def test_no_trace(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, 1)
obs = pm.Normal("obs", x * beta, 1, observed=y) # pylint: disable=unused-variable
idata = pm.sample(100, tune=100)
prior = pm.sample_prior_predictive(return_inferencedata=False)
posterior_predictive = pm.sample_posterior_predictive(
idata, return_inferencedata=False)
# Only prior
inference_data = to_inference_data(prior=prior, model=model)
test_dict = {"prior": ["beta"], "prior_predictive": ["obs"]}
fails = check_multiple_attrs(test_dict, inference_data)
assert not fails
# Only posterior_predictive
inference_data = to_inference_data(
posterior_predictive=posterior_predictive, model=model)
test_dict = {"posterior_predictive": ["obs"]}
fails = check_multiple_attrs(test_dict, inference_data)
assert not fails
# Prior and posterior_predictive but no trace
inference_data = to_inference_data(
prior=prior,
posterior_predictive=posterior_predictive,
model=model)
test_dict = {
"prior": ["beta"],
"prior_predictive": ["obs"],
"posterior_predictive": ["obs"],
}
fails = check_multiple_attrs(test_dict, inference_data)
assert not fails
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/pymc/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, size=3)
pm.Normal("obs", alpha[index], np.sqrt(1e-2), observed=y)
prior_trace = pm.sample_prior_predictive(1000)
idata = pm.sample(
1000,
init=None,
tune=1000,
chains=1,
compute_convergence_checks=False,
)
# 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(
idata, 1000, var_names=["alpha", "obs"])
assert prior_trace.prior["alpha"].shape == (1, 1000, 3)
assert idata.posterior["alpha"].shape == (1, 1000, 3)
assert pp_trace.posterior_predictive["alpha"].shape == (1, 1000, 3)
assert pp_trace.posterior_predictive["obs"].shape == (1, 1000, 3)
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,
compute_convergence_checks=False,
)
# 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_idata = pm.sample(
1000,
init=None,
tune=1000,
chains=1,
compute_convergence_checks=False,
)
pp_trace = pm.sample_posterior_predictive(new_idata, 1000)
assert pp_trace.posterior_predictive["obs"].shape == (1, 1000, 3)
np.testing.assert_allclose(new_y,
pp_trace.posterior_predictive["obs"].mean(
("chain", "draw")),
atol=1e-1)
def model_with_dims():
with pm.Model(coords={"city": ["Aachen", "Maastricht", "London", "Bergheim"]}) as pmodel:
economics = pm.Uniform("economics", lower=-1, upper=1, shape=(1,))
population = pm.HalfNormal("population", sd=5, dims=("city"))
time = pm.Data("year", [2014, 2015, 2016], dims="year")
n = pm.Deterministic(
"tax revenue", economics * population[None, :] * time[:, None], dims=("year", "city")
)
yobs = pm.Data("observed", np.ones((3, 4)))
L = pm.Normal("L", n, observed=yobs)
compute_graph = {
"economics": set(),
"population": set(),
"year": set(),
"tax revenue": {"economics", "population", "year"},
"L": {"tax revenue"},
"observed": {"L"},
}
plates = {
"1": {"economics"},
"city (4)": {"population"},
"year (3)": {"year"},
"year (3) x city (4)": {"tax revenue"},
"3 x 4": {"L", "observed"},
}
return pmodel, compute_graph, plates
def radon_model():
"""Similar in shape to the Radon model"""
n_homes = 919
counties = 85
uranium = np.random.normal(-0.1, 0.4, size=n_homes)
xbar = np.random.normal(1, 0.1, size=n_homes)
floor_measure = np.random.randint(0, 2, size=n_homes)
d, r = divmod(919, 85)
county = np.hstack((np.tile(np.arange(counties, dtype=int), d), np.arange(r)))
