def assimilate(self, old_task):
"""
Parses vasp runs. Then insert the result into the db. and return the
task_id or doc of the insertion.
Returns:
If in simulate_mode, the entire doc is returned for debugging
purposes. Else, only the task_id of the inserted doc is returned.
"""
path = old_task["dir_name"] # AJ: get dir name from task
d = self.get_task_doc(path, self.parse_dos, self.additional_fields)
d["dir_name_full"] = d["dir_name"].split(":")[1]
d["dir_name"] = get_block_part(d["dir_name_full"])
if not self.simulate:
# Perform actual insertion into db. Because db connections cannot
# be pickled, every insertion needs to create a new connection
# to the db.
conn = MongoClient(self.host, self.port)
db = conn[self.database]
if self.user:
db.authenticate(self.user, self.password)
coll = db[self.collection]
# Insert dos data into gridfs and then remove it from the dict.
# DOS data tends to be above the 4Mb limit for mongo docs. A ref
# to the dos file is in the dos_fs_id.
result = coll.find_one({"dir_name": d["dir_name"]})
if result is None or self.update_duplicates:
if self.parse_dos and "calculations" in d:
for calc in d["calculations"]:
if "dos" in calc:
dos = json.dumps(calc["dos"], cls=MontyEncoder)
fs = gridfs.GridFS(db, "dos_fs")
dosid = fs.put(dos)
calc["dos_fs_id"] = dosid
del calc["dos"]
d["last_updated"] = datetime.datetime.today()
if result is None:
d["task_id"] = "mp-{}".format(old_task["task_id"]) # AJ: old task_id is new
logger.info("Inserting {} with taskid = {}".format(d["dir_name"], d["task_id"]))
elif self.update_duplicates:
d["task_id"] = result["task_id"]
logger.info("Updating {} with taskid = {}".format(d["dir_name"], d["task_id"]))
# Fireworks processing
self.process_fw(old_task, d)
coll.update({"dir_name": d["dir_name"]}, {"$set": d}, upsert=True)
return d["task_id"], d
else:
logger.info("Skipping duplicate {}".format(d["dir_name"]))
return result["task_id"], result
else:
d["task_id"] = 0
logger.info("Simulated insert into database for {} with task_id {}".format(d["dir_name"], d["task_id"]))
return 0, d
def run_task(self, fw_spec):
# write a file containing the formula and task_type for somewhat
# easier file system browsing
self._write_formula_file(fw_spec)
# TODO: make this better - is there a way to load an environment
# variable as the VASP_EXE?
if 'nid' in socket.gethostname(): # hopper compute nodes
# TODO: can base ncores on FW_submit.script
v_exe = shlex.split('aprun -n 48 vasp')
gv_exe = shlex.split('aprun -n 48 gvasp')
print 'running on HOPPER'
elif 'c' in socket.gethostname(): # mendel compute nodes
# TODO: can base ncores on FW_submit.script
v_exe = shlex.split('mpirun -n 32 vasp')
gv_exe = shlex.split('aprun -n 32 gvasp')
print 'running on MENDEL'
else:
raise ValueError('Unrecognized host!')
for job in self.jobs:
job.vasp_cmd = v_exe
job.gamma_vasp_cmd = gv_exe
logging.basicConfig(level=logging.DEBUG)
c = Custodian(self.handlers, self.jobs, self.max_errors)
custodian_out = c.run()
all_errors = set()
for run in custodian_out:
for correction in run['corrections']:
all_errors.update(correction['errors'])
stored_data = {'error_list': list(all_errors)}
update_spec = {
'prev_vasp_dir': get_block_part(os.getcwd()),
'prev_task_type': fw_spec['task_type'],
'mpsnl': fw_spec['mpsnl'],
'snlgroup_id': fw_spec['snlgroup_id'],
'run_tags': fw_spec['run_tags']
}
return FWAction(stored_data=stored_data, update_spec=update_spec)
def run_task(self, fw_spec):
# write a file containing the formula and task_type for somewhat
# easier file system browsing
self._write_formula_file(fw_spec)
# TODO: make this better - is there a way to load an environment
# variable as the VASP_EXE?
if 'nid' in socket.gethostname(): # hopper compute nodes
# TODO: can base ncores on FW_submit.script
v_exe = shlex.split('aprun -n 48 vasp')
gv_exe = shlex.split('aprun -n 48 gvasp')
print 'running on HOPPER'
elif 'c' in socket.gethostname(): # mendel compute nodes
# TODO: can base ncores on FW_submit.script
v_exe = shlex.split('mpirun -n 32 vasp')
gv_exe = shlex.split('aprun -n 32 gvasp')
print 'running on MENDEL'
else:
raise ValueError('Unrecognized host!')
for job in self.jobs:
job.vasp_cmd = v_exe
job.gamma_vasp_cmd = gv_exe
logging.basicConfig(level=logging.DEBUG)
c = Custodian(self.handlers, self.jobs, self.max_errors)
custodian_out = c.run()
all_errors = set()
for run in custodian_out:
for correction in run['corrections']:
all_errors.update(correction['errors'])
stored_data = {'error_list': list(all_errors)}
update_spec = {'prev_vasp_dir': get_block_part(os.getcwd()),
'prev_task_type': fw_spec['task_type'],
'mpsnl': fw_spec['mpsnl'],
'snlgroup_id': fw_spec['snlgroup_id'],
'run_tags': fw_spec['run_tags']}
return FWAction(stored_data=stored_data, update_spec=update_spec)
def run_task(self, fw_spec):
# get the band structure and nelect from files
"""
prev_dir = get_loc(fw_spec['prev_vasp_dir'])
vasprun_loc = zpath(os.path.join(prev_dir, 'vasprun.xml'))
kpoints_loc = zpath(os.path.join(prev_dir, 'KPOINTS'))
vr = Vasprun(vasprun_loc)
bs = vr.get_band_structure(kpoints_filename=kpoints_loc)
"""
# get the band structure and nelect from DB
block_part = get_block_part(fw_spec['prev_vasp_dir'])
db_dir = os.environ['DB_LOC']
assert isinstance(db_dir, object)
db_path = os.path.join(db_dir, 'tasks_db.json')
with open(db_path) as f:
creds = json.load(f)
connection = MongoClient(creds['host'], creds['port'])
tdb = connection[creds['database']]
tdb.authenticate(creds['admin_user'], creds['admin_password'])
m_task = tdb.tasks.find_one({"dir_name": block_part}, {"calculations": 1, "task_id": 1})
nelect = m_task['calculations'][0]['input']['parameters']['NELECT']
bs_id = m_task['calculations'][0]['band_structure_fs_id']
print bs_id, type(bs_id)
fs = gridfs.GridFS(tdb, 'band_structure_fs')
bs_dict = json.loads(fs.get(bs_id).read())
bs_dict['structure'] = m_task['calculations'][0]['output']['crystal']
bs = BandStructure.from_dict(bs_dict)
print 'Band Structure found:', bool(bs)
print nelect
# run Boltztrap
runner = BoltztrapRunner(bs, nelect)
dir = runner.run(path_dir=os.getcwd())
# put the data in the database
bta = BoltztrapAnalyzer.from_files(dir)
data = bta.to_dict
data.update(get_meta_from_structure(bs._structure))
data['snlgroup_id'] = fw_spec['snlgroup_id']
data['run_tags'] = fw_spec['run_tags']
data['snl'] = fw_spec['mpsnl']
data['dir_name_full'] = dir
data['dir_name'] = get_block_part(dir)
data['task_id'] = m_task['task_id']
data['hall'] = {} # remove because it is too large and not useful
data['hall_doping'] = {} # remove because it is too large and not useful
tdb.boltztrap.insert(clean_json(data))
update_spec = {'prev_vasp_dir': fw_spec['prev_vasp_dir'],
'boltztrap_dir': os.getcwd(),
'prev_task_type': fw_spec['task_type'],
'mpsnl': fw_spec['mpsnl'],
'snlgroup_id': fw_spec['snlgroup_id'],
'run_tags': fw_spec['run_tags'], 'parameters': fw_spec.get('parameters')}
return FWAction(update_spec=update_spec)
def run_task(self, fw_spec):
# import here to prevent import errors in bigger MPCollab
# get the band structure and nelect from files
"""
prev_dir = get_loc(fw_spec['prev_vasp_dir'])
vasprun_loc = zpath(os.path.join(prev_dir, 'vasprun.xml'))
kpoints_loc = zpath(os.path.join(prev_dir, 'KPOINTS'))
vr = Vasprun(vasprun_loc)
bs = vr.get_band_structure(kpoints_filename=kpoints_loc)
"""
filename = get_slug(
'JOB--' + fw_spec['mpsnl'].structure.composition.reduced_formula + '--'
+ fw_spec['task_type'])
with open(filename, 'w+') as f:
f.write('')
# get the band structure and nelect from DB
block_part = get_block_part(fw_spec['prev_vasp_dir'])
db_dir = os.environ['DB_LOC']
assert isinstance(db_dir, object)
db_path = os.path.join(db_dir, 'tasks_db.json')
with open(db_path) as f:
creds = json.load(f)
connection = MongoClient(creds['host'], creds['port'])
tdb = connection[creds['database']]
tdb.authenticate(creds['admin_user'], creds['admin_password'])
props = {"calculations": 1, "task_id": 1, "state": 1, "pseudo_potential": 1, "run_type": 1, "is_hubbard": 1, "hubbards": 1, "unit_cell_formula": 1}
m_task = tdb.tasks.find_one({"dir_name": block_part}, props)
if not m_task:
time.sleep(60) # only thing to think of is wait for DB insertion(?)
