def setup_copy(self, from_dir, to_dir=None, filesystem=None, files_to_copy=None,
exclude_files=None, from_path_dict=None, suffix=None,
fw_spec=None, continue_on_missing=False):
"""
setup the copy i.e setup the from directory, filesystem, destination directory etc.
Args:
from_dir (str)
to_dir (str)
filesystem (str)
files_to_copy (list): if None all the files in the from_dir will be copied
exclude_files (list): list of file names to be excluded.
suffix (str): suffix to append to each filename when copying
(e.g., rename 'INCAR' to 'INCAR.precondition')
continue_on_missing(bool): Whether to continue copying when a file
in filenames is missing. Defaults to False.
from_path_dict (dict): dict specification of the path. If specified must contain atleast
the key "path" that specifies the path to the from_dir.
"""
from_path_dict = from_path_dict or {}
from_dir = env_chk(from_dir, fw_spec, strict=False) or from_path_dict.get("path", None)
filesystem = filesystem or from_path_dict.get("filesystem", None)
if from_dir is None:
raise ValueError("Must specify from_dir!")
self.fileclient = FileClient(filesystem=filesystem)
self.from_dir = self.fileclient.abspath(from_dir)
self.to_dir = env_chk(to_dir, fw_spec, strict=False) or os.getcwd()
exclude_files = exclude_files or []
self.files_to_copy = files_to_copy or [f for f in self.fileclient.listdir(self.from_dir) if f not in exclude_files]
self.suffix = suffix
self.continue_on_missing = continue_on_missing
def run_task(self, fw_spec):
handler_groups = {
"default": [VaspErrorHandler(), MeshSymmetryErrorHandler(), UnconvergedErrorHandler(),
NonConvergingErrorHandler(),PotimErrorHandler(), PositiveEnergyErrorHandler(),
FrozenJobErrorHandler()],
"strict": [VaspErrorHandler(), MeshSymmetryErrorHandler(), UnconvergedErrorHandler(),
NonConvergingErrorHandler(),PotimErrorHandler(), PositiveEnergyErrorHandler(),
FrozenJobErrorHandler(), AliasingErrorHandler()],
"md": [VaspErrorHandler(), NonConvergingErrorHandler()],
"no_handler": []
}
vasp_cmd = env_chk(self["vasp_cmd"], fw_spec)
if isinstance(vasp_cmd, six.string_types):
vasp_cmd = os.path.expandvars(vasp_cmd)
vasp_cmd = shlex.split(vasp_cmd)
# initialize variables
job_type = self.get("job_type", "normal")
scratch_dir = env_chk(self.get("scratch_dir"), fw_spec)
gzip_output = self.get("gzip_output", True)
max_errors = self.get("max_errors", 5)
auto_npar = env_chk(self.get("auto_npar"), fw_spec, strict=False, default=False)
gamma_vasp_cmd = env_chk(self.get("gamma_vasp_cmd"), fw_spec, strict=False, default=None)
if gamma_vasp_cmd:
gamma_vasp_cmd = shlex.split(gamma_vasp_cmd)
# construct jobs
if job_type == "normal":
jobs = [VaspJob(vasp_cmd, auto_npar=auto_npar, gamma_vasp_cmd=gamma_vasp_cmd)]
elif job_type == "double_relaxation_run":
jobs = VaspJob.double_relaxation_run(vasp_cmd, auto_npar=auto_npar, ediffg=self.get("ediffg"),
half_kpts_first_relax=False)
elif job_type == "full_opt_run":
jobs = VaspJob.full_opt_run(vasp_cmd, auto_npar=auto_npar, ediffg=self.get("ediffg"),
max_steps=5, half_kpts_first_relax=False)
else:
raise ValueError("Unsupported job type: {}".format(job_type))
# construct handlers
handlers = handler_groups[self.get("handler_group", "default")]
if self.get("max_force_threshold"):
handlers.append(MaxForceErrorHandler(max_force_threshold=self["max_force_threshold"]))
if self.get("wall_time"):
handlers.append(WalltimeHandler(wall_time=self["wall_time"]))
validators = [VasprunXMLValidator(), VaspFilesValidator()]
c = Custodian(handlers, jobs, validators=validators, max_errors=max_errors,
scratch_dir=scratch_dir, gzipped_output=gzip_output)
c.run()
def run_task(self, fw_spec):
cmd = env_chk(self["qchem_cmd"], fw_spec)
scratch_dir = env_chk(self.get("scratch_dir"), fw_spec)
if scratch_dir == None:
scratch_dir = "/dev/shm/qcscratch/"
os.putenv("QCSCRATCH", scratch_dir)
logger.info("Running command: {}".format(cmd))
return_code = subprocess.call(cmd, shell=True)
logger.info("Command {} finished running with return code: {}".format(
cmd, return_code))
def run_task(self, fw_spec):
# get the directory that contains the dir to parse
calc_dir = os.getcwd()
if "calc_dir" in self:
calc_dir = self["calc_dir"]
elif self.get("calc_loc"):
calc_dir = get_calc_loc(self["calc_loc"],
fw_spec["calc_locs"])["path"]
# parse the calc directory
logger.info("PARSING DIRECTORY: {} USING DRONE: {}".format(
calc_dir, self["drone"].__class__.__name__))
# get the database connection
db_file = env_chk(self.get("db_file"), fw_spec)
drone = self["drone"].__class__()
task_doc = drone.assimilate(calc_dir)
if not db_file:
with open("task.json", "w") as f:
f.write(json.dumps(task_doc, default=DATETIME_HANDLER))
else:
mmdb_str = self["mmdb"]
modname, classname = mmdb_str.strip().rsplit(".", 1)
cls_ = load_class(modname, classname)
db = cls_.from_db_file(db_file)
# insert the task document
t_id = db.insert(task_doc)
logger.info(f"Finished parsing with task_id: {t_id}")
return FWAction(
stored_data={"task_id": task_doc.get("task_id", None)},
defuse_children=(task_doc["state"] != "successful"),
)
def run_task(self, fw_spec):
# Get num of electrons and bands from static calc
uuid = self["wf_uuid"]
db_file = env_chk(self.get("db_file"), fw_spec)
db = VaspCalcDb.from_db_file(db_file, admin=True)
db.collection = db.db["tasks"]
task_doc = db.collection.find_one(
{"wf_meta.wf_uuid": uuid, "task_label": "static"}, ["input.parameters"]
)
nelec = int(task_doc["input"]["parameters"]["NELECT"])
nbands = int(task_doc["input"]["parameters"]["NBANDS"])
w90_file = [
"num_wann = %d" % (nelec),
"num_bands = %d" % (nelec), # 1 band / elec with SOC
"spinors=.true.",
"num_iter 0",
"shell_list 1",
"exclude_bands %d-%d" % (nelec + 1, 2 * nbands),
]
w90_file = "\n".join(w90_file)
with open("wannier90.win", "w") as f:
f.write(w90_file)
return FWAction()
def run_task(self, fw_spec):
irvsp = self["irvsp_out"] or fw_spec["irvsp_out"]
irvsp = jsanitize(irvsp)
additional_fields = self.get("additional_fields", {})
d = additional_fields.copy()
d["wf_uuid"] = self["wf_uuid"]
d["formula"] = fw_spec["formula"]
d["efermi"] = fw_spec["efermi"]
d["structure"] = fw_spec["structure"]
d["irvsp"] = irvsp
# store the results
db_file = env_chk(self.get("db_file"), fw_spec)
if not db_file:
with open("irvsp.json", "w") as f:
f.write(json.dumps(d, default=DATETIME_HANDLER))
else:
db = VaspCalcDb.from_db_file(db_file, admin=True)
db.collection = db.db["irvsp"]
db.collection.insert_one(d)
logger.info("IRVSP calculation complete.")
return FWAction()
def run_task(self, fw_spec):
db_file = env_chk(self["db_file"], fw_spec)
wf_uuid = self["wf_uuid"]
hmodel = loadfn("heisenberg_model.json")
# Exchange collection
mmdb = VaspCalcDb.from_db_file(db_file, admin=True)
mmdb.collection = mmdb.db["exchange"]
hmodel_dict = hmodel.as_dict()
parent_structure = hmodel.structures[0]
formula_pretty = parent_structure.composition.reduced_formula
wf_meta = {"wf_uuid": wf_uuid}
task_doc = {
"wf_meta": wf_meta,
"formula_pretty": formula_pretty,
"nn_cutoff": hmodel.cutoff,
"nn_tol": hmodel.tol,
"heisenberg_model": hmodel_dict,
"task_name": "heisenberg model",
}
if fw_spec.get("tags", None):
task_doc["tags"] = fw_spec["tags"]
mmdb.collection.insert_one(task_doc)
def run_task(self, fw_spec):
symm_check_data = self.check_symmetry()
passed = symm_check_data["symmetry_checks_passed"]
cur_isif = symm_check_data["isif"]
next_steps = self.get_next_steps(passed, cur_isif)
symm_check_data.update({
"tag": self["tag"],
"metadata": self.get("metadata"),
"version_info": {
"atomate": atomate_ver,
"dfttk": dfttk_ver,
"pymatgen": pymatgen_ver,
},
"next_steps": next_steps,
})
# write to JSON for debugging purposes
with open('relaxation_check_summary.json', 'w') as fp:
json.dump(symm_check_data, fp)
self.db_file = env_chk(self.get("db_file"), fw_spec)
vasp_db = VaspCalcDb.from_db_file(self.db_file, admin=True)
vasp_db.db['relaxations'].insert_one(symm_check_data)
return FWAction(detours=self.get_detour_workflow(next_steps, symm_check_data['final_energy_per_atom']))
def run_task(self, fw_spec):
calc_locs = list(fw_spec.get("calc_locs", []))
calc_locs.append({"name": self["name"],
"filesystem": env_chk(self.get('filesystem', None), fw_spec),
"path": self.get("path", os.getcwd())})
return FWAction(mod_spec=[{'_push_all': {'calc_locs': calc_locs}}])
def run_task(self, fw_spec):
from pymatgen.analysis.eos import EOS
tag = self["tag"]
db_file = env_chk(self.get("db_file"), fw_spec)
summary_dict = {"eos": self["eos"]}
mmdb = MMVaspDb.from_db_file(db_file, admin=True)
# get the optimized structure
d = mmdb.collection.find_one({"task_label": "{} structure optimization".format(tag)})
