Source code for lezargus.container.spectra

"""Spectra data container.

This module and class primarily deals with spectral data.
"""

import copy

import numpy as np

import lezargus
from lezargus.container import LezargusContainerArithmetic
from lezargus.library import hint
from lezargus.library import logging


[docs] class LezargusSpectra(LezargusContainerArithmetic): """Container to hold spectral data and perform operations on it. Attributes ---------- For all available attributes, see :py:class:`LezargusContainerArithmetic`. """
[docs] def __init__( self: "LezargusSpectra", wavelength: hint.ndarray, data: hint.ndarray, uncertainty: hint.ndarray | None = None, wavelength_unit: str | hint.Unit | None = None, data_unit: str | hint.Unit | None = None, pixel_scale: float | None = None, slice_scale: float | None = None, mask: hint.ndarray | None = None, flags: hint.ndarray | None = None, header: hint.Header | None = None, ) -> None: """Instantiate the spectra class. Parameters ---------- wavelength : ndarray The wavelength axis of the spectral component of the data, if any. The unit of wavelength is typically in meters; but, check the :py:attr:`wavelength_unit` value. data : ndarray The data stored in this container. The unit of the flux is typically in W m^-2 m^-1; but, check the :py:attr:`data_unit` value. uncertainty : ndarray The uncertainty in the data of the spectra. The unit of the uncertainty is the same as the data value; per :py:attr:`uncertainty_unit`. wavelength_unit : Astropy Unit The unit of the wavelength array. If None, we assume unit-less. data_unit : Astropy Unit The unit of the data array. If None, we assume unit-less. pixel_scale : float, default = None The E-W, "x" dimension, pixel plate scale of the spatial component, if any. Must be in radians per pixel. Scale is None if none is provided. slice_scale : float, default = None The N-S, "y" dimension, pixel slice scale of the spatial component, if any. Must be in radians per slice/pixel. Scale is None if none is provided. mask : ndarray, default = None A mask of the data, used to remove problematic areas. Where True, the values of the data is considered masked. If None, we assume the mask is all clear. flags : ndarray, default = None Flags of the data. These flags store metadata about the data. If None, we assume that there are no harmful flags. header : Header, default = None A set of header data describing the data. Note that when saving, this header is written to disk with minimal processing. We highly suggest writing of the metadata to conform to the FITS Header specification as much as possible. If None, we just use an empty header. Returns ------- None """ # The data must be one dimensional. container_dimensions = 1 if len(data.shape) != container_dimensions: logging.error( error_type=logging.InputError, message=( "The input data for a LezargusSpectra instantiation has a" f" shape {data.shape}, which is not the expected one" " dimension." ), ) # The wavelength and the data must be parallel, and thus the same # shape. wavelength = np.array(wavelength, dtype=float) data = np.array(data, dtype=float) if wavelength.shape != data.shape: logging.critical( critical_type=logging.InputError, message=( f"Wavelength array shape: {wavelength.shape}; data array" f" shape: {data.shape}. The arrays need to be the same" " shape or cast-able to such." ), ) # Constructing the original class. We do not deal with WCS here because # the base class does not support it. We do not involve units here as # well for speed concerns. Both are handled during reading and writing. super().__init__( wavelength=wavelength, data=data, uncertainty=uncertainty, wavelength_unit=wavelength_unit, data_unit=data_unit, pixel_scale=pixel_scale, slice_scale=slice_scale, mask=mask, flags=flags, header=header, )
[docs] @classmethod def read_fits_file( cls: hint.Type[hint.Self], filename: str, ) -> hint.Self: """Read a Lezargus spectra FITS file. We load a Lezargus FITS file from disk. Note that this should only be used for 1-D spectra files. Parameters ---------- filename : str The filename to load. Returns ------- spectra : Self-like The LezargusSpectra class instance. """ # Any pre-processing is done here. # Loading the file. spectra = cls._read_fits_file(filename=filename) # Any post-processing is done here. # All done. return spectra