m_task = tdb.tasks.find_one({"dir_name": block_part}, props)
if not m_task:
raise ValueError("Could not find task with dir_name: {}".format(block_part))
if m_task['state'] != 'successful':
raise ValueError("Cannot run Boltztrap; parent job unsuccessful")
nelect = m_task['calculations'][0]['input']['parameters']['NELECT']
bs_id = m_task['calculations'][0]['band_structure_fs_id']
print bs_id, type(bs_id)
fs = gridfs.GridFS(tdb, 'band_structure_fs')
bs_dict = json.loads(fs.get(bs_id).read())
bs_dict['structure'] = m_task['calculations'][0]['output']['crystal']
bs = BandStructure.from_dict(bs_dict)
print 'Band Structure found:', bool(bs)
print nelect
# run Boltztrap
runner = BoltztrapRunner(bs, nelect)
dir = runner.run(path_dir=os.getcwd())
# put the data in the database
bta = BoltztrapAnalyzer.from_files(dir)
# 8/21/15 - Anubhav removed fs_id (also see line further below, ted['boltztrap_full_fs_id'] ...)
# 8/21/15 - this is to save space in MongoDB, as well as non-use of full Boltztrap output (vs rerun)
"""
data = bta.as_dict()
data.update(get_meta_from_structure(bs._structure))
data['snlgroup_id'] = fw_spec['snlgroup_id']
data['run_tags'] = fw_spec['run_tags']
data['snl'] = fw_spec['mpsnl']
data['dir_name_full'] = dir
data['dir_name'] = get_block_part(dir)
data['task_id'] = m_task['task_id']
del data['hall'] # remove because it is too large and not useful
fs = gridfs.GridFS(tdb, "boltztrap_full_fs")
btid = fs.put(json.dumps(jsanitize(data)))
"""
# now for the "sanitized" data
ted = bta.as_dict()
del ted['seebeck']
del ted['hall']
del ted['kappa']
del ted['cond']
# ted['boltztrap_full_fs_id'] = btid
ted['snlgroup_id'] = fw_spec['snlgroup_id']
ted['run_tags'] = fw_spec['run_tags']
ted['snl'] = fw_spec['mpsnl'].as_dict()
ted['dir_name_full'] = dir
ted['dir_name'] = get_block_part(dir)
ted['task_id'] = m_task['task_id']
ted['pf_doping'] = bta.get_power_factor(output='tensor', relaxation_time=self.TAU)
ted['zt_doping'] = bta.get_zt(output='tensor', relaxation_time=self.TAU, kl=self.KAPPAL)
ted['pf_eigs'] = self.get_eigs(ted, 'pf_doping')
ted['pf_best'] = self.get_extreme(ted, 'pf_eigs')
ted['pf_best_dope18'] = self.get_extreme(ted, 'pf_eigs', max_didx=3)
ted['pf_best_dope19'] = self.get_extreme(ted, 'pf_eigs', max_didx=4)
ted['zt_eigs'] = self.get_eigs(ted, 'zt_doping')
ted['zt_best'] = self.get_extreme(ted, 'zt_eigs')
ted['zt_best_dope18'] = self.get_extreme(ted, 'zt_eigs', max_didx=3)
ted['zt_best_dope19'] = self.get_extreme(ted, 'zt_eigs', max_didx=4)
ted['seebeck_eigs'] = self.get_eigs(ted, 'seebeck_doping')
ted['seebeck_best'] = self.get_extreme(ted, 'seebeck_eigs')
ted['seebeck_best_dope18'] = self.get_extreme(ted, 'seebeck_eigs', max_didx=3)
ted['seebeck_best_dope19'] = self.get_extreme(ted, 'seebeck_eigs', max_didx=4)
ted['cond_eigs'] = self.get_eigs(ted, 'cond_doping')
ted['cond_best'] = self.get_extreme(ted, 'cond_eigs')
ted['cond_best_dope18'] = self.get_extreme(ted, 'cond_eigs', max_didx=3)
ted['cond_best_dope19'] = self.get_extreme(ted, 'cond_eigs', max_didx=4)
ted['kappa_eigs'] = self.get_eigs(ted, 'kappa_doping')
ted['kappa_best'] = self.get_extreme(ted, 'kappa_eigs', maximize=False)
ted['kappa_best_dope18'] = self.get_extreme(ted, 'kappa_eigs', maximize=False, max_didx=3)
ted['kappa_best_dope19'] = self.get_extreme(ted, 'kappa_eigs', maximize=False, max_didx=4)
try:
from mpcollab.thermoelectrics.boltztrap_TE import BoltzSPB
bzspb = BoltzSPB(ted)
maxpf_p = bzspb.get_maximum_power_factor('p', temperature=0, tau=1E-14, ZT=False, kappal=0.5,\
otherprops=('get_seebeck_mu_eig', 'get_conductivity_mu_eig', \
'get_thermal_conductivity_mu_eig', 'get_average_eff_mass_tensor_mu'))
maxpf_n = bzspb.get_maximum_power_factor('n', temperature=0, tau=1E-14, ZT=False, kappal=0.5,\
otherprops=('get_seebeck_mu_eig', 'get_conductivity_mu_eig', \
'get_thermal_conductivity_mu_eig', 'get_average_eff_mass_tensor_mu'))
maxzt_p = bzspb.get_maximum_power_factor('p', temperature=0, tau=1E-14, ZT=True, kappal=0.5, otherprops=('get_seebeck_mu_eig', 'get_conductivity_mu_eig', \
'get_thermal_conductivity_mu_eig', 'get_average_eff_mass_tensor_mu'))
maxzt_n = bzspb.get_maximum_power_factor('n', temperature=0, tau=1E-14, ZT=True, kappal=0.5, otherprops=('get_seebeck_mu_eig', 'get_conductivity_mu_eig', \
'get_thermal_conductivity_mu_eig', 'get_average_eff_mass_tensor_mu'))
ted['zt_best_finemesh'] = {'p': maxzt_p, 'n': maxzt_n}
ted['pf_best_finemesh'] = {'p': maxpf_p, 'n': maxpf_n}
except:
import traceback
traceback.print_exc()
print 'COULD NOT GET FINE MESH DATA'
# add is_compatible
mpc = MaterialsProjectCompatibility("Advanced")
try:
func = m_task["pseudo_potential"]["functional"]
labels = m_task["pseudo_potential"]["labels"]
symbols = ["{} {}".format(func, label) for label in labels]
parameters = {"run_type": m_task["run_type"],
"is_hubbard": m_task["is_hubbard"],
"hubbards": m_task["hubbards"],
"potcar_symbols": symbols}
entry = ComputedEntry(Composition(m_task["unit_cell_formula"]),
0.0, 0.0, parameters=parameters,
entry_id=m_task["task_id"])
ted["is_compatible"] = bool(mpc.process_entry(entry))
except:
traceback.print_exc()
print 'ERROR in getting compatibility, task_id: {}'.format(m_task["task_id"])
ted["is_compatible"] = None
tdb.boltztrap.insert(jsanitize(ted))
update_spec = {'prev_vasp_dir': fw_spec['prev_vasp_dir'],
'boltztrap_dir': os.getcwd(),
'prev_task_type': fw_spec['task_type'],
'mpsnl': fw_spec['mpsnl'].as_dict(),
'snlgroup_id': fw_spec['snlgroup_id'],
'run_tags': fw_spec['run_tags'], 'parameters': fw_spec.get('parameters')}
return FWAction(update_spec=update_spec)
def assimilate(self, old_task):
"""
Parses vasp runs. Then insert the result into the db. and return the
task_id or doc of the insertion.