with pm.Model() as model:
sigma_a = pm.HalfCauchy("sigma_a", 5)
gamma = pm.Normal("gamma", mu=0.0, sigma=1e5, shape=3)
mu_a = pm.Deterministic("mu_a", gamma[0] + gamma[1] * uranium + gamma[2] * xbar)
eps_a = pm.Normal("eps_a", mu=0, sigma=sigma_a, shape=counties)
a = pm.Deterministic("a", mu_a + eps_a[county])
b = pm.Normal("b", mu=0.0, sigma=1e15)
sigma_y = pm.Uniform("sigma_y", lower=0, upper=100)
# Anonymous SharedVariables don't show up
floor_measure = aesara.shared(floor_measure)
floor_measure_offset = pm.Data("floor_measure_offset", 1)
y_hat = a + b * floor_measure + floor_measure_offset
log_radon = pm.Data("log_radon", np.random.normal(1, 1, size=n_homes))
y_like = pm.Normal("y_like", mu=y_hat, sigma=sigma_y, observed=log_radon)
compute_graph = {
# variable_name : set of named parents in the graph
"sigma_a": set(),
"gamma": set(),
"mu_a": {"gamma"},
"eps_a": {"sigma_a"},
"a": {"mu_a", "eps_a"},
"b": set(),
"sigma_y": set(),
"y_like": {"a", "b", "sigma_y", "floor_measure_offset"},
"floor_measure_offset": set(),
# observed data don't have parents in the model graph, but are shown as decendants
# of the model variables that the observations belong to:
"log_radon": {"y_like"},
}
plates = {
"": {"b", "sigma_a", "sigma_y", "floor_measure_offset"},
"3": {"gamma"},
"85": {"eps_a"},
"919": {"a", "mu_a", "y_like", "log_radon"},
}
return model, compute_graph, plates
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", 0.0, 10.0)
pm.Normal("obs", b * x_shared, np.sqrt(1e-2), observed=y)
prior_trace0 = pm.sample_prior_predictive(1000)
idata = pm.sample(1000, init=None, tune=1000, chains=1)
pp_trace0 = pm.sample_posterior_predictive(idata, 1000)
x_shared.set_value(x_pred)
prior_trace1 = pm.sample_prior_predictive(1000)
pp_trace1 = pm.sample_posterior_predictive(idata, samples=1000)
assert prior_trace0.prior["b"].shape == (1, 1000)
assert prior_trace0.prior_predictive["obs"].shape == (1, 1000, 100)
assert prior_trace1.prior_predictive["obs"].shape == (1, 1000, 200)
assert pp_trace0.posterior_predictive["obs"].shape == (1, 1000, 100)
np.testing.assert_allclose(x,
pp_trace0.posterior_predictive["obs"].mean(
("chain", "draw")),
atol=1e-1)
assert pp_trace1.posterior_predictive["obs"].shape == (1, 1000, 200)
np.testing.assert_allclose(x_pred,
pp_trace1.posterior_predictive["obs"].mean(
("chain", "draw")),
atol=1e-1)
def test_data_mutable_default_warning(self):
with pm.Model():
with pytest.warns(FutureWarning,
match="`mutable` kwarg was not specified"):
data = pm.Data("x", [1, 2, 3])
assert isinstance(data, SharedVariable)
pass
def test_data_defined_size_dimension_can_register_dimname(self):
with pm.Model() as pmodel:
x = pm.Data("x", [[1, 2, 3, 4]], dims=("first", "second"))
assert "first" in pmodel.dim_lengths
assert "second" in pmodel.dim_lengths
# two dimensions are implied; a "third" dimension is created
y = pm.Normal("y", mu=x, size=2, dims=("third", "first", "second"))
assert "third" in pmodel.dim_lengths
assert y.eval().shape() == (2, 1, 4)
def test_data_naming():
"""
This is a test for issue #3793 -- `Data` objects in named models are
not given model-relative names.
"""
with pm.Model("named_model") as model:
x = pm.Data("x", [1.0, 2.0, 3.0])
y = pm.Normal("y")
assert y.name == "named_model_y"
assert x.name == "named_model_x"
def test_constant_data(self, use_context):
"""Test constant_data group behaviour."""
