def test_require_length_greater_than_one(self):
my_asset = Equity(
0,
exchange_info=ExchangeInfo('TEST', 'TEST FULL', 'US'),
)
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,
)
def pipeline_columns_and_mask(self):
factors, universe = self.__make_factors()
from collections import OrderedDict
factors_pipe = OrderedDict()
# Create returns over last n days.
factors_pipe['Returns'] = Returns(inputs=[USEquityPricing.close],
mask=universe,
window_length=5)
# Instantiate ranked factors
for name, f in factors.items():
f.window_safe = True
factors_pipe[name] = f.rank(
mask=universe) #rank 使用相对顺序，而不是绝对值，避免自相似性
predict = BasicFactorRegress(inputs=factors_pipe.values(),
window_length=42,
mask=universe) #进行预测，5天后价格
risk_beta = 0.66 * RollingLinearRegressionOfReturns(
target=symbol(risk_benchmark), # sid(8554),
returns_length=6,
regression_length=21,
# mask=long_short_screen
mask=(universe),
).beta + 0.33 * 1.0
sector = get_sector()
columns = {
'market_beta': risk_beta,
'sector': sector,
'predict': predict,
}
return columns, universe
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,
real_sid='0',
currency='USD',
exchange_info=ExchangeInfo('TEST', 'TEST FULL', 'US'),
)
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_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_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 pipeline_columns_and_mask(self):
universe = make_china_equity_universe(
target_size=2000,
mask=default_china_equity_universe_mask([risk_benchmark]),
max_group_weight=0.01,
smoothing_func=lambda f: f.downsample('month_start'),
)
private_universe = private_universe_mask(
self.portfolio.index) #把当前组合的stock 包含在universe中
last_price = USEquityPricing.close.latest >= 1.0 #大于1元
universe = universe & last_price | private_universe
hurst = HurstExp(window_length=int(252 * 0.25),
mask=universe) #判断动量或反转特性指标
sector = get_sector()
#combined_rank = (
# hurst.rank(mask=universe)
#)
pct_slope = Slope(window_length=21, mask=(universe)) #量和价格加速度
risk_beta = 0.66 * RollingLinearRegressionOfReturns(
target=symbol(risk_benchmark),
returns_length=5,
regression_length=21,
mask=(universe),
).beta + 0.33 * 1.0
returns = Returns(inputs=[USEquityPricing.close],
mask=universe,
window_length=2)
#returns.window_safe = True
#risk_beta.window_safe = True
#m = Markowitz(inputs=[returns,risk_beta],window_length=6,mask=universe)
columns = {
'hurst': hurst.downsample('week_start'),
'price_pct_slope': pct_slope.pslope,
'volume_pct_slope': pct_slope.vslope,
'sector': sector.downsample('month_start'),
'market_beta': risk_beta,
'returns': returns,
}
return columns, universe
def pipeline_columns_and_mask(self):
universe = make_china_equity_universe(
target_size=3000,
mask=default_china_equity_universe_mask([risk_benchmark]),
max_group_weight=0.01,
smoothing_func=lambda f: f.downsample('month_start'),
)
private_universe = private_universe_mask(
self.portfolio.index) # 把当前组合的stock 包含在universe中
last_price = USEquityPricing.close.latest >= 1.0 # 大于1元
universe = (universe & last_price) & ~private_universe
# print "universe:",universe
# Instantiate ranked factors
returns = Returns(inputs=[USEquityPricing.close],
mask=universe,
window_length=2)
risk_beta = 0.66 * RollingLinearRegressionOfReturns(
target=symbol(risk_benchmark), # sid(8554),
returns_length=5,
regression_length=21,
# mask=long_short_screen
mask=(universe),
).beta + 0.33 * 1.0
returns.window_safe = True
risk_beta.window_safe = True
predict = RNNPredict(universe, trigger_date=self.predict_time) # 进行回顾
universe = predict.top(20)
weights = Markowitz(inputs=[returns, risk_beta],
window_length=4,
mask=universe,
trigger_date=self.predict_time) #进行回顾
columns = {
'predict': predict,
'weights': weights,
}
return columns, universe
def pipeline_columns_and_mask(self):
'''
universe = make_china_equity_universe(
target_size=3000,
mask=default_china_equity_universe_mask([RISK_BENCHMARK]),
max_group_weight=0.01,
smoothing_func=lambda f: f.downsample('month_start'),
)
private_universe = private_universe_mask(self.portfolio.index) # 把当前组合的stock 包含在universe中
'''
last_price = USEquityPricing.close.latest >= 1.0 # 大于1元
sector = get_sector()
sector_filter = sector != 0.0
universe = last_price & sector_filter
# print "universe:",universe
# Instantiate ranked factors
returns = Returns(inputs=[USEquityPricing.close],
mask=universe,
window_length=2)
risk_beta = 0.66 * RollingLinearRegressionOfReturns(
target=symbol(RISK_BENCHMARK),
returns_length=5,
regression_length=21,
# mask=long_short_screen
mask=(universe),
).beta + 0.33 * 1.0
returns.window_safe = True
risk_beta.window_safe = True
predict = RNNPredict(universe,
source='predict.csv',
trigger_date=self.predict_time) # 进行回顾
columns = {
'predict': predict,
'market_beta': risk_beta,
'sector': sector,
}
return columns, universe
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_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 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,
)