def lnlike(theta): #, wp_val, wperr, model_instance):
logMmin, sigma_logM, alpha, logM0, logM1 = theta
model_instance.param_dict['logMmin'] = logMmin
model_instance.param_dict['sigma_logM'] = sigma_logM
model_instance.param_dict['alpha'] = alpha
model_instance.param_dict['logM0'] = logM0
model_instance.param_dict['logM1'] = logM1
model_instance.mock.populate()
table = model_instance.mock.halo_table
pos = return_xyz_formatted_array(model_instance.mock.galaxy_table['x'],
model_instance.mock.galaxy_table['y'],
model_instance.mock.galaxy_table['z'])
x = pos[:, 0]
y = pos[:, 1]
z = pos[:, 2]
velz = model_instance.mock.galaxy_table['vz']
pos_zdist = return_xyz_formatted_array(x,
y,
z,
velocity=velz,
velocity_distortion_dimension='z')
pi_max = 60.
Lbox = 250.
nthreads = 1
#model = wp(pos_zdist, bin_edges, pi_max, period=Lbox)
pos_zdist[:, 2][np.where(pos_zdist[:, 2] < 0.0)] = 0.0
pos_zdist[:, 2][np.where(pos_zdist[:, 2] > 250.0)] = 250.0
model = wp(Lbox, pi_max, nthreads, bin_edges, pos_zdist[:, 0],
pos_zdist[:, 1], pos_zdist[:, 2])
inv_sigma2 = 1.0 / err**2.
return -0.5 * (np.sum((wp_val - model['wp'])**2 * inv_sigma2 -
np.log(inv_sigma2)))
def wp_size_ratios_mock(mock,
logsm_min,
sample_cut,
size_key='r50_magr_kpc_meert15',
rp_bins=np.logspace(-1, 1.25, 20),
pi_max=20.,
period=250.):
"""
"""
rp_mids = 10**(0.5 * (np.log10(rp_bins[:-1]) + np.log10(rp_bins[1:])))
mask_sm_thresh = mock['obs_sm'] > 10**logsm_min
if sample_cut == 'sf':
sample_mask = mask_sm_thresh & (mock['ssfr'] >= -10.75)
elif sample_cut == 'q':
sample_mask = mask_sm_thresh & (mock['ssfr'] < -11.25)
elif sample_cut == 'bulge':
sample_mask = mask_sm_thresh & (mock['bt_meert15_random'] > 0.75)
elif sample_cut == 'disk':
sample_mask = mask_sm_thresh & (mock['bt_meert15_random'] < 0.25)
elif sample_cut == 'mixed':
sample_mask = mask_sm_thresh & (mock['bt_meert15_random'] >= 0.25) & (
mock['bt_meert15_random'] < 0.75)
else:
raise ValueError("sample_cut = {0} not recognized")
size_cut = np.median(mock[size_key][sample_mask])
sample_mask_small = sample_mask & (mock[size_key] < size_cut)
sample_mask_large = sample_mask & (mock[size_key] >= size_cut)
pos_sm_sf = return_xyz_formatted_array(mock['x'],
mock['y'],
mock['z'],
velocity=mock['vz'],
velocity_distortion_dimension='z',
period=period,
mask=sample_mask)
pos_sm_sf_small = return_xyz_formatted_array(
mock['x'],
mock['y'],
mock['z'],
velocity=mock['vz'],
velocity_distortion_dimension='z',
period=period,
mask=sample_mask_small)
pos_sm_sf_large = return_xyz_formatted_array(
mock['x'],
mock['y'],
mock['z'],
velocity=mock['vz'],
velocity_distortion_dimension='z',
period=period,
mask=sample_mask_large)
wp_sm = wp(pos_sm_sf, rp_bins, pi_max, period=period)
wp_sm_small = wp(pos_sm_sf_small, rp_bins, pi_max, period=period)
wp_sm_large = wp(pos_sm_sf_large, rp_bins, pi_max, period=period)
return rp_mids, wp_sm, wp_sm_small, wp_sm_large
def calc_all_observables(param):
model.param_dict.update(dict(zip(param_names, param))) ##update model.param_dict with pairs (param_names:params)
try:
model.mock.populate()
except:
model.populate_mock(halocat)
gc.collect()
output = []
pos_gals_d = return_xyz_formatted_array(*(model.mock.galaxy_table[ax] for ax in 'xyz'), \
velocity=model.mock.galaxy_table['vz'], velocity_distortion_dimension='z',\
period=Lbox) ##redshift space distorted
pos_gals_d = np.array(pos_gals_d,dtype=float)
pos_gals = return_xyz_formatted_array(*(model.mock.galaxy_table[ax] for ax in 'xyz'), period=Lbox)
pos_gals = np.array(pos_gals,dtype=float)
total_num_ptcls_in_snapshot = halocat.num_ptcl_per_dim**3
downsampling_factor = total_num_ptcls_in_snapshot/float(num_ptcls_to_use)
particle_masses = halocat.particle_mass*downsampling_factor
func,funccov = ngal_wp_ds_vpf_Pcic_jk(pos_gals_d, r_wp, pi_max, r_vpf, vpf_centers, proj_search_radius, cylinder_half_length, pos_gals, ptclpos, particle_masses, rp_bins_ggl, Lbox, args.Nsidejk, sum_40)
output.append(func)
output.append(funccov)
# parameter set
output.append(param)
return output
def cross_correlation_function(gals, red_cut=-11.0, cols=['ssfr', 'pred'],
box_size=250.0):
pi_max = 40.0
octants = util.jackknife_octant_samples(gals, box_size)
actual_wps, pred_wps = [], []
rp_bins = np.logspace(-1, np.log10(25), 18)
rp_centers = np.sqrt(rp_bins[:-1] * rp_bins[1:])
for octant in octants:
reds = gals[cols[0]] < red_cut
blues = gals[cols[0]] > red_cut
reds_pred = gals[cols[1]] < red_cut
blues_pred = gals[cols[1]] > red_cut
x = gals['x']
y = gals['y']
z = gals['z']
pos_red = return_xyz_formatted_array(x, y, z, mask=reds)
pos_blue = return_xyz_formatted_array(x, y, z, mask=blues)
pos_red_pred = return_xyz_formatted_array(x, y, z, mask=reds_pred)
pos_blue_pred = return_xyz_formatted_array(x, y, z, mask=blues_pred)
actual_wps.append(wp(pos_red, rp_bins=rp_bins, pi_max=pi_max,
sample2=pos_blue, period=box_size)[1])
pred_wps.append(wp(pos_red_pred, rp_bins=rp_bins, pi_max=pi_max,
sample2=pos_blue_pred, period=box_size)[1])
n_jack = len(octants)
true_wp = np.mean(actual_wps, axis=1)
pred_wp = np.mean(pred_wps, axis=1)
errs = np.sqrt(np.diag(np.cov(np.array(actual_wps) - np.array(pred_wps),
rowvar=0, bias=1)) * (n_jack - 1)),
return rp_centers, true_wp, pred_wp, errs
def calc_all_observables(param):
model.param_dict.update(dict(zip(param_names, param))) ##update model.param_dict with pairs (param_names:params)
try:
model.mock.populate()
except:
model.populate_mock(halocat)
gc.collect()
output = []
pos_gals_d = return_xyz_formatted_array(*(model.mock.galaxy_table[ax] for ax in 'xyz'), \
velocity=model.mock.galaxy_table['vz'], velocity_distortion_dimension='z',\
period=Lbox) ##redshift space distorted
pos_gals_d = np.array(pos_gals_d,dtype=float)
pos_gals = return_xyz_formatted_array(*(model.mock.galaxy_table[ax] for ax in 'xyz'), period=Lbox)
pos_gals = np.array(pos_gals,dtype=float)
########one mock, different vpfcens and ptclposes.
np.random.rand(num_sphere,3)*250, ptclpos
particle_masses = halocat.particle_mass
total_num_ptcls_in_snapshot = halocat.num_ptcl_per_dim**3
downsampling_factor = total_num_ptcls_in_snapshot/float(num_ptcls_to_use)
vpf = void_prob_func(pos_gals_d, r_vpf, random_sphere_centers=vpf_centers, period=Lbox)
ggl = delta_sigma(pos_gals, ptclpos, particle_masses=particle_masses, downsampling_factor=downsampling_factor,\
rp_bins=rp_bins_ggl, period=Lbox)[1]/1e12
########
# parameter set
output.append(param)
return output
def _get_lnlike(self, theta):
wp_vals, ng, ng_err, bin_edges, invcov = self._get_data()
logMmin, sigma_logM, alpha, logM0, logM1 = theta
model_instance.param_dict['logMmin'] = logMmin
model_instance.param_dict['sigma_logM'] = sigma_logM
model_instance.param_dict['alpha'] = alpha
model_instance.param_dict['logM0'] = logM0
model_instance.param_dict['logM1'] = logM1
if self['sim'] == 'smdpl':
Lbox = 400.