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, 1)
obs = pm.Normal("obs", x * beta, 1, observed=y) # pylint: disable=unused-variable
trace = pm.sample(100, tune=100, return_inferencedata=False)
if use_context:
inference_data = to_inference_data(trace=trace)
if not use_context:
inference_data = to_inference_data(trace=trace, model=model)
test_dict = {
"posterior": ["beta"],
"observed_data": ["obs"],
"constant_data": ["x"]
}
fails = check_multiple_attrs(test_dict, inference_data)
assert not fails
def test_data_kwargs(self):
strict_value = True
allow_downcast_value = False
with pm.Model():
data = pm.Data(
"data",
value=[[1.0], [2.0], [3.0]],
strict=strict_value,
allow_downcast=allow_downcast_value,
)
assert data.container.strict is strict_value
assert data.container.allow_downcast is allow_downcast_value
def test_priors_separation(self, use_context):
"""Test model is enough to get prior, prior predictive and observed_data."""
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, 1)
obs = pm.Normal("obs", x * beta, 1, observed=y) # pylint: disable=unused-variable
prior = pm.sample_prior_predictive(return_inferencedata=False)
test_dict = {
"prior": ["beta", "~obs"],
"observed_data": ["obs"],
"prior_predictive": ["obs"],
}
if use_context:
with model:
inference_data = to_inference_data(prior=prior)
else:
inference_data = to_inference_data(prior=prior, model=model)
fails = check_multiple_attrs(test_dict, inference_data)
assert not fails
def test_predictions_constant_data(self):
with pm.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, 1)
obs = pm.Normal("obs", x * beta, 1, observed=y) # pylint: disable=unused-variable
trace = pm.sample(100, tune=100, return_inferencedata=False)
inference_data = to_inference_data(trace)
test_dict = {
"posterior": ["beta"],
"observed_data": ["obs"],
"constant_data": ["x"]
}
fails = check_multiple_attrs(test_dict, inference_data)
assert not fails
with pm.Model():
x = pm.Data("x", [1.0, 2.0])
y = pm.Data("y", [1.0, 2.0])
beta = pm.Normal("beta", 0, 1)
obs = pm.Normal("obs", x * beta, 1, observed=y) # pylint: disable=unused-variable
predictive_trace = pm.sample_posterior_predictive(
inference_data, return_inferencedata=False)
assert set(predictive_trace.keys()) == {"obs"}
# this should be four chains of 100 samples
# assert predictive_trace["obs"].shape == (400, 2)
# but the shape seems to vary between pymc versions
inference_data = predictions_to_inference_data(
predictive_trace, posterior_trace=trace)
test_dict = {"posterior": ["beta"], "~observed_data": ""}
fails = check_multiple_attrs(test_dict, inference_data)
assert not fails, "Posterior data not copied over as expected."
test_dict = {"predictions": ["obs"]}
fails = check_multiple_attrs(test_dict, inference_data)
assert not fails, "Predictions not instantiated as expected."
test_dict = {"predictions_constant_data": ["x"]}
fails = check_multiple_attrs(test_dict, inference_data)
assert not fails, "Predictions constant data not instantiated as expected."
def test_can_resize_data_defined_size(self):
with pm.Model() as pmodel:
x = pm.Data("x", [[1, 2, 3, 4]], dims=("first", "second"))
y = pm.Normal("y", mu=0, dims=("first", "second"))
z = pm.Normal("z", mu=y, observed=np.ones((1, 4)))
assert x.eval().shape == (1, 4)
assert y.eval().shape == (1, 4)
assert z.eval().shape == (1, 4)
assert "first" in pmodel.dim_lengths
assert "second" in pmodel.dim_lengths
pmodel.set_data("x", [[1, 2], [3, 4], [5, 6]])
assert x.eval().shape == (3, 2)
assert y.eval().shape == (3, 2)
assert z.eval().shape == (3, 2)
def test_no_resize_of_implied_dimensions(self):
with pm.Model() as pmodel:
# Imply a dimension through RV params
pm.Normal("n", mu=[1, 2, 3], dims="city")
# _Use_ the dimension for a data variable
inhabitants = pm.Data("inhabitants", [100, 200, 300], dims="city")
