def H(self):
"""Returns the Hessian matrix extracted from the frozen phonon calculations.
"""
if self._H is not None:
return self._H
#Otherwise, we need to calculate it from scratch. This depends on
#whether we are using DFPT or frozen phonons.
if not self.dfpt:
self.calc_forcesets()
dim = ' '.join(map(str, self.supercell))
xargs = ["phonopy", '--dim="{}"'.format(dim), "--writefc"]
execute(xargs, self.phonodir, venv=True)
if not path.isfile(path.join(self.phonodir, "FORCE_CONSTANTS")):
msg.err("Cannot convert FORCE_SETS to FORCE_CONSTANTS")
msg.err(''.join(xargs["output"]))
else:
self.calc_fc()
with chdir(self.phonodir):
result = file_IO.parse_FORCE_CONSTANTS()
self._H = unroll_fc(result)
self.save_pkl(self._H, self.H_file)
return self._H
def sbatch(jobfile, folder, kwargs):
"""Submits jobs to a supercomputer with sbatch.
Args:
jobfile (str): the name of jobfile that needs to be submitted.
folder (str): the path to the jobfile.
kwargs (dict): other arguments to pass to the execute function.
"""
execute(["sbatch", jobfile], **kwargs)
def vasp_to_xyz(folder,
outfile="output.xyz",
recalc=0,
properties=["species", "pos", "z", "dft_force"],
parameters=["dft_energy", "dft_virial"],
config_type=None):
"""Creates an extended XYZ file for the calculated structure in
OUTCAR for the given folder.
Args:
folder (str): path to the folder to convert.
outfile (str): name of the XYZ file to create. The file will
be created in the same folder as the original if no absolute
path is given.
recalc (bool): when True, re-convert the OUTCAR file, even if
the target XYZ file already exists.
"""
from matdb.atoms import Atoms
if not path.isabs(outfile):
#Convert to absolute path if one wasn't given.
outfile = path.join(folder, outfile)
if (path.isfile(outfile) and stat(outfile).st_size > 100 and recalc <= 0):
return True
p = ','.join(properties)
P = ','.join(parameters)
renames = [("energy", "vasp_energy"), ("force", "vasp_force"),
("virial", "vasp_virial")]
sargs = ["convert.py", "-I", "vasprun.xml", "-p", p, "-P", P, "-f", "xyz"]
for s, d in renames:
sargs.append("-n")
sargs.append(s)
sargs.append(d)
sargs.extend(["-o", outfile, "vasprun.xml"])
from matdb.utility import execute
execute(sargs, folder, errignore="OMP_STACKSIZE")
if config_type is not None:
#We need to load the XYZ file, add the config_type parameter and then
#save it again. The -e parameter of convert.py should save this, but in
#our experiments, it doesn't :(.
a = Atoms(outfile)
a.params["config_type"] = config_type
a.write(outfile)
return path.isfile(outfile) and stat(outfile).st_size > 100
def test_execute():
"""Tests missing lines of execute.
"""
from matdb.utility import execute
# test early breaking on stderr and stdout.
temp=execute(('which','python'),'.',nlines=0)
temp=execute(('python','enum.x'),'.',nlines=0)
temp=execute(('which','python'),'.',env_vars={"POTENTIALS_DIR":'1'})
assert "bin/python\n" in temp['output'][0]
assert temp['error'] == []
def test_execution():
"""Tests the execution via shell subprocess in a different folder.
"""
from matdb.utility import execute, reporoot
sargs = ["pwd"]
target = path.join(reporoot, "matdb")
xres = execute(sargs, target, nlines=1, env_vars={"VASP_PP_PATH":"~/."})
assert xres["output"][0].strip() == target
sargs = ["cat dummy-file"]
target = path.join(reporoot, "matdb")
xres = execute(sargs, target, nlines=1)
assert len(xres["error"]) > 0
def calc_DOS(self, recalc=False):
"""Calculates the *total* density of states.
Args:
recalc (bool): when True, recalculate the DOS, even if the
file already exists.
