def __iter__(self):
asset_cache = {}
for dt, series in self.df.iterrows():
if dt < self.start_date:
continue
if dt > self.end_date:
return
event = FetcherEvent()
# when dt column is converted to be the dataframe's index
# the dt column is dropped. So, we need to manually copy
# dt into the event.
event.dt = dt
for k, v in series.iteritems():
# convert numpy integer types to
# int. This assumes we are on a 64bit
# platform that will not lose information
# by casting.
# TODO: this is only necessary on the
# amazon qexec instances. would be good
# to figure out how to use the numpy dtypes
# without this check and casting.
if isinstance(v, numpy.integer):
v = int(v)
setattr(event, k, v)
# If it has start_date, then it's already an Asset
# object from asset_for_symbol, and we don't have to
# transform it any further. Checking for start_date is
# faster than isinstance.
if event.sid in asset_cache:
event.sid = asset_cache[event.sid]
elif hasattr(event.sid, 'start_date'):
# Clone for user algo code, if we haven't already.
asset_cache[event.sid] = event.sid
elif self.finder and isinstance(event.sid, int):
asset = self.finder.retrieve_asset(event.sid,
default_none=True)
if asset:
# Clone for user algo code.
event.sid = asset_cache[asset] = asset
elif self.mask:
# When masking drop all non-mappable values.
continue
elif self.symbol is None:
# If the event's sid property is an int we coerce
# it into an Equity.
event.sid = asset_cache[event.sid] = Equity(event.sid)
event.type = DATASOURCE_TYPE.CUSTOM
event.source_id = self.namestring
yield event
def test_correlation_and_regression_with_bad_asset(self):
"""
Test that `RollingPearsonOfReturns`, `RollingSpearmanOfReturns` and
`RollingLinearRegressionOfReturns` raise the proper exception when
given a nonexistent target asset.
"""
my_asset = Equity(0, exchange="TEST")
start_date = self.pipeline_start_date
end_date = self.pipeline_end_date
run_pipeline = self.run_pipeline
# This filter is arbitrary; the important thing is that we test each
# factor both with and without a specified mask.
my_asset_filter = AssetID().eq(1)
for mask in (NotSpecified, my_asset_filter):
pearson_factor = RollingPearsonOfReturns(
target=my_asset,
returns_length=3,
correlation_length=3,
mask=mask,
)
spearman_factor = RollingSpearmanOfReturns(
target=my_asset,
returns_length=3,
correlation_length=3,
mask=mask,
)
regression_factor = RollingLinearRegressionOfReturns(
target=my_asset,
returns_length=3,
regression_length=3,
mask=mask,
)
with self.assertRaises(NonExistentAssetInTimeFrame):
run_pipeline(
Pipeline(columns={'pearson_factor': pearson_factor}),
start_date,
end_date,
)
with self.assertRaises(NonExistentAssetInTimeFrame):
run_pipeline(
Pipeline(columns={'spearman_factor': spearman_factor}),
start_date,
end_date,
)
with self.assertRaises(NonExistentAssetInTimeFrame):
run_pipeline(
Pipeline(columns={'regression_factor': regression_factor}),
start_date,
end_date,
)
def test_transaction_repr(self):
dt = pd.Timestamp('2017-01-01')
asset = Equity(1, exchange='test')
txn = Transaction(asset, amount=100, dt=dt, price=10, order_id=0)
expected = (
"Transaction(asset=Equity(1), dt=2017-01-01 00:00:00,"
" amount=100, price=10)"
)
self.assertEqual(repr(txn), expected)
def test_require_length_greater_than_one(self):
my_asset = Equity(0, exchange="TEST")
with self.assertRaises(ValueError):
RollingPearsonOfReturns(
target=my_asset,
returns_length=3,
correlation_length=1,
)
with self.assertRaises(ValueError):
RollingSpearmanOfReturns(
target=my_asset,
returns_length=3,
correlation_length=1,
)
with self.assertRaises(ValueError):
RollingLinearRegressionOfReturns(
target=my_asset,
returns_length=3,
regression_length=1,
)