r2rtf
The clinical-report table engine learned Chinese, then learned to leave RTF entirely
Comparison · Analytics
spatsoc vs tabnet
A side-by-side editorial comparison of spatsoc and tabnet — release velocity, themes, recent moves, and the top alternatives to consider.
spatsoc vs tabnet: at a glance
What is spatsoc?
One maintainer, one or two new collective-motion metrics per release, for two years straight
spatsoc turns animal relocation data into spatial and social groupings — dyads, fission-fusion events, group centroids — and the recent history is a metronomic accretion of collective-motion measures on top of that base. Since late 2024 nearly every release has added one or two: polarization, direction to leader, position along the group axis, directional correlation delay, edge alignment, edge zones. Development is essentially single-handed; almost every merged PR in this window carries the same author.
What is tabnet?
A tabular deep-learning model in R that keeps widening what counts as a tabular task.
tabnet ports the TabNet attentive tabular architecture to R on torch, wired into tidymodels through parsnip so it slots into workflows, tuning, and case weights like any other engine. The model surface has grown well past plain supervised fitting: unsupervised pretraining, missing values in predictors, multi-outcome fitting, hierarchical multi-label classification, and built-in explainability via tabnet_explain(). The 0.9.x line has been consolidating rather than adding, with 0.9.0 finally making hierarchical classification work correctly by accounting for the ancestor matrix.
spatsoc vs tabnet: editorial side-by-side
spatsoc
0.0ANALYTICS
One maintainer, one or two new collective-motion metrics per release, for two years straight
◆ Current state
spatsoc turns animal relocation data into spatial and social groupings — dyads, fission-fusion events, group centroids — and the recent history is a metronomic accretion of collective-motion measures on top of that base. Since late 2024 nearly every release has added one or two: polarization, direction to leader, position along the group axis, directional correlation delay, edge alignment, edge zones. Development is essentially single-handed; almost every merged PR in this window carries the same author.
◆ Where it's heading
The December 2025 release changes register. Alongside three new calc_distance / calc_direction / calc_centroid functions and an internal assertion family, it deprecates the `projection` argument in favour of `crs` and lands a round of checks and tests explicitly staged ahead of a new spatial interface. Read together, that is a package finishing its metric catalogue and starting to rework the coordinate-handling layer underneath it to match modern R-spatial conventions — the same evolution that made it drop its startup warning back in 0.2.7.
◆ Prediction
The next release is likely the spatial-interface rework the 0.2.12 test and assertion work was staged for, with `projection` moving from deprecated to removed. Feature additions should slow while that lands.
tabnet
2.5ANALYTICS
A tabular deep-learning model in R that keeps widening what counts as a tabular task.
◆ Current state
tabnet ports the TabNet attentive tabular architecture to R on torch, wired into tidymodels through parsnip so it slots into workflows, tuning, and case weights like any other engine. The model surface has grown well past plain supervised fitting: unsupervised pretraining, missing values in predictors, multi-outcome fitting, hierarchical multi-label classification, and built-in explainability via tabnet_explain(). The 0.9.x line has been consolidating rather than adding, with 0.9.0 finally making hierarchical classification work correctly by accounting for the ancestor matrix.
◆ Where it's heading
Two threads run through the release history. The first is task surface — each minor version tends to admit a class of problem the model previously could not express, from missing data to hierarchy to imbalanced binary outcomes. The second is torch-level performance and correctness, visible in the torch_ignite_adam default that cut pretraining time roughly 30% and the fix for optimizers frozen after checkpointing on cuda and mps. Tidymodels integration is treated as a first-class obligation, with parsnip breaking changes tracked release by release.
◆ Prediction
The hierarchical path is the least finished: 0.5.0 introduced it and 0.9.0 only just made it effective, so the next releases most likely extend evaluation and explainability to hierarchical fits rather than adding another task type.
Alternatives to spatsoc and tabnet
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 spatsoc or tabnet.
DoseFinding
New stewardship at openpharma, then two releases adding the methods MCP-Mod was missing
webmockr
The stubbing library added httr2 support, then spent a year cutting itself free of everything else
crul
crul took mocking back from webmockr and made it a property of the client itself
dendroNetwork
Six releases, six identical bodies — the feed carries the package abstract instead of release notes
chattr
chattr deleted every LLM integration it had written and outsourced the lot to ellmer
See all spatsoc alternatives → · See all tabnet alternatives →
Recent activity from spatsoc and tabnet
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
- 21d agotabnetvip dependency moves to r-universe
- 2mo agotabnetHierarchical classification made effective, augment() added
- 6mo agotabnetentmax15 and sparsemax15 masks, AUM loss for imbalanced data
- 8mo agospatsoccalc_* functions added; projection deprecated ahead of a spatial rework
- 10mo agospatsocEdge zones and edge direction added; centroid NA handling fixed
- 11mo agospatsocEdge alignment metric added
- 1y agospatsocLeader edge delay added; units dependency moves to a CRAN release
- 1y agotabnetBugfix release for R 4.5 and dials tuning
- 1y agospatsocDirectional correlation delay added; longlat direction bug fixed
- 1y agospatsocLeadership and group-axis position measures added
- 2y agotabnetCase weights and warm-start parameters via parsnip
- 2y agotabnetHierarchical multi-label classification via data.tree ⚡
Frequently asked questions
What is the difference between spatsoc and tabnet?
They serve adjacent needs but don't currently overlap on shipped themes. tabnet 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 spatsoc better than tabnet?
Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. tabnet 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 spatsoc?
Top spatsoc alternatives in Analytics are ranked by recent ship velocity. Browse the "spatsoc alternatives" section above for the current picks, or visit /alternatives/spatsoc for the full list with editorial commentary on each.
What are the best alternatives to tabnet?
Top tabnet alternatives in Analytics are ranked by recent ship velocity. Browse the "tabnet alternatives" section above for the current picks, or visit /alternatives/tabnet for the full list with editorial commentary on each.