def test_sum_normal(self):
with pm.Model() as model:
a = pm.Normal("a", sigma=0.2)
b = pm.Normal("b", mu=a)
trace = pm.sample()
with model:
# test list input
ppc0 = pm.sample_posterior_predictive([model.test_point], samples=10)
assert ppc0 == {}
ppc = pm.sample_posterior_predictive(trace, samples=1000, var_names=["b"])
assert len(ppc) == 1
assert ppc["b"].shape == (1000,)
scale = np.sqrt(1 + 0.2 ** 2)
_, pval = stats.kstest(ppc["b"], stats.norm(scale=scale).cdf)
assert pval > 0.001
# test list input
ppc0 = pm.fast_sample_posterior_predictive([model.test_point], samples=10)
assert ppc0 == {}
ppc = pm.fast_sample_posterior_predictive(trace, samples=1000, var_names=["b"])
assert len(ppc) == 1
assert ppc["b"].shape == (1000,)
scale = np.sqrt(1 + 0.2 ** 2)
_, pval = stats.kstest(ppc["b"], stats.norm(scale=scale).cdf)
assert pval > 0.001
def test_exceptions(self, caplog):
with pm.Model() as model:
mu = pm.Normal("mu", 0.0, 1.0)
a = pm.Normal("a", mu=mu, sigma=1, observed=np.array([0.5, 0.2]))
trace = pm.sample()
with model:
with pytest.raises(IncorrectArgumentsError):
ppc = pm.sample_posterior_predictive(trace,
samples=10,
keep_size=True)
with pytest.raises(IncorrectArgumentsError):
ppc = pm.fast_sample_posterior_predictive(trace,
samples=10,
keep_size=True)
# Not for fast_sample_posterior_predictive
with pytest.raises(IncorrectArgumentsError):
ppc = pm.sample_posterior_predictive(trace,
size=4,
keep_size=True)
with pytest.raises(IncorrectArgumentsError):
ppc = pm.sample_posterior_predictive(trace,
vars=[a],
var_names=["a"])
# test wrong type argument
bad_trace = {"mu": stats.norm.rvs(size=1000)}
with pytest.raises(TypeError):
ppc = pm.sample_posterior_predictive(bad_trace)
with pytest.raises(TypeError):
ppc = pm.fast_sample_posterior_predictive(bad_trace)
def test_vector_observed(self):
with pm.Model() as model:
mu = pm.Normal("mu", mu=0, sigma=1)
a = pm.Normal("a", mu=mu, sigma=1, observed=np.array([0.0, 1.0]))
trace = pm.sample()
with model:
# test list input
ppc0 = pm.sample_posterior_predictive([model.test_point], samples=10)
ppc = pm.sample_posterior_predictive(trace, samples=12, var_names=[])
assert len(ppc) == 0
ppc = pm.sample_posterior_predictive(trace, samples=12, var_names=["a"])
assert "a" in ppc
assert ppc["a"].shape == (12, 2)
ppc = pm.sample_posterior_predictive(trace, samples=10, var_names=["a"], size=4)
assert "a" in ppc
assert ppc["a"].shape == (10, 4, 2)
# now with fast version
# test list input
ppc0 = pm.fast_sample_posterior_predictive([model.test_point], samples=10)
ppc = pm.fast_sample_posterior_predictive(trace, samples=12, var_names=[])
assert len(ppc) == 0
ppc = pm.fast_sample_posterior_predictive(trace, samples=12, var_names=["a"])
assert "a" in ppc
assert ppc["a"].shape == (12, 2)
def test_sample(self):
x = np.random.normal(size=100)
y = x + np.random.normal(scale=1e-2, size=100)
x_pred = np.linspace(-3, 3, 200)
x_shared = theano.shared(x)
with pm.Model() as model:
b = pm.Normal("b", 0.0, 10.0)
pm.Normal("obs", b * x_shared, np.sqrt(1e-2), observed=y)
prior_trace0 = pm.sample_prior_predictive(1000)
trace = pm.sample(1000, init=None, tune=1000, chains=1)
pp_trace0 = pm.sample_posterior_predictive(trace, 1000)
pp_trace01 = pm.fast_sample_posterior_predictive(trace, 1000)
x_shared.set_value(x_pred)
prior_trace1 = pm.sample_prior_predictive(1000)
pp_trace1 = pm.sample_posterior_predictive(trace, 1000)
pp_trace11 = pm.fast_sample_posterior_predictive(trace, 1000)
assert prior_trace0["b"].shape == (1000,)
