def split_and_check(grid_fname, num_subgrids):
complete_g = FileSEDGrid(grid_fname)
sub_fnames = subgridding_tools.split_grid(grid_fname, num_subgrids)
# count the number of grid cells
sub_seds = []
sub_grids = []
for sub_fname in sub_fnames:
sub_g = FileSEDGrid(sub_fname)
sub_seds.append(sub_g.seds)
sub_grids.append(sub_g.grid.data)
np.testing.assert_equal(complete_g.lamb, sub_g.lamb)
if not complete_g.grid.columns.items() == sub_g.grid.columns.items():
raise AssertionError()
sub_seds_reconstructed = np.concatenate(sub_seds)
np.testing.assert_equal(sub_seds_reconstructed, complete_g.seds)
sub_grids_reconstructed = np.concatenate(sub_grids)
np.testing.assert_equal(sub_grids_reconstructed, complete_g.grid.data)
# the split method skips anything that already exists, so if we
# want to use this function multiple times for the same test
# grid, we need to do this.
for f in sub_fnames:
os.remove(f)
def fit_submodel(modelsedgridfile):
# input files
trimmed_modelsedgridfile = modelsedgridfile.replace(
'seds', 'seds_trim')
trimmed_noisemodelfile = trimmed_modelsedgridfile.replace(
'seds', 'noisemodel')
# output files
lnpfile = modelsedgridfile.replace('seds', 'lnp')
statsfile = modelsedgridfile.replace('seds', 'stats')
statsfile = statsfile.replace('.hd5', '.fits')
pdf1dfile = statsfile.replace('stats', 'pdf1d')
# load the subgrid seds and subgrid noisemodel
modelsedgrid = FileSEDGrid(trimmed_modelsedgridfile)
noisemodel_vals = noisemodel.get_noisemodelcat(
trimmed_noisemodelfile)
fit.summary_table_memory(obsdata, noisemodel_vals,
modelsedgrid, resume=args.resume,
threshold=-10.,
save_every_npts=100, lnp_npts=60,
stats_outname=statsfile,
pdf1d_outname=pdf1dfile,
grid_info_dict=grid_info_dict,
lnp_outname=lnpfile,
do_not_normalize=True)
print('Done fitting on grid ' + trimmed_modelsedgridfile)
def trim_submodel(modelsedgridfile):
modelsedgrid = FileSEDGrid(modelsedgridfile)
noisefile = modelsedgridfile.replace("seds", "noisemodel")
sed_trimname = modelsedgridfile.replace("seds", "seds_trim")
noisemodel_trimname = sed_trimname.replace("seds", "noisemodel")
# When working with density bins, we nees to work in a subfolder
if args.dens_bin is not None:
noisefile = os.path.join(bin_subfolder, noisefile)
sed_trimname = os.path.join(bin_subfolder, sed_trimname)
noisemodel_trimname = os.path.join(bin_subfolder,
noisemodel_trimname)
# read in the noise model just created
noisemodel_vals = noisemodel.get_noisemodelcat(noisefile)
# trim the model sedgrid
trim_grid.trim_models(
modelsedgrid,
noisemodel_vals,
obsdata,
sed_trimname,
noisemodel_trimname,
sigma_fac=3.0,
)
def gen_obsmodel(modelsedgridfile, source_density=None, use_rate=True):
"""
Code to create filenames and run the toothpick noise model
Parameters
----------
modelsedgridfile : string
path+name of the physics model grid file
source_density : string (default=None)
set to None if there's no source density info, otherwise set to
a string of the form "#-#"
use_rate : boolean (default=True)
Choose whether to use the rate or magnitude when creating the noise
model. This should always be True, but is currently an option to be
compatible with the phat_small example (which has no rate info).
When that gets fixed, please remove this option!
Returns
-------
noisefile : string
name of the created noise file
"""
print("")
# noise and AST file names
noisefile = modelsedgridfile.replace("seds", "noisemodel")
astfile = datamodel.astfile
# If we are treating regions with different
# backgrounds/source densities separately, pick one of the
# split ast files, and name noise file accordingly
if source_density is not None:
noisefile = noisefile.replace("noisemodel",
"noisemodel_bin" + source_density)
astfile = datamodel.astfile.replace(
".fits", "_bin" + source_density.replace("_", "-") + ".fits")
# only create noise file if it doesn't already exist
if not os.path.isfile(noisefile):
print("creating " + noisefile)
modelsedgrid = FileSEDGrid(modelsedgridfile)
noisemodel.make_toothpick_noise_model(
noisefile,
astfile,
modelsedgrid,
absflux_a_matrix=datamodel.absflux_a_matrix,
use_rate=use_rate,
)
else:
print(noisefile + " already exists")
return noisefile # (same as noisefile)
def gen_subobsmodel(modelsedgridfile):
modelsedgrid = FileSEDGrid(modelsedgridfile)
# generate the AST noise model
noisefile = modelsedgridfile.replace('seds', 'noisemodel')
noisemodel.make_toothpick_noise_model(
noisefile,
datamodel.astfile,
modelsedgrid,
absflux_a_matrix=datamodel.absflux_a_matrix)
def fit_submodel(modelsedgridfile):
# input files
trimmed_modelsedgridfile = modelsedgridfile.replace(
"seds", "seds_trim")
trimmed_noisemodelfile = trimmed_modelsedgridfile.replace(
"seds", "noisemodel")
# output files
lnpfile = modelsedgridfile.replace("seds", "lnp")
statsfile = modelsedgridfile.replace("seds", "stats")
statsfile = statsfile.replace(".hd5", ".fits")
pdf1dfile = statsfile.replace("stats", "pdf1d")
if args.dens_bin is not None:
# Put everything in the right subfolder
(
trimmed_modelsedgridfile,
trimmed_noisemodelfile,
lnpfile,
statsfile,
pdf1dfile,
) = [
os.path.join(bin_subfolder, f) for f in [
trimmed_modelsedgridfile,
trimmed_noisemodelfile,
lnpfile,
statsfile,
pdf1dfile,
]
]
# load the subgrid seds and subgrid noisemodel
modelsedgrid = FileSEDGrid(trimmed_modelsedgridfile)
noisemodel_vals = noisemodel.get_noisemodelcat(
trimmed_noisemodelfile)
try:
fit.summary_table_memory(
obsdata,
noisemodel_vals,
modelsedgrid,
resume=args.resume,
threshold=-10.0,
save_every_npts=100,
lnp_npts=60,
stats_outname=statsfile,
pdf1d_outname=pdf1dfile,
grid_info_dict=grid_info_dict,
lnp_outname=lnpfile,
do_not_normalize=True,
)
print("Done fitting on grid " + trimmed_modelsedgridfile)
except Exception as e:
if not args.ignore_missing_subresults:
raise e
def test_trim_grid():
# download the needed files
vega_fname = download_rename("vega.hd5")
seds_fname = download_rename("beast_example_phat_seds.grid.hd5")
noise_fname = download_rename("beast_example_phat_noisemodel.grid.hd5")
obs_fname = download_rename("b15_4band_det_27_A.fits")
# download cached version of noisemodel on the sed grid
noise_trim_fname_cache = download_rename(
"beast_example_phat_noisemodel_trim.grid.hd5"
)
seds_trim_fname_cache = download_rename("beast_example_phat_seds_trim.grid.hd5")
################
# read in the observed data
filters = [
"HST_WFC3_F275W",
"HST_WFC3_F336W",
"HST_ACS_WFC_F475W",
"HST_ACS_WFC_F814W",
"HST_WFC3_F110W",
"HST_WFC3_F160W",
]
basefilters = ["F275W", "F336W", "F475W", "F814W", "F110W", "F160W"]
obs_colnames = [f.lower() + "_rate" for f in basefilters]
obsdata = get_obscat(obs_fname, filters, obs_colnames, vega_fname=vega_fname)
# get the modesedgrid
modelsedgrid = FileSEDGrid(seds_fname)
# read in the noise model just created
noisemodel_vals = noisemodel.get_noisemodelcat(noise_fname)
# trim the model sedgrid
seds_trim_fname = "beast_example_phat_seds_trim.grid.hd5"
noise_trim_fname = seds_trim_fname.replace("_seds", "_noisemodel")
trim_models(
modelsedgrid,
noisemodel_vals,
obsdata,
seds_trim_fname,
noise_trim_fname,
sigma_fac=3.0,
)
# compare the new to the cached version
compare_hdf5(seds_trim_fname_cache, seds_trim_fname, ctype="seds")
compare_hdf5(noise_trim_fname_cache, noise_trim_fname, ctype="noise")
def trim_submodel(modelsedgridfile):
modelsedgrid = FileSEDGrid(modelsedgridfile)
# read in the noise model just created
noisefile = modelsedgridfile.replace('seds', 'noisemodel')
noisemodel_vals = noisemodel.get_noisemodelcat(noisefile)
# trim the model sedgrid
sed_trimname = modelsedgridfile.replace('seds', 'seds_trim')
noisemodel_trimname = sed_trimname.replace('seds', 'noisemodel')
trim_grid.trim_models(modelsedgrid, noisemodel_vals, obsdata,
sed_trimname, noisemodel_trimname, sigma_fac=3.)
