def run_sampler(self):
import pypolychord
from pypolychord.settings import PolyChordSettings
if self.kwargs['use_polychord_defaults']:
settings = PolyChordSettings(nDims=self.ndim,
nDerived=self.ndim,
base_dir=self._sample_file_directory,
file_root=self.label)
else:
self._setup_dynamic_defaults()
pc_kwargs = self.kwargs.copy()
pc_kwargs['base_dir'] = self._sample_file_directory
pc_kwargs['file_root'] = self.label
pc_kwargs.pop('use_polychord_defaults')
settings = PolyChordSettings(nDims=self.ndim,
nDerived=self.ndim,
**pc_kwargs)
self._verify_kwargs_against_default_kwargs()
out = pypolychord.run_polychord(loglikelihood=self.log_likelihood,
nDims=self.ndim,
nDerived=self.ndim,
settings=settings,
prior=self.prior_transform)
self.result.log_evidence = out.logZ
self.result.log_evidence_err = out.logZerr
log_likelihoods, physical_parameters = self._read_sample_file()
self.result.log_likelihood_evaluations = log_likelihoods
self.result.samples = physical_parameters
self.calc_likelihood_count()
return self.result
def run_sampler(self):
import pypolychord
from pypolychord.settings import PolyChordSettings
if self.kwargs['use_polychord_defaults']:
settings = PolyChordSettings(nDims=self.ndim,
nDerived=self.ndim,
base_dir=self.outdir,
file_root=self.label)
else:
self._setup_dynamic_defaults()
pc_kwargs = self.kwargs.copy()
pc_kwargs['base_dir'] = self.outdir
pc_kwargs['file_root'] = self.label
pc_kwargs.pop('use_polychord_defaults')
settings = PolyChordSettings(nDims=self.ndim,
nDerived=self.ndim,
**pc_kwargs)
self._verify_kwargs_against_default_kwargs()
pypolychord.run_polychord(loglikelihood=self.log_likelihood,
nDims=self.ndim,
nDerived=self.ndim,
settings=settings,
prior=self.prior_transform)
self.result.log_evidence, self.result.log_evidence_err = self._read_out_stats_file(
)
self.result.samples = self._read_sample_file()
return self.result
def __init__(self, mu, cov, file_root='untitled'):
self.mu = mu if isinstance(mu, numpy.ndarray) else numpy.array(mu)
self.cov = cov if isinstance(cov, numpy.ndarray) else numpy.array(cov)
self.isDiagonal = False
self.nDims = self.mu.size
shape = self.cov.shape
if (len(shape) > 2):
raise ValueError(
"Covariance matrix has higher rank than a 2-tensor. {}".format(
shape))
if len(shape) == 2:
a, b = shape
if a != b:
raise ValueError(
"Covariance matrix not square. It has shape {}x{}".format(
a, b))
if a != self.mu.size:
raise ValueError(
"Covariance matrix has different dimesnions to mean vector. {}x{} vs {}"
.format(a, b, self.mu.size))
else:
if self.cov.size != self.mu.size:
raise ValueError(
"Incompatible standard deviation vector. [sigma]={}, [mu]={}"
.format(self.cov.size, self.mu.size))
else:
self.isDiagonal = True
self.__invCov = numpy.linalg.inv(
self.cov) if not self.isDiagonal else numpy.linalg.inv(
numpy.diag(self.cov))
self.settings = PolyChordSettings(self.nDims, 0)
self.settings.file_root = file_root
self.settings.read_resume = False
self.settings.do_clustering = True
self.settings.nlive = 20
def __init__(self, sampled_parameters, loglikelihood, population_size):
"""Initialize the PolyChord Nested Sampler."""
self.sampled_parameters = sampled_parameters
self.loglikelihood = loglikelihood
self.population_size = population_size
self._nDims = len(sampled_parameters)
self._nDerived = 0
self._post_eval = False
self._posteriors = None
#if self.population_size is None:
# self.population_size = 25*self._nDims
# make the likelihood function for polychord
def likelihood(theta):
r2 = 0
return loglikelihood(theta), [r2]
self._likelihood = likelihood
# make the prior for polychord
def prior(hypercube):
return np.array([self.sampled_parameters[i].invcdf(value) for i,value in enumerate(hypercube)])
self._prior = prior
# PolyChord settings object
self._settings = PolyChordSettings(self._nDims, self._nDerived,
nlive=self.population_size)
self._settings.file_root = 'polychord_run' #string
self._settings.do_clustering = True
self._settings.read_resume = False
# Make the polychord dumper function
# param : array, array, array, float, float
def dumper(live, dead, logweights, logZ, logZerr):
print("Last dead point:", dead[-1]) # prints last element of dead (wich is an array)
self._dumper = dumper
return
def __init__(self, mu, sigma, b, a, file_root=''):
# super(RepartitionedGaussianModel, self).__init__(self, mu, cov)
self.mu = mu
if not isinstance(self.mu, numpy.ndarray):
self.mu = numpy.array(self.mu)
self.sigma = sigma
if not isinstance(self.sigma, numpy.ndarray):
self.sigma = numpy.array(self.sigma)
if len(self.sigma.shape) != 1:
raise ValueError(
"Standard deviations not provided as a vector, maybe you meant to use CorrelatedGaussianModel? {}"
.format(sigma))
else:
if self.mu.size != self.sigma.size:
raise ValueError(
"Incompatible sizes of standard deviation and mean vectors. [mu]={} vs [sigma]={}"
.format(self.mu.size, self.sigma.size))
self.nDims = self.mu.size
self.settings = PolyChordSettings(self.nDims, 0)
self.settings.file_root = file_root
self.settings.read_resume = False
self.settings.do_clustering = True
self.settings.nlive = 20
self.upper_bounds = b
self.lower_bounds = a
def _get_sampler(self, **kwargs):
if "file_root" in kwargs:
warnings.warn("file_root was defined in sampler_kwargs, "
"but is replaced by output_prefix")
del kwargs["file_root"]
if "base_dir" in kwargs:
warnings.warn("base_dir was defined in sampler_kwargs, "
"but is replaced by output_prefix")
del kwargs["base_dir"]
return PolyChordSettings(
self.nparams,
self.nderived,
base_dir=str(self.output_dir),
file_root=str(self.output_file_prefix),
nlive=kwargs.pop("nlive", 100 * self.nparams),
**kwargs,
)
def __init__(self, mu, cov, a, b, **kwargs):
self.mu = numpy.array(mu)
self.cov = numpy.array(cov)
self.invCov = numpy.linalg.inv(cov)
self.sigma = numpy.diag(self.cov)
self.gaussian_norm = numpy.linalg.slogdet(
2 * numpy.pi * self.cov)[1] / 2
self.nDims = self.mu.size
def unkwarg(arg, default):
return default if arg not in kwargs else kwargs[arg]
self.settings = PolyChordSettings(self.nDims, 0)
self.settings.file_root = unkwarg('file_root', 'test')
self.settings.nlive = unkwarg('live_points', 10**3)
self.settings.read_resume = unkwarg('read_resume', False)
self.settings.do_clustering = unkwarg('do_clustering', True)
self.settings.feedback = unkwarg('feedback', 0)
self.a = a
self.b = b
def run_polychord(num_live_points):
try:
import pypolychord
from pypolychord.settings import PolyChordSettings
from pypolychord.priors import UniformPrior
except:
raise ImportError("Polychord not installed.\nRun `git clone https://github.com/PolyChord/PolyChordLite.git \ncd PolyChordLite\npython setup.py install`.")