# Attempting to re-size the dimension through the data variable would
# cause shape problems in InferenceData conversion, because the RV remains (3,).
with pytest.raises(
ShapeError,
match=
"was initialized from 'n' which is not a shared variable"):
pmodel.set_data("inhabitants", [1, 2, 3, 4])
def test_model_to_graphviz_for_model_with_data_container(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)
obs_sigma = floatX(np.sqrt(1e-2))
pm.Normal("obs", beta * x, obs_sigma, observed=y)
pm.sample(
1000,
init=None,
tune=1000,
chains=1,
compute_convergence_checks=False,
)
for formatting in {"latex", "latex_with_params"}:
with pytest.raises(ValueError, match="Unsupported formatting"):
pm.model_to_graphviz(model, formatting=formatting)
exp_without = [
'x [label="x\n~\nData" shape=box style="rounded, filled"]',
'beta [label="beta\n~\nNormal"]',
'obs [label="obs\n~\nNormal" style=filled]',
]
exp_with = [
'x [label="x\n~\nData" shape=box style="rounded, filled"]',
'beta [label="beta\n~\nNormal(mu=0.0, sigma=10.0)"]',
f'obs [label="obs\n~\nNormal(mu=f(f(beta), x), sigma={obs_sigma})" style=filled]',
]
for formatting, expected_substrings in [
("plain", exp_without),
("plain_with_params", exp_with),
]:
g = pm.model_to_graphviz(model, formatting=formatting)
# check formatting of RV nodes
for expected in expected_substrings:
assert expected in g.source
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,
return_inferencedata=False,
compute_convergence_checks=False,
)
# 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)
assert y_test.posterior_predictive["obs"].shape == (1, 1000, 3)
np.testing.assert_allclose(x_test,
y_test.posterior_predictive["obs"].mean(
("chain", "draw")),
atol=1e-1)
def test_autodetect_coords_from_model(self, use_context):
df_data = pd.DataFrame(columns=["date"]).set_index("date")
dates = pd.date_range(start="2020-05-01", end="2020-05-20")
for city, mu in {"Berlin": 15, "San Marino": 18, "Paris": 16}.items():
df_data[city] = np.random.normal(loc=mu, size=len(dates))
df_data.index = dates
df_data.index.name = "date"
coords = {"date": df_data.index, "city": df_data.columns}
with pm.Model(coords=coords) as model:
europe_mean = pm.Normal("europe_mean_temp", mu=15.0, sd=3.0)
city_offset = pm.Normal("city_offset", mu=0.0, sd=3.0, dims="city")
city_temperature = pm.Deterministic("city_temperature",
europe_mean + city_offset,
dims="city")
data_dims = ("date", "city")
data = pm.Data("data", df_data, dims=data_dims)
_ = pm.Normal("likelihood",
mu=city_temperature,
sd=0.5,
observed=data,
dims=data_dims)
trace = pm.sample(
return_inferencedata=False,
compute_convergence_checks=False,
cores=1,
chains=1,
tune=20,
draws=30,
step=pm.Metropolis(),
)
if use_context:
idata = to_inference_data(trace=trace)
if not use_context:
idata = to_inference_data(trace=trace, model=model)
assert "city" in list(idata.posterior.dims)
assert "city" in list(idata.observed_data.dims)
assert "date" in list(idata.observed_data.dims)
np.testing.assert_array_equal(idata.posterior.coords["city"],
coords["city"])
np.testing.assert_array_equal(idata.observed_data.coords["date"],
coords["date"])
