def test_all_present_classifier_input(self):
"""Test classifier factor input to `AllPresent`"""
class SomeWindowSafeStringClassifier(Classifier):
dtype = object_dtype
inputs = ()
window_length = 0
missing_value = ""
window_safe = True
input_factor = SomeWindowSafeStringClassifier()
shape = (10, 6)
data = RandomState(6).choice(
array(["a", "e", "i", "o", "u"], dtype=object_dtype),
size=shape,
replace=True,
)
data[eye(*shape, dtype=bool)] = input_factor.missing_value
expected_3 = array(
[
[1, 0, 0, 0, 1, 1],
[1, 1, 0, 0, 0, 1],
[1, 1, 1, 0, 0, 0],
[1, 1, 1, 1, 0, 0],
[1, 1, 1, 1, 1, 0],
[1, 1, 1, 1, 1, 1],
[1, 1, 1, 1, 1, 1],
],
dtype=bool,
)
expected_4 = array(
[
[0, 0, 0, 0, 1, 1],
[1, 0, 0, 0, 0, 1],
[1, 1, 0, 0, 0, 0],
[1, 1, 1, 0, 0, 0],
[1, 1, 1, 1, 0, 0],
[1, 1, 1, 1, 1, 0],
[1, 1, 1, 1, 1, 1],
],
dtype=bool,
)
self.check_terms(
terms={
"3": AllPresent([input_factor], window_length=3),
"4": AllPresent([input_factor], window_length=4),
},
expected={
"3": expected_3,
"4": expected_4,
},
initial_workspace={input_factor: data},
mask=self.build_mask(ones(shape=shape)),
)
def test_all_present_int_factor_input(self):
"""Test int factor input to `AllPresent`"""
class SomeWindowSafeIntFactor(Factor):
dtype = int64_dtype
inputs = ()
window_length = 0
window_safe = True
missing_value = 0
input_factor = SomeWindowSafeIntFactor()
shape = (10, 6)
data = RandomState(5).choice(range(1, 5), size=shape, replace=True)
data[eye(*shape, dtype=bool)] = input_factor.missing_value
expected_3 = array(
[
[1, 0, 0, 0, 1, 1],
[1, 1, 0, 0, 0, 1],
[1, 1, 1, 0, 0, 0],
[1, 1, 1, 1, 0, 0],
[1, 1, 1, 1, 1, 0],
[1, 1, 1, 1, 1, 1],
[1, 1, 1, 1, 1, 1],
],
dtype=bool,
)
expected_4 = array(
[
[0, 0, 0, 0, 1, 1],
[1, 0, 0, 0, 0, 1],
[1, 1, 0, 0, 0, 0],
[1, 1, 1, 0, 0, 0],
[1, 1, 1, 1, 0, 0],
[1, 1, 1, 1, 1, 0],
[1, 1, 1, 1, 1, 1],
],
dtype=bool,
)
self.check_terms(
terms={
"3": AllPresent([input_factor], window_length=3),
"4": AllPresent([input_factor], window_length=4),
},
expected={
"3": expected_3,
"4": expected_4,
},
initial_workspace={input_factor: data},
mask=self.build_mask(ones(shape=shape)),
)
def test_all_present_float_factor_input(self):
"""Test float factor input to `AllPresent`"""
class SomeWindowSafeFactor(Factor):
dtype = float64_dtype
inputs = ()
window_length = 0
window_safe = True
input_factor = SomeWindowSafeFactor()
shape = (10, 6)
data = self.randn_data(seed=10, shape=shape)
data[eye(*shape, dtype=bool)] = input_factor.missing_value
expected_3 = array(
[
[1, 0, 0, 0, 1, 1],
[1, 1, 0, 0, 0, 1],
[1, 1, 1, 0, 0, 0],
[1, 1, 1, 1, 0, 0],
[1, 1, 1, 1, 1, 0],
[1, 1, 1, 1, 1, 1],
[1, 1, 1, 1, 1, 1],
],
dtype=bool,
)
expected_4 = array(
[
[0, 0, 0, 0, 1, 1],
[1, 0, 0, 0, 0, 1],
[1, 1, 0, 0, 0, 0],
[1, 1, 1, 0, 0, 0],
[1, 1, 1, 1, 0, 0],
[1, 1, 1, 1, 1, 0],
[1, 1, 1, 1, 1, 1],
],
dtype=bool,
)
self.check_terms(
terms={
"3": AllPresent([input_factor], window_length=3),
"4": AllPresent([input_factor], window_length=4),
},
expected={
"3": expected_3,
"4": expected_4,
},
initial_workspace={input_factor: data},
mask=self.build_mask(ones(shape=shape)),
)
def test_all_present_classifier_input(self):
"""Test classifier factor input to `AllPresent`
"""
class SomeWindowSafeStringClassifier(Classifier):
dtype = object_dtype
inputs = ()
window_length = 0
missing_value = ''
window_safe = True
input_factor = SomeWindowSafeStringClassifier()
shape = (10, 6)
data = choice(
array(['a', 'e', 'i', 'o', 'u'], dtype=object_dtype),
size=shape,
replace=True
)
data[eye(*shape, dtype=bool)] = input_factor.missing_value
expected_3 = array([[1, 0, 0, 0, 1, 1],
[1, 1, 0, 0, 0, 1],
[1, 1, 1, 0, 0, 0],
[1, 1, 1, 1, 0, 0],
[1, 1, 1, 1, 1, 0],
[1, 1, 1, 1, 1, 1],
[1, 1, 1, 1, 1, 1]], dtype=bool)
expected_4 = array([[0, 0, 0, 0, 1, 1],
[1, 0, 0, 0, 0, 1],
[1, 1, 0, 0, 0, 0],