def likelihood(theta):
""" Simple Gaussian Likelihood"""
nDims = len(theta)
r2 = sum(theta**2)
logL = -log(2*pi*sigma*sigma)*nDims/2.0
logL += -r2/2/sigma/sigma
return logL, [r2]
def prior(hypercube):
""" Uniform prior from [-1,1]^D. """
return UniformPrior(-1, 1)(hypercube)
def dumper(live, dead, logweights, logZ, logZerr):
return
# print("Last dead point:", dead[-1])
settings = PolyChordSettings(ndims, 1)
settings.file_root = 'gaussian'
settings.nlive = num_live_points
settings.do_clustering = True
settings.read_resume = False
t0 = default_timer()
output = pypolychord.run_polychord(likelihood, ndims, 1, settings, prior, dumper)
run_time = default_timer() - t0
print("polychord log(Z):", output.logZ)
return run_time
def initialize(self):
"""Imports the PolyChord sampler and prepares its arguments."""
if am_single_or_primary_process(
): # rank = 0 (MPI master) or None (no MPI)
self.log.info("Initializing")
# If path not given, try using general path to modules
if not self.path and self.path_install:
self.path = get_path(self.path_install)
if self.path:
if am_single_or_primary_process():
self.log.info("Importing *local* PolyChord from " + self.path)
if not os.path.exists(os.path.realpath(self.path)):
raise LoggedError(
self.log, "The given path does not exist. "
"Try installing PolyChord with "
"'cobaya-install polychord -m [modules_path]")
pc_build_path = get_build_path(self.path)
if not pc_build_path:
raise LoggedError(
self.log, "Either PolyChord is not in the given folder, "
"'%s', or you have not compiled it.", self.path)
# Inserting the previously found path into the list of import folders
sys.path.insert(0, pc_build_path)
else:
self.log.info("Importing *global* PolyChord.")
try:
import pypolychord
from pypolychord.settings import PolyChordSettings
self.pc = pypolychord
except ImportError:
raise LoggedError(
self.log, "Couldn't find the PolyChord python interface. "
"Make sure that you have compiled it, and that you either\n"
" (a) specify a path (you didn't) or\n"
" (b) install the Python interface globally with\n"
" '/path/to/PolyChord/python setup.py install --user'")
# Prepare arguments and settings
self.nDims = self.model.prior.d()
self.nDerived = (len(self.model.parameterization.derived_params()) +
len(self.model.prior) +
len(self.model.likelihood._likelihoods))
if self.logzero is None:
self.logzero = np.nan_to_num(-np.inf)
if self.max_ndead == np.inf:
self.max_ndead = -1
for p in ["nlive", "nprior", "max_ndead"]:
setattr(self, p,
read_dnumber(getattr(self, p), self.nDims, dtype=int))
# Fill the automatic ones
if getattr(self, "feedback", None) is None:
values = {
logging.CRITICAL: 0,
logging.ERROR: 0,
logging.WARNING: 0,
logging.INFO: 1,
logging.DEBUG: 2
}
self.feedback = values[self.log.getEffectiveLevel()]
try:
output_folder = getattr(self.output, "folder")
output_prefix = getattr(self.output, "prefix") or ""
self.read_resume = self.resuming
except AttributeError:
# dummy output -- no resume!
self.read_resume = False
from tempfile import gettempdir
output_folder = gettempdir()
if am_single_or_primary_process():
from random import random
output_prefix = hex(int(random() * 16**6))[2:]
else:
output_prefix = None
if more_than_one_process():
output_prefix = get_mpi_comm().bcast(output_prefix, root=0)
self.base_dir = os.path.join(output_folder, self.base_dir)
self.file_root = output_prefix
if am_single_or_primary_process():
# Creating output folder, if it does not exist (just one process)
if not os.path.exists(self.base_dir):
os.makedirs(self.base_dir)
# Idem, a clusters folder if needed -- notice that PolyChord's default
# is "True", here "None", hence the funny condition below
if self.do_clustering is not False: # None here means "default"
try:
os.makedirs(os.path.join(self.base_dir, clusters))
except OSError: # exists!
pass
self.log.info("Storing raw PolyChord output in '%s'.",
self.base_dir)
# Exploiting the speed hierarchy
if self.blocking:
speeds, blocks = self.model.likelihood._check_speeds_of_params(
self.blocking)
else:
speeds, blocks = self.model.likelihood._speeds_of_params(
int_speeds=True)
blocks_flat = list(chain(*blocks))
self.ordering = [
blocks_flat.index(p)
for p in self.model.parameterization.sampled_params()
]
self.grade_dims = np.array([len(block) for block in blocks])
# bugfix: pypolychord's C interface for Fortran does not like int numpy types
self.grade_dims = [int(x) for x in self.grade_dims]
# Steps per block
# NB: num_repeats is ignored by PolyChord when int "grade_frac" given,
# so needs to be applied by hand.
# Make sure that speeds are integer, and that the slowest is 1,
# for a straightforward application of num_repeats
speeds = relative_to_int(speeds, 1)
# In num_repeats, `d` is interpreted as dimension of each block
self.grade_frac = [
int(speed * read_dnumber(self.num_repeats, dim_block))
for speed, dim_block in zip(speeds, self.grade_dims)
]
# Assign settings
pc_args = [
"nlive", "num_repeats", "nprior", "do_clustering",
"precision_criterion", "max_ndead", "boost_posterior", "feedback",
"logzero", "posteriors", "equals", "compression_factor",
"cluster_posteriors", "write_resume", "read_resume", "write_stats",
"write_live", "write_dead", "base_dir", "grade_frac", "grade_dims",
"feedback", "read_resume", "base_dir", "file_root", "grade_frac",
"grade_dims"
]
# As stated above, num_repeats is ignored, so let's not pass it
pc_args.pop(pc_args.index("num_repeats"))
self.pc_settings = PolyChordSettings(
self.nDims,
self.nDerived,
seed=(self.seed if self.seed is not None else -1),
**{
p: getattr(self, p)
for p in pc_args if getattr(self, p) is not None
})
# prior conversion from the hypercube
bounds = self.model.prior.bounds(
confidence_for_unbounded=self.confidence_for_unbounded)
# Check if priors are bounded (nan's to inf)
inf = np.where(np.isinf(bounds))
if len(inf[0]):
params_names = self.model.parameterization.sampled_params()
params = [params_names[i] for i in sorted(list(set(inf[0])))]
raise LoggedError(
self.log,
"PolyChord needs bounded priors, but the parameter(s) '"
"', '".join(params) + "' is(are) unbounded.")