assert prior_trace0["obs"].shape == (1000, 100)
np.testing.assert_allclose(x, pp_trace0["obs"].mean(axis=0), atol=1e-1)
np.testing.assert_allclose(x, pp_trace01["obs"].mean(axis=0), atol=1e-1)
assert prior_trace1["b"].shape == (1000,)
assert prior_trace1["obs"].shape == (1000, 200)
np.testing.assert_allclose(x_pred, pp_trace1["obs"].mean(axis=0), atol=1e-1)
np.testing.assert_allclose(x_pred, pp_trace11["obs"].mean(axis=0), atol=1e-1)
def test_normal_scalar(self):
nchains = 2
ndraws = 500
with pm.Model() as model:
mu = pm.Normal("mu", 0.0, 1.0)
a = pm.Normal("a", mu=mu, sigma=1, observed=0.0)
trace = pm.sample(draws=ndraws, chains=nchains)
with model:
# test list input
ppc0 = pm.sample_posterior_predictive([model.test_point],
samples=10)
ppc0 = pm.fast_sample_posterior_predictive([model.test_point],
samples=10)
# deprecated argument is not introduced to fast version [2019/08/20:rpg]
with pytest.warns(DeprecationWarning):
ppc = pm.sample_posterior_predictive(trace, vars=[a])
# test empty ppc
ppc = pm.sample_posterior_predictive(trace, var_names=[])
assert len(ppc) == 0
ppc = pm.fast_sample_posterior_predictive(trace, var_names=[])
assert len(ppc) == 0
# test keep_size parameter
ppc = pm.sample_posterior_predictive(trace, keep_size=True)
assert ppc["a"].shape == (nchains, ndraws)
ppc = pm.fast_sample_posterior_predictive(trace, keep_size=True)
assert ppc["a"].shape == (nchains, ndraws)
# test keep_size parameter and idata input
idata = az.from_pymc3(trace)
ppc = pm.sample_posterior_predictive(idata, keep_size=True)
assert ppc["a"].shape == (nchains, ndraws)
ppc = pm.fast_sample_posterior_predictive(trace, keep_size=True)
assert ppc["a"].shape == (nchains, ndraws)
# test default case
ppc = pm.sample_posterior_predictive(trace, var_names=["a"])
assert "a" in ppc
assert ppc["a"].shape == (nchains * ndraws, )
# mu's standard deviation may have changed thanks to a's observed
_, pval = stats.kstest(ppc["a"] - trace["mu"],
stats.norm(loc=0, scale=1).cdf)
assert pval > 0.001
# test default case
ppc = pm.fast_sample_posterior_predictive(trace, var_names=["a"])
assert "a" in ppc
assert ppc["a"].shape == (nchains * ndraws, )
# mu's standard deviation may have changed thanks to a's observed
_, pval = stats.kstest(ppc["a"] - trace["mu"],
stats.norm(loc=0, scale=1).cdf)
assert pval > 0.001
# size argument not introduced to fast version [2019/08/20:rpg]
with model:
ppc = pm.sample_posterior_predictive(trace,
size=5,
var_names=["a"])
assert ppc["a"].shape == (nchains * ndraws, 5)
def test_density_dist_without_random_not_sampleable(self):
with pm.Model() as model:
mu = pm.Normal('mu', 0, 1)
normal_dist = pm.Normal.dist(mu, 1)
pm.DensityDist('density_dist', normal_dist.logp, observed=np.random.randn(100))
trace = pm.sample(100)
samples = 500
with pytest.raises(ValueError):
pm.sample_posterior_predictive(trace, samples=samples, model=model, size=100)
with pytest.raises((TypeError, ValueError)):
pm.fast_sample_posterior_predictive(trace, samples=samples, model=model, size=100)
def test_potentials_warning(self):
warning_msg = "The effect of Potentials on other parameters is ignored during"
with pm.Model() as m:
a = pm.Normal("a", 0, 1)
p = pm.Potential("p", a + 1)
obs = pm.Normal("obs", a, 1, observed=5)
trace = az.from_dict({"a": np.random.rand(10)})
with m:
with pytest.warns(UserWarning, match=warning_msg):
pm.sample_posterior_predictive(trace, samples=5)
with pytest.warns(UserWarning, match=warning_msg):
