BAyesian Model-Building Interface (Bambi) in Python.
This is the first version of Bambi that is released with a Governance structure. Added in #709.
The highlights are the shiny interpret
subpackage and the implementation of support for censored models.
"exponential"
and "weibull"
families (#697)"kidney"
dataset (#697)interpret
submodule (#684, #695, #699, #701, #732, #736)
comparisons
, predictions
, slopes
, plot_comparisons
, plot_predictions
, and plot_slopes
univariate_ordered
with ordered
(#724)center_predictors
(#726)plot_comparison
(#731)plots
submodule name to interpret
(#705)"ordinal"
and "sratio"
for modeling of ordinal responses (#678)create_extra_pps_coord()
(#688)"zero_inflated_poisson"
, "zero_inflated_binomial"
, and "zero_inflated_negativebinomial"
(#654)"beta_binomial"
and "dirichlet_multinomial"
(#659)plot_cap()
to show predictions at the observation level (#668)"hurdle_gamma"
, "hurdle_lognormal"
, "hurdle_negativebinomial"
, and "hurdle_poisson"
(#676)plot_cap()
works (#670)plot_cap()
gains a new argument target
that allows to plot different parameters of the response distribution (#627)tests
directory to the root of the repository (#607)dims
to the response of the likelihood distribution anymore (#629)pyproject.toml
config file to distribute the package (#631)censored()
(#581)Formula
class (#585)AsymmetricLaplace
family for Quantile Regression (#591)plot_cap()
(#594)plot_cap()
and make it more flexible (#596)model.initial_point()
(#592)automatic_priors
argument from Model
(#603)Model
(#604)plot_cap
(#517)"vonmises"
) built-in family (#453)Model.predict()
gains a new argument include_group_specific
to determine if group-specific effects are considered when making predictions (#470)"multinomial"
) built-in family (#490)link="inverse"
was wrong. It returned the same result as link="cloglog"
(#472)namedtuple
s when same dictionary structure was repeated many times (#472)check_full_rank()
in utils.py
now checks the array is 2 dimensional (#472)_extract_family_prior()
from bambi/families
as it was unnecesary (#472)bambi/families/utils.py
as it was unnecessary (#472)"_coord_group_factor"
with "__factor_dim"
and "_coord_group_expr"
with "__expr_dim"
in dimension/coord names (#499)bambi/defaults
(#472)draws
parameter from Model.predict()
method (#504)This is a patch release where we fix a bug related to the shape of 2 level categorical group-specific effects (#441)