def _load_covmat(self, prefer_load_old, auto_params=None):
if prefer_load_old and os.path.exists(self.covmat_filename()):
if is_main_process():
covmat = np.atleast_2d(np.loadtxt(self.covmat_filename()))
else:
covmat = None
covmat = share_mpi(covmat)
self.mpi_info("Covariance matrix from previous sample.")
return covmat, []
else:
return share_mpi(
self.initial_proposal_covmat(
auto_params=auto_params) if is_main_process() else None)
def _load_covmat(self,
from_old_chain,
default_not_found=None,
auto_params=None):
if from_old_chain and os.path.exists(self.covmat_filename()):
if is_main_process():
covmat = np.atleast_2d(np.loadtxt(self.covmat_filename()))
else:
covmat = None
covmat = share_mpi(covmat)
self.mpi_info("Covariance matrix from checkpoint.")
return covmat, []
elif default_not_found is not None:
return default_not_found, []
else:
return share_mpi(
self.initial_proposal_covmat(
auto_params=auto_params) if is_main_process() else None)
def __init__(self, *args, **kwargs):
if is_main_process():
Output.__init__(self, *args, **kwargs)
if more_than_one_process():
to_broadcast = (
"folder", "prefix", "kind", "ext", "_resuming", "prefix_regexp_str")
values = share_mpi([getattr(self, var) for var in to_broadcast]
if is_main_process() else None)
for name, var in zip(to_broadcast, values):
setattr(self, name, var)
def __init__(self,
info_sampler: SamplerDict,
model: Model,
output=Optional[Output],
packages_path: Optional[str] = None,
name: Optional[str] = None):
"""
Actual initialization of the class. Loads the default and input information and
call the custom ``initialize`` method.
[Do not modify this one.]
"""
self._model = model
self._output = output
self._updated_info = deepcopy_where_possible(info_sampler)
super().__init__(info_sampler,
packages_path=packages_path,
name=name,
initialize=False,
standalone=False)
if not model.parameterization.sampled_params():
self.mpi_warning("No sampled parameters requested! "
"This will fail for non-mock samplers.")
# Load checkpoint info, if resuming
if self.output.is_resuming() and not isinstance(self, Minimizer):
checkpoint_info = None
if mpi.is_main_process():
try:
checkpoint_info = yaml_load_file(
self.checkpoint_filename())
if self.get_name() not in checkpoint_info["sampler"]:
raise LoggedError(
self.log, "Checkpoint file found at '%s' "
"but it corresponds to a different sampler.",
self.checkpoint_filename())
except (IOError, TypeError):
pass
checkpoint_info = mpi.share_mpi(checkpoint_info)
if checkpoint_info:
self.set_checkpoint_info(checkpoint_info)
self.mpi_info("Resuming from previous sample!")
elif not isinstance(self, Minimizer) and mpi.is_main_process():
try:
output.delete_file_or_folder(self.checkpoint_filename())
output.delete_file_or_folder(self.progress_filename())
except (OSError, TypeError):
pass
self._set_rng()
self.initialize()
model.set_cache_size(self._get_requested_cache_size())
# Add to the updated info some values which are
# only available after initialisation
self._updated_info["version"] = self.get_version()
def info_random_gaussian_mixture(ranges, n_modes=1, input_params_prefix="",
output_params_prefix="", O_std_min=1e-2, O_std_max=1,
derived=False, mpi_aware=True,
random_state=None):
"""
Wrapper around ``random_mean`` and ``random_cov`` to generate the likelihood and
parameter info for a random Gaussian.
If ``mpi_aware=True``, it draws the random stuff only once, and communicates it to
the rest of the MPI processes.