np.testing.assert_array_equal(idata.observed_data.coords["city"],
coords["city"])
def test_eval_rv_shapes(self):
with pm.Model(coords={
"city": ["Sydney", "Las Vegas", "Düsseldorf"],
}) as pmodel:
pm.Data("budget", [1, 2, 3, 4], dims="year")
pm.Normal("untransformed", size=(1, 2))
pm.Uniform("transformed", size=(7, ))
obs = pm.Uniform("observed", size=(3, ), observed=[0.1, 0.2, 0.3])
pm.LogNormal("lognorm", mu=at.log(obs))
pm.Normal("from_dims", dims=("city", "year"))
shapes = pmodel.eval_rv_shapes()
assert shapes["untransformed"] == (1, 2)
assert shapes["transformed"] == (7, )
assert shapes["transformed_interval__"] == (7, )
assert shapes["lognorm"] == (3, )
assert shapes["lognorm_log__"] == (3, )
assert shapes["from_dims"] == (3, 4)
def test_ignores_observed(self):
observed = np.random.normal(10, 1, size=200)
with pm.Model():
# Use a prior that's way off to show we're ignoring the observed variables
observed_data = pm.Data("observed_data", observed)
mu = pm.Normal("mu", mu=-100, sigma=1)
positive_mu = pm.Deterministic("positive_mu", np.abs(mu))
z = -1 - positive_mu
pm.Normal("x_obs", mu=z, sigma=1, observed=observed_data)
prior = pm.sample_prior_predictive(return_inferencedata=False)
assert "observed_data" not in prior
assert (prior["mu"] < -90).all()
assert (prior["positive_mu"] > 90).all()
assert (prior["x_obs"] < -90).all()
assert prior["x_obs"].shape == (500, 200)
npt.assert_array_almost_equal(prior["positive_mu"], np.abs(prior["mu"]), decimal=4)
def test_shared_data_as_rv_input(self):
"""
Allow pm.Data to be used as input for other RVs.
See https://github.com/pymc-devs/pymc/issues/3842
"""
with pm.Model() as m:
x = pm.Data("x", [1.0, 2.0, 3.0])
y = pm.Normal("y", mu=x, size=(2, 3))
assert y.eval().shape == (2, 3)
idata = pm.sample(
chains=1,
tune=500,
draws=550,
return_inferencedata=True,
compute_convergence_checks=False,
)
samples = idata.posterior["y"]
assert samples.shape == (1, 550, 2, 3)
np.testing.assert_allclose(np.array([1.0, 2.0, 3.0]),
x.get_value(),
atol=1e-1)
np.testing.assert_allclose(np.array([1.0, 2.0, 3.0]),
samples.mean(("chain", "draw", "y_dim_0")),
atol=1e-1)
with m:
pm.set_data({"x": np.array([2.0, 4.0, 6.0])})
assert y.eval().shape == (2, 3)
idata = pm.sample(
chains=1,
tune=500,
draws=620,
return_inferencedata=True,
compute_convergence_checks=False,
)
samples = idata.posterior["y"]
assert samples.shape == (1, 620, 2, 3)
np.testing.assert_allclose(np.array([2.0, 4.0, 6.0]),
x.get_value(),
atol=1e-1)
np.testing.assert_allclose(np.array([2.0, 4.0, 6.0]),
samples.mean(("chain", "draw", "y_dim_0")),
atol=1e-1)
def test_implicit_coords_series(self):
ser_sales = pd.Series(
data=np.random.randint(low=0, high=30, size=22),
index=pd.date_range(start="2020-05-01",
periods=22,
freq="24H",
name="date"),
name="sales",
)
with pm.Model() as pmodel:
pm.Data("sales",
ser_sales,
dims="date",
export_index_as_coords=True)
assert "date" in pmodel.coords
assert len(pmodel.coords["date"]) == 22
assert pmodel.RV_dims == {"sales": ("date", )}
def test_symbolic_coords(self):
"""
In v4 dimensions can be created without passing coordinate values.
Their lengths are then automatically linked to the corresponding Tensor dimension.
