mgwr.gwr.GWR, ini_params=None, tol=1e-05, max_iter=20, solve='iwls', lite=False, pool=None)[source]

Method that fits a model with a particular estimation routine.

ini_betasarray, optional

k*1, initial coefficient values, including constant. Default is None, which calculates initial values during estimation.

tol: float, optional

Tolerence for estimation convergence. Default is 1.0e-5.

max_iterinteger, optional

Maximum number of iterations if convergence not achieved. Default is 20.

solvestring, optional

Technique to solve MLE equations. Default is ‘iwls’, meaning iteratively ( re)weighted least squares.

litebool, optional

Whether to estimate a lightweight GWR that computes the minimum diagnostics needed for bandwidth selection (could speed up bandwidth selection for GWR) or to estimate a full GWR. Default is False.

poolA multiprocessing Pool object to enable parallel fitting; default is None.

If lite=False, return a GWRResult instance; otherwise, return a GWRResultLite instance.