rjdqa
rjdqa keeps refining one screen: the seasonal adjustment quality dashboard
Comparison · Analytics
aedseo vs kernelshap
A side-by-side editorial comparison of aedseo and kernelshap — release velocity, themes, recent moves, and the top alternatives to consider.
aedseo vs kernelshap: at a glance
What is aedseo?
An epidemic-onset detector that now brackets the whole season, not just its start
aedseo is a Statens Serum Institut R package for automated early detection of seasonal epidemic onsets, built around growth-rate estimation over consecutive time intervals. The 1.0.0 line moved it well past its original scope: observations are now modelled as cases or population-adjusted incidence, multiple waves can be estimated in one pass, and disease-specific thresholds are computed by a dedicated function. Version 1.1.0 adds an estimate of when a season has ended after the first onset.
What is kernelshap?
kernelshap makes permutation SHAP practical past eight features, then fixes the kernel weights it had wrong.
kernelshap computes model-agnostic SHAP values in R through Kernel SHAP, permutation SHAP and an exact additive explainer. Version 0.8.0 added a sampling permutation-SHAP algorithm with standard errors and early stopping, lifting the practical feature ceiling past what the exact method allows. Version 0.9.0 then corrected a bug in how kernel weights were computed — exact Kernel SHAP now agrees with exact permutation SHAP — and moved parallelism from foreach to doFuture.
aedseo vs kernelshap: editorial side-by-side
aedseo
0.0ANALYTICS
An epidemic-onset detector that now brackets the whole season, not just its start
◆ Current state
aedseo is a Statens Serum Institut R package for automated early detection of seasonal epidemic onsets, built around growth-rate estimation over consecutive time intervals. The 1.0.0 line moved it well past its original scope: observations are now modelled as cases or population-adjusted incidence, multiple waves can be estimated in one pass, and disease-specific thresholds are computed by a dedicated function. Version 1.1.0 adds an estimate of when a season has ended after the first onset.
◆ Where it's heading
The arc runs from a single-purpose onset detector toward a full seasonal-surveillance toolkit. Each release since 1.0.0 has widened what the package can say about a season rather than improving how it says it: incidence denominators, background population, multi-wave detection, thresholds, and now season end. Fixes in between are narrow and numerical, such as confidence intervals under ATLAS BLAS.
◆ Prediction
The natural next step is symmetry with the onset machinery the package already has: turning the 1.1.0 seasonal offset into a first-class output alongside onset, with its own summary and plotting methods.
kernelshap
0.0ANALYTICS
kernelshap makes permutation SHAP practical past eight features, then fixes the kernel weights it had wrong.
◆ Current state
kernelshap computes model-agnostic SHAP values in R through Kernel SHAP, permutation SHAP and an exact additive explainer. Version 0.8.0 added a sampling permutation-SHAP algorithm with standard errors and early stopping, lifting the practical feature ceiling past what the exact method allows. Version 0.9.0 then corrected a bug in how kernel weights were computed — exact Kernel SHAP now agrees with exact permutation SHAP — and moved parallelism from foreach to doFuture.
◆ Where it's heading
Two concerns drive this package: making exact methods reach further, and being demonstrably right. The first shows in the additive explainer, the optional background dataset and the sampling permutation algorithm; the second in unit tests written against Python's shap, credited fixes from outside contributors, and a willingness to ship a correctness fix that changes numbers people have already published. Speed work runs continuously underneath — direct solves replacing the Moore-Penrose pseudo-inverse, roughly 10% less memory.
◆ Prediction
The 0.6.0 and 0.7.0 notes each promised a stable 1.0.0 that has not arrived; with the weighting bug fixed and parallelism reworked, a 1.0 release is the most plausible next step.
Alternatives to aedseo and kernelshap
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 aedseo or kernelshap.
epikit
epikit narrows to field-epidemiology helpers, handing proportions to a sibling package
SimInf
SimInf 10.0 turns an epidemic simulator into a tool that fits models to real time series
mutagen
A young package porting Stata's egen row-wise helpers to the tidyverse, one function per release
broman
A statistician's personal toolbox, growing one plotting utility at a time
qtl
R/qtl is in pure custodial mode: every recent release answers a compiler, not a user
See all aedseo alternatives → · See all kernelshap alternatives →
Recent activity from aedseo and kernelshap
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
- 6mo agoaedseocombined_seasonal_output() now estimates when a season ends
- 8mo agoaedseoFix growth-rate confidence intervals under ATLAS BLAS
- 9mo agoaedseoIncidence, population adjustment and multi-wave detection land in 1.0.0 ⚡
- 1y agokernelshapKernel weight bug fixed; parallelism moves to doFuture
- 1y agokernelshapSampling permutation SHAP with standard errors ⚡
- 1y agokernelshapBackground data now optional; ranger survival support
- 2y agokernelshapFactor-valued predictions dropped
- 2y agokernelshapadditive_shap() explains additive models exactly
- 2y agokernelshapFaster on plain data.frames
- 2y agoaedseoMaintainership transferred to Lasse Engbo Christiansen
- 2y agoaedseoepi_calendar() and richer autoplot displays
- 2y agoaedseoFirst CRAN release of the aeddo onset detector
Frequently asked questions
What is the difference between aedseo and kernelshap?
They serve adjacent needs but don't currently overlap on shipped themes. aedseo and kernelshap 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 aedseo better than kernelshap?
Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. aedseo and kernelshap 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 aedseo?
Top aedseo alternatives in Analytics are ranked by recent ship velocity. Browse the "aedseo alternatives" section above for the current picks, or visit /alternatives/aedseo-r for the full list with editorial commentary on each.
What are the best alternatives to kernelshap?
Top kernelshap alternatives in Analytics are ranked by recent ship velocity. Browse the "kernelshap alternatives" section above for the current picks, or visit /alternatives/kernelshap for the full list with editorial commentary on each.