pm.fast_sample_posterior_predictive(trace, samples=5)
def test_normal_vector(self, caplog):
with pm.Model() as model:
mu = pm.Normal("mu", 0.0, 1.0)
a = pm.Normal("a", mu=mu, sigma=1, observed=np.array([0.5, 0.2]))
trace = pm.sample()
with model:
# test list input
ppc0 = pm.sample_posterior_predictive([model.test_point],
samples=10)
ppc = pm.sample_posterior_predictive(trace,
samples=12,
var_names=[])
assert len(ppc) == 0
# test list input
ppc0 = pm.fast_sample_posterior_predictive([model.test_point],
samples=10)
ppc = pm.fast_sample_posterior_predictive(trace,
samples=12,
var_names=[])
assert len(ppc) == 0
# test keep_size parameter
ppc = pm.sample_posterior_predictive(trace, keep_size=True)
assert ppc["a"].shape == (trace.nchains, len(trace), 2)
with pytest.warns(UserWarning):
ppc = pm.sample_posterior_predictive(trace,
samples=12,
var_names=["a"])
assert "a" in ppc
assert ppc["a"].shape == (12, 2)
# test keep_size parameter
ppc = pm.fast_sample_posterior_predictive(trace, keep_size=True)
assert ppc["a"].shape == (trace.nchains, len(trace), 2)
with pytest.warns(UserWarning):
ppc = pm.fast_sample_posterior_predictive(trace,
samples=12,
var_names=["a"])
assert "a" in ppc
assert ppc["a"].shape == (12, 2)
# size unsupported by fast_ version argument. [2019/08/19:rpg]
ppc = pm.sample_posterior_predictive(trace,
samples=10,
var_names=["a"],
size=4)
assert "a" in ppc
assert ppc["a"].shape == (10, 4, 2)
def test_sample_from_xarray_posterior_fast(self,
point_list_arg_bug_fixture):
pmodel, trace = point_list_arg_bug_fixture
idat = az.from_pymc3(trace)
with pmodel:
pp = pm.fast_sample_posterior_predictive(idat.posterior,
var_names=["d"])
def test_deterministic_of_observed(self):
meas_in_1 = pm.theanof.floatX(2 + 4 * np.random.randn(100))
meas_in_2 = pm.theanof.floatX(5 + 4 * np.random.randn(100))
with pm.Model() as model:
mu_in_1 = pm.Normal("mu_in_1", 0, 1)
sigma_in_1 = pm.HalfNormal("sd_in_1", 1)
mu_in_2 = pm.Normal("mu_in_2", 0, 1)
sigma_in_2 = pm.HalfNormal("sd__in_2", 1)
in_1 = pm.Normal("in_1", mu_in_1, sigma_in_1, observed=meas_in_1)
in_2 = pm.Normal("in_2", mu_in_2, sigma_in_2, observed=meas_in_2)
out_diff = in_1 + in_2
pm.Deterministic("out", out_diff)
trace = pm.sample(100)
ppc_trace = pm.trace_to_dataframe(
trace, varnames=[n for n in trace.varnames
if n != "out"]).to_dict("records")
with pytest.warns(DeprecationWarning):
ppc = pm.sample_posterior_predictive(
model=model,
trace=ppc_trace,
samples=len(ppc_trace),
vars=(model.deterministics + model.basic_RVs),
)
rtol = 1e-5 if theano.config.floatX == "float64" else 1e-3
assert np.allclose(ppc["in_1"] + ppc["in_2"],
ppc["out"],
rtol=rtol)
ppc = pm.sample_posterior_predictive(
model=model,
trace=ppc_trace,
samples=len(ppc_trace),
var_names=[
var.name
for var in (model.deterministics + model.basic_RVs)
],
)
rtol = 1e-5 if theano.config.floatX == "float64" else 1e-3
assert np.allclose(ppc["in_1"] + ppc["in_2"],
ppc["out"],
rtol=rtol)
ppc = pm.fast_sample_posterior_predictive(
model=model,
trace=ppc_trace,
samples=len(ppc_trace),
var_names=[
var.name
for var in (model.deterministics + model.basic_RVs)
],
)
rtol = 1e-5 if theano.config.floatX == "float64" else 1e-3
assert np.allclose(ppc["in_1"] + ppc["in_2"],
ppc["out"],
rtol=rtol)
def sample_all(self,
*,
model: pm.Model = None,
var_names: List[str],
**sampler_kwargs) -> arviz.InferenceData:
"""
Sample the model and return the trace.
Parameters
----------
model : optional
A model previously created using `self.build_model()`.
