Skip to content

parameterspace.priors.uniform

Uniform (BasePrior)

Uninformed prior that puts equal weight on every value.

Source code in parameterspace/priors/uniform.py 
class Uniform(BasePrior):
    """Uninformed prior that puts equal weight on every value."""

    @store_init_arguments
    def __init__(self):
        super().__init__([0, 1])

    def pdf(self, value):
        """Calculate probability density function value.

        Return constant for values inside the bounds, zero if outside, and NaN for NaNs.
        """
        value = np.atleast_1d(value)
        active_idx = np.isfinite(value)
        pdf = np.full(value.shape, np.nan)
        inside = np.logical_and(
            self.bounds[0] <= value[active_idx], value[active_idx] <= self.bounds[1]
        )
        pdf[active_idx] = 1.0 / (self.bounds[1] - self.bounds[0]) * (inside)
        return pdf.squeeze()

    def sample(self, num_samples=None, random_state=np.random):
        return random_state.uniform(
            low=self.bounds[0], high=self.bounds[1], size=num_samples
        )

    def __repr__(self):
        """Minimal information about the Prior."""
        return f"Uniform prior in the interval [{self.bounds[0]}, {self.bounds[1]}]."

pdf(self, value)

Calculate probability density function value.

Return constant for values inside the bounds, zero if outside, and NaN for NaNs.

Source code in parameterspace/priors/uniform.py 
def pdf(self, value):
    """Calculate probability density function value.

    Return constant for values inside the bounds, zero if outside, and NaN for NaNs.
    """
    value = np.atleast_1d(value)
    active_idx = np.isfinite(value)
    pdf = np.full(value.shape, np.nan)
    inside = np.logical_and(
        self.bounds[0] <= value[active_idx], value[active_idx] <= self.bounds[1]
    )
    pdf[active_idx] = 1.0 / (self.bounds[1] - self.bounds[0]) * (inside)
    return pdf.squeeze()

sample(self, num_samples=None, random_state=<module 'numpy.random' from '/home/runner/.cache/pypoetry/virtualenvs/parameterspace-9AYrJA9h-py3.8/lib/python3.8/site-packages/numpy/random/__init__.py'>)

Draw random samples from the prior.

Parameters:

Name Type Description Default
num_samples

[description]

 None

Returns:

Type Description

[descriptions]
Source code in parameterspace/priors/uniform.py 
def sample(self, num_samples=None, random_state=np.random):
    return random_state.uniform(
        low=self.bounds[0], high=self.bounds[1], size=num_samples
    )