"""
cov: Any
mean: Any
if is_main_process() or not mpi_aware:
cov = random_cov(ranges, n_modes=n_modes, O_std_min=O_std_min,
O_std_max=O_std_max, mpi_warn=False, random_state=random_state)
if n_modes == 1:
cov = [cov]
# Make sure it stays away from the edges
mean = [[]] * n_modes
for i in range(n_modes):
std = np.sqrt(cov[i].diagonal())
factor = 3
ranges_mean = [[r[0] + factor * s, r[1] - +factor * s] for r, s in
zip(ranges, std)]
# If this implies min>max, take the centre
ranges_mean = [
(r if r[0] <= r[1] else 2 * [(r[0] + r[1]) / 2]) for r in ranges_mean]
mean[i] = random_mean(ranges_mean, n_modes=1, mpi_warn=False,
random_state=random_state)
else:
mean, cov = None, None
if mpi_aware:
mean, cov = share_mpi((mean, cov))
dimension = len(ranges)
info: InputDict = {"likelihood": {"gaussian_mixture": {
"means": mean, "covs": cov, "input_params_prefix": input_params_prefix,
"output_params_prefix": output_params_prefix, "derived": derived}},
"params": dict(
# sampled
tuple((input_params_prefix + "_%d" % i,
{"prior": {"min": ranges[i][0], "max": ranges[i][1]},
"latex": r"\alpha_{%i}" % i})
for i in range(dimension)) +
# derived
(tuple((output_params_prefix + "_%d" % i,
{"latex": r"\beta_{%i}" % i})
for i in range(dimension * n_modes)) if derived else ()))}
return info
def info_random_gaussian_mixture(
ranges, n_modes=1, input_params_prefix="", output_params_prefix="",
O_std_min=1e-2, O_std_max=1, derived=False, mpi_aware=True):
"""
Wrapper around ``random_mean`` and ``random_cov`` to generate the likelihood and
parameter info for a random Gaussian.
If ``mpi_aware=True``, it draws the random stuff only once, and communicates it to
the rest of the MPI processes.
"""
if is_main_process() or not mpi_aware:
cov = random_cov(ranges, n_modes=n_modes,
O_std_min=O_std_min, O_std_max=O_std_max, mpi_warn=False)
if n_modes == 1:
cov = [cov]
# Make sure it stays away from the edges
mean = [[]] * n_modes
for i in range(n_modes):
std = np.sqrt(cov[i].diagonal())
factor = 3
ranges_mean = [[l[0] + factor * s, l[1] - +factor * s] for l, s in
zip(ranges, std)]
# If this implies min>max, take the centre
ranges_mean = [
(l if l[0] <= l[1] else 2 * [(l[0] + l[1]) / 2]) for l in ranges_mean]
mean[i] = random_mean(ranges_mean, n_modes=1, mpi_warn=False)
if mpi_aware:
mean, cov = share_mpi((mean, cov) if is_main_process() else None)
dimension = len(ranges)
info = {kinds.likelihood: {"gaussian_mixture": {
"means": mean, "covs": cov, _input_params_prefix: input_params_prefix,
_output_params_prefix: output_params_prefix, "derived": derived}}}
info[_params] = dict(
# sampled
[(input_params_prefix + "_%d" % i,
{"prior": {"min": ranges[i][0], "max": ranges[i][1]},
"latex": r"\alpha_{%i}" % i})
for i in range(dimension)] +
# derived
([[output_params_prefix + "_%d" % i,
{"min": -3, "max": 3, "latex": r"\beta_{%i}" % i}]
for i in range(dimension * n_modes)] if derived else []))
return info
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!")
def process_results(self):
"""
Determines success (or not), chooses best (if MPI)
and produces output (if requested).
"""
evals_attr_ = evals_attr[self.method.lower()]
# If something failed
if not hasattr(self, "result"):
return
if more_than_one_process():
results = get_mpi_comm().gather(self.result, root=0)
successes = get_mpi_comm().gather(self.success, root=0)
_affine_transform_baselines = get_mpi_comm().gather(
self._affine_transform_baseline, root=0)
if is_main_process():
mins = [(getattr(r, evals_attr_) if s else np.inf)
for r, s in zip(results, successes)]
i_min = np.argmin(mins)
self.result = results[i_min]
self._affine_transform_baseline = _affine_transform_baselines[
i_min]
else:
successes = [self.success]
if is_main_process():
if not any(successes):
raise LoggedError(
self.log,
"Minimization failed! Here is the raw result object:\n%s",
str(self.result))
elif not all(successes):
self.log.warning('Some minimizations failed!')
