def check_downsampled_term(self, term):
# June 2014
# Mo Tu We Th Fr Sa Su
# 1
# 2 3 4 5 6 7 8
# 9 10 11 12 13 14 15
# 16 17 18 19 20 21 22
# 23 24 25 26 27 28 29
# 30
all_sessions = self.nyse_sessions
compute_dates = all_sessions[
all_sessions.slice_indexer('2014-06-05', '2015-01-06')
]
start_date, end_date = compute_dates[[0, -1]]
pipe = Pipeline({
'year': term.downsample(frequency='year_start'),
'quarter': term.downsample(frequency='quarter_start'),
'month': term.downsample(frequency='month_start'),
'week': term.downsample(frequency='week_start'),
})
# Raw values for term, computed each day from 2014 to the end of the
# target period.
raw_term_results = self.run_pipeline(
Pipeline({'term': term}),
start_date=pd.Timestamp('2014-01-02', tz='UTC'),
end_date=pd.Timestamp('2015-01-06', tz='UTC'),
)['term'].unstack()
expected_results = {
'year': (raw_term_results
.groupby(pd.TimeGrouper('AS'))
.first()
.reindex(compute_dates, method='ffill')),
'quarter': (raw_term_results
.groupby(pd.TimeGrouper('QS'))
.first()
.reindex(compute_dates, method='ffill')),
'month': (raw_term_results
.groupby(pd.TimeGrouper('MS'))
.first()
.reindex(compute_dates, method='ffill')),
'week': (raw_term_results
.groupby(pd.TimeGrouper('W', label='left'))
.first()
.reindex(compute_dates, method='ffill')),
}
results = self.run_pipeline(pipe, start_date, end_date)
for frequency in expected_results:
result = results[frequency].unstack()
expected = expected_results[frequency]
assert_frame_equal(result, expected)
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_adding_slice_column(self):
"""
Test that slices cannot be added as a pipeline column.
"""
my_asset = self.asset_finder.retrieve_asset(self.sids[0])
open_slice = OpenPrice()[my_asset]
with self.assertRaises(UnsupportedPipelineOutput):
Pipeline(columns={'open_slice': open_slice})
pipe = Pipeline(columns={})
with self.assertRaises(UnsupportedPipelineOutput):
pipe.add(open_slice, 'open_slice')
def test_slice_with_masking(self, unmasked_column, slice_column):
"""
Test that masking a factor that uses slices as inputs does not mask the
slice data.
"""
sids = self.sids
asset_finder = self.asset_finder
start_date = self.pipeline_start_date
end_date = self.pipeline_end_date
# Create a filter that masks out all but a single asset.
unmasked_asset = asset_finder.retrieve_asset(sids[unmasked_column])
unmasked_asset_only = (AssetID().eq(unmasked_asset.sid))
# Asset used to create our slice. In the cases where this is different
# than `unmasked_asset`, our slice should still have non-missing data
# when used as an input to our custom factor. That is, it should not be
# masked out.
slice_asset = asset_finder.retrieve_asset(sids[slice_column])
returns = Returns(window_length=2, inputs=[self.col])
returns_slice = returns[slice_asset]
returns_results = self.run_pipeline(
Pipeline(columns={'returns': returns}),
start_date,
end_date,
)
returns_results = returns_results['returns'].unstack()
class UsesSlicedInput(CustomFactor):
window_length = 1
inputs = [returns, returns_slice]
def compute(self, today, assets, out, returns, returns_slice):
# Ensure that our mask correctly affects the `returns` input
# and does not affect the `returns_slice` input.
assert returns.shape == (1, 1)
assert returns_slice.shape == (1, 1)
assert returns[0, 0] == \
returns_results.loc[today, unmasked_asset]
assert returns_slice[0, 0] == \
returns_results.loc[today, slice_asset]
columns = {'masked': UsesSlicedInput(mask=unmasked_asset_only)}
# Assertions about the expected data are made in the `compute` function
# of our custom factor above.
self.run_pipeline(Pipeline(columns=columns), start_date, end_date)
def test_slice(self, my_asset_column, window_length_):
"""
Test that slices can be created by indexing into a term, and that they
have the correct shape when used as inputs.