structure = Structure.from_dict(d["calcs_reversed"][-1]["output"]['structure'])
summary_dict["structure"] = structure.as_dict()
# get the data(energy, volume, force constant) from the deformation runs
docs = mmdb.collection.find({"task_label": {"$regex": "{} bulk_modulus*".format(tag)},
"formula_pretty": structure.composition.reduced_formula})
energies = []
volumes = []
for d in docs:
s = Structure.from_dict(d["calcs_reversed"][-1]["output"]['structure'])
energies.append(d["calcs_reversed"][-1]["output"]['energy'])
volumes.append(s.volume)
summary_dict["energies"] = energies
summary_dict["volumes"] = volumes
# fit the equation of state
eos = EOS(self["eos"])
eos_fit = eos.fit(volumes, energies)
summary_dict["results"] = dict(eos_fit.results)
with open("bulk_modulus.json", "w") as f:
f.write(json.dumps(summary_dict, default=DATETIME_HANDLER))
logger.info("BULK MODULUS CALCULATION COMPLETE")
def run_task(self, fw_spec):
# get the directory that contains the dir to parse
calc_dir = os.getcwd()
if "calc_dir" in self:
calc_dir = self["calc_dir"]
elif self.get("calc_loc"):
calc_dir = get_calc_loc(self["calc_loc"], fw_spec["calc_locs"])["path"]
# parse the calc directory
logger.info("PARSING DIRECTORY: {} USING DRONE: {}".format(
calc_dir, self['drone'].__class__.__name__))
# get the database connection
db_file = env_chk(self.get('db_file'), fw_spec)
drone = self['drone'].__class__()
task_doc = drone.assimilate(calc_dir)
if not db_file:
with open("task.json", "w") as f:
f.write(json.dumps(task_doc, default=DATETIME_HANDLER))
else:
mmdb = self["mmdb"]
db = mmdb.__class__.from_db_file(db_file)
# insert the task document
t_id = db.insert(task_doc)
logger.info("Finished parsing with task_id: {}".format(t_id))
return FWAction(stored_data={"task_id": task_doc.get("task_id", None)},
defuse_children=(task_doc["state"] != "successful"))
def run_task(self, fw_spec):
calc_locs = list(fw_spec.get("calc_locs", []))
calc_locs.append({"name": self["name"],
"filesystem": env_chk(self.get('filesystem', None), fw_spec),
"path": self.get("path", os.getcwd())})
return FWAction(mod_spec=[{'_push_all': {'calc_locs': calc_locs}}])
def run_task(self, fw_spec):
tag = self["tag"]
metadata = self.get('metadata', {})
metadata['tag'] = tag
unitcell = Structure.from_file('POSCAR-unitcell')
supercell_matrix = self['supercell_matrix']
temperatures, f_vib, s_vib, cv_vib, force_constants = get_f_vib_phonopy(
unitcell,
supercell_matrix,
vasprun_path='vasprun.xml',
t_min=self['t_min'],
t_max=self['t_max'],
t_step=self['t_step'])
if isinstance(supercell_matrix, np.ndarray):
supercell_matrix = supercell_matrix.tolist() # make serializable
thermal_props_dict = {
'volume': unitcell.volume,
'F_vib': f_vib.tolist(),
'CV_vib': cv_vib.tolist(),
'S_vib': s_vib.tolist(),
'temperatures': temperatures.tolist(),
'force_constants': force_constants.tolist(),
'metadata': metadata,
'unitcell': unitcell.as_dict(),
'supercell_matrix': supercell_matrix,
}
# insert into database
db_file = env_chk(self["db_file"], fw_spec)
vasp_db = VaspCalcDb.from_db_file(db_file, admin=True)
vasp_db.db['phonon'].insert_one(thermal_props_dict)
def run_task(self, fw_spec):
notes = self.get('notes', None)
tag_id = self['tag_id']
# get the database connection
db_file = env_chk(self.get('db_file'), fw_spec)
mmdb = VaspMDCalcDb.from_db_file(db_file, admin=True)
mmdb.db.trajectories.find_one_and_delete({"runs_label": tag_id})
runs = mmdb.db['tasks'].find(
{"task_label": re.compile(f'.*prod_run.*{tag_id}.*')})
runs_sorted = sorted(
runs,
key=lambda x: int(re.findall('run[_-](\d+)', x['task_label'])[0]))
# Remove duplicates of the same run (if they exist)
labels = [result['task_label'] for result in runs_sorted]
nums = [int(re.findall('run[_-](\d+)', label)[0]) for label in labels]
duplicates = np.where((nums - np.roll(nums, 1)) == 0)[0]
runs_sorted = [
runs_sorted[i] for i in range(len(runs_sorted))
if i not in duplicates
]
trajectory_doc = runs_to_trajectory_doc(runs_sorted, db_file, tag_id,
notes)
mmdb.db.trajectories.insert_one(trajectory_doc)
def run_task(self, fw_spec):
wf_uuid = self["wf_uuid"]
surfaces = ["kx_0", "kx_1", "ky_0", "ky_1", "kz_0", "kz_1"]
d = {
"wf_uuid": wf_uuid,
"formula": fw_spec["formula"],
"reduced_formula": fw_spec["reduced_formula"],
"structure": fw_spec["structure"],
}
for surface in surfaces:
if surface in fw_spec.keys():
d[surface] = fw_spec[surface]
d = jsanitize(d)
# store the results
db_file = env_chk(self.get("db_file"), fw_spec)
if not db_file:
with open("z2pack.json", "w") as f:
f.write(json.dumps(d, default=DATETIME_HANDLER))
else:
db = VaspCalcDb.from_db_file(db_file, admin=True)
db.collection = db.db["z2pack"]
db.collection.insert_one(d)
logger.info("Z2Pack surface calculation complete.")
return FWAction()
def run_task(self, fw_spec):
tag = self["tag"]
db_file = env_chk(self.get("db_file"), fw_spec)
t_step = self.get("t_step", 10)
t_min = self.get("t_min", 0)
t_max = self.get("t_max", 1000)
mesh = self.get("mesh", [20, 20, 20])
eos = self.get("eos", "vinet")
qha_type = self.get("qha_type", "debye_model")
pressure = self.get("pressure", 0.0)
gibbs_summary_dict = {}
mmdb = MMVaspDb.from_db_file(db_file, admin=True)
# get the optimized structure
d = mmdb.collection.find_one({"task_label": "{} structure optimization".format(tag)})
structure = Structure.from_dict(d["calcs_reversed"][-1]["output"]['structure'])
gibbs_summary_dict["structure"] = structure.as_dict()
# get the data(energy, volume, force constant) from the deformation runs
docs = mmdb.collection.find({"task_label": {"$regex": "{} gibbs*".format(tag)},
"formula_pretty": structure.composition.reduced_formula})
energies = []
volumes = []
force_constants = []
for d in docs:
s = Structure.from_dict(d["calcs_reversed"][-1]["output"]['structure'])
energies.append(d["calcs_reversed"][-1]["output"]['energy'])
if qha_type not in ["debye_model"]:
force_constants.append(d["calcs_reversed"][-1]["output"]['force_constants'])
volumes.append(s.volume)
gibbs_summary_dict["energies"] = energies
gibbs_summary_dict["volumes"] = volumes
if qha_type not in ["debye_model"]:
gibbs_summary_dict["force_constants"] = force_constants
G, T = None, None
# use debye model
if qha_type in ["debye_model"]:
from atomate.tools.analysis import get_debye_model_gibbs
G, T = get_debye_model_gibbs(energies, volumes, structure, t_min, t_step, t_max, eos,
pressure)
# use the phonopy interface
else:
from atomate.tools.analysis import get_phonopy_gibbs
G, T = get_phonopy_gibbs(energies, volumes, force_constants, structure, t_min, t_step,
t_max, mesh, eos, pressure)
gibbs_summary_dict["G"] = G
gibbs_summary_dict["T"] = T
with open("gibbs.json", "w") as f:
f.write(json.dumps(gibbs_summary_dict, default=DATETIME_HANDLER))
logger.info("GIBBS FREE ENERGY CALCULATION COMPLETE")
def run_task(self, fw_spec):
from atomate.vasp.analysis.phonopy import get_phonopy_thermal_expansion
tag = self["tag"]
db_file = env_chk(self.get("db_file"), fw_spec)
t_step = self.get("t_step", 10)
t_min = self.get("t_min", 0)
t_max = self.get("t_max", 1000)
mesh = self.get("mesh", [20, 20, 20])
eos = self.get("eos", "vinet")
pressure = self.get("pressure", 0.0)
summary_dict = {}
mmdb = VaspCalcDb.from_db_file(db_file, admin=True)
# get the optimized structure
d = mmdb.collection.find_one(
{"task_label": "{} structure optimization".format(tag)})
structure = Structure.from_dict(
d["calcs_reversed"][-1]["output"]['structure'])
summary_dict["structure"] = structure.as_dict()
summary_dict["formula_pretty"] = structure.composition.reduced_formula
# get the data(energy, volume, force constant) from the deformation runs
docs = mmdb.collection.find({
"task_label": {
"$regex": "{} thermal_expansion*".format(tag)
},
"formula_pretty":
structure.composition.reduced_formula
})
energies = []
volumes = []
force_constants = []
for d in docs:
s = Structure.from_dict(
d["calcs_reversed"][-1]["output"]['structure'])
energies.append(d["calcs_reversed"][-1]["output"]['energy'])
volumes.append(s.volume)
force_constants.append(
d["calcs_reversed"][-1]["output"]['force_constants'])
summary_dict["energies"] = energies
summary_dict["volumes"] = volumes
summary_dict["force_constants"] = force_constants
alpha, T = get_phonopy_thermal_expansion(energies, volumes,
force_constants, structure,
t_min, t_step, t_max, mesh,
eos, pressure)
summary_dict["alpha"] = alpha
summary_dict["T"] = T
with open("thermal_expansion.json", "w") as f:
f.write(json.dumps(summary_dict, default=DATETIME_HANDLER))
# TODO: @matk86 - there needs to be a way to insert this into a database! And also
# a builder to put it into materials collection... -computron
logger.info("Thermal expansion coefficient calculation complete.")