elif self['sim'] == 'old':
Lbox = 250.
elif self['sim'] == 'bolplanck':
Lbox = 250.
elif self['sim'] == 'mdr1':
Lbox = 1000.
model_instance.mock.populate()
pos = return_xyz_formatted_array(model_instance.mock.galaxy_table['x'],
model_instance.mock.galaxy_table['y'],
model_instance.mock.galaxy_table['z'],
period=Lbox)
x = pos[:, 0]
y = pos[:, 1]
z = pos[:, 2]
velz = model_instance.mock.galaxy_table['vz']
pos_zdist = return_xyz_formatted_array(
x,
y,
z,
period=Lbox,
velocity=velz,
velocity_distortion_dimension='z')
pi_max = 60.
nthreads = 1
wp_calc = wp(Lbox,
pi_max,
nthreads,
bin_edges,
pos_zdist[:, 0],
pos_zdist[:, 1],
pos_zdist[:, 2],
verbose=False)
#,xbin_refine_factor=3, ybin_refine_factor=3, zbin_refine_factor=2)
wp_diff = wp_vals - wp_calc['wp']
ng_diff = ng - model_instance.mock.number_density
#save current wp calculated value for blobs
self.cur_wp = wp_calc['wp']
return -0.5 * np.dot(wp_diff, np.dot(
invcov, wp_diff)) + -0.5 * (ng_diff**2) / (ng_err**2)
def calc_all_observables(param):
model.param_dict.update(dict(
zip(param_names,
param))) ##update model.param_dict with pairs (param_names:params)
c = Ngal_estimate(halocat, param)
n_est = c.ngal_estimate()
if n_est < 1e5 and n_est > 7.8e4:
try:
model.mock.populate()
except:
model.populate_mock(halocat)
gc.collect()
output = []
if model.mock.galaxy_table[
'x'].size < 9.8e4 and model.mock.galaxy_table['x'].size > 8e4:
pos_gals = return_xyz_formatted_array(*(model.mock.galaxy_table[ax]
for ax in 'xyz'),
period=Lbox)
pos_gals = np.array(pos_gals, dtype=float)
pos_gals_d = return_xyz_formatted_array(*(model.mock.galaxy_table[ax] for ax in 'xyz'), \
velocity=model.mock.galaxy_table['vz'], velocity_distortion_dimension='z',\
period=Lbox) ##redshift space distorted
pos_gals_d = np.array(pos_gals_d, dtype=float)
#ngals
output.append(model.mock.galaxy_table['x'].size)
#delta sigma
deltasigma = delta_sigma(pos_gals,
pos_part,
particle_masses=particle_masses,
downsampling_factor=downsampling_factor,
rp_bins=rp_bins,
period=Lbox)
output.append(deltasigma[1])
output.append(deltasigma[0])
# wprp
output.append(wp(pos_gals_d, r_wp, pi_max, period=Lbox))
# parameter set
output.append(param)
else:
output = 1
return output
def single_component_ratios(mock,
rp_bins=np.logspace(-1, 1.25, 20),
pi_max=20.,
period=250.,
size_key='r50',
num_gals_max=int(1e5)):
"""
"""
result_collector = []
rp_mids = 10**(0.5 * (np.log10(rp_bins[:-1]) + np.log10(rp_bins[1:])))
result_collector.append(rp_mids)
for logsm_cut in (9.75, 10.25, 10.75, 11.25):
sample = mock[mock['mstar'] > 10**logsm_cut]
if len(sample) > num_gals_max:
downsampling_mask = np.random.choice(np.arange(len(sample)),
num_gals_max,
replace=False)
sample = sample[downsampling_mask]
pos_all = return_xyz_formatted_array(sample['x'],
sample['y'],
sample['z'],
velocity=sample['vz'],
velocity_distortion_dimension='z',
period=period)
pos_small = return_xyz_formatted_array(
sample['x'],
sample['y'],
sample['z'],
velocity=sample['vz'],
velocity_distortion_dimension='z',
period=period,
mask=(sample[size_key] < sample[size_key + '_median']))
pos_large = return_xyz_formatted_array(
sample['x'],
sample['y'],
sample['z'],
velocity=sample['vz'],
velocity_distortion_dimension='z',
period=period,
mask=(sample[size_key] >= sample[size_key + '_median']))
wp_all = wp(pos_all, rp_bins, pi_max, period=period)
wp_small = wp(pos_small, rp_bins, pi_max, period=period)
wp_large = wp(pos_large, rp_bins, pi_max, period=period)
fracdiff = (wp_large - wp_small) / wp_all
result_collector.append(fracdiff)
return result_collector
def calc_all_observables(param, seed=seed):
model.param_dict.update(dict(
zip(param_names,
param))) ##update model.param_dict with pairs (param_names:params)
try:
model.mock.populate(seed=seed)
except:
model.populate_mock(halocat, seed=seed)
gc.collect()
output = []
pos_gals_d = return_xyz_formatted_array(*(model.mock.galaxy_table[ax] for ax in 'xyz'), \
velocity=model.mock.galaxy_table['vz'], velocity_distortion_dimension='z',\
period=Lbox) ##redshift space distorted
pos_gals_d = np.array(pos_gals_d, dtype=float)
pos_gals = return_xyz_formatted_array(*(model.mock.galaxy_table[ax]
for ax in 'xyz'),
period=Lbox)
pos_gals = np.array(pos_gals, dtype=float)
particle_masses = halocat.particle_mass
total_num_ptcls_in_snapshot = halocat.num_ptcl_per_dim**3
downsampling_factor = total_num_ptcls_in_snapshot / float(num_ptcls_to_use)
vpf = void_prob_func(pos_gals_d,
r_vpf,
random_sphere_centers=vpf_centers,
period=Lbox)
wprp = wp(pos_gals_d, r_wp, pi_max, period=Lbox)
Pcic = np.bincount(counts_in_cylinders(pos_gals_d, pos_gals_d, proj_search_radius, \
cylinder_half_length, period=Lbox), minlength=100)[1:71]/float(pos_gals_d.shape[0])
Pcic_40 = np.add.reduceat(Pcic, sum_40)
ggl = delta_sigma(pos_gals, ptclpos, particle_masses=particle_masses, downsampling_factor=downsampling_factor,\
rp_bins=rp_bins_ggl, period=Lbox)[1]/1e12
func = np.concatenate((np.array(
(pos_gals_d.shape[0] / float(Lbox**3), )), wprp, ggl, vpf, Pcic_40))
output.append(func)
# parameter set
output.append(param)
output.append(np.where(param - fid != 0)[0][0])
return output
def baofit_data_ht_jackknife(cat, n_rp_bins, n_pi_bins, num_threads):
# try:
# sim_name = cat.SimName
# except:
# sim_name = cat.simname
try:
L = cat.BoxSize
except:
L = cat.Lbox[0]
# redshift = cat.redshift
x = cat.halo_table['halo_x']
y = cat.halo_table['halo_y']
z = cat.halo_table['halo_z']
pos = return_xyz_formatted_array(x, y, z, period=L)
rp_bins = np.logspace(np.log10(80), np.log10(130),
n_rp_bins) # perpendicular bins
pi_bins = np.logspace(np.log10(80), np.log10(130),
n_pi_bins) # parallel bins
# rp_bin_centres = (rp_bins[1:] + rp_bins[:-1])/2
# pi_bin_centres = (pi_bins[1:] + pi_bins[:-1])/2
# define randoms
n_ran = len(cat.halo_table) * 50 # 500 ideal?
print('Preparing randoms...')
xran = np.random.uniform(0, L, n_ran)
yran = np.random.uniform(0, L, n_ran)
zran = np.random.uniform(0, L, n_ran)
randoms = return_xyz_formatted_array(xran, yran, zran, period=L)
print('2pt jackknife with ' + str(num_threads) + ' threads...')
