pymc.icdf#

pymc.icdf(rv, value, warn_rvs=None, **kwargs)[source]#

Create a graph for the inverse CDF of a random variable.

Parameters:

rvTensorVariable
valuetensor_like: Should be the same type (shape and dtype) as the rv.
warn_rvsbool, default True: Warn if RVs were found in the icdf graph. This can happen when a variable has other random variables as inputs. In that case, those random variables should be replaced by their respective values.

Returns:

icdfTensorVariable

Raises:

RuntimeError: If the icdf cannot be derived.

Examples

Create a compiled function that evaluates the icdf of a variable

import pymc as pm
import pytensor.tensor as pt

mu = pt.scalar("mu")
rv = pm.Normal.dist(mu, 1.0)

value = pt.scalar("value")
rv_icdf = pm.icdf(rv, value)

# Use .eval() for debugging
print(rv_icdf.eval({value: 0.9, mu: 0.0}))  # 1.28155157

# Compile a function for repeated evaluations
rv_icdf_fn = pm.compile_pymc([value, mu], rv_icdf)
print(rv_icdf_fn(value=0.9, mu=0.0))  # 1.28155157

Derive the graph for a transformation of a RandomVariable

import pymc as pm
import pytensor.tensor as pt

mu = pt.scalar("mu")
rv = pm.Normal.dist(mu, 1.0)
exp_rv = pt.exp(rv)

value = pt.scalar("value")
exp_rv_icdf = pm.icdf(exp_rv, value)

# Use .eval() for debugging
print(exp_rv_icdf.eval({value: 0.9, mu: 0.0}))  # 3.60222448

# Compile a function for repeated evaluations
exp_rv_icdf_fn = pm.compile_pymc([value, mu], exp_rv_icdf)
print(exp_rv_icdf_fn(value=0.9, mu=0.0))  # 3.60222448