def test_cvm(size=1000):
y_pred = random.uniform(size=size)
y = random.uniform(size=size) > 0.5
sample_weight = random.exponential(size=size)
bin_indices = random.randint(0, 10, size=size)
mask = y == 1
groups_indices = bin_to_group_indices(bin_indices=bin_indices, mask=mask)
cvm1 = bin_based_cvm(y_pred[mask], sample_weight=sample_weight[mask], bin_indices=bin_indices[mask])
cvm2 = group_based_cvm(y_pred, mask=mask, sample_weight=sample_weight, groups_indices=groups_indices)
assert numpy.allclose(cvm1, cvm2)
def test_cvm_sde_limit(size=2000):
""" Checks that in the limit CvM coincides with MSE """
effs = numpy.linspace(0, 1, 2000)
y_pred = random.uniform(size=size)
y = random.uniform(size=size) > 0.5
sample_weight = random.exponential(size=size)
bin_indices = random.randint(0, 10, size=size)
y_pred += bin_indices * random.uniform()
mask = y == 1
val1 = bin_based_cvm(y_pred[mask], sample_weight=sample_weight[mask], bin_indices=bin_indices[mask])
val2 = compute_sde_on_bins(y_pred, mask=mask, bin_indices=bin_indices, target_efficiencies=effs,
sample_weight=sample_weight)
assert numpy.allclose(val1, val2 ** 2, atol=1e-3, rtol=1e-2)
def test_cvm(size=1000):
y_pred = random.uniform(size=size)
y = random.uniform(size=size) > 0.5
sample_weight = random.exponential(size=size)
bin_indices = random.randint(0, 10, size=size)
mask = y == 1
groups_indices = bin_to_group_indices(bin_indices=bin_indices, mask=mask)
cvm1 = bin_based_cvm(y_pred[mask],
sample_weight=sample_weight[mask],
bin_indices=bin_indices[mask])
cvm2 = group_based_cvm(y_pred,
mask=mask,
sample_weight=sample_weight,
groups_indices=groups_indices)
assert numpy.allclose(cvm1, cvm2)
def test_cvm_sde_limit(size=2000):
""" Checks that in the limit CvM coincides with MSE """
effs = numpy.linspace(0, 1, 2000)
y_pred = random.uniform(size=size)
y = random.uniform(size=size) > 0.5
sample_weight = random.exponential(size=size)
bin_indices = random.randint(0, 10, size=size)
y_pred += bin_indices * random.uniform()
mask = y == 1
val1 = bin_based_cvm(y_pred[mask],
sample_weight=sample_weight[mask],
bin_indices=bin_indices[mask])
val2 = compute_sde_on_bins(y_pred,
mask=mask,
bin_indices=bin_indices,
target_efficiencies=effs,
sample_weight=sample_weight)
assert numpy.allclose(val1, val2**2, atol=1e-3, rtol=1e-2)