def evaluate(self, test_structures, ref_energies, ref_forces,
ref_stresses):
"""
Evaluate energies, forces and stresses of structures with trained
interatomic potentials.
Args:
test_structures ([Structure]): List of Pymatgen Structure Objects.
ref_energies ([float]): List of DFT-calculated total energies of
each structure in structures list.
ref_forces ([np.array]): List of DFT-calculated (m, 3) forces of
each structure with m atoms in structures list. m can be varied
with each single structure case.
ref_stresses (list): List of DFT-calculated (6, ) viriral stresses
of each structure in structures list.
"""
predict_pool = pool_from(test_structures, ref_energies, ref_forces,
ref_stresses)
_, df_orig = convert_docs(predict_pool)
_, df_predict = convert_docs(pool_from(test_structures))
outputs = self.model.predict(inputs=test_structures, override=True)
df_predict['y_orig'] = df_predict['n'] * outputs
return df_orig, df_predict
def train(self,
train_structures,
energies,
forces,
stresses=None,
**kwargs):
"""
Training data with model.
Args:
train_structures ([Structure]): The list of Pymatgen Structure object.
energies ([float]): The list of total energies of each structure
in structures list.
energies ([float]): List of total energies of each structure in
structures list.
forces ([np.array]): List of (m, 3) forces array of each structure
with m atoms in structures list. m can be varied with each
single structure case.
stresses (list): List of (6, ) virial stresses of each
structure in structures list.
"""
train_pool = pool_from(train_structures, energies, forces, stresses)
_, df = convert_docs(train_pool)
ytrain = df['y_orig'] / df['n']
self.model.fit(inputs=train_structures, outputs=ytrain, **kwargs)
self.specie = Element(train_structures[0].symbol_set[0])
def evaluate(self,
test_structures,
ref_energies=None,
ref_forces=None,
ref_stresses=None,
predict_energies=True,
predict_forces=True,
predict_stress=False):
"""
Evaluate energies, forces and stresses of structures with trained
interatomic potentials.
Args:
test_structures ([Structure]): List of Pymatgen Structure Objects.
ref_energies ([float]): List of DFT-calculated total energies of
each structure in structures list.
ref_forces ([np.array]): List of DFT-calculated (m, 3) forces of
each structure with m atoms in structures list. m can be varied
with each single structure case.
ref_stresses (list): List of DFT-calculated (6, ) viriral stresses
of each structure in structures list.
predict_energies (bool): Whether to predict energies of configurations.
predict_forces (bool): Whether to predict forces of configurations.
predict_stress (bool): Whether to predict virial stress of
configurations.
"""
if not which('quip'):
raise RuntimeError(
"quip has not been found.\n",
"Please refer to https://github.com/libAtoms/QUIP for ",
"further detail.")
xml_file = 'predict.xml'
original_file = 'original.xyz'
predict_file = 'predict.xyz'
predict_pool = pool_from(test_structures, ref_energies, ref_forces,
ref_stresses)
with ScratchDir('.'):
_ = self.write_param(xml_file)
original_file = self.write_cfgs(original_file,
cfg_pool=predict_pool)
_, df_orig = self.read_cfgs(original_file)
exe_command = ["quip"]
exe_command.append("atoms_filename={}".format(original_file))
exe_command.append("param_filename={}".format(xml_file))
if predict_energies:
exe_command.append("energy=T")
if predict_forces:
exe_command.append("forces=T")
if predict_stress:
exe_command.append("virial=T")
p = subprocess.Popen(exe_command, stdout=open(predict_file, 'w'))
stdout = p.communicate()[0]
rc = p.returncode
_, df_predict = self.read_cfgs(predict_file, predict=True)
return df_orig, df_predict
def test_pool_from(self):
test_pool = pool_from(self.test_structures, self.test_energies,
self.test_forces, self.test_stresses)
for p1, p2 in zip(test_pool, self.test_pool):
self.assertEqual(p1['outputs']['energy'], p2['outputs']['energy'])
self.assertEqual(p1['outputs']['forces'], p2['outputs']['forces'])
self.assertEqual(p1['outputs']['virial_stress'],
p2['outputs']['virial_stress'])
def evaluate(self, test_structures, ref_energies, ref_forces, ref_stresses):
"""
Evaluate energies, forces and stresses of structures with trained
interatomic potentials.
Args:
test_structures ([Structure]): List of Pymatgen Structure Objects.
ref_energies ([float]): List of DFT-calculated total energies of
each structure in structures list.
ref_forces ([np.array]): List of DFT-calculated (m, 3) forces of
each structure with m atoms in structures list. m can be varied
with each single structure case.
ref_stresses (list): List of DFT-calculated (6, ) viriral stresses
of each structure in structures list.