locs = bounds[:, 0]
scales = bounds[:, 1] - bounds[:, 0]
# This function re-scales the parameters AND puts them in the right order
self.pc_prior = lambda x: (locs + np.array(x)[self.ordering] * scales
).tolist()
# We will need the volume of the prior domain, since PolyChord divides by it
self.logvolume = np.log(np.prod(scales))
# Prepare callback function
if self.callback_function is not None:
self.callback_function_callable = (get_external_function(
self.callback_function))
self.last_point_callback = 0
# Prepare runtime live and dead points collections
self.live = Collection(self.model,
None,
name="live",
initial_size=self.pc_settings.nlive)
self.dead = Collection(self.model, self.output, name="dead")
self.n_sampled = len(self.model.parameterization.sampled_params())
self.n_derived = len(self.model.parameterization.derived_params())
self.n_priors = len(self.model.prior)
self.n_likes = len(self.model.likelihood._likelihoods)
# Done!
if am_single_or_primary_process():
self.log.info("Calling PolyChord with arguments:")
for p, v in inspect.getmembers(self.pc_settings,
lambda a: not (callable(a))):
if not p.startswith("_"):
self.log.info(" %s: %s", p, v)
return logL, [r2] # float, array-like
# param : array
def prior(hypercube):
""" Uniform prior from [-1,1]^D. """
return UniformPrior(-1, 1)(hypercube) # array
# param : array, array, array, float, float
def dumper(live, dead, logweights, logZ, logZerr):
print("Last dead point:",
dead[-1]) # prints last element of dead (wich is an array)
settings = PolyChordSettings(nDims, nDerived) #settings is an object
settings.file_root = functionName #string
settings.do_clustering = True
settings.read_resume = False
output = pypolychord.run_polychord(likelihood, nDims, nDerived, settings,
prior, dumper)
paramnames = [('p%i' % i, r'\theta_%i' % i) for i in range(nDims)]
paramnames += [('r*', 'r')]
output.make_paramnames_files(paramnames)
try:
import getdist.plots
import matplotlib.pyplot as plt
posterior = output.posterior
g = getdist.plots.getSubplotPlotter()
return logL, [r2] # float, array-like
# param : array
def prior(hypercube):
""" Uniform prior from [-1,1]^D. """
return UniformPrior(-1, 1)(hypercube) # array
# param : array, array, array, float, float
def dumper(live, dead, logweights, logZ, logZerr):
print("Last dead point:",
dead[-1]) # prints last element of dead (wich is an array)
settings = PolyChordSettings(nDims, nDerived)
settings.file_root = functionName
settings.do_clustering = True
settings.read_resume = False
output = pypolychord.run_polychord(likelihood, nDims, nDerived, settings,
prior, dumper)
paramnames = [('p%i' % i, r'\theta_%i' % i) for i in range(nDims)]
paramnames += [('r*', 'r')]
output.make_paramnames_files(paramnames)
try:
import getdist.plots
import matplotlib.pyplot as plt
posterior = output.posterior
g = getdist.plots.getSubplotPlotter()
def pc(test_statistic,
transform,
n_dim,
observed,
n_live=100,
base_dir="chains/",
file_root="pc_",
do_clustering=False,
resume=False,
ev_data=False,
feedback=0,
**kwargs):
"""
Nested sampling with PC
"""
# copy key word arguments to settings object
settings = PolyChordSettings(n_dim, 0, **kwargs)
settings.nfail = n_live
settings.precision_criterion = 0.
settings.read_resume = resume
settings.base_dir = base_dir
settings.file_root = file_root
settings.nlive = n_live
settings.logLstop = observed
settings.do_clustering = do_clustering
settings.feedback = feedback
loglike = pc_wrap(test_statistic)
output = pypolychord.run_polychord(loglike, n_dim, 0, settings, transform,
dumper(0, observed))
# get number of calls directly
calls = output.nlike
# get log X from resume file
label = "=== local volume -- log(<X_p>) ==="
log_xp = None
res_name = "{}/{}.resume".format(base_dir, file_root)
with open(res_name) as res_file:
for line in res_file:
if line.strip() == label:
next_line = res_file.readline()
log_xp = np.array([float(e) for e in next_line.split()])
break
else:
raise RuntimeError("didn't find {}".format(label))
log_x = logsumexp(log_xp)
n_iter = -log_x * n_live
if not ev_data:
return Result.from_ns(n_iter, n_live, calls)
# get ev data
ev_name = "{}/{}_dead.txt".format(base_dir, file_root)
ev_data = np.genfromtxt(ev_name)
test_statistic = ev_data[:, 0]
log_x = -np.arange(0, len(test_statistic), 1.) / n_live
log_x_delta = np.sqrt(-log_x / n_live)
return Result.from_ns(n_iter, n_live,
calls), [test_statistic, log_x, log_x_delta]
from pypolychord.settings import PolyChordSettings
import anesthetic
from scipy.special import erfinv
import time
# In this module I'm going to investigate the effect of the so-called
# Lasenby parameter as well as the effects of proper prior
# repartitioning, and benchmark to see a speedup.
# Vanilla
mu = numpy.array([1.0, 2.5])
cov = numpy.array([[1.0, 0.6], [0.6, 1.0]])
nDims = mu.size
settings = PolyChordSettings(nDims, 0)
settings.file_root = 'vanilla'
settings.nlive = 10**3
settings.read_resume = False
settings.do_clustering = True
settings.feedback = 0
def gaussian_likelihood(theta):
invSig = numpy.linalg.inv(cov)
norm = numpy.linalg.slogdet(2 * numpy.pi * cov)[1] / 2
logL = -norm - (theta - mu) @ invSig @ (theta - mu) / 2
return logL, []
def uniform_prior(point_in_hypercube):
def PC_fit(self,nlive_const='auto', dynamic=True,dynamic_goal=1.0, ninit=100,
basename='dypc_chains', verbose=True, plot=False):
'''
Parameters
----------
dynamic_goal : float, opt
Parameter in [0,1] determining whether algorithm prioritizes accuracy in
evidence accuracy (goal near 0) or parameter estimation (goal near 1).
ninit : int, opt
Number of live points to use in initial exploratory run.
nlive_const : int, opt
Total computational budget, equivalent to non-dynamic nested sampling with nlive_const live points.
dynamic : bool, opt
If True, use dynamic nested sampling via dyPolyChord. Otherwise, use the
standard PolyChord.
basename : str, opt
Location in which chains will be stored.
verbose : bool, opt
If True, text will be output on the terminal to check how run is proceeding.
plot : bool, opt
Display some sample plots to check result of dynamic slice nested sampling.
