def __call__(self, x):
"""
Weights based on input model choice
Parameters
----------
x : float
values for model evaluation
"""
# sort the initial mass along this isochrone
sindxs = np.argsort(x)
# Compute the mass bin boundaries
mass_bounds = compute_bin_boundaries(x[sindxs])
# integrate the IMF over each bin
if self.model["name"] == "kroupa":
imf_func = pmfuncs._imf_kroupa
elif self.model["name"] == "salpeter":
imf_func = pmfuncs._imf_salpeter
elif self.model["name"] == "flat":
imf_func = pmfuncs._imf_flat
# calculate the average prior in each mass bin
mass_weights = np.zeros(len(x))
for i, cindx in enumerate(sindxs):
# fmt: off
mass_weights[cindx] = (quad(imf_func, mass_bounds[i], mass_bounds[i + 1]))[0]
# fmt: on
mass_weights[cindx] /= mass_bounds[i + 1] - mass_bounds[i]
# normalize to avoid numerical issues (too small or too large)
mass_weights /= np.average(mass_weights)
return mass_weights
def test_bin_boundaries():
"""
Test bin boundaries
"""
bin_centers = np.array([1, 2, 5, 10, 50])
weights = compute_bin_boundaries(bin_centers)
expected_weights = [0.5, 1.5, 3.5, 7.5, 30.0, 70.0]
np.testing.assert_allclose(
weights, expected_weights, err_msg=("Stellar bin boundaries error")
)
def __call__(self, x):
"""
Weights based on input model choice
Parameters
----------
x : float
values for model evaluation
"""
# sort the initial mass along this isochrone
sindxs = np.argsort(x)
# Compute the mass bin boundaries
mass_bounds = compute_bin_boundaries(x[sindxs])
# integrate the IMF over each bin
args = None
if self.model["name"] == "kroupa":
if "alpha0" in self.model.keys(
): # assume other alphas also present
args = (
self.model["alpha0"],
self.model["alpha1"],
self.model["alpha2"],
self.model["alpha3"],
)
imf_func = pmfuncs._imf_kroupa
elif self.model["name"] == "salpeter":
if "slope" in self.model.keys():
slope = self.model["slope"]
args = (slope, )
imf_func = pmfuncs._imf_salpeter
elif self.model["name"] == "flat":
imf_func = pmfuncs._imf_flat
# calculate the average prior in each mass bin
mass_weights = np.zeros(len(x))
for i, cindx in enumerate(sindxs):
# fmt: off
if args is not None:
mass_weights[cindx] = (quad(imf_func, mass_bounds[i],
mass_bounds[i + 1], args))[0]
else:
mass_weights[cindx] = (quad(imf_func, mass_bounds[i],
mass_bounds[i + 1]))[0]
# fmt: on
mass_weights[cindx] /= mass_bounds[i + 1] - mass_bounds[i]
# normalize to avoid numerical issues (too small or too large)
mass_weights /= np.average(mass_weights)
return mass_weights
def compute_mass_prior_weights(masses, mass_prior_model):
"""
Compute the mass prior for the specificed model
Parameters
----------
masses : numpy vector
masses
mass_prior_model: dict
dict including prior model name and parameters
Returns
-------
mass_weights : numpy vector
Unnormalized IMF integral for each input mass
integration is done between each bin's boundaries
"""
# sort the initial mass along this isochrone
sindxs = np.argsort(masses)
# Compute the mass bin boundaries
mass_bounds = compute_bin_boundaries(masses[sindxs])
# compute the weights = mass bin widths
mass_weights = np.empty(len(masses))
# integrate the IMF over each bin
if mass_prior_model["name"] == "kroupa":
imf_func = imf_kroupa
elif mass_prior_model["name"] == "salpeter":
imf_func = imf_salpeter
elif mass_prior_model["name"] == "flat":
imf_func = imf_flat
else:
raise NotImplementedError("input mass prior function not supported")
# calculate the average prior in each mass bin
for i in range(len(masses)):
mass_weights[sindxs[i]] = (quad(
imf_func, mass_bounds[i],
mass_bounds[i + 1]))[0] / (mass_bounds[i + 1] - mass_bounds[i])
# normalize to avoid numerical issues (too small or too large)
mass_weights /= np.average(mass_weights)
return mass_weights
def __call__(self, x):
"""
Weights based on input model choice
Parameters
----------
x : float
values for model evaluation
"""
if self.model["name"] == "flat_log":
weights = 1.0 / np.diff(10**compute_bin_boundaries(x))
return weights / np.sum(weights)
elif self.model["name"] == "exponential":
return pmfuncs._exponential(10.0**x, tau=self.model["tau"] * 1e9)
else:
return super().__call__(x)
def gen_SimObs_from_sedgrid(
sedgrid,
sedgrid_noisemodel,
nsim=100,
compl_filter="F475W",
complcut=None,
magcut=None,
ranseed=None,
vega_fname=None,
weight_to_use="weight",
age_prior_model=None,
mass_prior_model=None,
):
"""
Generate simulated observations using the physics and observation grids.