Build a new model if None (default)
var_names: List[str]
Variables names passed to `pm.fast_sample_posterior_predictive`
**sampler_kwargs : dict
Additional arguments to `pm.sample`
"""
if model is None:
model = self.build_model()
with model:
prior_checks = pm.sample_prior_predictive()
trace = pm.sample(return_inferencedata=False, **sampler_kwargs)
post_checks = pm.fast_sample_posterior_predictive(
trace, var_names=var_names)
return arviz.from_pymc3(
trace=trace,
prior=prior_checks,
posterior_predictive=post_checks,
model=model,
)
def test_shared_data_as_index(self):
"""
Allow pm.Data to be used for index variables, i.e with integers as well as floats.
See https://github.com/pymc-devs/pymc3/issues/3813
"""
with pm.Model() as model:
index = pm.Data("index", [2, 0, 1, 0, 2])
y = pm.Data("y", [1.0, 2.0, 3.0, 2.0, 1.0])
alpha = pm.Normal("alpha", 0, 1.5, shape=3)
pm.Normal("obs", alpha[index], np.sqrt(1e-2), observed=y)
prior_trace = pm.sample_prior_predictive(1000, var_names=["alpha"])
trace = pm.sample(1000, init=None, tune=1000, chains=1)
# Predict on new data
new_index = np.array([0, 1, 2])
new_y = [5.0, 6.0, 9.0]
with model:
pm.set_data(new_data={"index": new_index, "y": new_y})
pp_trace = pm.sample_posterior_predictive(
trace, 1000, var_names=["alpha", "obs"])
pp_tracef = pm.fast_sample_posterior_predictive(
trace, 1000, var_names=["alpha", "obs"])
assert prior_trace["alpha"].shape == (1000, 3)
assert trace["alpha"].shape == (1000, 3)
assert pp_trace["alpha"].shape == (1000, 3)
assert pp_trace["obs"].shape == (1000, 3)
assert pp_tracef["alpha"].shape == (1000, 3)
assert pp_tracef["obs"].shape == (1000, 3)
def test_point_list_arg_bug_fspp(self, point_list_arg_bug_fixture):
pmodel, trace = point_list_arg_bug_fixture
with pmodel:
pp = pm.fast_sample_posterior_predictive(
[trace[15]],
var_names=['d']
)
def test_model_shared_variable(self):
x = np.random.randn(100)
y = x > 0
x_shared = aesara.shared(x)
y_shared = aesara.shared(y)
with pm.Model() as model:
coeff = pm.Normal("x", mu=0, sd=1)
logistic = pm.Deterministic("p", pm.math.sigmoid(coeff * x_shared))
obs = pm.Bernoulli("obs", p=logistic, observed=y_shared)
trace = pm.sample(100)
x_shared.set_value([-1, 0, 1.0])
y_shared.set_value([0, 0, 0])
samples = 100
with model:
post_pred = pm.sample_posterior_predictive(
trace, samples=samples, var_names=["p", "obs"]
)
expected_p = np.array([logistic.eval({coeff: val}) for val in trace["x"][:samples]])
assert post_pred["obs"].shape == (samples, 3)
npt.assert_allclose(post_pred["p"], expected_p)
# fast version
samples = 100
with model:
post_pred = pm.fast_sample_posterior_predictive(
trace, samples=samples, var_names=["p", "obs"]
)
expected_p = np.array([logistic.eval({coeff: val}) for val in trace["x"][:samples]])
assert post_pred["obs"].shape == (samples, 3)
npt.assert_allclose(post_pred["p"], expected_p)
def test_deterministic_of_observed(self):
meas_in_1 = pm.theanof.floatX(2 + 4 * np.random.randn(10))
meas_in_2 = pm.theanof.floatX(5 + 4 * np.random.randn(10))
nchains = 2
with pm.Model() as model:
mu_in_1 = pm.Normal("mu_in_1", 0, 1)
sigma_in_1 = pm.HalfNormal("sd_in_1", 1)
mu_in_2 = pm.Normal("mu_in_2", 0, 1)
sigma_in_2 = pm.HalfNormal("sd__in_2", 1)
in_1 = pm.Normal("in_1", mu_in_1, sigma_in_1, observed=meas_in_1)
in_2 = pm.Normal("in_2", mu_in_2, sigma_in_2, observed=meas_in_2)
out_diff = in_1 + in_2
pm.Deterministic("out", out_diff)
trace = pm.sample(100, chains=nchains)
np.random.seed(0)
with pytest.warns(DeprecationWarning):
ppc = pm.sample_posterior_predictive(
model=model,
trace=trace,
samples=len(trace) * nchains,