def run_task(self, fw_spec):
cmd = env_chk(self["cmd"], fw_spec)
if self.get("expand_vars", False):
cmd = os.path.expandvars(cmd)
logger.info("Running command: {}".format(cmd))
return_code = subprocess.call(cmd, shell=True)
logger.info("Command {} finished running with returncode: {}".format(cmd, return_code))
def run_task(self, fw_spec):
cmd = env_chk(self["vasp_cmd"], fw_spec)
if self.get("expand_vars", False):
cmd = os.path.expandvars(cmd)
logger.info("Running command: {}".format(cmd))
return_code = subprocess.call(cmd, shell=True)
logger.info("Command {} finished running with returncode: {}".format(cmd, return_code))
def run_task(self, fw_spec):
additional_fields = self.get("additional_fields", {})
# pass the additional_fields first to avoid overriding BoltztrapAnalyzer items
d = additional_fields.copy()
btrap_dir = os.path.join(os.getcwd(), "boltztrap")
d["boltztrap_dir"] = btrap_dir
bta = BoltztrapAnalyzer.from_files(btrap_dir)
d.update(bta.as_dict())
d["scissor"] = bta.intrans["scissor"]
# trim the output
for x in ['cond', 'seebeck', 'kappa', 'hall', 'mu_steps', 'mu_doping', 'carrier_conc']:
del d[x]
if not self.get("hall_doping"):
del d["hall_doping"]
bandstructure_dir = os.getcwd()
d["bandstructure_dir"] = bandstructure_dir
# add the structure
v, o = get_vasprun_outcar(bandstructure_dir, parse_eigen=False, parse_dos=False)
structure = v.final_structure
d["structure"] = structure.as_dict()
d["formula_pretty"] = structure.composition.reduced_formula
d.update(get_meta_from_structure(structure))
# add the spacegroup
sg = SpacegroupAnalyzer(Structure.from_dict(d["structure"]), 0.1)
d["spacegroup"] = {"symbol": sg.get_space_group_symbol(),
"number": sg.get_space_group_number(),
"point_group": sg.get_point_group_symbol(),
"source": "spglib",
"crystal_system": sg.get_crystal_system(),
"hall": sg.get_hall()}
d["created_at"] = datetime.utcnow()
db_file = env_chk(self.get('db_file'), fw_spec)
if not db_file:
del d["dos"]
with open(os.path.join(btrap_dir, "boltztrap.json"), "w") as f:
f.write(json.dumps(d, default=DATETIME_HANDLER))
else:
mmdb = VaspCalcDb.from_db_file(db_file, admin=True)
# dos gets inserted into GridFS
dos = json.dumps(d["dos"], cls=MontyEncoder)
fsid, compression = mmdb.insert_gridfs(dos, collection="dos_boltztrap_fs",
compress=True)
d["dos_boltztrap_fs_id"] = fsid
del d["dos"]
mmdb.db.boltztrap.insert(d)
def run_task(self, fw_spec):
additional_fields = self.get("additional_fields", {})
# pass the additional_fields first to avoid overriding BoltztrapAnalyzer items
d = additional_fields.copy()
btrap_dir = os.path.join(os.getcwd(), "boltztrap")
d["boltztrap_dir"] = btrap_dir
bta = BoltztrapAnalyzer.from_files(btrap_dir)
d.update(bta.as_dict())
d["scissor"] = bta.intrans["scissor"]
# trim the output
for x in ['cond', 'seebeck', 'kappa', 'hall', 'mu_steps', 'mu_doping', 'carrier_conc']:
del d[x]
if not self.get("hall_doping"):
del d["hall_doping"]
bandstructure_dir = os.getcwd()
d["bandstructure_dir"] = bandstructure_dir
# add the structure
v, o = get_vasprun_outcar(bandstructure_dir, parse_eigen=False, parse_dos=False)
structure = v.final_structure
d["structure"] = structure.as_dict()
d["formula_pretty"] = structure.composition.reduced_formula
d.update(get_meta_from_structure(structure))
# add the spacegroup
sg = SpacegroupAnalyzer(Structure.from_dict(d["structure"]), 0.1)
d["spacegroup"] = {"symbol": sg.get_space_group_symbol(),
"number": sg.get_space_group_number(),
"point_group": sg.get_point_group_symbol(),
"source": "spglib",
"crystal_system": sg.get_crystal_system(),
"hall": sg.get_hall()}
d["created_at"] = datetime.utcnow()
db_file = env_chk(self.get('db_file'), fw_spec)
if not db_file:
del d["dos"]
with open(os.path.join(btrap_dir, "boltztrap.json"), "w") as f:
f.write(json.dumps(d, default=DATETIME_HANDLER))
else:
mmdb = VaspCalcDb.from_db_file(db_file, admin=True)
# dos gets inserted into GridFS
dos = json.dumps(d["dos"], cls=MontyEncoder)
fsid, compression = mmdb.insert_gridfs(dos, collection="dos_boltztrap_fs",
compress=True)
d["dos_boltztrap_fs_id"] = fsid
del d["dos"]
mmdb.db.boltztrap.insert(d)
def run_task(self, fw_spec):
# get the directory that contains the QChem dir to parse
calc_dir = os.getcwd()
if "calc_dir" in self:
calc_dir = self["calc_dir"]
elif self.get("calc_loc"):
calc_dir = get_calc_loc(self["calc_loc"],
fw_spec["calc_locs"])["path"]
input_file = self.get("input_file", "mol.qin")
output_file = self.get("output_file", "mol.qout")
multirun = self.get("multirun", False)
# parse the QChem directory
logger.info("PARSING DIRECTORY: {}".format(calc_dir))
additional_fields = self.get("additional_fields", [])
drone = QChemDrone(additional_fields=additional_fields)
# assimilate (i.e., parse)
task_doc = drone.assimilate(
path=calc_dir,
input_file=input_file,
output_file=output_file,
multirun=multirun)
if "tags" in fw_spec:
task_doc.update({"tags": fw_spec["tags"]})
# Check for additional keys to set based on the fw_spec
if self.get("fw_spec_field"):
task_doc.update({self.get("fw_spec_field"): fw_spec.get(self.get("fw_spec_field"))})
# Update fw_spec with final/optimized structure
update_spec = {}
if task_doc.get("output").get("optimized_molecule"):
update_spec["prev_calc_molecule"] = task_doc["output"]["optimized_molecule"]
update_spec["prev_calc_mulliken"] = task_doc["output"]["mulliken"]
if "RESP" in task_doc["output"]:
update_spec["prev_calc_resp"] = task_doc["output"]["RESP"]
elif "ESP" in task_doc["output"]:
update_spec["prev_calc_esp"] = task_doc["output"]["ESP"]
# get the database connection
db_file = env_chk(self.get("db_file"), fw_spec)
# db insertion or taskdoc dump
if not db_file:
with open(os.path.join(calc_dir, "task.json"), "w") as f:
f.write(json.dumps(task_doc, default=DATETIME_HANDLER))
else:
mmdb = QChemCalcDb.from_db_file(db_file, admin=True)
t_id = mmdb.insert(task_doc)
logger.info("Finished parsing with task_id: {}".format(t_id))
return FWAction(
stored_data={"task_id": task_doc.get("task_id", None)},
update_spec=update_spec)
def run_task(self, fw_spec):
nm_norms = np.array(fw_spec["normalmodes"]["norms"])
nm_eigenvals = np.array(fw_spec["normalmodes"]["eigenvals"])
structure = fw_spec["normalmodes"]["structure"]
masses = np.array([site.specie.data['Atomic mass'] for site in structure])
# the eigenvectors read from vasprun.xml are not divided by sqrt(M_i)
nm_norms = nm_norms / np.sqrt(masses)
# To get the actual eigenvals, the values read from vasprun.xml must be multiplied by -1.
# frequency_i = sqrt(-e_i)
# To convert the frequency to THZ: multiply sqrt(-e_i) by 15.633
# To convert the frequency to cm^-1: multiply sqrt(-e_i) by 82.995
nm_frequencies = np.sqrt(np.abs(nm_eigenvals)) * 82.995 # cm^-1
d = {"structure": structure.as_dict(),
"normalmodes": {"eigenvals": fw_spec["normalmodes"]["eigenvals"],
"eigenvecs": fw_spec["normalmodes"]["eigenvecs"]
},
"frequencies": nm_frequencies.tolist()
}
mode_disps = fw_spec["raman_epsilon"].keys()
# store the displacement & epsilon for each mode in a dictionary
modes_eps_dict = defaultdict(list)
for md in mode_disps:
modes_eps_dict[fw_spec["raman_epsilon"][md]["mode"]].append(
[fw_spec["raman_epsilon"][md]["displacement"],
fw_spec["raman_epsilon"][md]["epsilon"]])
# raman tensor = finite difference derivative of epsilon wrt displacement.
raman_tensor_dict = {}
scale = np.sqrt(structure.volume/2.0) / 4.0 / np.pi
for k, v in modes_eps_dict.items():
raman_tensor = (np.array(v[0][1]) - np.array(v[1][1])) / (v[0][0] - v[1][0])
# frequency in cm^-1
omega = nm_frequencies[k]
if nm_eigenvals[k] > 0:
logger.warn("Mode: {} is UNSTABLE. Freq(cm^-1) = {}".format(k, -omega))
raman_tensor = scale * raman_tensor * np.sum(nm_norms[k]) / np.sqrt(omega)
raman_tensor_dict[str(k)] = raman_tensor.tolist()
d["raman_tensor"] = raman_tensor_dict
d["state"] = "successful"
# store the results
db_file = env_chk(self.get("db_file"), fw_spec)
if not db_file:
with open("raman.json", "w") as f:
f.write(json.dumps(d, default=DATETIME_HANDLER))
else:
db = MMVaspDb.from_db_file(db_file, admin=True)
db.collection = db.db["raman"]
db.collection.insert_one(d)
logger.info("RAMAN TENSOR CALCULATION COMPLETE")
logger.info("The frequencies are in the units of cm^-1")
logger.info("To convert the frequency to THz: multiply by 0.1884")
return FWAction()
def run_task(self, fw_spec):
from atomate.vasp.database import VaspCalcDb
db_file = env_chk(self["db_file"], fw_spec)
vasp_db = VaspCalcDb.from_db_file(db_file, admin=True)
content = {}
content["metadata"] = self.get('metadata', {})
content["path"] = fw_spec["calc_locs"][-1]["path"]
content["Pos_Shape_relax"] = self.get('Pos_Shape_relax')
vasp_db.db["relax"].insert_one(content)
def run_task(self, fw_spec):
cmd = env_chk(self["cmd"], fw_spec)
if self.get("expand_vars", False):
cmd = os.path.expandvars(cmd)
logger.info(f"Running command: {cmd}")
return_code = subprocess.call(cmd, shell=True)
logger.info(
f"Command {cmd} finished running with returncode: {return_code}")
def run_task(self, fw_spec):
lobster_cmd = env_chk(self.get("lobster_cmd"), fw_spec)
gzip_output = self.get("gzip_output", True)
gzip_WAVECAR = self.get("gzip_WAVECAR", False)
if gzip_WAVECAR:
add_files_to_gzip = VASP_OUTPUT_FILES
else:
add_files_to_gzip = [f for f in VASP_OUTPUT_FILES if f not in ["WAVECAR"]]
handler_groups = {"default": [], "no_handler": []}
validator_groups = {
"default": [
LobsterFilesValidator(),
EnoughBandsValidator(output_filename="lobsterout"),
],
"strict": [
ChargeSpillingValidator(output_filename="lobsterout"),
LobsterFilesValidator(),
EnoughBandsValidator(output_filename="lobsterout"),
],
"no_validator": [],
}
handler_group = self.get("handler_group", "default")
if isinstance(handler_group, str):
handlers = handler_groups[handler_group]
else:
handlers = handler_group
validator_group = self.get("validator_group", "default")
if isinstance(validator_group, str):
validators = validator_groups[validator_group]
else:
validators = handler_group
# LobsterJob gzips output files, Custodian would gzip all output files (even slurm)
jobs = [
LobsterJob(
lobster_cmd=lobster_cmd,
output_file="lobster.out",
stderr_file="std_err_lobster.txt",
gzipped=gzip_output,
add_files_to_gzip=add_files_to_gzip,
)
]
c = Custodian(
handlers=handlers,
jobs=jobs,
validators=validators,
gzipped_output=False,
max_errors=5,
)
c.run()
if os.path.exists(zpath("custodian.json")):
stored_custodian_data = {"custodian": loadfn(zpath("custodian.json"))}
return FWAction(stored_data=stored_custodian_data)
def run_task(self, fw_spec):
db_file = env_chk(self["db_file"], fw_spec)
vasp_db = VaspCalcDb.from_db_file(db_file, admin=True)
content = {}
content["metadata"] = self.get('metadata', {})
content["path"] = fw_spec["calc_locs"][-1]["path"]
content["run_isif2"] = self.get('run_isif2')
content["pass_isif4"] = self.get('pass_isif4')