xi, xi_cov = rp_pi_tpcf_jackknife(pos,
randoms,
rp_bins,
pi_bins,
Nsub=3,
period=L,
num_threads=num_threads)
try:
np.linalg.cholesky(xi_cov)
print('Covariance matrix passes cholesky decomposition')
except:
print('Covariance matrix fails cholesky decomposition')
# save xi as .data file for baofit
# baofit_data = np.column_stack((np.arange(xi.size), xi.flatten(order = 'c')))
# path = os.path.join('/home/dyt/analysis_data/', sim_name+'_'+str(redshift)+'.data')
# print 'saving: ' + path
# np.savetxt(path, baofit_data, fmt = ['%.0f', '%.30f'], delimiter=' ')
return xi, xi_cov
def calc_all_observables(param):
model.param_dict.update(dict(zip(param_names, param))) ##update model.param_dict with pairs (param_names:params)
try:
model.mock.populate()
except:
model.populate_mock(halocat)
gc.collect()
output = []
pos_gals_d = return_xyz_formatted_array(*(model.mock.galaxy_table[ax] for ax in 'xyz'), \
velocity=model.mock.galaxy_table['vz'], velocity_distortion_dimension='z',\
period=Lbox) ##redshift space distorted
pos_gals_d = np.array(pos_gals_d,dtype=float)
#func,funccov = ngal_wp_vpf_Pcic_jk(pos_gals_d, r_wp, pi_max, r_vpf, vpf_centers, proj_search_radius, cylinder_half_length, Lbox, args.Nsidejk)
func,funccov = projected_correlation(pos_gals_d, r_wp, pi_max, Lbox, args.Nsidejk)
output.append(func)
output.append(funccov)
# parameter set
output.append(param)
return output
def _galCorr(cat, scale_factor, outputdir):
'Helper function that uses the built in cat object'
h = 0.7
RBINS = np.logspace(-1, 1.25, 15)
redshift = 1.0/scale_factor - 1.0
print cat
if outputdir[-1] != '/':
outputdir+='/'
#Note: Confusing name between cat and halocat. Consider changing.
halocat = CachedHaloCatalog(simname = cat.simname, halo_finder = cat.halo_finder,version_name = cat.version_name, redshift = redshift)
model = HodModelFactory(
centrals_occupation=StepFuncCens(redshift=redshift),
centrals_profile=TrivialPhaseSpace(redshift=redshift),
satellites_occupation=StepFuncSats(redshift=redshift),
satellites_profile=NFWPhaseSpace(redshift=redshift))
model.populate_mock(halocat, Num_ptcl_requirement = 30)
#Now, calculate with Halotools builtin
#TODO include the fast version
x, y, z = [model.mock.galaxy_table[c] for c in ['x','y','z'] ]
pos = return_xyz_formatted_array(x,y,z)
#TODO N procs
xi_all = tpcf(pos*h, RBINS, period = model.mock.Lbox*h, num_threads = cpu_count())
np.savetxt(outputdir + 'xi_all_gal_%.3f_h.npy' %(scale_factor), xi_all)
def clustering_sample_iterator(table, *masks, **kwargs):
"""
Examples
--------
>>> from astropy.table import Table
>>> t = Table()
>>> t['halo_x'] = [1, 2, 3, 4]
>>> t['halo_y'] = [1, 2, 3, 4]
>>> t['halo_z'] = [1, 2, 3, 4]
>>> mask1 = t['halo_x'] > 2
>>> mask2 = t['halo_y'] <= 3
>>> subtables = list(clustering_sample_iterator(t, mask1, mask2, zspace=False))
"""
zspace = kwargs.get('zspace', True)
period = kwargs.get('period', None)
if (period is None) and (zspace is True):
raise ValueError(
"Must specify ``period`` keyword argument if ``zspace`` is True\n"
"Use ``np.inf`` to ignore periodic boundary conditions")
for i, mask in enumerate(masks):
sample = table[mask]
if zspace:
sample_pos = return_xyz_formatted_array(
sample['halo_x'],
sample['halo_y'],
sample['halo_z'],
velocity=sample['halo_vz'],
velocity_distortion_dimension='z',
period=period)
msg = ("Input ``table`` must have the following columns: \n"
"``halo_x``, ``halo_y``, ``halo_z``, ``halo_vz``")
assert set(('halo_x', 'halo_y', 'halo_z', 'halo_vz')) <= set(
list(table.keys())), msg
else:
sample_pos = return_xyz_formatted_array(sample['halo_x'],
sample['halo_y'],
sample['halo_z'])
msg = ("Input ``table`` must have the following columns: \n"
"``halo_x``, ``halo_y``, ``halo_z``")
assert set(
('halo_x', 'halo_y', 'halo_z')) <= set(list(table.keys())), msg
yield sample_pos
def ht_rp_pi_2pcf(model, L, n_rp_bins=12, n_pi_bins=12, num_threads=10):
x = model.mock.galaxy_table['x']
y = model.mock.galaxy_table['y']
z = model.mock.galaxy_table['z']
pos = return_xyz_formatted_array(x, y, z, period=L)
rp_bins = np.linspace(50, 150, n_rp_bins) # perpendicular bins
pi_bins = np.linspace(50, 150, n_pi_bins) # parallel bins
xi = rp_pi_tpcf(pos, rp_bins, pi_bins, period=L, num_threads=num_threads)
return xi
def popAndCorr(halocat, model, cat, params={}, do_jackknife=True, min_ptcl=MIN_PTCL, rbins=RBINS):
'''Populate a halocat with a model and calculate the tpcf, tpcf_1h, tpcf_2h, and projected corr fun'''
print 'Min Num Particles: %d\t%d bins' % (min_ptcl, len(rbins))
model.param_dict.update(params) # insert new params into model
print model.param_dict
# Note: slow
model.populate_mock(halocat, Num_ptcl_requirement=min_ptcl)
# Now, calculate with Halotools builtin
x, y, z = [model.mock.galaxy_table[c] for c in ['x', 'y', 'z']]
# mask = model.mock.galaxy_table['halo_mvir'] < 1e15/cat.h
pos = return_xyz_formatted_array(x, y, z) # , mask = mask)
t0 = time()
# TODO N procs
if do_jackknife:
Nrands = 5
Nsub = 5
randoms = np.random.random(
(pos.shape[0] * Nrands, 3)) * model.mock.Lbox * cat.h # Solution to NaNs: Just f**k me up with randoms
xi_all, xi_cov = tpcf_jackknife(pos * cat.h, randoms, rbins, period=model.mock.Lbox * cat.h,
num_threads=cpu_count(), Nsub=Nsub)
elif CORRFUNC:
# write bins to file
BINDIR = dirname(abspath(__file__)) # location of files with bin edges
with open(join(BINDIR, './binfile'), 'w') as f:
for low, high in zip(RBINS[:-1], RBINS[1:]):
f.write('\t%f\t%f\n' % (low, high))
# countpairs requires casting in order to work right.
xi_all = countpairs_xi(model.mock.Lbox * cat.h, cpu_count(), join(BINDIR, './binfile'),
x.astype('float32') * cat.h, y.astype('float32') * cat.h, z.astype('float32') * cat.h)
xi_all = np.array(xi_all, dtype='float64')[:, 3]
else:
xi_all = tpcf(pos * cat.h, rbins, period=model.mock.Lbox * cat.h, num_threads=cpu_count())
print 'Corr Calc Time: %.3f s' % (time() - t0)
# halo_hostid = model.mock.galaxy_table['halo_id']
# xi_1h, xi_2h = tpcf_one_two_halo_decomp(pos*cat.h,
# halo_hostid, rbins,
# period=model.mock.Lbox*cat.h, num_threads=cpu_count(),
# max_sample_size=1e7)
# wp_all = wp(pos*cat.h, RBINS, PI_MAX, period=model.mock.Lbox*cat.h, num_threads = cpu_count())
rbin_centers = (rbins[1:] + rbins[:-1]) / 2
output = np.stack([rbin_centers, xi_all]) # , xi_1h, xi_2h])
if do_jackknife:
return output, xi_cov
else:
return output
def _get_lnlike(theta):
logMmin, alpha = theta # sigma_logM, logM0, logM1 = theta
model_instance.param_dict['logMmin'] = logMmin
model_instance.param_dict['sigma_logM'] = sigma_logM
model_instance.param_dict['alpha'] = alpha
model_instance.param_dict['logM0'] = logM0
model_instance.param_dict['logM1'] = logM1
model_instance.mock.populate()
pos = return_xyz_formatted_array(model_instance.mock.galaxy_table['x'],
model_instance.mock.galaxy_table['y'],
model_instance.mock.galaxy_table['z'],
period=Lbox)
x = pos[:, 0]
y = pos[:, 1]
z = pos[:, 2]
velz = model_instance.mock.galaxy_table['vz']
pos_zdist = return_xyz_formatted_array(x,
y,
z,
period=Lbox,
velocity=velz,
velocity_distortion_dimension='z')
pi_max = 60.
