climb.tool.impl.data_suite.third_party.uq360.algorithms.infinitesimal_jackknife package

Submodules

climb.tool.impl.data_suite.third_party.uq360.algorithms.infinitesimal_jackknife.infinitesimal_jackknife module

class climb.tool.impl.data_suite.third_party.uq360.algorithms.infinitesimal_jackknife.infinitesimal_jackknife.InfinitesimalJackknife(params, gradients, hessian, config)[source]

Bases: PostHocUQ

Performs a first order Taylor series expansion around MLE / MAP fit. Requires the model being probed to be twice differentiable.

approx_ij(w_query)[source]
Parameters:

w_query – A n*1 vector to query parameters at.

Returns:

new parameters at w_query

get_parameter_uncertainty()[source]
get_params(deep=True)[source]

This method should not take any arguments and returns a dict of the __init__ parameters.

ij(w_query)[source]
Parameters:

w_query – A n*1 vector to query parameters at.

Returns:

new parameters at w_query

predict(X, model)[source]
Parameters:

  • X – array-like of shape (n_samples, n_features). Features vectors of the test points.

  • model – model object, must implement a set_parameters function

Returns:

A namedtupe that holds

y_mean: ndarray of shape (n_samples, [n_output_dims])

Mean of predictive distribution of the test points.

y_lower: ndarray of shape (n_samples, [n_output_dims])

Lower quantile of predictive distribution of the test points.

y_upper: ndarray of shape (n_samples, [n_output_dims])

Upper quantile of predictive distribution of the test points.

Return type:

namedtuple

Module contents