vars=(model.deterministics + model.basic_RVs),
)
rtol = 1e-5 if theano.config.floatX == "float64" else 1e-4
npt.assert_allclose(ppc["in_1"] + ppc["in_2"],
ppc["out"],
rtol=rtol)
np.random.seed(0)
ppc = pm.sample_posterior_predictive(
model=model,
trace=trace,
samples=len(trace) * nchains,
var_names=[
var.name
for var in (model.deterministics + model.basic_RVs)
],
)
npt.assert_allclose(ppc["in_1"] + ppc["in_2"],
ppc["out"],
rtol=rtol)
np.random.seed(0)
ppc = pm.fast_sample_posterior_predictive(
model=model,
trace=trace,
samples=len(trace) * nchains,
var_names=[
var.name
for var in (model.deterministics + model.basic_RVs)
],
)
npt.assert_allclose(ppc["in_1"] + ppc["in_2"],
ppc["out"],
rtol=rtol)
def test_sample(self):
x = np.random.normal(size=100)
y = x + np.random.normal(scale=1e-2, size=100)
x_pred = np.linspace(-3, 3, 200, dtype='float32')
with pm.Model():
x_shared = pm.Data('x_shared', x)
b = pm.Normal('b', 0., 10.)
pm.Normal('obs', b * x_shared, np.sqrt(1e-2), observed=y)
prior_trace0 = pm.sample_prior_predictive(1000)
trace = pm.sample(1000, init=None, tune=1000, chains=1)
pp_trace0 = pm.sample_posterior_predictive(trace, 1000)
pp_trace01 = pm.fast_sample_posterior_predictive(trace, 1000)
x_shared.set_value(x_pred)
pp_trace1 = pm.sample_posterior_predictive(trace, samples=1000)
pp_trace11 = pm.fast_sample_posterior_predictive(trace,
samples=1000)
prior_trace1 = pm.sample_prior_predictive(1000)
assert prior_trace0['b'].shape == (1000, )
assert prior_trace0['obs'].shape == (1000, 100)
assert prior_trace1['obs'].shape == (1000, 200)
assert pp_trace0['obs'].shape == (1000, 100)
assert pp_trace01['obs'].shape == (1000, 100)
np.testing.assert_allclose(x, pp_trace0['obs'].mean(axis=0), atol=1e-1)
np.testing.assert_allclose(x,
pp_trace01['obs'].mean(axis=0),
atol=1e-1)
assert pp_trace1['obs'].shape == (1000, 200)
assert pp_trace11['obs'].shape == (1000, 200)
np.testing.assert_allclose(x_pred,
pp_trace1['obs'].mean(axis=0),
atol=1e-1)
np.testing.assert_allclose(x_pred,
pp_trace11['obs'].mean(axis=0),
atol=1e-1)
def test_mixture_random_shape_fast():
# test the shape broadcasting in mixture random
y = np.concatenate([nr.poisson(5, size=10),
nr.poisson(9, size=10)])
with pm.Model() as m:
comp0 = pm.Poisson.dist(mu=np.ones(2))
w0 = pm.Dirichlet('w0', a=np.ones(2))
like0 = pm.Mixture('like0',
w=w0,
comp_dists=comp0,
observed=y)
comp1 = pm.Poisson.dist(mu=np.ones((20, 2)),
shape=(20, 2))
w1 = pm.Dirichlet('w1', a=np.ones(2))
like1 = pm.Mixture('like1',
w=w1,
comp_dists=comp1,
observed=y)
comp2 = pm.Poisson.dist(mu=np.ones(2))
w2 = pm.Dirichlet('w2',
a=np.ones(2),
shape=(20, 2))
like2 = pm.Mixture('like2',
w=w2,
comp_dists=comp2,
observed=y)
comp3 = pm.Poisson.dist(mu=np.ones(2),
shape=(20, 2))
w3 = pm.Dirichlet('w3',
a=np.ones(2),
shape=(20, 2))
like3 = pm.Mixture('like3',
w=w3,
comp_dists=comp3,
observed=y)
rand0, rand1, rand2, rand3 = draw_values([like0, like1, like2, like3],
point=m.test_point,
size=100)
assert rand0.shape == (100, 20)
assert rand1.shape == (100, 20)
assert rand2.shape == (100, 20)
assert rand3.shape == (100, 20)
# I *think* that the mixture means that this is not going to work,
# but I could be wrong. [2019/08/22:rpg]
with m:
ppc = pm.fast_sample_posterior_predictive([m.test_point], samples=200)
assert ppc['like0'].shape == (200, 20)
assert ppc['like1'].shape == (200, 20)
assert ppc['like2'].shape == (200, 20)
assert ppc['like3'].shape == (200, 20)
def forecast_election(self,
idata: arviz.InferenceData) -> arviz.InferenceData:
"""
Generate out-of-sample predictions for ``election_to_predict`` specified in ``__init__``.
