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()
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()
' 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)
# 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.' % n_mols
R = R[:n_mols, :, :]
F = F[:n_mols, :, :]
E = E[:n_mols]
print ui.info_str(
'[INFO]') + ' Geometries, forces and energies must have consistent units.'
R_conv_fact = raw_input_float('Unit conversion factor for geometries: ')
R = R * R_conv_fact
F_conv_fact = raw_input_float('Unit conversion factor for forces: ')
F = F * F_conv_fact
E_conv_fact = raw_input_float('Unit conversion factor for energies: ')
E = E * E_conv_fact
# Base variables contained in every model file.