Transition from the magrittr pipe to the base R pipe.
Fixed a bug (exposed by the new version of the tune package) where multi_predict() was called with a single component value (#47).
pls()) were moved to the parsnip package.Small updates so that plsmod can be run in parallel using psock clusters
Updates for encoding requirements related to current version of parsnip.
The num_terms argument was removed in favor of predictor_prop, which is the maximum proportion of original predictors that can have non-zero coefficients for each PLS component. This makes it easier to tune and consistent with recipes::step_pls().
Fixed a bug that could prevent multi_predict() from being invoked.
NEWS.md file to track changes to the package.