update.EffectData {effectplots} | R Documentation |
Updates an "EffectData" object by
sorting the variables by their importance, see effect_importance()
,
collapsing levels of categorical variables with many levels,
dropping small bins, or
dropping bins with missing name.
Except for sort_by
, all arguments are vectorized, i.e., you can
pass a vector or list of the same length as object
.
## S3 method for class 'EffectData'
update(
object,
sort_by = c("no", "pd", "pred_mean", "y_mean", "resid_mean", "ale"),
collapse_m = 30L,
collapse_by = c("weight", "N"),
drop_below_n = 0,
drop_below_weight = 0,
na.rm = FALSE,
...
)
object |
Object of class "EffectData". |
sort_by |
By which statistic ("pd", "pred_mean", "y_mean", "resid_mean", "ale") should the results be sorted? The default is "no" (no sorting). Calculated after all other update steps, e.g., after collapsing or dropping rare levels. |
collapse_m |
If a categorical X has more than |
collapse_by |
How to determine "rare" levels in |
drop_below_n |
Drop bins with N below this value. Applied after collapsing. |
drop_below_weight |
Drop bins with weight below this value. Applied after collapsing. |
na.rm |
Should missing bin centers be dropped? Default is |
... |
Currently not used. |
An object of class "EffectData".
feature_effects()
, average_observed()
, average_predicted()
,
partial_dependence()
, ale()
, bias()
, effect_importance()
fit <- lm(Sepal.Length ~ ., data = iris)
xvars <- colnames(iris)[-1]
feature_effects(fit, v = xvars, data = iris, y = "Sepal.Length", breaks = 5) |>
update(sort = "pd", collapse_m = 2) |>
plot()