def from_chemsys(cls, chemsys):
"""
Class factory method for constructing campaign from
chemsys.
Args:
chemsys (str): chemical system for the campaign
Returns:
(ProtoDFTCampaign): Standard proto-dft campaign from
the chemical system
"""
s3_prefix = "proto-dft-2/runs/{}".format(chemsys)
# Initialize s3
dumpfn({
"started": datetime.now().isoformat(),
"version": __version__
}, "start.json")
s3_sync(s3_bucket=CAMD_S3_BUCKET, s3_prefix=s3_prefix, sync_path='.')
# Get structure domain
element_list = chemsys.split('-')
max_coeff, charge_balanced = heuristic_setup(element_list)
domain = StructureDomain.from_bounds(element_list,
charge_balanced=charge_balanced,
n_max_atoms=20,
**{'grid': range(1, max_coeff)})
candidate_data = domain.candidates()
# Dump structure/candidate data
with open('candidate_data.pickle', 'wb') as f:
pickle.dump(candidate_data, f)
# Set up agents and loop parameters
agent = AgentStabilityAdaBoost(
model=MLPRegressor(hidden_layer_sizes=(84, 50)),
n_query=10,
hull_distance=0.2,
exploit_fraction=1.0,
uncertainty=True,
alpha=0.5,
diversify=True,
n_estimators=20)
analyzer = StabilityAnalyzer(hull_distance=0.2)
experiment = OqmdDFTonMC1(timeout=30000)
seed_data = load_dataframe("oqmd1.2_exp_based_entries_featurized_v2")
# Construct and start loop
return cls(candidate_data=candidate_data,
agent=agent,
experiment=experiment,
analyzer=analyzer,
seed_data=seed_data,
heuristic_stopper=5,
s3_prefix="proto-dft/runs/{}".format(chemsys))
def s3_sync(self):
"""
Syncs current run to s3_prefix and bucket
"""
s3_sync(self.s3_bucket, self.s3_prefix, self.path)
def run_proto_dft_campaign(chemsys, s3_prefix="proto-dft-2"):
"""
Args:
chemsys (str): chemical system for the campaign
s3_prefix (str): s3 prefix to sync to
Returns:
(bool): True if run exits
"""
s3_prefix = "{}/runs/{}".format(s3_prefix, chemsys)
# Initialize s3
dumpfn({"started": datetime.now().isoformat(),
"version": __version__}, "start.json")
s3_sync(s3_bucket=CAMD_S3_BUCKET, s3_prefix=s3_prefix, sync_path='.')
try:
# Get structure domain
element_list = chemsys.split('-')
g_max, charge_balanced = heuristic_setup(element_list)
domain = StructureDomain.from_bounds(
element_list, charge_balanced=charge_balanced,
n_max_atoms=20, **{'grid': range(1, g_max)})
candidate_data = domain.candidates()
structure_dict = domain.hypo_structures_dict
# Dump structure/candidate data
with open('candidate_data.pickle', 'wb') as f:
pickle.dump(candidate_data, f)
with open('structure_dict.pickle', 'wb') as f:
pickle.dump(structure_dict, f)
# Set up agents and loop parameters
agent = AgentStabilityAdaBoost
agent_params = {
'ml_algorithm': MLPRegressor,
'ml_algorithm_params': {'hidden_layer_sizes': (84, 50)},
'n_query': 10,
'hull_distance': 0.2, # Distance to hull to consider a finding as discovery (eV/atom)
'exploit_fraction': 1.0, # Fraction to exploit (rest will be explored -- randomly picked)
'uncertainty': True,
'alpha': 0.5,
'diversify': True,
'n_estimators': 20
}
analyzer = AnalyzeStability
analyzer_params = {'hull_distance': 0.2} # analysis criterion (need not be exactly same as agent's goal)
experiment = OqmdDFTonMC1
experiment_params = {'structure_dict': structure_dict, 'candidate_data': candidate_data, 'timeout': 30000}
experiment_params.update({'timeout': 30000})
finalizer = FinalizeQqmdCampaign
finalizer_params = {'hull_distance': 0.2}
n_max_iter = n_max_iter_heuristics(len(candidate_data), 10)
# Construct and start loop
new_loop = Loop(
candidate_data, agent, experiment, analyzer, agent_params=agent_params,
analyzer_params=analyzer_params, experiment_params=experiment_params,
finalizer=finalizer, finalizer_params=finalizer_params, heuristic_stopper=5,
s3_prefix=s3_prefix)
new_loop.auto_loop_in_directories(
n_iterations=n_max_iter, timeout=10, monitor=True,
initialize=True, with_icsd=True)
except Exception as e:
error_msg = {"error": "{}".format(e),
"traceback": traceback.format_exc()}
dumpfn(error_msg, "error.json")
dumpfn({"status": "error"}, "job_status.json")
s3_sync(s3_bucket=CAMD_S3_BUCKET, s3_prefix=s3_prefix, sync_path='.')