def remove_filters_from_files(catfile, physgrid, obsgrid, outbase, rm_filters):
# remove the requested filters from the catalog file
cat = Table.read(catfile)
for cfilter in rm_filters:
colname = "{}_rate".format(cfilter)
if colname in cat.colnames:
cat.remove_column(colname)
else:
print("{} not in catalog file".format(colname))
cat.write("{}_cat.fits".format(outbase), overwrite=True)
# get the sed grid and process
g0 = FileSEDGrid(physgrid, backend="cache")
filters = g0.header["filters"].split(" ")
shortfilters = [(cfilter.split("_"))[-1].lower() for cfilter in filters]
nlamb = []
nfilters = []
rindxs = []
for csfilter, clamb, cfilter in zip(shortfilters, g0.lamb, filters):
if csfilter not in rm_filters:
nlamb.append(clamb)
nfilters.append(cfilter)
else:
rindxs.append(shortfilters.index(csfilter))
nseds = np.delete(g0.seds, rindxs, 1)
print("orig filters: {}".format(" ".join(filters)))
print(" new filters: {}".format(" ".join(nfilters)))
g = SpectralGrid(np.array(nlamb),
seds=nseds,
grid=g0.grid,
backend="memory")
g.grid.header["filters"] = " ".join(nfilters)
g.writeHDF("{}_sed.grid.hd5".format(outbase))
# get and process the observation model
obsgrid = noisemodel.get_noisemodelcat(obsgrid)
with tables.open_file("{}_noisemodel.grid.hd5".format(outbase),
"w") as outfile:
outfile.create_array(outfile.root, "bias",
np.delete(obsgrid.root.bias, rindxs, 1))
outfile.create_array(outfile.root, "error",
np.delete(obsgrid.root.error, rindxs, 1))
outfile.create_array(
outfile.root,
"completeness",
np.delete(obsgrid.root.completeness, rindxs, 1),
)
def remove_filters_from_files(catfile,
physgrid,
obsgrid,
outbase,
rm_filters):
# remove the requested filters from the catalog file
cat = Table.read(catfile)
for cfilter in rm_filters:
colname = '{}_rate'.format(cfilter)
if colname in cat.colnames:
cat.remove_column(colname)
else:
print('{} not in catalog file'.format(colname))
cat.write('{}_cat.fits'.format(outbase), overwrite=True)
# get the sed grid and process
g0 = FileSEDGrid(physgrid, backend='cache')
filters = g0.header['filters'].split(' ')
shortfilters = [(cfilter.split('_'))[-1].lower() for cfilter in filters]
nlamb = []
nfilters = []
rindxs = []
for csfilter, clamb, cfilter in zip(shortfilters, g0.lamb, filters):
if csfilter not in rm_filters:
nlamb.append(clamb)
nfilters.append(cfilter)
else:
rindxs.append(shortfilters.index(csfilter))
nseds = np.delete(g0.seds, rindxs, 1)
print('orig filters: {}'.format(' '.join(filters)))
print(' new filters: {}'.format(' '.join(nfilters)))
g = SpectralGrid(np.array(nlamb), seds=nseds,
grid=g0.grid, backend='memory')
g.grid.header['filters'] = ' '.join(nfilters)
g.writeHDF('{}_sed.grid.hd5'.format(outbase))
# get and process the observation model
obsgrid = noisemodel.get_noisemodelcat(obsgrid)
with tables.open_file('{}_noisemodel.grid.hd5'.format(outbase), 'w') \
as outfile:
outfile.create_array(outfile.root, 'bias',
np.delete(obsgrid.root.bias, rindxs, 1))
outfile.create_array(outfile.root, 'error',
np.delete(obsgrid.root.error, rindxs, 1))
outfile.create_array(outfile.root, 'completeness',
np.delete(obsgrid.root.completeness, rindxs, 1))
def gen_subgrid(i, sub_name):
sub_g_pspec = FileSEDGrid(sub_name)
sub_seds_fname = '{}seds.gridsub{}.hd5'.format(file_prefix, i)
(sub_seds_fname, sub_g_seds) = make_extinguished_sed_grid(
datamodel.project,
sub_g_pspec,
datamodel.filters,
extLaw=datamodel.extLaw,
av=datamodel.avs,
rv=datamodel.rvs,
fA=datamodel.fAs,
rv_prior_model=datamodel.rv_prior_model,
av_prior_model=datamodel.av_prior_model,
fA_prior_model=datamodel.fA_prior_model,
add_spectral_properties_kwargs=extra_kwargs,
seds_fname=sub_seds_fname)
return sub_seds_fname
def test_toothpick_noisemodel():
# download the needed files
asts_fname = download_rename("fake_stars_b15_27_all.hd5")
filter_fname = download_rename("filters.hd5")
vega_fname = download_rename("vega.hd5")
hst_fname = download_rename("hst_whitedwarf_frac_covar.fits")
seds_fname = download_rename("beast_example_phat_seds.grid.hd5")
# download cached version of noisemodel on the sed grid
noise_fname_cache = download_rename("beast_example_phat_noisemodel.grid.hd5")
################
# get the modesedgrid on which to generate the noisemodel
modelsedgrid = FileSEDGrid(seds_fname)
# absflux calibration covariance matrix for HST specific filters (AC)
filters = [
"HST_WFC3_F275W",
"HST_WFC3_F336W",
"HST_ACS_WFC_F475W",
"HST_ACS_WFC_F814W",
"HST_WFC3_F110W",
"HST_WFC3_F160W",
]
absflux_a_matrix = hst_frac_matrix(
filters, hst_fname=hst_fname, filterLib=filter_fname
)
# generate the AST noise model
noise_fname = "/tmp/beast_example_phat_noisemodel.grid.hd5"
noisemodel.make_toothpick_noise_model(
noise_fname,
asts_fname,
modelsedgrid,
absflux_a_matrix=absflux_a_matrix,
vega_fname=vega_fname,
use_rate=False,
)
# compare the new to the cached version
compare_hdf5(noise_fname_cache, noise_fname)
def test_trim_grid():
# download the needed files
vega_fname = download_rename("vega.hd5")
seds_fname = download_rename("beast_example_phat_seds.grid.hd5")
noise_fname = download_rename("beast_example_phat_noisemodel.grid.hd5")
# download cached version of noisemodel on the sed grid
simobs_fname_cache = download_rename("beast_example_phat_simobs.fits")
################
# get the physics model grid - includes priors
modelsedgrid = FileSEDGrid(seds_fname)
# read in the noise model - includes bias, unc, and completeness
noisegrid = noisemodel.get_noisemodelcat(noise_fname)
table_new = gen_SimObs_from_sedgrid(
modelsedgrid,
noisegrid,
nsim=100,
compl_filter="f475w",
ranseed=1234,
vega_fname=vega_fname,
)
# check that the simobs files are exactly the same
table_cache = Table.read(simobs_fname_cache)
# to avoid issues with uppercase vs lowercase column names, make them all
# the same before comparing
for col in table_new.colnames:
table_new[col].name = col.upper()
for col in table_cache.colnames:
table_cache[col].name = col.upper()
compare_tables(table_cache, table_new)
def gen_subgrid(i, sub_name):
sub_g_pspec = FileSEDGrid(sub_name)
sub_seds_fname = "{}seds.gridsub{}.hd5".format(file_prefix, i)
# generate the SED grid by integrating the filter response functions
# effect of dust extinction applied before filter integration
# also computes the dust priors as weights
(sub_seds_fname, sub_g_seds) = make_extinguished_sed_grid(
datamodel.project,
sub_g_pspec,
datamodel.filters,
extLaw=datamodel.extLaw,
av=datamodel.avs,
rv=datamodel.rvs,
fA=datamodel.fAs,
rv_prior_model=datamodel.rv_prior_model,
av_prior_model=datamodel.av_prior_model,
fA_prior_model=datamodel.fA_prior_model,
add_spectral_properties_kwargs=extra_kwargs,
seds_fname=sub_seds_fname,
)
return sub_seds_fname
def gen_subobsmodel(modelsedgridfile):
modelsedgrid = FileSEDGrid(modelsedgridfile)
# generate the AST noise model
noisefile = modelsedgridfile.replace("seds", "noisemodel")
