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_concat_ext_xyz(dataset)
# Base variables contained in every model file.
base_vars = {'type': 'd',\
'R': R,\
'z': z,\
'E': E[:,None],\
'F': F,\
'name': name,\
'theory': 'unknown'}
base_vars['md5'] = io.dataset_md5(base_vars)
np.savez_compressed(dataset_file_name, **base_vars)
print ui.pass_str('DONE')
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]
# Base variables contained in every model file.
base_vars = {
'type': 'd',
'R': R,
'z': z,
'E': E[:, None],
'F': F,
'e_unit': 'kcal/mol',
'r_unit': 'Ang',
'name': name,
'theory': 'unknown',
}
base_vars['F_min'], base_vars['F_max'] = np.min(F.ravel()), np.max(F.ravel())
base_vars['F_mean'], base_vars['F_var'] = np.mean(F.ravel()), np.var(F.ravel())
base_vars['E_min'], base_vars['E_max'] = np.min(E), np.max(E)
base_vars['E_mean'], base_vars['E_var'] = np.mean(E), np.var(E)
base_vars['md5'] = io.dataset_md5(base_vars)
np.savez_compressed(dataset_file_name, **base_vars)
print(ui.pass_str('DONE'))
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')
f.write('\t'.join(str(x) for x in atom) + '\t')
f.write('\t'.join(str(x) for x in F[i][j]))
f.write('\n')
progr = float(i) / (n - 1)
ui.progr_bar(i, n - 1, disp_str='Exporting %d data points...' % n)
except IOError:
sys.exit("ERROR: Writing xyz file failed.")
print('\n' + ui.pass_str('DONE'))