vasp_db.db["relax"].insert_one(content)
def run_task(self, fw_spec):
# get the directory that contains the VASP dir to parse
calc_dir = os.getcwd()
if "calc_dir" in self:
calc_dir = self["calc_dir"]
elif self.get("calc_loc"):
calc_dir = get_calc_loc(self["calc_loc"],
fw_spec["calc_locs"])["path"]
# parse the VASP directory
logger.info("PARSING DIRECTORY: {}".format(calc_dir))
drone = VaspDrone(additional_fields=self.get("additional_fields"),
parse_dos=self.get("parse_dos", False),
bandstructure_mode=self.get("bandstructure_mode",
False))
# assimilate (i.e., parse)
task_doc = drone.assimilate(calc_dir)
# Check for additional keys to set based on the fw_spec
if self.get("fw_spec_field"):
task_doc.update(fw_spec[self.get("fw_spec_field")])
# get the database connection
db_file = env_chk(self.get('db_file'), fw_spec)
# db insertion or taskdoc dump
if not db_file:
with open("task.json", "w") as f:
f.write(json.dumps(task_doc, default=DATETIME_HANDLER))
else:
mmdb = VaspMDCalcDb.from_db_file(db_file, admin=True)
# prevent duplicate insertion
mmdb.db.tasks.find_one_and_delete({
'formula_pretty':
task_doc['formula_pretty'],
'task_label':
task_doc['task_label']
})
t_id = mmdb.insert_task(
task_doc,
parse_dos=self.get("parse_dos", False),
parse_bs=bool(self.get("bandstructure_mode", False)),
md_structures=self.get("md_structures", True))
logger.info("Finished parsing with task_id: {}".format(t_id))
if self.get("defuse_unsuccessful", True):
defuse_children = (task_doc["state"] != "successful")
else:
defuse_children = False
return FWAction(stored_data={"task_id": task_doc.get("task_id", None)},
defuse_children=defuse_children)
def run_task(self, fw_spec):
from pymatgen.analysis.eos import EOS
eos = self.get("eos", "vinet")
tag = self["tag"]
db_file = env_chk(self.get("db_file"), fw_spec)
summary_dict = {"eos": eos}
to_db = self.get("to_db", True)
# collect and store task_id of all related tasks to make unique links with "tasks" collection
all_task_ids = []
mmdb = VaspCalcDb.from_db_file(db_file, admin=True)
# get the optimized structure
d = mmdb.collection.find_one({"task_label": "{} structure optimization".format(tag)})
all_task_ids.append(d["task_id"])
structure = Structure.from_dict(d["calcs_reversed"][-1]["output"]['structure'])
summary_dict["structure"] = structure.as_dict()
summary_dict["formula_pretty"] = structure.composition.reduced_formula
# get the data(energy, volume, force constant) from the deformation runs
docs = mmdb.collection.find({"task_label": {"$regex": "{} bulk_modulus*".format(tag)},
"formula_pretty": structure.composition.reduced_formula})
energies = []
volumes = []
for d in docs:
s = Structure.from_dict(d["calcs_reversed"][-1]["output"]['structure'])
energies.append(d["calcs_reversed"][-1]["output"]['energy'])
volumes.append(s.volume)
all_task_ids.append(d["task_id"])
summary_dict["energies"] = energies
summary_dict["volumes"] = volumes
summary_dict["all_task_ids"] = all_task_ids
# fit the equation of state
eos = EOS(eos)
eos_fit = eos.fit(volumes, energies)
summary_dict["bulk_modulus"] = eos_fit.b0_GPa
# TODO: find a better way for passing tags of the entire workflow to db - albalu
if fw_spec.get("tags", None):
summary_dict["tags"] = fw_spec["tags"]
summary_dict["results"] = dict(eos_fit.results)
summary_dict["created_at"] = datetime.utcnow()
# db_file itself is required but the user can choose to pass the results to db or not
if to_db:
mmdb.collection = mmdb.db["eos"]
mmdb.collection.insert_one(summary_dict)
else:
with open("bulk_modulus.json", "w") as f:
f.write(json.dumps(summary_dict, default=DATETIME_HANDLER))
# TODO: @matk86 - there needs to be a builder to put it into materials collection... -computron
logger.info("Bulk modulus calculation complete.")
def run_task(self, fw_spec):
from pymatgen.analysis.eos import EOS
eos = self.get("eos", "vinet")
tag = self["tag"]
db_file = env_chk(self.get("db_file"), fw_spec)
summary_dict = {"eos": eos}
to_db = self.get("to_db", True)
# collect and store task_id of all related tasks to make unique links with "tasks" collection
all_task_ids = []
mmdb = VaspCalcDb.from_db_file(db_file, admin=True)
# get the optimized structure
d = mmdb.collection.find_one({"task_label": "{} structure optimization".format(tag)})
all_task_ids.append(d["task_id"])
structure = Structure.from_dict(d["calcs_reversed"][-1]["output"]['structure'])
summary_dict["structure"] = structure.as_dict()
summary_dict["formula_pretty"] = structure.composition.reduced_formula
# get the data(energy, volume, force constant) from the deformation runs
docs = mmdb.collection.find({"task_label": {"$regex": "{} bulk_modulus*".format(tag)},
"formula_pretty": structure.composition.reduced_formula})
energies = []
volumes = []
for d in docs:
s = Structure.from_dict(d["calcs_reversed"][-1]["output"]['structure'])
energies.append(d["calcs_reversed"][-1]["output"]['energy'])
volumes.append(s.volume)
all_task_ids.append(d["task_id"])
summary_dict["energies"] = energies
summary_dict["volumes"] = volumes
summary_dict["all_task_ids"] = all_task_ids
# fit the equation of state
eos = EOS(eos)
eos_fit = eos.fit(volumes, energies)
summary_dict["bulk_modulus"] = eos_fit.b0_GPa
# TODO: find a better way for passing tags of the entire workflow to db - albalu
if fw_spec.get("tags", None):
summary_dict["tags"] = fw_spec["tags"]
summary_dict["results"] = dict(eos_fit.results)
summary_dict["created_at"] = datetime.utcnow()
# db_file itself is required but the user can choose to pass the results to db or not
if to_db:
mmdb.collection = mmdb.db["eos"]
mmdb.collection.insert_one(summary_dict)
else:
with open("bulk_modulus.json", "w") as f:
f.write(json.dumps(summary_dict, default=DATETIME_HANDLER))
# TODO: @matk86 - there needs to be a builder to put it into materials collection... -computron
logger.info("Bulk modulus calculation complete.")
def run_task(self, fw_spec):
# get the database connection to the approx_neb collection
db_file = env_chk(self["db_file"], fw_spec)
mmdb = VaspCalcDb.from_db_file(db_file, admin=True)
mmdb.collection = mmdb.db["approx_neb"]
# get approx_neb doc specified by wf_uuid
wf_uuid = self.get("approx_neb_wf_uuid")
approx_neb_doc = mmdb.collection.find_one({"wf_uuid": wf_uuid}, {
"pathfinder": 1,
"images": 1
})
# get structures stored in "pathfinder" field
pathfinder_key = self["pathfinder_key"]
structure_docs = approx_neb_doc["pathfinder"][pathfinder_key]["images"]
fixed_index = approx_neb_doc["pathfinder"][pathfinder_key][
"relax_site_indexes"]
# apply selective dynamics to get images (list of pymatgen structures)
fixed_specie = self["mobile_specie"]
scheme = self["selective_dynamics_scheme"]
images = self.get_images_list(structure_docs, scheme, fixed_index,
fixed_specie)
# assemble images output to be stored in approx_neb collection
images_output = []
for n, image in enumerate(images):
images_output.append({
"index": n,
"input_structure": image.as_dict(),
"selective_dynamics_scheme": scheme,
})
# store images output in approx_neb collection
if "images" not in approx_neb_doc.keys():
images_subdoc = {}
else:
images_subdoc = approx_neb_doc["images"]
images_subdoc.update({pathfinder_key: images_output})
mmdb.collection.update_one(
{"wf_uuid": wf_uuid},
{
"$set": {
"images": images_subdoc,
"last_updated": datetime.utcnow()
}
},
)
return FWAction(stored_data={
"wf_uuid": wf_uuid,
"images_output": images_output
})
def run_task(self, fw_spec):
self.xml = self.get("xml", None)
self.kmesh_factor = self.get("kmesh_factor", 1)
with open("KPOINTS", "r") as f:
kpoints = f.readlines()
with open("INCAR", "r") as f:
incar = f.readlines()
if self.kmesh_factor > 1:
shutil.copyfile("INCAR", "INCAR.nscf")
shutil.copyfile("KPOINTS", "KPOINTS.nscf")
shutil.copyfile("INCAR.Static", "INCAR")
shutil.copyfile("KPOINTS.Static", "KPOINTS")
if self.xml is not None:
with open(self.xml, 'rb') as f:
xmldata = f.read()
binxmldata = gzip.compress(bytes(xmldata))
with open("DOSCAR", 'rb') as f:
doscar = f.read()
bindoscar = gzip.compress(bytes(doscar))
#with gzip.open("zen.txt.gz", "wb") as f:
#f.write(bindata)
self.db_file = env_chk(self.get("db_file"), fw_spec)
self.vasp_db = VaspCalcDb.from_db_file(self.db_file, admin=True)
structure = self.get('structure', Structure.from_file('POSCAR'))
xml_data = {
'metadata': {
'tag': self.get('tag')
},
'hostname':
socket.gethostname(),
self.xml.replace(".", "_") + "_gz":
bson.Binary(pickle.dumps(binxmldata)),
'DOSCAR_gz':
bson.Binary(pickle.dumps(bindoscar)),
'volume':
structure.volume,
'INCAR':
incar,
'KPOINTS':
kpoints,
'VASP':
get_code_version(),
'last_updated':
datetime.datetime.utcnow(),
'US_eastern_time':
datetime.datetime.now(pytz.timezone('US/Eastern')),
'structure':
structure.as_dict(),
'formula_pretty':
structure.composition.reduced_formula
}
self.vasp_db.db['xmlgz'].insert_one(xml_data)
def run_task(self, fw_spec):
cmd = self.get("qchem_cmd")
scratch_dir = env_chk(self.get("scratch_dir"), fw_spec)
if scratch_dir == None:
scratch_dir = "/dev/shm/qcscratch/"
os.putenv("QCSCRATCH", scratch_dir)
logger.info("Running command: {}".format(cmd))
return_code = subprocess.call(cmd, shell=True)
logger.info("Command {} finished running with return code: {}".format(
cmd, return_code))
def run_task(self, fw_spec):
# get the directory that contains the VASP dir to parse
calc_dir = os.getcwd()
if "calc_dir" in self:
calc_dir = self["calc_dir"]
elif self.get("calc_loc"):
calc_dir = get_calc_loc(self["calc_loc"],
fw_spec["calc_locs"])["path"]
# parse the VASP directory
logger.info("PARSING DIRECTORY: {}".format(calc_dir))
drone = VaspDrone(additional_fields=self.get("additional_fields"),
parse_dos=self.get("parse_dos", False),
compress_dos=1,
bandstructure_mode=self.get("bandstructure_mode",
False),
compress_bs=1)
# assimilate (i.e., parse)
task_doc = drone.assimilate(calc_dir)
# Check for additional keys to set based on the fw_spec
if self.get("fw_spec_field"):
task_doc.update(fw_spec[self.get("fw_spec_field")])
# get the database connection
db_file = env_chk(self.get('db_file'), fw_spec)
# db insertion or taskdoc dump
if not db_file:
with open("task.json", "w") as f:
f.write(json.dumps(task_doc, default=DATETIME_HANDLER))
else:
mmdb = VaspCalcDb.from_db_file(db_file, admin=True)
t_id = mmdb.insert_task(task_doc,
parse_dos=self.get("parse_dos", False),
parse_bs=bool(
self.get("bandstructure_mode", False)))
logger.info("Finished parsing with task_id: {}".format(t_id))
defuse_children = False
if task_doc["state"] != "successful":
if self.get("defuse_unsuccessful", DEFUSE_UNSUCCESSFUL) is True:
defuse_children = True
elif self.get("defuse_unsuccessful", DEFUSE_UNSUCCESSFUL).lower() \
== "fizzle":
raise RuntimeError(
"VaspToDb indicates that job is not successful "
"(perhaps your job did not converge within the "
"limit of electronic/ionic iterations)!")