astfile = settings.astfile
# If we are treating regions with different
# backgrounds/source densities separately, pick one of the
# split ast files, and put the results in a subfolder.
if args.dens_bin is not None:
noisefile = os.path.join(bin_subfolder, noisefile)
create_project_dir(os.path.dirname(noisefile))
astfile = subcatalog_fname(astfile, args.dens_bin)
outname = noisemodel.make_toothpick_noise_model(
noisefile,
astfile,
modelsedgrid,
absflux_a_matrix=settings.absflux_a_matrix,
)
return outname
def pick_models_toothpick_style(
sedgrid_fname,
filters,
Nfilter,
N_fluxes,
min_N_per_flux,
outfile=None,
outfile_params=None,
bins_outfile=None,
bright_cut=None,
):
"""
Creates a fake star catalog from a BEAST model grid. The chosen seds
are optimized for the toothpick model, by working with a given
number of flux bins, and making sure that every flux bin is covered
by at least a given number of models (for each filter individually,
which is how the toothpick model works).
Parameters
----------
sedgrid_fname: string
BEAST model grid from which the models are picked (hdf5 file)
filters: list of string
Names of the filters, to be used as columns of the output table
Nfilter: integer
In how many filters a fake star needs to be brighter than the
mag_cut value
N_fluxes: integer
The number of flux bins into which the dynamic range of the
model grid in each filter is divided
min_N_per_flux: integer
Minimum number of model seds that need to fall into each bin
outfile: string
Output path for the models (optional). If this file already
exists, the chosen seds are loaded from this file instead.
outfile_params: string (default=None)
If a file name is given, the physical parameters associated with
each model will be written to disk
bins_outfile: string
Output path for a file containing the flux bin limits for each
filter, and the number of samples for each (optional)
bright_cut: list of float
List of magnitude limits for each filter (won't sample model
SEDs that are too bright)
Returns
-------
sedsMags: astropy Table
A table containing the selected model seds (columns are named
after the filters)
"""
if outfile is not None and os.path.isfile(outfile):
print(
"{} already exists. Will attempt to load SEDs for ASTs from there."
.format(outfile))
t = Table.read(outfile, format="ascii")
return t
with Vega() as v:
vega_f, vega_flux, lambd = v.getFlux(filters)
modelsedgrid = FileSEDGrid(sedgrid_fname)
sedsMags = -2.5 * np.log10(modelsedgrid.seds[:] / vega_flux)
Nf = sedsMags.shape[1]
# Check if logL=-9.999 model points sliently sneak through
if min(modelsedgrid.grid["logL"]) < -9:
warnings.warn('There are logL=-9.999 model points in the SED grid!')
print('Excluding those SED models from selecting input ASTs')
idxs = np.where(modelsedgrid.grid["logL"] > -9)[0]
sedsMags = sedsMags[idxs]
# Set up a number of flux bins for each filter
maxes = np.amax(sedsMags, axis=0)
mins = np.amin(sedsMags, axis=0)
bin_edges = np.zeros((N_fluxes + 1, Nf)) # indexed on [fluxbin, nfilters]
for f in range(Nf):
bin_edges[:, f] = np.linspace(mins[f], maxes[f], N_fluxes + 1)
bin_mins = bin_edges[:-1, :]
bin_maxs = bin_edges[1:, :]
if not len(bin_mins) == len(bin_maxs) == N_fluxes:
raise AssertionError()
bin_count = np.zeros((N_fluxes, Nf))
chosen_idxs = []
counter = 0
successes = 0
include_mask = np.full(idxs.shape, True, dtype=bool)
chunksize = 100000
while True:
counter += 1
# pick some random models
rand_idx = np.random.choice(idxs[include_mask], size=chunksize)
randomseds = sedsMags[rand_idx, :]
# Find in which bin each model belongs, for each filter
fluxbins = np.zeros(randomseds.shape, dtype=int)
for fltr in range(Nf):
fluxbins[:, fltr] = np.digitize(randomseds[:, fltr],
bin_maxs[:, fltr])
# Clip in place (models of which the flux is equal to the max
# are assigned bin nr N_fluxes. Move these down to bin nr
# N_fluxes - 1)
np.clip(fluxbins, a_min=0, a_max=N_fluxes - 1, out=fluxbins)
add_these = np.full((len(rand_idx)), False, dtype=bool)
for r in range(len(rand_idx)):
# If any of the flux bins that this model falls into does
# not have enough samples yet, add it to the list of model
# spectra to be output
if (bin_count[fluxbins[r, :], range(Nf)] < min_N_per_flux).any():
bin_count[fluxbins[r, :], range(Nf)] += 1
successes += 1
add_these[r] = True
# If all these bins are full...
else:
# ... do not include this model again, since we will reject it
# anyway.
include_mask[idxs == rand_idx] = False
# Add the approved models
chosen_idxs.extend(rand_idx[add_these])
# If some of the randomly picked models were not added
if not add_these.any():
# ... check if we have enough samples everywhere, or if all
# the models have been exhausted (and hence the bins are
# impossible to fill).
enough_samples = (bin_count.flatten() >= min_N_per_flux).all()
still_models_left = include_mask.any()
if enough_samples or not still_models_left:
break
if not counter % 10:
print("Sampled {} models. {} successfull seds. Ratio = {}".format(
counter * chunksize, successes,
successes / counter / chunksize))
print("Bin array:")
print(bin_count)
# Gather the selected model seds in a table
sedsMags = Table(sedsMags[chosen_idxs, :], names=filters)
if outfile is not None:
ascii.write(
sedsMags,
outfile,
overwrite=True,
formats={k: "%.5f"
for k in sedsMags.colnames},
)
# if chosen, save the corresponding model parameters
if outfile_params is not None:
grid_dict = {}
for key in list(modelsedgrid.grid.keys()):
grid_dict[key] = modelsedgrid.grid[key][chosen_idxs]
grid_dict['sedgrid_indx'] = chosen_idxs
ast_params = Table(grid_dict)
ast_params.write(outfile_params, overwrite=True)
if bins_outfile is not None:
bin_info_table = Table()
col_bigarrays = [bin_mins, bin_maxs, bin_count]
col_basenames = ["bin_mins_", "bin_maxs_", "bin_count_"]
for fltr, filter_name in enumerate(filters):
for bigarray, basename in zip(col_bigarrays, col_basenames):
bin_info_table.add_column(
Column(bigarray[:, fltr], name=basename + filter_name))
ascii.write(bin_info_table, bins_outfile, overwrite=True)
return sedsMags
def plot_noisemodel(
sed_file,
noise_file_list,
plot_file,
samp=100,
color=["black", "red", "gold", "lime", "xkcd:azure"],
label=None,
):
"""
Make a plot of the noise model: for each of the bandsm make plots of bias
and uncertainty as a function of flux
If there are multiple files in noise_file_list, each of them will be
overplotted in each panel.
