def read_reference_data(f): # noqa C901
eV_to_kcalmol = 0.036749326 / 0.0015946679
e_next, f_next, geo_next = False, False, False
n_atoms = None
R, z, E, F = [], [], [], []
geo_idx = 0
for line in f:
if n_atoms:
cols = line.split()
if e_next:
E.append(float(cols[5]))
e_next = False
elif f_next:
a = int(cols[1]) - 1
F.append(list(map(float, cols[2:5])))
if a == n_atoms - 1:
f_next = False
elif geo_next:
if 'atom' in cols:
a_count += 1 # noqa: F821
R.append(list(map(float, cols[1:4])))
if geo_idx == 0:
z.append(io._z_str_to_z_dict[cols[4]])
if a_count == n_atoms:
geo_next = False
geo_idx += 1
elif 'Energy and forces in a compact form:' in line:
e_next = True
elif 'Total atomic forces (unitary forces cleaned) [eV/Ang]:' in line:
f_next = True
elif ('Atomic structure (and velocities) as used in the preceding time step:'
in line):
geo_next = True
a_count = 0
elif 'The structure contains' in line and 'atoms, and a total of' in line:
n_atoms = int(line.split()[3])
print('Number atoms per geometry: {:>7d}'.format(n_atoms))
continue
if geo_idx > 0 and geo_idx % 1000 == 0:
sys.stdout.write(
"\rNumber geometries found so far: {:>7d}".format(geo_idx))
sys.stdout.flush()
sys.stdout.write(
"\rNumber geometries found so far: {:>7d}".format(geo_idx))
sys.stdout.flush()
print('\n' + ui.info_str('[INFO]') +
' Energies and forces have been converted from eV to kcal/mol(/Ang)')
R = np.array(R).reshape(-1, n_atoms, 3)
z = np.array(z)
E = np.array(E) * eV_to_kcalmol
F = np.array(F).reshape(-1, n_atoms, 3) * eV_to_kcalmol
f.close()
return (R, z, E, F)
base_vars = {
'type': 'd',
'name': dataset['name'].astype(str),
'theory': dataset['theory'].astype(str),
'z': dataset['z'],
'R': R,
'E': E,
'F': F,
}
base_vars['md5'] = io.dataset_md5(base_vars)
subset_file_name = '%s_%s.npz' % (
os.path.splitext(os.path.basename(dataset_path))[0],
s,
)
file_exists = os.path.isfile(subset_file_name)
if file_exists and args.overwrite:
print(ui.info_str('[INFO]') + ' Overwriting existing model file.')
if not file_exists or args.overwrite:
np.savez_compressed(subset_file_name, **base_vars)
ui.progr_toggle(is_done=True, disp_str='Extracted %s dataset saved to \'%s\'' % (s, subset_file_name))
else:
print(
ui.warn_str('[WARN]')
+ ' %s dataset \'%s\' already exists.' % (s.capitalize(), subset_file_name)
+ '\n Run \'python %s -o %s %s\' to overwrite.\n'
% (os.path.basename(__file__), model_path, dataset_path)
)
sys.exit()
'--overwrite',
dest='overwrite',
action='store_true',
help='overwrite existing dataset file')
args = parser.parse_args()
geometries = args.geometries
forces = args.forces
energies = args.energies
energy_col = args.energy_col
name = os.path.splitext(os.path.basename(geometries.name))[0]
dataset_file_name = name + '.npz'
dataset_exists = os.path.isfile(dataset_file_name)
if dataset_exists and args.overwrite:
print ui.info_str('[INFO]') + ' Overwriting existing dataset file.'
if not dataset_exists or args.overwrite:
print 'Writing dataset to \'%s\'...' % dataset_file_name
else:
sys.exit(
ui.fail_str('[FAIL]') +
' Dataset \'%s\' already exists.' % dataset_file_name)
print 'Reading geometries...'
R, z = read_concat_xyz(geometries)
print 'Reading forces...'
F, _ = read_concat_xyz(forces)
print 'Reading energies from column %d...' % energy_col
E = read_out_file(energies, energy_col)
parser.add_argument(
'-o',
'--overwrite',
dest='overwrite',
action='store_true',
help='overwrite existing dataset file',
)
args = parser.parse_args()
dataset = args.dataset
name = os.path.splitext(os.path.basename(dataset.name))[0]
dataset_file_name = name + '.npz'
dataset_exists = os.path.isfile(dataset_file_name)
if dataset_exists and args.overwrite:
print(ui.info_str('[INFO]') + ' Overwriting existing dataset file.')
if not dataset_exists or args.overwrite:
print('Writing dataset to \'%s\'...' % dataset_file_name)
else:
sys.exit(
ui.fail_str('[FAIL]') +
' Dataset \'%s\' already exists.' % dataset_file_name)
R, z, E, F = read_reference_data(dataset)
# Prune all arrays to same length.
n_mols = min(min(R.shape[0], F.shape[0]), E.shape[0])
if n_mols != R.shape[0] or n_mols != F.shape[0] or n_mols != E.shape[0]:
print(
ui.warn_str('[WARN]') +
' Incomplete output detected: Final dataset was pruned to %d points.' %
help = 'path to dataset file')
parser.add_argument('-o',
'--overwrite',
dest='overwrite',
action='store_true',
help='overwrite existing xyz dataset file')
args = parser.parse_args()
dataset_path, dataset = args.dataset
name = os.path.splitext(os.path.basename(dataset_path))[0]
dataset_file_name = name + '.xyz'
xyz_exists = os.path.isfile(dataset_file_name)
if xyz_exists and args.overwrite:
print ui.info_str('[INFO]') + ' Overwriting existing xyz dataset file.'
if not xyz_exists or args.overwrite:
print 'Writing dataset to \'%s\'...' % dataset_file_name
else:
sys.exit(
ui.fail_str('[FAIL]') +
' Dataset \'%s\' already exists.' % dataset_file_name)
z = dataset['z']
R = dataset['R']
F = dataset['F']
E = dataset['E']
n = R.shape[0]
try:
with open(dataset_file_name, 'w') as f: