def initialize_population(self):
"""Create an initial population from the prior distribution."""
population = []
if self.init_samples is None:
init_rnd = sample_prior_predictive(
self.N,
var_names=[v.name for v in self.model.unobserved_RVs],
model=self.model,
)
for i in range(self.N):
point = Point(
{v.name: init_rnd[v.name][i]
for v in self.variables},
model=self.model)
population.append(self.model.dict_to_array(point))
self.prior_samples = np.array(floatX(population))
elif self.init_samples is not None:
self.prior_samples = np.copy(self.init_samples)
self.samples = np.copy(self.prior_samples)
self.nf_samples = np.copy(self.samples)
self.get_posterior_logp()
self.get_prior_logp()
self.log_weight = self.posterior_logp - self.prior_logp
self.log_evidence = logsumexp(self.log_weight) - np.log(
len(self.log_weight))
self.evidence = np.exp(self.log_evidence)
self.log_weight = self.log_weight - self.log_evidence
self.regularize_weights()
#same as in fitnf but prior~q
self.log_weight_pq_num = self.posterior_logp + 2 * self.prior_logp
self.log_weight_pq_den = 3 * self.prior_logp
self.log_evidence_pq = logsumexp(self.log_weight_pq_num) - logsumexp(
self.log_weight_pq_den)
self.evidence_pq = np.exp(self.log_evidence_pq)
self.log_weight_pq = self.posterior_logp - self.prior_logp - self.log_evidence_pq
self.pq_bw_loss = np.log(
(np.exp(self.posterior_logp) -
np.exp(self.log_evidence_pq +
self.prior_logp))**2) #not actually used yet I think
self.regularize_weights_pq()
#sum of mean loss (p - q*Z_pq)^2 /N for diagnostic purposes
self.log_mean_loss = np.log(
np.mean((np.exp(self.posterior_logp) -
np.exp(self.prior_logp + self.log_evidence_pq))**2))
self.init_weights_cleanup(lambda x: self.prior_logp(x),
lambda x: self.prior_dlogp(x))
self.q_ess = self.calculate_ess(self.log_weight)
self.total_ess = self.calculate_ess(self.sinf_logw)
self.all_logq = np.array([])
self.nf_models = []
self.nf_models_uw = []
def initialize_population(self):
"""Create an initial population from the prior distribution."""
population = []
var_info = OrderedDict()
if self.start is None:
init_rnd = sample_prior_predictive(
self.draws,
var_names=[v.name for v in self.model.unobserved_RVs],
model=self.model,
)
else:
init_rnd = self.start
init = self.model.initial_point
for v in self.variables:
var_info[v.name] = (init[v.name].shape, init[v.name].size)
for i in range(self.draws):
point = Point(
{v.name: init_rnd[v.name][i]
for v in self.variables},
model=self.model)
population.append(DictToArrayBijection.map(point).data)
self.posterior = np.array(floatX(population))
self.var_info = var_info
def initialize_population(self):
"""Create an initial population from the prior distribution."""
population = []
var_info = OrderedDict()
init_rnd = sample_prior_predictive(
self.draws,
var_names=[v.name for v in self.model.unobserved_RVs],
model=self.model,
)
init = self.model.test_point
for v in self.variables:
var_info[v.name] = (init[v.name].shape, init[v.name].size)
for i in range(self.draws):
point = Point({v.name: init_rnd[v.name][i] for v in self.variables}, model=self.model)
population.append(self.model.dict_to_array(point))
self.nf_samples = np.array(floatX(population))
self.live_points = np.array(floatX(population))
self.var_info = var_info
self.posterior = np.empty((0, np.shape(self.nf_samples)[1]))
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_interval__" in model.named_vars
assert "theta1_missing_interval__" in model.named_vars
assert isinstance(
model.rvs_to_values[model.named_vars["theta1_observed"]].tag.transform, Interval
)
prior_trace = sample_prior_predictive()
# 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)
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)
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_missing(data):
with Model() as model:
x = Normal("x", 1, 1)
with pytest.warns(ImputationWarning):
y = Normal("y", x, 1, observed=data)
assert "y_missing" in model.named_vars
test_point = model.initial_point
assert not np.isnan(model.logp(test_point))
with model:
prior_trace = sample_prior_predictive()
assert {"x", "y"} <= set(prior_trace.keys())
def test_missing_dual_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)
beta1 = Normal("beta1", 1, 1)
beta2 = Normal("beta2", 2, 1)
latent = Normal("theta", size=5)
with pytest.warns(ImputationWarning):
ovar1 = Normal("o1", mu=beta1 * latent, observed=obs1)
with pytest.warns(ImputationWarning):
ovar2 = Normal("o2", mu=beta2 * latent, observed=obs2)
prior_trace = sample_prior_predictive()
assert {"beta1", "beta2", "theta", "o1", "o2"} <= set(prior_trace.keys())
# TODO: Assert something
trace = sample(chains=1, draws=50)
def test_missing_with_predictors():
predictors = array([0.5, 1, 0.5, 2, 0.3])
data = ma.masked_values([1, 2, -1, 4, -1], value=-1)
with Model() as model:
x = Normal("x", 1, 1)
with pytest.warns(ImputationWarning):
y = Normal("y", x * predictors, 1, observed=data)
assert "y_missing" in model.named_vars
test_point = model.initial_point
assert not np.isnan(model.logp(test_point))
with model:
prior_trace = sample_prior_predictive()
assert {"x", "y"} <= set(prior_trace.keys())