def test_allowed_missing_doesnt_double_count(self):
# Test that allowed_missing only counts a row as missing one
# observation if it's missing in both the dependent and independent
# variable.
rand = np.random.RandomState(42)
true_betas = np.array([-0.5, 0.0, 0.5, 1.0, 1.5])
independent = as_column(np.linspace(-5.0, 5.0, 30))
noise = as_column(rand.uniform(-0.1, 0.1, 30))
dependents = 1.0 + true_betas * independent + noise
# Each column has three nans in the grid.
dependent_nan_grid = np.array(
[
[0, 1, 1, 1, 0],
[0, 0, 1, 1, 1],
[1, 0, 0, 1, 1],
[1, 1, 0, 0, 1],
[1, 1, 1, 0, 0],
],
dtype=bool,
)
# There are also two nans in the independent data.
independent_nan_grid = np.array([[0], [0], [1], [1], [0]], dtype=bool)
dependents[10:15][dependent_nan_grid] = np.nan
independent[10:15][independent_nan_grid] = np.nan
# With only two allowed missing values, everything should come up nan,
# because column has at least 3 nans in the dependent data.
result2 = vectorized_beta(dependents, independent, allowed_missing=2)
assert_equal(np.isnan(result2),
np.array([True, True, True, True, True]))
# With three allowed missing values, the first and last columns should
# produce a value, because they have nans at the same rows where the
# independent data has nans.
result3 = vectorized_beta(dependents, independent, allowed_missing=3)
assert_equal(np.isnan(result3),
np.array([False, True, True, True, False]))
# With four allowed missing values, everything but the middle column
# should produce a value. The middle column will have 5 nans because
# the dependent nans have no overlap with the independent nans.
result4 = vectorized_beta(dependents, independent, allowed_missing=4)
assert_equal(np.isnan(result4),
np.array([False, False, True, False, False]))
# With five allowed missing values, everything should produce a value.
result5 = vectorized_beta(dependents, independent, allowed_missing=5)
assert_equal(np.isnan(result5),
np.array([False, False, False, False, False]))
def test_allowed_missing_doesnt_double_count(self):
# Test that allowed_missing only counts a row as missing one
# observation if it's missing in both the dependent and independent
# variable.
rand = np.random.RandomState(42)
true_betas = np.array([-0.5, 0.0, 0.5, 1.0, 1.5])
independent = as_column(np.linspace(-5., 5., 30))
noise = as_column(rand.uniform(-.1, .1, 30))
dependents = 1.0 + true_betas * independent + noise
# Each column has three nans in the grid.
dependent_nan_grid = np.array([[0, 1, 1, 1, 0],
[0, 0, 1, 1, 1],
[1, 0, 0, 1, 1],
[1, 1, 0, 0, 1],
[1, 1, 1, 0, 0]], dtype=bool)
# There are also two nans in the independent data.
independent_nan_grid = np.array([[0],
[0],
[1],
[1],
[0]], dtype=bool)
dependents[10:15][dependent_nan_grid] = np.nan
independent[10:15][independent_nan_grid] = np.nan
# With only two allowed missing values, everything should come up nan,
# because column has at least 3 nans in the dependent data.
result2 = vectorized_beta(dependents, independent, allowed_missing=2)
assert_equal(np.isnan(result2),
np.array([True, True, True, True, True]))
# With three allowed missing values, the first and last columns should
# produce a value, because they have nans at the same rows where the
# independent data has nans.
result3 = vectorized_beta(dependents, independent, allowed_missing=3)
assert_equal(np.isnan(result3),
np.array([False, True, True, True, False]))
# With four allowed missing values, everything but the middle column
# should produce a value. The middle column will have 5 nans because
# the dependent nans have no overlap with the independent nans.
result4 = vectorized_beta(dependents, independent, allowed_missing=4)
assert_equal(np.isnan(result4),
np.array([False, False, True, False, False]))
# With five allowed missing values, everything should produce a value.
result5 = vectorized_beta(dependents, independent, allowed_missing=5)
assert_equal(np.isnan(result5),
np.array([False, False, False, False, False]))
def test_produce_nans_when_too_much_missing_data(self, nan_offset):
rand = np.random.RandomState(42)
true_betas = np.array([-0.5, 0.0, 0.5, 1.0, 1.5])
independent = as_column(np.linspace(-5., 5., 30))
noise = as_column(rand.uniform(-.1, .1, 30))