nthreads = 1
wp_calc = wp(Lbox,
pi_max,
nthreads,
bin_edges,
pos_zdist[:, 0],
pos_zdist[:, 1],
pos_zdist[:, 2],
verbose=False,
xbin_refine_factor=3,
ybin_refine_factor=3,
zbin_refine_factor=2)
wp_diff = wp_vals - wp_calc['wp']
ng_diff = ng - model_instance.mock.number_density
return -0.5 * np.dot(wp_diff, np.dot(
invcov, wp_diff)) + -0.5 * (ng_diff**2) / (ng_cov**2)
def main(model_gen_func, fiducial, output_fname):
global model
model = model_gen_func()
global fid
fid = np.array(fiducial)
params = fid * np.ones((7 * args.Nparam, 7))
dp_range = np.array((0.025, 0.05, 0.02, 0.1, 0.02, 0.05, 0.05))
for i in range(7):
params[args.Nparam * i:args.Nparam * i + args.Nparam / 2,
i] -= dp_range[i]
params[args.Nparam * i + args.Nparam / 2:args.Nparam * i + args.Nparam,
i] += dp_range[i]
output_dict = collections.defaultdict(list)
nproc = args.nproc
global halocat
global ptclpos
global num_ptcls_to_use
with Pool(nproc) as pool:
if 1:
halocat = CachedHaloCatalog(simname = args.simname, version_name = args.version,redshift = args.redshift, \
halo_finder = args.halofinder)
model.populate_mock(halocat)
if args.ptclpos:
ptclpos = np.loadtxt(args.ptclpos)
else:
mask = np.random.rand(len(halocat.ptcl_table)) < args.ptclrate
ptclpos = return_xyz_formatted_array(*(table[ax]
for ax in 'xyz'),
period=Lbox)
num_ptcls_to_use = len(ptclpos)
for i, output_data in enumerate(
pool.map(calc_all_observables, params)):
if i % nproc == nproc - 1:
print i
print str(datetime.now())
for name, data in zip(output_names, output_data):
output_dict[name].append(data)
for name in output_names:
output_dict[name] = np.array(output_dict[name])
np.savez(output_fname, **output_dict)
def masked_wp(subhalos, mask=None):
"""
"""
if mask is None:
mask = np.ones_like(subhalos).astype(bool)
rp_bins, pi_max = np.logspace(-1, 1.35, 25), 20.
rmids = 10**(0.5 * (np.log10(rp_bins[:-1]) + np.log10(rp_bins[1:])))
pos = return_xyz_formatted_array(subhalos['x'],
subhalos['y'],
subhalos['z'],
mask=mask,
period=250,
velocity=subhalos['vz'],
velocity_distortion_dimension='z')
return rmids, wp(pos, rp_bins, pi_max, period=250.)
def calc_all_observables(param):
model.param_dict.update(dict(
zip(param_names,
param))) ##update model.param_dict with pairs (param_names:params)
n_est = c.ngal_estimate(param)
print n_est
if n_est > 150000:
return [0, np.zeros(19), np.zeros((19, 19)), param]
try:
model.mock.populate()
except:
model.populate_mock(halocat)
gc.collect()
output = []
print model.mock.galaxy_table['x'].size
if model.mock.galaxy_table['x'].size < 100000 or model.mock.galaxy_table[
'x'].size > 105000:
return [0, np.zeros(19), np.zeros((19, 19)), param]
pos_gals_d = return_xyz_formatted_array(*(model.mock.galaxy_table[ax] for ax in 'xyz'), \
velocity=model.mock.galaxy_table['vz'], velocity_distortion_dimension='z',\
period=Lbox) ##redshift space distorted
pos_gals_d = np.array(pos_gals_d, dtype=float)
# ngals
output.append(model.mock.galaxy_table['x'].size)
# wprp and cov
wp_wpcov = projected_correlation(pos_gals_d,
r_wp,
pi_max,
Lbox,
jackknife_nside=args.Nsidejk)
output.append(wp_wpcov[0])
output.append(wp_wpcov[1])
# parameter set
output.append(param)
return output
def calc_all_observables(param):
model.param_dict.update(dict(
zip(param_names,
param))) ##update model.param_dict with pairs (param_names:params)
try:
model.mock.populate()
except:
model.populate_mock(halocat)
gc.collect()
output = []
pos_gals_d = return_xyz_formatted_array(*(model.mock.galaxy_table[ax] for ax in 'xyz'), \
velocity=model.mock.galaxy_table['vz'], velocity_distortion_dimension='z',\
period=Lbox) ##redshift space distorted
pos_gals_d = np.array(pos_gals_d, dtype=float)
if args.central:
mask_cen = model.mock.galaxy_table['gal_type'] == 'centrals'
pos_gals_d = pos_gals_d[mask_cen]
if args.Vmax != 0:
idx_galaxies, idx_halos = crossmatch(
model.mock.galaxy_table['halo_id'], halocat.halo_table['halo_id'])
model.mock.galaxy_table['halo_vmax'] = np.zeros(
len(model.mock.galaxy_table),
dtype=halocat.halo_table['halo_vmax'].dtype)
model.mock.galaxy_table['halo_vmax'][
idx_galaxies] = halocat.halo_table['halo_vmax'][idx_halos]
mask_Vmax = model.mock.galaxy_table['halo_vmax'] > args.Vmax
pos_gals_d = pos_gals_d[mask_Vmax]
# ngals
output.append(model.mock.galaxy_table['x'].size)
# wprp
output.append(wp(pos_gals_d, r_wp, pi_max, period=Lbox))
# parameter set
output.append(param)
return output
def calc_all_observables(param):
model.param_dict.update(dict(
zip(param_names,
param))) ##update model.param_dict with pairs (param_names:params)
try:
model.mock.populate()
except:
model.populate_mock(halocat)
gc.collect()
output = []
pos_gals_d = return_xyz_formatted_array(*(model.mock.galaxy_table[ax] for ax in 'xyz'), \
velocity=model.mock.galaxy_table['vz'], velocity_distortion_dimension='z',\
period=Lbox) ##redshift space distorted
pos_gals_d = np.array(pos_gals_d, dtype=float)
if args.central:
mask_cen = model.mock.galaxy_table['gal_type'] == 'centrals'
pos_gals_d = pos_gals_d[mask_cen]
# ngals
output.append(model.mock.galaxy_table['x'].size)
# wprp and cov
wp_wpcov = projected_correlation(pos_gals_d,
r_wp,
pi_max,
Lbox,
jackknife_nside=args.Nsidejk)
output.append(wp_wpcov[0])
output.append(wp_wpcov[1])
# parameter set
output.append(param)
return output
def calc_all_observables(param):
model.param_dict.update(dict(
zip(param_names,
param))) ##update model.param_dict with pairs (param_names:params)
try:
model.mock.populate()
except:
model.populate_mock(halocat)
gc.collect()
output = []
pos_gals_d = return_xyz_formatted_array(*(model.mock.galaxy_table[ax] for ax in 'xyz'), \
velocity=model.mock.galaxy_table['vz'], velocity_distortion_dimension='z',\
period=Lbox) ##redshift space distorted
pos_gals_d = np.array(pos_gals_d, dtype=float)
vpf = void_prob_func(pos_gals_d,
r_vpf,
random_sphere_centers=vpf_centers,
period=Lbox)
wprp = wp(pos_gals_d, r_wp, pi_max, period=Lbox)
Pcic = np.bincount(counts_in_cylinders(pos_gals_d, pos_gals_d, proj_search_radius, \
cylinder_half_length,period=Lbox), minlength=100)[1:71]/float(pos_gals_d.shape[0])
func = np.concatenate((np.array(
(pos_gals_d.shape[0] / float(Lbox**3), )), wprp, vpf, Pcic))
output.append(func)
# parameter set
output.append(param)
output.append(np.where(param - median_w != 0)[0][0])
return output
def tabulate(cls,
halocat,
tpcf,
*tpcf_args,
mode='auto',
Num_ptcl_requirement=sim_defaults.Num_ptcl_requirement,
cosmology=sim_defaults.default_cosmology,
prim_haloprop_key=model_defaults.prim_haloprop_key,
prim_haloprop_bins=100,
sec_haloprop_key=model_defaults.sec_haloprop_key,
sec_haloprop_percentile_bins=None,
sats_per_prim_haloprop=3e-12,
downsample=1.0,
verbose=False,
redshift_space_distortions=True,
cens_prof_model=None,
sats_prof_model=None,
project_xyz=False,
cosmology_ref=None,
comm=None,
**tpcf_kwargs):
"""
Tabulates correlation functions for halos such that galaxy correlation
functions can be calculated rapidly.
Parameters
----------
halocat : object
Either an instance of `halotools.sim_manager.CachedHaloCatalog` or
`halotools.sim_manager.UserSuppliedHaloCatalog`. This halo catalog
is used to tabubulate correlation functions.
tpcf : function
The halotools correlation function for which values are tabulated.
Positional arguments should be passed after this function.
Additional keyword arguments for the correlation function are also
passed through this function.