"""
sids = self.sids
my_asset = self.asset_finder.retrieve_asset(self.sids[my_asset_column])
returns = Returns(window_length=2, inputs=[self.col])
returns_slice = returns[my_asset]
class UsesSlicedInput(CustomFactor):
window_length = window_length_
inputs = [returns, returns_slice]
def compute(self, today, assets, out, returns, returns_slice):
# Make sure that our slice is the correct shape (i.e. has only
# one column) and that it has the same values as the original
# returns factor from which it is derived.
assert returns_slice.shape == (self.window_length, 1)
assert returns.shape == (self.window_length, len(sids))
check_arrays(returns_slice[:, 0], returns[:, my_asset_column])
# Assertions about the expected slice data are made in the `compute`
# function of our custom factor above.
self.run_pipeline(
Pipeline(columns={'uses_sliced_input': UsesSlicedInput()}),
self.pipeline_start_date,
self.pipeline_end_date,
)
def test_load_properly_forward_fills(self):
engine = SimplePipelineEngine(
lambda x: self.loader,
self.trading_days,
self.asset_finder,
)
# Cut the dates in half so we need to forward fill some data which
# is not in our window. The results should be computed the same as if
# we had computed across the entire window and then sliced after the
# computation.
dates = self.trading_days[len(self.trading_days) // 2:]
results = engine.run_pipeline(
Pipeline({c.name: c.latest for c in EventDataSet.columns}),
start_date=dates[0],
end_date=dates[-1],
)
for c in EventDataSet.columns:
if c in self.next_value_columns:
self.check_next_value_results(
c,
results[c.name].unstack(),
dates,
)
elif c in self.previous_value_columns:
self.check_previous_value_results(
c,
results[c.name].unstack(),
dates,
)
else:
raise AssertionError("Unexpected column %s." % c)
def test_load_with_trading_calendar(self):
engine = SimplePipelineEngine(
lambda x: self.loader,
self.trading_days,
self.asset_finder,
)
results = engine.run_pipeline(
Pipeline({c.name: c.latest for c in EventDataSet.columns}),
start_date=self.trading_days[0],
end_date=self.trading_days[-1],
)
for c in EventDataSet.columns:
if c in self.next_value_columns:
self.check_next_value_results(
c,
results[c.name].unstack(),
self.trading_days,
)
elif c in self.previous_value_columns:
self.check_previous_value_results(
c,
results[c.name].unstack(),
self.trading_days,
)
else:
raise AssertionError("Unexpected column %s." % c)
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 check_equivalent_terms(self, terms):
self.assertTrue(len(terms) > 1, "Need at least two terms to compare")
pipe = Pipeline(terms)
start, end = self.trading_days[[-10, -1]]
results = self.pipeline_engine.run_pipeline(pipe, start, end)
first_column = results.iloc[:, 0]
for name in terms:
assert_equal(results.loc[:, name], first_column, check_names=False)
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_load_empty(self):
"""
For the case where raw data is empty, make sure we have a result for
all sids, that the dimensions are correct, and that we have the
correct missing value.