return True
def from_chemsys(cls,
chemsys,
prefix="proto-dft-2/runs",
n_max_atoms=20,
agent=None,
analyzer=None,
experiment=None,
log_file="campaign.log",
cloudwatch_group="/camd/worker/dev/"):
"""
Class factory method for constructing campaign from
chemsys.
Args:
chemsys (str): chemical system for the campaign
prefix (str): prefix for s3
n_max_atoms (int): number of maximum atoms
agent (Agent): agent for stability campaign
analyzer (Analyzer): analyzer for stability campaign
experiment (Agent): experiment for stability campaign
log_file (str): log filename
cloudwatch_group (str): cloudwatch group to log to
Returns:
(ProtoDFTCampaign): Standard proto-dft campaign from
the chemical system
"""
logger = logging.Logger("camd")
logger.setLevel("INFO")
file_handler = logging.FileHandler(log_file)
cw_handler = CloudWatchLogHandler(log_group=cloudwatch_group,
stream_name=chemsys)
logger.addHandler(file_handler)
logger.addHandler(cw_handler)
logger.addHandler(logging.StreamHandler())
logger.info(
"Starting campaign factory from_chemsys {}".format(chemsys))
s3_prefix = "{}/{}".format(prefix, chemsys)
# Initialize s3
dumpfn({
"started": datetime.now().isoformat(),
"version": __version__
}, "start.json")
s3_sync(s3_bucket=CAMD_S3_BUCKET, s3_prefix=s3_prefix, sync_path='.')
# Get structure domain
element_list = chemsys.split('-')
max_coeff, charge_balanced = heuristic_setup(element_list)
domain = StructureDomain.from_bounds(element_list,
charge_balanced=charge_balanced,
n_max_atoms=n_max_atoms,
**{'grid': range(1, max_coeff)})
candidate_data = domain.candidates()
# Dump structure/candidate data
with open('candidate_data.pickle', 'wb') as f:
pickle.dump(candidate_data, f)
s3_sync(s3_bucket=CAMD_S3_BUCKET, s3_prefix=s3_prefix, sync_path='.')
logger.info("Candidates generated")
# Set up agents and loop parameters
agent = agent or AgentStabilityAdaBoost(
model=MLPRegressor(hidden_layer_sizes=(84, 50)),
n_query=10,
hull_distance=0.2,
exploit_fraction=1.0,
uncertainty=True,
alpha=0.5,
diversify=True,
n_estimators=20)
analyzer = analyzer or StabilityAnalyzer(hull_distance=0.2)
experiment = experiment or OqmdDFTonMC1(timeout=30000)
seed_data = load_dataframe("oqmd1.2_exp_based_entries_featurized_v2")
# Construct and start loop
return cls(candidate_data=candidate_data,
agent=agent,
experiment=experiment,
analyzer=analyzer,
seed_data=seed_data,
heuristic_stopper=5,
s3_prefix=s3_prefix,
logger=logger)
def from_chemsys(cls,
chemsys,
prefix="proto-dft-2/runs",
n_max_atoms=20,
agent=None,
analyzer=None,
experiment=None,
log_file="campaign.log",
cloudwatch_group="/camd/worker/dev/"):
"""
Class factory method for constructing campaign from
chemsys.