Parameters
----------
idata: arviz.InferenceData
Posterior trace generated by ``self.sample_all`` on the training dataset.
The dataset used for predictions is generated automatically: one observation for each
of the days in ``self.coords["countdown"]``. The corresponding values of predictors are
handled automatically.
"""
new_dates, oos_data = self._generate_oos_data(idata)
oos_data = self._join_with_continuous_predictors(oos_data)
forecast_data_index = pd.DataFrame(
data=0, # just a placeholder
index=pd.MultiIndex.from_frame(oos_data),
columns=self.parties_complete,
)
forecast_data = forecast_data_index.reset_index()
PREDICTION_COORDS = {"observations": new_dates}
PREDICTION_DIMS = {
"latent_popularity": ["observations", "parties_complete"],
"noisy_popularity": ["observations", "parties_complete"],
"N_approve": ["observations", "parties_complete"],
}
forecast_model = self.build_model(
polls=forecast_data,
continuous_predictors=forecast_data,
)
with forecast_model:
ppc = pm.fast_sample_posterior_predictive(
idata,
var_names=[
"party_intercept",
"latent_popularity",
"noisy_popularity",
"N_approve",
"latent_pop_t0",
"R",
],
)
ppc = arviz.from_pymc3_predictions(
ppc,
idata_orig=idata,
inplace=False,
coords=PREDICTION_COORDS,
dims=PREDICTION_DIMS,
)
return ppc
def test_density_dist_with_random_sampleable_failure(self, shape):
with pm.Model() as model:
mu = pm.Normal('mu', 0, 1)
normal_dist = pm.Normal.dist(mu, 1, shape=shape)
pm.DensityDist(
'density_dist',
normal_dist.logp,
observed=np.random.randn(100, *shape),
shape=shape,
random=normal_dist.random,
wrap_random_with_dist_shape=False
)
trace = pm.sample(100)
samples = 500
with pytest.raises(RuntimeError):
pm.sample_posterior_predictive(trace, samples=samples, model=model, size=100)
with pytest.raises((TypeError, RuntimeError)):
pm.fast_sample_posterior_predictive(trace, samples=samples, model=model, size=100)
def sample_mod(
self,
posterior_draws = 2000, # this is not enough
post_pred_draws = 1000,
prior_pred_draws = 1000,
random_seed = 42,
chains = 2):
"""Sample the posterior, the posterior predictive and the prior predictive distribution.
Args:
posterior_draws (int, optional): Number of draws for the posterior. Defaults to 2000.
prior_pred_draws (int, optional): Number of draws for the prior predictive distribution. Defaults to 1000.
post_pred_draws (int, optional): Number of draws from the posterior predictive distribution. Defaults to 1000.
random_seed (int, optional): Random seed for ensuring reproducibility. Defaults to 42.
chains (int, optional): Number of chains used for sampling the posterior. Defaults to 2.
