A Python-based spectral fitting pipeline for analyzing quasar and galaxy spectra. This pipeline enables the decomposition of spectral components and allows users to fit models to data with customizable parameters.
- Customizable spectral models for quasar and galaxy fitting.
- Simultaneous spectral fitting for multiple (for example, multi-epoch) spectra.
- Supports multi-component decomposition (e.g., AGN/galaxy continuum, emission lines).
- Easy-to-modify parameters to suit various data sources and needs.
- Outputs key metrics, plots, and statistical fits for analysis.
To install the required packages, clone the repository and use the following commands:
git clone https://github.com/qian-yang/QGfit.git
cd QGfitWe recommend to create a new conda environment with Python 3.8:
conda create -n QGfit_public python=3.8
conda activate QGfit_publicInstall the package with setup.py and requirements.txt:
pip install .Install kapteyn:
pip install https://www.astro.rug.nl/software/kapteyn/kapteyn-3.0.tar.gzTo use the Galactic dust extinction map from Schlegel, Finkbeiner & Davis (1998), set up your SFD_PATH path in your bash file:
export SFD_PATH=your/path/to/sfddata- Prepare Your Data: Ensure the input spectra are in the correct format, for example,
- wave: wavelength, in units of angstrom.
- flux: flux density, in units of ergs/s/cm^2/A.
- fluxerr: flux density uncertainty, in units of ergs/s/cm^2/A. [Optional: If no, you may set them to identical values.]
- z: redshift, if the wavelength is in the observational frame. [Optional: set to 0 if the wavelength is in the rest frame.]
- ra and dec: Right Ascension (RA) and Declination (Dec) for Galactic extinction.
-
QGfit can fit a single spectrum, for example,
from astropy.io import fits from qgfit.fitter import QGfitObj z = 0.29379 ra = 10.160011 dec = 16.16387 file = './J0040+1609/J0040+1609_2023-08-25_MMT.fits' hdu = fits.open(file) spec = hdu[1].data obj = [{'wave':spec['wave'], 'flux':spec['flux'], 'fluxerr':spec['fluxerr'], 'ra':ra, 'dec':dec}] fitter = QGfitObj(obj, z=z, path='./J0040+1609/', name='J0040+1609_bright', conti_mcmc=False, line_fit=True, comp_plot=['Ha', 'Hb']) result = fitter.run_fit()
Figure 1. Example of spectral fitting using `QGfit` to J0040+1609, as an example. The black and gray lines are the spectral flux densities (in units of 10⁻¹⁷ erg s⁻¹ cm⁻² Å⁻¹) and their uncertainties. The top panel shows the decomposition of continuum emission, including AGN power-law (purple), UV Fe II (green), and host galaxy stellar populations, both young (orange) and old (yellow). The continuum windows we used are shown as blue shaded bars on the top x-axis. The cyan dotted lines are the total models from the continuum components described above, and the red dash lines are the total models including continuum and line emission. In the bottom panels, we show the emission-line fitting in the Hα (left) and Hβ (right) window, showing best-fit broad (cyan dash lines) and narrow (green solid lines) emission components. The red dash lines show the total model of broad and narrow line components.
You can disable the vertical lines by setting plot_vertical_line=False in the qfitobj function or in the configuration.py file.
- QGfit can fit multiple spectra simutaniously, for example,
file1 = './J0040+1609/J0040+1609_2000-12-06_SDSS.fits'
file2 = './J0040+1609/J0040+1609_2023-08-25_MMT.fits'
hdu1 = fits.open(file1)
hdu2 = fits.open(file2)
spec1 = hdu1[1].data
spec2 = hdu2[1].data
obj = [{'wave':spec1['wave'], 'flux':spec1['flux'], 'fluxerr':spec1['fluxerr'],
'ra':ra, 'dec':dec},
{'wave':spec2['wave'], 'flux':spec2['flux'], 'fluxerr':spec2['fluxerr'],
'ra':ra, 'dec':dec}]
fitter = QGfitObj(obj, z=z, path='./J0040+1609/', name='J0040+1609',
conti_mcmc=False, line_fit=True,
comp_plot=['Ha', 'Hb'], host_tie='same')
result = fitter.run_fit()
Figure 2. Example of spectral fitting using `QGfit` to J0040+1609, as an example, in the faint (left) and bright (right) states.
The host_tie parameter can be used to define the relationship of the host galaxy components between different spectra. The available options are:
host_tie='same': The host galaxy components are identical across different spectra.host_tie='similar': The host galaxy components have a similar shape, but with a scaling factor as a free parameter.host_tie='separate': The host galaxy components are fitted independently in each spectrum.
- Outputs, for example,
The data is stored in a .pkl file, and you can customize the saved data in configuration.py.
The figure is stored in a PDF file, and you can customize the figure settings in configuration.py. The multiple spectra are stored on separate pages within the PDF file.
Check the examples/ folder for sample input data and corresponding output plots.
python example_J1231+3232_bright.py
python example_J1231+3232.pyUsers can modify the following parameters in the configuration file (configuration.py):
The format is parameter name: default setting (notes).
