def test_factor_correlation_methods(self, returns_length,
correlation_length):
"""
Ensure that `Factor.pearsonr` and `Factor.spearmanr` are consistent
with the built-in factors `RollingPearsonOfReturns` and
`RollingSpearmanOfReturns`.
"""
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]
pearson = returns.pearsonr(
target=returns_slice,
correlation_length=correlation_length,
)
spearman = returns.spearmanr(
target=returns_slice,
correlation_length=correlation_length,
)
expected_pearson = RollingPearsonOfReturns(
target=my_asset,
returns_length=returns_length,
correlation_length=correlation_length,
)
expected_spearman = RollingSpearmanOfReturns(
target=my_asset,
returns_length=returns_length,
correlation_length=correlation_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_pearson.inputs = [returns, returns_slice]
expected_spearman.inputs = [returns, returns_slice]
columns = {
'pearson': pearson,
'spearman': spearman,
'expected_pearson': expected_pearson,
'expected_spearman': expected_spearman,
}
results = run_pipeline(Pipeline(columns=columns), start_date, end_date)
pearson_results = results['pearson'].unstack()
spearman_results = results['spearman'].unstack()
expected_pearson_results = results['expected_pearson'].unstack()
expected_spearman_results = results['expected_spearman'].unstack()
assert_frame_equal(pearson_results, expected_pearson_results)
assert_frame_equal(spearman_results, expected_spearman_results)
def test_correlation_methods_bad_type(self):
"""
Make sure we cannot call the Factor correlation methods on factors or
slices that are not of float or int dtype.
"""
# These are arbitrary for the purpose of this test.
returns_length = 2
correlation_length = 10
returns = Returns(window_length=returns_length, inputs=[self.col])
returns_slice = returns[self.my_asset]
class BadTypeFactor(CustomFactor):
inputs = []
window_length = 1
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.pearsonr(
target=returns_slice,
correlation_length=correlation_length,
)
with self.assertRaises(TypeError):
bad_type_factor.spearmanr(
target=returns_slice,
correlation_length=correlation_length,
)
with self.assertRaises(TypeError):
returns.pearsonr(
target=bad_type_factor_slice,
correlation_length=correlation_length,
)
with self.assertRaises(TypeError):
returns.spearmanr(
target=bad_type_factor_slice,
correlation_length=correlation_length,
)
def test_factor_correlation_methods(self,
returns_length,
correlation_length):
"""
Ensure that `Factor.pearsonr` and `Factor.spearmanr` are consistent
with the built-in factors `RollingPearsonOfReturns` and
`RollingSpearmanOfReturns`.
"""
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]
pearson = returns.pearsonr(
target=returns_slice, correlation_length=correlation_length,
)
spearman = returns.spearmanr(
target=returns_slice, correlation_length=correlation_length,
)
expected_pearson = RollingPearsonOfReturns(
target=my_asset,
returns_length=returns_length,
correlation_length=correlation_length,
)
expected_spearman = RollingSpearmanOfReturns(
target=my_asset,
returns_length=returns_length,
correlation_length=correlation_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_pearson.inputs = [returns, returns_slice]
expected_spearman.inputs = [returns, returns_slice]
columns = {
'pearson': pearson,
'spearman': spearman,
'expected_pearson': expected_pearson,
'expected_spearman': expected_spearman,
}
results = run_pipeline(Pipeline(columns=columns), start_date, end_date)
pearson_results = results['pearson'].unstack()
spearman_results = results['spearman'].unstack()
expected_pearson_results = results['expected_pearson'].unstack()
expected_spearman_results = results['expected_spearman'].unstack()
assert_frame_equal(pearson_results, expected_pearson_results)
assert_frame_equal(spearman_results, expected_spearman_results)
def test_correlation_methods_bad_type(self):
"""
Make sure we cannot call the Factor correlation methods on factors or
slices that are not of float or int dtype.
"""
# These are arbitrary for the purpose of this test.
returns_length = 2
correlation_length = 10
returns = Returns(window_length=returns_length, inputs=[self.col])
returns_slice = returns[self.my_asset]
class BadTypeFactor(CustomFactor):
inputs = []
window_length = 1
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.pearsonr(
target=returns_slice, correlation_length=correlation_length,
)
with self.assertRaises(TypeError):
bad_type_factor.spearmanr(
target=returns_slice, correlation_length=correlation_length,
)
with self.assertRaises(TypeError):
returns.pearsonr(
target=bad_type_factor_slice,
correlation_length=correlation_length,
)
with self.assertRaises(TypeError):
returns.spearmanr(
target=bad_type_factor_slice,
correlation_length=correlation_length,
)
def test_factor_correlation_methods(self, returns_length,
correlation_length):
"""
Ensure that `Factor.pearsonr` and `Factor.spearmanr` are consistent
with the built-in factors `RollingPearsonOfReturns` and
`RollingSpearmanOfReturns`.