Example:
Pc.sample_mod(posterior_draws = 3000, post_pred_draws = 1500, prior_pred_draws = 55, random_seed = 13, chains = 4)
"""
# we need these for later
self.posterior_draws = posterior_draws
self.post_pred_draws = post_pred_draws
self.prior_pred_draws = prior_pred_draws
with self.model:
self.trace = pm.sample(
return_inferencedata = False,
draws = posterior_draws,
target_accept = .99,
random_seed = random_seed,
chains = chains) #hard set to 42
self.post_pred = pm.sample_posterior_predictive(self.trace, samples = post_pred_draws)
self.prior_pred = pm.sample_prior_predictive(samples = prior_pred_draws)
self.m_idata = az.from_pymc3(trace = self.trace, posterior_predictive=self.post_pred, prior=self.prior_pred)
with self.model:
pm.set_data({"t1_shared": self.t1_test})
pm.set_data({"t2_shared": self.t2_test})
pm.set_data({"idx_shared": self.idx_test})
pm.set_data({"t3_shared": np.array(self.t3_test)})
predictions = pm.fast_sample_posterior_predictive(
self.m_idata.posterior
)
az.from_pymc3_predictions(
predictions,
idata_orig = self.m_idata,
coords = {'idx': self.test[self.index].values},
inplace = True)
def test_multivariate2(self):
# Added test for issue #3271
mn_data = np.random.multinomial(n=100, pvals=[1 / 6.0] * 6, size=10)
with pm.Model() as dm_model:
probs = pm.Dirichlet("probs", a=np.ones(6), shape=6)
obs = pm.Multinomial("obs", n=100, p=probs, observed=mn_data)
burned_trace = pm.sample(20, tune=10, cores=1)
sim_priors = pm.sample_prior_predictive(samples=20, model=dm_model)
sim_ppc = pm.sample_posterior_predictive(burned_trace, samples=20, model=dm_model)
assert sim_priors["probs"].shape == (20, 6)
assert sim_priors["obs"].shape == (20,) + obs.distribution.shape
assert sim_ppc["obs"].shape == (20,) + obs.distribution.shape
sim_ppc = pm.fast_sample_posterior_predictive(burned_trace, samples=20, model=dm_model)
assert sim_ppc["obs"].shape == (20,) + obs.distribution.shape
def predict(self): ## make this work for only one.
with self.model:
pm.set_data({"t1_shared": self.t1_test})
pm.set_data({"t2_shared": self.t2_test})
pm.set_data({"idx_shared": self.idx_test})
pm.set_data({"t3_shared": np.array(self.t3_test)})
predictions = pm.fast_sample_posterior_predictive(
self.m_idata.posterior
)
az.from_pymc3_predictions(
predictions,
idata_orig = self.m_idata,
coords = {'idx': self.test[self.index].values},
inplace = True)
def test_model_not_drawable_prior(self):
data = np.random.poisson(lam=10, size=200)
model = pm.Model()
with model:
mu = pm.HalfFlat("sigma")
pm.Poisson("foo", mu=mu, observed=data)
trace = pm.sample(tune=1000)
with model:
with pytest.raises(ValueError) as excinfo:
pm.sample_prior_predictive(50)
assert "Cannot sample" in str(excinfo.value)
samples = pm.sample_posterior_predictive(trace, 40)
assert samples["foo"].shape == (40, 200)
samples = pm.fast_sample_posterior_predictive(trace, 40)
assert samples["foo"].shape == (40, 200)
def sample_posterior_predictive(self, kind='pymc', fast=False, **kwargs):
""" Sample posterior predictive for
base class self.sample_posterior_predictive_kws or passed kwargs
Option to use pm.fast_sample_posterior_predictive()
"""
random_seed = kwargs.pop('random_seed', self.sample_kws['random_seed'])
if self.model is None:
self.build()
with self.model:
if fast:
self._posterior_predictive = pm.fast_sample_posterior_predictive(
self.trace, random_seed=random_seed, **kwargs)
else:
self._posterior_predictive = pm.sample_posterior_predictive(
self.trace, random_seed=random_seed, **kwargs)
return None
def test_density_dist_with_random_sampleable_handcrafted_success_fast(self):
with pm.Model() as model:
mu = pm.Normal('mu', 0, 1)
normal_dist = pm.Normal.dist(mu, 1)
rvs = pm.Normal.dist(mu, 1, shape=100).random
obs = pm.DensityDist(
'density_dist',
normal_dist.logp,
observed=np.random.randn(100),
random=rvs,
wrap_random_with_dist_shape=False
)
trace = pm.sample(100)
samples = 500
size = 100
ppc = pm.fast_sample_posterior_predictive(trace, samples=samples, model=model, size=size)
assert ppc['density_dist'].shape == (samples, size) + obs.distribution.shape
def test_sample_posterior_predictive_after_set_data(self):
with pm.Model() as model:
x = pm.Data('x', [1., 2., 3.])
y = pm.Data('y', [1., 2., 3.])
beta = pm.Normal('beta', 0, 10.)