Parameters
----------
sed_file : string
path+name of the SED grid file
noise_file_list : list of strings
path+name of the noise model file(s)
plot_file : string
name of the file to save the plot
samp : int (default=100)
plotting all of the SED points takes a long time for a viewer to load,
so set this to plot every Nth point
color : list of strings (default=['black','red','gold','lime','xkcd:azure'])
colors to cycle through when making plots
label : list of strings (default=None)
if set, use these labels in a legend for each item in noise_file_list
"""
# read in the SED grid
print("* reading SED grid file")
sed_object = FileSEDGrid(sed_file)
if hasattr(sed_object.seds, "read"):
sed_grid = sed_object.seds.read()
else:
sed_grid = sed_object.seds
filter_list = sed_object.filters
n_filter = len(filter_list)
# figure
fig = plt.figure(figsize=(4 * n_filter, 10))
# go through noise files
for n, nfile in enumerate(noise_file_list):
print("* reading " + nfile)
# read in the values
noisemodel_vals = noisemodel.get_noisemodelcat(nfile)
# extract error and bias
noise_err = noisemodel_vals.root.error[:]
noise_bias = noisemodel_vals.root.bias[:]
# plot things
for f, filt in enumerate(filter_list):
# error is negative where it's been extrapolated -> trim those
good_err = np.where(noise_err[:, f] > 0)[0]
plot_sed = sed_grid[good_err, f][::samp]
plot_err = noise_err[good_err, f][::samp]
plot_bias = noise_bias[good_err, f][::samp]
# subplot region: bias
ax1 = plt.subplot(2, n_filter, f + 1)
(plot1,) = ax1.plot(
np.log10(plot_sed),
plot_bias / plot_sed,
marker="o",
linestyle="none",
mew=0,
ms=2,
color=color[n % len(color)],
alpha=0.1,
)
if label is not None:
plot1.set_label(label[n])
ax1.tick_params(axis="both", which="major", labelsize=13)
# ax.set_xlim(ax.get_xlim()[::-1])
plt.xlabel("log " + filt, fontsize=12)
plt.ylabel(r"Bias ($\mu$/F)", fontsize=12)
# subplot region: error
ax2 = plt.subplot(2, n_filter, n_filter + f + 1)
(plot2,) = ax2.plot(
np.log10(plot_sed),
plot_err / plot_sed,
marker="o",
linestyle="none",
mew=0,
ms=2,
color=color[n % len(color)],
alpha=0.1,
)
if label is not None:
plot2.set_label(label[n])
ax2.tick_params(axis="both", which="major", labelsize=13)
# ax.set_xlim(ax.get_xlim()[::-1])
plt.xlabel("log " + filt, fontsize=12)
plt.ylabel(r"Error ($\sigma$/F)", fontsize=12)
# do a legend if this is
# (a) the leftmost panel
# (b) the last line to be added
# (c) there are labels set
if (f == 0) and (n == len(noise_file_list) - 1) and (label is not None):
leg = ax1.legend(fontsize=12)
for lh in leg.legendHandles:
lh._legmarker.set_alpha(1)
leg = ax2.legend(fontsize=12)
for lh in leg.legendHandles:
lh._legmarker.set_alpha(1)
plt.tight_layout()
fig.savefig(plot_file)
plt.close(fig)
parser.add_argument("obsgrid", help="filename of observation/nosie grid")
parser.add_argument("outfile", help="filename for simulated observations")
parser.add_argument("--nsim",
default=100,
type=int,
help="number of simulated objects")
parser.add_argument("--compl_filter",
default="F475W",
help="filter name to use for completeness")
parser.add_argument("--ranseed",
default=None,
type=int,
help="seed for random number generator")
args = parser.parse_args()
# get the physics model grid - includes priors
modelsedgrid = FileSEDGrid(args.physgrid)
# read in the noise model - includes bias, unc, and completeness
noisegrid = noisemodel.get_noisemodelcat(args.obsgrid)
simtable = gen_SimObs_from_sedgrid(
modelsedgrid,
noisegrid,
nsim=args.nsim,
compl_filter=args.compl_filter,
ranseed=args.ranseed,
)
simtable.write(args.outfile, overwrite=True)
def simulate_obs(
physgrid_list,
noise_model_list,
output_catalog,
nsim=100,
compl_filter="F475W",
ranseed=None,
):
"""
Wrapper for creating a simulated photometry.
Parameters
----------
physgrid_list : list of strings
Name of the physics model file. If there are multiple physics model
grids (i.e., if there are subgrids), list them all here, and they will
each be sampled nsim/len(physgrid_list) times.
noise_model_list : list of strings
Name of the noise model file. If there are multiple files for
physgrid_list (because of subgrids), list the noise model file
associated with each physics model file.
output_catalog : string
Name of the output simulated photometry catalog
n_sim : int (default=100)
Number of simulated objects to create. If nsim/len(physgrid_list) isn't
an integer, this will be increased so that each grid has the same
number of samples.
compl_filter : string (default='F475W')
filter name to use for completeness
ranseed : int
seed for random number generator
"""
# numbers of samples to do
# (ensure there are enough for even sampling of multiple model grids)
n_phys = len(physgrid_list)
samples_per_grid = int(np.ceil(nsim / n_phys))
# list to hold all simulation tables
simtable_list = []
# make a table for each physics model + noise model
for physgrid, noise_model in zip(
np.atleast_1d(physgrid_list), np.atleast_1d(noise_model_list)
):
# get the physics model grid - includes priors
modelsedgrid = FileSEDGrid(str(physgrid))
# read in the noise model - includes bias, unc, and completeness
noisegrid = noisemodel.get_noisemodelcat(str(noise_model))
# generate the table
simtable = gen_SimObs_from_sedgrid(
modelsedgrid,
noisegrid,
nsim=samples_per_grid,
compl_filter=compl_filter,
ranseed=ranseed,
)
# append to the list
simtable_list.append(simtable)
# stack all the tables into one and write it out
vstack(simtable_list).write(output_catalog, overwrite=True)
def run_beast_production(basename,
physicsmodel=False,
ast=False,
observationmodel=False,
trim=False,
fitting=False,
resume=False,
source_density='',
sub_source_density=''):
"""
Turns the original command-line version of run_beast_production.py into
something callable from within a function
Parameters
----------
basename : string
name of the gst file (assuming it's located in ./data/)
For the info related to the other inputs, see the argparse info at the bottom
"""