Returns:
If in simulate_mode, the entire doc is returned for debugging
purposes. Else, only the task_id of the inserted doc is returned.
"""
path = old_task['dir_name'] # AJ: get dir name from task
d = self.get_task_doc(path, self.parse_dos,
self.additional_fields)
d["dir_name_full"] = d["dir_name"].split(":")[1]
d["dir_name"] = get_block_part(d["dir_name_full"])
if not self.simulate:
# Perform actual insertion into db. Because db connections cannot
# be pickled, every insertion needs to create a new connection
# to the db.
conn = MongoClient(self.host, self.port)
db = conn[self.database]
if self.user:
db.authenticate(self.user, self.password)
coll = db[self.collection]
# Insert dos data into gridfs and then remove it from the dict.
# DOS data tends to be above the 4Mb limit for mongo docs. A ref
# to the dos file is in the dos_fs_id.
result = coll.find_one({"dir_name": d["dir_name"]})
if result is None or self.update_duplicates:
if self.parse_dos and "calculations" in d:
for calc in d["calculations"]:
if "dos" in calc:
dos = json.dumps(calc["dos"])
fs = gridfs.GridFS(db, "dos_fs")
dosid = fs.put(dos)
calc["dos_fs_id"] = dosid
del calc["dos"]
d["last_updated"] = datetime.datetime.today()
if result is None:
d["task_id"] = "mp-{}".format(old_task['task_id']) # AJ: old task_id is new
logger.info("Inserting {} with taskid = {}"
.format(d["dir_name"], d["task_id"]))
elif self.update_duplicates:
d["task_id"] = result["task_id"]
logger.info("Updating {} with taskid = {}"
.format(d["dir_name"], d["task_id"]))
#Fireworks processing
self.process_fw(old_task, d)
coll.update({"dir_name": d["dir_name"]}, {"$set": d},
upsert=True)
return d["task_id"], d
else:
logger.info("Skipping duplicate {}".format(d["dir_name"]))
return result["task_id"], result
else:
d["task_id"] = 0
logger.info("Simulated insert into database for {} with task_id {}"
.format(d["dir_name"], d["task_id"]))
return 0, d
def run_task(self, fw_spec):
# import here to prevent import errors in bigger MPCollab
# get the band structure and nelect from files
"""
prev_dir = get_loc(fw_spec['prev_vasp_dir'])
vasprun_loc = zpath(os.path.join(prev_dir, 'vasprun.xml'))
kpoints_loc = zpath(os.path.join(prev_dir, 'KPOINTS'))
vr = Vasprun(vasprun_loc)
bs = vr.get_band_structure(kpoints_filename=kpoints_loc)
"""
filename = get_slug(
'JOB--' + fw_spec['mpsnl'].structure.composition.reduced_formula +
'--' + fw_spec['task_type'])
with open(filename, 'w+') as f:
f.write('')
# get the band structure and nelect from DB
block_part = get_block_part(fw_spec['prev_vasp_dir'])
db_dir = os.environ['DB_LOC']
assert isinstance(db_dir, object)
db_path = os.path.join(db_dir, 'tasks_db.json')
with open(db_path) as f:
creds = json.load(f)
connection = MongoClient(creds['host'], creds['port'])
tdb = connection[creds['database']]
tdb.authenticate(creds['admin_user'], creds['admin_password'])
props = {
"calculations": 1,
"task_id": 1,
"state": 1,
"pseudo_potential": 1,
"run_type": 1,
"is_hubbard": 1,
"hubbards": 1,
"unit_cell_formula": 1
}
m_task = tdb.tasks.find_one({"dir_name": block_part}, props)
if not m_task:
time.sleep(
60) # only thing to think of is wait for DB insertion(?)
m_task = tdb.tasks.find_one({"dir_name": block_part}, props)
if not m_task:
raise ValueError(
"Could not find task with dir_name: {}".format(block_part))
if m_task['state'] != 'successful':
raise ValueError(
"Cannot run Boltztrap; parent job unsuccessful")
nelect = m_task['calculations'][0]['input']['parameters']['NELECT']
bs_id = m_task['calculations'][0]['band_structure_fs_id']
print bs_id, type(bs_id)
fs = gridfs.GridFS(tdb, 'band_structure_fs')
bs_dict = json.loads(fs.get(bs_id).read())
bs_dict['structure'] = m_task['calculations'][0]['output'][
'crystal']
bs = BandStructure.from_dict(bs_dict)
print("find previous run with block_part {}".format(block_part))
print 'Band Structure found:', bool(bs)
print(bs.as_dict())
print("nelect: {}".format(nelect))
# run Boltztrap
doping = []
for d in [1e16, 1e17, 1e18, 1e19, 1e20]:
doping.extend([1 * d, 2.5 * d, 5 * d, 7.5 * d])
doping.append(1e21)
runner = BoltztrapRunner(bs, nelect, doping=doping)
dir = runner.run(path_dir=os.getcwd())
# put the data in the database
bta = BoltztrapAnalyzer.from_files(dir)