"""
raw_events = pd.DataFrame(
columns=["sid",
"timestamp",
"event_date",
"float",
"int",
"datetime",
"string"]
)
next_value_columns = {
EventDataSet.next_datetime: 'datetime',
EventDataSet.next_event_date: 'event_date',
EventDataSet.next_float: 'float',
EventDataSet.next_int: 'int',
EventDataSet.next_string: 'string',
EventDataSet.next_string_custom_missing: 'string'
}
previous_value_columns = {
EventDataSet.previous_datetime: 'datetime',
EventDataSet.previous_event_date: 'event_date',
EventDataSet.previous_float: 'float',
EventDataSet.previous_int: 'int',
EventDataSet.previous_string: 'string',
EventDataSet.previous_string_custom_missing: 'string'
}
loader = EventsLoader(
raw_events, next_value_columns, previous_value_columns
)
engine = SimplePipelineEngine(
lambda x: loader,
self.trading_days,
self.asset_finder,
)
results = engine.run_pipeline(
Pipeline({c.name: c.latest for c in EventDataSet.columns}),
start_date=self.trading_days[0],
end_date=self.trading_days[-1],
)
assets = self.asset_finder.retrieve_all(self.ASSET_FINDER_EQUITY_SIDS)
dates = self.trading_days
expected = self.frame_containing_all_missing_values(
index=pd.MultiIndex.from_product([dates, assets]),
columns=EventDataSet.columns,
)
assert_equal(results, expected)
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 test_simple_beta_matches_regression(self):
run_pipeline = self.run_pipeline
simple_beta = SimpleBeta(target=self.my_asset, regression_length=10)
complex_beta = RollingLinearRegressionOfReturns(
target=self.my_asset,
returns_length=2,
regression_length=10,
).beta
pipe = Pipeline({'simple': simple_beta, 'complex': complex_beta})
results = run_pipeline(
pipe,
self.pipeline_start_date,
self.pipeline_end_date,
)
assert_equal(results['simple'], results['complex'], check_names=False)
def test_masked_single_column_output(self):
"""
Tests for masking custom factors that compute a 1D out.
"""
start_date = self.pipeline_start_date
end_date = self.pipeline_end_date
alternating_mask = (AssetIDPlusDay() % 2).eq(0)
cascading_mask = AssetIDPlusDay() < (self.sids[-1] + start_date.day)
alternating_mask.window_safe = True
cascading_mask.window_safe = True
for mask in (alternating_mask, cascading_mask):
class SingleColumnOutput(CustomFactor):
window_length = 1
inputs = [self.col, mask]
window_safe = True
ndim = 1
def compute(self, today, assets, out, col, mask):
# Because we specified ndim as 1, `out` should always be a
# singleton array but `close` should be a sized based on
# the mask we passed.
assert out.shape == (1, )
assert col.shape == (1, mask.sum())
out[:] = col.sum()
# Since we cannot add single column output factors as pipeline
# columns, we have to test its output through another factor.
class UsesSingleColumnInput(CustomFactor):
window_length = 1
inputs = [self.col, mask, SingleColumnOutput(mask=mask)]
def compute(self, today, assets, out, col, mask,
single_column_output):
# Make sure that `single_column` has the correct value
# based on the masked it used.
assert single_column_output.shape == (1, 1)
single_column_output_value = single_column_output[0][0]
expected_value = where(mask, col, 0).sum()
assert single_column_output_value == expected_value
columns = {'uses_single_column_input': UsesSingleColumnInput()}
# Assertions about the expected shapes of our data are made in the
# `compute` function of our custom factors above.
self.run_pipeline(Pipeline(columns=columns), start_date, end_date)
def test_single_column_output(self):
"""
Tests for custom factors that compute a 1D out.
"""
start_date = self.pipeline_start_date
end_date = self.pipeline_end_date
alternating_mask = (AssetIDPlusDay() % 2).eq(0)
cascading_mask = AssetIDPlusDay() < (self.sids[-1] + start_date.day)
class SingleColumnOutput(CustomFactor):
window_length = 1
inputs = [self.col]
window_safe = True
ndim = 1
def compute(self, today, assets, out, col):
# Because we specified ndim as 1, `out` should be a singleton
# array but `close` should be a regular sized input.
assert out.shape == (1, )
assert col.shape == (1, 3)
out[:] = col.sum()
# Since we cannot add single column output factors as pipeline
# columns, we have to test its output through another factor.
class UsesSingleColumnOutput(CustomFactor):
window_length = 1
inputs = [SingleColumnOutput()]
def compute(self, today, assets, out, single_column_output):
# Make sure that `single_column` has the correct shape. That
# is, it should always have one column regardless of any mask
# passed to `UsesSingleColumnInput`.
assert single_column_output.shape == (1, 1)
for mask in (alternating_mask, cascading_mask):
columns = {
'uses_single_column_output':
UsesSingleColumnOutput(),
'uses_single_column_output_masked':
