeline_loader=lambda column: self.pipeline_loader,
start=self.dates[max(window_lengths)],
end=self.dates[-1],
env=self.env,
)
algo.run(
FakeDataPortal(self.env),
# Yes, I really do want to use the start and end dates I passed to
# TradingAlgorithm.
overwrite_sim_params=False,
)