*tpcf_args : tuple, optional
Positional arguments passed to the ``tpcf`` function.
mode : string, optional
String describing whether an auto- ('auto') or a cross-correlation
('cross') function is going to be tabulated.
Num_ptcl_requirement : int, optional
Requirement on the number of dark matter particles in the halo
catalog. The column defined by the ``prim_haloprop_key`` string
will have a cut placed on it: all halos with
halocat.halo_table[prim_haloprop_key] <
Num_ptcl_requirement*halocat.particle_mass will be thrown out
immediately after reading the original halo catalog in memory.
Default value is set in
`~halotools.sim_defaults.Num_ptcl_requirement`.
cosmology : object, optional
Instance of an astropy `~astropy.cosmology`. Default cosmology is
set in `~halotools.sim_manager.sim_defaults`. This might be used to
calculate phase-space distributions and redshift space distortions.
prim_haloprop_key : string, optional
String giving the column name of the primary halo property
governing the occupation statistics of gal_type galaxies. Default
value is specified in the model_defaults module.
prim_haloprop_bins : int or list, optional
Integer determining how many (logarithmic) bins in primary halo
property will be used. If a list or numpy array is provided, these
will be used as bins directly.
sec_haloprop_key : string, optional
String giving the column name of the secondary halo property
governing the assembly bias. Must be a key in the table passed to
the methods of `HeavisideAssembiasComponent`. Default value is
specified in the `~halotools.empirical_models.model_defaults`
module.
sec_haloprop_percentile_bins : int, float, list or None, optional
If an integer, it determines how many evenly spaced bins in the
secondary halo property percentiles are going to be used. If a
float between 0 and 1, it determines the split. Finally, if a list
or numpy array, it directly describes the bins that are going to be
used. If None is provided, no binning is applied.
sats_per_prim_haloprop : float, optional
Float determing how many satellites sample each halo. For each
halo, the number is drawn from a Poisson distribution with an
expectation value of ``sats_per_prim_haloprop`` times the primary
halo property.
downsample : float, optional
Fraction between 0 and 1 used to downsample the total sample used
to tabulate correlation functions. Values below unity can be used
to reduce the computation time. It should not result in biases but
the resulting correlation functions will be less accurate.
verbose : boolean, optional
Boolean determing whether the progress should be displayed.
redshift_space_distortions : boolean, optional
Boolean determining whether redshift space distortions should be
applied to halos/galaxies.
cens_prof_model : object, optional
Instance of `halotools.empirical_models.MonteCarloGalProf` that
determines the phase space coordinates of centrals. If none is
provided, `halotools.empirical_models.TrivialPhaseSpace` will be
used.
sats_prof_model : object, optional
Instance of `halotools.empirical_models.MonteCarloGalProf` that
determines the phase space coordinates of satellites. If none is
provided, `halotools.empirical_models.NFWPhaseSpace` will be used.
project_xyz : bool, optional
If True, the coordinates will be projected along all three spatial
axes. By default, only the projection onto the z-axis is used.
comm : MPI communicator
If not None, then will distribute calculation via MPI
**tpcf_kwargs : dict, optional
Keyword arguments passed to the ``tpcf`` function.
Returns
-------
halotab : TabCorr
Object containing all necessary information to calculate
correlation functions for arbitrary galaxy models.
"""
if sec_haloprop_percentile_bins is None:
sec_haloprop_percentile_bins = np.array([0, 1])
elif isinstance(sec_haloprop_percentile_bins, float):
sec_haloprop_percentile_bins = np.array(
[0, sec_haloprop_percentile_bins, 1])
if 'period' in tpcf_kwargs:
print('Warning: TabCorr will pass the keyword argument "period" ' +
'to {} based on the Lbox argument of'.format(tpcf.__name__) +
' the halo catalog. The value you provided will be ignored.')
del tpcf_kwargs['period']
halotab = cls()
if cosmology_ref is not None and mode == 'auto':
rp_stretch = (
(cosmology_ref.comoving_distance(halocat.redshift) *
cosmology_ref.H0) /
(cosmology.comoving_distance(halocat.redshift) * cosmology.H0))
pi_stretch = (cosmology.efunc(halocat.redshift) /
cosmology_ref.efunc(halocat.redshift))
lbox_stretch = np.array([rp_stretch, rp_stretch, pi_stretch])
else:
lbox_stretch = np.ones(3)
# First, we tabulate the halo number densities.
halos = halocat.halo_table
halos = halos[halos['halo_pid'] == -1]
halos = halos[halos[prim_haloprop_key] >=
(Num_ptcl_requirement - 0.5) * halocat.particle_mass]
if isinstance(prim_haloprop_bins, int):
prim_haloprop_bins = np.linspace(
np.log10(np.amin(halos[prim_haloprop_key])) - 1e-3,
np.log10(np.amax(halos[prim_haloprop_key])) + 1e-3,
prim_haloprop_bins + 1)
elif not isinstance(prim_haloprop_bins, (list, np.ndarray)):
raise ValueError('prim_haloprop_bins must be an int, list or ' +
'numpy array.')
halos[sec_haloprop_key +
'_percentile'] = (compute_conditional_percentiles(
table=halos,
prim_haloprop_key=prim_haloprop_key,
sec_haloprop_key=sec_haloprop_key))
halotab.gal_type = Table()
n_h, prim_haloprop_bins, sec_haloprop_percentile_bins = (
np.histogram2d(
np.log10(halos[prim_haloprop_key]),
halos[sec_haloprop_key + '_percentile'],
bins=[prim_haloprop_bins, sec_haloprop_percentile_bins]))
halotab.gal_type['n_h'] = n_h.ravel(order='F') / np.prod(
halocat.Lbox * lbox_stretch)
grid = np.meshgrid(prim_haloprop_bins, sec_haloprop_percentile_bins)
halotab.gal_type['log_prim_haloprop_min'] = grid[0][:-1, :-1].ravel()
halotab.gal_type['log_prim_haloprop_max'] = grid[0][:-1, 1:].ravel()
halotab.gal_type['sec_haloprop_percentile_min'] = (
grid[1][:-1, :-1].ravel())
halotab.gal_type['sec_haloprop_percentile_max'] = (
grid[1][1:, :-1].ravel())
halotab.gal_type = vstack([halotab.gal_type, halotab.gal_type])
halotab.gal_type['gal_type'] = np.concatenate(
(np.repeat('centrals'.encode('utf8'),
len(halotab.gal_type) // 2),
np.repeat('satellites'.encode('utf8'),
len(halotab.gal_type) // 2)))
halotab.gal_type['prim_haloprop'] = 10**(
0.5 * (halotab.gal_type['log_prim_haloprop_min'] +
halotab.gal_type['log_prim_haloprop_max']))
halotab.gal_type['sec_haloprop_percentile'] = (
0.5 * (halotab.gal_type['sec_haloprop_percentile_min'] +
halotab.gal_type['sec_haloprop_percentile_max']))
