DogBoxLSQFitter#
- class astropy.modeling.fitting.DogBoxLSQFitter(calc_uncertainties=False, use_min_max_bounds=False)[source]#
Bases:
_NLLSQFitter
DogBox algorithm and least squares statistic.
- Parameters:
- calc_uncertaintiesbool
If the covariance matrix should be computed and set in the fit_info. Default: False
- Attributes:
- fit_info
A
scipy.optimize.OptimizeResult
class which contains all of the most recent fit information
Attributes Summary
The constraint types supported by this fitter type.
Methods Summary
__call__
(model, x, y[, z, weights, maxiter, ...])Fit data to this model.
objective_function
(fps, *args[, ...])Function to minimize.
Attributes Documentation
- supported_constraints = ['fixed', 'tied', 'bounds']#
The constraint types supported by this fitter type.
Methods Documentation
- __call__(model, x, y, z=None, weights=None, maxiter=100, acc=1e-07, epsilon=np.float64(1.4901161193847656e-08), estimate_jacobian=False, filter_non_finite=False, *, inplace=False)#
Fit data to this model.
- Parameters:
- model
FittableModel
model to fit to x, y, z
- x
array
input coordinates
- y
array
input coordinates
- z
array
, optional input coordinates
- weights
array
, optional Weights for fitting. For data with Gaussian uncertainties, the weights should be 1/sigma.
Changed in version 5.3: Calculate parameter covariances while accounting for
weights
as “absolute” inverse uncertainties. To recover the old behavior, chooseweights=None
.- maxiter
int
maximum number of iterations
- acc
float
Relative error desired in the approximate solution
- epsilon
float
A suitable step length for the forward-difference approximation of the Jacobian (if model.fjac=None). If epsfcn is less than the machine precision, it is assumed that the relative errors in the functions are of the order of the machine precision.
- estimate_jacobianbool
If False (default) and if the model has a fit_deriv method, it will be used. Otherwise the Jacobian will be estimated. If True, the Jacobian will be estimated in any case.
- equivalencies
list
orNone
, optional, keyword-only List of additional equivalencies that are should be applied in case x, y and/or z have units. Default is None.
- filter_non_finitebool, optional
Whether or not to filter data with non-finite values. Default is False
- inplacebool, optional
If
False
(the default), a copy of the model with the fitted parameters set will be returned. IfTrue
, the returned model will be the same instance as the model passed in, and the parameter values will be changed inplace.
- model
- Returns:
- fitted_model
FittableModel
If
inplace
isFalse
(the default), this is a copy of the input model with parameters set by the fitter. Ifinplace
isTrue
, this is the same model as the input model, with parameters updated to be those set by the fitter.
- fitted_model
- objective_function(fps, *args, fit_param_indices=None)#
Function to minimize.
- Parameters:
- fps
list
parameters returned by the fitter
- args
list
[model, [weights], [input coordinates]]
- fit_param_indices
list
, optional The
fit_param_indices
as returned bymodel_to_fit_params
. This is a list of the parameter indices being fit, so excluding any tied or fixed parameters. This can be passed in to the objective function to prevent it having to be computed on every call. This must be optional as not all fitters support passing kwargs to the objective function.
- fps