# before doing ANYTHING, force datamodel to re-import (otherwise, any
# changes within this python session will not be loaded!)
importlib.reload(datamodel)
# check input parameters, print what is the problem, stop run_beast
verify_params.verify_input_format(datamodel)
# update the filenames as needed for production
# - photometry sub-file
datamodel.obsfile = basename.replace(
'.fits',
'_with_sourceden' + '_SD_' + source_density.replace('_', '-') +
'_sub' + sub_source_density + '.fits')
# - stats files
stats_filebase = "%s/%s"%(datamodel.project,datamodel.project) \
+ '_sd' + source_density.replace('_','-') \
+ '_sub' + sub_source_density
sed_trimname = stats_filebase + '_sed_trim.grid.hd5'
# - trimmed noise model
noisemodel_trimname = stats_filebase + '_noisemodel_trim.hd5'
# - SED grid
#modelsedgrid_filename = "%s/%s_seds.grid.hd5"%(datamodel.project,
# datamodel.project)
modelsedgrid_filename = "METAL_seds.grid.hd5"
print("***run information***")
print(" project = " + datamodel.project)
print(" obsfile = " + datamodel.obsfile)
print(" astfile = " + datamodel.astfile)
print(" noisefile = " + datamodel.noisefile)
print(" trimmed sedfile = " + sed_trimname)
print("trimmed noisefiles = " + noisemodel_trimname)
print(" stats filebase = " + stats_filebase)
# make sure the project directory exists
pdir = create_project_dir(datamodel.project)
if physicsmodel:
# download and load the isochrones
(iso_fname, oiso) = make_iso_table(datamodel.project,
oiso=datamodel.oiso,
logtmin=datamodel.logt[0],
logtmax=datamodel.logt[1],
dlogt=datamodel.logt[2],
z=datamodel.z)
if hasattr(datamodel, 'add_spectral_properties_kwargs'):
extra_kwargs = datamodel.add_spectral_properties_kwargs
else:
extra_kwargs = None
if hasattr(datamodel, 'velocity'):
redshift = (datamodel.velocity / const.c).decompose().value
else:
redshift = 0
# generate the spectral library (no dust extinction)
(spec_fname, g_spec) = make_spectral_grid(
datamodel.project,
oiso,
osl=datamodel.osl,
redshift=redshift,
distance=datamodel.distances,
distance_unit=datamodel.distance_unit,
add_spectral_properties_kwargs=extra_kwargs)
# add the stellar priors as weights
# also computes the grid weights for the stellar part
(pspec_fname, g_pspec) = add_stellar_priors(datamodel.project, g_spec)
# generate the SED grid by integrating the filter response functions
# effect of dust extinction applied before filter integration
# also computes the dust priors as weights
(seds_fname, g_seds) = make_extinguished_sed_grid(
datamodel.project,
g_pspec,
datamodel.filters,
extLaw=datamodel.extLaw,
av=datamodel.avs,
rv=datamodel.rvs,
fA=datamodel.fAs,
rv_prior_model=datamodel.rv_prior_model,
av_prior_model=datamodel.av_prior_model,
fA_prior_model=datamodel.fA_prior_model,
spec_fname=modelsedgrid_filename,
add_spectral_properties_kwargs=extra_kwargs)
if ast:
N_models = datamodel.ast_models_selected_per_age
Nfilters = datamodel.ast_bands_above_maglimit
Nrealize = datamodel.ast_realization_per_model
mag_cuts = datamodel.ast_maglimit
obsdata = datamodel.get_obscat(basename, datamodel.filters)
if len(mag_cuts) == 1:
tmp_cuts = mag_cuts
min_mags = np.zeros(len(datamodel.filters))
for k, filtername in enumerate(obsdata.filters):
sfiltername = obsdata.data.resolve_alias(filtername)
sfiltername = sfiltername.replace('rate', 'vega')
sfiltername = sfiltername.replace('RATE', 'VEGA')
keep, = np.where(obsdata[sfiltername] < 99.)
min_mags[k] = np.percentile(obsdata[keep][sfiltername], 90.)
# max. mags from the gst observation cat.
mag_cuts = min_mags + tmp_cuts
outfile = './' + datamodel.project + '/' + datamodel.project + '_inputAST.txt'
outfile_params = './' + datamodel.project + '/' + datamodel.project + '_ASTparams.fits'
chosen_seds = pick_models(modelsedgrid_filename,
datamodel.filters,
mag_cuts,
Nfilter=Nfilters,
N_stars=N_models,
Nrealize=Nrealize,
outfile=outfile,
outfile_params=outfile_params)
if datamodel.ast_with_positions == True:
separation = datamodel.ast_pixel_distribution
filename = datamodel.project + '/' + datamodel.project + '_inputAST.txt'
if datamodel.ast_reference_image is not None:
# With reference image, use the background or source density map if available
if datamodel.ast_density_table is not None:
pick_positions_from_map(
obsdata,
chosen_seds,
datamodel.ast_density_table,
datamodel.ast_N_bins,
datamodel.ast_realization_per_model,
outfile=filename,
refimage=datamodel.ast_reference_image,
refimage_hdu=0,
Nrealize=1,
set_coord_boundary=datamodel.ast_coord_boundary)
else:
pick_positions(obsdata,
filename,
separation,
refimage=datamodel.ast_reference_image)
else:
# Without reference image, we can only use this function
if datamodel.ast_density_table is None:
pick_positions(obsdata, filename, separation)
else:
print(
"To use ast_density_table, ast_reference_image must be specified."
)
if observationmodel:
print('Generating noise model from ASTs and absflux A matrix')
# get the modesedgrid on which to generate the noisemodel
modelsedgrid = FileSEDGrid(modelsedgrid_filename)
# generate the AST noise model
noisemodel.make_toothpick_noise_model( \
datamodel.noisefile,
datamodel.astfile,
modelsedgrid,
use_rate=True,
absflux_a_matrix=datamodel.absflux_a_matrix)
if trim:
print('Trimming the model and noise grids')
# read in the observed data
obsdata = datamodel.get_obscat(basename, datamodel.filters)
# get the modesedgrid on which to generate the noisemodel
modelsedgrid = FileSEDGrid(modelsedgrid_filename)
# read in the noise model just created
noisemodel_vals = noisemodel.get_noisemodelcat(datamodel.noisefile)
# trim the model sedgrid
trim_grid.trim_models(modelsedgrid,
noisemodel_vals,
obsdata,
sed_trimname,
noisemodel_trimname,
sigma_fac=3.)
if fitting:
start_time = time.clock()
# read in the the AST noise model
noisemodel_vals = noisemodel.get_noisemodelcat(noisemodel_trimname)
# read in the observed data
obsdata = datamodel.get_obscat(datamodel.obsfile, datamodel.filters)
# output files
statsfile = stats_filebase + '_stats.fits'
pdf1dfile = statsfile.replace('stats.fits', 'pdf1d.fits')
lnpfile = statsfile.replace('stats.fits', 'lnp.hd5')
fit.summary_table_memory(obsdata,
noisemodel_vals,
sed_trimname,
resume=resume,
threshold=-10.,
save_every_npts=100,
lnp_npts=500,
stats_outname=statsfile,
pdf1d_outname=pdf1dfile,
lnp_outname=lnpfile,
surveyname=datamodel.surveyname)
new_time = time.clock()
print('time to fit: ', (new_time - start_time) / 60., ' min')
def remove_filters_from_files(
catfile,
physgrid=None,
obsgrid=None,
outbase=None,
physgrid_outfile=None,
rm_filters=None,
beast_filt=None,
):
"""
Remove filters from catalog, physics grid, and/or obsmodel grid. This has
two primary use cases:
1. When making simulated observations, you want to test how your fit quality
changes with different combinations of filters. In that case, put in
files for both `physgrid` and `obsgrid`. Set `rm_filters` to the
filter(s) you wish to remove, and they will be removed both from those
and from the catalog file. The three new files will be output with the
name prefix set in `outbase`.