# 8/21/15 - Anubhav removed fs_id (also see line further below, ted['boltztrap_full_fs_id'] ...)
# 8/21/15 - this is to save space in MongoDB, as well as non-use of full Boltztrap output (vs rerun)
"""
data = bta.as_dict()
data.update(get_meta_from_structure(bs._structure))
data['snlgroup_id'] = fw_spec['snlgroup_id']
data['run_tags'] = fw_spec['run_tags']
data['snl'] = fw_spec['mpsnl']
data['dir_name_full'] = dir
data['dir_name'] = get_block_part(dir)
data['task_id'] = m_task['task_id']
del data['hall'] # remove because it is too large and not useful
fs = gridfs.GridFS(tdb, "boltztrap_full_fs")
btid = fs.put(json.dumps(jsanitize(data)))
"""
# now for the "sanitized" data
ted = bta.as_dict()
del ted['seebeck']
del ted['hall']
del ted['kappa']
del ted['cond']
# ted['boltztrap_full_fs_id'] = btid
ted['snlgroup_id'] = fw_spec['snlgroup_id']
ted['run_tags'] = fw_spec['run_tags']
ted['snl'] = fw_spec['mpsnl'].as_dict()
ted['dir_name_full'] = dir
ted['dir_name'] = get_block_part(dir)
ted['task_id'] = m_task['task_id']
ted['pf_doping'] = bta.get_power_factor(output='tensor',
relaxation_time=self.TAU)
ted['zt_doping'] = bta.get_zt(output='tensor',
relaxation_time=self.TAU,
kl=self.KAPPAL)
ted['pf_eigs'] = self.get_eigs(ted, 'pf_doping')
ted['pf_best'] = self.get_extreme(ted, 'pf_eigs')
ted['pf_best_dope18'] = self.get_extreme(ted,
'pf_eigs',
max_didx=3)
ted['pf_best_dope19'] = self.get_extreme(ted,
'pf_eigs',
max_didx=4)
ted['zt_eigs'] = self.get_eigs(ted, 'zt_doping')
ted['zt_best'] = self.get_extreme(ted, 'zt_eigs')
ted['zt_best_dope18'] = self.get_extreme(ted,
'zt_eigs',
max_didx=3)
ted['zt_best_dope19'] = self.get_extreme(ted,
'zt_eigs',
max_didx=4)
ted['seebeck_eigs'] = self.get_eigs(ted, 'seebeck_doping')
ted['seebeck_best'] = self.get_extreme(ted, 'seebeck_eigs')
ted['seebeck_best_dope18'] = self.get_extreme(ted,
'seebeck_eigs',
max_didx=3)
ted['seebeck_best_dope19'] = self.get_extreme(ted,
'seebeck_eigs',
max_didx=4)
ted['cond_eigs'] = self.get_eigs(ted, 'cond_doping')
ted['cond_best'] = self.get_extreme(ted, 'cond_eigs')
ted['cond_best_dope18'] = self.get_extreme(ted,
'cond_eigs',
max_didx=3)
ted['cond_best_dope19'] = self.get_extreme(ted,
'cond_eigs',
max_didx=4)
ted['kappa_eigs'] = self.get_eigs(ted, 'kappa_doping')
ted['kappa_best'] = self.get_extreme(ted,
'kappa_eigs',
maximize=False)
ted['kappa_best_dope18'] = self.get_extreme(ted,
'kappa_eigs',
maximize=False,
max_didx=3)
ted['kappa_best_dope19'] = self.get_extreme(ted,
'kappa_eigs',
maximize=False,
max_didx=4)
try:
from mpcollab.thermoelectrics.boltztrap_TE import BoltzSPB
bzspb = BoltzSPB(ted)
maxpf_p = bzspb.get_maximum_power_factor(
'p',
temperature=0,
tau=1E-14,
ZT=False,
kappal=0.5,
otherprops=('get_seebeck_mu_eig',
'get_conductivity_mu_eig',
'get_thermal_conductivity_mu_eig',
'get_average_eff_mass_tensor_mu'))
maxpf_n = bzspb.get_maximum_power_factor(
'n',
temperature=0,
tau=1E-14,
ZT=False,
kappal=0.5,
otherprops=('get_seebeck_mu_eig',
'get_conductivity_mu_eig',
'get_thermal_conductivity_mu_eig',
'get_average_eff_mass_tensor_mu'))
maxzt_p = bzspb.get_maximum_power_factor(
'p',
temperature=0,
tau=1E-14,
ZT=True,
kappal=0.5,
otherprops=('get_seebeck_mu_eig',
'get_conductivity_mu_eig',
'get_thermal_conductivity_mu_eig',
'get_average_eff_mass_tensor_mu'))
maxzt_n = bzspb.get_maximum_power_factor(
'n',
temperature=0,
tau=1E-14,
ZT=True,
kappal=0.5,
otherprops=('get_seebeck_mu_eig',
'get_conductivity_mu_eig',
'get_thermal_conductivity_mu_eig',
'get_average_eff_mass_tensor_mu'))
ted['zt_best_finemesh'] = {'p': maxzt_p, 'n': maxzt_n}
ted['pf_best_finemesh'] = {'p': maxpf_p, 'n': maxpf_n}
except:
import traceback
traceback.print_exc()
print 'COULD NOT GET FINE MESH DATA'
# add is_compatible
mpc = MaterialsProjectCompatibility("Advanced")
try:
func = m_task["pseudo_potential"]["functional"]
labels = m_task["pseudo_potential"]["labels"]
symbols = ["{} {}".format(func, label) for label in labels]
parameters = {
"run_type": m_task["run_type"],
"is_hubbard": m_task["is_hubbard"],
"hubbards": m_task["hubbards"],
"potcar_symbols": symbols
}
entry = ComputedEntry(Composition(m_task["unit_cell_formula"]),
0.0,
0.0,
parameters=parameters,
entry_id=m_task["task_id"])
ted["is_compatible"] = bool(mpc.process_entry(entry))
except:
traceback.print_exc()
print 'ERROR in getting compatibility, task_id: {}'.format(
m_task["task_id"])
ted["is_compatible"] = None
tdb.boltztrap.insert(jsanitize(ted))
update_spec = {
'prev_vasp_dir': fw_spec['prev_vasp_dir'],
'boltztrap_dir': os.getcwd(),
'prev_task_type': fw_spec['task_type'],
'mpsnl': fw_spec['mpsnl'].as_dict(),
'snlgroup_id': fw_spec['snlgroup_id'],
'run_tags': fw_spec['run_tags'],
'parameters': fw_spec.get('parameters')
}
return FWAction(update_spec=update_spec)
def assimilate(self, path, launches_coll=None):
"""
Parses vasp runs. Then insert the result into the db. and return the
task_id or doc of the insertion.
Returns:
If in simulate_mode, the entire doc is returned for debugging
purposes. Else, only the task_id of the inserted doc is returned.
