tidymodels/recipes

Roadmap: recipes support for sparse tibbles

EmilHvitfeldt opened this issue · 1 comments

This issue is purely based on the integration part of using sparse tibbles in recipes as input/output. A different roadmap issue will be posted about having individual steps produce sparse columns.

What we need:

  • recipe() to take sparse tibbles as data #1364
  • recipe() to take {Matrix} sparse matrix as data #1367
    • turn them into sparse tibbles early
  • prep() to take sparse tibbles as data #1366
  • prep() to take {Matrix} sparse matrix as data #1368
    • turn them into sparse tibbles early
  • bake() to take sparse tibbles as data #1366
  • bake() to take {Matrix} sparse matrix as data #1369
    • turn them into sparse tibbles early
  • Document how sparse tibbles work within a recipe #1370
    • not all transformations are sparse safe

Adding all of this will give us

  • standalone usage of sparse matrices in {recipes}
  • everything it needs to be able to work with the rest of {tidymodels} in regards to sparse tibbles

This issue has been automatically locked. If you believe you have found a related problem, please file a new issue (with a reprex https://reprex.tidyverse.org) and link to this issue.