How to use the stingray.modeling.PSDParEst function in stingray

max_post=True
                    fitmethod="BFGS"

                else:
                    as_priors=None
                    logging.warn("fit_power_density_spectrum: can't create priors from dave_priors.")

            if as_priors:
                # Creates a Posterior object with the priors
                lpost = PSDPosterior(pds.freq, pds.power, fit_model, priors=as_priors, m=pds.m)
            else:
                # Creates the Maximum Likelihood object for fitting
                lpost = PSDLogLikelihood(pds.freq, pds.power, fit_model, m=pds.m)

            # Creates the PSD Parameters Estimation object and runs the fitting
            parest = PSDParEst(pds, fitmethod=fitmethod, max_post=max_post)
            res = parest.fit(lpost, starting_pars, neg=True)

            sample = None
            if as_priors and sampling_params is not None:
                # If is a Bayesian Par. Est. and has sampling parameters
                # then sample the posterior distribution defined in `lpost` using MCMC
                sample = parest.sample(lpost, res.p_opt, cov=res.cov,
                                         nwalkers=sampling_params["nwalkers"],
                                         niter=sampling_params["niter"],
                                         burnin=sampling_params["burnin"],
                                         threads=sampling_params["threads"],
                                         print_results=False, plot=False)

            # Prepares the results to be returned to GUI
            fixed = [fit_model.fixed[n] for n in fit_model.param_names]
            parnames = [n for n, f in zip(fit_model.param_names, fixed) \