'''
if dynamic:
print('Dynamic slice nested sampling')
else:
print('Slice nested sampling')
# obtain maximum likelihood fits
theta0 = self.lineModel.guessFit()
self.result_ml = self.optimizeFit(theta0)
self.theta_ml = self.result_ml['x']
# save theta_ml also in the lineModel object,
# so that constraints may be set based on ML result
self.lineModel.theta_ml = self.theta_ml
# save moments obtained from maximum likelihood optimization
self.m_ml = self.lineModel.modelMoments(self.theta_ml)
# dimensionality of the problem
self.ndim = int(self.lineModel.thetaLength())
if dynamic:
# dyPolyChord (dynamic slice nested sampling)
# ------------------------------
try:
import dyPolyChord.pypolychord_utils
import dyPolyChord
except:
print("********************")
print("Could not import dyPolyChord! Make sure that this is in your PYTHONPATH.")
print("PolyChord must also be on your LD_LIBRARY_PATH")
raise ValueError("Abort BSFC fit")
#Make a callable for running dyPolyChord
my_callable = dyPolyChord.pypolychord_utils.RunPyPolyChord(
self.PC_loglike,
self.lineModel.hypercube_lnprior_generalized_simplex,
self.ndim
)
# Specify sampler settings (see run_dynamic_ns.py documentation for more details)
settings_dict = {'file_root': 'bsfc',
'base_dir': basename,
'seed': 1}
# Run dyPolyChord
MPI_parallel=True
if MPI_parallel:
from mpi4py import MPI
comm = MPI.COMM_WORLD
dyPolyChord.run_dypolychord(my_callable, dynamic_goal, settings_dict,
ninit=ninit,
nlive_const=int(25*self.ndim) if nlive_const=='auto' else nlive_const,
comm=comm)
else:
dyPolyChord.run_dypolychord(my_callable, dynamic_goal, settings_dict,
ninit=ninit,
nlive_const=int(25*self.ndim) if nlive_const=='auto' else nlive_const)
else:
# PolyChord (slice nested sampling)
# ------------------------------
try:
import pypolychord
from pypolychord.settings import PolyChordSettings
except:
print("********************")
print("Could not import pypolychord! Make sure that this is in your PYTHONPATH.")
raise ValueError("Abort BSFC fit")
nDerived=0
settings = PolyChordSettings(self.ndim, nDerived)
settings.file_root = 'bsfc'
settings.base_dir = basename
settings.nlive = int(25*self.ndim) if nlive_const=='auto' else int(nlive_const)
#settings.do_clustering = True
#settings.read_resume = False
settings.feedback = 3
def dumper(live, dead, logweights, logZ, logZerr):
#print("Last dead point:", dead[-1])
print("logZ = "+str(logZ)+"+/-"+str(logZerr))
self.polychord_output = pypolychord.run_polychord(self.PC_loglike,
self.ndim,
nDerived,
settings,
self.lineModel.hypercube_lnprior_generalized_simplex,
dumper)
self.good=True
def get_polychord_settings(polychord_setup, num_params, num_derived):
"""Extract polychord settings and create the settings object.
Parameters
----------
polychord_setup : ConfigParser
Polychord section from the main config
num_params : int
Number of sampled parameters
num_derived : int
Number of derived parameters
Returns
-------
PolyChordSettings
Settings object for running Polychord
"""
# Seed and path/name
seed = polychord_setup.getint('seed', int(0))
path = os.path.expandvars(polychord_setup.get('path'))
name = polychord_setup.get('name')
# The key config parameters
num_live = polychord_setup.getint('num_live', int(25 * num_params))
num_repeats = polychord_setup.getint('num_repeats',
int(5 * num_params))
precision = polychord_setup.getfloat('precision', float(0.001))
# Resume should almost always be true
resume = polychord_setup.getboolean('resume', True)
write_dead = polychord_setup.getboolean('write_dead', True)
# Useful for plotting as it gives you more posterior samples
boost_posterior = polychord_setup.getfloat('boost_posterior',
float(0.0))
# Do we do clustering, useful for multimodal distributions
do_clustering = polychord_setup.getboolean('do_clustering', False)
cluster_posteriors = polychord_setup.getboolean(
'cluster_posteriors', False)
# Perform maximisation at the end of the chain
maximise = polychord_setup.getboolean('maximise', False)
# These control different sampling speeds
# grade_frac : List[float]
# (Default: [1])
# The amount of time to spend in each speed.
# If any of grade_frac are <= 1, then polychord will time each
# sub-speed, and then choose num_repeats for the number of slowest
# repeats, and spend the proportion of time indicated by grade_frac.
# Otherwise this indicates the number of repeats to spend in
# each speed.
# grade_dims : List[int]
# (Default: nDims)
# The number of parameters within each speed.
# Initialize the settings
settings = PolyChordSettings(num_params,
num_derived,
base_dir=path,
file_root=name,
seed=seed,
nlive=num_live,
num_repeats=num_repeats,
precision_criterion=precision,
write_resume=resume,
read_resume=resume,
boost_posterior=boost_posterior,
do_clustering=do_clustering,
cluster_posteriors=cluster_posteriors,
equals=False,
write_dead=write_dead,
maximise=maximise,
write_live=False,
write_prior=False)
# Check the path and get the paramnames path
output_path = Path(path)
err_msg = ("The PolyChord 'path' does not correspond to an existing"
" folder. Create the output folder before running.")
assert output_path.exists(), err_msg
parnames_path = output_path / (name + '.paramnames')
return settings, parnames_path
# return UniformPrior(-5, 5)(cube)
def log_likelihood(theta):
x = theta[:-1]
beta = theta[-1:].item()
# norm =
norm = numpy.log(numpy.product(numpy.diagonal(numpy.pi * 2 * cov))) / 2
gaussian = -norm - numpy.sum(((x - mu_pi) / sig_prior)**2) / 2
# return (2-beta)*(gaussian) + numpy.log(zed(beta)), []
# print(gaussian, log_zed(beta), beta)
return (2 - beta) * gaussian + log_zed(beta), []
# return gaussian, []
# return -numpy.linalg.slogdet(cov)[1]/2 - (x - mu_pi)@ numpy.linalg.inv(cov)@(x - mu_pi)/2, []
settings = PolyChordSettings(nDims + 1, 0)
settings.file_root = 'ppr'
settings.nlive = 200
settings.do_clustering = True
settings.read_resume = False
def exe():
run_polychord(log_likelihood, nDims + 1, 0, settings, prior)
samples = anesthetic.NestedSamples(root='./chains/ppr')
# floating point overflow:
# zed(0.5) = -inf
def run_polychord(loglikelihood, prior, dumper, nDims, nlive, root, ndump,
num_repeats):
"""Run PolyChord.
