run_retries#

pharmpy.tools.run_retries(model=None, results=None, number_of_candidates=5, fraction=0.1, use_initial_estimates=False, strictness='minimization_successful or (rounding_errors and sigdigs >= 0.1)', scale='UCP', prefix_name='', seed=None, **kwargs)#

Run retries tool.

Parameters:

  • model (Optional[Model], optional) – Model object to run retries on. The default is None.

  • results (Optional[ModelfitResults], optional) – Connected ModelfitResults object. The default is None.

  • number_of_candidates (int, optional) – Number of retry candidates to run. The default is 5.

  • fraction (float) – Determines allowed increase/decrease from initial parameter estimate. Default is 0.1 (10%)

  • use_initial_estimates (bool) – Use initial parameter estimates instead of final estimates of input model when creating candidate models.

  • strictness (Optional[str], optional) – Strictness criteria. The default is “minimization_successful or (rounding_errors and sigdigs >= 0.1)”.

  • scale ({‘normal’, ‘UCP’}) – Which scale to update the initial values on. Either normal scale or UCP scale.

  • prefix_name (Optional[str]) – Prefix the candidate model names with given string.

  • seed (int or rng) – Random number generator or seed to be used

  • kwargs – Arguments to pass to tool

Returns:

RetriesResults – Retries tool results object.

On this page