NEWS.md
calculation_method
for surv_shap()
called "treeshap"
that uses the treeshap
package (#75)categorical_variables
were providedmodel_survshap()
function)plot.aggregated_surv_shap()
)model_profile(..., type = "accumulated")
)model_profile_2d()
function)plot(..., geom="variable")
function for plotting PDP and ALE explanations without the time dimensionflexsurv
models and for Python scikit-survival models (can be used with reticulate
)model_survshap()
- curves (with functional box plot)model_diagnostics()
function)"survival_quantiles"
and setting it as default (see explain()
)vignette("pdp")
and vignette("global-survshap")
)requireNamespace()
calls (#83)model_performance_survival
object - calculated metrics are now in a $result
list.calculation_method
for surv_shap()
called "kernelshap"
that use kernelshap
package and its implementation of improved Kernel SHAP (set as default) (#45)"kernel"
to "exact_kernel"
kernelshap
package)max_vars
parameter for predict_parts explanations (#27)max_vars
to 7 for every methodset_theme_survex()
(#32)predict_parts()
and model_parts()
explanations in one plot (#12)surv_feature_importance.R
- change auxiliary columns to include _
in their name. Necessary changes also done to plotting and printing functions. (#28)type
argument of model_parts()
to "difference"
(#33)categorical_variables
argument in model_parts()
and predict_parts()
. If it contains variable names not present in the variables
argument, they will be added at the end. (#39)model_performance()
(#22)explanation_label
parameter to predict_parts()
function that can overwrite explainer label and thus, enable plotting multiple local SurvSHAP(t) explanations. (#47)gridExtra
to patchwork
(#7)mlr3proba
(#10)mlr3proba
with survex
ingredients
from imports to suggestssurvex
package is now publicmodel_parts
, model_profile
, predict_parts
, predict_profile
explanations implementedsurvival
, ranger
, randomForestSRC
, censored
and mlr3proba
packages.