A Pipeline of learners is a way to "chain" Learners together, where the
output of one learner is used as output for the next learner. This can be
used for things like screening, two stage machine learning methods, and Super
Learning. A pipeline is fit by fitting the first
chain() to create the next task, which becomes the training data for
Learner. Similarly, for prediction, the predictions from the
Learner become the data to predict on for the next
Learner object with methods for training and prediction. See
Lrnr_base for documentation on learners.
Parameters should be individual
Learners, in the
order they should be applied.
Individual learners have their own sets of parameters. Below is a list of shared parameters, implemented by
Lrnr_base, and shared
by all learners.
A character vector of covariates. The learner will use this to subset the covariates for any specified task
variable_type object used to control the outcome_type used by the learner. Overrides the task outcome_type if specified
All other parameters should be handled by the invidual learner classes. See the documentation for the learner class you're instantiating