"""
d = self.get_task_doc(path)
if self.additional_fields:
d.update(self.additional_fields) # always add additional fields, even for failed jobs
try:
d["dir_name_full"] = d["dir_name"].split(":")[1]
d["dir_name"] = get_block_part(d["dir_name_full"])
d["stored_data"] = {}
except:
print 'COULD NOT GET DIR NAME'
pprint.pprint(d)
print traceback.format_exc()
raise ValueError('IMPROPER PARSING OF {}'.format(path))
if not self.simulate:
# Perform actual insertion into db. Because db connections cannot
# be pickled, every insertion needs to create a new connection
# to the db.
conn = MongoClient(self.host, self.port)
db = conn[self.database]
if self.user:
db.authenticate(self.user, self.password)
coll = db[self.collection]
# Insert dos data into gridfs and then remove it from the dict.
# DOS data tends to be above the 4Mb limit for mongo docs. A ref
# to the dos file is in the dos_fs_id.
result = coll.find_one({"dir_name": d["dir_name"]})
if result is None or self.update_duplicates:
if self.parse_dos and "calculations" in d:
for calc in d["calculations"]:
if "dos" in calc:
dos = json.dumps(calc["dos"], cls=MontyEncoder)
fs = gridfs.GridFS(db, "dos_fs")
dosid = fs.put(dos)
calc["dos_fs_id"] = dosid
del calc["dos"]
d["last_updated"] = datetime.datetime.today()
if result is None:
if ("task_id" not in d) or (not d["task_id"]):
d["task_id"] = "mp-{}".format(
db.counter.find_one_and_update(
{"_id": "taskid"}, {"$inc": {"c": 1}}
)["c"])
logger.info("Inserting {} with taskid = {}"
.format(d["dir_name"], d["task_id"]))
elif self.update_duplicates:
d["task_id"] = result["task_id"]
logger.info("Updating {} with taskid = {}"
.format(d["dir_name"], d["task_id"]))
#Fireworks processing
self.process_fw(path, d)
try:
#Add oxide_type
struct=Structure.from_dict(d["output"]["crystal"])
d["oxide_type"]=oxide_type(struct)
except:
logger.error("can't get oxide_type for {}".format(d["task_id"]))
d["oxide_type"] = None
#Override incorrect outcar subdocs for two step relaxations
if "optimize structure" in d['task_type'] and \
os.path.exists(os.path.join(path, "relax2")):
try:
run_stats = {}
for i in [1,2]:
o_path = os.path.join(path,"relax"+str(i),"OUTCAR")
o_path = o_path if os.path.exists(o_path) else o_path+".gz"
outcar = Outcar(o_path)
d["calculations"][i-1]["output"]["outcar"] = outcar.as_dict()
run_stats["relax"+str(i)] = outcar.run_stats
except:
logger.error("Bad OUTCAR for {}.".format(path))
try:
overall_run_stats = {}
for key in ["Total CPU time used (sec)", "User time (sec)",
"System time (sec)", "Elapsed time (sec)"]:
overall_run_stats[key] = sum([v[key]
for v in run_stats.values()])
run_stats["overall"] = overall_run_stats
except:
logger.error("Bad run stats for {}.".format(path))
d["run_stats"] = run_stats
# add is_compatible
mpc = MaterialsProjectCompatibility("Advanced")
try:
func = d["pseudo_potential"]["functional"]
labels = d["pseudo_potential"]["labels"]
symbols = ["{} {}".format(func, label) for label in labels]
parameters = {"run_type": d["run_type"],
"is_hubbard": d["is_hubbard"],
"hubbards": d["hubbards"],
"potcar_symbols": symbols}
entry = ComputedEntry(Composition(d["unit_cell_formula"]),
0.0, 0.0, parameters=parameters,
entry_id=d["task_id"])
d['is_compatible'] = bool(mpc.process_entry(entry))
except:
traceback.print_exc()
print 'ERROR in getting compatibility'
d['is_compatible'] = None
#task_type dependent processing
if 'static' in d['task_type']:
launch_doc = launches_coll.find_one({"fw_id": d['fw_id'], "launch_dir": {"$regex": d["dir_name"]}}, {"action.stored_data": 1})
for i in ["conventional_standard_structure", "symmetry_operations",
"symmetry_dataset", "refined_structure"]:
try:
d['stored_data'][i] = launch_doc['action']['stored_data'][i]
except:
pass
#parse band structure if necessary
if ('band structure' in d['task_type'] or "Uniform" in d['task_type'])\
and d['state'] == 'successful':
launch_doc = launches_coll.find_one({"fw_id": d['fw_id'], "launch_dir": {"$regex": d["dir_name"]}},
{"action.stored_data": 1})
vasp_run = Vasprun(zpath(os.path.join(path, "vasprun.xml")), parse_projected_eigen=False)
if 'band structure' in d['task_type']:
def string_to_numlist(stringlist):
g=re.search('([0-9\-\.eE]+)\s+([0-9\-\.eE]+)\s+([0-9\-\.eE]+)', stringlist)
return [float(g.group(i)) for i in range(1,4)]
for i in ["kpath_name", "kpath"]:
d['stored_data'][i] = launch_doc['action']['stored_data'][i]
kpoints_doc = d['stored_data']['kpath']['kpoints']
for i in kpoints_doc:
kpoints_doc[i]=string_to_numlist(kpoints_doc[i])
bs=vasp_run.get_band_structure(efermi=d['calculations'][0]['output']['outcar']['efermi'],
line_mode=True)
else:
bs=vasp_run.get_band_structure(efermi=d['calculations'][0]['output']['outcar']['efermi'],
line_mode=False)
bs_json = json.dumps(bs.as_dict(), cls=MontyEncoder)
fs = gridfs.GridFS(db, "band_structure_fs")
bs_id = fs.put(bs_json)
d['calculations'][0]["band_structure_fs_id"] = bs_id
# also override band gap in task doc
gap = bs.get_band_gap()
vbm = bs.get_vbm()
cbm = bs.get_cbm()
update_doc = {'bandgap': gap['energy'], 'vbm': vbm['energy'], 'cbm': cbm['energy'], 'is_gap_direct': gap['direct']}
d['analysis'].update(update_doc)
d['calculations'][0]['output'].update(update_doc)
coll.update_one({"dir_name": d["dir_name"]}, {'$set': d}, upsert=True)
return d["task_id"], d
else:
logger.info("Skipping duplicate {}".format(d["dir_name"]))
return result["task_id"], result
else:
d["task_id"] = 0
logger.info("Simulated insert into database for {} with task_id {}"
.format(d["dir_name"], d["task_id"]))
return 0, d
def assimilate(self, path, launches_coll=None):
"""
Parses vasp runs. Then insert the result into the db. and return the
task_id or doc of the insertion.
Returns:
If in simulate_mode, the entire doc is returned for debugging
purposes. Else, only the task_id of the inserted doc is returned.
"""
d = self.get_task_doc(path)
if self.additional_fields:
d.update(self.additional_fields
) # always add additional fields, even for failed jobs
try:
d["dir_name_full"] = d["dir_name"].split(":")[1]
d["dir_name"] = get_block_part(d["dir_name_full"])
d["stored_data"] = {}
except:
print 'COULD NOT GET DIR NAME'
pprint.pprint(d)
print traceback.format_exc()
raise ValueError('IMPROPER PARSING OF {}'.format(path))
if not self.simulate:
# Perform actual insertion into db. Because db connections cannot
# be pickled, every insertion needs to create a new connection
# to the db.
conn = MongoClient(self.host, self.port)
db = conn[self.database]
if self.user:
db.authenticate(self.user, self.password)
coll = db[self.collection]
