def run(self):
"""
Prepares the posterior function and calls ``PolyChord``'s ``run`` function.
"""
# Prepare the posterior
# Don't forget to multiply by the volume of the physical hypercube,
# since PolyChord divides by it
def logpost(params_values):
result = self.model.logposterior(params_values)
loglikes = result.loglikes
if len(loglikes) != self.n_likes:
loglikes = np.full(self.n_likes, np.nan)
derived = result.derived
if len(derived) != self.n_derived:
derived = np.full(self.n_derived, np.nan)
derived = list(derived) + list(result.logpriors) + list(loglikes)
return (max(result.logpost + self.logvolume, self.pc_settings.logzero),
derived)
sync_processes()
self.mpi_info("Calling PolyChord...")
self.pc.run_polychord(logpost, self.nDims, self.nDerived, self.pc_settings,
self.pc_prior, self.dumper)
self.process_raw_output()
def run(self):
"""
Prepares the posterior function and calls ``PolyChord``'s ``run`` function.
"""
# Prepare the posterior
# Don't forget to multiply by the volume of the physical hypercube,
# since PolyChord divides by it
def logpost(params_values):
logposterior, logpriors, loglikes, derived = (
self.model.logposterior(params_values))
if len(derived) != len(
self.model.parameterization.derived_params()):
derived = np.full(
len(self.model.parameterization.derived_params()), np.nan)
if len(loglikes) != len(self.model.likelihood._likelihoods):
loglikes = np.full(len(self.model.likelihood._likelihoods),
np.nan)
derived = list(derived) + list(logpriors) + list(loglikes)
return (max(logposterior + self.logvolume,
0.99 * self.pc_settings.logzero), derived)
sync_processes()
if am_single_or_primary_process():
self.log.info("Sampling!")
self.pc.run_polychord(logpost, self.nDims, self.nDerived,
self.pc_settings, self.pc_prior, self.dumper)
def run(self):
"""
Prepares the posterior function and calls ``PolyChord``'s ``run`` function.
"""
# Prepare the polychord likelihood
def loglikelihood(params_values):
result = self.model.logposterior(params_values)
loglikes = result.loglikes
if len(loglikes) != self.n_likes:
loglikes = np.full(self.n_likes, np.nan)
derived = result.derived
if len(derived) != self.n_derived:
derived = np.full(self.n_derived, np.nan)
derived = list(derived) + list(result.logpriors) + list(loglikes)
return max(loglikes.sum(), self.pc_settings.logzero), derived
def prior(cube):
theta = np.empty_like(cube)
for i, xi in enumerate(np.array(cube)[self.ordering]):
theta[i] = self.model.prior.pdf[i].ppf(xi)
return theta
if is_main_process():
self.dump_paramnames(self.raw_prefix)
sync_processes()
self.mpi_info("Calling PolyChord...")
self.pc.run_polychord(loglikelihood, self.nDims, self.nDerived,
self.pc_settings, prior, self.dumper)
self.process_raw_output()
def check_all_ready(self):
"""
Checks if the chain(s) is(/are) ready to check convergence and, if requested,
learn a new covariance matrix for the proposal distribution.
"""
msg_ready = ("Ready to check convergence" +
(" and learn a new proposal covmat"
if self.learn_proposal else ""))
n = len(self.collection)
# If *just* (weight==1) got ready to check+learn
if not (n % self.learn_every.value) and n > 0:
self.log.info("Learn + convergence test @ %d samples accepted.", n)
if more_than_one_process():
self.been_waiting += 1
if self.been_waiting > self.max_waiting:
self.send_error_signal()
raise LoggedError(
self.log,
"Waiting for too long for all chains to be ready. "
"Maybe one of them is stuck or died unexpectedly?")
self.model.dump_timing()
# If not MPI size > 1, we are ready
if not more_than_one_process():
self.log.debug(msg_ready)
return True
# Error check in case any process already sent an error signal
self.check_error_signal()
# If MPI, tell the rest that we are ready -- we use a "gather"
# ("reduce" was problematic), but we are in practice just pinging
if not hasattr(self, "req"): # just once!
self.all_ready = np.empty(get_mpi_size())
self.req = get_mpi_comm().Iallgather(np.array([1.]),
self.all_ready)
self.log.info(msg_ready + " (waiting for the rest...)")
# If all processes are ready to learn (= communication finished)
if self.req.Test() if hasattr(self, "req") else False:
# Sanity check: actually all processes have finished
assert np.all(self.all_ready == 1), (
"This should not happen! Notify the developers. (Got %r)",
self.all_ready)
if more_than_one_process() and is_main_process():
self.log.info("All chains are r" + msg_ready[1:])
delattr(self, "req")
self.been_waiting = 0
# Another error check, in case the error occurred after sending "ready" signal
self.check_error_signal()
# Just in case, a barrier here
sync_processes()
return True
return False
def check_all_ready(self):
"""
Checks if the chain(s) is(/are) ready to check convergence and, if requested,
learn a new covariance matrix for the proposal distribution.
"""
msg_ready = ("Ready to check convergence" +
(" and learn a new proposal covmat"
if self.learn_proposal else ""))
# If *just* (weight==1) got ready to check+learn
if (self.n() > 0 and self.current_point[_weight] == 1
and not (self.n() % self.check_every)):
self.log.info("Checkpoint: %d samples accepted.", self.n())
if more_than_one_process():
self.been_waiting += 1
if self.been_waiting > self.max_waiting:
self.log.error(
"Waiting for too long for all chains to be ready. "
"Maybe one of them is stuck or died unexpectedly?")
raise HandledException
self.model.dump_timing()
# If not MPI size > 1, we are ready
if not more_than_one_process():
if msg_ready:
self.log.info(msg_ready)
return True
# If MPI, tell the rest that we are ready -- we use a "gather"
# ("reduce" was problematic), but we are in practice just pinging
if not hasattr(self, "req"): # just once!
self.all_ready = np.empty(get_mpi_size())
self.req = get_mpi_comm().Iallgather(np.array([1.]),
self.all_ready)
self.log.info(msg_ready + " (waiting for the rest...)")
# If all processes are ready to learn (= communication finished)
if self.req.Test() if hasattr(self, "req") else False:
# Sanity check: actually all processes have finished
assert np.all(self.all_ready == 1), (
"This should not happen! Notify the developers. (Got %r)",
self.all_ready)
if more_than_one_process() and am_single_or_primary_process():
self.log.info("All chains are r" + msg_ready[1:])
delattr(self, "req")
self.been_waiting = 0
# Just in case, a barrier here
sync_processes()
return True
return False
def initialize(self):
"""Initializes the sampler:
creates the proposal distribution and draws the initial sample."""
if not self.model.prior.d():
raise LoggedError(self.log,
"No parameters being varied for sampler")
self.log.debug("Initializing")
# MARKED FOR DEPRECATION IN v3.0
if getattr(self, "oversample", None) is not None:
raise LoggedError(
self.log, "`oversample` has been deprecated. "
"Oversampling is now requested by setting "
"`oversample_power` > 0.")
