mlr3proba
mlr3proba is shedding weight as its survival work moves into sibling packages
Comparison · Analytics
probably vs workflowsets
A side-by-side editorial comparison of probably and workflowsets — release velocity, themes, recent moves, and the top alternatives to consider.
Shared themes:tidymodels
probably vs workflowsets: at a glance
What is probably?
The package that made calibration a step instead of an afterthought.
probably started as a small utility for class predictions and equivocal zones, and version 1.0.0 turned it into tidymodels' calibration and uncertainty package: cal_plot_*, cal_estimate_*, cal_validate_* and cal_apply across binary, multiclass and regression problems, plus conformal prediction intervals. Since then the work has been consolidation — a large internal refactor with no API change, split conformal and conformal quantile regression, bound_prediction(), and required_pkgs() and butcher methods so conformal objects can be deployed and stripped.
What is workflowsets?
workflowsets keeps widening what counts as a model worth comparing.
workflowsets holds a grid of preprocessor and model combinations and evaluates all of them under one call to workflow_map(). The releases in view widen that grid — clustering specifications via tidyclust, censored regression via an eval_time argument, case weights — and fill in the accessors around it with collect_notes(), collect_extracts() and fit_best(). The long-running pull_*() deprecation finally reached the error stage in 1.1.1.
probably vs workflowsets: editorial side-by-side
probably
0.0ANALYTICS
The package that made calibration a step instead of an afterthought.
◆ Current state
probably started as a small utility for class predictions and equivocal zones, and version 1.0.0 turned it into tidymodels' calibration and uncertainty package: cal_plot_*, cal_estimate_*, cal_validate_* and cal_apply across binary, multiclass and regression problems, plus conformal prediction intervals. Since then the work has been consolidation — a large internal refactor with no API change, split conformal and conformal quantile regression, bound_prediction(), and required_pkgs() and butcher methods so conformal objects can be deployed and stripped.
◆ Where it's heading
The recent releases are about making these objects survive leaving the session. butcher and required_pkgs() methods are what a model needs to be pinned, containerised and served, and their arrival alongside workflows adding a tailor postprocessing stage and vetiver adding probably support points the same way: calibration is being moved out of analysis scripts and into the deployed pipeline. The cal_*_none() reference implementations are the tell that calibration is now something people tune rather than apply once.
◆ Prediction
Expect the calibration functions to be reachable directly from a tuned workflow's postprocessing stage rather than applied to predictions afterwards, following the tailor integration that workflows just shipped.
workflowsets
0.0ANALYTICS
workflowsets keeps widening what counts as a model worth comparing.
◆ Current state
workflowsets holds a grid of preprocessor and model combinations and evaluates all of them under one call to workflow_map(). The releases in view widen that grid — clustering specifications via tidyclust, censored regression via an eval_time argument, case weights — and fill in the accessors around it with collect_notes(), collect_extracts() and fit_best(). The long-running pull_*() deprecation finally reached the error stage in 1.1.1.
◆ Where it's heading
The package's job is comparison, so its direction is set by what tidymodels can express: every time a new model paradigm lands elsewhere, workflowsets has to learn to rank it. Clustering was the largest of those steps because it has no outcome column to score against. Alongside that runs a slower cleanup — named-only optional arguments, type checking on inputs, informative errors when someone passes a workflow set to fit() — that reads as a package hardening after its API settled.
◆ Prediction
Expect the tailor postprocessors that workflows added in 1.3.0 to need representation here next, since a workflow set that cannot vary the postprocessor cannot compare calibration choices.
Alternatives to probably and workflowsets
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 probably or workflowsets.
mlr3viz
mlr3viz keeps the ecosystem's plots working while the plots themselves move out
mlr3tuning
mlr3tuning is rebuilding its async machinery under a stable public surface
timetk
timetk swallowed anomalize whole, then went quiet for two years
modelbased
modelbased is turning marginal effects into a full contrast grammar
parameters
easystats' parameters package absorbs one more model class every few weeks
See all probably alternatives → · See all workflowsets alternatives →
Recent activity from probably and workflowsets
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
- 10mo agoprobablyConformal objects gain required_pkgs() and butcher methods
- 1y agoprobablyggplot2 test updates and a clearer validation-set error
- 1y agoworkflowsetscollect_extracts() added; pull_*() functions now error
- 1y agoprobablyCalibration internals refactored; isotonic bootstrap bug fixed
- 2y agoworkflowsetsCensored regression evaluation; eval_time breaks positional args
- 2y agoprobablyFix grouping sensitivity to variable type
- 3y agoprobablySplit conformal and conformal quantile regression added
- 3y agoprobablyCalibration and conformal inference arrive in tidymodels ⚡
- 3y agoworkflowsetsClustering models enter workflow sets via tidyclust ⚡
- 4y agoworkflowsetsCase weights supported across a workflow set
- 4y agoworkflowsetsUpdate models and recipes across a set; mixed inputs accepted
- 5y agoworkflowsetsextract_*() supersedes pull_*() across tidymodels
Frequently asked questions
What is the difference between probably and workflowsets?
Both compete on the same themes — tidymodels — within Analytics. probably and workflowsets are shipping at a similar cadence (velocity 0.0 vs 0.0, both within Sparkpulse's "active" band). See the at-a-glance table above for a side-by-side breakdown of velocity, recent sparks, and editorial themes.
Is probably better than workflowsets?
Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. probably and workflowsets are shipping at a similar cadence (velocity 0.0 vs 0.0, both within Sparkpulse's "active" band). For your specific use case, the alternatives sections above list other Analytics products to evaluate alongside.
What are the best alternatives to probably?
Top probably alternatives in Analytics are ranked by recent ship velocity. Browse the "probably alternatives" section above for the current picks, or visit /alternatives/probably for the full list with editorial commentary on each.
What are the best alternatives to workflowsets?
Top workflowsets alternatives in Analytics are ranked by recent ship velocity. Browse the "workflowsets alternatives" section above for the current picks, or visit /alternatives/workflowsets for the full list with editorial commentary on each.