# Insert dos data into gridfs and then remove it from the dict.
# DOS data tends to be above the 4Mb limit for mongo docs. A ref
# to the dos file is in the dos_fs_id.
result = coll.find_one({"dir_name": d["dir_name"]})
if result is None or self.update_duplicates:
if self.parse_dos and "calculations" in d:
for calc in d["calculations"]:
if "dos" in calc:
dos = json.dumps(calc["dos"], cls=MontyEncoder)
fs = gridfs.GridFS(db, "dos_fs")
dosid = fs.put(dos)
calc["dos_fs_id"] = dosid
del calc["dos"]
d["last_updated"] = datetime.datetime.today()
if result is None:
if ("task_id" not in d) or (not d["task_id"]):
d["task_id"] = "mp-{}".format(
db.counter.find_one_and_update({"_id": "taskid"},
{"$inc": {
"c": 1
}})["c"])
logger.info("Inserting {} with taskid = {}".format(
d["dir_name"], d["task_id"]))
elif self.update_duplicates:
d["task_id"] = result["task_id"]
logger.info("Updating {} with taskid = {}".format(
d["dir_name"], d["task_id"]))
#Fireworks processing
self.process_fw(path, d)
try:
#Add oxide_type
struct = Structure.from_dict(d["output"]["crystal"])
d["oxide_type"] = oxide_type(struct)
except:
logger.error("can't get oxide_type for {}".format(
d["task_id"]))
d["oxide_type"] = None
#Override incorrect outcar subdocs for two step relaxations
if "optimize structure" in d['task_type'] and \
os.path.exists(os.path.join(path, "relax2")):
try:
run_stats = {}
for i in [1, 2]:
o_path = os.path.join(path, "relax" + str(i),
"OUTCAR")
o_path = o_path if os.path.exists(
o_path) else o_path + ".gz"
outcar = Outcar(o_path)
d["calculations"][
i - 1]["output"]["outcar"] = outcar.as_dict()
run_stats["relax" + str(i)] = outcar.run_stats
except:
logger.error("Bad OUTCAR for {}.".format(path))
try:
overall_run_stats = {}
for key in [
"Total CPU time used (sec)", "User time (sec)",
"System time (sec)", "Elapsed time (sec)"
]:
overall_run_stats[key] = sum(
[v[key] for v in run_stats.values()])
run_stats["overall"] = overall_run_stats
except:
logger.error("Bad run stats for {}.".format(path))
d["run_stats"] = run_stats
# add is_compatible
mpc = MaterialsProjectCompatibility("Advanced")
try:
func = d["pseudo_potential"]["functional"]
labels = d["pseudo_potential"]["labels"]
symbols = ["{} {}".format(func, label) for label in labels]
parameters = {
"run_type": d["run_type"],
"is_hubbard": d["is_hubbard"],
"hubbards": d["hubbards"],
"potcar_symbols": symbols
}
entry = ComputedEntry(Composition(d["unit_cell_formula"]),
0.0,
0.0,
parameters=parameters,
entry_id=d["task_id"])
d['is_compatible'] = bool(mpc.process_entry(entry))
except:
traceback.print_exc()
print 'ERROR in getting compatibility'
d['is_compatible'] = None
#task_type dependent processing
if 'static' in d['task_type']:
launch_doc = launches_coll.find_one(
{
"fw_id": d['fw_id'],
"launch_dir": {
"$regex": d["dir_name"]
}
}, {"action.stored_data": 1})
for i in [
"conventional_standard_structure",
"symmetry_operations", "symmetry_dataset",
"refined_structure"
]:
try:
d['stored_data'][i] = launch_doc['action'][
'stored_data'][i]
except:
pass
#parse band structure if necessary
if ('band structure' in d['task_type'] or "Uniform" in d['task_type'])\
and d['state'] == 'successful':
launch_doc = launches_coll.find_one(
{
"fw_id": d['fw_id'],
"launch_dir": {
"$regex": d["dir_name"]
}
}, {"action.stored_data": 1})
vasp_run = Vasprun(zpath(os.path.join(path,
"vasprun.xml")),
parse_projected_eigen=True)
if 'band structure' in d['task_type']:
def string_to_numlist(stringlist):
g = re.search(
'([0-9\-\.eE]+)\s+([0-9\-\.eE]+)\s+([0-9\-\.eE]+)',
stringlist)
return [float(g.group(i)) for i in range(1, 4)]
for i in ["kpath_name", "kpath"]:
d['stored_data'][i] = launch_doc['action'][
'stored_data'][i]
kpoints_doc = d['stored_data']['kpath']['kpoints']
for i in kpoints_doc:
if isinstance(kpoints_doc[i], six.string_types):
kpoints_doc[i] = string_to_numlist(
kpoints_doc[i])
bs = vasp_run.get_band_structure(
efermi=d['calculations'][0]['output']['outcar']
['efermi'],
line_mode=True)
else:
bs = vasp_run.get_band_structure(
efermi=d['calculations'][0]['output']['outcar']
['efermi'],
line_mode=False)
bs_json = json.dumps(bs.as_dict(), cls=MontyEncoder)
fs = gridfs.GridFS(db, "band_structure_fs")
bs_id = fs.put(bs_json)
d['calculations'][0]["band_structure_fs_id"] = bs_id
# also override band gap in task doc
gap = bs.get_band_gap()
vbm = bs.get_vbm()
cbm = bs.get_cbm()
update_doc = {
'bandgap': gap['energy'],
'vbm': vbm['energy'],
'cbm': cbm['energy'],
'is_gap_direct': gap['direct']
}
d['analysis'].update(update_doc)
d['calculations'][0]['output'].update(update_doc)
coll.update_one({"dir_name": d["dir_name"]}, {'$set': d},
upsert=True)
return d["task_id"], d
else:
logger.info("Skipping duplicate {}".format(d["dir_name"]))
return result["task_id"], result
else:
d["task_id"] = 0
logger.info(
"Simulated insert into database for {} with task_id {}".format(
d["dir_name"], d["task_id"]))
return 0, d
def run_task(self, fw_spec):
# get the band structure and nelect from files
"""
prev_dir = get_loc(fw_spec['prev_vasp_dir'])
vasprun_loc = zpath(os.path.join(prev_dir, 'vasprun.xml'))
kpoints_loc = zpath(os.path.join(prev_dir, 'KPOINTS'))
vr = Vasprun(vasprun_loc)
bs = vr.get_band_structure(kpoints_filename=kpoints_loc)
"""
# get the band structure and nelect from DB
block_part = get_block_part(fw_spec['prev_vasp_dir'])
db_dir = os.environ['DB_LOC']
assert isinstance(db_dir, object)
db_path = os.path.join(db_dir, 'tasks_db.json')
with open(db_path) as f:
creds = json.load(f)
connection = MongoClient(creds['host'], creds['port'])
tdb = connection[creds['database']]
tdb.authenticate(creds['admin_user'], creds['admin_password'])
m_task = tdb.tasks.find_one({"dir_name": block_part}, {
"calculations": 1,
"task_id": 1
})
nelect = m_task['calculations'][0]['input']['parameters']['NELECT']
bs_id = m_task['calculations'][0]['band_structure_fs_id']
print bs_id, type(bs_id)
fs = gridfs.GridFS(tdb, 'band_structure_fs')
bs_dict = json.loads(fs.get(bs_id).read())
bs_dict['structure'] = m_task['calculations'][0]['output'][
'crystal']
bs = BandStructure.from_dict(bs_dict)
print 'Band Structure found:', bool(bs)
print nelect
# run Boltztrap
runner = BoltztrapRunner(bs, nelect)
dir = runner.run(path_dir=os.getcwd())
# put the data in the database
bta = BoltztrapAnalyzer.from_files(dir)
data = bta.to_dict
data.update(get_meta_from_structure(bs._structure))
data['snlgroup_id'] = fw_spec['snlgroup_id']
data['run_tags'] = fw_spec['run_tags']
data['snl'] = fw_spec['mpsnl']
data['dir_name_full'] = dir
data['dir_name'] = get_block_part(dir)
data['task_id'] = m_task['task_id']
data['hall'] = {} # remove because it is too large and not useful
data['hall_doping'] = {
} # remove because it is too large and not useful
tdb.boltztrap.insert(clean_json(data))
update_spec = {
'prev_vasp_dir': fw_spec['prev_vasp_dir'],
'boltztrap_dir': os.getcwd(),
'prev_task_type': fw_spec['task_type'],
'mpsnl': fw_spec['mpsnl'],
'snlgroup_id': fw_spec['snlgroup_id'],
'run_tags': fw_spec['run_tags'],
'parameters': fw_spec.get('parameters')
}
return FWAction(update_spec=update_spec)
def assimilate(self, path, launches_coll=None):
"""
Parses vasp runs. Then insert the result into the db. and return the
task_id or doc of the insertion.