return FWAction(stored_data={"task_id": task_doc.get("task_id", None)},
defuse_children=defuse_children)
def run_task(self, fw_spec):
incar_name = self.get("input_filename", "INCAR")
incar = Incar.from_file(incar_name)
incar_update = env_chk(self.get('incar_update'), fw_spec)
incar_multiply = env_chk(self.get('incar_multiply'), fw_spec)
incar_dictmod = env_chk(self.get('incar_dictmod'), fw_spec)
if incar_update:
incar.update(incar_update)
if incar_multiply:
for k in incar_multiply:
incar[k] = incar[k] * incar_multiply[k]
if incar_dictmod:
apply_mod(incar_dictmod, incar)
incar.write_file(self.get("output_filename", "INCAR"))
def run_task(self, fw_spec):
nm_eigenvecs = np.array(fw_spec["normalmodes"]["eigenvecs"])
nm_eigenvals = np.array(fw_spec["normalmodes"]["eigenvals"])
nm_norms = np.linalg.norm(nm_eigenvecs, axis=2)
structure = fw_spec["normalmodes"]["structure"]
masses = np.array([site.specie.data['Atomic mass'] for site in structure])
nm_norms = nm_norms / np.sqrt(masses) # eigenvectors in vasprun.xml are not divided by sqrt(M_i)
# To get the actual eigenvals, the values read from vasprun.xml must be multiplied by -1.
# frequency_i = sqrt(-e_i)
# To convert the frequency to THZ: multiply sqrt(-e_i) by 15.633
# To convert the frequency to cm^-1: multiply sqrt(-e_i) by 82.995
nm_frequencies = np.sqrt(np.abs(nm_eigenvals)) * 82.995 # cm^-1
d = {"structure": structure.as_dict(),
"formula_pretty": structure.composition.reduced_formula,
"normalmodes": {"eigenvals": fw_spec["normalmodes"]["eigenvals"],
"eigenvecs": fw_spec["normalmodes"]["eigenvecs"]
},
"frequencies": nm_frequencies.tolist()}
# store the displacement & epsilon for each mode in a dictionary
mode_disps = fw_spec["raman_epsilon"].keys()
modes_eps_dict = defaultdict(list)
for md in mode_disps:
modes_eps_dict[fw_spec["raman_epsilon"][md]["mode"]].append(
[fw_spec["raman_epsilon"][md]["displacement"],
fw_spec["raman_epsilon"][md]["epsilon"]])
# raman tensor = finite difference derivative of epsilon wrt displacement.
raman_tensor_dict = {}
scale = np.sqrt(structure.volume/2.0) / 4.0 / np.pi
for k, v in modes_eps_dict.items():
raman_tensor = (np.array(v[0][1]) - np.array(v[1][1])) / (v[0][0] - v[1][0])
# frequency in cm^-1
omega = nm_frequencies[k]
if nm_eigenvals[k] > 0:
logger.warn("Mode: {} is UNSTABLE. Freq(cm^-1) = {}".format(k, -omega))
raman_tensor = scale * raman_tensor * np.sum(nm_norms[k]) / np.sqrt(omega)
raman_tensor_dict[str(k)] = raman_tensor.tolist()
d["raman_tensor"] = raman_tensor_dict
d["state"] = "successful"
# store the results
db_file = env_chk(self.get("db_file"), fw_spec)
if not db_file:
with open("raman.json", "w") as f:
f.write(json.dumps(d, default=DATETIME_HANDLER))
else:
db = VaspCalcDb.from_db_file(db_file, admin=True)
db.collection = db.db["raman"]
db.collection.insert_one(d)
logger.info("Raman tensor calculation complete.")
return FWAction()
def test_env_chk(self):
fw_spec_valid = {"_fw_env": {"hello": "there"}}
fw_spec_invalid = {}
self.assertEqual(env_chk("hello", fw_spec_valid), "hello")
self.assertEqual(env_chk([1, 2, 3], fw_spec_valid), [1, 2, 3])
self.assertEqual(env_chk(defaultdict(int), fw_spec_valid), defaultdict(int))
self.assertEqual(env_chk(">>hello<<", fw_spec_valid), "there")
self.assertRaises(KeyError, env_chk, ">>hello1<<", fw_spec_valid)
self.assertEqual(env_chk(">>hello1<<", fw_spec_valid, False), None)
self.assertRaises(KeyError, env_chk, ">>hello<<", fw_spec_invalid)
self.assertEqual(env_chk(">>hello<<", fw_spec_invalid, False), None)
self.assertEqual(env_chk(">>hello<<", fw_spec_invalid, False, "fallback"), "fallback")
self.assertEqual(env_chk(None, fw_spec_valid, False), None)
self.assertEqual(env_chk(None, fw_spec_valid, False, "fallback"), "fallback")
def run_task(self, fw_spec):
kpoints_name = self.get("input_filename", "KPOINTS")
kpoints = Kpoints.from_file(kpoints_name)
kpoints_update = env_chk(self.get("kpoints_update"), fw_spec)
if kpoints_update:
for key, value in kpoints_update.items():
setattr(kpoints, key, value)
kpoints.write_file(self.get("output_filename", "KPOINTS"))
def run_task(self, fw_spec):
db_file = env_chk(self["db_file"], fw_spec)
wf_uuid = self["wf_uuid"]
# Get Heisenberg models from db
mmdb = VaspCalcDb.from_db_file(db_file, admin=True)
mmdb.collection = mmdb.db["exchange"]
# Get documents
docs = list(
mmdb.collection.find({"wf_meta.wf_uuid": wf_uuid},
["heisenberg_model", "nn_cutoff"]))
hmodels = [
HeisenbergModel.from_dict(d["heisenberg_model"]) for d in docs
]
cutoffs = [d["nn_cutoff"] for d in docs]
# Take <J> only if no static calcs
if self["average"]:
hmodel = hmodels[0].as_dict()
else:
# Check for J_ij convergence
converged_list = []
for cutoff, hmodel in zip(cutoffs, hmodels):
ex_params = hmodel.ex_params
converged = True
# J_ij exists
if len(ex_params) > 1:
E0 = abs(ex_params["E0"])
for k, v in ex_params.items():
if k != "E0":
if abs(v) > E0: # |J_ij| > |E0| unphysical!
converged = False
else: # Only <J> was computed
converged = False
if converged:
converged_list.append(hmodel.as_dict())
# If multiple Heisenberg Models converged, take the maximal cutoff
if len(converged_list) > 0:
hmodel = converged_list[-1] # Largest cutoff
else: # No converged models
hmodel = None
# Update FW spec with converged hmodel or None
update_spec = {"converged_heisenberg_model": hmodel}
return FWAction(update_spec=update_spec)
def run_task(self, fw_spec):
