mlr3proba
mlr3proba is shedding weight as its survival work moves into sibling packages
A side-by-side editorial comparison of finetune and mlr3viz — release velocity, themes, recent moves, and the top alternatives to consider.
finetune tracks tune's evolving contracts more than it advances racing itself
finetune provides the racing and simulated-annealing alternatives to grid search in tidymodels. The core algorithms have been stable since 1.0.x; what has changed is everything around them — censored regression support arriving with a tune release, weighted resampling estimates preserved through racing, and a breaking move to named-only optional arguments.
mlr3viz keeps the ecosystem's plots working while the plots themselves move out
mlr3viz supplies autoplot methods across mlr3 objects — learners, resample and benchmark results, tuning instances, ensemble feature-selection results. Recent releases are mostly defensive: suppressing ggplot2::fortify() warnings on ROC and PRC curves, pinning legend order so plots are deterministic across ggplot2 environments, and tracking mlr3 1.7.2. A visible piece of scope also left, with the LearnerSurvCoxPH plot moving to mlr3proba.
finetune provides the racing and simulated-annealing alternatives to grid search in tidymodels. The core algorithms have been stable since 1.0.x; what has changed is everything around them — censored regression support arriving with a tune release, weighted resampling estimates preserved through racing, and a breaking move to named-only optional arguments.
This is a package operating downstream of tune, adopting whatever the shared resampling machinery grows next rather than proposing new search strategies. The 1.3.0 weighting work is a clear example: tune changed how resampling estimates are computed, and finetune's job was to not lose the weights during racing. Error messages and input checks are the steady internal theme.
Expect the next release to absorb whatever tune changes about metric collection or resampling weights; nothing in the entries points to a new search algorithm.
mlr3viz supplies autoplot methods across mlr3 objects — learners, resample and benchmark results, tuning instances, ensemble feature-selection results. Recent releases are mostly defensive: suppressing ggplot2::fortify() warnings on ROC and PRC curves, pinning legend order so plots are deterministic across ggplot2 environments, and tracking mlr3 1.7.2. A visible piece of scope also left, with the LearnerSurvCoxPH plot moving to mlr3proba.
The package is being narrowed toward generic plotting infrastructure while learner-specific plots migrate to the packages that own those learners. What it does add is access rather than new charts — passing parameters through to precrec::autoplot(), better hints when the wrong autoplot type is requested, and a confidence-interval plot for mlr3inferr. Determinism across ggplot2 versions has become a recurring concern, which is what happens when a visualization package is depended on by documentation and tests.
Following the Cox proportional-hazards precedent, further learner-specific plots are likely to move to their owning packages, leaving mlr3viz with the cross-cutting result objects.
Other Analytics products tracked by Sparkpulse, ranked by recent ship velocity. Each card links to a full editorial trajectory and lets you pivot into a head-to-head comparison with either finetune or mlr3viz.
mlr3proba is shedding weight as its survival work moves into sibling packages
mlr3tuning is rebuilding its async machinery under a stable public surface
timetk swallowed anomalize whole, then went quiet for two years
modelbased is turning marginal effects into a full contrast grammar
easystats' parameters package absorbs one more model class every few weeks
A finished Bayesian model-comparison package in pure maintenance mode
See all finetune alternatives → · See all mlr3viz alternatives →
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
They serve adjacent needs but don't currently overlap on shipped themes. mlr3viz is currently shipping more aggressively (velocity 2.5 vs 0.0), with 0 editorial sparks in the last 30 days against 0. See the at-a-glance table above for a side-by-side breakdown of velocity, recent sparks, and editorial themes.
Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. mlr3viz is currently shipping more aggressively (velocity 2.5 vs 0.0), with 0 editorial sparks in the last 30 days against 0. For your specific use case, the alternatives sections above list other Analytics products to evaluate alongside.
Top finetune alternatives in Analytics are ranked by recent ship velocity. Browse the "finetune alternatives" section above for the current picks, or visit /alternatives/finetune for the full list with editorial commentary on each.
Top mlr3viz alternatives in Analytics are ranked by recent ship velocity. Browse the "mlr3viz alternatives" section above for the current picks, or visit /alternatives/mlr3viz for the full list with editorial commentary on each.