2. When running the BEAST, you have a master physics model grid with all
filters present in the survey, but some fields don't have observations in
all of those filters. In that case, put the master grid in `physgrid`
and set `rm_filters` to None. The catalog will be used to determine the
filters to remove (if any). `obsgrid` should be left as None, because in
this use case, the obsmodel grid has not yet been generated. The output
physics model grid will be named using the filename in `physgrid_outfile`
(if given) or with the prefix in `outbase`.
Parameters
----------
catfile : string
file name of photometry catalog
physgrid : string (default=None)
If set, remove filters from this physics model grid
obsgrid : string (default=None)
If set, remove filters from this obsmodel grid
outbase : string (default=None)
Path+file to prepend to all output file names. Useful for case 1 above.
physgrid_outfile : string (default=None)
Path+name of the output physics model grid. Useful for case 2 above.
rm_filters : string or list of strings (default=None)
If set, these are the filters to remove from all of the files. If not
set, only the filters present in catfile will be retained in physgrid
and/or obsgrid.
beast_filt : list of strings
Sometimes there is ambiguity in the filter name (e.g., the grid has
both HST_ACS_WFC_F475W and HST_WFC3_F475W, and the filter name is
F475W). Set this to the BEAST filter name to resolve any
ambiguities. For example, ['HST_WFC3_F475W', 'HST_WFC3_F814W'] ensures
that these are the names used for F475W and F814W.
"""
# read in the photometry catalog
cat = Table.read(catfile)
# if rm_filters set, remove the requested filters from the catalog
if rm_filters is not None:
for cfilter in np.atleast_1d(rm_filters):
colname = "{}_rate".format(cfilter)
if colname.upper() in cat.colnames:
cat.remove_column(colname.upper())
elif colname.lower() in cat.colnames:
cat.remove_column(colname.lower())
else:
print("{} not in catalog file".format(colname))
cat.write("{}_cat.fits".format(outbase), overwrite=True)
# if rm_filters not set, extract the filter names that are present
if rm_filters is None:
cat_filters = [f[:-5].upper() for f in cat.colnames if f[-4:].lower() == "rate"]
# if beast_filt is set, make a list of the short versions
if beast_filt is not None:
beast_filt_short = [(f.split("_"))[-1].upper() for f in beast_filt]
# if physgrid set, process the SED grid
if physgrid is not None:
# read in the sed grid
g0 = FileSEDGrid(physgrid, backend="cache")
# extract info
filters = g0.header["filters"].split(" ")
shortfilters = [(cfilter.split("_"))[-1].upper() for cfilter in filters]
rindxs = []
rgridcols = []
# loop through filters and determine what needs deleting
for csfilter, cfilter in zip(shortfilters, filters):
# --------------------------
# if the user chose the filters to remove
if rm_filters is not None:
# if the current filter is in the list of filters to remove
if csfilter in np.atleast_1d(rm_filters):
# if there's a list of BEAST instrument+filter references
if beast_filt is not None:
# if the current filter is in the list of BEAST references
if csfilter in beast_filt_short:
# if it's the same instrument, delete it
# (if it's not the same instrument, keep it)
if beast_filt[beast_filt_short.index(csfilter)] == cfilter:
rindxs.append(filters.index(cfilter))
for grid_col in g0.grid.colnames:
if cfilter in grid_col:
rgridcols.append(grid_col)
# if the current filter isn't in the BEAST ref list, delete it
else:
rindxs.append(filters.index(cfilter))
for grid_col in g0.grid.colnames:
if cfilter in grid_col:
rgridcols.append(grid_col)
# if there isn't a list of BEAST refs, delete it
else:
rindxs.append(filters.index(cfilter))
for grid_col in g0.grid.colnames:
if cfilter in grid_col:
rgridcols.append(grid_col)
# --------------------------
# if the removed filters are determined from the catalog file
if rm_filters is None:
# if the current filter is present in the catalog filters
if csfilter in cat_filters:
# if there's a list of BEAST instrument+filter references
# (if there isn't a list of BEAST refs, keep it)
if beast_filt is not None:
# if the current filter is in the list of BEAST references
# (if the current filter isn't in the BEAST ref list, keep it)
if csfilter in beast_filt_short:
# if it's not the same instrument, delete it
# (if it's the same instrument, keep it)
if beast_filt[beast_filt_short.index(csfilter)] != cfilter:
rindxs.append(filters.index(cfilter))
for grid_col in g0.grid.colnames:
if cfilter in grid_col:
rgridcols.append(grid_col)
# if the current filter isn't in the catalog filters, delete it
else:
rindxs.append(filters.index(cfilter))
for grid_col in g0.grid.colnames:
if cfilter in grid_col:
rgridcols.append(grid_col)
# delete column(s)
nseds = np.delete(g0.seds, rindxs, 1)
nlamb = np.delete(g0.lamb, rindxs, 0)
nfilters = np.delete(filters, rindxs, 0)
for rcol in rgridcols:
g0.grid.delCol(rcol)
print("orig filters: {}".format(" ".join(filters)))
print(" new filters: {}".format(" ".join(nfilters)))
# save the modified grid
g = SpectralGrid(np.array(nlamb), seds=nseds, grid=g0.grid, backend="memory")
g.grid.header["filters"] = " ".join(nfilters)
if physgrid_outfile is not None:
g.writeHDF(physgrid_outfile)
elif outbase is not None:
g.writeHDF("{}_seds.grid.hd5".format(outbase))
else:
raise ValueError("Need to set either outbase or physgrid_outfile")
# if obsgrid set, process the observation model
if obsgrid is not None:
obsgrid = noisemodel.get_noisemodelcat(obsgrid)
with tables.open_file("{}_noisemodel.grid.hd5".format(outbase), "w") as outfile:
outfile.create_array(
outfile.root, "bias", np.delete(obsgrid["bias"], rindxs, 1)
)
outfile.create_array(
outfile.root, "error", np.delete(obsgrid["error"], rindxs, 1)
)
outfile.create_array(
outfile.root,
"completeness",
np.delete(obsgrid["completeness"], rindxs, 1),
)
def pick_models(
sedgrid_fname,
filters,
mag_cuts,
Nfilter=3,
N_stars=70,
Nrealize=20,
outfile=None,
outfile_params=None,
bright_cut=None,
vega_fname=None,
ranseed=None,
):
"""Creates a fake star catalog from a BEAST model grid
Parameters
----------
sedgrid_fname: string
BEAST model grid from which the models are picked (hdf5 file)
filters: list of string
Names of the filters
mag_cuts: list
List of magnitude limits for each filter
Nfilter: Integer
In how many filters, you want a fake star to be brighter
than the limit (mag_cut) (default = 3)
N_stars: Integer
Number of stellar models picked per a single log(age)
(default=70)
Nrealize: Integer
Number of realization of each models (default = 20)
outfile: str
If a file name is given, the selected models will be written to
disk
outfile_params: str
If a file name is given, the physical parameters associated with
each model will be written to disk
bright_cut: list of float
Same as mag_cuts, but for the bright end
vega_fname: str
filename of vega file
ranseed : int
used to set the seed to make the results reproducable
useful for testing
Returns
-------
astropy Table of selected models
- and optionally -
ascii file: A list of selected models, written to 'outfile'
fits file: the corresponding physical parameters, written to 'outfile_params'
"""
with Vega(source=vega_fname) as v: # Get the vega fluxes
vega_f, vega_flux, lamb = v.getFlux(filters)
# gridf = h5py.File(sedgrid_fname)
modelsedgrid = FileSEDGrid(sedgrid_fname)
# Convert to Vega mags
# sedsMags = -2.5 * np.log10(gridf['seds'][:] / vega_flux)
sedsMags = -2.5 * np.log10(modelsedgrid.seds[:] / vega_flux)
# make sure Nfilters isn't larger than the total number of filters
if Nfilter > len(filters):
Nfilter = len(filters)
# Select the models above the magnitude limits in N filters
idxs = mag_limits(sedsMags,
mag_cuts,
Nfilter=Nfilter,
bright_cut=bright_cut)
# grid_cut = gridf['grid'][list(idxs)]
cols = {}
for key in list(modelsedgrid.grid.keys()):
cols[key] = modelsedgrid.grid[key][idxs]
grid_cut = Table(cols)
# Sample the model grid uniformly
prime_params = np.column_stack(
(grid_cut["logA"], grid_cut["M_ini"], grid_cut["Av"]))
search_age = np.unique(prime_params[:, 0])
N_sample = N_stars
model_ind = [] # indices for the model grid
ast_params = grid_cut[[]] # the corresponding model parameters
# set the random seed - mainly for testing
if not None:
np.random.seed(ranseed)
for iage in search_age:
tmp, = np.where(prime_params[:, 0] == iage)
new_ind = np.random.choice(tmp, N_sample)
model_ind.append(new_ind)
[ast_params.add_row(grid_cut[new_ind[i]]) for i in range(len(new_ind))]
index = np.repeat(idxs[np.array(model_ind).reshape((-1))], Nrealize)
sedsMags = Table(sedsMags[index, :], names=filters)
if outfile is not None:
ascii.write(
sedsMags,
outfile,
overwrite=True,
formats={k: "%.5f"
for k in sedsMags.colnames},
)
if outfile_params is not None:
ast_params.write(outfile_params, overwrite=True)
return sedsMags
def plot_completeness(
physgrid_list,
noise_model_list,
output_plot_filename,
param_list=['Av', 'Rv', 'logA', 'f_A', 'M_ini', 'Z', 'distance'],
compl_filter='F475W',
):
"""
Make visualization of the completeness
Parameters
----------
physgrid_list : string or list of strings
Name of the physics model file. If there are multiple physics model
grids (i.e., if there are subgrids), list them all here.