# END OF DEPRECATION BLOCK
# MARKED FOR DEPRECATION IN v3.0
if getattr(self, "check_every", None) is not None:
raise LoggedError(
self.log, "`check_every` has been deprecated. "
"Please use `learn_every` instead.")
# END OF DEPRECATION BLOCK
if self.callback_every is None:
self.callback_every = self.learn_every
self._quants_d_units = []
for q in ["max_tries", "learn_every", "callback_every", "burn_in"]:
number = NumberWithUnits(getattr(self, q), "d", dtype=int)
self._quants_d_units.append(number)
setattr(self, q, number)
self.output_every = NumberWithUnits(self.output_every, "s", dtype=int)
if is_main_process():
if self.output.is_resuming() and (max(self.mpi_size or 0, 1) !=
mpi.size()):
raise LoggedError(
self.log,
"Cannot resume a run with a different number of chains: "
"was %d and now is %d.", max(self.mpi_size or 0, 1),
mpi.size())
sync_processes()
# One collection per MPI process: `name` is the MPI rank + 1
name = str(1 + mpi.rank())
self.collection = SampleCollection(self.model,
self.output,
name=name,
resuming=self.output.is_resuming())
self.current_point = OneSamplePoint(self.model)
# Use standard MH steps by default
self.get_new_sample = self.get_new_sample_metropolis
# Prepare callback function
if self.callback_function:
self.callback_function_callable = (get_external_function(
self.callback_function))
# Useful for getting last points added inside callback function
self.last_point_callback = 0
self.i_learn = 1
# Monitoring/restore progress
if is_main_process():
cols = [
"N", "timestamp", "acceptance_rate", "Rminus1", "Rminus1_cl"
]
self.progress = DataFrame(columns=cols)
if self.output and not self.output.is_resuming():
header_fmt = {
"N": 6 * " " + "N",
"timestamp": 17 * " " + "timestamp"
}
with open(self.progress_filename(), "w",
encoding="utf-8") as progress_file:
progress_file.write("# " + " ".join([
header_fmt.get(col, ((7 + 8) - len(col)) * " " + col)
for col in self.progress.columns
]) + "\n")
# Get first point, to be discarded -- not possible to determine its weight
# Still, we need to compute derived parameters, since, as the proposal "blocked",
# we may be saving the initial state of some block.
# NB: if resuming but nothing was written (burn-in not finished): re-start
if self.output.is_resuming() and len(self.collection):
last = len(self.collection) - 1
initial_point = (self.collection[
self.collection.sampled_params].iloc[last]).to_numpy(
dtype=np.float64, copy=True)
results = LogPosterior(
logpost=-self.collection[OutPar.minuslogpost].iloc[last],
logpriors=-(self.collection[
self.collection.minuslogprior_names].iloc[last].to_numpy(
dtype=np.float64, copy=True)),
loglikes=-0.5 *
(self.collection[self.collection.chi2_names].iloc[last].
to_numpy(dtype=np.float64, copy=True)),
derived=(self.collection[
self.collection.derived_params].iloc[last].to_numpy(
dtype=np.float64, copy=True)))
else:
# NB: max_tries adjusted to dim instead of #cycles (blocking not computed yet)
self.max_tries.set_scale(self.model.prior.d())
self.log.info(
"Getting initial point... (this may take a few seconds)")
initial_point, results = \
self.model.get_valid_point(max_tries=self.max_tries.value,
random_state=self._rng)
# If resuming but no existing chain, assume failed run and ignore blocking
# if speeds measurement requested
if self.output.is_resuming() and not len(self.collection) \
and self.measure_speeds:
self.blocking = None
if self.measure_speeds and self.blocking:
self.mpi_warning(
"Parameter blocking manually fixed: speeds will not be measured."
)
elif self.measure_speeds:
n = None if self.measure_speeds is True else int(
self.measure_speeds)
self.model.measure_and_set_speeds(n=n,
discard=0,
random_state=self._rng)
self.set_proposer_blocking()
self.set_proposer_initial_covmat(load=True)
self.current_point.add(initial_point, results)
self.log.info("Initial point: %s", self.current_point)
# Max #(learn+convergence checks) to wait,
# in case one process dies/hangs without raising error
self.been_waiting = 0
self.max_waiting = max(50, self.max_tries.unit_value)
# Burning-in countdown -- the +1 accounts for the initial point (always accepted)
self.burn_in_left = self.burn_in.value * self.current_point.output_thin + 1
self._msg_ready = ("Ready to check convergence" +
(" and learn a new proposal covmat"
if self.learn_proposal else ""))
# Initial dummy checkpoint
# (needed when 1st "learn point" not reached in prev. run)
self.write_checkpoint()
def post(info_or_yaml_or_file: Union[InputDict, str, os.PathLike],
sample: Union[SampleCollection, List[SampleCollection], None] = None
) -> PostTuple:
info = load_input_dict(info_or_yaml_or_file)
logger_setup(info.get("debug"), info.get("debug_file"))
log = get_logger(__name__)
# MARKED FOR DEPRECATION IN v3.0
if info.get("modules"):
raise LoggedError(log, "The input field 'modules' has been deprecated."
"Please use instead %r", packages_path_input)
# END OF DEPRECATION BLOCK
info_post: PostDict = info.get("post") or {}
if not info_post:
raise LoggedError(log, "No 'post' block given. Nothing to do!")
if mpi.is_main_process() and info.get("resume"):
log.warning("Resuming not implemented for post-processing. Re-starting.")
if not info.get("output") and info_post.get("output") \
and not info.get("params"):
raise LoggedError(log, "The input dictionary must have be a full option "
"dictionary, or have an existing 'output' root to load "
"previous settings from ('output' to read from is in the "
"main block not under 'post'). ")
# 1. Load existing sample
output_in = get_output(prefix=info.get("output"))
if output_in:
info_in = output_in.load_updated_info() or update_info(info)
else:
info_in = update_info(info)
params_in: ExpandedParamsDict = info_in["params"] # type: ignore
dummy_model_in = DummyModel(params_in, info_in.get("likelihood", {}),
info_in.get("prior"))
in_collections = []
thin = info_post.get("thin", 1)
skip = info_post.get("skip", 0)
if info.get('thin') is not None or info.get('skip') is not None: # type: ignore
raise LoggedError(log, "'thin' and 'skip' should be "
"parameters of the 'post' block")
if sample:
# If MPI, assume for each MPI process post is passed in the list of
# collections that should be processed by that process
# (e.g. single chain output from sampler)
if isinstance(sample, SampleCollection):
in_collections = [sample]
else:
in_collections = sample
for i, collection in enumerate(in_collections):
if skip:
if 0 < skip < 1:
skip = int(round(skip * len(collection)))
collection = collection.filtered_copy(slice(skip, None))
if thin != 1:
collection = collection.thin_samples(thin)
in_collections[i] = collection
elif output_in:
files = output_in.find_collections()
numbered = files
if not numbered:
# look for un-numbered output files
files = output_in.find_collections(name=False)
if files:
if mpi.size() > len(files):
raise LoggedError(log, "Number of MPI processes (%s) is larger than "
"the number of sample files (%s)",
mpi.size(), len(files))
for num in range(mpi.rank(), len(files), mpi.size()):
in_collections += [SampleCollection(
dummy_model_in, output_in,
onload_thin=thin, onload_skip=skip, load=True, file_name=files[num],
name=str(num + 1) if numbered else "")]
else:
raise LoggedError(log, "No samples found for the input model with prefix %s",
os.path.join(output_in.folder, output_in.prefix))
else:
raise LoggedError(log, "No output from where to load from, "
"nor input collections given.")