See https://arxiv.org/abs/1506.00171 for more detail
Parameters
----------
loglikelihood: :obj:`callable`
probability function taking a single parameter:
- theta: numpy.array
physical parameters, `shape=(nDims,)`
returning a log-likelihood (float)
prior: :obj:`callable`
tranformation function taking a single parameter
- cube: numpy.array
hypercube parameters, `shape=(nDims,)`
returning physical parameters (`numpy.array`)
dumper: :obj:`callable`
access function called every nlive iterations giving a window onto
current live points. Single parameter, no return:
- live:
`numpy.array of` live parameters and loglikelihoods,
`shape=(nlive,nDims+1)`
nDims: int
Dimensionality of sampling space
nlive: int
Number of live points
root: str
base name for output files
ndump: int
How many iterations between dumper function calls
num_repeats: int
Length of chain to generate new live points
"""
import pypolychord
from pypolychord.settings import PolyChordSettings
nDerived = 0
settings = PolyChordSettings(nDims, nDerived)
settings.base_dir = os.path.dirname(root)
settings.file_root = os.path.basename(root)
settings.nlive = nlive
settings.num_repeats = num_repeats
settings.do_clustering = True
settings.read_resume = False
settings.compression_factor = numpy.exp(-float(ndump)/nlive)
settings.precision_criterion = 0.01
def polychord_loglikelihood(theta):
return loglikelihood(theta), []
def polychord_dumper(live, dead, logweights, logZ, logZerr):
dumper(live[:, :-2], live[:, -1], dead[:, :-2], dead[:, -1])
pypolychord.run_polychord(polychord_loglikelihood, nDims, nDerived,
settings, prior, polychord_dumper)
def __init__(self, dimensionality, number_derived, file_root='', **kwargs):
self.settings = PolyChordSettings(dimensionality, number_derived)
self.settings.file_root = file_root
def polychord_sampler(self):
import pypolychord
from pypolychord.settings import PolyChordSettings
from pypolychord.priors import UniformPrior, GaussianPrior
ndim = len(self.params.p0)
nder = 0
# Log-likelihood compliant with PolyChord's input
def likelihood(theta):
return self.lnlike(theta), [0]
def prior(hypercube):
prior = []
for h, pr in zip(hypercube, self.params.p_free_priors):
if pr[1] == 'Gaussian':
prior.append(
GaussianPrior(float(pr[2][0]), float(pr[2][1]))(h))
else:
prior.append(
UniformPrior(float(pr[2][0]), float(pr[2][2]))(h))
return prior
# Optional dumper function giving run-time read access to
# the live points, dead points, weights and evidences
def dumper(live, dead, logweights, logZ, logZerr):
print("Last dead point:", dead[-1])
settings = PolyChordSettings(ndim, nder)
settings.base_dir = self.get_output(
'param_chains')[:-4] # Remove ".npz"
settings.file_root = 'pch'
settings.nlive = self.config['nlive']
settings.num_repeats = self.config['nrepeat']
settings.do_clustering = False # Assume unimodal posterior
settings.boost_posterior = 10 # Increase number of posterior samples
settings.nprior = 200 # Draw nprior initial prior samples
settings.maximise = True # Maximize posterior at the end
settings.read_resume = False # Read from resume file of earlier run
settings.feedback = 2 # Verbosity {0,1,2,3}
output = pypolychord.run_polychord(likelihood, ndim, nder, settings,
prior, dumper)
return output
curlimit = resource.getrlimit(
resource.RLIMIT_STACK) # get current stack resource size
resource.setrlimit(
resource.RLIMIT_STACK,
(resource.RLIM_INFINITY, resource.RLIM_INFINITY)) # set to unlimited
# setup run settings using the PolyChordSetting class
pargs = {
'nlive': nlive,
'precision_criterion': tol,
'base_dir': basedir,
'file_root': fileroot,
'write_resume': False, # don't output a resume file
'read_resume': False
} # don't read a resume file
settings = PolyChordSettings(ndims, nderived, **pargs)
# run nested sampling
output = pypolychord.run_polychord(loglikelihood_polychord, ndims, nderived,
settings, prior_transform_polychord)
# reset stack resource size
resource.setrlimit(resource.RLIMIT_STACK, curlimit)
# output marginal likelihood
print('Marginalised evidence is {} ± {}'.format(output.logZ, output.logZerr))
# plot posterior samples (if corner.py is installed)
try:
import matplotlib as mpl
mpl.use("Agg") # force Matplotlib backend to Agg
def prior(hypercube):
""" Uniform prior from [-1,1]^D. """
return UniformPrior(-1, 1)(hypercube)
#| Optional dumper function giving run-time read access to
#| the live points, dead points, weights and evidences
def dumper(live, dead, logweights, logZ, logZerr):
print("Last dead point:", dead[-1])
#| Initialise the settings
settings = PolyChordSettings(nDims, nDerived)
settings.file_root = 'gaussian'
settings.nlive = 200
settings.do_clustering = True
settings.read_resume = False
#| Run PolyChord
output = pypolychord.run_polychord(likelihood, nDims, nDerived, settings,
prior, dumper)
#| Create a paramnames file
paramnames = [('p%i' % i, r'\theta_%i' % i) for i in range(nDims)]
paramnames += [('r*', 'r')]
output.make_paramnames_files(paramnames)
from pypolychord.settings import PolyChordSettings
import matplotlib.pyplot as plt
import pypolychord as ppc
from pypolychord.priors import UniformPrior
def quantile(cube):
return UniformPrior(-10, 10)(cube)
def lnL(theta):
return theta**2
settings = PolyChordSettings(2, 0)
ppc.run_polychord(lnL, 2, 0, settings, quantile)
def set_polysettings(rundict, polysettings, ndim, nderived, isodate, parnames):
"""
Sets the correct settings for polychord and returns the PolyChordSettings
object.
Parameters
----------
rundict : dict
Dictionary with information about the run itself.
polysettings : dict
Dictionary with the custom PolyChord settings to be set for this run
ndim : int
Number of free parameters
nderived : int
Number of derived parameters
isodate : datetime
Date stamp to identify the current run
parnames : list
List containing the names of the free parameters
Returns
-------
settings : PolyChordSettings object
Object with all the information that PolyChord needs to run nested
sampling on this model.
