Lightdash
Lightdash keeps handing authoring to outside agents and keeping the governed layer for itself.
Comparison · Analytics
kernelshap vs Whatagraph
A side-by-side editorial comparison of kernelshap and Whatagraph — release velocity, themes, recent moves, and the top alternatives to consider.
kernelshap vs Whatagraph: at a glance
| Feature | kernelshap | Whatagraph |
|---|---|---|
| Sector | Analytics | Analytics |
| Velocity score | 0.0 | 5.0 |
| Sparks · 30d | 0 | 0 |
| Top themes | shap, model explainability, sampling algorithms, numerical correctness | reporting, agencies, integrations, reliability |
| Last editorial update | 4d ago | 38m ago |
| Website | Visit → | — |
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 Whatagraph?
Whatagraph keeps fixing what breaks when one account runs a thousand sources.
Whatagraph is working on the parts of agency reporting that break under volume rather than on new analysis capability. Stored data removed live API calls from render time in the Basis rebuild, connection failover keeps widgets alive when one teammate's token expires, and report shortcuts let a heavy report be split into a hub with supporting detail. Presentation control arrives steadily alongside — automatic conditional formatting, per-metric decimal places, chosen comparison colors. The newest change moves unified-field mapping into the Source Group builder, so a cross-channel group can be fixed in place instead of rebuilt.
kernelshap vs Whatagraph: 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.
Whatagraph
5.0ANALYTICS
Whatagraph keeps fixing what breaks when one account runs a thousand sources.
◆ Current state
Whatagraph is working on the parts of agency reporting that break under volume rather than on new analysis capability. Stored data removed live API calls from render time in the Basis rebuild, connection failover keeps widgets alive when one teammate's token expires, and report shortcuts let a heavy report be split into a hub with supporting detail. Presentation control arrives steadily alongside — automatic conditional formatting, per-metric decimal places, chosen comparison colors. The newest change moves unified-field mapping into the Source Group builder, so a cross-channel group can be fixed in place instead of rebuilt.
◆ Where it's heading
The through-line is reliability and workflow cost at agency scale, where one account runs hundreds or thousands of sources across several people. Each release picks a specific moment where that scale used to force a detour — a dead token, a forty-widget report, a half-built source group — and removes the detour rather than adding a capability. Integration work stays additive and named: Ahrefs Rank Tracker, WhatConverts, Snowflake, bol., each filling a stated reporting gap rather than broadening a connector catalog.
◆ Prediction
Expect the same volume-driven treatment applied to the remaining multi-step setup flows, and further integrations chosen to close named gaps rather than to grow the connector count.
Alternatives to kernelshap and Whatagraph
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 Whatagraph.
Delta Lake
A 4.4.0 tag appears, but the feed carries only its release plumbing
distributions3
distributions3 0.3.0 adds sample-based distributions and likelihood derivatives
Basedash
Basedash keeps pushing its data out of the workspace — now to people without accounts
RStudio
RStudio ships through release branches, and the notes are commit messages
dbt Core
dbt Fusion's second beta is adapter work: ClickHouse gets materializations, indexes, and catalogs
See all kernelshap alternatives → · See all Whatagraph alternatives →
Recent activity from kernelshap and Whatagraph
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
- 20h agoWhatagraphUnify metrics and dimensions while creating a Source Group
- 7d agoWhatagraphTurn your report into client portal with Report shortcuts
- 21d agoWhatagraphOne broken connection won't break your reports
- 21d agoWhatagraphClearer charts and tables, and a faster way to find the right template
- 27d agoWhatagraphTrack your keywords against competitors with Ahrefs Rank Tracker
- 1mo agoWhatagraphBasis rebuilt: faster data, cleaner numbers, per-client sources
- 1y agokernelshapKernel weight bug fixed; parallelism moves to doFuture
- 1y agokernelshapSampling permutation SHAP with standard errors ⚡
- 2y 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 Whatagraph?
They serve adjacent needs but don't currently overlap on shipped themes. Whatagraph is currently shipping more aggressively (velocity 5.0 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 kernelshap better than Whatagraph?
Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. Whatagraph is currently shipping more aggressively (velocity 5.0 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 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 Whatagraph?
Top Whatagraph alternatives in Analytics are ranked by recent ship velocity. Browse the "Whatagraph alternatives" section above for the current picks, or visit /alternatives/whatagraph for the full list with editorial commentary on each.