if any(len(c) <= 1 for c in in_collections):
raise LoggedError(
log, "Not enough samples for post-processing. Try using a larger sample, "
"or skipping or thinning less.")
mpi.sync_processes()
log.info("Will process %d sample points.", sum(len(c) for c in in_collections))
# 2. Compare old and new info: determine what to do
add = info_post.get("add") or {}
if "remove" in add:
raise LoggedError(log, "remove block should be under 'post', not 'add'")
remove = info_post.get("remove") or {}
# Add a dummy 'one' likelihood, to absorb unused parameters
if not add.get("likelihood"):
add["likelihood"] = {}
add["likelihood"]["one"] = None
# Expand the "add" info, but don't add new default sampled parameters
orig_params = set(add.get("params") or [])
add = update_info(add, add_aggr_chi2=False)
add_params: ExpandedParamsDict = add["params"] # type: ignore
for p in set(add_params) - orig_params:
if p in params_in:
add_params.pop(p)
# 2.1 Adding/removing derived parameters and changes in priors of sampled parameters
out_combined_params = deepcopy_where_possible(params_in)
remove_params = list(str_to_list(remove.get("params")) or [])
for p in remove_params:
pinfo = params_in.get(p)
if pinfo is None or not is_derived_param(pinfo):
raise LoggedError(
log,
"You tried to remove parameter '%s', which is not a derived parameter. "
"Only derived parameters can be removed during post-processing.", p)
out_combined_params.pop(p)
# Force recomputation of aggregated chi2
for p in list(out_combined_params):
if p.startswith(get_chi2_name("")):
out_combined_params.pop(p)
prior_recompute_1d = False
for p, pinfo in add_params.items():
pinfo_in = params_in.get(p)
if is_sampled_param(pinfo):
if not is_sampled_param(pinfo_in):
# No added sampled parameters (de-marginalisation not implemented)
if pinfo_in is None:
raise LoggedError(
log, "You added a new sampled parameter %r (maybe accidentally "
"by adding a new likelihood that depends on it). "
"Adding new sampled parameters is not possible. Try fixing "
"it to some value.", p)
else:
raise LoggedError(
log,
"You tried to change the prior of parameter '%s', "
"but it was not a sampled parameter. "
"To change that prior, you need to define as an external one.", p)
# recompute prior if potentially changed sampled parameter priors
prior_recompute_1d = True
elif is_derived_param(pinfo):
if p in out_combined_params:
raise LoggedError(
log, "You tried to add derived parameter '%s', which is already "
"present. To force its recomputation, 'remove' it too.", p)
elif is_fixed_or_function_param(pinfo):
# Only one possibility left "fixed" parameter that was not present before:
# input of new likelihood, or just an argument for dynamical derived (dropped)
if pinfo_in and p in params_in and pinfo["value"] != pinfo_in.get("value"):
raise LoggedError(
log,
"You tried to add a fixed parameter '%s: %r' that was already present"
" but had a different value or was not fixed. This is not allowed. "
"The old info of the parameter was '%s: %r'",
p, dict(pinfo), p, dict(pinfo_in))
elif not pinfo_in: # OK as long as we have known value for it
raise LoggedError(log, "Parameter %s no known value. ", p)
out_combined_params[p] = pinfo
out_combined: InputDict = {"params": out_combined_params} # type: ignore
# Turn the rest of *derived* parameters into constants,
# so that the likelihoods do not try to recompute them
# But be careful to exclude *input* params that have a "derived: True" value
# (which in "updated info" turns into "derived: 'lambda [x]: [x]'")
# Don't assign to derived parameters to theories, only likelihoods, so they can be
# recomputed if needed. If the theory does not need to be computed, it doesn't matter
# if it is already assigned parameters in the usual way; likelihoods can get
# the required derived parameters from the stored sample derived parameter inputs.
out_params_with_computed = deepcopy_where_possible(out_combined_params)
dropped_theory = set()
for p, pinfo in out_params_with_computed.items():
if (is_derived_param(pinfo) and "value" not in pinfo
and p not in add_params):
out_params_with_computed[p] = {"value": np.nan}
dropped_theory.add(p)
# 2.2 Manage adding/removing priors and likelihoods
warn_remove = False
kind: ModelBlock
for kind in ("prior", "likelihood", "theory"):
out_combined[kind] = deepcopy_where_possible(info_in.get(kind)) or {}
for remove_item in str_to_list(remove.get(kind)) or []:
try:
out_combined[kind].pop(remove_item, None)
if remove_item not in (add.get(kind) or []) and kind != "theory":
warn_remove = True
except ValueError:
raise LoggedError(
log, "Trying to remove %s '%s', but it is not present. "
"Existing ones: %r", kind, remove_item, list(out_combined[kind]))
if kind != "theory" and kind in add:
dups = set(add.get(kind) or []).intersection(out_combined[kind]) - {"one"}
if dups:
raise LoggedError(
log, "You have added %s '%s', which was already present. If you "
"want to force its recomputation, you must also 'remove' it.",
kind, dups)
out_combined[kind].update(add[kind])
if warn_remove and mpi.is_main_process():
log.warning("You are removing a prior or likelihood pdf. "
"Notice that if the resulting posterior is much wider "
"than the original one, or displaced enough, "
"it is probably safer to explore it directly.")
mlprior_names_add = minuslogprior_names(add.get("prior") or [])
chi2_names_add = [get_chi2_name(name) for name in add["likelihood"] if
name != "one"]
out_combined["likelihood"].pop("one", None)
add_theory = add.get("theory")
if add_theory:
if len(add["likelihood"]) == 1 and not any(
is_derived_param(pinfo) for pinfo in add_params.values()):
log.warning("You are adding a theory, but this does not force recomputation "
"of any likelihood or derived parameters unless explicitly "
"removed+added.")
