def test_interval_missing_observations():
with Model() as model:
obs1 = ma.masked_values([1, 2, -1, 4, -1], value=-1)
obs2 = ma.masked_values([-1, -1, 6, -1, 8], value=-1)
rng = aesara.shared(np.random.RandomState(2323), borrow=True)
with pytest.warns(ImputationWarning):
theta1 = Uniform("theta1", 0, 5, observed=obs1, rng=rng)
with pytest.warns(ImputationWarning):
theta2 = Normal("theta2", mu=theta1, observed=obs2, rng=rng)
assert "theta1_observed" in model.named_vars
assert "theta1_missing_interval__" in model.named_vars
assert not hasattr(
model.rvs_to_values[model.named_vars["theta1_observed"]].tag, "transform"
)
prior_trace = sample_prior_predictive(return_inferencedata=False)
# Make sure the observed + missing combined deterministics have the
# same shape as the original observations vectors
assert prior_trace["theta1"].shape[-1] == obs1.shape[0]
assert prior_trace["theta2"].shape[-1] == obs2.shape[0]
# Make sure that the observed values are newly generated samples
assert np.all(np.var(prior_trace["theta1_observed"], 0) > 0.0)
assert np.all(np.var(prior_trace["theta2_observed"], 0) > 0.0)
# Make sure the missing parts of the combined deterministic matches the
# sampled missing and observed variable values
assert np.mean(prior_trace["theta1"][:, obs1.mask] - prior_trace["theta1_missing"]) == 0.0
assert np.mean(prior_trace["theta1"][:, ~obs1.mask] - prior_trace["theta1_observed"]) == 0.0
assert np.mean(prior_trace["theta2"][:, obs2.mask] - prior_trace["theta2_missing"]) == 0.0
assert np.mean(prior_trace["theta2"][:, ~obs2.mask] - prior_trace["theta2_observed"]) == 0.0
assert {"theta1", "theta2"} <= set(prior_trace.keys())
trace = sample(
chains=1, draws=50, compute_convergence_checks=False, return_inferencedata=False
)
assert np.all(0 < trace["theta1_missing"].mean(0))
assert np.all(0 < trace["theta2_missing"].mean(0))
assert "theta1" not in trace.varnames
assert "theta2" not in trace.varnames
# Make sure that the observed values are newly generated samples and that
# the observed and deterministic matche
pp_trace = sample_posterior_predictive(trace, return_inferencedata=False, keep_size=False)
assert np.all(np.var(pp_trace["theta1"], 0) > 0.0)
assert np.all(np.var(pp_trace["theta2"], 0) > 0.0)
assert np.mean(pp_trace["theta1"][:, ~obs1.mask] - pp_trace["theta1_observed"]) == 0.0
assert np.mean(pp_trace["theta2"][:, ~obs2.mask] - pp_trace["theta2_observed"]) == 0.0
def test_list_mvnormals_predictive_sampling_shape(self):
N = 100 # number of data points
K = 3 # number of mixture components
D = 3 # dimensionality of the data
X = MvNormal.dist(np.zeros(D), np.eye(D), size=N).eval()
with Model() as model:
pi = Dirichlet("pi", np.ones(K), shape=(K,))
comp_dist = []
mu = []
packed_chol = []
chol = []
for i in range(K):
mu.append(Normal(f"mu{i}", 0, 10, shape=D))
packed_chol.append(
LKJCholeskyCov(
f"chol_cov_{i}",
eta=2,
n=D,
sd_dist=HalfNormal.dist(2.5, size=D),
compute_corr=False,
)
)
chol.append(expand_packed_triangular(D, packed_chol[i], lower=True))
comp_dist.append(MvNormal.dist(mu=mu[i], chol=chol[i], shape=D))
Mixture("x_obs", pi, comp_dist, observed=X)
n_samples = 20
with model:
prior = sample_prior_predictive(samples=n_samples, return_inferencedata=False)
ppc = sample_posterior_predictive(
[self.get_inital_point(model)], samples=n_samples, return_inferencedata=False
)
assert ppc["x_obs"].shape == (n_samples,) + X.shape
assert prior["x_obs"].shape == (n_samples,) + X.shape
assert prior["mu0"].shape == (n_samples, D)
assert prior["chol_cov_0"].shape == (n_samples, D * (D + 1) // 2)
def test_single_poisson_predictive_sampling_shape(self):
# test the shape broadcasting in mixture random
rng = self.get_random_state()
y = np.concatenate([rng.poisson(5, size=10), rng.poisson(9, size=10)])
with Model() as model:
comp0 = Poisson.dist(mu=np.ones(2))
w0 = Dirichlet("w0", a=np.ones(2), shape=(2,))
like0 = Mixture("like0", w=w0, comp_dists=comp0, observed=y)
comp1 = Poisson.dist(mu=np.ones((20, 2)), shape=(20, 2))
w1 = Dirichlet("w1", a=np.ones(2), shape=(2,))
like1 = Mixture("like1", w=w1, comp_dists=comp1, observed=y)
comp2 = Poisson.dist(mu=np.ones(2))
w2 = Dirichlet("w2", a=np.ones(2), shape=(20, 2))
like2 = Mixture("like2", w=w2, comp_dists=comp2, observed=y)
comp3 = Poisson.dist(mu=np.ones(2), shape=(20, 2))
w3 = Dirichlet("w3", a=np.ones(2), shape=(20, 2))
like3 = Mixture("like3", w=w3, comp_dists=comp3, observed=y)
n_samples = 30
with model:
prior = sample_prior_predictive(samples=n_samples, return_inferencedata=False)
ppc = sample_posterior_predictive(
[self.get_inital_point(model)], samples=n_samples, return_inferencedata=False
)
assert prior["like0"].shape == (n_samples, 20)
assert prior["like1"].shape == (n_samples, 20)
assert prior["like2"].shape == (n_samples, 20)
assert prior["like3"].shape == (n_samples, 20)
assert ppc["like0"].shape == (n_samples, 20)
assert ppc["like1"].shape == (n_samples, 20)
assert ppc["like2"].shape == (n_samples, 20)
assert ppc["like3"].shape == (n_samples, 20)
def test_linear():
lam = -0.78
sig2 = 5e-3
N = 300
dt = 1e-1
sde = lambda x, lam: (lam * x, sig2)
x = floatX(_gen_sde_path(sde, (lam, ), dt, N, 5.0))
z = x + np.random.randn(x.size) * sig2
# build model
with Model() as model:
lamh = Flat("lamh")
xh = EulerMaruyama("xh", dt, sde, (lamh, ), shape=N + 1, initval=x)
Normal("zh", mu=xh, sigma=sig2, observed=z)
# invert
with model:
trace = sample(init="advi+adapt_diag", chains=1)
ppc = sample_posterior_predictive(trace, model=model)
p95 = [2.5, 97.5]
lo, hi = np.percentile(trace[lamh], p95, axis=0)
assert (lo < lam) and (lam < hi)
lo, hi = np.percentile(ppc["zh"], p95, axis=0)
assert ((lo < z) * (z < hi)).mean() > 0.95