def result(self):
"""
The fitting result, either a LBFGSResult or EmceeResult
"""
try:
return self._result
except AttributeError:
# check if combined mcmc result is there
path = os.path.join(self.fitting_dir, 'info', 'combined_result.npz')
if os.path.isfile(path):
r = EmceeResults.from_npz(path)
else:
files = glob(os.path.join(self.fitting_dir, '*npz'))
if not len(files):
raise ValueError("no suitable results files found in directory '%s'" %d)
# grab the file modified last
times = [os.stat(f).st_mtime for f in files]
try:
r = LBFGSResults.from_npz(files[np.argmax(times)])
except:
raise ValueError("if directory is from mcmc fit, define the `info` directory")
self._result = r
return self._result
def load_results(filename):
"""
Load a result from file
"""
try:
result = EmceeResults.from_npz(filename)
except:
result = LBFGSResults.from_npz(filename)
return result
def load_fits():
"""
Load a set of fit results.
Returns a structued numpy array holding best-fit values for all free
parameters all mocks.
"""
# find matches
pattern = os.path.join(os.environ['RSDFIT_FITS'], 'cutsky',
'ChallengeMockN', 'fkp_1e4', 'box*')
pattern = os.path.join(pattern, 'poles',
'nlopt_gausscov_base_high_nbar_unscaled_kmax04')
matches = glob(pattern)
assert len(matches) > 0
driver = None
data = defaultdict(list)
for f in matches:
r = sorted(glob(os.path.join(f, '*.npz')),
key=os.path.getmtime,
reverse=True)
assert len(
r
) > 0, "no npz results found in directory '%s'" % os.path.normpath(f)
th = ParameterSet.from_file(os.path.join(f, 'params.dat'),
tags='theory')
r = LBFGSResults.from_npz(r[0])
for param in r.free_names:
data[param].append(r[param])
th[param].value = r[param]
if driver is None:
driver = FittingDriver.from_directory(f, init_model=False)
# add fsigma8
if 'f' in r.free_names and 'sigma8_z' in r.free_names:
data['fsigma8'].append(r['f'] * r['sigma8_z'])
# the prior to add back
lnprior = sum(par.lnprior for par in th.free)
# add the reduced chi2
red_chi2 = (2 * (r.min_chi2 + lnprior)) / driver.dof
data['red_chi2'].append(red_chi2)
params = list(data.keys())
dtype = list(zip(params, ['f8'] * len(params)))
out = numpy.empty(len(matches), dtype=dtype)
for param in out.dtype.names:
out[param] = numpy.array(data[param])
return out
def load_fits(sample, params):
"""
Load a set of ezmock fit results.
Returns a structued numpy array holding best-fit values for all free
parameters all mocks.
"""
# find matches
pattern = os.path.join(os.environ['EBOSS_FITS'], 'mocks', 'ezmock', 'v1.8e-fph', '0.0001-0.3', params)
assert os.path.isdir(pattern)
assert sample in 'NS'
pattern = os.path.join(pattern, '0.8-2.2', f'QSO-{sample}-*-P0+P2-mock-cov-*')
matches = glob(pattern)
assert len(matches) > 0
driver = None
data = defaultdict(list)
for f in matches:
r = sorted(glob(os.path.join(f, '*.npz')), key=os.path.getmtime, reverse=True)
assert len(r) > 0, "no npz results found in directory '%s'" %os.path.normpath(f)
th = ParameterSet.from_file(os.path.join(f, 'params.dat'), tags='theory')
r = LBFGSResults.from_npz(r[0])
for param in r.free_names:
data[param].append(r[param])
th[param].value = r[param]
if driver is None:
driver = FittingDriver.from_directory(f, init_model=False)
# add fsigma8
if 'f' in r.free_names and 'sigma8_z' in r.free_names:
data['fsigma8'].append(r['f'] * r['sigma8_z'])
# the prior to add back
lnprior = sum(par.lnprior for par in th.free)
# add the reduced chi2
red_chi2 = (2*(r.min_chi2 + lnprior)) / driver.dof
data['red_chi2'].append(red_chi2)
params = list(data.keys())
dtype = list(zip(params, ['f8']*len(params)))
out = numpy.empty(len(matches), dtype=dtype)
for param in out.dtype.names:
out[param] = numpy.array(data[param])
return out
def start_from(self, val):
if val is None:
self._start_from = val
return
if '$' in val:
from pyRSD.rsdfit.parameters.tools import replace_vars
val = replace_vars(val, {})
import os
