Utilities for nonlinear least-squares fits.
- This package facilitates least-squares fitting of noisy data by
multi-dimensional, nonlinear functions of arbitrarily many parameters. lsqfit provides the fitting capability; it makes heavy use of package gvar, which provides tools for the analysis of error propagation, and also for the creation of complicated multi-dimensional gaussian distributions. (gvar is distributed separately.) lsqfit supports Bayesian priors for the fit parameters, with arbitrarily complicated multidimensional Gaussian distributions. It uses automatic differentiation to compute gradients, greatly simplifying the design of fit functions.
In addition to gvar, this package uses the Gnu Scientific Library (GSL) to do the fitting, numpy for efficient array arithmetic, and cython to compile efficient core routines and interface code.