# Get optimized structure
# TODO: will this find the correct path if the workflow is rerun from the start?
optimize_loc = fw_spec["calc_locs"][0]["path"]
logger.info("PARSING INITIAL OPTIMIZATION DIRECTORY: {}".format(optimize_loc))
drone = VaspDrone()
optimize_doc = drone.assimilate(optimize_loc)
opt_struct = Structure.from_dict(optimize_doc["calcs_reversed"][0]["output"]["structure"])
d = {"analysis": {}, "deformation_tasks": fw_spec["deformation_tasks"],
"initial_structure": self['structure'].as_dict(),
"optimized_structure": opt_struct.as_dict()}
if fw_spec.get("tags",None):
d["tags"] = fw_spec["tags"]
dtypes = fw_spec["deformation_tasks"].keys()
defos = [fw_spec["deformation_tasks"][dtype]["deformation_matrix"]
for dtype in dtypes]
stresses = [fw_spec["deformation_tasks"][dtype]["stress"] for dtype in dtypes]
stress_dict = {IndependentStrain(defo) : Stress(stress) for defo, stress
in zip(defos, stresses)}
logger.info("ANALYZING STRESS/STRAIN DATA")
# DETERMINE IF WE HAVE 6 "UNIQUE" deformations
if len(set([de[:3] for de in dtypes])) == 6:
# Perform Elastic tensor fitting and analysis
result = ElasticTensor.from_stress_dict(stress_dict)
d["elastic_tensor"] = result.voigt.tolist()
kg_average = result.kg_average
d.update({"K_Voigt": kg_average[0], "G_Voigt": kg_average[1],
"K_Reuss": kg_average[2], "G_Reuss": kg_average[3],
"K_Voigt_Reuss_Hill": kg_average[4],
"G_Voigt_Reuss_Hill": kg_average[5]})
d["universal_anisotropy"] = result.universal_anisotropy
d["homogeneous_poisson"] = result.homogeneous_poisson
else:
raise ValueError("Fewer than 6 unique deformations")
d["state"] = "successful"
# Save analysis results in json or db
db_file = env_chk(self.get('db_file'), fw_spec)
if not db_file:
with open("elasticity.json", "w") as f:
f.write(json.dumps(d, default=DATETIME_HANDLER))
else:
db = MMVaspDb.from_db_file(db_file, admin=True)
db.collection = db.db["elasticity"]
db.collection.insert_one(d)
logger.info("ELASTIC ANALYSIS COMPLETE")
return FWAction()
def run_task(self, fw_spec):
handler_groups = {
"default": [VaspErrorHandler(), MeshSymmetryErrorHandler(), UnconvergedErrorHandler(),
NonConvergingErrorHandler(),PotimErrorHandler(),
PositiveEnergyErrorHandler(), FrozenJobErrorHandler(), StdErrHandler(),
DriftErrorHandler()],
"strict": [VaspErrorHandler(), MeshSymmetryErrorHandler(), UnconvergedErrorHandler(),
NonConvergingErrorHandler(),PotimErrorHandler(),
PositiveEnergyErrorHandler(), FrozenJobErrorHandler(),
StdErrHandler(), AliasingErrorHandler(), DriftErrorHandler()],
"md": [VaspErrorHandler(), NonConvergingErrorHandler()],
"no_handler": []
}
vasp_cmd = env_chk(self["vasp_cmd"], fw_spec)
if isinstance(vasp_cmd, six.string_types):
vasp_cmd = os.path.expandvars(vasp_cmd)
vasp_cmd = shlex.split(vasp_cmd)
# initialize variables
scratch_dir = env_chk(self.get("scratch_dir"), fw_spec)
gzip_output = self.get("gzip_output", True)
max_errors = self.get("max_errors", 5)
auto_npar = env_chk(self.get("auto_npar"), fw_spec, strict=False, default=False)
gamma_vasp_cmd = env_chk(self.get("gamma_vasp_cmd"), fw_spec, strict=False, default=None)
jobs = [VaspJob(vasp_cmd, auto_npar=auto_npar, gamma_vasp_cmd=gamma_vasp_cmd)]
# construct handlers
handlers = handler_groups[self.get("handler_group", "default")]
validators = []
c = Custodian(handlers, jobs, validators=validators, max_errors=max_errors,
scratch_dir=scratch_dir, gzipped_output=gzip_output)
c.run()
def run_task(self, fw_spec):
mpr = MPRester(env_chk(self.get("MAPI_KEY"), fw_spec))
vasprun, outcar = get_vasprun_outcar(self.get("calc_dir", "."), parse_dos=False, parse_eigen=False)
my_entry = vasprun.get_computed_entry(inc_structure=False)
stored_data = mpr.get_stability([my_entry])[0]
if stored_data["e_above_hull"] > self.get("ehull_cutoff", 0.05):
return FWAction(stored_data=stored_data, exit=True, defuse_workflow=True)
else:
return FWAction(stored_data=stored_data)
def run_task(self, fw_spec):
ref_file = self.get("json_filename", "task.json")
calc_dir = self.get("calc_dir", os.getcwd())
with open(os.path.join(calc_dir, ref_file), "r") as fp:
task_doc = json.load(fp)
db_file = env_chk(self.get('db_file'), fw_spec)
if not db_file:
with open("task.json", "w") as f:
f.write(json.dumps(task_doc, default=DATETIME_HANDLER))
else:
mmdb = VaspCalcDb.from_db_file(db_file, admin=True)
mmdb.insert(task_doc)
def run_task(self, fw_spec):
# load INCAR
incar_name = self.get("input_filename", "INCAR")
incar = Incar.from_file(incar_name)
# process FireWork env values via env_chk
incar_update = env_chk(self.get("incar_update"), fw_spec)
incar_multiply = env_chk(self.get("incar_multiply"), fw_spec)
incar_dictmod = env_chk(self.get("incar_dictmod"), fw_spec)
if incar_update:
incar.update(incar_update)
if incar_multiply:
for k in incar_multiply:
incar[k] = incar[k] * incar_multiply[k]
if incar_dictmod:
apply_mod(incar_dictmod, incar)
# write INCAR
incar.write_file(self.get("output_filename", "INCAR"))
def run_task(self, fw_spec):
incar_name = self.get("input_filename", "INCAR")
incar = Incar.from_file(incar_name)
incar_update = env_chk(self.get('incar_update'), fw_spec)
incar_multiply = env_chk(self.get('incar_multiply'), fw_spec)
incar_dictmod = env_chk(self.get('incar_dictmod'), fw_spec)
if incar_update:
incar.update(incar_update)
if incar_multiply:
for k in incar_multiply:
if hasattr(incar[k], '__iter__'): # is list-like
incar[k] = list(np.multiply(incar[k], incar_multiply[k]))
else:
incar[k] = incar[k] * incar_multiply[k]
if incar_dictmod:
apply_mod(incar_dictmod, incar)
incar.write_file(self.get("output_filename", "INCAR"))
def run_task(self, fw_spec):
potcar_symbols = env_chk(self.get("potcar_symbols"), fw_spec)
functional = self.get("functional", None)
potcar_name = self.get("input_filename", "POTCAR")
potcar = Potcar.from_file(potcar_name)
# Replace PotcarSingles corresponding to elements
# contained in potcar_symbols
for n, psingle in enumerate(potcar):
if psingle.element in potcar_symbols:
potcar[n] = PotcarSingle.from_symbol_and_functional(
potcar_symbols[psingle.element], functional)
potcar.write_file(self.get("output_filename", "POTCAR"))
def run_task(self, fw_spec):
# get the directory that contains the QChem dir to parse
calc_dir = os.getcwd()
if "calc_dir" in self:
calc_dir = self["calc_dir"]
elif self.get("calc_loc"):
calc_dir = get_calc_loc(self["calc_loc"],
fw_spec["calc_locs"])["path"]
input_file = self.get("input_file", "mol.qin")
output_file = self.get("output_file", "mol.qout")
multirun = self.get("multirun", False)
# parse the QChem directory
logger.info("PARSING DIRECTORY: {}".format(calc_dir))
drone = QChemDrone(additional_fields=self.get("additional_fields"))
# assimilate (i.e., parse)
task_doc = drone.assimilate(
path=calc_dir,
input_file=input_file,
output_file=output_file,
multirun=multirun)
# Check for additional keys to set based on the fw_spec
if self.get("fw_spec_field"):
task_doc.update(fw_spec[self.get("fw_spec_field")])
# Update fw_spec with final/optimized structure
update_spec = {}
if task_doc.get("output").get("optimized_molecule"):
update_spec["prev_calc_molecule"] = task_doc["output"][
"optimized_molecule"]
# get the database connection
db_file = env_chk(self.get("db_file"), fw_spec)
# db insertion or taskdoc dump
if not db_file:
with open(os.path.join(calc_dir, "task.json"), "w") as f:
f.write(json.dumps(task_doc, default=DATETIME_HANDLER))
else:
mmdb = QChemCalcDb.from_db_file(db_file, admin=True)
t_id = mmdb.insert(task_doc)
logger.info("Finished parsing with task_id: {}".format(t_id))
return FWAction(
stored_data={"task_id": task_doc.get("task_id", None)},
update_spec=update_spec)
def run_task(self, fw_spec):
from atomate.vasp.analysis.phonopy import get_phonopy_thermal_expansion
tag = self["tag"]
db_file = env_chk(self.get("db_file"), fw_spec)
t_step = self.get("t_step", 10)
t_min = self.get("t_min", 0)
t_max = self.get("t_max", 1000)
mesh = self.get("mesh", [20, 20, 20])
eos = self.get("eos", "vinet")
pressure = self.get("pressure", 0.0)
summary_dict = {}
mmdb = VaspCalcDb.from_db_file(db_file, admin=True)
# get the optimized structure
d = mmdb.collection.find_one({"task_label": "{} structure optimization".format(tag)})
structure = Structure.from_dict(d["calcs_reversed"][-1]["output"]['structure'])
summary_dict["structure"] = structure.as_dict()
summary_dict["formula_pretty"] = structure.composition.reduced_formula
# get the data(energy, volume, force constant) from the deformation runs
docs = mmdb.collection.find({"task_label": {"$regex": "{} thermal_expansion*".format(tag)},
"formula_pretty": structure.composition.reduced_formula})
energies = []
volumes = []
force_constants = []
for d in docs:
s = Structure.from_dict(d["calcs_reversed"][-1]["output"]['structure'])
energies.append(d["calcs_reversed"][-1]["output"]['energy'])
volumes.append(s.volume)
force_constants.append(d["calcs_reversed"][-1]["output"]['force_constants'])
summary_dict["energies"] = energies
summary_dict["volumes"] = volumes
summary_dict["force_constants"] = force_constants
alpha, T = get_phonopy_thermal_expansion(energies, volumes, force_constants, structure,
t_min, t_step, t_max, mesh, eos, pressure)
summary_dict["alpha"] = alpha
summary_dict["T"] = T
with open("thermal_expansion.json", "w") as f:
f.write(json.dumps(summary_dict, default=DATETIME_HANDLER))
# TODO: @matk86 - there needs to be a way to insert this into a database! And also
# a builder to put it into materials collection... -computron
logger.info("Thermal expansion coefficient calculation complete.")
def run_task(self, fw_spec):
from atomate.tools.analysis import get_phonopy_thermal_expansion
tag = self["tag"]
db_file = env_chk(self.get("db_file"), fw_spec)
t_step = self.get("t_step", 10)
t_min = self.get("t_min", 0)
t_max = self.get("t_max", 1000)
mesh = self.get("mesh", [20, 20, 20])
eos = self.get("eos", "vinet")
pressure = self.get("pressure", 0.0)
summary_dict = {}
mmdb = MMVaspDb.from_db_file(db_file, admin=True)
# get the optimized structure
d = mmdb.collection.find_one({"task_label": "{} structure optimization".format(tag)})
structure = Structure.from_dict(d["calcs_reversed"][-1]["output"]['structure'])
summary_dict["structure"] = structure.as_dict()
# get the data(energy, volume, force constant) from the deformation runs
docs = mmdb.collection.find({"task_label": {"$regex": "{} thermal_expansion*".format(tag)},
"formula_pretty": structure.composition.reduced_formula})
energies = []
volumes = []
force_constants = []
for d in docs:
s = Structure.from_dict(d["calcs_reversed"][-1]["output"]['structure'])
energies.append(d["calcs_reversed"][-1]["output"]['energy'])
volumes.append(s.volume)
force_constants.append(d["calcs_reversed"][-1]["output"]['force_constants'])
summary_dict["energies"] = energies
summary_dict["volumes"] = volumes
summary_dict["force_constants"] = force_constants
alpha, T = get_phonopy_thermal_expansion(energies, volumes, force_constants, structure,
t_min, t_step, t_max, mesh, eos, pressure)
summary_dict["alpha"] = alpha
summary_dict["T"] = T
with open("thermal_expansion.json", "w") as f:
f.write(json.dumps(summary_dict, default=DATETIME_HANDLER))
logger.info("THERMAL EXPANSION COEFF CALCULATION COMPLETE")
def run_task(self, fw_spec):
lammps_input = self["lammps_input"]
diffusion_params = self.get("diffusion_params", {})
# get the directory that contains the LAMMPS dir to parse
calc_dir = os.getcwd()
if "calc_dir" in self:
calc_dir = self["calc_dir"]
elif self.get("calc_loc"):
calc_dir = get_calc_loc(self["calc_loc"], fw_spec["calc_locs"])["path"]
# parse the directory
logger.info("PARSING DIRECTORY: {}".format(calc_dir))
d = {}
d["dir_name"] = os.path.abspath(os.getcwd())
d["last_updated"] = datetime.today()
d["input"] = lammps_input.as_dict()
log_file = lammps_input.config_dict["log"]
if isinstance(lammps_input.config_dict["dump"], list):
dump_file = lammps_input.config_dict["dump"][0].split()[4]
else:
dump_file = lammps_input.config_dict["dump"].split()[4]
is_forcefield = hasattr(lammps_input.lammps_data, "bonds_data")
lammpsrun = LammpsRun(lammps_input.data_filename, dump_file, log_file, is_forcefield=is_forcefield)
d["natoms"] = lammpsrun.natoms
d["nmols"] = lammpsrun.nmols
d["box_lengths"] = lammpsrun.box_lengths
d["mol_masses"] = lammpsrun.mol_masses
d["mol_config"] = lammpsrun.mol_config
if diffusion_params:
diffusion_analyzer = lammpsrun.get_diffusion_analyzer(**diffusion_params)
d["analysis"]["diffusion"] = diffusion_analyzer.get_summary_dict()
db_file = env_chk(self.get('db_file'), fw_spec)
# db insertion
if not db_file:
with open("task.json", "w") as f:
f.write(json.dumps(d, default=DATETIME_HANDLER))
else:
mmdb = MMLammpsDb.from_db_file(db_file)
# insert the task document
t_id = mmdb.insert(d)
logger.info("Finished parsing with task_id: {}".format(t_id))
return FWAction(stored_data={"task_id": d.get("task_id", None)})
def run_task(self, fw_spec):
