def test_regression_method_bad_type(self):
"""
Make sure we cannot call the Factor linear regression method on factors
or slices that are not of float or int dtype.
"""
# These are arbitrary for the purpose of this test.
returns_length = 2
regression_length = 10
returns = Returns(window_length=returns_length, inputs=[self.col])
returns_slice = returns[self.my_asset]
class BadTypeFactor(CustomFactor):
window_length = 1
inputs = []
dtype = datetime64ns_dtype
window_safe = True
def compute(self, today, assets, out):
pass
bad_type_factor = BadTypeFactor()
bad_type_factor_slice = bad_type_factor[self.my_asset]
with self.assertRaises(TypeError):
bad_type_factor.linear_regression(
target=returns_slice,
regression_length=regression_length,
)
with self.assertRaises(TypeError):
returns.linear_regression(
target=bad_type_factor_slice,
regression_length=regression_length,
)
def test_regression_method_bad_type(self):
"""
Make sure we cannot call the Factor linear regression method on factors
or slices that are not of float or int dtype.
"""
# These are arbitrary for the purpose of this test.
returns_length = 2
regression_length = 10
returns = Returns(window_length=returns_length, inputs=[self.col])
returns_slice = returns[self.my_asset]
class BadTypeFactor(CustomFactor):
window_length = 1
inputs = []
dtype = datetime64ns_dtype
window_safe = True
def compute(self, today, assets, out):
pass
bad_type_factor = BadTypeFactor()
bad_type_factor_slice = bad_type_factor[self.my_asset]
with self.assertRaises(TypeError):
bad_type_factor.linear_regression(
target=returns_slice, regression_length=regression_length,
)
with self.assertRaises(TypeError):
returns.linear_regression(
target=bad_type_factor_slice,
regression_length=regression_length,
)
def test_factor_regression_method(self, returns_length, regression_length):
"""
Ensure that `Factor.linear_regression` is consistent with the built-in
factor `RollingLinearRegressionOfReturns`.
"""
my_asset = self.my_asset
start_date = self.pipeline_start_date
end_date = self.pipeline_end_date
run_pipeline = self.run_pipeline
returns = Returns(window_length=returns_length, inputs=[self.col])
returns_slice = returns[my_asset]
regression = returns.linear_regression(
target=returns_slice,
regression_length=regression_length,
)
expected_regression = RollingLinearRegressionOfReturns(
target=my_asset,
returns_length=returns_length,
regression_length=regression_length,
)
# This built-in constructs its own Returns factor to use as an input,
# so the only way to set our own input is to do so after the fact. This
# should not be done in practice. It is necessary here because we want
# Returns to use our random data as an input, but by default it is
# using USEquityPricing.close.
expected_regression.inputs = [returns, returns_slice]
columns = {
'regression': regression,
'expected_regression': expected_regression,
}
results = run_pipeline(Pipeline(columns=columns), start_date, end_date)
regression_results = results['regression'].unstack()
expected_regression_results = results['expected_regression'].unstack()
assert_frame_equal(regression_results, expected_regression_results)
def test_factor_regression_method(self, returns_length, regression_length):
"""
Ensure that `Factor.linear_regression` is consistent with the built-in
factor `RollingLinearRegressionOfReturns`.
"""
my_asset = self.my_asset
start_date = self.pipeline_start_date
end_date = self.pipeline_end_date
run_pipeline = self.run_pipeline
returns = Returns(window_length=returns_length, inputs=[self.col])
returns_slice = returns[my_asset]
regression = returns.linear_regression(
target=returns_slice, regression_length=regression_length,
)
expected_regression = RollingLinearRegressionOfReturns(
target=my_asset,
returns_length=returns_length,
regression_length=regression_length,
)
# This built-in constructs its own Returns factor to use as an input,
# so the only way to set our own input is to do so after the fact. This
# should not be done in practice. It is necessary here because we want
# Returns to use our random data as an input, but by default it is
# using USEquityPricing.close.
expected_regression.inputs = [returns, returns_slice]
columns = {
'regression': regression,
'expected_regression': expected_regression,
}
results = run_pipeline(Pipeline(columns=columns), start_date, end_date)
regression_results = results['regression'].unstack()
expected_regression_results = results['expected_regression'].unstack()
assert_frame_equal(regression_results, expected_regression_results)
def test_factor_regression_method(self, returns_length, regression_length):
"""
Ensure that `Factor.linear_regression` is consistent with the built-in
factor `RollingLinearRegressionOfReturns`.