# Now, we tabulate the correlation functions.
cens_occ_model = Zheng07Cens(prim_haloprop_key=prim_haloprop_key)
if cens_prof_model is None:
cens_prof_model = TrivialPhaseSpace(redshift=halocat.redshift)
sats_occ_model = Zheng07Sats(prim_haloprop_key=prim_haloprop_key)
if sats_prof_model is None:
sats_prof_model = NFWPhaseSpace(redshift=halocat.redshift)
model = HodModelFactory(centrals_occupation=cens_occ_model,
centrals_profile=cens_prof_model,
satellites_occupation=sats_occ_model,
satellites_profile=sats_prof_model)
model.param_dict['logMmin'] = 0
model.param_dict['sigma_logM'] = 0.1
model.param_dict['alpha'] = 1.0
model.param_dict['logM0'] = 0
model.param_dict['logM1'] = -np.log10(sats_per_prim_haloprop)
model.populate_mock(halocat, Num_ptcl_requirement=Num_ptcl_requirement)
gals = model.mock.galaxy_table
gals = gals[np.random.random(len(gals)) < downsample]
idx_gals, idx_halos = crossmatch(gals['halo_id'], halos['halo_id'])
assert np.all(gals['halo_id'][idx_gals] == halos['halo_id'][idx_halos])
gals[sec_haloprop_key + '_percentile'] = np.zeros(len(gals))
gals[sec_haloprop_key +
'_percentile'][idx_gals] = (halos[sec_haloprop_key +
'_percentile'][idx_halos])
if verbose:
print("Number of tracer particles: {0}".format(len(gals)))
for xyz in ['xyz', 'yzx', 'zxy']:
pos_all = return_xyz_formatted_array(
x=gals[xyz[0]],
y=gals[xyz[1]],
z=gals[xyz[2]],
velocity=gals['v' +
xyz[2]] if redshift_space_distortions else 0,
velocity_distortion_dimension='z',
period=halocat.Lbox,
redshift=halocat.redshift,
cosmology=cosmology) * lbox_stretch
pos = []
n_gals = []
for i in range(len(halotab.gal_type)):
mask = ((10**(halotab.gal_type['log_prim_haloprop_min'][i]) <
gals[prim_haloprop_key]) &
(10**(halotab.gal_type['log_prim_haloprop_max'][i]) >=
gals[prim_haloprop_key]) &
(halotab.gal_type['sec_haloprop_percentile_min'][i] <
gals[sec_haloprop_key + '_percentile']) &
(halotab.gal_type['sec_haloprop_percentile_max'][i] >=
gals[sec_haloprop_key + '_percentile']) &
(halotab.gal_type['gal_type'][i] == gals['gal_type']))
pos.append(pos_all[mask])
n_gals.append(np.sum(mask))
n_gals = np.array(n_gals)
n_done = 0
if verbose:
print("Projecting onto {0}-axis...".format(xyz[2]))
gal_type_index = np.arange(len(halotab.gal_type))
if (comm is not None) & (has_mpi):
size = comm.size
rank = comm.rank
gal_type_index = gal_type_index[rank::size]
print('{}: len(gal_type_index)={}'.format(
rank, len(gal_type_index)))
elif (comm is not None) & (not has_mpi):
raise (ImportError(
"You passed something to the comm argument, but I couldn't import mpi4py"
))
for i in gal_type_index:
if mode == 'auto':
for k in np.arange(i, len(halotab.gal_type)):
if len(pos[i]) * len(pos[k]) > 0:
if verbose:
if comm:
if comm.rank == 0:
n_done += (n_gals[i] * n_gals[k] *
(2 if k != i else 1))
print_progress(n_done /
np.sum(n_gals)**2)
else:
n_done += (n_gals[i] * n_gals[k] *
(2 if k != i else 1))
print_progress(n_done / np.sum(n_gals)**2)
if i == k:
xi = tpcf(pos[i],
*tpcf_args,
sample2=pos[k] if k != i else None,
do_auto=True,
do_cross=False,
period=halocat.Lbox * lbox_stretch,
**tpcf_kwargs)
else:
xi = tpcf(pos[i],
*tpcf_args,
sample2=pos[k] if k != i else None,
do_auto=False,
do_cross=True,
period=halocat.Lbox * lbox_stretch,
**tpcf_kwargs)
if 'tpcf_matrix' not in locals():
tpcf_matrix = np.zeros(
(len(xi.ravel()), len(halotab.gal_type),
len(halotab.gal_type)))
tpcf_shape = xi.shape
tpcf_matrix[:, i, k] += xi.ravel()
tpcf_matrix[:, k, i] = tpcf_matrix[:, i, k]
elif mode == 'cross':
if len(pos[i]) > 0:
if verbose:
n_done += n_gals[i]
print_progress(n_done / np.sum(n_gals))
xi = tpcf(pos[i],
*tpcf_args,
**tpcf_kwargs,
period=halocat.Lbox * lbox_stretch)
if tpcf.__name__ == 'delta_sigma':
xi = xi[1]
if 'tpcf_matrix' not in locals():
tpcf_matrix = np.zeros(
(len(xi.ravel()), len(halotab.gal_type)))
tpcf_shape = xi.shape
tpcf_matrix[:, i] = xi.ravel()
if not project_xyz or mode == 'cross':
break
if comm:
tpcf_matrix = comm.allreduce(tpcf_matrix, op=MPI.SUM)
if project_xyz and mode == 'auto':
tpcf_matrix /= 3.0
if mode == 'auto':
tpcf_matrix_flat = []
for i in range(tpcf_matrix.shape[0]):
tpcf_matrix_flat.append(
symmetric_matrix_to_array(tpcf_matrix[i]))
tpcf_matrix = np.array(tpcf_matrix_flat)
halotab.attrs = {}
halotab.attrs['tpcf'] = tpcf.__name__
halotab.attrs['mode'] = mode
halotab.attrs['simname'] = halocat.simname
halotab.attrs['redshift'] = halocat.redshift
halotab.attrs['Num_ptcl_requirement'] = Num_ptcl_requirement
halotab.attrs['prim_haloprop_key'] = prim_haloprop_key
halotab.attrs['sec_haloprop_key'] = sec_haloprop_key
halotab.tpcf_args = tpcf_args
halotab.tpcf_kwargs = tpcf_kwargs
halotab.tpcf_shape = tpcf_shape
halotab.tpcf_matrix = tpcf_matrix
halotab.init = True
return halotab
def get_deltasigma(galaxy_data, particle_data, min_sep=44, max_sep=2e3, binning='log', nbins=20, verbosity=1, downsampling_factor=1):
if verbosity>0:
print 'Will construct %s - %s \Delta \Sigma profile'%ctype
# Decide on an appropriate binning scheme
if (binning.lower()=='log'):
rbins = np.logspace(np.log10(min_sep), np.log10(max_sep), nbins )
elif (binning.lower()=='linear'):
rbins = np.linspace(min_sep, max_sep, nbins )
if verbosity>1:
print 'Will use %s binning:'%binning, rbins
# Parse the mask
#mask1 = tools.choose_cs_mask(data,ctype[0])
#mask2 = tools.choose_cs_mask(data,ctype[1])
pos1 = pretending.return_xyz_formatted_array(particle_data['x'], particle_data['y'], particle_data['z']) #, mask = mask1)
pos2 = pretending.return_xyz_formatted_array(galaxy_data['x'], galaxy_data['y'], galaxy_data['z']) #, mask = mask2)
R = np.sqrt(np.array(rbins)[1:]*np.array(rbins)[:-1])
rp, DeltaSigma = pretending.delta_sigma(pos2, pos1, particle_data['mass'], downsampling_factor,
rbins, info.Lbox, cosmology=info.cosmology, num_threads='max')
return rp, DeltaSigma
halo_finder = args.halofinder)
model = decorated_hod_model()
model.param_dict.update(dict(zip(
param_names,
fiducial_p))) ##update model.param_dict with pairs (param_names:params)
try:
model.mock.populate()
except:
model.populate_mock(halocat)
gc.collect()
pos_gals_d = return_xyz_formatted_array(*(model.mock.galaxy_table[ax] for ax in 'xyz'), \
velocity=model.mock.galaxy_table['vz'], velocity_distortion_dimension='z',\
period=Lbox) ##redshift space distorted
pos_gals_d = np.array(pos_gals_d, dtype=float)
pos_gals = return_xyz_formatted_array(*(model.mock.galaxy_table[ax]
for ax in 'xyz'),
period=Lbox)
pos_gals = np.array(pos_gals, dtype=float)
particle_masses = halocat.particle_mass
total_num_ptcls_in_snapshot = halocat.num_ptcl_per_dim**3
##########################################################
def random_vpfcen(nsphere):
model_instance.mock.populate()
except:
model_instance.populate_mock(halocat)
theta = [11.96, 0.38, 1.16, 13.28 - 1.7, 13.28]
logMmin, sigma_logM, alpha, logM0, logM1 = theta
model_instance.param_dict['logMmin'] = logMmin
model_instance.param_dict['sigma_logM'] = sigma_logM
model_instance.param_dict['alpha'] = alpha
model_instance.param_dict['logM0'] = logM0
model_instance.param_dict['logM1'] = logM1
Lbox = 250.
model_instance.mock.populate()
pos = return_xyz_formatted_array(model_instance.mock.galaxy_table['x'],
model_instance.mock.galaxy_table['y'],
model_instance.mock.galaxy_table['z'],
period=Lbox)
x = pos[:, 0]
y = pos[:, 1]
z = pos[:, 2]
velz = model_instance.mock.galaxy_table['vz']
pos_zdist = return_xyz_formatted_array(x,
y,
z,
period=Lbox,
velocity=velz,
velocity_distortion_dimension='z')
pi_max = 60.
nthreads = 4
import halotools, Corrfunc
def downsample_ptclpos(rate):
mask = np.random.rand(len(halocat.ptcl_table)) < rate
table = halocat.ptcl_table[mask]
return return_xyz_formatted_array(*(table[ax] for ax in 'xyz'),
period=Lbox)
particle_portion = 0.1
rp_bins = np.logspace(-1.398, 1.176, 14) ##to match the leauthaud paper
num_ptcls_to_use = int(1e6)
particle_masses = np.zeros(
num_ptcls_to_use) + halocat.particle_mass / particle_portion
total_num_ptcls_in_snapshot = len(halocat.ptcl_table)
downsampling_factor = total_num_ptcls_in_snapshot / float(num_ptcls_to_use)
##ggl
pi_max = 60
r_wp = np.logspace(-1, np.log10(Lbox) - 1, 20)
##wp
pos_part = return_xyz_formatted_array(*(halocat.ptcl_table[ax]
for ax in 'xyz'),
period=Lbox)
pos_part = randomly_downsample_data(pos_part, num_ptcls_to_use)
#########################################################
def calc_all_observables(param):
model.param_dict.update(dict(
zip(param_names,
param))) ##update model.param_dict with pairs (param_names:params)
c = Ngal_estimate(halocat, param)
n_est = c.ngal_estimate()
if n_est < 1e5 and n_est > 7.8e4:
def tabulate(cls,
halocat,
tpcf,
*tpcf_args,
mode='auto',
Num_ptcl_requirement=sim_defaults.Num_ptcl_requirement,
prim_haloprop_key=model_defaults.prim_haloprop_key,
prim_haloprop_bins=100,
sec_haloprop_key=model_defaults.sec_haloprop_key,
sec_haloprop_percentile_bins=None,
sats_per_prim_haloprop=3e-12,
downsample=1.0,
verbose=False,
redshift_space_distortions=True,
cens_prof_model=None,
sats_prof_model=None,
project_xyz=False,
cosmology_obs=None,
num_threads=1,
**tpcf_kwargs):
"""
Tabulates correlation functions for halos such that galaxy correlation
functions can be calculated rapidly.