- Wavelength Mask
wave_range:[1275, 8150]mask:False(If True, can customizemask_arrarray, valid value = 0)
-
Process Spectrum
do_deredden:True(If true, galactic deredden the spectrum)flux_factor:1e-17(default flux density factor 1e-17 ergs/s/A/cm^2)
-
Cosmology (FlatLambdaCDM)
H0:70Om0:0.3
-
Fit Continuum
conti_pl:True(continuum component: AGN power law)conti_fe_uv:True(continuum component: UV FeII)conti_fe_op:True(continuum component: optical FeII)conti_balmer:False(continuum component: Balmer emission)conti_host:True(continuum component: host galaxy)
-
Host Galaxy
host_zcut:1.2(turn off host components whenz > host_zcut)host_young:True(young stellar component)host_old:True(old stellar component)host_av:True(host galaxy components extinction)
-
Tie Host Method
host_tie:'same'(choices:'same','similar', or'separate')- Note for
'similar'host_factor_low:0.5host_factor_high:2.0
- Note for
host_input:False(force the host component from input)
-
Continuum Technique
-
check_nelder:False -
check_kmpfit:True -
ftol:1e-8 -
xtol:1e-8 -
conti_redchi_limit:1.5(If the continuum fitting reduced chi2 value is grea 872E ter than this value, try additional methods) -
line_redchi_limit:1.5(If the line fitting reduced chi2 value is greater than this value, try additional methods) -
Continuum MCMC Parameters
conti_mcmc:Falseconti_workers:1conti_nwalkers:100conti_steps:1000conti_burn:200conti_thin:1conti_progress:True
-
-
Line Fitting
-
line_fit:True -
mask_lowSN:True(mask strong absorption region) -
SN_mask:1.0(If flux < fluxerr * SN_mask, mask this region) -
line_file:os.path.join(datadir, 'lines.csv')(emission lines and parameters listed in template/lines.csv) -
line_input:False -
Tie Narrow Lines
tie_width:Truetie_shift:Truetie_flux:True
-
Line MCMC Parameters
line_mcmc:Falseline_workers:1line_nwalkers:100line_steps:1000line_burn:200line_thin:1line_progress:True
-
Line Parameters
fwhm_broad_min:1200(in units of km/s)fwhm_broad_max:20000fwhm_mix_min:160fwhm_mix_max:20000fwhm_narrow_min:160fwhm_narrow_max:1200gammar_max_broad:1e5gammar_max_mix:1e5gammar_max_narrow:10.0skew_limit:1test_add_broad:True(If True, determine whether the broad component is necessary by using the BIC)
-
-
Save Options
write:Truesave_input:True(If True, save the input data)save_config:True(If True, save the configuration; highly recommend to save this)save_window:True(save the continuum fitting windows)save_data:Truesave_conti_chains:Falsesave_line_chains:False
-
Calculate Physical Properties
prop:True(If True, calculate physical properties, such as luminosities)conti_wave:[1350.0, 2500.0, 3000.0, 4400.0, 5100.0](continuum luminosity at wavelength in the rest frame)
-
Plotting Options
plot:Trueplot_conti_mcmc_corner:Falseplot_line:Trueplot_vertical_line:False(If True, plot vertical dash lines for emission lines.)comp_plot:['Ha', 'Hb', 'MgII', 'CIII', 'CIV', 'Lya'](plot emission line windows)
-
Print Options
verbose_conti:True(If True, print continuum fitting details, such as redchi2, time)verbose_line:False(If True, print line fitting details)
The initial values for the continuum fitting parameters are stored in the template/conti_pars2.csv file.
The emission lines to be fitted and their initial values are stored in the template/lines.csv file.
The initial continuum fitting windows are stored in the conti_window function in the init_par.py file.
If you use this pipeline in your research, please cite the following paper:
Yang, et al. (2024), arXiv:2408.16183. doi:10.48550/arXiv.2408.16183
Alternatively, use this BibTeX entry:
@ARTICLE{Yang2024,
author = {{Yang}, Qian and {Green}, Paul J. and {Wu}, Xue-Bing and {Eracleous}, Michael and {Jiang}, Linhua and {Fu}, Yuming},
title = "{Galaxies Lighting Up: Discovery of Seventy New Turn-on Changing-look Quasars}",
journal = {arXiv e-prints},
keywords = {Astrophysics - Astrophysics of Galaxies},
year = 2024,
month = aug,
eid = {arXiv:2408.16183},
pages = {arXiv:2408.16183},
doi = {10.48550/arXiv.2408.16183},
archivePrefix = {arXiv},
eprint = {2408.16183},
primaryClass = {astro-ph.GA},
adsurl = {https://ui.adsabs.harvard.edu/abs/2024arXiv240816183Y},
adsnote = {Provided by the SAO/NASA Astrophysics Data System}
}This project is licensed under the MIT License - see the LICENSE file for details.
For questions or issues, please reach out to qianyang.astro@gmail.com.
This code is inspired by Yue Shen's QSOFit and Hengxiao Guo's code PyQSOFit. For details, see Shen et al. (2015) and Guo et al. (2018).
Qian Yang gratefully acknowledges the valuable comments and suggestions from Paul J. Green.