"""
dosfile = path.join(self.phonodir, "mesh.yaml")
if not recalc and path.isfile(dosfile):
return
#Make sure we have calculated the force sets already.
self.calc_forcesets(recalc)
settings = {
"ATOM_NAME": ' '.join(self.database.parent.species),
"DIM": ' '.join(map(str, self.supercell)),
"MP": ' '.join(map(str, self.dosmesh))
}
with open(path.join(self.phonodir, "dos.conf"), 'w') as f:
for k, v in settings.items():
f.write("{} = {}\n".format(k, v))
sargs = ["phonopy", "-p", "dos.conf", "-s"]
xres = execute(sargs, self.phonodir, venv=True)
#Make sure that phonopy actually produced files; otherwise show the output
#(phonopy doesn't write to stderr, only stdout).
if not path.isfile(dosfile): #pragma: no cover
msg.std(''.join(xres["error"]))
msg.err("could not calculate the DOS; see errors.")
def test_cat(tmpdir):
"""Tests concatenation of multiple files.
"""
from matdb.utility import cat, execute, reporoot
files = [path.join(reporoot, "tests", "files", f)
for f in ["A.txt", "B.txt"]]
outfile = str(tmpdir.join("cat_C.txt"))
cat(files, outfile)
sargs = ["diff", "C.txt", outfile]
xres = execute(sargs, path.join(reporoot, "tests/files"))
assert len(xres["output"]) == 0
def _setup_configs(self, rerun):
"""Displaces the seed configuration preparatory to calculating the force
sets for phonon spectra.
.. note:: This method *appears* to be VASP-specific. However, the
configurations that are generated by `phonopy` as VASP `POSCAR` files
are turned into :class:`~matdb.atoms.Atoms` objects before they are
passed to the super class that sets up the actual calculations. So, it
is quite general.
Args:
rerun (int): when > 1, recreate the folders even if they
already exist. If > 0, recreate the jobfile.
"""
#We also don't want to setup again if we have the results already.
if self.ready() and rerun == 0:
return
if not self.is_setup() or rerun > 1:
from ase.io import write
write(path.join(self.phonodir, "POSCAR"), self.atoms, "vasp")
scell = ' '.join(map(str, self.supercell))
sargs = ["phonopy", "-d", '--dim="{}"'.format(scell)]
pres = execute(sargs, self.phonodir, venv=True)
#Make sure that phonopy produced the supercell. If it didn't, it
#should have printed an error to *stdout* because it doesn't know
#about stderr...
if not path.isfile(path.join(self.phonodir, "SPOSCAR")):
msg.err('\n'.join(pres["output"]))
from matdb.atoms import Atoms
if not self.dfpt:
#Frozen phonons, create a config execution folder for each of
#the displacements.
from glob import glob
with chdir(self.phonodir):
for dposcar in glob("POSCAR-*"):
dind = int(dposcar.split('-')[1])
datoms = Atoms(dposcar, format="vasp")
self.create(datoms)
else:
#Pull the perfect supercell and set it up for executing with
#DFPT parameters.
with chdir(self.phonodir):
datoms = Atoms("SPOSCAR", format="vasp")
self.create(datoms)
# Last of all, create the job file to execute the job array.
self.jobfile(rerun)
def execute(self, dryrun=False):
"""Submits the job script for the currently configured potential training.
Args:
dryrun (bool): when True, simulate the submission without actually
submitting.
Returns:
bool: True if the submission generated a job id (considered
successful).
"""
if self.ready():
msg.info(
"Trainer {} is already done;".format(self.root) +
"skipping execute step.", 2)
return
if not path.isfile(self._jobfile):
return False
if not path.isfile(self._trainfile):
msg.std("train.h5 missing in {}; can't execute.".format(self.root))
return False
# We must have what we need to execute. Compile the command and submit.
shell_command = self.controller.db.shell_command
# We suport 'bash' and 'sbatch' shell commands, if it's neighter one
# of them, default to 'bash'
if shell_command not in ['bash', 'sbatch']:
shell_command = 'bash'
cargs = [shell_command, self._jobfile]
if dryrun:
msg.okay("Executed {} in {}".format(' '.join(cargs), self.root))
return True
else:
xres = execute(cargs, self.root)
# supercompute will return "Submitted"
if len(xres["output"]) > 0 and "Submitted" in xres["output"][0]:
msg.okay("{}: {}".format(self.root, xres["output"][0].strip()))
return True
# local computer
elif len(xres["error"]) == 0:
return True
else:
return False
def modulate_atoms(db):
"""Generates modulated configurations using the dynamical matrix of the
:class:`DynMatrix` instance.
