Recreate the cached data sets for the ggRandomForests package
cache_rfsrc_datasets(set = NA, save = TRUE, pth, ...)Defaults to all sets (NA), however for individual sets specify one or more of c("boston", "iris")
Defaults to write files to the current data directory.
the directory to store files.
extra arguments passed to randomForestSRC functions.
Constructing random forests are computationally expensive, and the
ggRandomForests operates directly on randomForestSRC objects.
We cache computationally intensive randomForestSRC objects to improve
the ggRandomForests examples, diagnostics and vignettes run times. The
set of precompiled randomForestSRC objects are stored in the package
data subfolder, however version changes in the dependent packages may break
some functionality. This function was created to help the package developer
deal with those changes. We make the function available to end users to
create objects for further experimentation.
There are five cached data set types: '
rfsrc_data - rfsrc
objects.
varsel_data - var.select
minimal depth variable selection objects.
interaction_data -
find.interaction minimal depth, pairwise
variable interaction matrices.
partial_data -
plot.variable objects
(partial=TRUE) for partial variable dependence.
partial_coplot_data -
plot.variable objects
(partial=TRUE) for partial variable dependence.
For the following data sets: #'
_iris - The iris data set.
_boston - The boston housing data set
(MASS package).
iris airq mtcars Boston
pbc
veteran
rfsrc_data
varsel_data
interaction_data
partial_data
partial_coplot_data