Parameters
----------
halocat : object
Either an instance of `halotools.sim_manager.CachedHaloCatalog` or
`halotools.sim_manager.UserSuppliedHaloCatalog`. This halo catalog
is used to tabubulate correlation functions.
tpcf : function
The halotools correlation function for which values are tabulated.
Positional arguments should be passed after this function.
Additional keyword arguments for the correlation function are also
passed through this function.
*tpcf_args : tuple, optional
Positional arguments passed to the ``tpcf`` function.
mode : string, optional
String describing whether an auto- ('auto') or a cross-correlation
('cross') function is going to be tabulated.
Num_ptcl_requirement : int, optional
Requirement on the number of dark matter particles in the halo
catalog. The column defined by the ``prim_haloprop_key`` string
will have a cut placed on it: all halos with
halocat.halo_table[prim_haloprop_key] <
Num_ptcl_requirement*halocat.particle_mass will be thrown out
immediately after reading the original halo catalog in memory.
Default value is set in
`~halotools.sim_defaults.Num_ptcl_requirement`.
prim_haloprop_key : string, optional
String giving the column name of the primary halo property
governing the occupation statistics of gal_type galaxies. Default
value is specified in the model_defaults module.
prim_haloprop_bins : int or list, optional
Integer determining how many (logarithmic) bins in primary halo
property will be used. If a list or numpy array is provided, these
will be used as bins directly.
sec_haloprop_key : string, optional
String giving the column name of the secondary halo property
governing the assembly bias. Must be a key in the table passed to
the methods of `HeavisideAssembiasComponent`. Default value is
specified in the `~halotools.empirical_models.model_defaults`
module.
sec_haloprop_percentile_bins : int, float or None, optional
If an integer, it determines how many evenly spaced bins in the
secondary halo property percentiles are going to be used. If a
float between 0 and 1, it determines the split. If None is
provided, no binning is applied.
sats_per_prim_haloprop : float, optional
Float determing how many satellites sample each halo. For each
halo, the number is drawn from a Poisson distribution with an
expectation value of ``sats_per_prim_haloprop`` times the primary
halo property.
downsample : float or function, optional
Fraction between 0 and 1 used to downsample the total sample used
to tabulate correlation functions. Values below unity can be used
to reduce the computation time. It should not result in biases but
the resulting correlation functions will be less accurate. If
float, the same value is applied to all halos. If function, it
should return the fraction is a function of the primary halo
property.
verbose : boolean, optional
Boolean determing whether the progress should be displayed.
redshift_space_distortions : boolean, optional
Boolean determining whether redshift space distortions should be
applied to halos/galaxies.
cens_prof_model : object, optional
Instance of `halotools.empirical_models.MonteCarloGalProf` that
determines the phase space coordinates of centrals. If none is
provided, `halotools.empirical_models.TrivialPhaseSpace` will be
used.
sats_prof_model : object, optional
Instance of `halotools.empirical_models.MonteCarloGalProf` that
determines the phase space coordinates of satellites. If none is
provided, `halotools.empirical_models.NFWPhaseSpace` will be used.
project_xyz : bool, optional
If True, the coordinates will be projected along all three spatial
axes. By default, only the projection onto the z-axis is used.
cosmology_obs : object, optional
Instance of an astropy `~astropy.cosmology`. This can be used to
correct coordinates in the simulation for the Alcock-Paczynski (AP)
effect, i.e. a mismatch between the cosmology of the model
(simulation) and the cosmology used to interpret observations. Note
that the cosmology of the simulation is part of the halocat object.
If None, no correction for the AP effect is applied. Also, a
correction for the AP effect is only applied for auto-correlation
functions.
num_threads : int, optional
How many threads to use for the tabulation.
**tpcf_kwargs : dict, optional
Keyword arguments passed to the ``tpcf`` function.
Returns
-------
halotab : TabCorr
Object containing all necessary information to calculate
correlation functions for arbitrary galaxy models.
"""
if 'period' in tpcf_kwargs:
print('Warning: TabCorr will pass the keyword argument "period" ' +
'to {} based on the Lbox argument of'.format(tpcf.__name__) +
' the halo catalog. The value you provided will be ignored.')
del tpcf_kwargs['period']
halotab = cls()
if cosmology_obs is not None and mode == 'auto':
rp_stretch = (
(cosmology_obs.comoving_distance(halocat.redshift) *
cosmology_obs.H0) /
(halocat.cosmology.comoving_distance(halocat.redshift) *
halocat.cosmology.H0))
pi_stretch = (halocat.cosmology.efunc(halocat.redshift) /
cosmology_obs.efunc(halocat.redshift))
lbox_stretch = np.array([rp_stretch, rp_stretch, pi_stretch])
else:
lbox_stretch = np.ones(3)
# First, we tabulate the halo number densities.
halos = halocat.halo_table
halos = halos[halos['halo_pid'] == -1]
halos = halos[halos[prim_haloprop_key] >=
(Num_ptcl_requirement + 0.5) * halocat.particle_mass]
if isinstance(prim_haloprop_bins, int):
prim_haloprop_bins = np.linspace(
np.log10(np.amin(halos[prim_haloprop_key])) - 1e-3,
np.log10(np.amax(halos[prim_haloprop_key])) + 1e-3,
prim_haloprop_bins + 1)
elif isinstance(prim_haloprop_bins, (list, np.ndarray)):
pass
else:
raise ValueError('prim_haloprop_bins must be an int, list or ' +
'numpy array.')
if sec_haloprop_percentile_bins is None:
sec_haloprop_percentile_bins = np.array([-1e-3, 1 + 1e-3])
elif isinstance(sec_haloprop_percentile_bins, float):
if not (0 < sec_haloprop_percentile_bins
and sec_haloprop_percentile_bins < 1):
raise ValueError('sec_haloprop_percentile_bins must be ' +
'between 0 and 1.')
sec_haloprop_percentile_bins = np.array(
[-1e-3, sec_haloprop_percentile_bins, 1 + 1e-3])
elif isinstance(sec_haloprop_percentile_bins, int):
sec_haloprop_percentile_bins = np.linspace(
-1e-3, 1 + 1e-3, sec_haloprop_percentile_bins + 1)
else:
raise ValueError('sec_haloprop_percentile_bins must be an int, ' +
'float, list or numpy array.')