Args:
db (Group): database with parameters needed to module the
atoms, (Calibration or Modulation databases).
"""
#Generating the modulation file. We need to sample the DOS in order to
#compute that correctly.
dosfile = path.join(db.base.phonodir, "mesh.yaml")
qvecs = sample_dos(dosfile, sampling=db.sampling, nfreqs=db.nconfigs)
conffile = path.join(db.base.phonodir, db.confname)
modstr = [' '.join(map(str, db.base.supercell))]
for iq, (bandi, qvec) in enumerate(qvecs):
mstr = "{0:.7f} {1:.7f} {2:.7f} {3:d} {4:.7f} {5:.7f}"
if hasattr(db, "_amplitudes"):
A = db._amplitudes[iq]
else:
A = np.random.normal(1, 0.25) * db.amplitude
phi = np.random.uniform(0, 180)
args = qvec + [bandi, A, phi]
modstr.append(mstr.format(*args))
phondict = db.phonons.copy()
phondict["dim"] = db.base.supercell
phondict["atom_name"] = ' '.join(db.base.parent.species)
phondict["modulation"] = ', '.join(modstr)
with open(conffile, 'w') as f:
for k, v in phondict.items():
if isinstance(v, (list, tuple, set)):
value = ' '.join(map(str, v))
f.write("{} = {}\n".format(k.upper(), value))
else:
f.write("{} = {}\n".format(k.upper(), v))
from matdb.utility import execute
sargs = ["phonopy", db.confname]
xres = execute(sargs, db.base.phonodir, venv=True)
#Make sure that phonopy actually produced files; otherwise show the output
#(phonopy doesn't write to stderr, only stdout).
testmod = path.join(db.base.phonodir, "MPOSCAR-001")
if not path.isfile(testmod): #pragma: no cover
msg.err(''.join(xres["output"]))
def execute(self, dryrun=False, recovery=False, env_vars=None):
"""Submits the job script for each of the folders in this
database if they are ready to run.
Args:
dryrun (bool): when True, simulate the submission without actually submitting.
recovery (bool): when True, submit the script for running recovery jobs.
env_vars (dict): `dict` of environment variables to set before calling the execution. The variables will be set back after execution.
Returns:
bool: True if the submission generated a job id (considered successful).
"""
self._expand_sequence()
if len(self.sequence) == 0:
jobfile = "recovery.sh" if recovery else "jobfile.sh"
if not path.isfile(path.join(self.root, jobfile)):
return False
if not recovery:
if not all(
a.calc.can_execute(self.configs[i])
for i, a in self.config_atoms.items()):
return False
#We also need to check that we haven't already submitted this
#job. Check to see if it is executing.
if any(
a.calc.is_executing(self.configs[i])
for i, a in self.config_atoms.items()):
return False
#Make sure that the calculation isn't complete.
if self.last_config_atoms is not None:
if any(
a.calc.can_extract(self.last_iteration[i])
for i, a in self.last_config_atoms.items()):
return False
# We must have what we need to execute. Compile the command and
# submit.
from matdb.utility import execute
cargs = [self.database.parent.shell_command, jobfile]
if dryrun:
from matdb.msg import okay
okay("Executed {} in {}".format(' '.join(cargs), self.root))
return True
else:
xres = execute(cargs, self.root, env_vars=env_vars)
if len(xres["output"]) > 0 and "Submitted" in xres["output"][0]:
from matdb.msg import okay
okay("{}: {}".format(self.root, xres["output"][0].strip()))
return True
else: #pragma: no cover
return False
else: #pragma: no cover, enumerated database shouldn't take seeds
already_executed = []
for group in self.sequence.values():
already_executed.append(
group.execute(dryrun=dryrun,
recovery=recovery,
env_vars=env_vars))
return all(already_executed)
def command(self):
"""Returns the command that is needed to train the GAP
potentials specified by this object.
.. note:: This method also configures the directory that the command
will run in so that it has the relevant files.