# Inherit from the original chain (input|output_params, renames, etc)
added_theory = add_theory.copy()
for theory, theory_info in out_combined["theory"].items():
if theory in list(added_theory):
out_combined["theory"][theory] = \
recursive_update(theory_info, added_theory.pop(theory))
out_combined["theory"].update(added_theory)
# Prepare recomputation of aggregated chi2
# (they need to be recomputed by hand, because auto-computation won't pick up
# old likelihoods for a given type)
all_types = {like: str_to_list(opts.get("type") or [])
for like, opts in out_combined["likelihood"].items()}
types = set(chain(*all_types.values()))
inv_types = {t: [like for like, like_types in all_types.items() if t in like_types]
for t in sorted(types)}
add_aggregated_chi2_params(out_combined_params, types)
# 3. Create output collection
# Use default prefix if it exists. If it does not, produce no output by default.
# {post: {output: None}} suppresses output, and if it's a string, updates it.
out_prefix = info_post.get("output", info.get("output"))
if out_prefix:
suffix = info_post.get("suffix")
if not suffix:
raise LoggedError(log, "You need to provide a '%s' for your output chains.",
"suffix")
out_prefix += separator_files + "post" + separator_files + suffix
output_out = get_output(prefix=out_prefix, force=info.get("force"))
output_out.set_lock()
if output_out and not output_out.force and output_out.find_collections():
raise LoggedError(log, "Found existing post-processing output with prefix %r. "
"Delete it manually or re-run with `force: True` "
"(or `-f`, `--force` from the shell).", out_prefix)
elif output_out and output_out.force and mpi.is_main_process():
output_out.delete_infos()
for _file in output_out.find_collections():
output_out.delete_file_or_folder(_file)
info_out = deepcopy_where_possible(info)
info_post = info_post.copy()
info_out["post"] = info_post
# Updated with input info and extended (updated) add info
info_out.update(info_in) # type: ignore
info_post["add"] = add
dummy_model_out = DummyModel(out_combined_params, out_combined["likelihood"],
info_prior=out_combined["prior"])
out_func_parameterization = Parameterization(out_params_with_computed)
# TODO: check allow_renames=False?
model_add = Model(out_params_with_computed, add["likelihood"],
info_prior=add.get("prior"), info_theory=out_combined["theory"],
packages_path=(info_post.get(packages_path_input) or
info.get(packages_path_input)),
allow_renames=False, post=True,
stop_at_error=info.get('stop_at_error', False),
skip_unused_theories=True, dropped_theory_params=dropped_theory)
# Remove auxiliary "one" before dumping -- 'add' *is* info_out["post"]["add"]
add["likelihood"].pop("one")
out_collections = [SampleCollection(dummy_model_out, output_out, name=c.name,
cache_size=OutputOptions.default_post_cache_size)
for c in in_collections]
# TODO: should maybe add skip/thin to out_combined, so can tell post-processed?
output_out.check_and_dump_info(info_out, out_combined, check_compatible=False)
collection_in = in_collections[0]
collection_out = out_collections[0]
last_percent = None
known_constants = dummy_model_out.parameterization.constant_params()
known_constants.update(dummy_model_in.parameterization.constant_params())
missing_params = dummy_model_in.parameterization.sampled_params().keys() - set(
collection_in.columns)
if missing_params:
raise LoggedError(log, "Input samples do not contain expected sampled parameter "
"values: %s", missing_params)
missing_priors = set(name for name in collection_out.minuslogprior_names if
name not in mlprior_names_add
and name not in collection_in.columns)
if _minuslogprior_1d_name in missing_priors:
prior_recompute_1d = True
if prior_recompute_1d:
missing_priors.discard(_minuslogprior_1d_name)
mlprior_names_add.insert(0, _minuslogprior_1d_name)
prior_regenerate: Optional[Prior]
if missing_priors and "prior" in info_in:
# in case there are input priors that are not stored in input samples
# e.g. when postprocessing GetDist/CosmoMC-format chains
in_names = minuslogprior_names(info_in["prior"])
info_prior = {piname: inf for (piname, inf), in_name in
zip(info_in["prior"].items(), in_names) if
in_name in missing_priors}
regenerated_prior_names = minuslogprior_names(info_prior)
missing_priors.difference_update(regenerated_prior_names)
prior_regenerate = Prior(dummy_model_in.parameterization, info_prior)
else:
prior_regenerate = None
regenerated_prior_names = None
if missing_priors:
raise LoggedError(log, "Missing priors: %s", missing_priors)
mpi.sync_processes()
output_in.check_lock()
# 4. Main loop! Loop over input samples and adjust as required.
if mpi.is_main_process():
log.info("Running post-processing...")
difflogmax: Optional[float] = None
to_do = sum(len(c) for c in in_collections)
weights = []
done = 0
last_dump_time = time.time()
for collection_in, collection_out in zip(in_collections, out_collections):
importance_weights = []
def set_difflogmax():
nonlocal difflogmax
difflog = (collection_in[OutPar.minuslogpost].to_numpy(
dtype=np.float64)[:len(collection_out)]
- collection_out[OutPar.minuslogpost].to_numpy(dtype=np.float64))
difflogmax = np.max(difflog)
if abs(difflogmax) < 1:
difflogmax = 0 # keep simple when e.g. very similar
log.debug("difflogmax: %g", difflogmax)
if mpi.more_than_one_process():
difflogmax = max(mpi.allgather(difflogmax))
if mpi.is_main_process():
log.debug("Set difflogmax: %g", difflogmax)
_weights = np.exp(difflog - difflogmax)
importance_weights.extend(_weights)
collection_out.reweight(_weights)
for i, point in collection_in.data.iterrows():
all_params = point.to_dict()
for p in remove_params:
all_params.pop(p, None)
log.debug("Point: %r", point)
sampled = np.array([all_params[param] for param in
dummy_model_in.parameterization.sampled_params()])
all_params = out_func_parameterization.to_input(all_params).copy()
# Add/remove priors
if prior_recompute_1d:
priors_add = [model_add.prior.logps_internal(sampled)]
if priors_add[0] == -np.inf:
continue
else:
priors_add = []
if model_add.prior.external:
priors_add.extend(model_add.prior.logps_external(all_params))
logpriors_add = dict(zip(mlprior_names_add, priors_add))
logpriors_new = [logpriors_add.get(name, - point.get(name, 0))
for name in collection_out.minuslogprior_names]
if prior_regenerate:
regenerated = dict(zip(regenerated_prior_names,
prior_regenerate.logps_external(all_params)))
for _i, name in enumerate(collection_out.minuslogprior_names):
if name in regenerated_prior_names:
logpriors_new[_i] = regenerated[name]
if is_debug(log):
log.debug("New set of priors: %r",
dict(zip(dummy_model_out.prior, logpriors_new)))
if -np.inf in logpriors_new:
continue
# Add/remove likelihoods and/or (re-)calculate derived parameters
loglikes_add, output_derived = model_add._loglikes_input_params(
all_params, return_output_params=True)
loglikes_add = dict(zip(chi2_names_add, loglikes_add))
output_derived = dict(zip(model_add.output_params, output_derived))
loglikes_new = [loglikes_add.get(name, -0.5 * point.get(name, 0))
for name in collection_out.chi2_names]
if is_debug(log):
log.debug("New set of likelihoods: %r",
dict(zip(dummy_model_out.likelihood, loglikes_new)))
if output_derived:
log.debug("New set of derived parameters: %r", output_derived)
if -np.inf in loglikes_new:
continue
all_params.update(output_derived)
all_params.update(out_func_parameterization.to_derived(all_params))
derived = {param: all_params.get(param) for param in
dummy_model_out.parameterization.derived_params()}
# We need to recompute the aggregated chi2 by hand
for type_, likes in inv_types.items():
derived[get_chi2_name(type_)] = sum(
-2 * lvalue for lname, lvalue
in zip(collection_out.chi2_names, loglikes_new)
if undo_chi2_name(lname) in likes)
if is_debug(log):
log.debug("New derived parameters: %r",
{p: derived[p]
for p in dummy_model_out.parameterization.derived_params()
if p in add["params"]})
# Save to the collection (keep old weight for now)
weight = point.get(OutPar.weight)
mpi.check_errors()
if difflogmax is None and i > OutputOptions.reweight_after and \
time.time() - last_dump_time > OutputOptions.output_inteveral_s / 2:
set_difflogmax()
collection_out.out_update()
if difflogmax is not None:
logpost_new = sum(logpriors_new) + sum(loglikes_new)
importance_weight = np.exp(logpost_new + point.get(OutPar.minuslogpost)
- difflogmax)
weight = weight * importance_weight
importance_weights.append(importance_weight)
if time.time() - last_dump_time > OutputOptions.output_inteveral_s:
collection_out.out_update()
last_dump_time = time.time()
if weight > 0:
collection_out.add(sampled, derived=derived.values(), weight=weight,
logpriors=logpriors_new, loglikes=loglikes_new)
# Display progress
percent = int(np.round((i + done) / to_do * 100))
if percent != last_percent and not percent % 5:
last_percent = percent
progress_bar(log, percent, " (%d/%d)" % (i + done, to_do))
if difflogmax is None:
set_difflogmax()
if not collection_out.data.last_valid_index():
raise LoggedError(
log, "No elements in the final sample. Possible causes: "
"added a prior or likelihood valued zero over the full sampled "
"domain, or the computation of the theory failed everywhere, etc.")