halos[sec_haloprop_key +
'_percentile'] = (compute_conditional_percentiles(
table=halos,
prim_haloprop_key=prim_haloprop_key,
sec_haloprop_key=sec_haloprop_key))
halotab.gal_type = Table()
n_h, prim_haloprop_bins, sec_haloprop_percentile_bins = (
np.histogram2d(
np.log10(halos[prim_haloprop_key]),
halos[sec_haloprop_key + '_percentile'],
bins=[prim_haloprop_bins, sec_haloprop_percentile_bins]))
halotab.gal_type['n_h'] = n_h.ravel(order='F')
grid = np.meshgrid(prim_haloprop_bins, sec_haloprop_percentile_bins)
halotab.gal_type['log_prim_haloprop_min'] = grid[0][:-1, :-1].ravel()
halotab.gal_type['log_prim_haloprop_max'] = grid[0][:-1, 1:].ravel()
halotab.gal_type['sec_haloprop_percentile_min'] = (
grid[1][:-1, :-1].ravel())
halotab.gal_type['sec_haloprop_percentile_max'] = (
grid[1][1:, :-1].ravel())
halotab.gal_type = vstack([halotab.gal_type, halotab.gal_type])
halotab.gal_type['gal_type'] = np.concatenate(
(np.repeat('centrals'.encode('utf8'),
len(halotab.gal_type) // 2),
np.repeat('satellites'.encode('utf8'),
len(halotab.gal_type) // 2)))
halotab.gal_type['prim_haloprop'] = 10**(
0.5 * (halotab.gal_type['log_prim_haloprop_min'] +
halotab.gal_type['log_prim_haloprop_max']))
halotab.gal_type['sec_haloprop_percentile'] = (
0.5 * (halotab.gal_type['sec_haloprop_percentile_min'] +
halotab.gal_type['sec_haloprop_percentile_max']))
# Now, we tabulate the correlation functions.
cens_occ_model = Zheng07Cens(prim_haloprop_key=prim_haloprop_key)
if cens_prof_model is None:
cens_prof_model = TrivialPhaseSpace(redshift=halocat.redshift)
sats_occ_model = Zheng07Sats(prim_haloprop_key=prim_haloprop_key)
if sats_prof_model is None:
sats_prof_model = NFWPhaseSpace(redshift=halocat.redshift)
model = HodModelFactory(centrals_occupation=cens_occ_model,
centrals_profile=cens_prof_model,
satellites_occupation=sats_occ_model,
satellites_profile=sats_prof_model)
model.param_dict['logMmin'] = 0
model.param_dict['sigma_logM'] = 0.1
model.param_dict['alpha'] = 1.0
model.param_dict['logM0'] = 0
model.param_dict['logM1'] = -np.log10(sats_per_prim_haloprop)
model.populate_mock(halocat, Num_ptcl_requirement=Num_ptcl_requirement)
gals = model.mock.galaxy_table
idx_gals, idx_halos = crossmatch(gals['halo_id'], halos['halo_id'])
assert np.all(gals['halo_id'][idx_gals] == halos['halo_id'][idx_halos])
gals[sec_haloprop_key + '_percentile'] = np.zeros(len(gals))
gals[sec_haloprop_key +
'_percentile'][idx_gals] = (halos[sec_haloprop_key +
'_percentile'][idx_halos])
if verbose:
print("Number of tracer particles: {0}".format(len(gals)))
for xyz in ['xyz', 'yzx', 'zxy']:
if verbose and project_xyz:
print("Projecting onto {0}-axis...".format(xyz[2]))
pos_all = (return_xyz_formatted_array(
x=gals[xyz[0]],
y=gals[xyz[1]],
z=gals[xyz[2]],
velocity=gals['v' +
xyz[2]] if redshift_space_distortions else 0,
velocity_distortion_dimension='z',
period=halocat.Lbox,
redshift=halocat.redshift,
cosmology=halocat.cosmology) * lbox_stretch)
period = halocat.Lbox * lbox_stretch
# Get a list of the positions of each sub-population.
i_prim = np.digitize(np.log10(gals[prim_haloprop_key]),
bins=prim_haloprop_bins,
right=False) - 1
mask = (i_prim < 0) | (i_prim >= len(prim_haloprop_bins))
i_sec = np.digitize(gals[sec_haloprop_key + '_percentile'],
bins=sec_haloprop_percentile_bins,
right=False) - 1
i_type = np.where(gals['gal_type'] == 'centrals', 0, 1)
# Throw out those that don't fall into any bin.
pos_all = pos_all[~mask]
i = (i_prim + i_sec * (len(prim_haloprop_bins) - 1) + i_type *
((len(prim_haloprop_bins) - 1) *
(len(sec_haloprop_percentile_bins) - 1)))
pos_all = pos_all[np.argsort(i)]
counts = np.bincount(i, minlength=len(halotab.gal_type))
assert len(counts) == len(halotab.gal_type)
pos_bin = []
for i in range(len(halotab.gal_type)):
pos = pos_all[np.sum(counts[:i]):np.sum(counts[:i + 1]), :]
if halotab.gal_type['gal_type'][i] == 'centrals':
# Make sure the number of halos are consistent.
try:
assert len(pos) == int(halotab.gal_type['n_h'][i])
except AssertionError:
raise RuntimeError('There was an internal error in ' +
'TabCorr. If possible, please ' +
'report this bug in the TabCorr ' +
'GitHub repository.')
else:
if len(pos) == 0 and halotab.gal_type['n_h'][i] != 0:
raise RuntimeError(
'There was at least one bin without satellite ' +
'tracers. Increase sats_per_prim_haloprop.')
if len(pos) > 0:
if isinstance(downsample, float):
use = np.random.random(len(pos)) < downsample
else:
use = (np.random.random(len(pos)) < downsample(
halotab.gal_type['prim_haloprop'][i]))
# If the down-sampling reduced the number of tracers to at
# or below one, force at least 2 tracers to not bias the
# clustering estimates.
if np.sum(use) <= 1 and len(pos) > 1:
use = np.zeros(len(pos), dtype=bool)
use[np.random.choice(len(pos), size=2)] = True
pos = pos[use]
pos_bin.append(pos)
if mode == 'auto':
combinations = itertools.combinations_with_replacement(
range(len(halotab.gal_type)), 2)
else:
combinations = range(len(halotab.gal_type))
if xyz == 'xyz':
tpcf_matrix, tpcf_shape = compute_tpcf_matrix(
mode,
pos_bin,
tpcf,
period,
tpcf_args,
tpcf_kwargs,
combinations,
num_threads=num_threads,
verbose=verbose)
if not project_xyz or mode == 'cross':
break
elif xyz != 'xyz':
tpcf_matrix += compute_tpcf_matrix(mode,
pos_bin,
tpcf,
period,
tpcf_args,
tpcf_kwargs,
combinations,
num_threads=num_threads,
verbose=verbose)[0]
if project_xyz and mode == 'auto':
tpcf_matrix /= 3.0
if mode == 'auto':
tpcf_matrix_flat = []
for i in range(tpcf_matrix.shape[0]):
tpcf_matrix_flat.append(
symmetric_matrix_to_array(tpcf_matrix[i]))
tpcf_matrix = np.array(tpcf_matrix_flat)
# Remove entries that don't have any halos.
use = halotab.gal_type['n_h'] != 0
halotab.gal_type = halotab.gal_type[use]
if mode == 'auto':
use = symmetric_matrix_to_array(np.outer(use, use))
tpcf_matrix = tpcf_matrix[:, use]
halotab.gal_type['n_h'] /= np.prod(halocat.Lbox * lbox_stretch)
halotab.attrs = {}
halotab.attrs['tpcf'] = tpcf.__name__
halotab.attrs['mode'] = mode
halotab.attrs['simname'] = halocat.simname
halotab.attrs['redshift'] = halocat.redshift
halotab.attrs['Num_ptcl_requirement'] = Num_ptcl_requirement
halotab.attrs['prim_haloprop_key'] = prim_haloprop_key
halotab.attrs['sec_haloprop_key'] = sec_haloprop_key
halotab.tpcf_args = tpcf_args
halotab.tpcf_kwargs = tpcf_kwargs
halotab.tpcf_shape = tpcf_shape
halotab.tpcf_matrix = tpcf_matrix
halotab.init = True
return halotab
for ngal in xolmis.NGAL:
table = Table()
table.meta['ngal'] = ngal
ngal *= boxsize**3
mabs_cut = np.percentile(mock['M'], 100 * (ngal / len(mock)))
select = mock['M'] < mabs_cut
dd_all = np.zeros((len(s_bins) - 1) * (len(mu_bins) - 1))
for xyz in ['xyz', 'yzx', 'zxy']:
pos = return_xyz_formatted_array(
x=mock[xyz[0]], y=mock[xyz[1]], z=mock[xyz[2]],
velocity=mock['v'+xyz[2]], velocity_distortion_dimension='z',
period=boxsize, redshift=redshift, cosmology=cosmology)[select]
pos = pos.astype(float)
dd_all += DDsmu(1, n_threads, s_bins, 1, len(mu_bins) - 1, pos[:, 0],
pos[:, 1], pos[:, 2], periodic=True, boxsize=boxsize)[
'npairs'] / 3.0
xi = xi_from_dd(dd_all, len(pos), boxsize, s_bins, mu_bins)
n_jk = 10
for order in [0, 2, 4]:
table['xi{}'.format(order)] = tpcf_multipole(xi, mu_bins, order=order)
table['xi{}_jk'.format(order)] = np.zeros((len(table), n_jk**3))
for i_x, i_y, i_z in tqdm.tqdm(itertools.product(
range(n_jk), range(n_jk), range(n_jk)), total=n_jk**3):
select = ~((pos[:, 0] < boxsize / n_jk * i_x) |
(pos[:, 0] >= boxsize / n_jk * (i_x + 1)) |