"""
rundict_keys = list(rundict.keys())
# Define PolyChord settings
# Use the settings provided in polysettings otherwise use default
# Definition of default values for PolyChordSettings
default_settings = {'nlive': 25*ndim,
'num_repeats': 5*ndim,
'do_clustering': True,
'write_resume': False,
'read_resume': False,
'feedback': 1,
'precision_criterion': 0.001,
'boost_posterior': 0.0
}
# Update default values with settings provided by user
if polysettings != None:
if type(polysettings) is not dict:
raise TypeError("polysettings has to be a dictionary")
else:
setting = 'nlive'
if setting in polysettings.keys():
if type(polysettings[setting]) is not int:
raise TypeError(
f'{setting} has to be an integer (got type {type(polysettings[setting])})')
setting = 'num_repeats'
if setting in polysettings.keys():
if type(polysettings[setting]) is not int:
raise TypeError(
f'{setting} has to be an integer (got type {type(polysettings[setting])})')
setting = 'do_clustering'
if setting in polysettings.keys():
if type(polysettings[setting]) is not bool:
raise TypeError(
f'{setting} has to be a boolean (got type {type(polysettings[setting])})')
setting = 'read_resume'
if setting in polysettings.keys():
if type(polysettings[setting]) is not bool:
raise TypeError(
f'{setting} has to be a boolean (got type {type(polysettings[setting])})')
setting = 'precision_criterion'
if setting in polysettings.keys():
if type(polysettings[setting]) is not float:
raise TypeError(
f'{setting} has to be a float (got type {type(polysettings[setting])})')
default_settings.update(polysettings)
# Define fileroot name (identifies this specific run)
rundict['target'] = rundict['target'].replace(
' ', '') # Remove any whitespace
rundict['runid'] = rundict['runid'].replace(
' ', '') # Remove any whitespace
file_root = rundict['target']+'_'+rundict['runid']
# Add comment if it exists and is not empty
if 'comment' in rundict_keys:
if rundict['comment'] != '':
file_root += '-' + rundict['comment']
# Add number of planets if it exists
if 'nplanets' in rundict_keys:
if rundict['nplanets'] is not None:
file_root += f'_k{rundict["nplanets"]}'
# Check if there is a drift and add "d{n}" to file name
drift_order = 0
for par in parnames:
if 'drift' in par:
if par[6:] in ['lin', 'quad', 'cub', 'quar']:
drift_order += 1
if drift_order > 0:
file_root += f'_d{drift_order}'
# Label the run with nr of planets, live points, nr of cores, sampler and date
file_root += f'_nlive{default_settings["nlive"]}'
file_root += f'_ncores{size}'
file_root += '_polychord'
file_root += '_'+isodate
# Base directory
# Check if a save directory was provided
if 'save_dir' in rundict_keys:
save_dir = rundict['save_dir']
else:
save_dir = ''
base_dir = os.path.join(save_dir, file_root, 'polychains')
# Update settings dictionary with fileroot and basedir
default_settings.update({'file_root': file_root, 'base_dir': base_dir})
# Create PolyChorSettings object and assign settings
settings = PolyChordSettings(ndim, nderived, **default_settings)
# TODO Think about how to implement resumes
return settings
def run(self):
"""
Executes the inference
"""
if self.prepare():
# Setup the inference
ndim = np.sum(self.pstep > 0)
settings = PolyChordSettings(ndim, 0)
settings.base_dir = self.outputdir
settings.file_root = self.fprefix
settings.nlive = self.nlive
settings.read_resume = self.resume
if self.nrepeat is not None:
settings.num_repeat = self.nrepeat
settings.precision_criterion = self.dlogz
settings.grade_dims = [int(ndim)]
settings.read_resume = False
settings.feedback = self.verb
# Run it
if self.dumper is not None:
out = pypolychord.run_polychord(self.loglike, ndim, 0,
settings, self.prior,
self.dumper)
else:
out = pypolychord.run_polychord(self.loglike, ndim, 0,
settings, self.prior)
outp = np.loadtxt(os.path.join(self.outputdir, self.fprefix) +\
'_equal_weights.txt')
self.outp = outp[:, 2:].T
ibest = np.argmin(outp[:, 1])
self.bestp = self.outp[:, ibest]
# Save posterior and bestfit params
if self.fsavefile is not None:
np.save(self.fsavefile, self.outp)
if self.fbestp is not None:
np.save(self.fbestp, self.bestp)
return self.outp, self.bestp
else:
if self.verb:
print("Sampler is not fully prepared to run. " + \
"Correct the above errors and try again.")
def run(self):
'''
Run Polychord
We need to pass 3 functions:
log_lik - compute likelihood for a paramater set theta
prior - defines the box prior
dumper - extracts info during runtime - empty for now
'''
par_names = {name: name for d in self.data for name in d.pars_init}
val_dict = {
name: val
for d in self.data for name, val in d.pars_init.items()
}
lim_dict = {
name: lim
for d in self.data for name, lim in d.par_limit.items()
}
fix_dict = {
name: fix
for d in self.data for name, fix in d.par_fixed.items()
}
# Select the parameters we sample
sampled_pars_ind = np.array(
[i for i, val in enumerate(fix_dict.values()) if not val])
npar = len(sampled_pars_ind)
nder = 0
# Get the limits for the free params
limits = np.array(
[list(lim_dict.values())[i] for i in sampled_pars_ind])
names = np.array(
[list(par_names.values())[i] for i in sampled_pars_ind])
def log_lik(theta):
''' Wrapper for likelihood function passed to Polychord '''
pars = val_dict.copy()
for i, name in enumerate(names):
pars[name] = theta[i]
log_lik = self.log_lik(pars)
return log_lik, []
def prior(hypercube):
''' Uniform prior '''
prior = []
for i, lims in enumerate(limits):
prior.append(UniformPrior(lims[0], lims[1])(hypercube[i]))
return prior
def dumper(live, dead, logweights, logZ, logZerr):
''' Dumper function empty for now '''
pass
# Get the settings we need and add defaults
# These are the same as PolyChord recommends
nlive = self.polychord_setup.getint('nlive', int(25 * npar))
seed = self.polychord_setup.getint('seed', int(0))
num_repeats = self.polychord_setup.getint('num_repeats', int(5 * npar))
precision = self.polychord_setup.getfloat('precision', float(0.001))
boost_posterior = self.polychord_setup.getfloat(
'boost_posterior', float(0.0))
resume = self.polychord_setup.getboolean('resume', True)
cluster_posteriors = self.polychord_setup.getboolean(
'cluster_posteriors', False)
do_clustering = self.polychord_setup.getboolean('do_clustering', False)
path = self.polychord_setup.get('path')
filename = self.polychord_setup.get('name')
write_live = self.polychord_setup.getboolean('write_live', False)
write_dead = self.polychord_setup.getboolean('write_dead', True)
write_prior = self.polychord_setup.getboolean('write_prior', False)
# Initialize and run PolyChord
settings = PolyChordSettings(npar,
nder,
base_dir=path,
file_root=filename,
seed=seed,
nlive=nlive,
precision_criterion=precision,
num_repeats=num_repeats,
boost_posterior=boost_posterior,
cluster_posteriors=cluster_posteriors,
do_clustering=do_clustering,
equals=False,
write_resume=resume,
read_resume=resume,
write_live=write_live,
write_dead=write_dead,
write_prior=write_prior)
pypolychord.run_polychord(log_lik, npar, nder, settings, prior, dumper)
def initialize(self):
"""Imports the PolyChord sampler and prepares its arguments."""
if not get_mpi_rank(): # rank = 0 (MPI master) or None (no MPI)
self.log.info("Initializing")
# If path not given, try using general path to modules
if not self.path and self.path_install:
self.path = get_path(self.path_install)
if self.path:
if not get_mpi_rank():
self.log.info("Importing *local* PolyChord from " + self.path)
if not os.path.exists(os.path.realpath(self.path)):
self.log.error("The given path does not exist.")
raise HandledException
pc_build_path = get_build_path(self.path)
if not pc_build_path:
self.log.error("Either PolyChord is not in the given folder, "
"'%s', or you have not compiled it.", self.path)
raise HandledException
# Inserting the previously found path into the list of import folders
sys.path.insert(0, pc_build_path)
else:
self.log.info("Importing *global* PolyChord.")