collection_out.out_update()
weights.append(np.array(importance_weights))
done += len(collection_in)
assert difflogmax is not None
points = 0
tot_weight = 0
min_weight = np.inf
max_weight = -np.inf
max_output_weight = -np.inf
sum_w2 = 0
points_removed = 0
for collection_in, collection_out, importance_weights in zip(in_collections,
out_collections,
weights):
output_weights = collection_out[OutPar.weight]
points += len(collection_out)
tot_weight += np.sum(output_weights)
points_removed += len(importance_weights) - len(output_weights)
min_weight = min(min_weight, np.min(importance_weights))
max_weight = max(max_weight, np.max(importance_weights))
max_output_weight = max(max_output_weight, np.max(output_weights))
sum_w2 += np.dot(output_weights, output_weights)
(tot_weights, min_weights, max_weights, max_output_weights, sum_w2s, points_s,
points_removed_s) = mpi.zip_gather(
[tot_weight, min_weight, max_weight, max_output_weight, sum_w2,
points, points_removed])
if mpi.is_main_process():
output_out.clear_lock()
log.info("Finished! Final number of distinct sample points: %s", sum(points_s))
log.info("Importance weight range: %.4g -- %.4g",
min(min_weights), max(max_weights))
if sum(points_removed_s):
log.info("Points deleted due to zero weight: %s", sum(points_removed_s))
log.info("Effective number of single samples if independent (sum w)/max(w): %s",
int(sum(tot_weights) / max(max_output_weights)))
log.info(
"Effective number of weighted samples if independent (sum w)^2/sum(w^2): "
"%s", int(sum(tot_weights) ** 2 / sum(sum_w2s)))
products: PostResultDict = {"sample": value_or_list(out_collections),
"stats": {'min_importance_weight': (min(min_weights) /
max(max_weights)),
'points_removed': sum(points_removed_s),
'tot_weight': sum(tot_weights),
'max_weight': max(max_output_weights),
'sum_w2': sum(sum_w2s),
'points': sum(points_s)},
"logpost_weight_offset": difflogmax,
"weights": value_or_list(weights)}
return PostTuple(info=out_combined, products=products)
def run(
info_or_yaml_or_file: Union[InputDict, str, os.PathLike],
packages_path: Optional[str] = None,
output: Union[str, LiteralFalse, None] = None,
debug: Union[bool, int, None] = None,
stop_at_error: Optional[bool] = None,
resume: bool = False,
force: bool = False,
no_mpi: bool = False,
test: bool = False,
override: Optional[InputDict] = None,
) -> Union[InfoSamplerTuple, PostTuple]:
"""
Run from an input dictionary, file name or yaml string, with optional arguments
to override settings in the input as needed.
:param info_or_yaml_or_file: input options dictionary, yaml file, or yaml text
:param packages_path: path where external packages were installed
:param output: path name prefix for output files, or False for no file output
:param debug: true for verbose debug output, or a specific logging level
:param stop_at_error: stop if an error is raised
:param resume: continue an existing run
:param force: overwrite existing output if it exists
:param no_mpi: run without MPI
:param test: only test initialization rather than actually running
:param override: option dictionary to merge into the input one, overriding settings
(but with lower precedence than the explicit keyword arguments)
:return: (updated_info, sampler) tuple of options dictionary and Sampler instance,
or (updated_info, results) if using "post" post-processing
"""
# This function reproduces the model-->output-->sampler pipeline one would follow
# when instantiating by hand, but alters the order to performs checks and dump info
# as early as possible, e.g. to check if resuming possible or `force` needed.
if no_mpi or test:
mpi.set_mpi_disabled()
with mpi.ProcessState("run"):
info: InputDict = load_info_overrides(info_or_yaml_or_file, debug,
stop_at_error, packages_path,
override)
if test:
info["test"] = True
# If any of resume|force given as cmd args, ignore those in the input file
if resume or force:
if resume and force:
raise ValueError("'rename' and 'force' are exclusive options")
info["resume"] = bool(resume)
info["force"] = bool(force)
if info.get("post"):
if isinstance(output, str) or output is False:
info["post"]["output"] = output or None
return post(info)
if isinstance(output, str) or output is False:
info["output"] = output or None
logger_setup(info.get("debug"), info.get("debug_file"))
logger_run = get_logger(run.__name__)
# MARKED FOR DEPRECATION IN v3.0
# BEHAVIOUR TO BE REPLACED BY ERROR:
check_deprecated_modules_path(info)
# END OF DEPRECATION BLOCK
# 1. Prepare output driver, if requested by defining an output_prefix
# GetDist needs to know the original sampler, so don't overwrite if minimizer
try:
which_sampler = list(info["sampler"])[0]
except (KeyError, TypeError):
raise LoggedError(
logger_run,
"You need to specify a sampler using the 'sampler' key "
"as e.g. `sampler: {mcmc: None}.`")
infix = "minimize" if which_sampler == "minimize" else None
with get_output(prefix=info.get("output"),
resume=info.get("resume"),
force=info.get("force"),
infix=infix) as out:
# 2. Update the input info with the defaults for each component
updated_info = update_info(info)
if is_debug(logger_run):
# Dump only if not doing output
# (otherwise, the user can check the .updated file)
if not out and mpi.is_main_process():
logger_run.info(
"Input info updated with defaults (dumped to YAML):\n%s",
yaml_dump(sort_cosmetic(updated_info)))
