finnts
Microsoft's automated forecasting framework, still mostly a one-maintainer effort.
Comparison · Infra & APIs
fdacluster vs Luminescence
A side-by-side editorial comparison of fdacluster and Luminescence — release velocity, themes, recent moves, and the top alternatives to consider.
Shared themes:r-package
fdacluster vs Luminescence: at a glance
What is fdacluster?
Functional data clustering grew from one algorithm into a comparable suite
fdacluster clusters functional data while separating amplitude from phase variation, aligning curves as part of the clustering rather than before it. The algorithm set covers k-means, hierarchical clustering and DBSCAN, all producing a common caps result object so runs can be compared directly. Version 0.4.0 tightened the interface with is_domain_interval and transformation arguments describing the input data, added compatibility checking between incompatible option combinations, and split the L2 and normalized L2 distances into separate C++ classes to enforce that plain L2 cannot be combined with dilation or affine warping it is not invariant to.
What is Luminescence?
Luminescence is revisiting the statistical assumptions baked into its dose-response fits.
The package provides luminescence dating analysis for the geochronology community — signal import from several instrument formats, dose-response curve fitting, and a large library of analysis routines. The current release changes how fitting weights are handled by default, on the reasoning that individual relative uncertainties do not in fact scale with dose as the previous approach assumed. Several releases in this window are historical versions backfilled into the feed, so their timestamps sit within minutes of each other and do not reflect when the work shipped.
fdacluster vs Luminescence: editorial side-by-side
fdacluster
0.0INFRA · APIS
Functional data clustering grew from one algorithm into a comparable suite
◆ Current state
fdacluster clusters functional data while separating amplitude from phase variation, aligning curves as part of the clustering rather than before it. The algorithm set covers k-means, hierarchical clustering and DBSCAN, all producing a common caps result object so runs can be compared directly. Version 0.4.0 tightened the interface with is_domain_interval and transformation arguments describing the input data, added compatibility checking between incompatible option combinations, and split the L2 and normalized L2 distances into separate C++ classes to enforce that plain L2 cannot be combined with dilation or affine warping it is not invariant to.
◆ Where it's heading
The trajectory runs from method implementation toward guardrails and portability. Early releases added capability; recent ones prevent misuse and reduce weight - dplyr, forcats, tidyr and purrr removed in 0.4.0, furrr swapped for future.apply - while 0.4.2 is entirely C++ correctness, replacing Armadillo's whole-object finiteness check with scalar std::isfinite and fixing an integer overflow in linear index computation that broke large datasets. Cadence is roughly one release a year.
◆ Prediction
Given that the last two releases were dependency reduction and numerical correctness rather than method work, expect the next to continue in that vein unless a new clustering algorithm is contributed.
Luminescence
2.5INFRA · APIS
Luminescence is revisiting the statistical assumptions baked into its dose-response fits.
◆ Current state
The package provides luminescence dating analysis for the geochronology community — signal import from several instrument formats, dose-response curve fitting, and a large library of analysis routines. The current release changes how fitting weights are handled by default, on the reasoning that individual relative uncertainties do not in fact scale with dose as the previous approach assumed. Several releases in this window are historical versions backfilled into the feed, so their timestamps sit within minutes of each other and do not reflect when the work shipped.
◆ Where it's heading
Two kinds of change dominate. The first is deliberate breaking changes made for correctness or consistency: the weighting rework, and import functions now uniformly appending the detector to record types so all formats behave as one always did. The second is a steady stream of new analysis functions contributed by the wider research community, covering crosstalk correction, spatial autocorrelation on grain discs, and incomplete bleaching models. Deprecated functions are being removed on a clear schedule rather than left indefinitely.
◆ Prediction
Expect further consolidation of defaults that were inherited rather than chosen, since the weighting change is framed as correcting earlier reasoning rather than adding an option.
Alternatives to fdacluster and Luminescence
Other Infra & APIs 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 fdacluster or Luminescence.
BayLum
Bayesian luminescence dating that finally replaced its folder-structure input format.
daedalus
An epidemic-economic model teaching its interventions to react to the outbreak itself.
bkmrhat
A parallel-chain helper for bkmr that has settled into pure upkeep.
driveR
A cancer driver prioritization package that ships rarely and mostly to stay installable
metR
A meteorology ggplot2 extension where the netCDF reader became the main event
See all fdacluster alternatives → · See all Luminescence alternatives →
Recent activity from fdacluster and Luminescence
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
- 26d agoLuminescenceReworks dose-response fitting weights, changing prior defaults
- 4mo agoLuminescenceFixes an uninitialised array and background overcounting
- 5mo agoLuminescenceImport functions now append detector type to record names
- 7mo agoLuminescenceAdds crosstalk correction, Moran's I, and dose-response fitting
- 7mo agoLuminescenceFixes baSAR reporting, fading input checks, and plot regressions
- 7mo agoLuminescenceAdds automatic background subtraction and record removal helpers
- 7mo agofdaclusterInteger overflow fixed for large datasets, C++ finiteness checks corrected
- 1y agofdaclusterParallel worker setup and an acronym correction
- 1y agofdaclusterInput description arguments and enforced distance-warping compatibility
- 3y agofdaclusterMedian centroids and centroids defined on unioned grids
- 3y agofdaclusterNamespace notation and optional dependency guards
- 3y agofdaclusterHierarchical clustering, DBSCAN and a shared result class arrive together ⚡
Frequently asked questions
What is the difference between fdacluster and Luminescence?
Both compete on the same themes — r-package — within Infra & APIs. Luminescence 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 fdacluster better than Luminescence?
Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. Luminescence 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 Infra & APIs products to evaluate alongside.
What are the best alternatives to fdacluster?
Top fdacluster alternatives in Infra & APIs are ranked by recent ship velocity. Browse the "fdacluster alternatives" section above for the current picks, or visit /alternatives/fdacluster for the full list with editorial commentary on each.
What are the best alternatives to Luminescence?
Top Luminescence alternatives in Infra & APIs are ranked by recent ship velocity. Browse the "Luminescence alternatives" section above for the current picks, or visit /alternatives/luminescence for the full list with editorial commentary on each.