try:
import pypolychord
from pypolychord.settings import PolyChordSettings
self.pc = pypolychord
except ImportError:
self.log.error(
"Couldn't find the PolyChord python interface. "
"Make sure that you have compiled it, and that you either\n"
" (a) specify a path (you didn't) or\n"
" (b) install the Python interface globally with\n"
" '/path/to/PolyChord/python setup.py install --user'")
raise HandledException
# Prepare arguments and settings
self.nDims = self.model.prior.d()
self.nDerived = (len(self.model.parameterization.derived_params()) +
len(self.model.prior) + len(self.model.likelihood._likelihoods))
if self.logzero is None:
self.logzero = np.nan_to_num(-np.inf)
if self.max_ndead == np.inf:
self.max_ndead = -1
for p in ["nlive", "num_repeats", "nprior", "max_ndead"]:
setattr(self, p, read_dnumber(getattr(self, p), self.nDims, dtype=int))
# Fill the automatic ones
if getattr(self, "feedback", None) is None:
values = {logging.CRITICAL: 0, logging.ERROR: 0, logging.WARNING: 0,
logging.INFO: 1, logging.DEBUG: 2}
self.feedback = values[self.log.getEffectiveLevel()]
try:
output_folder = getattr(self.output, "folder")
output_prefix = getattr(self.output, "prefix") or ""
self.read_resume = self.resuming
except AttributeError:
# dummy output -- no resume!
self.read_resume = False
from tempfile import gettempdir
output_folder = gettempdir()
if not get_mpi_rank():
from random import random
output_prefix = hex(int(random() * 16 ** 6))[2:]
else:
output_prefix = None
if get_mpi():
output_prefix = get_mpi_comm().bcast(output_prefix, root=0)
self.base_dir = os.path.join(output_folder, self.base_dir)
self.file_root = output_prefix
if not get_mpi_rank():
# Creating output folder, if it does not exist (just one process)
if not os.path.exists(self.base_dir):
os.makedirs(self.base_dir)
# Idem, a clusters folder if needed -- notice that PolyChord's default
# is "True", here "None", hence the funny condition below
if self.do_clustering is not False: # None here means "default"
try:
os.makedirs(os.path.join(self.base_dir, clusters))
except OSError: # exists!
pass
self.log.info("Storing raw PolyChord output in '%s'.",
self.base_dir)
# Exploiting the speed hierarchy
speeds, blocks = self.model.likelihood._speeds_of_params(int_speeds=True)
blocks_flat = list(chain(*blocks))
self.ordering = [
blocks_flat.index(p) for p in self.model.parameterization.sampled_params()]
self.grade_dims = [len(block) for block in blocks]
# self.grade_frac = np.array(
# [i*j for i,j in zip(self.grade_dims, speeds)])
# self.grade_frac = (
# self.grade_frac/sum(self.grade_frac))
# Disabled for now. We need a way to override the "time" part of the meaning of grade_frac
self.grade_frac = [1 / len(self.grade_dims) for _ in self.grade_dims]
# Assign settings
pc_args = ["nlive", "num_repeats", "nprior", "do_clustering",
"precision_criterion", "max_ndead", "boost_posterior", "feedback",
"logzero", "update_files", "posteriors", "equals",
"cluster_posteriors", "write_resume", "read_resume", "write_stats",
"write_live", "write_dead", "base_dir", "grade_frac", "grade_dims",
"feedback", "read_resume", "base_dir", "file_root", "grade_frac",
"grade_dims"]
self.pc_settings = PolyChordSettings(
self.nDims, self.nDerived, seed=(self.seed if self.seed is not None else -1),
**{p: getattr(self, p) for p in pc_args if getattr(self, p) is not None})
# prior conversion from the hypercube
bounds = self.model.prior.bounds(
confidence_for_unbounded=self.confidence_for_unbounded)
# Check if priors are bounded (nan's to inf)
inf = np.where(np.isinf(bounds))
if len(inf[0]):
params_names = self.model.parameterization.sampled_params()
params = [params_names[i] for i in sorted(list(set(inf[0])))]
self.log.error("PolyChord needs bounded priors, but the parameter(s) '"
"', '".join(params) + "' is(are) unbounded.")
raise HandledException
locs = bounds[:, 0]
scales = bounds[:, 1] - bounds[:, 0]
# This function re-scales the parameters AND puts them in the right order
self.pc_prior = lambda x: (locs + np.array(x)[self.ordering] * scales).tolist()
# We will need the volume of the prior domain, since PolyChord divides by it
self.logvolume = np.log(np.prod(scales))
# Done!
if not get_mpi_rank():
self.log.info("Calling PolyChord with arguments:")
for p, v in inspect.getmembers(self.pc_settings, lambda a: not (callable(a))):
if not p.startswith("_"):
self.log.info(" %s: %s", p, v)
def compute_fit(self):
self._polychord_output = None
data = self._observed.spectrum
datastd = self._observed.errorBar
sqrtpi = np.sqrt(2 * np.pi)
ndim = len(self.fitting_parameters)
def polychord_loglike(cube):
# log-likelihood function called by polychord
fit_params_container = np.array(
[cube[i] for i in range(len(self.fitting_parameters))])
chi_t = self.chisq_trans(fit_params_container, data, datastd)
# print('---------START---------')
# print('chi_t',chi_t)
# print('LOG',loglike)
loglike = -np.sum(np.log(datastd * sqrtpi)) - 0.5 * chi_t
return loglike, [0.0]
def polychord_uniform_prior(hypercube):
# prior distributions called by polychord. Implements a uniform prior
# converting parameters from normalised grid to uniform prior
# print(type(cube))
cube = [0.0] * ndim
for idx, bounds in enumerate(self.fit_boundaries):
# print(idx,self.fitting_parameters[idx])
bound_min, bound_max = bounds
cube[idx] = (hypercube[idx] *
(bound_max - bound_min)) + bound_min
#print('CUBE idx',cube[idx])
# print('-----------')
return cube
status = None
datastd_mean = np.mean(datastd)
settings = PolyChordSettings(ndim, 1)
settings.nlive = ndim * 25
settings.num_repeats = ndim * 5
settings.do_clustering = self.do_clustering
settings.num_repeats = ndim
settings.precision_criterion = self.evidence_tolerance
settings.logzero = -1e70
settings.read_resume = self.resume
settings.base_dir = self.dir_polychord
settings.file_root = '1-'
self.warning('Number of dimensions {}'.format(ndim))
self.warning('Fitting parameters {}'.format(self.fitting_parameters))
self.info('Beginning fit......')
pypolychord.run_polychord(polychord_loglike, ndim, 1, settings,
polychord_uniform_prior)
self._polychord_output = self.store_polychord_solutions()
print(self._polychord_output)
run_polychord(log_likelihood, nDims, nDerived, settings, prior)
_samples = NestedSamples(root='chains/' + file_root)
_samples.rename(columns={0: 'm', 1: 'c'}, inplace=True)
return _samples
def bench(prior, series):
# global linear_start, samples, linear_stop
start = time()
_samples = run_iteration(series, prior, log_likelihood)
stop = time()
return start, stop, _samples
if __name__ == "__main__":
settings = PolyChordSettings(2, 0, read_resume=False)
x_data = numpy.linspace(-3, 3, 250)
# x_data, y_data = generate_noisy_from_model(lambda x: 1.2 * x + 1.2,
# x_data, 0, 0.1)
x_data, y_data = mixture_model(lambda x: 1.1 * x + 1.1,
lambda x: 1.4 * x + 1.1,
x_data, x_noise_amplitude=0,
y_noise_amplitude=0.1)
log_likelihood = lambda theta: lnz(x_data, y_data, theta)
linear_start, linear_stop, samples = bench(uniform_prior, 'linear')
# samples.plot_2d(['m', 'c'])
# plt.show()
muc = numpy.linspace(0.1, 2, 10)
mum = numpy.linspace(0.1, 2, 10)
def initialize(self):
"""Imports the PolyChord sampler and prepares its arguments."""