"""
my_asset = self.asset_finder.retrieve_asset(self.sids[0])
returns = Returns(window_length=returns_length, inputs=[self.col])
returns_slice = returns[my_asset]
regression = returns.linear_regression(
target=returns_slice,
regression_length=regression_length,
)
expected_regression = RollingLinearRegressionOfReturns(
target=my_asset,
returns_length=returns_length,
regression_length=regression_length,
)
# These built-ins construct their own Returns factor to use as inputs,
# so the only way to set our own inputs is to do so after the fact.
# This should not be done in practice. It is necessary here because we
# want Returns to use our random data as an input, but by default it is
# using USEquityPricing.close.
expected_regression.inputs = [returns, returns_slice]
class MyFactor(CustomFactor):
inputs = ()
window_length = 1
def compute(self, today, assets, out):
out[:] = 0
columns = {
'regression': regression,
'expected_regression': expected_regression,
}
results = self.run_pipeline(
Pipeline(columns=columns),
self.pipeline_start_date,
self.pipeline_end_date,
)
regression_results = results['regression'].unstack()
expected_regression_results = results['expected_regression'].unstack()
assert_frame_equal(regression_results, expected_regression_results)
# Make sure we cannot call the linear regression method on factors or
# slices of dtype `datetime64[ns]`.
class DateFactor(CustomFactor):
window_length = 1
inputs = []
dtype = datetime64ns_dtype
window_safe = True
def compute(self, today, assets, out):
pass
date_factor = DateFactor()
date_factor_slice = date_factor[my_asset]
with self.assertRaises(TypeError):
date_factor.linear_regression(
target=returns_slice,
regression_length=regression_length,
)
with self.assertRaises(TypeError):
returns.linear_regression(
target=date_factor_slice,
regression_length=regression_length,
)
def test_factor_regression_method_two_factors(self, regression_length):
"""
Tests for `Factor.linear_regression` when passed another 2D factor
instead of a Slice.
"""
assets = self.assets
dates = self.dates
start_date = self.pipeline_start_date
end_date = self.pipeline_end_date
start_date_index = self.start_date_index
end_date_index = self.end_date_index
num_days = self.num_days
run_pipeline = self.run_pipeline
# The order of these is meant to align with the output of `linregress`.
outputs = ['beta', 'alpha', 'r_value', 'p_value', 'stderr']
# Ensure that the `linear_regression` method cannot be called with two
# 2D factors which have different masks.
returns_masked_1 = Returns(
window_length=5,
inputs=[self.col],
mask=AssetID().eq(1),
)
returns_masked_2 = Returns(
window_length=5,
inputs=[self.col],
mask=AssetID().eq(2),
)
with self.assertRaises(IncompatibleTerms):
returns_masked_1.linear_regression(
target=returns_masked_2,
regression_length=regression_length,
)
returns_5 = Returns(window_length=5, inputs=[self.col])
returns_10 = Returns(window_length=10, inputs=[self.col])
regression_factor = returns_5.linear_regression(
target=returns_10,
regression_length=regression_length,
)
columns = {
output: getattr(regression_factor, output)
for output in outputs
}
pipeline = Pipeline(columns=columns)
results = run_pipeline(pipeline, start_date, end_date)
output_results = {}
expected_output_results = {}
for output in outputs:
output_results[output] = results[output].unstack()
expected_output_results[output] = full_like(
output_results[output],
nan,
)
# Run a separate pipeline that calculates returns starting
# (regression_length - 1) days prior to our start date. This is because
# we need (regression_length - 1) extra days of returns to compute our
# expected regressions.
columns = {'returns_5': returns_5, 'returns_10': returns_10}
results = run_pipeline(
Pipeline(columns=columns),
dates[start_date_index - (regression_length - 1)],
dates[end_date_index],
)
returns_5_results = results['returns_5'].unstack()
returns_10_results = results['returns_10'].unstack()
# On each day, for each asset, calculate the expected regression
# results of Y ~ X where Y is the asset's rolling 5 day returns and X
# is the asset's rolling 10 day returns. Each regression is calculated
# over `regression_length` days of data.
for day in range(num_days):
todays_returns_5 = returns_5_results.iloc[day:day +
regression_length]
todays_returns_10 = returns_10_results.iloc[day:day +
regression_length]
for asset, asset_returns_5 in todays_returns_5.iteritems():
asset_column = int(asset) - 1
asset_returns_10 = todays_returns_10[asset]
expected_regression_results = linregress(
y=asset_returns_5,
x=asset_returns_10,
)
for i, output in enumerate(outputs):
expected_output_results[output][day, asset_column] = \
expected_regression_results[i]
for output in outputs:
output_result = output_results[output]
expected_output_result = DataFrame(
expected_output_results[output],
index=dates[start_date_index:end_date_index + 1],
columns=assets,
)
assert_frame_equal(output_result, expected_output_result)
def test_factor_regression_method_two_factors(self, regression_length):
"""
Tests for `Factor.linear_regression` when passed another 2D factor
instead of a Slice.