UsesSingleColumnOutput(mask=mask, ),
}
# Assertions about the expected shapes of our data are made in the
# `compute` function of our custom factors above.
self.run_pipeline(Pipeline(columns=columns), start_date, end_date)
def test_latest(self):
columns = TDS.columns
pipe = Pipeline(
columns={c.name: c.latest for c in columns},
)
cal_slice = slice(20, 40)
dates_to_test = self.calendar[cal_slice]
result = self.engine.run_pipeline(
pipe,
dates_to_test[0],
dates_to_test[-1],
)
for column in columns:
with ignore_pandas_nan_categorical_warning():
col_result = result[column.name].unstack()
expected_col_result = self.expected_latest(column, cal_slice)
assert_frame_equal(col_result, expected_col_result)
def _check_filters(self, evens, odds, first_five, last_three):
pipe = Pipeline(
columns={
'sid': SidFactor(),
'evens': evens,
'odds': odds,
'first_five': first_five,
'last_three': last_three,
},
)
start, end = self.trading_days[[-10, -1]]
results = self.run_pipeline(pipe, start, end).unstack()
sids = results.sid.astype(int64_dtype)
assert_equal(results.evens, ~(sids % 2).astype(bool))
assert_equal(results.odds, (sids % 2).astype(bool))
assert_equal(results.first_five, sids < 5)
assert_equal(results.last_three, sids >= 7)
def test_downsampled_rank(self):
downsampled_rank = self.factor.rank().downsample('month_start')
pipeline = Pipeline({'rank': downsampled_rank})
results_month_start = self.pipeline_engine.run_pipeline(
pipeline,
self.START_DATE,
self.END_DATE,
)
half_way_start = self.HALF_WAY_POINT + pd.Timedelta(days=1)
results_halfway_start = self.pipeline_engine.run_pipeline(
pipeline,
half_way_start,
self.END_DATE,
)
results_month_start_aligned = results_month_start.loc[half_way_start:]
assert_frame_equal(results_month_start_aligned, results_halfway_start)
def test_non_existent_asset(self):
"""
Test that indexing into a term with a non-existent asset raises the
proper exception.
"""
my_asset = Asset(0, exchange="TEST")
returns = Returns(window_length=2, inputs=[self.col])
returns_slice = returns[my_asset]
class UsesSlicedInput(CustomFactor):
window_length = 1
inputs = [returns_slice]
def compute(self, today, assets, out, returns_slice):
pass
with self.assertRaises(NonExistentAssetInTimeFrame):
self.run_pipeline(
Pipeline(columns={'uses_sliced_input': UsesSlicedInput()}),
self.pipeline_start_date,
self.pipeline_end_date,
)
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_correlation_factors(self, returns_length, correlation_length):
"""
Tests for the built-in factors `RollingPearsonOfReturns` and
`RollingSpearmanOfReturns`.
"""
assets = self.assets
my_asset = self.my_asset
my_asset_column = self.my_asset_column
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
returns = Returns(window_length=returns_length)
masks = (self.cascading_mask, self.alternating_mask, NotSpecified)
expected_mask_results = (
self.expected_cascading_mask_result,
self.expected_alternating_mask_result,
self.expected_no_mask_result,
)
for mask, expected_mask in zip(masks, expected_mask_results):
pearson_factor = RollingPearsonOfReturns(
target=my_asset,
returns_length=returns_length,
correlation_length=correlation_length,
mask=mask,
)
spearman_factor = RollingSpearmanOfReturns(
target=my_asset,
returns_length=returns_length,
correlation_length=correlation_length,
mask=mask,
)
columns = {
'pearson_factor': pearson_factor,
'spearman_factor': spearman_factor,
}
pipeline = Pipeline(columns=columns)
if mask is not NotSpecified:
pipeline.add(mask, 'mask')
results = run_pipeline(pipeline, start_date, end_date)
pearson_results = results['pearson_factor'].unstack()
spearman_results = results['spearman_factor'].unstack()
if mask is not NotSpecified:
mask_results = results['mask'].unstack()
check_arrays(mask_results.values, expected_mask)
