SinusoidalRegressions.jl is a package that focuses on fitting data to sinusoidal models. Source and docs. It has been submitted to the general registry but it’s on the 3-day waiting period. Main features are:
- Implements IEEE 1057 3- and 4-parameter algorithms.
- Implements the sinusoidal regression algorithms developed by Jacquelin, which do not require initial parameter estimates and are non-iterative.
- A convenience front-end to
LsqFit.curve_fit. - Plot recipes for easy plotting of data and fit.
- Some basic fit error measurements.
I am not an expert in this field (I just needed this functionality for a project). I’d love to have feedback and ideas about how to improve the package, which at this point is still in development. Finally, if people would like to reserve the name for a future package, I’ll be happy to rename it.