'--overwrite',
dest='overwrite',
action='store_true',
help='overwrite existing files',
)
args = parser.parse_args()
model_path, model = args.model
dataset_path, dataset = args.dataset
for s in ['train', 'valid']:
if dataset['md5'] != model['md5_' + s]:
sys.exit(
ui.fail_str('[FAIL]')
+ ' Dataset fingerprint does not match the one referenced in model for \'%s\'.'
% s
)
idxs = model['idxs_' + s]
R = dataset['R'][idxs, :, :]
E = dataset['E'][idxs]
F = dataset['F'][idxs, :, :]
base_vars = {
'type': 'd',
'name': dataset['name'].astype(str),
'theory': dataset['theory'].astype(str),
'z': dataset['z'],
'R': R,
def raw_input_float(prompt):
while True:
try:
return float(raw_input(prompt))
except ValueError:
print ui.fail_str('[FAIL]') + ' That is not a valid float.'
)
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:
for i, r in enumerate(R):
f.write(str(len(r)) + '\n' + str(np.squeeze(E[i])))
for j, atom in enumerate(r):
f.write('\n' + io._z_to_z_str_dict[z[j]] + '\t')
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)
mols = read(dataset, index=':')
print("\rNumber geometries found: {:>7d}\n".format(len(mols)))
#cell = np.array(mols[0].get_cell())
#print(cell)
Z = np.array([mol.get_atomic_numbers() for mol in mols])
all_z_the_same = (Z == Z[0]).all()
if not all_z_the_same:
sys.exit(ui.fail_str('[FAIL]') + ' Order of atoms changes within dataset.')
# Base variables contained in every model file.
base_vars = {
