def orca_results(spline_NEB, step_to_use, i, state):
"""
A method for reading in the output of Orca single point calculations for
spline_NEB calculations. This will both (a) assign forces to the atoms stored
in state and (b) return the energy and atoms.
**Parameters**
spline_NEB: :class:`spline_NEB`
A spline_NEB container holding the main spline_NEB simulation
step_to_use: *int*
Which iteration in the spline_NEB sequence the output to be read in is on.
i: *int*
The index corresponding to which image on the frame is to be
simulated.
state: *list,* :class:`structures.Atom`
A list of atoms describing the image on the frame associated with
index *i*.
**Returns**
new_energy: *float*
The energy of the system in Hartree (Ha).
new_atoms: *list,* :class:`structures.Atom`
A list of atoms with the forces attached in units of Hartree per
Angstrom (Ha/Ang).
"""
read_data = orca.engrad_read('%s-%d-%d' %
(spline_NEB.name, step_to_use, i),
force='Ha/Ang',
pos='Ang')
new_atoms, new_energy = read_data
for a, b in zip(state, new_atoms):
a.fx, a.fy, a.fz = b.fx, b.fy, b.fz
return new_energy, new_atoms
def _read_orca(name):
"""
A method for reading in the output of Orca single point calculations to
get the atomic positions with forces. Further, energy is also returned.
**Parameters**
name: *str*
The name of the Orca simulation in questions.
**Returns**
new_energy: *float*
The energy of the system in Hartree (Ha).
new_atoms: *list,* :class:`structures.Atom`
A list of atoms with the forces attached in units of Hartree per
Angstrom (Ha/Ang).
"""
read_data = orca.engrad_read(name,
force='Ha/Ang',
pos='Ang')
new_atoms, new_energy = read_data
return new_energy, new_atoms
def pickle_training_set(run_name,
training_sets_folder="training_set",
pickle_file_name="training_set",
high_energy_cutoff=500.0,
system_x_offset=1000.0,
verbose=False,
extra_parameters={}):
"""
A function to pickle together the training set in a manner that is
readable for MCSMRFF. This is a single LAMMPs data file with each
training set offset alongst the x-axis by system_x_offset. The pickle
file, when read in later, holds a list of two objects. The first is
the entire system as described above. The second is a dictionary of all
molecules in the system, organized by composition.
**Parameters**
run_name: *str*
Name of final training set.
training_sets_folder: *str, optional*
Path to the folder where all the training set data is.
pickle_file_name: *str, optional*
A name for the pickle file and training set system.
high_energy_cutoff: *float, optional*
A cutoff for systems that are too large in energy, as MD is likely
never to sample them.
system_x_offset: *float, optional*
The x offset for the systems to be added by.
verbose: *bool, optional*
Whether to have additional stdout or not.
extra_parameters: *dict, optional*
A dictionaries for additional parameters that do not exist
in the default OPLSAA parameter file.
**Returns**
system: *System*
The entire training set system.
systems_by_composition: *dict, list, Molecule*
Each molecule organized in this hash table.
"""
# Take care of pickle file I/O
if training_sets_folder.endswith("/"):
training_sets_folder = training_sets_folder[:-1]
if pickle_file_name is not None and pickle_file_name.endswith(".pickle"):
pickle_file_name = pickle_file_name.split(".pickle")[0]
pfile = training_sets_folder + "/" + pickle_file_name + ".pickle"
sys_name = pickle_file_name
if os.path.isfile(pfile):
raise Exception("Pickled training set already exists!")