Returns:
If in simulate_mode, the entire doc is returned for debugging
purposes. Else, only the task_id of the inserted doc is returned.
"""
d = self.get_task_doc(path, self.parse_dos,
self.additional_fields)
try:
d["dir_name_full"] = d["dir_name"].split(":")[1]
d["dir_name"] = get_block_part(d["dir_name_full"])
d["stored_data"] = {}
except:
print 'COULD NOT GET DIR NAME'
pprint.pprint(d)
print traceback.format_exc()
raise ValueError('IMPROPER PARSING OF {}'.format(path))
if not self.simulate:
# Perform actual insertion into db. Because db connections cannot
# be pickled, every insertion needs to create a new connection
# to the db.
conn = MongoClient(self.host, self.port)
db = conn[self.database]
if self.user:
db.authenticate(self.user, self.password)
coll = db[self.collection]
# Insert dos data into gridfs and then remove it from the dict.
# DOS data tends to be above the 4Mb limit for mongo docs. A ref
# to the dos file is in the dos_fs_id.
result = coll.find_one({"dir_name": d["dir_name"]})
if result is None or self.update_duplicates:
if self.parse_dos and "calculations" in d:
for calc in d["calculations"]:
if "dos" in calc:
dos = json.dumps(calc["dos"])
fs = gridfs.GridFS(db, "dos_fs")
dosid = fs.put(dos)
calc["dos_fs_id"] = dosid
del calc["dos"]
d["last_updated"] = datetime.datetime.today()
if result is None:
if ("task_id" not in d) or (not d["task_id"]):
d["task_id"] = "mp-{}".format(
db.counter.find_and_modify(
query={"_id": "taskid"},
update={"$inc": {"c": 1}})["c"])
logger.info("Inserting {} with taskid = {}"
.format(d["dir_name"], d["task_id"]))
elif self.update_duplicates:
d["task_id"] = result["task_id"]
logger.info("Updating {} with taskid = {}"
.format(d["dir_name"], d["task_id"]))
#Fireworks processing
self.process_fw(path, d)
#Override incorrect outcar subdocs for two step relaxations
if "optimize structure" in d['task_type'] and \
os.path.exists(os.path.join(path, "relax2")):
try:
run_stats = {}
for i in [1,2]:
outcar = Outcar(os.path.join(path,"relax"+str(i),"OUTCAR"))
d["calculations"][i-1]["output"]["outcar"] = outcar.to_dict
run_stats["relax"+str(i)] = outcar.run_stats
except:
logger.error("Bad OUTCAR for {}.".format(path))
try:
overall_run_stats = {}
for key in ["Total CPU time used (sec)", "User time (sec)",
"System time (sec)", "Elapsed time (sec)"]:
overall_run_stats[key] = sum([v[key]
for v in run_stats.values()])
run_stats["overall"] = overall_run_stats
except:
logger.error("Bad run stats for {}.".format(path))
d["run_stats"] = run_stats
#task_type dependent processing
if 'static' in d['task_type']:
launch_doc = launches_coll.find_one({"fw_id": d['fw_id'], "launch_dir": {"$regex": d["dir_name"]}}, {"action.stored_data": 1})
for i in ["conventional_standard_structure", "symmetry_operations",
"symmetry_dataset", "refined_structure"]:
try:
d['stored_data'][i] = launch_doc['action']['stored_data'][i]
except:
pass
#parse band structure if necessary
if ('band structure' in d['task_type'] or "Uniform" in d['task_type'])\
and d['state'] == 'successful':
launch_doc = launches_coll.find_one({"fw_id": d['fw_id'], "launch_dir": {"$regex": d["dir_name"]}},
{"action.stored_data": 1})
vasp_run = Vasprun(os.path.join(path, "vasprun.xml"), parse_projected_eigen=False)
if 'band structure' in d['task_type']:
def string_to_numlist(stringlist):
g=re.search('([0-9\-\.eE]+)\s+([0-9\-\.eE]+)\s+([0-9\-\.eE]+)', stringlist)
return [float(g.group(i)) for i in range(1,4)]
for i in ["kpath_name", "kpath"]:
d['stored_data'][i] = launch_doc['action']['stored_data'][i]
kpoints_doc = d['stored_data']['kpath']['kpoints']
for i in kpoints_doc:
kpoints_doc[i]=string_to_numlist(kpoints_doc[i])
bs=vasp_run.get_band_structure(efermi=d['calculations'][0]['output']['outcar']['efermi'],
line_mode=True)
else:
bs=vasp_run.get_band_structure(efermi=d['calculations'][0]['output']['outcar']['efermi'],
line_mode=False)
bs_json = json.dumps(bs.to_dict)
fs = gridfs.GridFS(db, "band_structure_fs")
bs_id = fs.put(bs_json)
d['calculations'][0]["band_structure_fs_id"] = bs_id
coll.update({"dir_name": d["dir_name"]}, d, upsert=True)
return d["task_id"], d
else:
logger.info("Skipping duplicate {}".format(d["dir_name"]))
return result["task_id"], result
else:
d["task_id"] = 0
logger.info("Simulated insert into database for {} with task_id {}"
.format(d["dir_name"], d["task_id"]))
return 0, d
def run_task(self, fw_spec):
if '_fizzled_parents' in fw_spec and not 'prev_vasp_dir' in fw_spec:
prev_dir = get_loc(fw_spec['_fizzled_parents'][0]['launches'][0]['launch_dir'])
update_spec = {}
fizzled_parent = True
parse_dos = False
else:
prev_dir = get_loc(fw_spec['prev_vasp_dir'])
update_spec = {'prev_vasp_dir': get_block_part(prev_dir),
'prev_task_type': fw_spec['prev_task_type'],
'run_tags': fw_spec['run_tags']}
self.additional_fields['run_tags'] = fw_spec['run_tags']
fizzled_parent = False
parse_dos = 'Uniform' in fw_spec['prev_task_type']
if MOVE_TO_GARDEN_DEV:
prev_dir = move_to_garden(prev_dir, prod=False)
elif MOVE_TO_GARDEN_PROD:
prev_dir = move_to_garden(prev_dir, prod=True)
# get the directory containing the db file
db_dir = os.environ['DB_LOC']
db_path = os.path.join(db_dir, 'tasks_db.json')
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger('MPVaspDrone')
logger.setLevel(logging.INFO)
sh = logging.StreamHandler(stream=sys.stdout)
sh.setLevel(getattr(logging, 'INFO'))
logger.addHandler(sh)
with open(db_path) as f:
db_creds = json.load(f)
drone = MPVaspDrone(
host=db_creds['host'], port=db_creds['port'],
database=db_creds['database'], user=db_creds['admin_user'],
password=db_creds['admin_password'],
collection=db_creds['collection'], parse_dos=parse_dos,
additional_fields=self.additional_fields,
update_duplicates=self.update_duplicates)
t_id, d = drone.assimilate(prev_dir, launches_coll=LaunchPad.auto_load().launches)
mpsnl = d['snl_final'] if 'snl_final' in d else d['snl']
snlgroup_id = d['snlgroup_id_final'] if 'snlgroup_id_final' in d else d['snlgroup_id']
update_spec.update({'mpsnl': mpsnl, 'snlgroup_id': snlgroup_id})
print 'ENTERED task id:', t_id
stored_data = {'task_id': t_id}
if d['state'] == 'successful':
update_spec['analysis'] = d['analysis']
update_spec['output'] = d['output']
return FWAction(stored_data=stored_data, update_spec=update_spec)
# not successful - first test to see if UnconvergedHandler is needed
if not fizzled_parent:
unconverged_tag = 'unconverged_handler--{}'.format(fw_spec['prev_task_type'])
output_dir = last_relax(os.path.join(prev_dir, 'vasprun.xml'))
ueh = UnconvergedErrorHandler(output_filename=output_dir)
if ueh.check() and unconverged_tag not in fw_spec['run_tags']:
print 'Unconverged run! Creating dynamic FW...'