if not os.path.exists(val):
raise RuntimeError("cannot set `start_from` to `%s`: no such file" %val)
if os.path.isdir(val):
from glob import glob
from pyRSD.rsdfit.results import EmceeResults, LBFGSResults
import operator
pattern = os.path.join(val, "*.npz")
result_files = glob(pattern)
if not len(result_files):
raise RuntimeError("did not find any chain (`.npz`) files matching pattern `%s`" %pattern)
# find the chain file which has the maximum log prob in it and use that
max_lnprobs = []
for f in result_files:
try:
r = EmceeResults.from_npz(f)
max_lnprobs.append(r.max_lnprob)
except:
r = LBFGSResults.from_npz(f)
max_lnprobs.append(-r.min_chi2)
index, value = max(enumerate(max_lnprobs), key=operator.itemgetter(1))
self._start_from = result_files[index]
else:
self._start_from = val
def find_init_result(val):
"""
Return the name of the file holding the maximum probability
from a directory
"""
import os
if not os.path.exists(val):
raise RuntimeError("cannot set `start_from` to `%s`: no such file" %
val)
if os.path.isdir(val):
from glob import glob
from pyRSD.rsdfit.results import EmceeResults, LBFGSResults
import operator
pattern = os.path.join(val, "*.npz")
result_files = glob(pattern)
if not len(result_files):
raise RuntimeError(
"did not find any chain (`.npz`) files matching pattern `%s`" %
pattern)
# find the chain file which has the maximum log prob in it and use that
max_lnprobs = []
for f in result_files:
try:
r = EmceeResults.from_npz(f)
max_lnprobs.append(r.max_lnprob)
except:
r = LBFGSResults.from_npz(f)
max_lnprobs.append(-r.min_chi2)
index, value = max(enumerate(max_lnprobs), key=operator.itemgetter(1))
return result_files[index]
else:
return val
def load_ezmock_results(version, sample, krange, params, z_weighted, p=None):
"""
Load a set of ezmock fit results.
Returns a structued numpy array holding best-fit values for all free
parameters all mocks.
"""
from pyRSD.rsdfit.results import LBFGSResults
from pyRSD.rsdfit import FittingDriver
from pyRSD.rsdfit.parameters import ParameterSet
from collections import defaultdict
assert sample in ['N', 'S']
assert version in ['v1.8e-no', 'v1.8e-fph', 'v1.8e-reg']
d = os.path.join(os.environ['EBOSS_DIR'], 'fits', 'results', 'mocks',
'ezmock', version)
d = os.path.join(d, krange, params, '0.8-2.2')
assert os.path.isdir(d), "'%s' directory not found" % d
if p is None or p == 1.6:
p = [None, 1.6]
else:
p = [p]
matches = glob(os.path.join(d, f'QSO-{sample}-0001-*'))
match = None
for f in matches:
hashkeys = get_hashkeys(f, None)
if hashkeys['p'] in p and hashkeys['z-weighted'] == z_weighted:
match = f
if match is None:
raise ValueError((
f"no matches found: version={version}, sample={sample}, "
f"krange={krange}, params={params}, z_weighted={z_weighted}, p={p}"
))
# load the driver
driver = FittingDriver.from_directory(match)
dirname, basename = os.path.split(match)
pattern = os.path.join(dirname, basename.replace('0001', '*'))
data = defaultdict(list)
matches = glob(pattern)
for f in matches:
r = sorted(glob(os.path.join(f, '*.npz')),
key=os.path.getmtime,
reverse=True)
if len(r) == 0:
raise ValueError(
"warning: no npz results found in directory '%s'" %
os.path.normpath(f))
th = ParameterSet.from_file(os.path.join(f, 'params.dat'),
tags='theory')
r = LBFGSResults.from_npz(r[0])
for param in r.free_names:
data[param].append(r[param])
th[param].value = r[param]
# add fsigma8
if 'f' in r.free_names and 'sigma8_z' in r.free_names:
data['fsigma8'].append(r['f'] * r['sigma8_z'])
# the prior to add back
lnprior = sum(par.lnprior for par in th.free)
# add the reduced chi2
red_chi2 = (2 * (r.min_chi2 + lnprior)) / driver.dof
data['red_chi2'].append(red_chi2)
params = list(data.keys())
dtype = list(zip(params, ['f8'] * len(params)))
out = numpy.empty(len(matches), dtype=dtype)
for param in out.dtype.names:
out[param] = numpy.array(data[param])
return out