# Generate empty system for your training set
system = None
system = structures.System(box_size=[1e3, 100.0, 100.0], name=sys_name)
systems_by_composition = {}
# For each folder in the training_sets folder lets get the cml file we
# want and write the energies and forces for that file
for name in os.listdir(training_sets_folder):
# We'll read in any training subset that succeeded and print a warning
# on those that failed
try:
result = orca.read("%s/%s/%s.out" %
(training_sets_folder, name, name))
except IOError:
print(
"Warning - Training Subset %s not included as \
out file not found..." % name)
continue
# Check for convergence
if not result.converged:
print("Warning - Results for %s have not converged." % name)
continue
# Parse the force output and change units. In the case of no force
# found, do not use this set of data
try:
forces = orca.engrad_read("%s/%s/%s.orca.engrad" %
(training_sets_folder, name, name),
pos="Ang")[0]
# Convert force from Ha/Bohr to kcal/mol-Ang
def convert(x):
return units.convert_dist(
"Ang", "Bohr", units.convert_energy("Ha", "kcal", x))
for a, b in zip(result.atoms, forces):
a.fx, a.fy, a.fz = convert(b.fx), convert(b.fy), convert(b.fz)
except (IndexError, IOError):
print(
"Warning - Training Subset %s not included as \
results not found..." % name)
continue
# Get the bonding information
with_bonds = structures.Molecule("%s/%s/%s.cml" %
(training_sets_folder, name, name),
extra_parameters=extra_parameters,
allow_errors=True,
test_charges=False)
# Copy over the forces read in into the system that has the bonding
# information
for a, b in zip(with_bonds.atoms, result.atoms):
a.fx, a.fy, a.fz = b.fx, b.fy, b.fz
# sanity check on atom positions
if geometry.dist(a, b) > 1e-4:
raise Exception('Atoms are different:', (a.x, a.y, a.z),
(b.x, b.y, b.z))
# Rename and save energy
with_bonds.energy = result.energy
with_bonds.name = name
# Now, we read in all the potential three-body interactions that our
# training set takes into account. This will be in a 1D array
composition = ' '.join(sorted([a.element for a in result.atoms]))
if composition not in systems_by_composition:
systems_by_composition[composition] = []
systems_by_composition[composition].append(with_bonds)
# Generate:
# (1) xyz file of various systems as different time steps
# (2) system to simulate
xyz_atoms = []
to_delete = []
for i, composition in enumerate(systems_by_composition):
# Sort so that the lowest energy training subset is first
# in the system
systems_by_composition[composition].sort(key=lambda s: s.energy)
baseline_energy = systems_by_composition[composition][0].energy
# Offset the energies by the lowest energy, and convert energy units
for j, s in enumerate(systems_by_composition[composition]):
s.energy -= baseline_energy
s.energy = units.convert_energy("Ha", "kcal/mol", s.energy)
# Don't use high-energy systems, because these will not likely
# be sampled in MD
if s.energy > high_energy_cutoff:
to_delete.append([composition, j])
continue
# For testing purposes, output
if verbose:
print "Using:", s.name, s.energy
xyz_atoms.append(s.atoms)
system.add(s, len(system.molecules) * system_x_offset)
# Delete the system_names that we aren't actually using due to energy
# being too high
to_delete = sorted(to_delete, key=lambda x: x[1])[::-1]
for d1, d2 in to_delete:
if verbose:
print "Warning - Training Subset %s not included as energy \
is too high..." % systems_by_composition[d1][d2].name
del systems_by_composition[d1][d2]
# Make the box just a little bigger (100) so that we can fit all our
# systems
system.xhi = len(system.molecules) * system_x_offset + 100.0
# Write all of the states we are using to training_sets.xyz
files.write_xyz(xyz_atoms, training_sets_folder + '/' + pickle_file_name)
# Generate our pickle file
print("Saving pickle file %s..." % pfile)
fptr = open(pfile, "wb")
pickle.dump([system, systems_by_composition], fptr)
fptr.close()
# Now we have the data, save it to files for this simulation of
# "run_name" and return parameters
if not os.path.isdir(run_name):
os.mkdir(run_name)
os.chdir(run_name)
mcsmrff_files.write_system_and_training_data(run_name, system,
systems_by_composition)
os.chdir("../")
shutil.copyfile(pfile, "%s/%s.pickle" % (run_name, run_name))
return system, systems_by_composition
def pickle_training_set(run_name,
training_sets_folder="training_set",
pickle_file_name="training_set",
high_energy_cutoff=500.0,
system_x_offset=1000.0,
verbose=False,
extra_parameters={}):
"""
A function to pickle together the training set in a manner that is
readable for MCSMRFF. This is a single LAMMPs data file with each
training set offset alongst the x-axis by system_x_offset. The pickle
file, when read in later, holds a list of two objects. The first is
the entire system as described above. The second is a dictionary of all
molecules in the system, organized by composition.
**Parameters**
run_name: *str*
Name of final training set.
training_sets_folder: *str, optional*
Path to the folder where all the training set data is.
pickle_file_name: *str, optional*
A name for the pickle file and training set system.
high_energy_cutoff: *float, optional*
A cutoff for systems that are too large in energy, as MD is likely
never to sample them.
system_x_offset: *float, optional*
The x offset for the systems to be added by.
verbose: *bool, optional*
Whether to have additional stdout or not.
extra_parameters: *dict, optional*
A dictionaries for additional parameters that do not exist
in the default OPLSAA parameter file.
**Returns**
system: *System*
The entire training set system.
systems_by_composition: *dict, list, Molecule*
Each molecule organized in this hash table.