[1, 1, 1, 0, 0, 0],
[1, 1, 1, 1, 0, 0],
[1, 1, 1, 1, 1, 0],
[1, 1, 1, 1, 1, 1]], dtype=bool)
self.check_terms(
terms={
'3': AllPresent([input_factor], window_length=3),
'4': AllPresent([input_factor], window_length=4),
},
expected={
'3': expected_3,
'4': expected_4,
},
initial_workspace={input_factor: data},
mask=self.build_mask(ones(shape=shape))
)
def TradableStocksUS(sector):
# Equities listed as common stock (not preferred stock, ETF, ADR, LP, etc)
common_stock = master.SecuritiesMaster.usstock_SecurityType2.latest.eq(
'Common Stock')
# Filter for primary share equities; primary shares can be identified by a
# null usstock_PrimaryShareSid field (i.e. no pointer to a primary share)
is_primary_share = master.SecuritiesMaster.usstock_PrimaryShareSid.latest.isnull(
)
in_sector = master.SecuritiesMaster.usstock_Sector.latest.eq(sector)
# combine the security type filters to begin forming our universe
tradable_stocks = common_stock & is_primary_share & in_sector
# also require high dollar volume
tradable_stocks = AverageDollarVolume(
window_length=200, mask=tradable_stocks).percentile_between(90, 100)
# also require price > $5. Note that we use Latest(...) instead of EquityPricing.close.latest
# so that we can pass a mask
tradable_stocks = Latest([USEquityPricing.close],
mask=tradable_stocks) > 10
# also require no missing data for 200 days
tradable_stocks = AllPresent(inputs=[USEquityPricing.close],
window_length=200,
mask=tradable_stocks)
tradable_stocks = All([USEquityPricing.volume.latest > 0],
window_length=200,
mask=tradable_stocks)
return tradable_stocks
def test_all_present_filter_input(self):
"""Test error is raised when filter factor is input to `AllPresent`
"""
with self.assertRaises(TypeError) as err:
AllPresent([Mask()], window_length=4)
self.assertEqual("Input to filter `AllPresent` cannot be a Filter.",
str(err.exception))
def TradableStocksUS(market_cap_filter=False):
"""
Returns a Pipeline filter of tradable stocks, defined as:
- Common stocks only (no preferred stocks, ADRs, LPs, or ETFs)
- Primary shares only
- 200-day average dollar volume >= $2.5M
- price >= $5
- 200 continuous days of price and volume.
If market_cap_filter=True, also requires market cap > $500M.
"""
# Equities listed as common stock (not preferred stock, ETF, ADR, LP, etc)
common_stock = master.SecuritiesMaster.usstock_SecurityType2.latest.eq(
'Common Stock')
# Filter for primary share equities; primary shares can be identified by a
# null usstock_PrimaryShareSid field (i.e. no pointer to a primary share)
is_primary_share = master.SecuritiesMaster.usstock_PrimaryShareSid.latest.isnull(
)
# combine the security type filters to begin forming our universe
tradable_stocks = common_stock & is_primary_share
# also require high dollar volume
tradable_stocks = AverageDollarVolume(window_length=200,
mask=tradable_stocks) >= 2.5e6
# also require price > $5. Note that we use Latest(...) instead of EquityPricing.close.latest
# so that we can pass a mask
tradable_stocks = Latest([EquityPricing.close], mask=tradable_stocks) > 5
# also require no missing data for 200 days
tradable_stocks = AllPresent(inputs=[EquityPricing.close],
window_length=200,
mask=tradable_stocks)
tradable_stocks = All([EquityPricing.volume.latest > 0],
window_length=200,
mask=tradable_stocks)
if market_cap_filter:
# also require market cap over $500M
tradable_stocks = Latest([
sharadar.Fundamentals.slice(dimension='ARQ',
period_offset=0).MARKETCAP
],
mask=tradable_stocks) >= 500e6
return tradable_stocks
def test_all_present_filter_input(self):
"""Test error is raised when filter factor is input to `AllPresent`"""
expected_msg = "Input to filter `AllPresent` cannot be a Filter."
with pytest.raises(TypeError, match=expected_msg):
AllPresent([Mask()], window_length=4)
