def get_best_covmat_ext(packages_path, params_info, likelihoods_info, random_state,
cached=True) -> Optional[dict]:
"""
Actual covmat finder used by `get_best_covmat`. Call directly for more control on
the parameters used.
Returns the same dict as `get_best_covmat`, except for the covariance matrix itself.
"""
global _loaded_covmats_database
covmats_database = (
_loaded_covmats_database or get_covmat_database(packages_path, cached=cached))
_loaded_covmats_database = covmats_database
# Prepare params and likes aliases
params_renames = set(chain(*[
[p] + str_to_list(info.get("renames", [])) for p, info in
params_info.items()]))
likes_renames = set(chain(*[[like] + str_to_list((info or {}).get("aliases", []))
for like, info in likelihoods_info.items()]))
delimiters = r"[_\.]"
likes_regexps = [re.compile(delimiters + re.escape(_like) + delimiters)
for _like in likes_renames]
# Match number of params
score_params = (
lambda covmat: len(set(covmat["params"]).intersection(params_renames)))
best_p = get_best_score(covmats_database, score_params)
if not best_p:
log.warning(
"No covariance matrix found including at least one of the given parameters")
return None
# Match likelihood names / keywords
# No debug print here: way too many!
score_likes = (
lambda covmat: len([0 for r in likes_regexps if r.search(covmat["name"])]))
best_p_l = get_best_score(best_p, score_likes)
if is_debug(log):
log.debug("Subset based on params + likes:\n - " +
"\n - ".join([b["name"] for b in best_p_l]))
# Finally, in case there is more than one, select shortest #params and name (simpler!)
# #params first, to avoid extended models with shorter covmat name
def score_simpler_params(covmat):
return -len(covmat["params"])
best_p_l_sp = get_best_score(best_p_l, score_simpler_params)
if is_debug(log):
log.debug("Subset based on params + likes + fewest params:\n - " +
"\n - ".join([b["name"] for b in best_p_l_sp]))
score_simpler_name = (
lambda covmat: -len(covmat["name"].replace("_", " ").replace("-", " ").split()))
best_p_l_sp_sn = get_best_score(best_p_l_sp, score_simpler_name)
if is_debug(log):
log.debug("Subset based on params + likes + fewest params + shortest name:\n - " +
"\n - ".join([b["name"] for b in best_p_l_sp_sn]))
# if there is more than one (unlikely), just pick one at random
if len(best_p_l_sp_sn) > 1:
log.warning("WARNING: >1 possible best covmats: %r",
[b["name"] for b in best_p_l_sp_sn])
random_state = np.random.default_rng(random_state)
return best_p_l_sp_sn[random_state.choice(range(len(best_p_l_sp_sn)))].copy()
def get_sampler(info_sampler: SamplersDict,
model: Model,
output: Optional[Output] = None,
packages_path: Optional[str] = None) -> 'Sampler':
assert isinstance(info_sampler, Mapping), (
"The first argument must be a dictionary with the info needed for the sampler. "
"If you were trying to pass the name of an input file instead, "
"load it first with 'cobaya.input.load_input', "
"or, if you were passing a yaml string, load it with 'cobaya.yaml.yaml_load'."
)
logger_sampler = get_logger(__name__)
info_sampler = deepcopy_where_possible(info_sampler)
if output is None:
output = OutputDummy()
# Check and update info
check_sane_info_sampler(info_sampler)
updated_info_sampler = update_info({"sampler": info_sampler
})["sampler"] # type: ignore
if is_debug(logger_sampler):
logger_sampler.debug(
"Input info updated with defaults (dumped to YAML):\n%s",
yaml_dump(updated_info_sampler))
# Get sampler class & check resume/force compatibility
sampler_name, sampler_class = get_sampler_name_and_class(
updated_info_sampler, logger=logger_sampler)
check_sampler_info((output.reload_updated_info(use_cache=True)
or {}).get("sampler"),
updated_info_sampler,
is_resuming=output.is_resuming())
# Check if resumable run
sampler_class.check_force_resume(output,
info=updated_info_sampler[sampler_name])
# Instantiate the sampler
sampler_instance = sampler_class(updated_info_sampler[sampler_name],
model,
output,
packages_path=packages_path)
# If output, dump updated
if output:
to_dump = model.info()
to_dump["sampler"] = {sampler_name: sampler_instance.info()}
to_dump["output"] = os.path.join(output.folder, output.prefix)
output.check_and_dump_info(None, to_dump, check_compatible=False)
return sampler_instance
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)