RMVMR
RMVMR is being tidied in lockstep with MVMR, the package it wraps
Comparison · Analytics
kernelshap vs spmodel
A side-by-side editorial comparison of kernelshap and spmodel — release velocity, themes, recent moves, and the top alternatives to consider.
kernelshap vs spmodel: at a glance
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.
What is spmodel?
Spatial regression in R, adding block kriging and then tuning the numerics underneath it
spmodel fits spatial linear and generalised linear models, for both point-referenced and areal data, with prediction and diagnostics attached. Block prediction arrived in 0.11.0 and the releases since have refined it. The most recent release changes optimiser behaviour: the default Nelder-Mead relative stopping tolerance tightens from 1e-4 to 1e-6 to reduce convergence on local rather than global maxima.
kernelshap vs spmodel: editorial side-by-side
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.
spmodel
0.0ANALYTICS
Spatial regression in R, adding block kriging and then tuning the numerics underneath it
◆ Current state
spmodel fits spatial linear and generalised linear models, for both point-referenced and areal data, with prediction and diagnostics attached. Block prediction arrived in 0.11.0 and the releases since have refined it. The most recent release changes optimiser behaviour: the default Nelder-Mead relative stopping tolerance tightens from 1e-4 to 1e-6 to reduce convergence on local rather than global maxima.
◆ Where it's heading
Two threads run in parallel. The first is expanding what can be predicted — point predictions, then areal averages over a region via block kriging, then better accuracy and efficiency for that path as the block size default moved from 1000 to 4000 in 0.12.0. The second is numerical trustworthiness, and it is unusually prominent here: a range-constraint option for stability in 0.9.0, a corrected log determinant of the fixed effects in the restricted log likelihood in 0.11.0, a cloud semivariogram that had been doubling the semivariance fixed in 0.11.1, and now a tighter optimiser tolerance. Several of these silently changed results before they were caught.
◆ Prediction
Expect the maintainers to keep publishing explicit reproduction instructions alongside numerical default changes, as 0.13.0 does by documenting the `control = list(reltol = 1e-4)` escape hatch. The entries give no signal of expansion beyond the current model families.
Alternatives to kernelshap and spmodel
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 kernelshap or spmodel.
geoarrow-r
geoarrow tracks the GeoArrow spec and otherwise just keeps compiling
n2khab
n2khab keeps retracting interpretations of habitat data it can't actually support
tidypolars
tidypolars is grinding toward complete dplyr coverage, one supported function at a time
OneSampleMR
OneSampleMR found that argument order in a formula was silently changing its estimates
bpbounds
bpbounds found the same swapped-cell bug twice and clamped its bounds back into range
See all kernelshap alternatives → · See all spmodel alternatives →
Recent activity from kernelshap and spmodel
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
- 2mo agospmodelTighter optimiser tolerance to avoid local maxima
- 6mo agospmodelEmpirical autocovariance function and better block kriging accuracy
- 9mo agospmodelCloud semivariogram doubling fixed; geometry warnings added
- 1y agokernelshapKernel weight bug fixed; parallelism moves to doFuture
- 1y agokernelshapSampling permutation SHAP with standard errors ⚡
- 1y agospmodelBlock kriging for areal averages and their uncertainty ⚡
- 1y agospmodelRobust semivariogram and new covariance types for areal models
- 1y agospmodelRange constraint option and redefined covariance type names
- 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
Frequently asked questions
What is the difference between kernelshap and spmodel?
They serve adjacent needs but don't currently overlap on shipped themes. kernelshap and spmodel 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 kernelshap better than spmodel?
Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. kernelshap and spmodel 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 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.
What are the best alternatives to spmodel?
Top spmodel alternatives in Analytics are ranked by recent ship velocity. Browse the "spmodel alternatives" section above for the current picks, or visit /alternatives/spmodel for the full list with editorial commentary on each.