mlr3proba
mlr3proba is shedding weight as its survival work moves into sibling packages
Comparison · Analytics
modeldata vs probably
A side-by-side editorial comparison of modeldata and probably — release velocity, themes, recent moves, and the top alternatives to consider.
Shared themes:tidymodels
modeldata vs probably: at a glance
What is modeldata?
The tidymodels example-data package grows one dataset at a time, on nobody's schedule
modeldata exists to supply the datasets and simulation functions that tidymodels documentation, tests, and teaching material depend on. Releases arrive roughly once or twice a year and consist almost entirely of new data sets plus occasional simulation methods. The most recent work adds a Worley (1987) regression simulation and moves the package off the magrittr pipe onto base R's.
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.
modeldata vs probably: editorial side-by-side
modeldata
0.0ANALYTICS
The tidymodels example-data package grows one dataset at a time, on nobody's schedule
◆ Current state
modeldata exists to supply the datasets and simulation functions that tidymodels documentation, tests, and teaching material depend on. Releases arrive roughly once or twice a year and consist almost entirely of new data sets plus occasional simulation methods. The most recent work adds a Worley (1987) regression simulation and moves the package off the magrittr pipe onto base R's.
◆ Where it's heading
Two lines run through the history: broadening coverage of task types — ordinal classification, multinomial, regression, QSAR-style chemistry data — and building out synthetic simulation so tutorials can demonstrate a method without shipping a real dataset for it. The simulation side has grown from a single regression generator into a family with logistic and multinomial variants and a keep_truth option that exposes the error-free outcome. Infrastructure changes appear only when the wider tidyverse moves, as the base-pipe transition shows.
◆ Prediction
The pattern points to another simulation method or a dataset filling a task type the collection still lacks, rather than any change in what the package does.
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.
Alternatives to modeldata and probably
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 modeldata or probably.
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 modeldata alternatives → · See all probably alternatives →
Recent activity from modeldata and probably
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
- 10mo agoprobablyConformal objects gain required_pkgs() and butcher methods
- 11mo agomodeldatamodeldata 1.5.1 fixes documentation and column-name typos
- 1y agomodeldatamodeldata 1.5.0 adds a Worley (1987) regression simulation
- 1y agoprobablyggplot2 test updates and a clearer validation-set error
- 1y agoprobablyCalibration internals refactored; isotonic bootstrap bug fixed
- 2y agomodeldatamodeldata 1.4.0 adds the cat_adoption data set
- 2y agoprobablyFix grouping sensitivity to variable type
- 2y agomodeldatamodeldata 1.3.0 adds the deliveries data set
- 3y agomodeldatamodeldata 1.2.0 adds eight data sets across regression and classification
- 3y agoprobablySplit conformal and conformal quantile regression added
- 3y agoprobablyCalibration and conformal inference arrive in tidymodels ⚡
- 3y agomodeldatamodeldata 1.1.0 adds logistic and multinomial simulation plus keep_truth
Frequently asked questions
What is the difference between modeldata and probably?
Both compete on the same themes — tidymodels — within Analytics. modeldata and probably 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 modeldata better than probably?
Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. modeldata and probably 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 modeldata?
Top modeldata alternatives in Analytics are ranked by recent ship velocity. Browse the "modeldata alternatives" section above for the current picks, or visit /alternatives/modeldata for the full list with editorial commentary on each.
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.