[docs] def write_fits_file( self: hint.Self, filename: str, overwrite: bool = False, ) -> hint.Self: """Write a Lezargus spectra FITS file. We write a Lezargus FITS file to disk. Parameters ---------- filename : str The filename to write to. overwrite : bool, default = False If True, overwrite file conflicts. Returns ------- None """ # Any pre-processing is done here. # Saving the file. self._write_fits_file(filename=filename, overwrite=overwrite)
# Any post-processing is done here. # All done.
[docs] def convolve(self: hint.Self, kernel: hint.ndarray) -> hint.Self: """Convolve the spectra with a custom kernel. We compute the convolution and return a near copy of the spectra after convolution. The wavelength is not affected. Parameters ---------- kernel : ndarray The kernel which we are using to convolve. Returns ------- convolved_spectra : ndarray A near copy of the spectra after convolution. """ # Using this kernel, we convolve the spectra. We assume that the # uncertainties add in quadrature. convolved_data = ( lezargus.library.convolution.convolve_1d_array_by_1d_kernel( array=self.data, kernel=kernel, ) ) convolved_uncertainty = np.sqrt( lezargus.library.convolution.convolve_1d_array_by_1d_kernel( self.uncertainty**2, kernel=kernel, ), ) # We also propagate the convolution of the mask and the flags where # needed. logging.error( error_type=logging.ToDoError, message=( "Propagation of mask and flags via convolution is not done." ), ) convolved_mask = self.mask convolved_flags = self.flags # From the above information, we construct the new spectra. spectra_class = type(self) convolved_spectra = spectra_class( wavelength=self.wavelength, data=convolved_data, uncertainty=convolved_uncertainty, wavelength_unit=self.wavelength_unit, data_unit=self.data_unit, mask=convolved_mask, flags=convolved_flags, header=self.header, ) # All done. return convolved_spectra
[docs] def interpolate( self: hint.Self, wavelength: hint.ndarray, skip_mask: bool = True, skip_flags: bool = True, ) -> tuple[ hint.ndarray, hint.ndarray, hint.ndarray | None, hint.ndarray | None, ]: """Interpolation calling function for spectra. Each entry is considered a single point to interpolate over. Parameters ---------- wavelength : ndarray The wavelength values which we are going to interpolate to. The units of the data of this array should be the same as the wavelength unit stored. skip_mask : bool, default = True If provided, the propagation of data mask through the interpolation is skipped. It is computationally a little expensive otherwise. skip_flags : bool, default = True If provided, the propagation of data flags through the interpolation is skipped. It is computationally a little expensive otherwise. Returns ------- interp_data : ndarray The interpolated data. interp_uncertainty : ndarray The interpolated uncertainty. interp_mask : ndarray or None A best guess attempt at finding the appropriate mask for the interpolated data. If skip_mask=True, then we skip the computation and return None instead. interp_flags : ndarray or None A best guess attempt at finding the appropriate flags for the interpolated data. If skip_flags=True, then we skip the computation and return None instead. """ # Interpolation cannot deal with NaNs, so we exclude any set of data # which includes them. ( clean_wavelength, clean_data, clean_uncertainty, ) = lezargus.library.array.clean_finite_arrays( self.wavelength, self.data, self.uncertainty, ) # If the wavelengths we are using to interpolate to are not all # numbers, it is a good idea to warn. It is not a good idea to change # the input the user provided. if not np.all(np.isfinite(wavelength)): logging.warning( warning_type=logging.AccuracyWarning, message=( "The input wavelength for interpolation are not all finite." ), ) # As a sanity check, we check if we are trying to interpolate outside # of our data range. overlap = lezargus.library.wrapper.wavelength_overlap_fraction( base=clean_wavelength, contain=wavelength, ) if overlap < 1: logging.warning( warning_type=logging.AccuracyWarning, message=( "Interpolation is attempted at a wavelength beyond the" " domain of wavelengths of this spectrum. The overlap" f" fraction is {overlap}." ), ) # The interpolated data for both the data itself and uncertainty. # We use gaps to remove any unwanted data, assuming the cleaned # wavelength is perfect. gap_size = lezargus.library.interpolate.get_smallest_gap( wavelength=clean_wavelength, ) interp_data = ( lezargus.library.interpolate.spline_1d_interpolate_gap_factory( x=clean_wavelength, y=clean_data, gap_size=gap_size, )(wavelength) ) interp_uncertainty = ( lezargus.library.interpolate.spline_1d_interpolate_gap_factory( x=clean_wavelength, y=clean_uncertainty, gap_size=gap_size, )(wavelength) ) # Checking if we need to compute the interpolation of a mask. if skip_mask: interp_mask = None else: interp_mask = np.full_like(interp_data, False) logging.error( error_type=logging.ToDoError, message=( "The interpolation of a mask for spectra is not yet" " implemented." ), ) # Checking if we need to compute the interpolation of flag array. if skip_flags: interp_flags = None else: interp_flags = np.full_like(interp_data, 1) logging.error( error_type=logging.ToDoError, message=( "The interpolation of flags for spectra is not yet" " implemented." ), ) # All done. return interp_data, interp_uncertainty, interp_mask, interp_flags