pm.Normal('obs', beta * x, np.sqrt(1e-2), observed=y)
trace = pm.sample(1000, tune=1000, chains=1)
# Predict on new data.
with model:
x_test = [5, 6, 9]
pm.set_data(new_data={'x': x_test})
y_test = pm.sample_posterior_predictive(trace)
y_test1 = pm.fast_sample_posterior_predictive(trace)
assert y_test['obs'].shape == (1000, 3)
assert y_test1['obs'].shape == (1000, 3)
np.testing.assert_allclose(x_test, y_test['obs'].mean(axis=0),
atol=1e-1)
np.testing.assert_allclose(x_test, y_test1['obs'].mean(axis=0),
atol=1e-1)
def test_sample_posterior_predictive_after_set_data(self):
with pm.Model() as model:
x = pm.Data("x", [1.0, 2.0, 3.0])
y = pm.Data("y", [1.0, 2.0, 3.0])
beta = pm.Normal("beta", 0, 10.0)
pm.Normal("obs", beta * x, np.sqrt(1e-2), observed=y)
trace = pm.sample(1000, tune=1000, chains=1)
# Predict on new data.
with model:
x_test = [5, 6, 9]
pm.set_data(new_data={"x": x_test})
y_test = pm.sample_posterior_predictive(trace)
y_test1 = pm.fast_sample_posterior_predictive(trace)
assert y_test["obs"].shape == (1000, 3)
assert y_test1["obs"].shape == (1000, 3)
np.testing.assert_allclose(x_test,
y_test["obs"].mean(axis=0),
atol=1e-1)
np.testing.assert_allclose(x_test,
y_test1["obs"].mean(axis=0),
atol=1e-1)
def test_sample_after_set_data(self):
with pm.Model() as model:
x = pm.Data('x', [1., 2., 3.])
y = pm.Data('y', [1., 2., 3.])
beta = pm.Normal('beta', 0, 10.)
pm.Normal('obs', beta * x, np.sqrt(1e-2), observed=y)
pm.sample(1000, init=None, tune=1000, chains=1)
# Predict on new data.
new_x = [5., 6., 9.]
new_y = [5., 6., 9.]
with model:
pm.set_data(new_data={'x': new_x, 'y': new_y})
new_trace = pm.sample(1000, init=None, tune=1000, chains=1)
pp_trace = pm.sample_posterior_predictive(new_trace, 1000)
pp_tracef = pm.fast_sample_posterior_predictive(new_trace, 1000)
assert pp_trace['obs'].shape == (1000, 3)
assert pp_tracef['obs'].shape == (1000, 3)
np.testing.assert_allclose(new_y, pp_trace['obs'].mean(axis=0),
atol=1e-1)
np.testing.assert_allclose(new_y, pp_tracef['obs'].mean(axis=0),
atol=1e-1)
def test_density_dist_with_random_sampleable_hidden_error(self, shape):
with pm.Model() as model:
mu = pm.Normal('mu', 0, 1)
normal_dist = pm.Normal.dist(mu, 1, shape=shape)
obs = pm.DensityDist(
'density_dist',
normal_dist.logp,
observed=np.random.randn(100, *shape),
shape=shape,
random=normal_dist.random,
wrap_random_with_dist_shape=False,
check_shape_in_random=False
)
trace = pm.sample(100)
samples = 500
ppc = pm.sample_posterior_predictive(trace, samples=samples, model=model)
assert len(ppc['density_dist']) == samples
assert ((samples,) + obs.distribution.shape) != ppc['density_dist'].shape
ppc = pm.fast_sample_posterior_predictive(trace, samples=samples, model=model)
assert len(ppc['density_dist']) == samples
assert ((samples,) + obs.distribution.shape) != ppc['density_dist'].shape
def test_sample_after_set_data(self):
with pm.Model() as model:
x = pm.Data("x", [1.0, 2.0, 3.0])
y = pm.Data("y", [1.0, 2.0, 3.0])
beta = pm.Normal("beta", 0, 10.0)
pm.Normal("obs", beta * x, np.sqrt(1e-2), observed=y)
pm.sample(1000, init=None, tune=1000, chains=1)
# Predict on new data.
new_x = [5.0, 6.0, 9.0]
new_y = [5.0, 6.0, 9.0]
with model:
pm.set_data(new_data={"x": new_x, "y": new_y})
new_trace = pm.sample(1000, init=None, tune=1000, chains=1)
pp_trace = pm.sample_posterior_predictive(new_trace, 1000)
pp_tracef = pm.fast_sample_posterior_predictive(new_trace, 1000)
assert pp_trace["obs"].shape == (1000, 3)
assert pp_tracef["obs"].shape == (1000, 3)
np.testing.assert_allclose(new_y,
pp_trace["obs"].mean(axis=0),
atol=1e-1)
np.testing.assert_allclose(new_y,
pp_tracef["obs"].mean(axis=0),
atol=1e-1)
