pystra.active_learning.stopping.LearningThreshold

Use it: User guide · Worked example · Theory

class LearningThreshold(*, target_cov=0.1)

Bases: StoppingCriterion

Require the selection threshold and an interior failure probability.

This is the existing AK-MCS-style default. It uses the selection policy’s threshold, so choosing a different learning function also changes that threshold’s meaning. target_cov defaults to 0.1 for the final sample.

Methods

accepts_estimate	Require an interior probability and adequate finite sampling CoV.
should_stop	Accept a completed fit with nonzero failure and survival probabilities.

should_stop(history)

Accept a completed fit with nonzero failure and survival probabilities.

Return type:

bool

accepts_estimate(estimate)

Require an interior probability and adequate finite sampling CoV.

Return type:

bool