tidytext
Finished, widely taught, and shipping roxygen fixes.
Comparison · Analytics
loo vs scales
A side-by-side editorial comparison of loo and scales — release velocity, themes, recent moves, and the top alternatives to consider.
loo vs scales: at a glance
What is loo?
loo keeps rewriting the diagnostics Bayesian modellers read off model comparison
loo computes leave-one-out cross-validation and model comparison for Bayesian models in the Stan ecosystem. Two releases in this window changed what users actually read: 2.7.0 replaced the fixed Pareto-k thresholds with sample-size-dependent ones and dropped the middle category, and 2.10.0 reshaped loo_compare's output into a data.frame with new uncertainty columns. The releases between are diagnostic robustness fixes and moment-matching corrections.
What is scales?
scales keeps widening what ggplot2 can put on an axis.
scales supplies the breaks, labels and transformations behind ggplot2's axes and legends. Unlike much of the tidyverse infrastructure around it, it still ships genuine feature work each release: native timespan handling in 1.3.0, then custom range-training classes and label_glue() in 1.4.0.
loo vs scales: editorial side-by-side
loo
2.5ANALYTICS
loo keeps rewriting the diagnostics Bayesian modellers read off model comparison
◆ Current state
loo computes leave-one-out cross-validation and model comparison for Bayesian models in the Stan ecosystem. Two releases in this window changed what users actually read: 2.7.0 replaced the fixed Pareto-k thresholds with sample-size-dependent ones and dropped the middle category, and 2.10.0 reshaped loo_compare's output into a data.frame with new uncertainty columns. The releases between are diagnostic robustness fixes and moment-matching corrections.
◆ Where it's heading
The package is being brought in line with the current PSIS literature rather than extended with new features, and the practical effect is that the numbers practitioners quote in papers keep changing meaning. Work is increasingly delegated to posterior for shared computations, and the project has added contributor process, benchmarks and a published AI contribution policy.
◆ Prediction
Expect further work on comparison diagnostics — the p_worse and diag_* columns are new enough that their defaults and documentation will likely be revised next.
scales
0.0ANALYTICS
scales keeps widening what ggplot2 can put on an axis.
◆ Current state
scales supplies the breaks, labels and transformations behind ggplot2's axes and legends. Unlike much of the tidyverse infrastructure around it, it still ships genuine feature work each release: native timespan handling in 1.3.0, then custom range-training classes and label_glue() in 1.4.0.
◆ Where it's heading
The arc runs toward extensibility and type coverage. First came built-in support for awkward types like difftime and hms; 1.4.0 inverts that by letting any third-party class participate in range training simply by implementing range() or levels(). Labelling is getting more expressive rather than merely more numerous.
◆ Prediction
Expect continued type-support and labelling work, with extension points that let downstream packages plug in their own classes instead of scales enumerating every one.
Alternatives to loo and scales
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 loo or scales.
textrecipes
Text features finally stay sparse all the way to the model.
probably
The package that made calibration a step instead of an afterthought.
workflowsets
workflowsets keeps widening what counts as a model worth comparing.
workflows
The tidymodels pipeline grew a third stage, and it happens after the model runs.
vetiver
Posit's MLOps package went quiet for two years, then came back to keep up with recipes.
Recent activity from loo and scales
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
- 20d agoloopsis_smooth_tail revert and simplify arg restored
- 1mo agolooloo_compare returns a data.frame with new uncertainty columns ⚡
- 7mo agolooStacking overflow fixes and posterior-based ESS
- 1y agoscalesscales 1.4.0 opens range training to custom classes
- 2y agolooMore robust Pareto-k diagnostics and moment matching
- 2y agolooPareto-k thresholds now depend on sample size ⚡
- 2y agoscalesscales 1.3.0 makes timespans first-class on axes
- 3y agolooLOO predictive metrics and CRPS scoring functions
- 3y agoscalesscales 1.2.1 re-documents to fix .Rd HTML issues
- 4y agoscalesscales 1.2.0 fixes currency sign order and adds scale_cut
- 6y agoscalesscales 1.1.1 fixes palette inversion and adds oob_keep()
- 6y agoscalesscales 1.1.0 reorganises breaks and labels into a naming scheme
Frequently asked questions
What is the difference between loo and scales?
They serve adjacent needs but don't currently overlap on shipped themes. loo 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.
Is loo better than scales?
Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. loo 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.
What are the best alternatives to loo?
Top loo alternatives in Analytics are ranked by recent ship velocity. Browse the "loo alternatives" section above for the current picks, or visit /alternatives/loo for the full list with editorial commentary on each.
What are the best alternatives to scales?
Top scales alternatives in Analytics are ranked by recent ship velocity. Browse the "scales alternatives" section above for the current picks, or visit /alternatives/scales-r for the full list with editorial commentary on each.