predictsr vs radiatR

radiatR reads movement trajectories, plots them on circular axes, computes kinematics such as speed and path sinuosity, and runs the circular statistics that go with them, including tests of mean direction, symmetry and unimodality. It arrived as a first public release on 9 July 2026 with an accompanying Shiny app, and has had two releases since at roughly weekly intervals. The 0.1.x line is still setting its boundaries: 0.1.2 removes a loader dialect and makes previously silent data problems into errors.

Three releases in twelve days show a package hardening in public rather than accreting features. The direction of travel is toward refusing bad input instead of quietly working around it: non-finite coordinate rows now error by default rather than being dropped silently, combining Tracks objects rejects colliding trajectory ids and conflicting calibration metadata instead of merging them and discarding one side, and the Shiny app clears prior state before reading a new upload. The statistical surface is growing in parallel, but within the scope the first release already claimed.

Expect the remaining goodness-of-fit gap the notes name explicitly, Jones-Pewsey, to be filled in a later release, and the error-on-bad-input treatment to reach the parts of the loader it has not yet covered. A CRAN submission is the natural next step for a package this young, though nothing in these entries commits to one.