[docs] def stitch( self: "LezargusSpectra", *spectra: "LezargusSpectra", weight: list[hint.ndarray] | str = "uniform", average_routine: hint.Callable[ [hint.ndarray, hint.ndarray, hint.ndarray], tuple[float, float], ] = None, ) -> hint.Self: """Stitch together different spectra; we do not scaling. We stitch this spectra with input spectra. If the spectra are not already to the same scale however, this will result in wildly incorrect results. The header information is preserved, though we take what we can from the other objects. Parameters ---------- *spectra : LezargusSpectra A set of Lezargus spectra which we will stitch to this one. weight : list[ndarray] or str, default = None A list of the weights in the data for stitching. Each entry in the list must have a corresponding entry in the wavelength and data list, or None. For convenience, we provide short-cut inputs for the following: - `uniform` : Uniform weights. - `invar` : Inverse variance weights. average_routine : Callable, str, default = None The function used to average all of the spectra together. It must also be able to accept weights and propagate uncertainties. If None, we default to the weighted mean. Namely, it must be of the form f(val, uncert, weight) = avg, uncert. Returns ------- stitch_spectra : LezargusSpectra The spectra after stitching. """ # If there are no spectra to stitch, then we do nothing. if len(spectra) == 0: # We still warn just in case. logging.warning( warning_type=logging.InputWarning, message=( "No additional spectra objects were submitted to stitch, no" " stitching applied." ), ) return self # We need to make sure these are all Lezargus spectra. lz_spectra = [] for spectradex in spectra: if not isinstance(spectradex, LezargusSpectra): logging.critical( critical_type=logging.InputError, message=( f"Input type {type(spectradex)} is not a" " LezargusSpectra, we cannot use it to stitch." ), ) lz_spectra.append(spectradex) # We finally append ourselves. Working on a copy is probably for the # best. lz_spectra.append(copy.deepcopy(self)) # We need to translate the weight input. if isinstance(weight, str): weight = weight.casefold() if weight == "uniform": # We compute uniform weights. using_weights = [ np.ones_like(spectradex.wavelength) for spectradex in spectra ] elif weight == "invar": # We compute weights which are the inverse of the variance # in the data. using_weights = [ 1 / spectradex.uncertainty**2 for spectradex in spectra ] else: # A valid shortcut string has not been provided. accepted_options = ["uniform", "invar"] logging.critical( critical_type=logging.InputError, message=( f"The weight shortcut option {weight} is not valid; it" f" must be one of: {accepted_options}" ), ) else: using_weights = weight # Next, we stitch together the data for the spectra. ( stitch_wavelength, stitch_data, stitch_uncertainty, ) = lezargus.library.stitch.stitch_spectra_discrete( wavelength_arrays=[spectradex.wavelength for spectradex in spectra], data_arrays=[spectradex.data for spectradex in spectra], uncertainty_arrays=[ spectradex.uncertainty for spectradex in spectra ], weight_arrays=using_weights, average_routine=average_routine, ) # We also stitch together the flags and the mask. They are handled # with a different function. logging.error( error_type=logging.ToDoError, message="Flag and mask stitching not yet supported.", ) stitch_mask = None stitch_flags = None # We merge the header. logging.error( error_type=logging.ToDoError, message="Header stitching not yet supported.", ) stitch_header = None # We compile the new Spectra. We do not expect a subclass but we # try and allow it. stitch_spectra = self.__class__( wavelength=stitch_wavelength, data=stitch_data, uncertainty=stitch_uncertainty, wavelength_unit=self.wavelength_unit, data_unit=self.wavelength_unit, mask=stitch_mask, flags=stitch_flags, header=stitch_header, ) # All done. return stitch_spectra