# 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.
results = run_pipeline(
Pipeline(columns={'returns': returns}),
dates[start_date_index - (correlation_length - 1)],
dates[end_date_index],
)
returns_results = results['returns'].unstack()
# On each day, calculate the expected correlation coefficients
# between the asset we are interested in and each other asset. 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 = returns_results.iloc[
day:day + correlation_length
]
my_asset_returns = todays_returns.iloc[:, my_asset_column]
for asset, other_asset_returns in todays_returns.iteritems():
asset_column = int(asset) - 1
expected_pearson_results[day, asset_column] = pearsonr(
my_asset_returns, other_asset_returns,
)[0]
expected_spearman_results[day, asset_column] = spearmanr(
my_asset_returns, other_asset_returns,
)[0]
expected_pearson_results = DataFrame(
data=where(expected_mask, expected_pearson_results, nan),
index=dates[start_date_index:end_date_index + 1],
columns=assets,
)
assert_frame_equal(pearson_results, expected_pearson_results)
expected_spearman_results = DataFrame(
data=where(expected_mask, expected_spearman_results, nan),
index=dates[start_date_index:end_date_index + 1],
columns=assets,
)
assert_frame_equal(spearman_results, expected_spearman_results)
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_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 initialize(context):
p = attach_pipeline(Pipeline(), 'test', chunks=chunks)
p.add(USEquityPricing.close.latest, 'close')
def initialize(context):
pipeline_close = attach_pipeline(Pipeline(), 'test_close')
pipeline_volume = attach_pipeline(Pipeline(), 'test_volume')
pipeline_close.add(USEquityPricing.close.latest, 'close')
pipeline_volume.add(USEquityPricing.volume.latest, 'volume')
def test_regression_of_returns_factor(self,
returns_length,
regression_length):
"""
Tests for the built-in factor `RollingLinearRegressionOfReturns`.
"""
assets = self.assets
my_asset = self.my_asset
my_asset_column = self.my_asset_column
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']
returns = Returns(window_length=returns_length)
masks = self.cascading_mask, self.alternating_mask, NotSpecified
expected_mask_results = (
self.expected_cascading_mask_result,
self.expected_alternating_mask_result,
self.expected_no_mask_result,
)
for mask, expected_mask in zip(masks, expected_mask_results):
regression_factor = RollingLinearRegressionOfReturns(
target=my_asset,
returns_length=returns_length,
regression_length=regression_length,
mask=mask,
)
columns = {
output: getattr(regression_factor, output)
for output in outputs
}
pipeline = Pipeline(columns=columns)
if mask is not NotSpecified:
pipeline.add(mask, 'mask')
results = run_pipeline(pipeline, start_date, end_date)
if mask is not NotSpecified:
mask_results = results['mask'].unstack()
check_arrays(mask_results.values, expected_mask)
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.
results = run_pipeline(
Pipeline(columns={'returns': returns}),
dates[start_date_index - (regression_length - 1)],
dates[end_date_index],
)
returns_results = results['returns'].unstack()
# On each day, calculate the expected regression results for Y ~ X
# where Y is the asset we are interested in and X is each other
# asset. Each regression is calculated over `regression_length`
# days of data.
for day in range(num_days):
todays_returns = returns_results.iloc[
day:day + regression_length
]
my_asset_returns = todays_returns.iloc[:, my_asset_column]
for asset, other_asset_returns in todays_returns.iteritems():
asset_column = int(asset) - 1
expected_regression_results = linregress(
y=other_asset_returns, x=my_asset_returns,
)
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(
where(expected_mask, expected_output_results[output], nan),
index=dates[start_date_index:end_date_index + 1],
columns=assets,
)
assert_frame_equal(output_result, expected_output_result)
def initialize(context):
attach_pipeline(Pipeline(), 'test')
attach_pipeline(Pipeline(), 'test')
def initialize(context):
attach_pipeline(Pipeline(), 'test')
pipeline_output('test')
raise AssertionError("Shouldn't make it past pipeline_output()")
def make_pipeline():
rsi = RSI()
return Pipeline(columns={
'longs': rsi.top(3),
'shorts': rsi.bottom(3),
}, )
def late_attach(context, data):
attach_pipeline(Pipeline(), 'test')
raise AssertionError("Shouldn't make it past attach_pipeline!")