# 3. If output requested, check compatibility if existing one, and dump.
# 3.1 First: model only
out.check_and_dump_info(info,
updated_info,
cache_old=True,
ignore_blocks=["sampler"])
# 3.2 Then sampler -- 1st get the last sampler mentioned in the updated.yaml
# TODO: ideally, using Minimizer would *append* to the sampler block.
# Some code already in place, but not possible at the moment.
try:
last_sampler = list(updated_info["sampler"])[-1]
last_sampler_info = {
last_sampler: updated_info["sampler"][last_sampler]
}
except (KeyError, TypeError):
raise LoggedError(logger_run, "No sampler requested.")
sampler_name, sampler_class = get_sampler_name_and_class(
last_sampler_info)
check_sampler_info((out.reload_updated_info(use_cache=True)
or {}).get("sampler"),
updated_info["sampler"],
is_resuming=out.is_resuming())
# Dump again, now including sampler info
out.check_and_dump_info(info, updated_info, check_compatible=False)
# Check if resumable run
sampler_class.check_force_resume(
out, info=updated_info["sampler"][sampler_name])
# 4. Initialize the posterior and the sampler
with Model(updated_info["params"],
updated_info["likelihood"],
updated_info.get("prior"),
updated_info.get("theory"),
packages_path=info.get("packages_path"),
timing=updated_info.get("timing"),
allow_renames=False,
stop_at_error=info.get("stop_at_error",
False)) as model:
# Re-dump the updated info, now containing parameter routes and version
updated_info = recursive_update(updated_info, model.info())
out.check_and_dump_info(None,
updated_info,
check_compatible=False)
sampler = sampler_class(
updated_info["sampler"][sampler_name],
model,
out,
name=sampler_name,
packages_path=info.get("packages_path"))
# Re-dump updated info, now also containing updates from the sampler
updated_info["sampler"][sampler_name] = \
recursive_update(updated_info["sampler"][sampler_name],
sampler.info())
out.check_and_dump_info(None,
updated_info,
check_compatible=False)
mpi.sync_processes()
if info.get("test", False):
logger_run.info(
"Test initialization successful! "
"You can probably run now without `--%s`.", "test")
return InfoSamplerTuple(updated_info, sampler)
# Run the sampler
sampler.run()
return InfoSamplerTuple(updated_info, sampler)
def initialize(self):
"""Initializes the sampler:
creates the proposal distribution and draws the initial sample."""
self.log.debug("Initializing")
for p in [
"burn_in", "max_tries", "output_every", "check_every",
"callback_every"
]:
setattr(
self, p,
read_dnumber(getattr(self, p), self.model.prior.d(),
dtype=int))
if self.callback_every is None:
self.callback_every = self.check_every
# Burning-in countdown -- the +1 accounts for the initial point (always accepted)
self.burn_in_left = self.burn_in + 1
# Max # checkpoints to wait, in case one process dies without sending MPI_ABORT
self.been_waiting = 0
self.max_waiting = max(50, self.max_tries / self.model.prior.d())
if am_single_or_primary_process():
if self.resuming and (max(self.mpi_size or 0, 1) != max(
get_mpi_size(), 1)):
self.log.error(
"Cannot resume a sample with a different number of chains: "
"was %d and now is %d.", max(self.mpi_size, 1),
max(get_mpi_size(), 1))
raise HandledException
sync_processes()
if not self.resuming and self.output:
# Delete previous files (if not "forced", the run would have already failed)
if ((os.path.abspath(self.covmat_filename()) != os.path.abspath(
str(self.covmat)))):
try:
os.remove(self.covmat_filename())
except OSError:
pass
# There may be more that chains than expected,
# if #ranks was bigger in a previous run
i = 0
while True:
i += 1
collection_filename, _ = self.output.prepare_collection(str(i))
try:
os.remove(collection_filename)
except OSError:
break
# One collection per MPI process: `name` is the MPI rank + 1
name = str(1 + (lambda r: r if r is not None else 0)(get_mpi_rank()))
self.collection = Collection(self.model,
self.output,
name=name,
resuming=self.resuming)
self.current_point = OnePoint(self.model, OutputDummy({}), name=name)
# Use standard MH steps by default
self.get_new_sample = self.get_new_sample_metropolis
# Prepare oversampling / dragging if applicable
self.effective_max_samples = self.max_samples
if self.oversample and self.drag:
self.log.error("Choose either oversampling or dragging, not both.")
raise HandledException
if self.blocking:
try:
speeds, blocks = zip(*list(self.blocking))
speeds = np.array(speeds)
except:
raise HandledException(
"Manual blocking not understood. Check documentation.")
check = compare_params_lists(
list(chain(*blocks)),
list(self.model.parameterization.sampled_params()))
duplicate = check.pop("duplicate_A", None)
missing = check.pop("B_but_not_A", None)
unknown = check.pop("A_but_not_B", None)
if duplicate:
self.log.error("Manual blocking: repeated parameters: %r",
duplicate)
raise HandledException
if missing:
self.log.error("Manual blocking: missing parameters: %r",
missing)
raise HandledException
if unknown:
self.log.error("Manual blocking: unkown parameters: %r",
unknown)
raise HandledException
int_speeds = self.oversample or self.drag
if int_speeds:
speeds = relative_to_int(speeds)
if (speeds != np.sort(speeds)).all():
self.log.warn(
"Manual blocking: speed-blocking non-optimal: sort by "
"ascending speed when possible")
else:
speeds, blocks = self.model.likelihood._speeds_of_params(
int_speeds=self.oversample or self.drag, fast_slow=self.drag)
if self.oversample:
self.oversampling_factors = speeds
self.log.info("Oversampling with factors:\n" + "\n".join([
" %d : %r" % (f, b)
for f, b in zip(self.oversampling_factors, blocks)
]))
self.i_last_slow_block = None
# No way right now to separate slow and fast
slow_params = list(self.model.parameterization.sampled_params())
elif self.drag:
# For now, no blocking inside either fast or slow: just 2 blocks
self.i_last_slow_block = 0
if np.all(speeds == speeds[0]):
self.log.error(
"All speeds are equal or too similar: cannot drag! "
"Make sure to define accurate likelihoods' speeds.")