# Allow global import if no direct path specification
allow_global = not self.path
if not self.path and self.packages_path:
self.path = self.get_path(self.packages_path)
self.pc = self.is_installed(path=self.path, allow_global=allow_global)
if not self.pc:
raise NotInstalledError(
self.log,
"Could not find PolyChord. Check error message above. "
"To install it, run 'cobaya-install polychord --%s "
"[packages_path]'", _packages_path_arg)
# Prepare arguments and settings
from pypolychord.settings import PolyChordSettings
self.n_sampled = len(self.model.parameterization.sampled_params())
self.n_derived = len(self.model.parameterization.derived_params())
self.n_priors = len(self.model.prior)
self.n_likes = len(self.model.likelihood)
self.nDims = self.model.prior.d()
self.nDerived = (self.n_derived + self.n_priors + self.n_likes)
if self.logzero is None:
self.logzero = np.nan_to_num(-np.inf)
if self.max_ndead == np.inf:
self.max_ndead = -1
self._quants_d_units = ["nlive", "max_ndead"]
for p in self._quants_d_units:
if getattr(self, p) is not None:
setattr(
self, p,
NumberWithUnits(getattr(self, p),
"d",
scale=self.nDims,
dtype=int).value)
self._quants_nlive_units = ["nprior"]
for p in self._quants_nlive_units:
if getattr(self, p) is not None:
setattr(
self, p,
NumberWithUnits(getattr(self, p),
"nlive",
scale=self.nlive,
dtype=int).value)
# Fill the automatic ones
if getattr(self, "feedback", None) is None:
values = {
logging.CRITICAL: 0,
logging.ERROR: 0,
logging.WARNING: 0,
logging.INFO: 1,
logging.DEBUG: 2
}
self.feedback = values[self.log.getEffectiveLevel()]
# Prepare output folders and prefixes
if self.output:
self.file_root = self.output.prefix
self.read_resume = self.output.is_resuming()
else:
output_prefix = share_mpi(
hex(int(random() * 16**6))[2:] if is_main_process() else None)
self.file_root = output_prefix
# dummy output -- no resume!
self.read_resume = False
self.base_dir = self.get_base_dir(self.output)
self.raw_clusters_dir = os.path.join(self.base_dir, self._clusters_dir)
self.output.create_folder(self.base_dir)
if self.do_clustering:
self.clusters_folder = self.get_clusters_dir(self.output)
self.output.create_folder(self.clusters_folder)
self.mpi_info("Storing raw PolyChord output in '%s'.", self.base_dir)
# Exploiting the speed hierarchy
if self.blocking:
blocks, oversampling_factors = self.model.check_blocking(
self.blocking)
else:
if self.measure_speeds:
self.model.measure_and_set_speeds(n=self.measure_speeds)
blocks, oversampling_factors = self.model.get_param_blocking_for_sampler(
oversample_power=self.oversample_power)
self.mpi_info("Parameter blocks and their oversampling factors:")
max_width = len(str(max(oversampling_factors)))
for f, b in zip(oversampling_factors, blocks):
self.mpi_info("* %" + "%d" % max_width + "d : %r", f, b)
# Save blocking in updated info, in case we want to resume
self._updated_info["blocking"] = list(zip(oversampling_factors,
blocks))
blocks_flat = list(chain(*blocks))
self.ordering = [
blocks_flat.index(p)
for p in self.model.parameterization.sampled_params()
]
self.grade_dims = [len(block) for block in blocks]
# Steps per block
# NB: num_repeats is ignored by PolyChord when int "grade_frac" given,
# so needs to be applied by hand.
# In num_repeats, `d` is interpreted as dimension of each block
self.grade_frac = [
int(o * read_dnumber(self.num_repeats, dim_block))
for o, dim_block in zip(oversampling_factors, self.grade_dims)
]
# Assign settings
pc_args = [
"nlive", "num_repeats", "nprior", "do_clustering",
"precision_criterion", "max_ndead", "boost_posterior", "feedback",
"logzero", "posteriors", "equals", "compression_factor",
"cluster_posteriors", "write_resume", "read_resume", "write_stats",
"write_live", "write_dead", "base_dir", "grade_frac", "grade_dims",
"feedback", "read_resume", "base_dir", "file_root", "grade_frac",
"grade_dims"
]
# As stated above, num_repeats is ignored, so let's not pass it
pc_args.pop(pc_args.index("num_repeats"))
self.pc_settings = PolyChordSettings(
self.nDims,
self.nDerived,
seed=(self.seed if self.seed is not None else -1),
**{
p: getattr(self, p)
for p in pc_args if getattr(self, p) is not None
})
# prior conversion from the hypercube
bounds = self.model.prior.bounds(
confidence_for_unbounded=self.confidence_for_unbounded)
# Check if priors are bounded (nan's to inf)
inf = np.where(np.isinf(bounds))
if len(inf[0]):
params_names = self.model.parameterization.sampled_params()
params = [params_names[i] for i in sorted(list(set(inf[0])))]
raise LoggedError(
self.log,
"PolyChord needs bounded priors, but the parameter(s) '"
"', '".join(params) + "' is(are) unbounded.")
locs = bounds[:, 0]
scales = bounds[:, 1] - bounds[:, 0]
# This function re-scales the parameters AND puts them in the right order
self.pc_prior = lambda x: (locs + np.array(x)[self.ordering] * scales
).tolist()
# We will need the volume of the prior domain, since PolyChord divides by it
self.logvolume = np.log(np.prod(scales))
# Prepare callback function
if self.callback_function is not None:
self.callback_function_callable = (get_external_function(
self.callback_function))
self.last_point_callback = 0
# Prepare runtime live and dead points collections
self.live = Collection(self.model,
None,
name="live",
initial_size=self.pc_settings.nlive)
self.dead = Collection(self.model, self.output, name="dead")
# Done!
if is_main_process():
self.log.debug("Calling PolyChord with arguments:")
for p, v in inspect.getmembers(self.pc_settings,
lambda a: not (callable(a))):
if not p.startswith("_"):
self.log.debug(" %s: %s", p, v)
self.mpi_info("Initialized!")
return result, []
def prior(hypercube):
""" Priors for each parameter. """
theta = [0.0] * nDims
for i, x in enumerate(hypercube):
theta[i] = priordict[parnames[i]].ppf(x)
return theta
# Define PolyChord settings
settings = PolyChordSettings(
nDims,
nDerived,
)
settings.do_clustering = args_params.noclust
settings.nlive = nDims * args_params.nlive
settings.base_dir = base_dir
settings.file_root = 'hd40307_k{}'.format(nplanets) # modelpath[12:-3]
settings.num_repeats = nDims * args_params.nrep
settings.precision_criterion = args_params.prec
settings.read_resume = False
# Change settings if resume is true
if args_params.resume:
settings.read_resume = args_params.resume
settings.base_dir = dirname + prev_run
# Run PolyChord