# get the directory that contains the LAMMPS run parse.
calc_dir = os.getcwd()
if "calc_dir" in self:
calc_dir = self["calc_dir"]
elif self.get("calc_loc"):
calc_dir = get_calc_loc(self["calc_loc"], fw_spec["calc_locs"])["path"]
# parse the directory
logger.info("PARSING DIRECTORY: {}".format(calc_dir))
drone = LammpsDrone(additional_fields=self.get("additional_fields"),
diffusion_params=self.get("diffusion_params", None))
task_doc = drone.assimilate(calc_dir, input_filename=self["input_filename"],
log_filename=self.get("log_filename", "log.lammps"),
is_forcefield=self.get("is_forcefield", False),
data_filename=self.get("data_filename", None),
dump_files=self.get("dump_filenames", None))
# Check for additional keys to set based on the fw_spec
if self.get("fw_spec_field"):
task_doc.update(fw_spec[self.get("fw_spec_field")])
db_file = env_chk(self.get('db_file'), fw_spec)
# db insertion
if not db_file:
with open("task.json", "w") as f:
f.write(json.dumps(task_doc, default=DATETIME_HANDLER))
else:
mmdb = LammpsCalcDb.from_db_file(db_file)
# insert the task document
t_id = mmdb.insert(task_doc)
logger.info("Finished parsing with task_id: {}".format(t_id))
return FWAction(stored_data={"task_id": task_doc.get("task_id", None)})
def run_task(self, fw_spec):
calc_dir = os.getcwd()
if "calc_dir" in self:
calc_dir = self["calc_dir"]
elif self.get("calc_loc"):
calc_dir = get_calc_loc(self["calc_loc"], fw_spec["calc_locs"])["path"]
logger.info("PARSING DIRECTORY: {}".format(calc_dir))
db_file = env_chk(self.get('db_file'), fw_spec)
cluster_dict = None
tags = Tags.from_file(filename="feff.inp")
if "RECIPROCAL" not in tags:
cluster_dict = Atoms.cluster_from_file("feff.inp").as_dict()
doc = {"input_parameters": tags.as_dict(),
"cluster": cluster_dict,
"structure": self["structure"].as_dict(),
"absorbing_atom": self["absorbing_atom"],
"spectrum_type": self["spectrum_type"],
"spectrum": np.loadtxt(os.path.join(calc_dir, self["output_file"])).tolist(),
"edge": self.get("edge", None),
"metadata": self.get("metadata", None),
"dir_name": os.path.abspath(os.getcwd()),
"last_updated": datetime.today()}
if not db_file:
with open("feff_task.json", "w") as f:
f.write(json.dumps(doc, default=DATETIME_HANDLER))
# db insertion
else:
db = MMFeffDb.from_db_file(db_file, admin=True)
db.insert(doc)
logger.info("Finished parsing the spectrum")
return FWAction(stored_data={"task_id": doc.get("task_id", None)})
def run_task(self, fw_spec):
wfid = list(filter(lambda x: 'wfid' in x, fw_spec['tags'])).pop()
db_file = env_chk(self.get("db_file"), fw_spec)
vaspdb = VaspCalcDb.from_db_file(db_file, admin=True)
# ferroelectric workflow groups calculations by generated wfid tag
polarization_tasks = vaspdb.collection.find({"tags": wfid, "task_label": {"$regex": ".*polarization"}})
tasks = []
outcars = []
structure_dicts = []
sort_weight = []
energies_per_atom = []
energies = []
zval_dicts = []
for p in polarization_tasks:
# Grab data from each polarization task
energies_per_atom.append(p['calcs_reversed'][0]['output']['energy_per_atom'])
energies.append(p['calcs_reversed'][0]['output']['energy'])
tasks.append(p['task_label'])
outcars.append(p['calcs_reversed'][0]['output']['outcar'])
structure_dicts.append(p['calcs_reversed'][0]['input']['structure'])
zval_dicts.append(p['calcs_reversed'][0]['output']['outcar']['zval_dict'])
# Add weight for sorting
# Want polarization calculations in order of nonpolar to polar for Polarization object
# This number needs to be bigger than the number of calculations
max_sort_weight = 1000000
if 'nonpolar_polarization' in p['task_label']:
sort_weight.append(0)
elif "polar_polarization" in p['task_label']:
sort_weight.append(max_sort_weight)
elif "interpolation_" in p['task_label']:
num = 0
part = re.findall(r'interpolation_[0-9]+_polarization', p['task_label'])
if part != []:
part2 = re.findall(r'[0-9]+', part.pop())
if part2 != []:
num = part2.pop()
sort_weight.append(max_sort_weight - int(num))
# Sort polarization tasks
# nonpolar -> interpolation_n -> interpolation_n-1 -> ... -> interpolation_1 -> polar
data = zip(tasks, structure_dicts, outcars, energies_per_atom, energies, sort_weight)
data = sorted(data,key=lambda x: x[-1])
# Get the tasks, structures, etc in sorted order from the zipped data.
tasks, structure_dicts, outcars, energies_per_atom, energies, sort_weight = zip(*data)
structures = [Structure.from_dict(structure) for structure in structure_dicts]
# If LCALCPOL = True then Outcar will parse and store the pseudopotential zvals.
zval_dict = zval_dicts.pop()
# Assumes that we want to calculate the ionic contribution to the dipole moment.
# VASP's ionic contribution is sometimes strange.
# See pymatgen.analysis.ferroelectricity.polarization.Polarization for details.
p_elecs = [outcar['p_elec'] for outcar in outcars]
p_ions = [get_total_ionic_dipole(structure, zval_dict) for structure in structures]
polarization = Polarization(p_elecs, p_ions, structures)
p_change = polarization.get_polarization_change().A1.tolist()
p_norm = polarization.get_polarization_change_norm()
polarization_max_spline_jumps = polarization.max_spline_jumps()
same_branch = polarization.get_same_branch_polarization_data(convert_to_muC_per_cm2=True)
raw_elecs, raw_ions = polarization.get_pelecs_and_pions()
quanta = polarization.get_lattice_quanta(convert_to_muC_per_cm2=True)
energy_trend = EnergyTrend(energies_per_atom)
energy_max_spline_jumps = energy_trend.max_spline_jump()
polarization_dict = {}
def split_abc(var, var_name):
d = {}
for i, j in enumerate('abc'):
d.update({var_name + "_{}".format(j): var[:, i].A1.tolist()})
return d
# Add some sort of id for the structures? Like cid but more general?
# polarization_dict.update({'cid': cid})
# General information
polarization_dict.update({'pretty_formula': structures[0].composition.reduced_formula})
polarization_dict.update({'wfid': wfid})
polarization_dict.update({'task_label_order': tasks})
# Polarization information
polarization_dict.update({'polarization_change': p_change})
polarization_dict.update({'polarization_change_norm': p_norm})
polarization_dict.update({'polarization_max_spline_jumps': polarization_max_spline_jumps})
polarization_dict.update(split_abc(same_branch, "same_branch_polarization"))
polarization_dict.update(split_abc(raw_elecs, "raw_electron_polarization"))
polarization_dict.update(split_abc(raw_ions, "raw_electron_polarization"))
polarization_dict.update(split_abc(quanta, "polarization_quanta"))
polarization_dict.update({"zval_dict": zval_dict})
# Energy information
polarization_dict.update({'energy_per_atom_max_spline_jumps': energy_max_spline_jumps})
polarization_dict.update({"energies": energies})
polarization_dict.update({"energies_per_atom": energies_per_atom})
polarization_dict.update({'outcars': outcars})
polarization_dict.update({"structures": structure_dicts})
# Write all the info to db.
coll = vaspdb.db["polarization_tasks"]
coll.insert_one(polarization_dict)
def run_task(self, fw_spec):
# get the directory that contains the VASP dir to parse
calc_dir = os.getcwd()
if "calc_dir" in self:
calc_dir = self["calc_dir"]
elif self.get("calc_loc"):
calc_dir = get_calc_loc(self["calc_loc"], fw_spec["calc_locs"])["path"]
# parse the VASP directory
logger.info("PARSING DIRECTORY: {}".format(calc_dir))
drone = VaspDrone(additional_fields=self.get("additional_fields"),
parse_dos=self.get("parse_dos", False),
bandstructure_mode=self.get("bandstructure_mode", False),
parse_chgcar=self.get("parse_chgcar", False),
parse_aeccar=self.get("parse_aeccar", False))
# assimilate (i.e., parse)
task_doc = drone.assimilate(calc_dir)
# Check for additional keys to set based on the fw_spec
if self.get("fw_spec_field"):
task_doc.update(fw_spec[self.get("fw_spec_field")])
# get the database connection
db_file = env_chk(self.get('db_file'), fw_spec)
# db insertion or taskdoc dump
if not db_file:
with open("task.json", "w") as f:
f.write(json.dumps(task_doc, default=DATETIME_HANDLER))
else:
mmdb = VaspCalcDb.from_db_file(db_file, admin=True)
t_id = mmdb.insert_task(
task_doc, use_gridfs=self.get("parse_dos", False)
or bool(self.get("bandstructure_mode", False))
or self.get("parse_chgcar", False)
or self.get("parse_aeccar", False))
logger.info("Finished parsing with task_id: {}".format(t_id))
defuse_children = False
if task_doc["state"] != "successful":
defuse_unsuccessful = self.get("defuse_unsuccessful",
DEFUSE_UNSUCCESSFUL)
if defuse_unsuccessful is True:
defuse_children = True
elif defuse_unsuccessful is False:
pass
elif defuse_unsuccessful == "fizzle":
raise RuntimeError(
"VaspToDb indicates that job is not successful "
"(perhaps your job did not converge within the "
"limit of electronic/ionic iterations)!")
