U e{j*@sddlZddlmZmZddgZGdddeZGdddeZdd Z d d Z d d Z ddZ d#ddZ ddZddZddZddZd$ddZd%ddZdd Zd!d"ZdS)&N)Model custom_modeldiscretize_modelKernelSizeErrorc@seZdZdZdS)DiscretizationErrorz: Called when discretization of models goes wrong. N__name__ __module__ __qualname____doc__r r X/var/www/html/bwave/python/venv/lib/python3.8/site-packages/astropy/convolution/utils.pyr src@seZdZdZdS)rz. Called when size of kernels is even. Nrr r r r rscCs4t|ttfrt|d Stdd|jDSdS)Ncss|]}|d VqdS)rNr .0Z axes_sizer r r sz has_even_axis..) isinstancelisttuplelenanyshape)arrayr r r has_even_axissrcCs tddS)Nz$Kernel size must be odd in all axes.)rr r r r raise_even_kernel_exceptionsrcCs|j|jkrT|}|jd}t||jd||jdd}|||7<|S|j|jkr|}|jd}t||jd||jdd}|||7<|S||S)zw Add two 1D kernel arrays of different size. The arrays are added with the centers lying upon each other. r)sizecopyslice)array_1array_2 new_arraycenterZslice_r r r add_kernel_arrays_1D s  "  "r#cCsJ|j|jkr|}dd|jD}t|d|jdd|d|jddd}t|d|jdd|d|jddd}|||f|7<|S|j|jkrB|}dd|jD}t|d|jdd|d|jddd}t|d|jdd|d|jddd}|||f|7<|S||S)zw Add two 2D kernel arrays of different size. The arrays are added with the centers lying upon each other. cSsg|] }|dqSrr rr r r =sz(add_kernel_arrays_2D..rrrcSsg|] }|dqSr$r rr r r r%Hs)rrrr)rr r!r"Zslice_xZslice_yr r r add_kernel_arrays_2D5s6 r&r" cCst|stdt|ts$t|}|j}|dkr:tdtt | sTtd|rrtt | srtd|dkr|dkrtd|dkr|dk rtd |d kr|dkrt ||S|dkrt |||Sn|d kr|dkrt ||S|dkr~t|||Snx|d kr@|dkr&t|||S|dkr~t||||Sn>|d krv|dkr^t||S|dkr~t|||SntddS)a Function to evaluate analytical model functions on a grid. So far the function can only deal with pixel coordinates. Parameters ---------- model : `~astropy.modeling.Model` or callable. Analytic model function to be discretized. Callables, which are not an instances of `~astropy.modeling.Model` are passed to `~astropy.modeling.custom_model` and then evaluated. x_range : tuple x range in which the model is evaluated. The difference between the upper an lower limit must be a whole number, so that the output array size is well defined. y_range : tuple, optional y range in which the model is evaluated. The difference between the upper an lower limit must be a whole number, so that the output array size is well defined. Necessary only for 2D models. mode : str, optional One of the following modes: * ``'center'`` (default) Discretize model by taking the value at the center of the bin. * ``'linear_interp'`` Discretize model by linearly interpolating between the values at the corners of the bin. For 2D models interpolation is bilinear. * ``'oversample'`` Discretize model by taking the average on an oversampled grid. * ``'integrate'`` Discretize model by integrating the model over the bin using `scipy.integrate.quad`. Very slow. factor : float or int Factor of oversampling. Default = 10. Returns ------- array : `numpy.array` Model value array Notes ----- The ``oversample`` mode allows to conserve the integral on a subpixel scale. Here is the example of a normalized Gaussian1D: .. plot:: :include-source: import matplotlib.pyplot as plt import numpy as np from astropy.modeling.models import Gaussian1D from astropy.convolution.utils import discretize_model gauss_1D = Gaussian1D(1 / (0.5 * np.sqrt(2 * np.pi)), 0, 0.5) y_center = discretize_model(gauss_1D, (-2, 3), mode='center') y_corner = discretize_model(gauss_1D, (-2, 3), mode='linear_interp') y_oversample = discretize_model(gauss_1D, (-2, 3), mode='oversample') plt.plot(y_center, label='center sum = {0:3f}'.format(y_center.sum())) plt.plot(y_corner, label='linear_interp sum = {0:3f}'.format(y_corner.sum())) plt.plot(y_oversample, label='oversample sum = {0:3f}'.format(y_oversample.sum())) plt.xlabel('pixels') plt.ylabel('value') plt.legend() plt.show() zModel must be callable.rz2discretize_model only supports 1-d and 2-d models.zUThe difference between the upper and lower limit of 'x_range' must be a whole number.zUThe difference between the upper and lower limit of 'y_range' must be a whole number.Nz'y range not specified, but model is 2-drz)y range specified, but model is only 1-d.r"Z linear_interpZ oversampleZ integratez Invalid mode.)callable TypeErrorrrrZn_inputs ValueErrorfloatnpdiff is_integerdiscretize_center_1Ddiscretize_center_2Ddiscretize_linear_1Ddiscretize_bilinear_2Ddiscretize_oversample_1Ddiscretize_oversample_2Ddiscretize_integrate_1Ddiscretize_integrate_2Dr)modelx_rangey_rangemodefactorndimr r r rTsRF              cCstj|}||S)zH Discretize model by taking the value at the center of the bin. r,arange)r7r8xr r r r/s r/cCs.tj|}tj|}t||\}}|||S)zJ Discretize model by taking the value at the center of the pixel. r,r>meshgrid)r7r8r9r?yr r r r0s  r0cCs@t|dd|dd}||}d|dd|ddS)z@ Discretize model by performing a linear interpolation. r?rNr=)r7r8r?values_intermediate_gridr r r r1sr1cCst|dd|dd}t|dd|dd}t||\}}|||}d|ddddf|ddddf}d|ddddf|ddddf}|S)zB Discretize model by performing a bilinear interpolation. rrCrNrDr@)r7r8r9r?rBrEvaluesr r r r2s ,,r2cCsvtj|dddd||dddd|t|d|d|d}||}t||j||f}|jddS)H Discretize model by taking the average on an oversampled grid. rrCrnumZaxis)r,linspaceintreshapermean)r7r8r;r?rFr r r r3sr3c Cstj|dddd||dddd|t|d|d|d}tj|dddd||dddd|t|d|d|d}t||\}}|||}|j|||j||f} t|| }|jddjddS)rGrrCrrHrJ)r,rKrLrArrMrN) r7r8r9r;r?rBZx_gridZy_gridrFrr r r r4 s  r4c Csnddlm}t|dd|dd}tg}t|jdD](}t|||||||dd}q@|S)zM Discretize model by integrating numerically the model over the bin. r)quadrCr)scipy.integraterPr,r>rrangerappend)r7r8rPr?rFir r r r5#s   &r5c sddlm}t|dd|dd}t|dd|ddtjd|jdf}t|jdD]^}tjdD]J|fdd||||dfddfddd d||f<q~ql|S) zC Discretize model by integrating the model over the pixel. r)dblquadrCrcs ||SNr )rBr?)r7r r Bz)discretize_integrate_2D..csSrVr r?jrBr r rWErXcs dS)Nrr rYrZr r rWFrX)funcabZgfunZhfun)rQrUr,r>emptyrrR)r7r8r9rUr?rFrTr )r[r7rBr r63s      r6)Nr"r')r')r')numpyr,Zastropy.modeling.corerr__all__ Exceptionrrrrr#r&rr/r0r1r2r3r4r5r6r r r r s" w