Args:
chemsys (str): chemical system for the campaign
prefix (str): prefix for s3
n_max_atoms (int): number of maximum atoms
agent (Agent): agent for stability campaign
analyzer (Analyzer): analyzer for stability campaign
experiment (Agent): experiment for stability campaign
log_file (str): log filename
cloudwatch_group (str): cloudwatch group to log to
Returns:
(ProtoDFTCampaign): Standard proto-dft campaign from
the chemical system
"""
logger = logging.Logger("camd")
logger.setLevel("INFO")
file_handler = logging.FileHandler(log_file)
cw_handler = CloudWatchLogHandler(log_group=cloudwatch_group,
stream_name=chemsys)
logger.addHandler(file_handler)
logger.addHandler(cw_handler)
logger.addHandler(logging.StreamHandler())
logger.info(
"Starting campaign factory from_chemsys {}".format(chemsys))
s3_prefix = "{}/{}".format(prefix, chemsys)
# Initialize s3
dumpfn({
"started": datetime.now().isoformat(),
"version": __version__
}, "start.json")
s3_sync(s3_bucket=CAMD_S3_BUCKET, s3_prefix=s3_prefix, sync_path='.')
# Get structure domain
# Check cache
cache_key = "protosearch_cache/v1/{}/{}/candidates.pickle".format(
chemsys, n_max_atoms)
# TODO: create test of isfile
if s3_key_exists(bucket=CAMD_S3_BUCKET, key=cache_key):
logger.info("Found cached protosearch domain.")
candidate_data = pd.read_pickle("s3://{}/{}".format(
CAMD_S3_BUCKET, cache_key))
logger.info("Loaded cached {}.".format(cache_key))
else:
logger.info(
"Generating domain with max {} atoms.".format(n_max_atoms))
element_list = chemsys.split('-')
max_coeff, charge_balanced = heuristic_setup(element_list)
domain = StructureDomain.from_bounds(
element_list,
charge_balanced=charge_balanced,
n_max_atoms=n_max_atoms,
**{'grid': range(1, max_coeff)})
candidate_data = domain.candidates()
logger.info("Candidates generated")
candidate_data.to_pickle("s3://{}/{}".format(
CAMD_S3_BUCKET, cache_key))
logger.info("Cached protosearch domain at {}.".format(cache_key))
# Dump structure/candidate data
candidate_data.to_pickle("candidate_data.pickle")
s3_sync(s3_bucket=CAMD_S3_BUCKET, s3_prefix=s3_prefix, sync_path='.')
# Set up agents and loop parameters
agent = agent or AgentStabilityAdaBoost(
model=MLPRegressor(hidden_layer_sizes=(84, 50)),
n_query=10,
hull_distance=0.2,
exploit_fraction=1.0,
uncertainty=True,
alpha=0.5,
diversify=True,
n_estimators=20)
analyzer = analyzer or StabilityAnalyzer(hull_distance=0.2)
experiment = experiment or OqmdDFTonMC1(timeout=30000,
prefix_append="proto-dft")
seed_data = load_dataframe("oqmd1.2_exp_based_entries_featurized_v2")
# Load cached experiments
logger.info("Loading cached experiments")
cached_experiments = experiment.fetch_cached(candidate_data)
logger.info("Found {} experiments.".format(len(cached_experiments)))
if len(cached_experiments) > 0:
summary, seed_data = analyzer.analyze(cached_experiments,
seed_data)
# Remove cached experiments from candidate_data
candidate_space = candidate_data.index.difference(
cached_experiments.index, sort=False).tolist()
candidate_data = candidate_data.loc[candidate_space]
logger.info("Cached experiments added to seed.")
# Construct and start loop
return cls(candidate_data=candidate_data,
agent=agent,
experiment=experiment,
analyzer=analyzer,
seed_data=seed_data,
heuristic_stopper=5,
s3_prefix=s3_prefix,
logger=logger)
