def marginal_mixture_logcdf(op, value, rng, weights, *components, **kwargs):
# single component
if len(components) == 1:
# Need to broadcast value across mixture axis
mix_axis = -components[0].owner.op.ndim_supp - 1
components_logcdf = logcdf(components[0],
at.expand_dims(value, mix_axis))
else:
components_logcdf = at.stack(
[logcdf(component, value) for component in components],
axis=-1,
)
mix_logcdf = at.logsumexp(at.log(weights) + components_logcdf, axis=-1)
mix_logcdf = check_parameters(
mix_logcdf,
0 <= weights,
weights <= 1,
at.isclose(at.sum(weights, axis=-1), 1),
msg="0 <= weights <= 1, sum(weights) == 1",
)
return mix_logcdf
def marginal_mixture_logcdf(op, value, rng, weights, *components, **kwargs):
# single component
if len(components) == 1:
# Need to broadcast value across mixture axis
mix_axis = -components[0].owner.op.ndim_supp - 1
components_logcdf = logcdf(components[0],
at.expand_dims(value, mix_axis))
else:
components_logcdf = at.stack(
[logcdf(component, value) for component in components],
axis=-1,
)
mix_logcdf = at.logsumexp(at.log(weights) + components_logcdf, axis=-1)
# Squeeze stack dimension
# There is a Aesara bug in squeeze with negative axis
# https://github.com/aesara-devs/aesara/issues/830
# mix_logp = at.squeeze(mix_logp, axis=-1)
mix_logcdf = at.squeeze(mix_logcdf, axis=mix_logcdf.ndim - 1)
mix_logcdf = check_parameters(
mix_logcdf,
0 <= weights,
weights <= 1,
at.isclose(at.sum(weights, axis=-1), 1),
msg="0 <= weights <= 1, sum(weights) == 1",
)
return mix_logcdf
def test_logcdf_helper():
value = at.vector("value")
x = Normal.dist(0, 1)
x_logcdf = logcdf(x, value)
np.testing.assert_almost_equal(x_logcdf.eval({value: [0, 1]}), sp.norm(0, 1).logcdf([0, 1]))
x_logcdf = logcdf(x, [0, 1])
np.testing.assert_almost_equal(x_logcdf.eval(), sp.norm(0, 1).logcdf([0, 1]))
def test_logcdf_helper():
value = at.vector("value")
x = Normal.dist(0, 1, size=2)
x_logp = logcdf(x, value, sum=False)
np.testing.assert_almost_equal(x_logp.eval({value: [0, 1]}), sp.norm(0, 1).logcdf([0, 1]))
x_logp = logcdf(x, [0, 1], sum=False)
np.testing.assert_almost_equal(x_logp.eval(), sp.norm(0, 1).logcdf([0, 1]))
def test_logcdf_transformed_argument():
with Model() as m:
sigma = HalfFlat("sigma")
x = Normal("x", 0, sigma)
Potential("norm_term", -logcdf(x, 1.0))
sigma_value_log = -1.0
sigma_value = np.exp(sigma_value_log)
x_value = 0.5
observed = m.logp_nojac({"sigma_log__": sigma_value_log, "x": x_value})
expected = logp(TruncatedNormal.dist(0, sigma_value, lower=None, upper=1.0), x_value).eval()
assert np.isclose(observed, expected)