"""
self._set_root()
if not path.isfile(path.join(self.root, "status.txt")):
self.iter_status = "train"
self.iter_count = 1
self.cell_iter = 0
else:
with open(path.join(self.root, "status.txt"), "r") as f:
for line in f:
old_status = line.strip().split()
if old_status[0] == "done":
self.iter_status = "train"
# iter_count is the total iteration number for the whole process, not limited to one cell
self.iter_count = int(old_status[1]) + 1
self.cell_iter = int(old_status[2])
if int(old_status[3]) <= self.next_cell_threshold:
self.cell_iter = int(old_status[2]) + 1
if len(self.cell_sizes) > self.cell_iter:
self.relax_max_atoms = self.cell_sizes[self.cell_iter]
else: #pragma: no cover
msg.err(
"The MTP process has finished for the cell sizes "
"specified in the YML file.")
target1 = path.join(self.root, "unrelaxed.cfg")
target2 = path.join(self.root, "to-relax.cfg")
if path.isfile(target1):
remove(target1)
if path.isfile(target2):
remove(target2)
if self.iter_count >= self.iter_threshold: #pragma: no cover
msg.err(
"The number of iterations has exceeded "
"the allowed number of {0}. To increase this limit "
"use the iteration_threshold aption in the YML "
"file.".format(self.iter_threshold))
else:
self.iter_status = old_status[0]
self.iter_count = int(old_status[1])
self.cell_iter = int(old_status[2])
#if we're at the start of a training iteration use the command to train the potential
if self.iter_status == "train":
self._make_train_cfg(self.iter_count)
#remove the selected.cfg and rexaed.cfg from the last iteration if they exist
if path.isfile(path.join(self.root, "new_training.cfg")):
remove(path.join(self.root, "new_training.cfg"))
if path.isfile(path.join(self.root, "relaxed.cfg")):
remove(path.join(self.root, "relaxed.cfg"))
if not path.isfile(path.join(self.root, "relax.ini")):
self._make_relax_ini()
if not path.isfile(path.join(self.root, "pot.mtp")):
self._make_pot_initial()
template = self._train_template()
with open(path.join(self.root, "status.txt"), "w+") as f:
f.write("relax_setup {0} {1}".format(self.iter_count,
self.cell_iter))
if self.iter_status == "relax_setup":
# If pot has been trained
if path.isfile(path.join(self.root, "Trained.mtp_")):
rename(path.join(self.root, "Trained.mtp_"),
path.join(self.root, "pot.mtp"))
# Calculate the grad of the training configurations.
calc_grade = self._calc_grade_template()
execute(calc_grade.split(), self.root)
if path.isfile(path.join(self.root, "temp1.cfg")):
remove(path.join(self.root, "temp1.cfg"))
if not path.isfile(path.join(self.root,
"state.mvs")): #pragma: no cover
raise MlpError(
"mlp failed to produce the 'state.mvs` file with command "
"'mlp calc-grade pot.mtp train.cfg train.cfg temp1.cfg'")
# if the unrelaxed.cfg file exists we need to move it to
# replace the existing 'to-relax.cfg' otherwise we need to
# create the 'to-relax.cfg' file.
if path.isfile(path.join(self.root,
"unrelaxed.cfg")) and self.use_unrelaxed:
rename(path.join(self.root, "unrelaxed.cfg"),
path.join(self.root, "to-relax.cfg"))
self.iter_status = "relax"
elif not path.isfile(path.join(self.root, "to-relax.cfg")):
self._setup_to_relax_cfg()
template = "matdb_mtp_to_relax.py > create-to-relax.txt"
with open(path.join(self.root, "status.txt"), "w+") as f:
f.write("relax {0} {1}".format(self.iter_count,
self.cell_iter))
else:
self.iter_status = "relax"
if self.iter_status == "relax":
# command to relax structures
if path.isfile(path.join(self.root, "candidate.cfg")):
remove(path.join(self.root, "candidate.cfg"))
template = self._relax_template()
with open(path.join(self.root, "status.txt"), "w+") as f:
f.write("select {0} {1}".format(self.iter_count,
self.cell_iter))
# if relaxation is done
if self.iter_status == "select":
cand_files = glob(path.join(self.root, "candidate.cfg_*"))
cat(cand_files, path.join(self.root, "candidate.cfg"))
for cfile in cand_files:
remove(cfile)
# command to select next training set.
template = self._select_template()
with open(path.join(self.root, "status.txt"), "w+") as f:
f.write("add {0} {1}".format(self.iter_count, self.cell_iter))
if self.iter_status == "add":
with chdir(self.root):
