def test_rvs_to_value_vars():
with pm.Model() as m:
a = pm.Uniform("a", 0.0, 1.0)
b = pm.Uniform("b", 0, a + 1.0)
c = pm.Normal("c")
d = at.log(c + b) + 2.0
a_value_var = m.rvs_to_values[a]
assert a_value_var.tag.transform
b_value_var = m.rvs_to_values[b]
c_value_var = m.rvs_to_values[c]
(res, ), replaced = rvs_to_value_vars((d, ))
assert res.owner.op == at.add
log_output = res.owner.inputs[0]
assert log_output.owner.op == at.log
log_add_output = res.owner.inputs[0].owner.inputs[0]
assert log_add_output.owner.op == at.add
c_output = log_add_output.owner.inputs[0]
# We make sure that the random variables were replaced
# with their value variables
assert c_output == c_value_var
b_output = log_add_output.owner.inputs[1]
assert b_output == b_value_var
res_ancestors = list(walk_model((res, ), walk_past_rvs=True))
res_rv_ancestors = [
v for v in res_ancestors
if v.owner and isinstance(v.owner.op, RandomVariable)
]
# There shouldn't be any `RandomVariable`s in the resulting graph
assert len(res_rv_ancestors) == 0
assert b_value_var in res_ancestors
assert c_value_var in res_ancestors
assert a_value_var not in res_ancestors
(res, ), replaced = rvs_to_value_vars((d, ), apply_transforms=True)
res_ancestors = list(walk_model((res, ), walk_past_rvs=True))
res_rv_ancestors = [
v for v in res_ancestors
if v.owner and isinstance(v.owner.op, RandomVariable)
]
assert len(res_rv_ancestors) == 0
assert a_value_var in res_ancestors
assert b_value_var in res_ancestors
assert c_value_var in res_ancestors
def __init__(self, vars, proposal="uniform", order="random", model=None):
model = pm.modelcontext(model)
vars = [model.rvs_to_values.get(var, var) for var in vars]
vars = pm.inputvars(vars)
initial_point = model.initial_point()
dimcats = []
# The above variable is a list of pairs (aggregate dimension, number
# of categories). For example, if vars = [x, y] with x being a 2-D
# variable with M categories and y being a 3-D variable with N
# categories, we will have dimcats = [(0, M), (1, M), (2, N), (3, N), (4, N)].
for v in vars:
v_init_val = initial_point[v.name]
rv_var = model.values_to_rvs[v]
distr = getattr(rv_var.owner, "op", None)
if isinstance(distr, CategoricalRV):
k_graph = rv_var.owner.inputs[3].shape[-1]
(k_graph, ), _ = rvs_to_value_vars((k_graph, ),
apply_transforms=True)
k = model.compile_fn(k_graph,
inputs=model.value_vars,
on_unused_input="ignore")(initial_point)
elif isinstance(distr, BernoulliRV):
k = 2
else:
raise ValueError(
"All variables must be categorical or binary" +
"for CategoricalGibbsMetropolis")
start = len(dimcats)
dimcats += [(dim, k)
for dim in range(start, start + v_init_val.size)]
if order == "random":
self.shuffle_dims = True
self.dimcats = dimcats
else:
if sorted(order) != list(range(len(dimcats))):
raise ValueError("Argument 'order' has to be a permutation")
self.shuffle_dims = False
self.dimcats = [dimcats[j] for j in order]
if proposal == "uniform":
self.astep = self.astep_unif
elif proposal == "proportional":
# Use the optimized "Metropolized Gibbs Sampler" described in Liu96.
self.astep = self.astep_prop
else:
raise ValueError(
"Argument 'proposal' should either be 'uniform' or 'proportional'"
)
super().__init__(vars, [model.compile_logp()])
def test_rvs_to_value_vars_nested():
# Test that calling rvs_to_value_vars in models with nested transformations
# does not change the original rvs in place. See issue #5172
with pm.Model() as m:
one = pm.LogNormal("one", mu=0)
two = pm.LogNormal("two", mu=at.log(one))
# We add potentials or deterministics that are not in topological order
pm.Potential("two_pot", two)
pm.Potential("one_pot", one)
before = aesara.clone_replace(m.free_RVs)
# This call would change the model free_RVs in place in #5172
res, _ = rvs_to_value_vars(m.potentials, apply_transforms=True)
after = aesara.clone_replace(m.free_RVs)
assert equal_computations(before, after)
def logcdfpt(
var: TensorVariable,
rv_values: Optional[Union[TensorVariable, Dict[TensorVariable, TensorVariable]]] = None,
*,
scaling: bool = True,
sum: bool = True,
**kwargs,
) -> TensorVariable:
"""Create a measure-space (i.e. log-cdf) graph for a random variable at a given point.
Parameters
==========
var
The `RandomVariable` output that determines the log-likelihood graph.
rv_values
A variable, or ``dict`` of variables, that represents the value of
`var` in its log-likelihood. If no `rv_value` is provided,
``var.tag.value_var`` will be checked and, when available, used.
jacobian
Whether or not to include the Jacobian term.
scaling
A scaling term to apply to the generated log-likelihood graph.
transformed
Apply transforms.
sum
Sum the log-likelihood.
"""
if not isinstance(rv_values, Mapping):
rv_values = {var: rv_values} if rv_values is not None else {}
rv_var, rv_value_var = extract_rv_and_value_vars(var)
rv_value = rv_values.get(rv_var, rv_value_var)
if rv_var is not None and rv_value is None:
raise ValueError(f"No value variable specified or associated with {rv_var}")
if rv_value is not None:
rv_value = at.as_tensor(rv_value)
if rv_var is not None:
# Make sure that the value is compatible with the random variable
rv_value = rv_var.type.filter_variable(rv_value.astype(rv_var.dtype))
if rv_value_var is None:
rv_value_var = rv_value
rv_node = rv_var.owner
rng, size, dtype, *dist_params = rv_node.inputs
# Here, we plug the actual random variable into the log-likelihood graph,
# because we want a log-likelihood graph that only contains
# random variables. This is important, because a random variable's
# parameters can contain random variables themselves.
# Ultimately, with a graph containing only random variables and
# "deterministics", we can simply replace all the random variables with
# their value variables and be done.
tmp_rv_values = rv_values.copy()
tmp_rv_values[rv_var] = rv_var
logp_var = _logcdf(rv_node.op, rv_var, tmp_rv_values, *dist_params, **kwargs)
transform = getattr(rv_value_var.tag, "transform", None) if rv_value_var else None
# Replace random variables with their value variables
replacements = rv_values.copy()
replacements.update({rv_var: rv_value, rv_value_var: rv_value})
(logp_var,), _ = rvs_to_value_vars(
(logp_var,),
apply_transforms=False,
initial_replacements=replacements,
)
if sum:
logp_var = at.sum(logp_var)
if scaling:
logp_var *= _get_scaling(
getattr(rv_var.tag, "total_size", None), rv_value.shape, rv_value.ndim
)
# Recompute test values for the changes introduced by the replacements
# above.
if config.compute_test_value != "off":
for node in io_toposort(graph_inputs((logp_var,)), (logp_var,)):
compute_test_value(node)
if rv_var.name is not None:
logp_var.name = f"__logp_{rv_var.name}"
return logp_var