raise HandledException
# Make the 1st factor 1:
speeds = [1, speeds[1] / speeds[0]]
# Target: dragging step taking as long as slow step
self.drag_interp_steps = self.drag * speeds[1]
# Per dragging step, the (fast) posterior is evaluated *twice*,
self.drag_interp_steps /= 2
self.drag_interp_steps = int(np.round(self.drag_interp_steps))
fast_params = list(chain(*blocks[1 + self.i_last_slow_block:]))
# Not too much or too little dragging
drag_limits = [(int(l) * len(fast_params) if l is not None else l)
for l in self.drag_limits]
if drag_limits[
0] is not None and self.drag_interp_steps < drag_limits[0]:
self.log.warning(
"Number of dragging steps clipped from below: was not "
"enough to efficiently explore the fast directions -- "
"avoid this limit by decreasing 'drag_limits[0]'.")
self.drag_interp_steps = drag_limits[0]
if drag_limits[
1] is not None and self.drag_interp_steps > drag_limits[1]:
self.log.warning(
"Number of dragging steps clipped from above: "
"excessive, probably inefficient, exploration of the "
"fast directions -- "
"avoid this limit by increasing 'drag_limits[1]'.")
self.drag_interp_steps = drag_limits[1]
# Re-scale steps between checkpoint and callback to the slow dimensions only
slow_params = list(chain(*blocks[:1 + self.i_last_slow_block]))
self.n_slow = len(slow_params)
for p in ["check_every", "callback_every"]:
setattr(
self, p,
int(getattr(self, p) * self.n_slow / self.model.prior.d()))
self.log.info("Dragging with oversampling per step:\n" +
"\n".join([
" %d : %r" % (f, b)
for f, b in zip([1, self.drag_interp_steps],
[blocks[0], fast_params])
]))
self.get_new_sample = self.get_new_sample_dragging
else:
self.oversampling_factors = [1 for b in blocks]
slow_params = list(self.model.parameterization.sampled_params())
self.n_slow = len(slow_params)
# Turn parameter names into indices
self.blocks = [[
list(self.model.parameterization.sampled_params()).index(p)
for p in b
] for b in blocks]
self.proposer = BlockedProposer(
self.blocks,
oversampling_factors=self.oversampling_factors,
i_last_slow_block=self.i_last_slow_block,
proposal_scale=self.proposal_scale)
# Build the initial covariance matrix of the proposal, or load from checkpoint
if self.resuming:
covmat = np.loadtxt(self.covmat_filename())
self.log.info("Covariance matrix from checkpoint.")
else:
covmat = self.initial_proposal_covmat(slow_params=slow_params)
self.log.info("Initial covariance matrix.")
self.log.debug(
"Sampling with covmat:\n%s",
DataFrame(
covmat,
columns=self.model.parameterization.sampled_params(),
index=self.model.parameterization.sampled_params()).to_string(
line_width=_line_width))
self.proposer.set_covariance(covmat)
# Prepare callback function
if self.callback_function is not None:
self.callback_function_callable = (get_external_function(
self.callback_function))
# Useful for getting last points added inside callback function
self.last_point_callback = 0
def initialize(self):
"""Initializes the sampler:
creates the proposal distribution and draws the initial sample."""
if not self.model.prior.d():
raise LoggedError(self.log,
"No parameters being varied for sampler")
self.log.debug("Initializing")
# MARKED FOR DEPRECATION IN v3.0
if getattr(self, "oversample", None) is not None:
self.log.warning(
"*DEPRECATION*: `oversample` will be deprecated in the "
"next version. Oversampling is now requested by setting "
"`oversample_power` > 0.")
# END OF DEPRECATION BLOCK
# MARKED FOR DEPRECATION IN v3.0
if getattr(self, "check_every", None) is not None:
self.log.warning(
"*DEPRECATION*: `check_every` will be deprecated in the "
"next version. Please use `learn_every` instead.")
# BEHAVIOUR TO BE REPLACED BY ERROR:
self.learn_every = getattr(self, "check_every")
# END OF DEPRECATION BLOCK
if self.callback_every is None:
self.callback_every = self.learn_every
self._quants_d_units = []
for q in ["max_tries", "learn_every", "callback_every", "burn_in"]:
number = NumberWithUnits(getattr(self, q), "d", dtype=int)
self._quants_d_units.append(number)
setattr(self, q, number)
self.output_every = NumberWithUnits(self.output_every, "s", dtype=int)
if is_main_process():
if self.output.is_resuming() and (max(self.mpi_size or 0, 1) !=
max(get_mpi_size(), 1)):
raise LoggedError(
self.log,
"Cannot resume a run with a different number of chains: "
"was %d and now is %d.", max(self.mpi_size, 1),
max(get_mpi_size(), 1))
if more_than_one_process():
if get_mpi().Get_version()[0] < 3:
raise LoggedError(
self.log, "MPI use requires MPI version 3.0 or "
"higher to support IALLGATHER.")
sync_processes()
# One collection per MPI process: `name` is the MPI rank + 1
name = str(1 + (lambda r: r if r is not None else 0)(get_mpi_rank()))
self.collection = Collection(self.model,
self.output,
name=name,
resuming=self.output.is_resuming())
self.current_point = OneSamplePoint(self.model)
# Use standard MH steps by default
self.get_new_sample = self.get_new_sample_metropolis
# Prepare callback function
if self.callback_function is not None:
self.callback_function_callable = (get_external_function(
self.callback_function))
# Useful for getting last points added inside callback function
self.last_point_callback = 0
# Monitoring/restore progress
if is_main_process():
cols = [
"N", "timestamp", "acceptance_rate", "Rminus1", "Rminus1_cl"
]
self.progress = DataFrame(columns=cols)
self.i_learn = 1
if self.output and not self.output.is_resuming():
with open(self.progress_filename(), "w",
encoding="utf-8") as progress_file:
progress_file.write("# " +
" ".join(self.progress.columns) + "\n")
# Get first point, to be discarded -- not possible to determine its weight
# Still, we need to compute derived parameters, since, as the proposal "blocked",
# we may be saving the initial state of some block.
# NB: if resuming but nothing was written (burn-in not finished): re-start
if self.output.is_resuming() and len(self.collection):
initial_point = (self.collection[
self.collection.sampled_params].iloc[len(self.collection) -
1]).values.copy()
logpost = -(self.collection[_minuslogpost].iloc[
len(self.collection) - 1].copy())
logpriors = -(self.collection[self.collection.minuslogprior_names].
iloc[len(self.collection) - 1].copy())
loglikes = -0.5 * (self.collection[self.collection.chi2_names].
iloc[len(self.collection) - 1].copy())
derived = (self.collection[self.collection.derived_params].iloc[
len(self.collection) - 1].values.copy())
else:
# NB: max_tries adjusted to dim instead of #cycles (blocking not computed yet)
self.max_tries.set_scale(self.model.prior.d())
self.log.info(
"Getting initial point... (this may take a few seconds)")
initial_point, logpost, logpriors, loglikes, derived = \
self.model.get_valid_point(max_tries=self.max_tries.value)
# If resuming but no existing chain, assume failed run and ignore blocking
# if speeds measurement requested
if self.output.is_resuming() and not len(self.collection) \
and self.measure_speeds:
self.blocking = None
if self.measure_speeds and self.blocking:
self.log.warning(
"Parameter blocking manually fixed: speeds will not be measured."