# Now add the selected atoms to the Active database.
# input filename sould always be entered before output filename
execute([
"mlp", "convert-cfg", "new_training.cfg", "POSCAR",
"--output-format=vasp-poscar"
], self.root)
if path.isfile("new_training.cfg"):
rename("new_training.cfg",
"new_training.cfg_iter_{}".format(self.iter_count))
if path.isfile("relaxed.cfg"):
rename("relaxed.cfg",
"relaxed.cfg_iter_{}".format(self.iter_count))
new_configs = []
new_POSCARS = glob("POSCAR*")
# Here We need to re-write the POSCARs so that they
# have the correct species.
for POSCAR in new_POSCARS:
# We need to put the correct species into the
# title of the POSCAR so that ASE can read it
pos_file = []
with open(POSCAR, 'r') as f:
for line in f:
pos_file.append(line)
pos_file[0] = "{0} : {1}".format(" ".join(self.species),
pos_file[0])
with open(POSCAR, 'w+') as f:
for line in pos_file:
f.write(line)
new_configs.append(Atoms(POSCAR, format="vasp"))
remove(POSCAR)
self.active.add_configs(new_configs, self.iter_count)
self.active.setup()
if len(self.active.configs
) != self.active.nconfigs: #pragma: no cover
raise LogicError(
"The active database failed to setup the calculations "
"for iteration {0}".format(self.iter_count))
self.active.execute()
with open(path.join(self.root, "status.txt"), "w+") as f:
f.write("done {0} {1} {2}".format(self.iter_count,
self.cell_iter,
len(new_configs)))
template = ''
return template
def _calc_bands(atoms, hessian, supercell=(1, 1, 1), outfile=None, grid=None):
"""Calculates the band structure for the given Hessian matrix.
Args:
atoms (matdb.atoms.Atoms): atoms object corresponding to the *primitive*
cell. The specified supercell matrix should result in a number
of atoms that matches the dimensionality of the Hessian.
supercell (tuple): tuple of `int` supercell matrix components; can have either
3 or 9 components.
hessian (numpy.ndarray): with shape `(natoms*3, natoms*3)`.
grid (list): list of `int` specifying the number of divisions in k-space
along each reciprocal unit vector.
outfile (str): path to the output `band.yaml` file that should be
created by this function.
Returns:
If `outfile` is None, then this method returns a dictionary that has the
same format as :func:`from_yaml`.
"""
#Create a temporary directory in which to work.
target = mkdtemp()
bandfile = path.join(target, "band.yaml")
if grid is None:
grid = [13, 13, 13]
if isinstance(supercell, np.ndarray):
supercell = supercell.flatten()
#First, roll up the Hessian and write it as a FORCE_CONSTANTS file.
with chdir(target):
HR = roll(hessian)
write_FORCE_CONSTANTS(HR)
atoms.write("POSCAR", format="vasp")
#We need to create the band.conf file and write the special
#paths in k-space at which the phonons should be calculated.
atom_types = _ordered_unique(atoms.get_chemical_symbols())
settings = [("FORCE_CONSTANTS", "READ"),
("ATOM_NAME", ' '.join(atom_types)),
("DIM", ' '.join(map(str, supercell))),
("MP", ' '.join(map(str, grid)))]
labels, bands = parsed_kpath(atoms)
bandfmt = "{0:.3f} {1:.3f} {2:.3f}"
sband = []
for Q in bands:
sband.append(bandfmt.format(*Q))
settings.append(("BAND", " ".join(sband)))
settings.append(("BAND_LABELS", ' '.join(labels)))
with open("band.conf", 'w') as f:
for k, v in settings:
f.write("{} = {}\n".format(k, v))
sargs = ["phonopy", "band.conf"]
xres = execute(sargs, target, venv=True)
if not path.isfile(bandfile): #pragma: no cover
msg.err("could not calculate phonon bands; see errors.")
msg.std(''.join(xres["output"]))
result = None
if outfile is not None:
#Move the band.yaml file to the new target location.
from shutil import move
move(bandfile, outfile)
else:
result = from_yaml(bandfile)
#Remove the temporary directory that we created and return the result.
rmtree(target)
return result