else:
raise RuntimeError("Unknown option for defuse_unsuccessful: "
"{}".format(defuse_unsuccessful))
task_fields_to_push = self.get("task_fields_to_push", None)
update_spec = {}
if task_fields_to_push:
if isinstance(task_fields_to_push, dict):
for key, path_in_task_doc in task_fields_to_push.items():
if has(task_doc, path_in_task_doc):
update_spec[key] = get(task_doc, path_in_task_doc)
else:
logger.warn("Could not find {} in task document. Unable to push to next firetask/firework".format(path_in_task_doc))
else:
raise RuntimeError("Inappropriate type {} for task_fields_to_push. It must be a "
"dictionary of format: {key: path} where key refers to a field "
"in the spec and path is a full mongo-style path to a "
"field in the task document".format(type(task_fields_to_push)))
return FWAction(stored_data={"task_id": task_doc.get("task_id", None)},
defuse_children=defuse_children, update_spec=update_spec)
def run_task(self, fw_spec):
feff_cmd = env_chk(self["feff_cmd"], fw_spec)
logger.info("Running FEFF using exe: {}".format(feff_cmd))
return_code = subprocess.call(feff_cmd, shell=True)
logger.info("FEFF finished running with returncode: {}".format(return_code))
def run_task(self, fw_spec):
gibbs_dict = {}
tag = self["tag"]
t_step = self.get("t_step", 10)
t_min = self.get("t_min", 0)
t_max = self.get("t_max", 1000)
mesh = self.get("mesh", [20, 20, 20])
eos = self.get("eos", "vinet")
qha_type = self.get("qha_type", "debye_model")
pressure = self.get("pressure", 0.0)
poisson = self.get("poisson", 0.25)
anharmonic_contribution = self.get("anharmonic_contribution", False)
gibbs_dict["metadata"] = self.get("metadata", {})
db_file = env_chk(self.get("db_file"), fw_spec)
mmdb = VaspCalcDb.from_db_file(db_file, admin=True)
# get the optimized structure
d = mmdb.collection.find_one({"task_label": "{} structure optimization".format(tag)},
{"calcs_reversed": 1})
structure = Structure.from_dict(d["calcs_reversed"][-1]["output"]['structure'])
gibbs_dict["structure"] = structure.as_dict()
gibbs_dict["formula_pretty"] = structure.composition.reduced_formula
# get the data(energy, volume, force constant) from the deformation runs
docs = mmdb.collection.find({"task_label": {"$regex": "{} gibbs*".format(tag)},
"formula_pretty": structure.composition.reduced_formula},
{"calcs_reversed": 1})
energies = []
volumes = []
force_constants = []
for d in docs:
s = Structure.from_dict(d["calcs_reversed"][-1]["output"]['structure'])
energies.append(d["calcs_reversed"][-1]["output"]['energy'])
if qha_type not in ["debye_model"]:
force_constants.append(d["calcs_reversed"][-1]["output"]['force_constants'])
volumes.append(s.volume)
gibbs_dict["energies"] = energies
gibbs_dict["volumes"] = volumes
if qha_type not in ["debye_model"]:
gibbs_dict["force_constants"] = force_constants
try:
# use quasi-harmonic debye approximation
if qha_type in ["debye_model"]:
from pymatgen.analysis.quasiharmonic import QuasiharmonicDebyeApprox
qhda = QuasiharmonicDebyeApprox(energies, volumes, structure, t_min, t_step, t_max,
eos, pressure=pressure, poisson=poisson,
anharmonic_contribution=anharmonic_contribution)
gibbs_dict.update(qhda.get_summary_dict())
gibbs_dict["anharmonic_contribution"] = anharmonic_contribution
gibbs_dict["success"] = True
# use the phonopy interface
else:
from atomate.vasp.analysis.phonopy import get_phonopy_gibbs
G, T = get_phonopy_gibbs(energies, volumes, force_constants, structure, t_min,
t_step, t_max, mesh, eos, pressure)
gibbs_dict["gibbs_free_energy"] = G
gibbs_dict["temperatures"] = T
gibbs_dict["success"] = True
# quasi-harmonic analysis failed, set the flag to false
except:
import traceback
logger.warn("Quasi-harmonic analysis failed!")
gibbs_dict["success"] = False
gibbs_dict["traceback"] = traceback.format_exc()
gibbs_dict['metadata'].update({"task_label_tag": tag})
gibbs_dict["created_at"] = datetime.utcnow()
gibbs_dict = jsanitize(gibbs_dict)
# TODO: @matk86: add a list of task_ids that were used to construct the analysis to DB?
# -computron
if not db_file:
dump_file = "gibbs.json"
logger.info("Dumping the analysis summary to {}".format(dump_file))
with open(dump_file, "w") as f:
f.write(json.dumps(gibbs_dict, default=DATETIME_HANDLER))
else:
coll = mmdb.db["gibbs_tasks"]
coll.insert_one(gibbs_dict)
logger.info("Gibbs free energy calculation complete.")
if not gibbs_dict["success"]:
return FWAction(defuse_children=True)
def run_task(self, fw_spec):
ref_struct = self['structure']
d = {
"analysis": {},
"initial_structure": self['structure'].as_dict()
}
# Get optimized structure
calc_locs_opt = [cl for cl in fw_spec.get('calc_locs', []) if 'optimiz' in cl['name']]
if calc_locs_opt:
optimize_loc = calc_locs_opt[-1]['path']
logger.info("Parsing initial optimization directory: {}".format(optimize_loc))
drone = VaspDrone()
optimize_doc = drone.assimilate(optimize_loc)
opt_struct = Structure.from_dict(optimize_doc["calcs_reversed"][0]["output"]["structure"])
d.update({"optimized_structure": opt_struct.as_dict()})
ref_struct = opt_struct
eq_stress = -0.1*Stress(optimize_doc["calcs_reversed"][0]["output"]["ionic_steps"][-1]["stress"])
else:
eq_stress = None
if self.get("fw_spec_field"):
d.update({self.get("fw_spec_field"): fw_spec.get(self.get("fw_spec_field"))})
# Get the stresses, strains, deformations from deformation tasks
defo_dicts = fw_spec["deformation_tasks"].values()
stresses, strains, deformations = [], [], []
for defo_dict in defo_dicts:
stresses.append(Stress(defo_dict["stress"]))
strains.append(Strain(defo_dict["strain"]))
deformations.append(Deformation(defo_dict["deformation_matrix"]))
# Add derived stresses and strains if symmops is present
for symmop in defo_dict.get("symmops", []):
stresses.append(Stress(defo_dict["stress"]).transform(symmop))
strains.append(Strain(defo_dict["strain"]).transform(symmop))
deformations.append(Deformation(defo_dict["deformation_matrix"]).transform(symmop))
stresses = [-0.1*s for s in stresses]
pk_stresses = [stress.piola_kirchoff_2(deformation)
for stress, deformation in zip(stresses, deformations)]
d['fitting_data'] = {'cauchy_stresses': stresses,
'eq_stress': eq_stress,
'strains': strains,
'pk_stresses': pk_stresses,
'deformations': deformations
}
logger.info("Analyzing stress/strain data")
# TODO: @montoyjh: what if it's a cubic system? don't need 6. -computron
# TODO: Can add population method but want to think about how it should
# be done. -montoyjh
order = self.get('order', 2)
if order > 2:
method = 'finite_difference'
else:
method = self.get('fitting_method', 'finite_difference')
if method == 'finite_difference':
result = ElasticTensorExpansion.from_diff_fit(
strains, pk_stresses, eq_stress=eq_stress, order=order)
if order == 2:
result = ElasticTensor(result[0])
elif method == 'pseudoinverse':
result = ElasticTensor.from_pseudoinverse(strains, pk_stresses)
elif method == 'independent':
result = ElasticTensor.from_independent_strains(strains, pk_stresses, eq_stress=eq_stress)
else:
raise ValueError("Unsupported method, method must be finite_difference, "
"pseudoinverse, or independent")
ieee = result.convert_to_ieee(ref_struct)
d.update({
"elastic_tensor": {
"raw": result.voigt,
"ieee_format": ieee.voigt
}
})
if order == 2:
d.update({"derived_properties": ieee.get_structure_property_dict(ref_struct)})
else:
soec = ElasticTensor(ieee[0])
d.update({"derived_properties": soec.get_structure_property_dict(ref_struct)})
d["formula_pretty"] = ref_struct.composition.reduced_formula
d["fitting_method"] = method
d["order"] = order
d = jsanitize(d)
# Save analysis results in json or db
db_file = env_chk(self.get('db_file'), fw_spec)
if not db_file:
with open("elasticity.json", "w") as f:
f.write(json.dumps(d, default=DATETIME_HANDLER))
else:
db = VaspCalcDb.from_db_file(db_file, admin=True)
db.collection = db.db["elasticity"]
db.collection.insert_one(d)
logger.info("Elastic analysis complete.")
return FWAction()
def run_task(self, fw_spec):
vasp_cmd = env_chk(self["vasp_cmd"], fw_spec)
logger.info("Running VASP using exe: {}".format(vasp_cmd))
return_code = subprocess.call(vasp_cmd, shell=True)
logger.info("VASP finished running with returncode: {}".format(return_code))
def run_task(self, fw_spec):
# initialize variables
qchem_cmd = env_chk(self["qchem_cmd"], fw_spec)
multimode = env_chk(self.get("multimode"), fw_spec)
if multimode == None:
multimode = "openmp"
input_file = self.get("input_file", "mol.qin")
output_file = self.get("output_file", "mol.qout")
max_cores = env_chk(self["max_cores"], fw_spec)
qclog_file = self.get("qclog_file", "mol.qclog")
suffix = self.get("suffix", "")
scratch_dir = env_chk(self.get("scratch_dir"), fw_spec)
if scratch_dir == None:
scratch_dir = "/dev/shm/qcscratch/"
save_scratch = self.get("save_scratch", False)
save_name = self.get("save_name", "default_save_name")
max_errors = self.get("max_errors", 5)
max_iterations = self.get("max_iterations", 10)
max_molecule_perturb_scale = self.get("max_molecule_perturb_scale",
0.3)
job_type = self.get("job_type", "normal")
gzipped_output = self.get("gzipped_output", True)
handler_groups = {
"default": [
QChemErrorHandler(
input_file=input_file, output_file=output_file)
],
"no_handler": []
}
# construct jobs
if job_type == "normal":
jobs = [
QCJob(
qchem_command=qchem_cmd,
max_cores=max_cores,
multimode=multimode,
input_file=input_file,
output_file=output_file,
qclog_file=qclog_file,
suffix=suffix,
scratch_dir=scratch_dir,
save_scratch=save_scratch,
save_name=save_name)
]
elif job_type == "opt_with_frequency_flattener":
jobs = QCJob.opt_with_frequency_flattener(
qchem_command=qchem_cmd,
multimode=multimode,
input_file=input_file,
output_file=output_file,
qclog_file=qclog_file,
max_iterations=max_iterations,
max_molecule_perturb_scale=max_molecule_perturb_scale,
scratch_dir=scratch_dir,
save_scratch=save_scratch,
save_name=save_name,
max_cores=max_cores)
else:
raise ValueError("Unsupported job type: {}".format(job_type))
# construct handlers
handlers = handler_groups[self.get("handler_group", "default")]
c = Custodian(
handlers,
jobs,
max_errors=max_errors,
gzipped_output=gzipped_output)
c.run()