"""
my_asset = self.asset_finder.retrieve_asset(self.sids[0])
returns = Returns(window_length=returns_length, inputs=[self.col])
returns_slice = returns[my_asset]
pearson = returns.pearsonr(
target=returns_slice,
correlation_length=correlation_length,
)
spearman = returns.spearmanr(
target=returns_slice,
correlation_length=correlation_length,
)
expected_pearson = RollingPearsonOfReturns(
target=my_asset,
returns_length=returns_length,
correlation_length=correlation_length,
)
expected_spearman = RollingSpearmanOfReturns(
target=my_asset,
returns_length=returns_length,
correlation_length=correlation_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_pearson.inputs = [returns, returns_slice]
expected_spearman.inputs = [returns, returns_slice]
columns = {
'pearson': pearson,
'spearman': spearman,
'expected_pearson': expected_pearson,
'expected_spearman': expected_spearman,
}
results = self.run_pipeline(
Pipeline(columns=columns),
self.pipeline_start_date,
self.pipeline_end_date,
)
pearson_results = results['pearson'].unstack()
spearman_results = results['spearman'].unstack()
expected_pearson_results = results['expected_pearson'].unstack()
expected_spearman_results = results['expected_spearman'].unstack()
assert_frame_equal(pearson_results, expected_pearson_results)
assert_frame_equal(spearman_results, expected_spearman_results)
# Make sure we cannot call the correlation methods 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.pearsonr(
target=returns_slice,
correlation_length=correlation_length,
)
with self.assertRaises(TypeError):
date_factor.spearmanr(
target=returns_slice,
correlation_length=correlation_length,
)
with self.assertRaises(TypeError):
returns.pearsonr(
target=date_factor_slice,
correlation_length=correlation_length,
)
with self.assertRaises(TypeError):
returns.pearsonr(
target=date_factor_slice,
correlation_length=correlation_length,
)
def test_factor_correlation_methods_two_factors(self, correlation_length):
"""
Tests for `Factor.pearsonr` and `Factor.spearmanr` 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
# Ensure that the correlation methods 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.pearsonr(
target=returns_masked_2,
correlation_length=correlation_length,
)
with self.assertRaises(IncompatibleTerms):
returns_masked_1.spearmanr(
target=returns_masked_2,
correlation_length=correlation_length,
)
returns_5 = Returns(window_length=5, inputs=[self.col])
returns_10 = Returns(window_length=10, inputs=[self.col])
pearson_factor = returns_5.pearsonr(
target=returns_10,
correlation_length=correlation_length,
)
spearman_factor = returns_5.spearmanr(
target=returns_10,
correlation_length=correlation_length,
)
columns = {
'pearson_factor': pearson_factor,
'spearman_factor': spearman_factor,
}
pipeline = Pipeline(columns=columns)
results = run_pipeline(pipeline, start_date, end_date)
pearson_results = results['pearson_factor'].unstack()
spearman_results = results['spearman_factor'].unstack()
# Run a separate pipeline that calculates returns starting
# (correlation_length - 1) days prior to our start date. This is
# because we need (correlation_length - 1) extra days of returns to
# compute our expected correlations.
columns = {'returns_5': returns_5, 'returns_10': returns_10}
results = run_pipeline(
Pipeline(columns=columns),
dates[start_date_index - (correlation_length - 1)],
dates[end_date_index],
)
returns_5_results = results['returns_5'].unstack()
returns_10_results = results['returns_10'].unstack()
# On each day, calculate the expected correlation coefficients
# between each asset's 5 and 10 day rolling returns. Each correlation
# is calculated over `correlation_length` days.
expected_pearson_results = full_like(pearson_results, nan)
expected_spearman_results = full_like(spearman_results, nan)
for day in range(num_days):
todays_returns_5 = returns_5_results.iloc[day:day +
correlation_length]
todays_returns_10 = returns_10_results.iloc[day:day +
correlation_length]
for asset, asset_returns_5 in todays_returns_5.iteritems():
asset_column = int(asset) - 1
asset_returns_10 = todays_returns_10[asset]
expected_pearson_results[day, asset_column] = pearsonr(
asset_returns_5,
asset_returns_10,
)[0]
expected_spearman_results[day, asset_column] = spearmanr(
asset_returns_5,
asset_returns_10,
)[0]
expected_pearson_results = DataFrame(
data=expected_pearson_results,
index=dates[start_date_index:end_date_index + 1],
columns=assets,
)
assert_frame_equal(pearson_results, expected_pearson_results)
expected_spearman_results = DataFrame(
data=expected_spearman_results,
index=dates[start_date_index:end_date_index + 1],
columns=assets,
)
assert_frame_equal(spearman_results, expected_spearman_results)
def test_factor_correlation_methods_two_factors(self, correlation_length):
"""
Tests for `Factor.pearsonr` and `Factor.spearmanr` 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
# Ensure that the correlation methods 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.pearsonr(
target=returns_masked_2, correlation_length=correlation_length,
)
with self.assertRaises(IncompatibleTerms):
returns_masked_1.spearmanr(
target=returns_masked_2, correlation_length=correlation_length,
)
returns_5 = Returns(window_length=5, inputs=[self.col])
returns_10 = Returns(window_length=10, inputs=[self.col])
pearson_factor = returns_5.pearsonr(
target=returns_10, correlation_length=correlation_length,
)
spearman_factor = returns_5.spearmanr(
target=returns_10, correlation_length=correlation_length,
)
columns = {
'pearson_factor': pearson_factor,
'spearman_factor': spearman_factor,
}
pipeline = Pipeline(columns=columns)
results = run_pipeline(pipeline, start_date, end_date)
pearson_results = results['pearson_factor'].unstack()
spearman_results = results['spearman_factor'].unstack()
