Create new task identical to the old one, but with newdata instead
of old data. This should either preserve the orig.features of the
original task, or should add new noise-features, in which case orig.features
should mark the features that correspond to the full original task.
clonetask(
task,
newdata,
newid,
orig.features = rep(TRUE, ncol(newdata) - length(getTaskTargetNames(task)))
)Task
[Task] mlr Task to use.
[data.frame] data to replace task data with; must
include the target column with same name.
[character(1)] ID to use for new Task.
[logical] features that correspond to original task's data.
Other Artificial Datasets:
create.hypersphere.data(),
create.linear.data(),
create.linear.toy.data(),
create.regr.task(),
task.add.permuted.cols(),
task.add.random.cols()