"""
assets = self.assets
dates = self.dates
start_date = self.pipeline_start_date
end_date = self.pipeline_end_date
start_date_index = self.start_date_index
end_date_index = self.end_date_index
num_days = self.num_days
run_pipeline = self.run_pipeline
# The order of these is meant to align with the output of `linregress`.
outputs = ['beta', 'alpha', 'r_value', 'p_value', 'stderr']
# Ensure that the `linear_regression` method cannot be called with two
# 2D factors which have different masks.
returns_masked_1 = Returns(
window_length=5, inputs=[self.col], mask=AssetID().eq(1),
)
returns_masked_2 = Returns(
window_length=5, inputs=[self.col], mask=AssetID().eq(2),
)
with self.assertRaises(IncompatibleTerms):
returns_masked_1.linear_regression(
target=returns_masked_2, regression_length=regression_length,
)
returns_5 = Returns(window_length=5, inputs=[self.col])
returns_10 = Returns(window_length=10, inputs=[self.col])
regression_factor = returns_5.linear_regression(
target=returns_10, regression_length=regression_length,
)
columns = {
output: getattr(regression_factor, output)
for output in outputs
}
pipeline = Pipeline(columns=columns)
results = run_pipeline(pipeline, start_date, end_date)
output_results = {}
expected_output_results = {}
for output in outputs:
output_results[output] = results[output].unstack()
expected_output_results[output] = full_like(
output_results[output], nan,
)
# Run a separate pipeline that calculates returns starting
# (regression_length - 1) days prior to our start date. This is because
# we need (regression_length - 1) extra days of returns to compute our
# expected regressions.
columns = {'returns_5': returns_5, 'returns_10': returns_10}
results = run_pipeline(
Pipeline(columns=columns),
dates[start_date_index - (regression_length - 1)],
dates[end_date_index],
)
returns_5_results = results['returns_5'].unstack()
returns_10_results = results['returns_10'].unstack()
# On each day, for each asset, calculate the expected regression
# results of Y ~ X where Y is the asset's rolling 5 day returns and X
# is the asset's rolling 10 day returns. Each regression is calculated
# over `regression_length` days of data.
for day in range(num_days):
todays_returns_5 = returns_5_results.iloc[
day:day + regression_length
]
todays_returns_10 = returns_10_results.iloc[
day:day + regression_length
]
for asset, asset_returns_5 in todays_returns_5.iteritems():
asset_column = int(asset) - 1
asset_returns_10 = todays_returns_10[asset]
expected_regression_results = linregress(
y=asset_returns_5, x=asset_returns_10,
)
for i, output in enumerate(outputs):
expected_output_results[output][day, asset_column] = \
expected_regression_results[i]
for output in outputs:
output_result = output_results[output]
expected_output_result = DataFrame(
expected_output_results[output],
index=dates[start_date_index:end_date_index + 1],
columns=assets,
)
assert_frame_equal(output_result, expected_output_result)
def test_factor_regression_method(self, returns_length, regression_length):
"""
Ensure that `Factor.linear_regression` is consistent with the built-in
factor `RollingLinearRegressionOfReturns`.
"""
my_asset = self.asset_finder.retrieve_asset(self.sids[0])
returns = Returns(window_length=returns_length, inputs=[self.col])
returns_slice = returns[my_asset]
regression = returns.linear_regression(
target=returns_slice, regression_length=regression_length,
)
expected_regression = RollingLinearRegressionOfReturns(
target=my_asset,
returns_length=returns_length,
regression_length=regression_length,
)
# These built-ins construct their own Returns factor to use as inputs,
# so the only way to set our own inputs is to do so after the fact.
# This should not be done in practice. It is necessary here because we
# want Returns to use our random data as an input, but by default it is
# using USEquityPricing.close.
expected_regression.inputs = [returns, returns_slice]
columns = {
'regression': regression,
'expected_regression': expected_regression,
}
results = self.run_pipeline(
Pipeline(columns=columns),
self.pipeline_start_date,
self.pipeline_end_date,
)
regression_results = results['regression'].unstack()
expected_regression_results = results['expected_regression'].unstack()
assert_frame_equal(regression_results, expected_regression_results)
# Make sure we cannot call the linear regression method on factors or
# slices of dtype `datetime64[ns]`.
class DateFactor(CustomFactor):
window_length = 1
inputs = []
dtype = datetime64ns_dtype
window_safe = True
def compute(self, today, assets, out):
pass
date_factor = DateFactor()
date_factor_slice = date_factor[my_asset]
with self.assertRaises(TypeError):
date_factor.linear_regression(
target=returns_slice, regression_length=regression_length,
)
with self.assertRaises(TypeError):
returns.linear_regression(
target=date_factor_slice, regression_length=regression_length,
)