elif more_than_one_process():
if max(mins) - min(mins) > 1:
self.log.warning('Big spread in minima: %r', mins)
elif max(mins) - min(mins) > 0.2:
self.log.warning('Modest spread in minima: %r', mins)
logp_min = -np.array(getattr(self.result, evals_attr_))
x_min = self.inv_affine_transform(self.result.x)
self.log.info("-log(%s) minimized to %g",
"likelihood" if self.ignore_prior else "posterior",
-logp_min)
recomputed_post_min = self.model.logposterior(x_min, cached=False)
recomputed_logp_min = (sum(recomputed_post_min.loglikes)
if self.ignore_prior else
recomputed_post_min.logpost)
if not np.allclose(logp_min, recomputed_logp_min, atol=1e-2):
raise LoggedError(
self.log,
"Cannot reproduce log minimum to within 0.01. Maybe your "
"likelihood is stochastic or large numerical error? "
"Recomputed min: %g (was %g) at %r", recomputed_logp_min,
logp_min, x_min)
self.minimum = OnePoint(self.model,
self.output,
name="",
extension=get_collection_extension(
self.ignore_prior))
self.minimum.add(x_min,
derived=recomputed_post_min.derived,
logpost=recomputed_post_min.logpost,
logpriors=recomputed_post_min.logpriors,
loglikes=recomputed_post_min.loglikes)
self.log.info("Parameter values at minimum:\n%s",
self.minimum.data.to_string())
self.minimum.out_update()
self.dump_getdist()
# Share results ('result' object may not be picklable)
self.minimum = share_mpi(getattr(self, "minimum", None))
self._inv_affine_transform_matrix = share_mpi(
getattr(self, "_inv_affine_transform_matrix"))
self._affine_transform_baseline = share_mpi(
getattr(self, "_affine_transform_baseline"))
try:
self.result = share_mpi(getattr(self, "result"))
except:
self.result = None
def tmpdir():
return mpi.share_mpi()
def tmpdir(tmpdir):
return mpi.share_mpi(str(tmpdir))
def check_convergence_and_learn_proposal(self):
"""
Checks the convergence of the sampling process, and, if requested,
learns a new covariance matrix for the proposal distribution from the covariance
of the last samples.
"""
if more_than_one_process():
# Compute and gather means, covs and CL intervals of last half of chains
use_first = int(self.n() / 2)
mean = self.collection.mean(first=use_first)
cov = self.collection.cov(first=use_first)
mcsamples = self.collection._sampled_to_getdist_mcsamples(
first=use_first)
try:
bound = np.array([[
mcsamples.confidence(i,
limfrac=self.Rminus1_cl_level / 2.,
upper=which)
for i in range(self.model.prior.d())
] for which in [False, True]]).T
success_bounds = True
except:
bound = None
success_bounds = False
Ns, means, covs, bounds, acceptance_rates = map(
lambda x: np.array(get_mpi_comm().gather(x)),
[self.n(), mean, cov, bound, self.acceptance_rate])
else:
# Compute and gather means, covs and CL intervals of last m-1 chain fractions
m = 1 + self.Rminus1_single_split
cut = int(len(self.collection) / m)
try:
Ns = (m - 1) * [cut]
means = np.array([
self.collection.mean(first=i * cut, last=(i + 1) * cut - 1)
for i in range(1, m)
])
covs = np.array([
self.collection.cov(first=i * cut, last=(i + 1) * cut - 1)
for i in range(1, m)
])
mcsamples_list = [
self.collection._sampled_to_getdist_mcsamples(
first=i * cut, last=(i + 1) * cut - 1)
for i in range(1, m)
]
except:
self.log.info(
"Not enough points in chain to check convergence. "
"Waiting for next checkpoint.")
return
acceptance_rates = self.acceptance_rate
try:
bounds = [
np.array([[
mcs.confidence(i,
limfrac=self.Rminus1_cl_level / 2.,
upper=which)
for i in range(self.model.prior.d())
] for which in [False, True]]).T for mcs in mcsamples_list
]
success_bounds = True
except:
bounds = None
success_bounds = False
# Compute convergence diagnostics
if is_main_process():
self.progress.at[self.i_learn,
"N"] = (sum(Ns)
if more_than_one_process() else self.n())
self.progress.at[self.i_learn, "timestamp"] = \
datetime.datetime.now().isoformat()
acceptance_rate = (np.average(acceptance_rates, weights=Ns) if
more_than_one_process() else acceptance_rates)
self.log.info(
" - Acceptance rate: %.3f" +
(" = avg(%r)" %
list(acceptance_rates) if more_than_one_process() else ""),
acceptance_rate)
self.progress.at[self.i_learn, "acceptance_rate"] = acceptance_rate
# "Within" or "W" term -- our "units" for assessing convergence
# and our prospective new covariance matrix
mean_of_covs = np.average(covs, weights=Ns, axis=0)
# "Between" or "B" term
# We don't weight with the number of samples in the chains here:
# shorter chains will likely be outliers, and we want to notice them
cov_of_means = np.atleast_2d(np.cov(means.T)) # , fweights=Ns)
# For numerical stability, we turn mean_of_covs into correlation matrix:
# rho = (diag(Sigma))^(-1/2) * Sigma * (diag(Sigma))^(-1/2)
# and apply the same transformation to the mean of covs (same eigenvals!)
diagSinvsqrt = np.diag(np.power(np.diag(cov_of_means), -0.5))
corr_of_means = diagSinvsqrt.dot(cov_of_means).dot(diagSinvsqrt)
norm_mean_of_covs = diagSinvsqrt.dot(mean_of_covs).dot(
diagSinvsqrt)
success = False
# Cholesky of (normalized) mean of covs and eigvals of Linv*cov_of_means*L
try:
L = np.linalg.cholesky(norm_mean_of_covs)
except np.linalg.LinAlgError:
self.log.warning(
"Negative covariance eigenvectors. "
"This may mean that the covariance of the samples does not "
"contain enough information at this point. "
"Skipping learning a new covmat for now.")
