models.deviance_score()

A score for cross_validate: the family’s mean deviance on the

Usage

Source

models.deviance_score(
    family,
    theta=None,
    power=None,
)

test rows, sum(w * d) / sum(w) with the test design’s weights.

Parameters

family: str

As Glm.

theta: float = None

power: float = None

Returns

callable

score(y_test, predicted, test_design) -> float.

Examples

>>> from prospicio.models import Design, deviance_score
>>> d = Design([[1.0, 1.0]], ["(Intercept)"])
>>> deviance_score("gaussian")([1.0, 3.0], [2.0, 2.0], d)

1.0