"""
with pm.Model() as pmodel:
intensity = pm.Data("intensity",
np.ones((2, 3)),
dims=("row", "column"))
assert "row" in pmodel.dim_lengths
assert "column" in pmodel.dim_lengths
assert isinstance(pmodel.dim_lengths["row"], TensorVariable)
assert isinstance(pmodel.dim_lengths["column"], TensorVariable)
assert pmodel.dim_lengths["row"].eval() == 2
assert pmodel.dim_lengths["column"].eval() == 3
intensity.set_value(floatX(np.ones((4, 5))))
assert pmodel.dim_lengths["row"].eval() == 4
assert pmodel.dim_lengths["column"].eval() == 5
def test_implicit_coords_dataframe(self):
N_rows = 5
N_cols = 7
df_data = pd.DataFrame()
for c in range(N_cols):
df_data[f"Column {c+1}"] = np.random.normal(size=(N_rows, ))
df_data.index.name = "rows"
df_data.columns.name = "columns"
# infer coordinates from index and columns of the DataFrame
with pm.Model() as pmodel:
pm.Data("observations",
df_data,
dims=("rows", "columns"),
export_index_as_coords=True)
assert "rows" in pmodel.coords
assert "columns" in pmodel.coords
assert pmodel.RV_dims == {"observations": ("rows", "columns")}
def test_ovewrite_model_coords_dims(self):
"""Check coords and dims from model object can be partially overwrited."""
dim1 = ["a", "b"]
new_dim1 = ["c", "d"]
coords = {"dim1": dim1, "dim2": ["c1", "c2"]}
x_data = np.arange(4).reshape((2, 2))
y = x_data + np.random.normal(size=(2, 2))
with pm.Model(coords=coords):
x = pm.Data("x", x_data, dims=("dim1", "dim2"))
beta = pm.Normal("beta", 0, 1, dims="dim1")
_ = pm.Normal("obs",
x * beta,
1,
observed=y,
dims=("dim1", "dim2"))
trace = pm.sample(100, tune=100, return_inferencedata=False)
idata1 = to_inference_data(trace)
idata2 = to_inference_data(trace,
coords={"dim1": new_dim1},
dims={"beta": ["dim2"]})
test_dict = {
"posterior": ["beta"],
"observed_data": ["obs"],
"constant_data": ["x"]
}
fails1 = check_multiple_attrs(test_dict, idata1)
assert not fails1
fails2 = check_multiple_attrs(test_dict, idata2)
assert not fails2
assert "dim1" in list(idata1.posterior.beta.dims)
assert "dim2" in list(idata2.posterior.beta.dims)
assert np.all(idata1.constant_data.x.dim1.values == np.array(dim1))
assert np.all(
idata1.constant_data.x.dim2.values == np.array(["c1", "c2"]))
assert np.all(idata2.constant_data.x.dim1.values == np.array(new_dim1))
assert np.all(
idata2.constant_data.x.dim2.values == np.array(["c1", "c2"]))
def test_explicit_coords(self):
N_rows = 5
N_cols = 7
data = np.random.uniform(size=(N_rows, N_cols))
coords = {
"rows": [f"R{r+1}" for r in range(N_rows)],
"columns": [f"C{c+1}" for c in range(N_cols)],
}
# pass coordinates explicitly, use numpy array in Data container
with pm.Model(coords=coords) as pmodel:
pm.Data("observations", data, dims=("rows", "columns"))
assert "rows" in pmodel.coords
assert pmodel.coords["rows"] == ("R1", "R2", "R3", "R4", "R5")
assert "rows" in pmodel.dim_lengths
assert isinstance(pmodel.dim_lengths["rows"], ScalarSharedVariable)
assert pmodel.dim_lengths["rows"].eval() == 5
assert "columns" in pmodel.coords
assert pmodel.coords["columns"] == ("C1", "C2", "C3", "C4", "C5", "C6",
"C7")
assert pmodel.RV_dims == {"observations": ("rows", "columns")}
assert "columns" in pmodel.dim_lengths
assert isinstance(pmodel.dim_lengths["columns"], ScalarSharedVariable)
assert pmodel.dim_lengths["columns"].eval() == 7
def test_creation_of_data_outside_model_context(self):
with pytest.raises((IndexError, TypeError)) as error:
pm.Data("data", [1.1, 2.2, 3.3])
error.match("No model on context stack")
def test_deterministic(self):
data_values = np.array([0.5, 0.4, 5, 2])
with pm.Model() as model:
X = pm.Data("X", data_values)
pm.Normal("y", 0, 1, observed=X)
model.logp(model.initial_point)
