← Back to home
Comparison · Analytics

fairmodels vs vellumplot

A side-by-side editorial comparison of fairmodels and vellumplot — release velocity, themes, recent moves, and the top alternatives to consider.

fairmodels vs vellumplot: at a glance

Featurefairmodelsvellumplot
SectorAnalyticsAnalytics
Velocity score0.06.3
Sparks · 30d01
Top themesfairness auditing, bias detection, dalex, r packager-graphics, grammar-of-graphics, accessibility, data-visualization
Last editorial update4h ago47m ago
WebsiteVisit →Visit →

What is fairmodels?

fairmodels sits dormant for three years, resurfacing only to satisfy a CRAN check.

fairmodels audits classification models for bias, built around fairness_check() and parity-loss metrics on top of DALEX explainers. The last substantive work dates from 2021; the 2025 release is a single-line change swapping ifelse for if/else in fairness_heatmap. Version 0.2.2 set the package's core design when it superseded metric differences with ratios.

Read the full fairmodels trajectory →

What is vellumplot?

vellumplot tags its first release with a bet most R grammars don't make: the static figure and the widget are the same object.

A new grammar of graphics built on the vellum vector engine, developing fast — ten releases in roughly three weeks — and now at its first tagged release. The distinguishing architectural claim is that the compiled plot is the scene, so a static export and an interactive widget cannot drift apart, and that it renders without a graphics device because vellum measures text itself. Accessibility is treated as a first-class output rather than an afterthought: tagged PDF with a navigable structure tree and alt text, a plot_lint() check, and colour-vision-deficiency simulation at render time.

Read the full vellumplot trajectory →

fairmodels vs vellumplot: editorial side-by-side

F
fairmodels
ANALYTICS
0.0

fairmodels sits dormant for three years, resurfacing only to satisfy a CRAN check.

◆ Current state

fairmodels audits classification models for bias, built around fairness_check() and parity-loss metrics on top of DALEX explainers. The last substantive work dates from 2021; the 2025 release is a single-line change swapping ifelse for if/else in fairness_heatmap. Version 0.2.2 set the package's core design when it superseded metric differences with ratios.

◆ Where it's heading

The release history describes a package that reached its intended shape early and has been custodial since — the gap from August 2022 to October 2025 carries no functional change at all. What movement exists is CRAN-driven: documentation compliance, example runtimes, coding-style notes. The fairness metrics themselves have not changed since the parity_loss corrections of 2020.

◆ Prediction

On this cadence the next release is most likely another CRAN-prompted one-liner rather than new fairness metrics; nothing in these entries points to active development.

V
vellumplot
ANALYTICS
6.3

vellumplot tags its first release with a bet most R grammars don't make: the static figure and the widget are the same object.

◆ Current state

A new grammar of graphics built on the vellum vector engine, developing fast — ten releases in roughly three weeks — and now at its first tagged release. The distinguishing architectural claim is that the compiled plot is the scene, so a static export and an interactive widget cannot drift apart, and that it renders without a graphics device because vellum measures text itself. Accessibility is treated as a first-class output rather than an afterthought: tagged PDF with a navigable structure tree and alt text, a plot_lint() check, and colour-vision-deficiency simulation at render time.

◆ Where it's heading

The release sequence shows a grammar filling in ggplot2-parity features and specialist marks in parallel. Parity work landed as secondary axes, rich legend titles, and Sankey styling; the specialist end added categorical datashading, image marks, flow maps and edge bundling for dense graphs. Version 0.7.0 shows a willingness to break early — vsunburst() was removed outright in favour of one vhierarchy() constructor covering sunburst, icicle, treemap and circlepack — which is the right time to do it and suggests the API is still being consolidated toward fewer, more general constructors.

◆ Prediction

Expect more consolidation of near-duplicate constructors under type arguments and continued expansion of the declarative interactivity introduced in 0.7.0, now that the first tagged release has fixed a public API surface.

Alternatives to fairmodels and vellumplot

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 fairmodels or vellumplot.

See all fairmodels alternatives → · See all vellumplot alternatives →

Recent activity from fairmodels and vellumplot

Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.

  1. 14d agovellumplotFirst tagged release: one spec compiles to PNG, SVG, tagged PDF and a widget
  2. 19d agovellumplotFlow maps and edge bundling for dense graph plots
  3. 24d agovellumplotvhierarchy() replaces vsunburst(); declarative interactivity arrives
  4. 26d agovellumplotSankey crossing minimisation and per-branch sunburst colouring
  5. 29d agovellumplotSecondary axes land; rich legend titles stop clipping
  6. 1mo agovellumplotCategorical datashading in one call, plus image marks at data points
  7. 9mo agofairmodelsOne-line fix in fairness_heatmap
  8. 3y agofairmodelsCRAN compliance fixes and citation update
  9. 4y agofairmodelsCRAN v1.2.0
  10. 5y agofairmodelsCRAN v1.1.0
  11. 5y agofairmodelsDocumentation fixes and trimmed example runtimes
  12. 5y agofairmodelsCorrects parity_loss in the cutoff functions

Frequently asked questions

What is the difference between fairmodels and vellumplot?

They serve adjacent needs but don't currently overlap on shipped themes. vellumplot is currently shipping more aggressively (velocity 6.3 vs 0.0), with 1 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 fairmodels better than vellumplot?

Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. vellumplot is currently shipping more aggressively (velocity 6.3 vs 0.0), with 1 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 fairmodels?

Top fairmodels alternatives in Analytics are ranked by recent ship velocity. Browse the "fairmodels alternatives" section above for the current picks, or visit /alternatives/fairmodels for the full list with editorial commentary on each.

What are the best alternatives to vellumplot?

Top vellumplot alternatives in Analytics are ranked by recent ship velocity. Browse the "vellumplot alternatives" section above for the current picks, or visit /alternatives/vellumplot for the full list with editorial commentary on each.