The goal is to be on CRAN by late November, with reasonable functionality but perhaps not meeting the entire model-implementations-principles spec. Tests will probably be in-house for the first release, then migrate to modeltests and become more strict after that.
[ ] knn via kknn package
[ ] naive Bayes (klaR, spark?)
[ ] null model wrapper as well as fit and pred functions
[ ] decision_tree via rpart,C5.0,spark` (others?)
[ ] SVM models: linear, RBF, polynomial as separate functions (kernlab)
Following https://github.com/topepo/parsnip/issues/35:
The goal is to be on CRAN by late November, with reasonable functionality but perhaps not meeting the entire model-implementations-principles spec. Tests will probably be in-house for the first release, then migrate to
modeltestsand become more strict after that.