The priors are sampled as they give the ensemble model for the stellar
and dust distributions (IMF, Av distribution etc.).
The physics model gives the SEDs based on the priors.
The observation model gives the noise, bias, and completeness all of
which are used in simulating the observations.
Currently written to only work for the toothpick noisemodel.
Parameters
----------
sedgrid: grid.SEDgrid instance
model grid
sedgrid_noisemodel: beast noisemodel instance
noise model data
nsim : int
number of observations to simulate
compl_filter : str
Filter to use for completeness (required for toothpick model).
Set to max to use the max value in all filters.
complcut : float (defualt=None)
completeness cut for only including model seds above the cut
where the completeness cut ranges between 0 and 1.
magcut : float (defualt=None)
faint-end magnitude cut for only including model seds brighter
than the given magnitude in compl_filter.
ranseed : int
used to set the seed to make the results reproducable,
useful for testing
vega_fname : string
filename for the vega info, useful for testing
weight_to_use : string (default='weight')
Set to either 'weight' (prior+grid), 'prior_weight', 'grid_weight',
or 'uniform' (this option is valid only when nsim is supplied) to
choose the weighting for SED selection.
age_prior_model : dict
age prior model in the BEAST dictonary format
mass_prior_model : dict
mass prior model in the BEAST dictonary format
Returns
-------
simtable : astropy Table
table giving the simulated observed fluxes as well as the
physics model parmaeters
"""
n_models, n_filters = sedgrid.seds.shape
flux = sedgrid.seds
# get the vega fluxes for the filters
_, vega_flux, _ = Vega(source=vega_fname).getFlux(sedgrid.filters)
# cache the noisemodel values
model_bias = sedgrid_noisemodel["bias"]
model_unc = np.fabs(sedgrid_noisemodel["error"])
model_compl = sedgrid_noisemodel["completeness"]
# only use models that have non-zero completeness in all filters
# zero completeness means the observation model is not defined for that filters/flux
ast_defined = model_compl > 0.0
sum_ast_defined = np.sum(ast_defined, axis=1)
goodobsmod = sum_ast_defined >= n_filters
# completeness from toothpick model so n band completeness values
# require only 1 completeness value for each model
# max picked to best "simulate" how the photometry detection is done
if compl_filter.lower() == "max":
model_compl = np.max(model_compl, axis=1)
else:
short_filters = [
filter.split(sep="_")[-1].upper() for filter in sedgrid.filters
]
if compl_filter.upper() not in short_filters:
raise NotImplementedError(
"Requested completeness filter not present:" +
compl_filter.upper() + "\nPossible filters:" +
"\n".join(short_filters))
filter_k = short_filters.index(compl_filter.upper())
print("Completeness from %s" % sedgrid.filters[filter_k])
model_compl = model_compl[:, filter_k]
# if complcut is provided, only use models above that completeness cut
# in addition to the non-zero completeness criterion
if complcut is not None:
goodobsmod = (goodobsmod) & (model_compl >= complcut)
# if magcut is provided, only use models brighter than the magnitude cut
# in addition to the non-zero completeness criterion
if magcut is not None:
fluxcut_compl_filter = 10**(-0.4 * magcut) * vega_flux[filter_k]
goodobsmod = (goodobsmod) & (flux[:, filter_k] >= fluxcut_compl_filter)
# initialize the random number generator
rangen = default_rng(ranseed)
# if the age and mass prior models are given, use them to determine the
# total number of stars to simulate
model_indx = np.arange(n_models)
if (age_prior_model is not None) and (mass_prior_model is not None):
nsim = 0
# logage_range = [min(sedgrid["logA"]), max(sedgrid["logA"])]
mass_range = [min(sedgrid["M_ini"]), max(sedgrid["M_ini"])]