spec = {'prev_vasp_dir': get_block_part(prev_dir),
'prev_task_type': fw_spec['task_type'],
'mpsnl': mpsnl, 'snlgroup_id': snlgroup_id,
'task_type': fw_spec['prev_task_type'],
'run_tags': list(fw_spec['run_tags']),
'_dupefinder': DupeFinderVasp().to_dict(),
'_priority': fw_spec['_priority']}
snl = StructureNL.from_dict(spec['mpsnl'])
spec['run_tags'].append(unconverged_tag)
spec['_queueadapter'] = QA_VASP
fws = []
connections = {}
f = Composition.from_formula(
snl.structure.composition.reduced_formula).alphabetical_formula
fws.append(FireWork(
[VaspCopyTask({'files': ['INCAR', 'KPOINTS', 'POSCAR', 'POTCAR', 'CONTCAR'],
'use_CONTCAR': False}), SetupUnconvergedHandlerTask(),
get_custodian_task(spec)], spec, name=get_slug(f + '--' + spec['task_type']),
fw_id=-2))
spec = {'task_type': 'VASP db insertion', '_allow_fizzled_parents': True,
'_priority': fw_spec['_priority'], '_queueadapter': QA_DB,
'run_tags': list(fw_spec['run_tags'])}
spec['run_tags'].append(unconverged_tag)
fws.append(
FireWork([VaspToDBTask()], spec, name=get_slug(f + '--' + spec['task_type']),
fw_id=-1))
connections[-2] = -1
wf = Workflow(fws, connections)
return FWAction(detours=wf)
# not successful and not due to convergence problem - FIZZLE
raise ValueError("DB insertion successful, but don't know how to fix this FireWork! Can't continue with workflow...")
def detect():
for d in glob.glob(os.path.join(SCRATCH_PATH, 'block*/launch*')):
block_part = get_block_part(d)
garden_dir = os.path.join(GARDEN_PATH, block_part)
if os.path.exists(garden_dir):
print garden_dir
def run_task(self, fw_spec):
if '_fizzled_parents' in fw_spec and not 'prev_vasp_dir' in fw_spec:
prev_dir = get_loc(
fw_spec['_fizzled_parents'][0]['launches'][0]['launch_dir'])
update_spec = {}
fizzled_parent = True
parse_dos = False
else:
prev_dir = get_loc(fw_spec['prev_vasp_dir'])
update_spec = {
'prev_vasp_dir': get_block_part(prev_dir),
'prev_task_type': fw_spec['prev_task_type'],
'run_tags': fw_spec['run_tags']
}
self.additional_fields['run_tags'] = fw_spec['run_tags']
fizzled_parent = False
parse_dos = 'Uniform' in fw_spec['prev_task_type']
if MOVE_TO_GARDEN_DEV:
prev_dir = move_to_garden(prev_dir, prod=False)
elif MOVE_TO_GARDEN_PROD:
prev_dir = move_to_garden(prev_dir, prod=True)
# get the directory containing the db file
db_dir = os.environ['DB_LOC']
db_path = os.path.join(db_dir, 'tasks_db.json')
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger('MPVaspDrone')
logger.setLevel(logging.INFO)
sh = logging.StreamHandler(stream=sys.stdout)
sh.setLevel(getattr(logging, 'INFO'))
logger.addHandler(sh)
with open(db_path) as f:
db_creds = json.load(f)
drone = MPVaspDrone(host=db_creds['host'],
port=db_creds['port'],
database=db_creds['database'],
user=db_creds['admin_user'],
password=db_creds['admin_password'],
collection=db_creds['collection'],
parse_dos=parse_dos,
additional_fields=self.additional_fields,
update_duplicates=self.update_duplicates)
t_id, d = drone.assimilate(
prev_dir, launches_coll=LaunchPad.auto_load().launches)
mpsnl = d['snl_final'] if 'snl_final' in d else d['snl']
snlgroup_id = d['snlgroup_id_final'] if 'snlgroup_id_final' in d else d[
'snlgroup_id']
update_spec.update({'mpsnl': mpsnl, 'snlgroup_id': snlgroup_id})
print 'ENTERED task id:', t_id
stored_data = {'task_id': t_id}
if d['state'] == 'successful':
update_spec['analysis'] = d['analysis']
update_spec['output'] = d['output']
return FWAction(stored_data=stored_data, update_spec=update_spec)
# not successful - first test to see if UnconvergedHandler is needed
if not fizzled_parent:
unconverged_tag = 'unconverged_handler--{}'.format(
fw_spec['prev_task_type'])
output_dir = last_relax(os.path.join(prev_dir, 'vasprun.xml'))
ueh = UnconvergedErrorHandler(output_filename=output_dir)
if ueh.check() and unconverged_tag not in fw_spec['run_tags']:
print 'Unconverged run! Creating dynamic FW...'
spec = {
'prev_vasp_dir': get_block_part(prev_dir),
'prev_task_type': fw_spec['task_type'],
'mpsnl': mpsnl,
'snlgroup_id': snlgroup_id,
'task_type': fw_spec['prev_task_type'],
'run_tags': list(fw_spec['run_tags']),
'_dupefinder': DupeFinderVasp().to_dict(),
'_priority': fw_spec['_priority']
}
snl = StructureNL.from_dict(spec['mpsnl'])
spec['run_tags'].append(unconverged_tag)
spec['_queueadapter'] = QA_VASP
fws = []
connections = {}
f = Composition.from_formula(
snl.structure.composition.reduced_formula
).alphabetical_formula
fws.append(
FireWork([
VaspCopyTask({
'files': [
'INCAR', 'KPOINTS', 'POSCAR', 'POTCAR',
'CONTCAR'
],
'use_CONTCAR':
False
}),
SetupUnconvergedHandlerTask(),
get_custodian_task(spec)
],
spec,
name=get_slug(f + '--' + spec['task_type']),
fw_id=-2))
spec = {
'task_type': 'VASP db insertion',
'_allow_fizzled_parents': True,
'_priority': fw_spec['_priority'],
'_queueadapter': QA_DB,
'run_tags': list(fw_spec['run_tags'])
}
spec['run_tags'].append(unconverged_tag)
fws.append(
FireWork([VaspToDBTask()],
spec,
name=get_slug(f + '--' + spec['task_type']),
fw_id=-1))
connections[-2] = -1
wf = Workflow(fws, connections)
return FWAction(detours=wf)
# not successful and not due to convergence problem - FIZZLE
raise ValueError(
"DB insertion successful, but don't know how to fix this FireWork! Can't continue with workflow..."
)
def detect():
for d in glob.glob(os.path.join(SCRATCH_PATH, 'block*/launch*')):
block_part = get_block_part(d)
garden_dir = os.path.join(GARDEN_PATH, block_part)
if os.path.exists(garden_dir):
print garden_dir