"""
# Take care of pickle file I/O
if training_sets_folder.endswith("/"):
training_sets_folder = training_sets_folder[:-1]
if pickle_file_name is not None and pickle_file_name.endswith(".pickle"):
pickle_file_name = pickle_file_name.split(".pickle")[0]
pfile = training_sets_folder + "/" + pickle_file_name + ".pickle"
sys_name = pickle_file_name
if os.path.isfile(pfile):
raise Exception("Pickled training set already exists!")
# Generate empty system for your training set
system = None
system = structures.System(box_size=[1e3, 100.0, 100.0], name=sys_name)
systems_by_composition = {}
# For each folder in the training_sets folder lets get the cml file we
# want and write the energies and forces for that file
for name in os.listdir(training_sets_folder):
# We'll read in any training subset that succeeded and print a warning
# on those that failed
try:
result = orca.read("%s/%s/%s.out"
% (training_sets_folder, name, name))
except IOError:
print("Warning - Training Subset %s not included as \
out file not found..." % name)
continue
# Check for convergence
if not result.converged:
print("Warning - Results for %s have not converged." % name)
continue
# Parse the force output and change units. In the case of no force
# found, do not use this set of data
try:
forces = orca.engrad_read("%s/%s/%s.orca.engrad"
% (training_sets_folder, name, name),
pos="Ang")[0]
# Convert force from Ha/Bohr to kcal/mol-Ang
def convert(x):
return units.convert_dist("Ang", "Bohr",
units.convert_energy("Ha",
"kcal",
x)
)
for a, b in zip(result.atoms, forces):
a.fx, a.fy, a.fz = convert(b.fx), convert(b.fy), convert(b.fz)
except (IndexError, IOError):
print("Warning - Training Subset %s not included as \
results not found..." % name)
continue
# Get the bonding information
with_bonds = structures.Molecule("%s/%s/%s.cml"
% (training_sets_folder, name, name),
extra_parameters=extra_parameters,
allow_errors=True,
test_charges=False)
# Copy over the forces read in into the system that has the bonding
# information
for a, b in zip(with_bonds.atoms, result.atoms):
a.fx, a.fy, a.fz = b.fx, b.fy, b.fz
# sanity check on atom positions
if geometry.dist(a, b) > 1e-4:
raise Exception('Atoms are different:', (a.x, a.y, a.z),
(b.x, b.y, b.z)
)
# Rename and save energy
with_bonds.energy = result.energy
with_bonds.name = name
# Now, we read in all the potential three-body interactions that our
# training set takes into account. This will be in a 1D array
composition = ' '.join(sorted([a.element for a in result.atoms]))
if composition not in systems_by_composition:
systems_by_composition[composition] = []
systems_by_composition[composition].append(with_bonds)
# Generate:
# (1) xyz file of various systems as different time steps
# (2) system to simulate
xyz_atoms = []
to_delete = []
for i, composition in enumerate(systems_by_composition):
# Sort so that the lowest energy training subset is first
# in the system
systems_by_composition[composition].sort(key=lambda s: s.energy)
baseline_energy = systems_by_composition[composition][0].energy
# Offset the energies by the lowest energy, and convert energy units
for j, s in enumerate(systems_by_composition[composition]):
s.energy -= baseline_energy
s.energy = units.convert_energy("Ha", "kcal/mol", s.energy)
# Don't use high-energy systems, because these will not likely
# be sampled in MD
if s.energy > high_energy_cutoff:
to_delete.append([composition, j])
continue
# For testing purposes, output
if verbose:
print "Using:", s.name, s.energy
xyz_atoms.append(s.atoms)
system.add(s, len(system.molecules) * system_x_offset)
# Delete the system_names that we aren't actually using due to energy
# being too high
to_delete = sorted(to_delete, key=lambda x: x[1])[::-1]
for d1, d2 in to_delete:
if verbose:
print "Warning - Training Subset %s not included as energy \
is too high..." % systems_by_composition[d1][d2].name
del systems_by_composition[d1][d2]
# Make the box just a little bigger (100) so that we can fit all our
# systems
system.xhi = len(system.molecules) * system_x_offset + 100.0
# Write all of the states we are using to training_sets.xyz
files.write_xyz(xyz_atoms, training_sets_folder + '/' + pickle_file_name)
# Generate our pickle file
print("Saving pickle file %s..." % pfile)
fptr = open(pfile, "wb")
pickle.dump([system, systems_by_composition], fptr)
fptr.close()
# Now we have the data, save it to files for this simulation of
# "run_name" and return parameters
if not os.path.isdir(run_name):
os.mkdir(run_name)
os.chdir(run_name)
mcsmrff_files.write_system_and_training_data(run_name,
system,
systems_by_composition
)
os.chdir("../")
shutil.copyfile(pfile, "%s/%s.pickle" % (run_name, run_name))
return system, systems_by_composition