else:
Linv = np.linalg.inv(L)
# Suppress numpy warnings (restored later in this function)
error_handling = deepcopy(np.geterr())
np.seterr(all="ignore")
try:
eigvals = np.linalg.eigvalsh(
Linv.dot(corr_of_means).dot(Linv.T))
success = True
except np.linalg.LinAlgError:
self.log.warning("Could not compute eigenvalues. "
"Skipping learning a new covmat for now.")
else:
Rminus1 = max(np.abs(eigvals))
self.progress.at[self.i_learn, "Rminus1"] = Rminus1
# For real square matrices, a possible def of the cond number is:
condition_number = Rminus1 / min(np.abs(eigvals))
self.log.debug(" - Condition number = %g",
condition_number)
self.log.debug(" - Eigenvalues = %r", eigvals)
self.log.info(
" - Convergence of means: R-1 = %f after %d accepted steps"
%
(Rminus1,
(sum(Ns) if more_than_one_process() else self.n())) +
(" = sum(%r)" %
list(Ns) if more_than_one_process() else ""))
# Have we converged in means?
# (criterion must be fulfilled twice in a row)
if max(Rminus1, self.Rminus1_last) < self.Rminus1_stop:
# Check the convergence of the bounds of the confidence intervals
# Same as R-1, but with the rms deviation from the mean bound
# in units of the mean standard deviation of the chains
if success_bounds:
Rminus1_cl = (np.std(bounds, axis=0).T /
np.sqrt(np.diag(mean_of_covs)))
self.log.debug(
" - normalized std's of bounds = %r",
Rminus1_cl)
Rminus1_cl = np.max(Rminus1_cl)
self.progress.at[self.i_learn,
"Rminus1_cl"] = Rminus1_cl
self.log.info(
" - Convergence of bounds: R-1 = %f after %d "
% (Rminus1_cl,
(sum(Ns) if more_than_one_process(
) else self.n())) + "accepted steps" +
(" = sum(%r)" %
list(Ns) if more_than_one_process() else ""))
if Rminus1_cl < self.Rminus1_cl_stop:
self.converged = True
self.log.info("The run has converged!")
self._Ns = Ns
else:
self.log.info(
"Computation of the bounds was not possible. "
"Waiting until the next converge check.")
np.seterr(**error_handling)
else:
mean_of_covs = np.empty(
(self.model.prior.d(), self.model.prior.d()))
success = None
Rminus1 = None
# Broadcast and save the convergence status and the last R-1 of means
success = share_mpi(success)
if success:
self.Rminus1_last, self.converged = share_mpi((
Rminus1, self.converged) if is_main_process() else None)
# Do we want to learn a better proposal pdf?
if self.learn_proposal and not self.converged:
good_Rminus1 = (self.learn_proposal_Rminus1_max >
self.Rminus1_last >
self.learn_proposal_Rminus1_min)
if not good_Rminus1:
self.mpi_info(
"Convergence less than requested for updates: "
"waiting until the next convergence check.")
return
if more_than_one_process():
get_mpi_comm().Bcast(mean_of_covs, root=0)
else:
mean_of_covs = covs[0]
try:
self.proposer.set_covariance(mean_of_covs)
if is_main_process():
self.log.info(
" - Updated covariance matrix of proposal pdf.")
self.log.debug("%r", mean_of_covs)
except:
if is_main_process():
self.log.debug(
"Updating covariance matrix failed unexpectedly. "
"waiting until next covmat learning attempt.")
# Save checkpoint info
self.write_checkpoint()
def load_input_MPI(input_file):
return share_mpi(load_input(input_file) if is_main_process() else None)
def set_resuming(self, *args, **kwargs):
if is_main_process():
Output.set_resuming(self, *args, **kwargs)
if more_than_one_process():
self._resuming = share_mpi(
self._resuming if is_main_process() else None)
def check_and_dump_info(self, *args, **kwargs):
if is_main_process():
Output.check_and_dump_info(self, *args, **kwargs)
# Share cached loaded info
self._old_updated_info = share_mpi(
getattr(self, "_old_updated_info", None))