bittermelon
bittermelon is growing from binary bitmaps toward greyscale and color glyphs
Comparison · Analytics
distributions3 vs weird
A side-by-side editorial comparison of distributions3 and weird — release velocity, themes, recent moves, and the top alternatives to consider.
Shared themes:r-package
distributions3 vs weird: at a glance
What is distributions3?
distributions3 changes hands to Achim Zeileis, and a moment calculation bug goes with it.
An R package giving probability distributions a consistent object interface — d/p/q/r functions, moments, and prodist() methods that extract a fitted distribution from a regression object. Releases are infrequent, roughly one a year, and the last one is largely administrative: Achim Zeileis takes over maintenance from Alex Hayes, with all URLs and documentation updated to match, alongside a fix to incorrect moment calculations reported by a user.
What is weird?
weird rebuilt itself on distributional objects, and now the anomaly tooling composes with everything else.
An R package for anomaly detection and unusual-observation diagnostics, at four releases with a long gap between the 2024 patch and the 2026 major line. The current shape is set by 2.0.0, which refactored the package onto distributional objects and renamed its central concept from density_scores() to surprisals(). Since then the work has been filling that structure in: surprisals for more model classes, faster bandwidth and probability calculations, and new visual diagnostics.
distributions3 vs weird: editorial side-by-side
distributions3
2.5ANALYTICS
distributions3 changes hands to Achim Zeileis, and a moment calculation bug goes with it.
◆ Current state
An R package giving probability distributions a consistent object interface — d/p/q/r functions, moments, and prodist() methods that extract a fitted distribution from a regression object. Releases are infrequent, roughly one a year, and the last one is largely administrative: Achim Zeileis takes over maintenance from Alex Hayes, with all URLs and documentation updated to match, alongside a fix to incorrect moment calculations reported by a user.
◆ Where it's heading
The package's growth has come in two modes. Early releases absorbed whole families of distributions from outside contributors — the extreme-value set, Erlang, later the Poisson binomial — while later ones tightened the interface itself with is_discrete() and is_continuous() generics and elementwise type-safety when applying a distribution vector to a numeric vector. The handover is the notable event in the current window: maintenance moves to the author of the surrounding statistical ecosystem this package already integrates with through prodist() and countreg, which suggests the interface work will continue over the distribution-collection work.
◆ Prediction
Expect closer alignment with Zeileis's own packages, with prodist() coverage widening to more model classes; the entries here do not indicate whether new distribution families remain on the agenda.
weird
0.0ANALYTICS
weird rebuilt itself on distributional objects, and now the anomaly tooling composes with everything else.
◆ Current state
An R package for anomaly detection and unusual-observation diagnostics, at four releases with a long gap between the 2024 patch and the 2026 major line. The current shape is set by 2.0.0, which refactored the package onto distributional objects and renamed its central concept from density_scores() to surprisals(). Since then the work has been filling that structure in: surprisals for more model classes, faster bandwidth and probability calculations, and new visual diagnostics.
◆ Where it's heading
The refactor onto a shared distribution representation is the decision everything else follows from. It let 2.1.0 add hdr() and parameters() methods for kde objects rather than bespoke accessors, and it let 3.0.0 bring in dist_mclust() to turn a Gaussian mixture model into the same object type — so a mixture, a kernel density estimate and a fitted distribution all flow through one interface. The 3.0.0 additions lean visual and multivariate: outlier maps plotting score distance against orthogonal distance, biplot projections with variable axes overlaid, and an augment() method for robust PCA objects. Dependencies have been shed steadily along the way — lookout, interpolation — while mvscale() moved out and then back in.
◆ Prediction
Expect surprisals() coverage to keep extending to further model classes, and the multivariate and robust-PCA diagnostics introduced in 3.0.0 to gain the same distributional-object treatment as the univariate side.
Alternatives to distributions3 and weird
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 distributions3 or weird.
epiworldR
epiworldR is a thin R shell whose releases track the C++ simulator underneath it
watina
A groundwater database client that has started doing the domain analysis too
inbospatial
A thin R wrapper over Flemish geospatial services, adding one standard at a time
Fluent Bit
Fluent Bit keeps two lines alive while the 5.x branch quietly opens 5.1.
OpenCTI
OpenCTI is rebuilding its connector layer into a marketplace and wiring the platform to XTM Hub
See all distributions3 alternatives → · See all weird alternatives →
Recent activity from distributions3 and weird
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
- 24d agodistributions3Maintenance moves to Achim Zeileis; moment calculations corrected
- 1mo agoweirdOutlier maps, biplot projections, and Gaussian mixtures as distributional objects
- 3mo agoweirdsurprisals() reaches glm objects; lookout dependency dropped
- 6mo agoweirdPackage refactored onto distributional objects; density_scores becomes surprisals
- 10mo agodistributions3ggplot2 compatibility for the plotting functions
- 1y agodistributions3Poisson binomial distribution, with a normal-approximation fallback
- 2y agoweirdWine reviews dataset replaced with a fetch function
- 3y agodistributions3is_discrete and is_continuous generics, plus elementwise type-safety
- 4y agodistributions3Extreme-value family, Erlang, and a plotting generic
Frequently asked questions
What is the difference between distributions3 and weird?
Both compete on the same themes — r-package — within Analytics. distributions3 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 distributions3 better than weird?
Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. distributions3 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 distributions3?
Top distributions3 alternatives in Analytics are ranked by recent ship velocity. Browse the "distributions3 alternatives" section above for the current picks, or visit /alternatives/distributions3-r for the full list with editorial commentary on each.
What are the best alternatives to weird?
Top weird alternatives in Analytics are ranked by recent ship velocity. Browse the "weird alternatives" section above for the current picks, or visit /alternatives/weird-r for the full list with editorial commentary on each.