brsa.py 文件源码

def _set_SNR_grids(self):
        """ Set the grids and weights for SNR used in numerical integration
            of SNR parameters.
        """
        if self.SNR_prior == 'unif':
            SNR_grids = np.linspace(0, 1, self.SNR_bins)
            SNR_weights = np.ones(self.SNR_bins) / (self.SNR_bins - 1)
            SNR_weights[0] = SNR_weights[0] / 2.0
            SNR_weights[-1] = SNR_weights[-1] / 2.0
        elif self.SNR_prior == 'lognorm':
            dist = scipy.stats.lognorm
            alphas = np.arange(np.mod(self.SNR_bins, 2),
                               self.SNR_bins + 2, 2) / self.SNR_bins
            # The goal here is to divide the area under the pdf curve
            # to segments representing equal probabilities.
            bounds = dist.interval(alphas, (self.logS_range,))
            bounds = np.unique(bounds)
            # bounds contain the boundaries which equally separate
            # the probability mass of the distribution
            SNR_grids = np.zeros(self.SNR_bins)
            for i in np.arange(self.SNR_bins):
                SNR_grids[i] = dist.expect(
                    lambda x: x, args=(self.logS_range,),
                    lb=bounds[i], ub=bounds[i + 1]) * self.SNR_bins
            # Center of mass of each segment between consecutive
            # bounds are set as the grids for SNR.
            SNR_weights = np.ones(self.SNR_bins) / self.SNR_bins
        else:  # SNR_prior == 'exp'
            SNR_grids = self._bin_exp(self.SNR_bins)
            SNR_weights = np.ones(self.SNR_bins) / self.SNR_bins
        SNR_weights = SNR_weights / np.sum(SNR_weights)
        return SNR_grids, SNR_weights