Chord
Chord's assistant can now write to the team's knowledge base, not just read from it.
Comparison · Analytics
etn vs kernelshap
A side-by-side editorial comparison of etn and kernelshap — release velocity, themes, recent moves, and the top alternatives to consider.
etn vs kernelshap: at a glance
What is etn?
etn stopped being an RStudio-server package and became something you can run anywhere.
etn is the R client for the European Tracking Network's acoustic telemetry database, maintained at INBO. The 3.0.0 release routes queries through an API served by the companion etnservice package, so the package no longer requires a session on the ETN RStudio server. Credentials moved out of a connection object and into .Renviron, and the data model was rescoped in 2.0.0 around tag_serial_number so acoustic work is one scope among several rather than the whole package.
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.
etn vs kernelshap: editorial side-by-side
etn
0.0ANALYTICS
etn stopped being an RStudio-server package and became something you can run anywhere.
◆ Current state
etn is the R client for the European Tracking Network's acoustic telemetry database, maintained at INBO. The 3.0.0 release routes queries through an API served by the companion etnservice package, so the package no longer requires a session on the ETN RStudio server. Credentials moved out of a connection object and into .Renviron, and the data model was rescoped in 2.0.0 around tag_serial_number so acoustic work is one scope among several rather than the whole package.
◆ Where it's heading
Two arcs run in parallel: widening access, and making room for non-acoustic data. The access work has been deliberate — an API-backed beta in 2024, then a stable release that picks the transport automatically and checks that a local etnservice install matches the deployed one, because the same query returning different results by transport would be worse than requiring the server. The Darwin Core export added in 2.1.0 points the same outward direction, moving data to OBIS and GBIF instead of keeping it in the ETN silo.
◆ Prediction
The cpod scope named in the 2.0.0 notes is the most likely next addition, now that the naming and the API transport are both in place to carry it.
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 etn 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 etn or kernelshap.
tidytransit
tidytransit tracks the GTFS spec as it grows, one reader and one router feature at a time.
oblicubes
A tiny grid renderer for oblique-projection cubes, complete since its first release.
biocro
BioCro swapped an unstable iteration for real root finders, changing what its crop models compute.
redist
redist keeps rewriting the sampler underneath a district-drawing API it has held stable since 4.0.
epiflows
epiflows has shipped four releases in eight years, none of which changed the code.
See all etn alternatives → · See all kernelshap alternatives →
Recent activity from etn and kernelshap
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
- 5mo agoetnetn runs off the ETN RStudio server via the etnservice API ⚡
- 6mo agoetnData model rescoped; acoustic becomes one named scope
- 6mo agoetnwrite_dwc() exports telemetry as Darwin Core for OBIS and GBIF
- 6mo agoetndepth_in_meters added to acoustic detections
- 6mo agoetnwrite_dwc() fixes for uppercase project codes
- 6mo agoetnNA formatting and duplicate receiver ID fixes
- 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
Frequently asked questions
What is the difference between etn and kernelshap?
They serve adjacent needs but don't currently overlap on shipped themes. etn 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 etn better than kernelshap?
Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. etn 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 etn?
Top etn alternatives in Analytics are ranked by recent ship velocity. Browse the "etn alternatives" section above for the current picks, or visit /alternatives/etn-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.