dependents = 1.0 + true_betas * independent + noise
# Write nans in a triangular pattern into the middle of the dependent
# array.
nan_grid = np.array([[1, 0, 0, 0, 0], [1, 1, 0, 0, 0], [1, 1, 1, 0, 0],
[1, 1, 1, 1, 0], [1, 1, 1, 1, 1]],
dtype=bool)
num_nans = nan_grid.sum(axis=0)
# Move the grid around in the parameterized tests. The positions
# shouldn't matter.
dependents[10 + nan_offset:15 + nan_offset][nan_grid] = np.nan
for allowed_missing in range(7):
results = vectorized_beta(dependents, independent, allowed_missing)
for i, expected in enumerate(true_betas):
result = results[i]
expect_nan = num_nans[i] > allowed_missing
true_beta = true_betas[i]
if expect_nan:
self.assertTrue(np.isnan(result))
else:
self.assertTrue(np.abs(result - true_beta) < 0.01)
def test_produce_nans_when_too_much_missing_data(self, nan_offset):
rand = np.random.RandomState(42)
true_betas = np.array([-0.5, 0.0, 0.5, 1.0, 1.5])
independent = as_column(np.linspace(-5., 5., 30))
noise = as_column(rand.uniform(-.1, .1, 30))
dependents = 1.0 + true_betas * independent + noise
# Write nans in a triangular pattern into the middle of the dependent
# array.
nan_grid = np.array([[1, 0, 0, 0, 0],
[1, 1, 0, 0, 0],
[1, 1, 1, 0, 0],
[1, 1, 1, 1, 0],
[1, 1, 1, 1, 1]], dtype=bool)
num_nans = nan_grid.sum(axis=0)
# Move the grid around in the parameterized tests. The positions
# shouldn't matter.
dependents[10 + nan_offset:15 + nan_offset][nan_grid] = np.nan
for allowed_missing in range(7):
results = vectorized_beta(dependents, independent, allowed_missing)
for i, expected in enumerate(true_betas):
result = results[i]
expect_nan = num_nans[i] > allowed_missing
true_beta = true_betas[i]
if expect_nan:
self.assertTrue(np.isnan(result))
else:
self.assertTrue(np.abs(result - true_beta) < 0.01)
def compute(self, today, assets, out, closes, sectors):
res = np.zeros(closes.shape[1])
change_ratio = np.diff(closes, axis=0) / closes[:-1]
latest_sectors = sectors[-1]
stock_in_sector = latest_sectors == self.sector_code
change_ratio_in_sector = change_ratio[:, stock_in_sector]
# epsilon = 0.000001
# nan_locs = np.where(np.isnan(change_ratio_in_sector))[1] # 列
# print(assets[np.unique(nan_locs)])
# change_ratio_in_sector = np.where(np.isnan(change_ratio_in_sector), epsilon, change_ratio_in_sector)
# 行业收益率
sector_returns = nanmean(change_ratio_in_sector, axis=1).reshape(-1, 1)
allowed_missing = int(self.window_length * 0.25)
# 行业内各股票收益率基于行业平均收益率回归得到各股票的β值，即敞口
beta = vectorized_beta(
dependents=change_ratio_in_sector,
independent=sector_returns,
allowed_missing=allowed_missing,
)
# 更新β值，其余部分为0
res[stock_in_sector] = beta
out[:] = res
def compare_with_empyrical(self, dependents, independent):
INFINITY = 1000000 # close enough
result = vectorized_beta(
dependents, independent, allowed_missing=INFINITY,
)
expected = np.array([
empyrical_beta(dependents[:, i].ravel(), independent.ravel())
for i in range(dependents.shape[1])
])
assert_equal(result, expected, array_decimal=7)
return result
def compare_with_empyrical(self, dependents, independent):
INFINITY = 1000000 # close enough
result = vectorized_beta(
dependents, independent, allowed_missing=INFINITY,
)
expected = np.array([
empyrical_beta(dependents[:, i].ravel(), independent.ravel())
for i in range(dependents.shape[1])
])
assert_equal(result, expected, array_decimal=7)
return result