# compute the total mass and average mass of a star given the mass_prior_model
nmass = 100
masspts = np.logspace(np.log10(mass_range[0]), np.log10(mass_range[1]),
nmass)
massprior = compute_mass_prior_weights(masspts, mass_prior_model)
totmass = np.trapz(massprior, masspts)
avemass = np.trapz(masspts * massprior, masspts) / totmass
# compute the mass of the remaining stars at each age and
# simulate the stars assuming everything is complete
gridweights = sedgrid[weight_to_use]
gridweights = gridweights / np.sum(gridweights)
grid_ages = np.unique(sedgrid["logA"])
ageprior = compute_age_prior_weights(grid_ages, age_prior_model)
bin_boundaries = compute_bin_boundaries(grid_ages)
bin_widths = np.diff(10**(bin_boundaries))
totsim_indx = np.array([], dtype=int)
for cage, cwidth, cprior in zip(grid_ages, bin_widths, ageprior):
gmods = sedgrid["logA"] == cage
cur_mass_range = [
min(sedgrid["M_ini"][gmods]),
max(sedgrid["M_ini"][gmods]),
]
gmass = (masspts >= cur_mass_range[0]) & (masspts <=
cur_mass_range[1])
curmasspts = masspts[gmass]
curmassprior = massprior[gmass]
totcurmass = np.trapz(curmassprior, curmasspts)
# compute the mass remaining at each age -> this is the mass to simulate
simmass = cprior * cwidth * totcurmass / totmass
nsim_curage = int(round(simmass / avemass))
# simluate the stars at the current age
curweights = gridweights[gmods]
curweights /= np.sum(curweights)
cursim_indx = rangen.choice(model_indx[gmods],
size=nsim_curage,
p=curweights)
totsim_indx = np.concatenate((totsim_indx, cursim_indx))
nsim += nsim_curage
# totsimcurmass = np.sum(sedgrid["M_ini"][cursim_indx])
# print(cage, totcurmass / totmass, simmass, totsimcurmass, nsim_curage)
totsimmass = np.sum(sedgrid["M_ini"][totsim_indx])
print(f"number total simulated stars = {nsim}; mass = {totsimmass}")
compl_choice = rangen.random(nsim)
compl_indx = model_compl[totsim_indx] >= compl_choice
sim_indx = totsim_indx[compl_indx]
totcompsimmass = np.sum(sedgrid["M_ini"][sim_indx])
print(
f"number of simulated stars w/ completeness = {len(sim_indx)}; mass = {totcompsimmass}"
)
else: # total number of stars to simulate set by command line input
if weight_to_use == "uniform":
# sample to get the indices of the picked models
sim_indx = rangen.choice(model_indx[goodobsmod], nsim)
else:
gridweights = sedgrid[weight_to_use][goodobsmod] * model_compl[
goodobsmod]
gridweights = gridweights / np.sum(gridweights)
# sample to get the indexes of the picked models
sim_indx = rangen.choice(model_indx[goodobsmod],
size=nsim,
p=gridweights)
print(f"number of simulated stars = {nsim}")
# setup the output table
ot = Table()
qnames = list(sedgrid.keys())
# simulated data
for k, filter in enumerate(sedgrid.filters):
simflux_wbias = flux[sim_indx, k] + model_bias[sim_indx, k]
simflux = rangen.normal(loc=simflux_wbias,
scale=model_unc[sim_indx, k])
bname = filter.split(sep="_")[-1].upper()
fluxname = f"{bname}_FLUX"
colname = f"{bname}_RATE"
magname = f"{bname}_VEGA"
ot[fluxname] = Column(simflux)
ot[colname] = Column(ot[fluxname] / vega_flux[k])
pindxs = ot[colname] > 0.0
nindxs = ot[colname] <= 0.0
ot[magname] = Column(ot[colname])
ot[magname][pindxs] = -2.5 * np.log10(ot[colname][pindxs])
ot[magname][nindxs] = 99.999
# add in the physical model values in a form similar to
# the output simulated (physics+obs models) values
# useful if using the simulated data to interpolate ASTs
# (e.g. for MATCH)
fluxname = f"{bname}_INPUT_FLUX"
ratename = f"{bname}_INPUT_RATE"
magname = f"{bname}_INPUT_VEGA"
ot[fluxname] = Column(flux[sim_indx, k])
ot[ratename] = Column(ot[fluxname] / vega_flux[k])
pindxs = ot[ratename] > 0.0
nindxs = ot[ratename] <= 0.0
ot[magname] = Column(ot[ratename])
ot[magname][pindxs] = -2.5 * np.log10(ot[ratename][pindxs])
ot[magname][nindxs] = 99.999
# model parmaeters
for qname in qnames:
ot[qname] = Column(sedgrid[qname][sim_indx])
return ot