)
elif self.measure_speeds:
n = None if self.measure_speeds is True else int(
self.measure_speeds)
self.model.measure_and_set_speeds(n=n, discard=0)
self.set_proposer_blocking()
self.set_proposer_covmat(load=True)
self.current_point.add(initial_point,
derived=derived,
logpost=logpost,
logpriors=logpriors,
loglikes=loglikes)
self.log.info("Initial point: %s", self.current_point)
# Max #(learn+convergence checks) to wait,
# in case one process dies without sending MPI_ABORT
self.been_waiting = 0
self.max_waiting = max(50, self.max_tries.unit_value)
# Burning-in countdown -- the +1 accounts for the initial point (always accepted)
self.burn_in_left = self.burn_in.value * self.current_point.output_thin + 1
# Initial dummy checkpoint
# (needed when 1st "learn point" not reached in prev. run)
self.write_checkpoint()
def test_cosmo_run_resume_post(tmpdir, packages_path=None):
# only vary As, so fast chain. Chain does not need to converge (tested elsewhere).
info['output'] = os.path.join(tmpdir, 'testchain')
if packages_path:
info["packages_path"] = process_packages_path(packages_path)
run(info, force=True)
# note that continuing from files leads to text-file precision at read in, so a mix of
# precision in the output SampleCollection returned from run
run(info, resume=True, override={'sampler': {'mcmc': {'Rminus1_stop': 0.2}}})
updated_info, sampler = run(info['output'] + '.updated' + Extension.dill,
resume=True,
override={'sampler': {'mcmc': {'Rminus1_stop': 0.05}}})
results = mpi.allgather(sampler.products()["sample"])
samp = MCSamplesFromCobaya(updated_info, results, ignore_rows=0.2)
assert np.isclose(samp.mean('As100'), 100 * samp.mean('As'))
# post-processing
info_post: PostDict = {'add': {'params': {'h': None},
"likelihood": {"test_likelihood2": likelihood2}},
'remove': {'likelihood': ["test_likelihood"]},
'suffix': 'testpost',
'skip': 0.2, 'thin': 4
}
output_info, products = run(updated_info, override={'post': info_post}, force=True)
results2 = mpi.allgather(products["sample"])
samp2 = MCSamplesFromCobaya(output_info, results2)
samp_test = samp.copy()
samp_test.weighted_thin(4)
sigma8 = samp_test.getParams().sigma8
samp_test.reweightAddingLogLikes(-(sigma8 - 0.7) ** 2 / 0.1 ** 2
+ (sigma8 - 0.75) ** 2 / 0.07 ** 2)
assert np.isclose(samp_test.mean('sigma8'), samp2.mean('sigma8'))
# from getdist-format chain files
root = os.path.join(tmpdir, 'getdist_format')
if mpi.is_main_process():
samp.saveChainsAsText(root)
mpi.sync_processes()
from_txt = dict(updated_info, output=root)
post_from_text = dict(info_post, skip=0) # getdist already skipped
output_info, products = run(from_txt, override={'post': post_from_text}, force=True)
samp_getdist = MCSamplesFromCobaya(output_info, mpi.allgather(products["sample"]))
assert not products["stats"]["points_removed"]
assert samp2.numrows == samp_getdist.numrows
assert np.isclose(samp2.mean('sigma8'), samp_getdist.mean('sigma8'))
# again with inferred-inputs for params
info_conv = cosmomc_root_to_cobaya_info_dict(root)
# have to manually add consistent likelihoods if re-computing
info_conv['likelihood'] = info['likelihood']
info_conv['theory'] = info['theory']
post_from_text = dict(info_post, skip=0, suffix='getdist2') # getdist already skipped
output_info, products = run(info_conv, override={'post': post_from_text},
output=False)
samp_getdist2 = MCSamplesFromCobaya(output_info, mpi.allgather(products["sample"]))
assert np.isclose(samp2.mean('sigma8'), samp_getdist2.mean('sigma8'))
# from save info, no output
info_post['output'] = None
output_info, products = run({'output': info['output'], 'post': info_post}, force=True)
results3 = mpi.allgather(products["sample"])
samp3 = MCSamplesFromCobaya(output_info, results3)
assert np.isclose(samp3.mean("sigma8"), samp2.mean("sigma8"))
assert np.isclose(samp3.mean("joint"), samp2.mean("joint"))
samps4 = loadMCSamples(info['output'] + '.post.testpost')
assert np.isclose(samp3.mean("joint"), samps4.mean("joint"))
# test recover original answer swapping likelihoods back
info_revert = {'add': {'likelihood': info['likelihood']},
'remove': {'likelihood': ["test_likelihood2"]},
'suffix': 'revert',
'skip': 0, 'thin': 1,
'output': None
}
output_info, products = run({'output': info['output'] + '.post.testpost',
'post': info_revert}, force=True)
results_revert = mpi.allgather(products["sample"])
samp_revert = MCSamplesFromCobaya(output_info, results_revert)
samp_thin = MCSamplesFromCobaya(updated_info, results, ignore_rows=0.2)
samp_thin.weighted_thin(4)
assert samp_thin.numrows == samp_revert.numrows + products["stats"]["points_removed"]
if not products["stats"]["points_removed"]:
assert np.isclose(samp_revert.mean("sigma8"), samp_thin.mean("sigma8"))
else:
assert abs(samp_revert.mean("sigma8") - samp_thin.mean("sigma8")) < 0.01
assert not products["stats"]["points_removed"]
# no remove
info_post = {
'add': {'params': {'h': None}, "likelihood": {"test_likelihood2": likelihood2}},
'suffix': 'test2', 'skip': 0.2, 'thin': 4}
output_info, products = run(updated_info, override={'post': info_post}, force=True)
results2 = mpi.allgather(products["sample"])
samp2 = MCSamplesFromCobaya(output_info, results2)
assert "chi2__type1" in samp2.paramNames.list()
# check what has been saved to disk is consistent
samps4 = loadMCSamples(updated_info['output'] + '.post.test2')
assert samp2.paramNames.list() == samps4.paramNames.list()
assert np.isclose(samp2.mean("sigma8"), samps4.mean("sigma8"))
# adding new theory derived
info_post['add']['theory'] = {'new_param_theory': BTheory}
output_info, products = run(updated_info, override={'post': info_post}, output=False)
results3 = mpi.allgather(products["sample"])
samp3 = MCSamplesFromCobaya(output_info, results3)
assert np.isclose(samp3.mean("sigma8"), samp2.mean("sigma8"))
assert np.isclose(samp3.mean("As1000"), samp2.mean("As") * 1000)
info_post['add']['theory'] = {'new_param_theory': CTheory}
with pytest.raises(LoggedError) as e, NoLogging(logging.ERROR):
run(updated_info, override={'post': info_post}, output=False)
assert 'Parameter AsX no known value' in str(e)
