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 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 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 wp_measurement_iterator(table, *masks, **kwargs):
"""
"""
pi_max = kwargs.get('pi_max', 20)
rp_bins = kwargs.get('rp_bins', np.logspace(-1, 1.5, 25))
period = kwargs.get('period', np.inf)
for sample1 in clustering_sample_iterator(table, *masks, **kwargs):
yield rp_bins, wp(sample1, rp_bins, pi_max, period=period)
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 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 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)
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 model(theta, Mstar, prior_range = None):
'''
Given theta (HOD parameters) and stellar mass threshold Mstar,
compute wp
not sure prior_range is necessary here
'''
model = PrebuiltHodModelFactory('hearin15', threshold = Mstar,
redshift = 0.0 ,
central_assembias_strength = 0.,
satellite_assembias_strength = 0.)
model.param_dict['alphasat'] = theta[0]#1.0
model.param_dict['bcut'] = theta[1]#1.47,
model.param_dict['betacut'] = theta[2]#0.13
model.param_dict['betasat'] = theta[3]#0.859
model.param_dict['bsat'] = theta[4]#0.62
model.param_dict['mean_occupation_centrals_assembias_param1'] = theta[5] # 0
model.param_dict['mean_occupation_satellites_assembias_param1'] = theta[6] #.75
model.param_dict['scatter_model_param1'] = theta[7]#0.2
model.param_dict['smhm_beta_0'] = theta[8]# 0.43
model.param_dict['smhm_beta_a'] = theta[9]#0.18
model.param_dict['smhm_delta_0'] = theta[10]#0.56
model.param_dict['smhm_delta_a'] = theta[11]#0.18,
model.param_dict['smhm_gamma_0']= theta[12]#1.54
model.param_dict['smhm_gamma_a'] = theta[13]#2.52,
model.param_dict['smhm_m0_0'] = theta[14]# 10.72,
model.param_dict['smhm_m0_a'] = theta[15]# 0.59
model.param_dict['smhm_m1_0'] = theta[16]# 12.35,
model.param_dict['smhm_m1_a'] = theta[17]#0.3
model.populate_mock(simname = 'bolshoi', redshift = 0, halo_finder = 'rockstar')
#x = model.mock.galaxy_table['x']
#y = model.mock.galaxy_table['y']
#z = model.mock.galaxy_table['z']
#all_positions = return_xyz_formatted_array(x, y, z)
all_positions = three_dim_pos_bundle(model.mock.galaxy_table, 'x', 'y', 'z')
wp_all = wp(all_positions, rp_bins, pi_bins,
period=model.mock.Lbox, estimator = 'Landy-Szalay', num_threads = 1)
#wp = proj_clustering(pos , rbins , pbins , cellsize = [rmax, rmax, rmax])
print 1
return rp_bin_centers, wp_all
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
min_ptcl * cat.pmass] #mass cut
galaxy_catalog = halo_catalog[halo_catalog[mag_key] < mag_cut] # mag cut
if shuffle_type:
sham_pos = np.c_[galaxy_catalog['halo_%s_x'%shuffle_type],\
galaxy_catalog['halo_%s_y'%shuffle_type],\
galaxy_catalog['halo_%s_z'%shuffle_type]]
else:
sham_pos = np.c_[galaxy_catalog['halo_x'],\
galaxy_catalog['halo_y'],\
galaxy_catalog['halo_z']]
y = np.log10(
wp(sham_pos * cat.h,
rp_bins,
40.0 * cat.h,
period=cat.Lbox * cat.h,
num_threads=1))
obs_nd = len(galaxy_catalog) * 1.0 / ((cat.Lbox * cat.h)**3)
wp_vals = []
nds = []
for i in xrange(50):
cat.populate(em_params)
wp_vals.append(cat.calc_wp(rp_bins, 40))
nds.append(cat.calc_number_density())
#y = np.mean(np.log10(np.array(wp_vals)),axis = 0 )
# TODO need a way to get a measurement cov for the shams
cov = np.cov(np.log10(np.array(wp_vals).T)) #/np.sqrt(50)
#obs_nd = np.mean(np.array(nds))
def proj_clustering(pos , rbins, pbins , cellsize):
return wp(sample1 = pos, rp_bins = rbins,
pi_bins = pbins, sample2 = None,
period = np.array([250,250,250]), approx_cell1_size = cellsize)