noise_model_list : string or list of strings
Name of the noise model file. If there are multiple files for
physgrid_list (because of subgrids), list the noise model file
associated with each physics model file.
param_list : list of strings
names of the parameters to plot
compl_filter : str
filter to use for completeness (required for toothpick model)
output_plot_filename : string
name of the file in which to save the output plot
"""
n_params = len(param_list)
# If there are subgrids, we can't read them all into memory. Therefore,
# we'll go through each one and just grab the relevant parts.
compl_table_list = []
# make a table for each physics model + noise model
for physgrid, noise_model in zip(
np.atleast_1d(physgrid_list), np.atleast_1d(noise_model_list)
):
# get the physics model grid - includes priors
modelsedgrid = FileSEDGrid(str(physgrid))
# get list of filters
short_filters = [filter.split(sep="_")[-1].upper() for filter in modelsedgrid.filters]
if compl_filter.upper() not in short_filters:
raise ValueError("requested completeness filter not present")
filter_k = short_filters.index(compl_filter.upper())
print("Completeness from {0}".format(modelsedgrid.filters[filter_k]))
# read in the noise model
noisegrid = noisemodel.get_noisemodelcat(str(noise_model))
# get the completeness
model_compl = noisegrid["completeness"]
# close the file to save memory
noisegrid.close()
# put it all into a table
table_dict = {x:modelsedgrid[x] for x in param_list}
table_dict['compl'] = model_compl[:, filter_k]
# append to the list
compl_table_list.append(Table(table_dict))
# stack all the tables into one
compl_table = vstack(compl_table_list)
#import pdb; pdb.set_trace()
# figure
fig = plt.figure(figsize=(4*n_params, 4*n_params))
# label font sizes
label_font = 25
tick_font = 22
# load in color map
cmap = matplotlib.cm.get_cmap('magma')
# iterate through the panels
for i,pi in enumerate(param_list):
for j,pj in enumerate(param_list[i:], i):
print('plotting {0} and {1}'.format(pi, pj))
# not along diagonal
if i != j:
# set up subplot
plt.subplot(n_params, n_params, i + j*(n_params) + 1)
ax = plt.gca()
# create image and labels
x_col, x_bins, x_label = setup_axis(compl_table, pi)
y_col, y_bins, y_label = setup_axis(compl_table, pj)
compl_image, _, _, _ = binned_statistic_2d(
x_col,
y_col,
compl_table['compl'],
statistic='mean',
bins=(x_bins, y_bins),
)
# plot points
im = plt.imshow(
compl_image.T,
#np.random.random((4,4)),
extent=(
np.min(x_bins), np.max(x_bins),
np.min(y_bins), np.max(y_bins)
),
cmap='magma',
vmin=0,
vmax=1,
aspect='auto',
origin='lower',
)
ax.tick_params(axis='both', which='both', direction='in', labelsize=tick_font,
bottom=True, top=True, left=True, right=True)
# axis labels and ticks
if i == 0:
ax.set_ylabel(y_label, fontsize=label_font)
#ax.get_yaxis().set_label_coords(-0.35,0.5)
else:
ax.set_yticklabels([])
if j == n_params-1:
ax.set_xlabel(x_label, fontsize=label_font)
plt.xticks(rotation=-45)
else:
ax.set_xticklabels([])
# along diagonal
if i == j:
# set up subplot
plt.subplot(n_params, n_params, i + j*(n_params) + 1)
ax = plt.gca()
# create histogram and labels
x_col, x_bins, x_label = setup_axis(compl_table, pi)
compl_hist, _, _ = binned_statistic(
x_col,
compl_table['compl'],
statistic='mean',
bins=x_bins,
)
# make histogram
_, _, patches = plt.hist(x_bins[:-1], x_bins, weights=compl_hist)
# color each bar by its completeness
for c,comp in enumerate(compl_hist):
patches[c].set_color(cmap(comp))
patches[c].set_linewidth=0.1
# make a black outline so it stands out as a histogram
plt.hist(x_bins[:-1], x_bins, weights=compl_hist, histtype='step', color='k')
# axis ranges
plt.xlim(np.min(x_bins), np.max(x_bins))
plt.ylim(0, 1.05)
ax.tick_params(axis='y',which='both',length=0, labelsize=tick_font)
ax.tick_params(axis='x',which='both',direction='in', labelsize=tick_font)
# axis labels and ticks
ax.set_yticklabels([])
if i < n_params-1:
ax.set_xticklabels([])
if i == n_params-1:
ax.set_xlabel(x_label, fontsize=label_font)
plt.xticks(rotation=-45)
#plt.subplots_adjust(wspace=0.05, hspace=0.05)
plt.tight_layout()
# add a colorbar
gs = GridSpec(nrows=20, ncols=n_params)
cax = fig.add_subplot(gs[0, 2:])
cbar = plt.colorbar(im, cax=cax, orientation='horizontal')
cbar.set_label('Completeness', fontsize=label_font)
cbar.ax.tick_params(labelsize=tick_font)
gs.tight_layout(fig)
fig.savefig(output_plot_filename)
plt.close(fig)
def fit_submodel(
photometry_file,
modelsedgrid_file,
noise_file,
stats_file,
pdf_file,
pdf2d_file,
pdf2d_param_list,
lnp_file,
grid_info_file=None,
resume=False,
):
"""
Code to run the SED fitting
Parameters
----------
photometry_file : string
path+name of the photometry file
modelsedgrid_file : string
path+name of the physics model grid file
noise_file : string
path+name of the noise model file
stats_file : string
path+name of the file to contain stats output
pdf_file : string
path+name of the file to contain 1D PDF output
pdf2d_file : string
path+name of the file to contain 2D PDF output
pdf2d_param_list: list of strings or None
parameters for which to make 2D PDFs (or None)
lnp_file : string
path+name of the file to contain log likelihood output
grid_info_file : string (default=None)
path+name for pickle file that contains dictionary with subgrid
min/max/n_unique (required for a run with subgrids)
resume : boolean (default=False)
choose whether to resume existing run or start over
Returns
-------
noisefile : string
name of the created noise file
"""
# read in the photometry catalog
obsdata = datamodel.get_obscat(photometry_file, datamodel.filters)
# check if it's a subgrid run by looking in the file name
if "gridsub" in modelsedgrid_file:
subgrid_run = True
print("loading grid_info_dict from " + grid_info_file)
with open(grid_info_file, "rb") as p:
grid_info_dict = pickle.loads(p.read())
else:
subgrid_run = False