# Run a separate pipeline that calculates returns starting
# (correlation_length - 1) days prior to our start date. This is
# because we need (correlation_length - 1) extra days of returns to
# compute our expected correlations.
columns = {'returns_5': returns_5, 'returns_10': returns_10}
results = run_pipeline(
Pipeline(columns=columns),
dates[start_date_index - (correlation_length - 1)],
dates[end_date_index],
)
returns_5_results = results['returns_5'].unstack()
returns_10_results = results['returns_10'].unstack()
# On each day, calculate the expected correlation coefficients
# between each asset's 5 and 10 day rolling returns. Each correlation
# is calculated over `correlation_length` days.
expected_pearson_results = full_like(pearson_results, nan)
expected_spearman_results = full_like(spearman_results, nan)
for day in range(num_days):
todays_returns_5 = returns_5_results.iloc[
day:day + correlation_length
]
todays_returns_10 = returns_10_results.iloc[
day:day + correlation_length
]
for asset, asset_returns_5 in todays_returns_5.iteritems():
asset_column = int(asset) - 1
asset_returns_10 = todays_returns_10[asset]
expected_pearson_results[day, asset_column] = pearsonr(
asset_returns_5, asset_returns_10,
)[0]
expected_spearman_results[day, asset_column] = spearmanr(
asset_returns_5, asset_returns_10,
)[0]
expected_pearson_results = DataFrame(
data=expected_pearson_results,
index=dates[start_date_index:end_date_index + 1],
columns=assets,
)
assert_frame_equal(pearson_results, expected_pearson_results)
expected_spearman_results = DataFrame(
data=expected_spearman_results,
index=dates[start_date_index:end_date_index + 1],
columns=assets,
)
assert_frame_equal(spearman_results, expected_spearman_results)
def test_factor_correlation_methods(self,
returns_length,
correlation_length):
"""
Ensure that `Factor.pearsonr` and `Factor.spearmanr` are consistent
with the built-in factors `RollingPearsonOfReturns` and
`RollingSpearmanOfReturns`.
"""
my_asset = self.asset_finder.retrieve_asset(self.sids[0])
returns = Returns(window_length=returns_length, inputs=[self.col])
returns_slice = returns[my_asset]
pearson = returns.pearsonr(
target=returns_slice, correlation_length=correlation_length,
)
spearman = returns.spearmanr(
target=returns_slice, correlation_length=correlation_length,
)
expected_pearson = RollingPearsonOfReturns(
target=my_asset,
returns_length=returns_length,
correlation_length=correlation_length,
)
expected_spearman = RollingSpearmanOfReturns(
target=my_asset,
returns_length=returns_length,
correlation_length=correlation_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_pearson.inputs = [returns, returns_slice]
expected_spearman.inputs = [returns, returns_slice]
columns = {
'pearson': pearson,
'spearman': spearman,
'expected_pearson': expected_pearson,
'expected_spearman': expected_spearman,
}
results = self.run_pipeline(
Pipeline(columns=columns),
self.pipeline_start_date,
self.pipeline_end_date,
)
pearson_results = results['pearson'].unstack()
spearman_results = results['spearman'].unstack()
expected_pearson_results = results['expected_pearson'].unstack()
expected_spearman_results = results['expected_spearman'].unstack()
assert_frame_equal(pearson_results, expected_pearson_results)
assert_frame_equal(spearman_results, expected_spearman_results)
# Make sure we cannot call the correlation methods 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.pearsonr(
target=returns_slice, correlation_length=correlation_length,
)
with self.assertRaises(TypeError):
date_factor.spearmanr(
target=returns_slice, correlation_length=correlation_length,
)
with self.assertRaises(TypeError):
returns.pearsonr(
target=date_factor_slice,
correlation_length=correlation_length,
)
with self.assertRaises(TypeError):
returns.pearsonr(
target=date_factor_slice,
correlation_length=correlation_length,
)