# load the SED grid and noise model
modelsedgrid = FileSEDGrid(modelsedgrid_file)
noisemodel_vals = noisemodel.get_noisemodelcat(noise_file)
if subgrid_run:
fit.summary_table_memory(
obsdata,
noisemodel_vals,
modelsedgrid,
resume=resume,
threshold=-10.0,
save_every_npts=100,
lnp_npts=500,
stats_outname=stats_file,
pdf1d_outname=pdf_file,
pdf2d_outname=pdf2d_file,
pdf2d_param_list=pdf2d_param_list,
grid_info_dict=grid_info_dict,
lnp_outname=lnp_file,
do_not_normalize=True,
surveyname=datamodel.surveyname,
)
print("Done fitting on grid " + modelsedgrid_file)
else:
fit.summary_table_memory(
obsdata,
noisemodel_vals,
modelsedgrid,
resume=resume,
threshold=-10.0,
save_every_npts=100,
lnp_npts=500,
stats_outname=stats_file,
pdf1d_outname=pdf_file,
pdf2d_outname=pdf2d_file,
pdf2d_param_list=pdf2d_param_list,
lnp_outname=lnp_file,
surveyname=datamodel.surveyname,
)
print("Done fitting on grid " + modelsedgrid_file)
g_pspec,
datamodel.filters,
extLaw=datamodel.extLaw,
av=datamodel.avs,
rv=datamodel.rvs,
fA=datamodel.fAs,
rv_prior_model=datamodel.rv_prior_model,
av_prior_model=datamodel.av_prior_model,
fA_prior_model=datamodel.fA_prior_model,
add_spectral_properties_kwargs=extra_kwargs)
if args.ast:
# get the modesedgrid on which to grab input AST
modelsedgridfile = datamodel.project + '/' + datamodel.project + \
'_seds.grid.hd5'
modelsedgrid = FileSEDGrid(modelsedgridfile)
N_models = datamodel.ast_models_selected_per_age
Nfilters = datamodel.ast_bands_above_maglimit
Nrealize = datamodel.ast_realization_per_model
mag_cuts = datamodel.ast_maglimit
if len(mag_cuts) == 1:
tmp_cuts = mag_cuts
obsdata = datamodel.get_obscat(datamodel.obsfile,
datamodel.filters)
min_mags = np.zeros(len(datamodel.filters))
for k, filtername in enumerate(obsdata.filters):
sfiltername = obsdata.data.resolve_alias(filtername)
sfiltername = sfiltername.replace('rate', 'vega')
separation = datamodel.ast_pixel_distribution
filename = datamodel.project + '/' + datamodel.project + '_inputAST.txt'
if datamodel.ast_reference_image is not None:
pick_positions(obsdata,
filename,
separation,
refimage=datamodel.ast_reference_image)
else:
pick_positions(obsdata, filename, separation)
if args.observationmodel:
print('Generating noise model from ASTs and absflux A matrix')
# get the modesedgrid on which to generate the noisemodel
modelsedgrid = FileSEDGrid(modelsedgrid_filename)
# generate the AST noise model
noisemodel.make_toothpick_noise_model( \
datamodel.noisefile,
datamodel.astfile,
modelsedgrid,
use_rate=True,
absflux_a_matrix=datamodel.absflux_a_matrix)
if args.trim:
print('Trimming the model and noise grids')
# read in the observed data
obsdata = datamodel.get_obscat(datamodel.obsfile, datamodel.filters)
parser.add_argument("trimfile",
help="file with modelgrid, obsfiles, filebase to use")
args = parser.parse_args()
start_time = time.clock()
# read in trim file
f = open(args.trimfile, "r")
file_lines = list(f)
# physics model grid name
modelfile = file_lines[0].rstrip()
# get the modesedgrid on which to generate the noisemodel
print("Reading the model grid files = ", modelfile)
modelsedgrid = FileSEDGrid(modelfile)
new_time = time.clock()
print("time to read: ", (new_time - start_time) / 60.0, " min")
old_noisefile = ""
for k in range(1, len(file_lines)):
print("\n\n")
# file names
noisefile, obsfile, filebase = file_lines[k].split()
# make sure the proper directories exist
if not os.path.isdir(os.path.dirname(filebase)):
os.makedirs(os.path.dirname(filebase))
def plot_ast(ast_file, sed_grid_file=None):
"""
Make a histogram of the AST fluxes. If an SED grid is given, also plot
a comparison histogram of the SED fluxes.
The histogram bins are set by the bins originally used to create the ASTs
(using the flux bin method), which are saved in
ast_file.replace('inputAST','ASTfluxbins')
and are automatically read in.
Output plot is saved in the same location/name as ast_file, but with a .png
instead of .txt.
Parameters
----------
ast_file : string
name of AST input file
sed_grid_file : string (default=None)
name of SED grid file
"""
# read in AST info
ast_table = Table.read(ast_file, format='ascii')
ast_fluxbins = Table.read(ast_file.replace('inputAST', 'ASTfluxbins'),
format='ascii')
# get filter names (and it's even in order!)
filter_cols = [col for col in ast_table.colnames if '_' in col]
filter_list = [col[-5:] for col in filter_cols]
n_filter = len(filter_list)
# if chosen, read in model grid
if sed_grid_file is not None:
modelsedgrid = FileSEDGrid(sed_grid_file)
with Vega() as v:
_, vega_flux, _ = v.getFlux(filter_cols)
sedsMags = -2.5 * np.log10(modelsedgrid.seds[:] / vega_flux)
good_seds = np.where(modelsedgrid.grid['logL'] > -9)[0]
# make a histogram for each filter
fig = plt.figure(figsize=(7, 4 * n_filter))
for f, filt in enumerate(filter_list):
# names of table columns with bin values
min_bin_col = [
b for b in ast_fluxbins.colnames if ('mins' in b and filt in b)
][0]
max_bin_col = [
b for b in ast_fluxbins.colnames if ('maxs' in b and filt in b)
][0]
# use those to make a bin list
bin_list = np.append(ast_fluxbins[min_bin_col],
ast_fluxbins[max_bin_col][-1])
# make histograms
ax = plt.subplot(n_filter, 1, f + 1)
ast_col = [b for b in ast_table.colnames if filt in b][0]
plt.hist(ast_table[ast_col],
bins=bin_list,
normed=True,
facecolor='black',
edgecolor='none',
alpha=0.3,
label='ASTs')
if sed_grid_file is not None:
plt.hist(sedsMags[good_seds, f],
bins=bin_list,
normed=True,
histtype='step',
facecolor='none',
edgecolor='black',
label='Model grid')
# labels
ax.tick_params(axis='both', which='major', labelsize=13)
ax.set_xlim(ax.get_xlim()[::-1])
plt.xlabel(filt + ' (Vega mag)', fontsize=14)
plt.ylabel('Normalized Histogram', fontsize=14)
# add legend in first plot
if f == 0:
ax.legend(fontsize=14)
plt.tight_layout()
fig.savefig(ast_file.replace('.txt', '.png'))
plt.close(fig)