"""
if not which('nnp-predict'):
raise RuntimeError("NNP Predictor has not been found.")
original_file = 'input.data'
predict_file = 'output.data'
predict_pool = pool_from(test_structures, ref_energies,
ref_forces, ref_stresses)
with ScratchDir('.'):
_, _ = self.write_param()
original_file = self.write_cfgs(original_file, cfg_pool=predict_pool)
_, df_orig = self.read_cfgs(original_file)
input_filename = self.write_input()
dfs = []
for data in predict_pool:
_ = self.write_cfgs(original_file, cfg_pool=[data])
p = subprocess.Popen(['nnp-predict', input_filename], stdout=subprocess.PIPE)
stdout = p.communicate()[0]
rc = p.returncode
if rc != 0:
error_msg = 'RuNNer exited with return code %d' % rc
msg = stdout.decode("utf-8").split('\n')[:-1]
try:
error_line = [i for i, m in enumerate(msg)
if m.startswith('ERROR')][0]
error_msg += ', '.join([e for e in msg[error_line:]])
except:
error_msg += msg[-1]
raise RuntimeError(error_msg)
_, df = self.read_cfgs(predict_file)
dfs.append(df)
df_predict = pd.concat(dfs, ignore_index=True)
return df_orig, df_predict
def train(self, train_structures, energies=None, forces=None, stresses=None,
**kwargs):
"""
Training data with moment tensor method.
Args:
train_structures ([Structure]): The list of Pymatgen Structure object.
energies ([float]): The list of total energies of each structure
in structures list.
energies ([float]): List of total energies of each structure in
structures list.
forces ([np.array]): List of (m, 3) forces array of each structure
with m atoms in structures list. m can be varied with each
single structure case.
stresses (list): List of (6, ) virial stresses of each
structure in structures list.
kwargs: Parameters in write_input method.
"""
if not which('nnp-train'):
raise RuntimeError("NNP Trainer has not been found.")
train_pool = pool_from(train_structures, energies, forces, stresses)
atoms_filename = 'input.data'
with ScratchDir('.'):
atoms_filename = self.write_cfgs(filename=atoms_filename, cfg_pool=train_pool)
output = 'training_output'
input_filename = self.write_input(**kwargs)
p_scaling = subprocess.Popen(['nnp-scaling', input_filename])
stdout = p_scaling.communicate()[0]
p_train = subprocess.Popen(['nnp-train', input_filename],
stdout=open(output, 'w'))
stdout = p_train.communicate()[0]
rc = p_train.returncode
if rc != 0:
error_msg = 'RuNNer exited with return code %d' % rc
msg = stdout.decode("utf-8").split('\n')[:-1]
try:
error_line = [i for i, m in enumerate(msg)
if m.startswith('ERROR')][0]
error_msg += ', '.join([e for e in msg[error_line:]])
except:
error_msg += msg[-1]
raise RuntimeError(error_msg)
with zopen(output) as f:
error_lines = f.read()
energy_rmse_pattern = re.compile('ENERGY\s*\S*\s*(\S*)\s*(\S*).*?\n')
forces_rmse_pattern = re.compile('FORCES\s*\S*\s*(\S*)\s*(\S*).*?\n')
self.train_energy_rmse, self.validation_energy_rmse = \
np.array([line for line in energy_rmse_pattern.findall(error_lines)],
dtype=np.float).T
self.train_forces_rmse, self.validation_forces_rmse = \
np.array([line for line in forces_rmse_pattern.findall(error_lines)],
dtype=np.float).T
weights_filename_pattern = 'weights*{}.out'.format(self.param.get('epochs'))
weights_filename = glob.glob(weights_filename_pattern)[0]
self.suffix = weights_filename.split('.')[1]
self.load_weights(weights_filename)
self.load_scaler('scaling.data')
return rc
def evaluate(self,
test_structures,
ref_energies=None,
ref_forces=None,
ref_stresses=None,
**kwargs):
"""
Evaluate energies, forces and stresses of structures with trained
interatomic potentials.
Args:
test_structures ([Structure]): List of Pymatgen Structure Objects.
ref_energies ([float]): List of DFT-calculated total energies of
each structure in structures list.
ref_forces ([np.array]): List of DFT-calculated (m, 3) forces of
each structure with m atoms in structures list. m can be varied
with each single structure case.
ref_stresses (list): List of DFT-calculated (6, ) viriral stresses
of each structure in structures list.
kwargs: Parameters of write_param method.
"""
if not which('mlp'):
raise RuntimeError(
"mlp has not been found.\n",
"Please refer to http://gitlab.skoltech.ru/shapeev/mlip ",
"for further detail.")
fitted_mtp = 'fitted.mtp'
original_file = 'original.cfgs'
predict_file = 'predict.cfgs'
predict_pool = pool_from(test_structures, ref_energies, ref_forces,
ref_stresses)
dataset = predict_pool[0]
if isinstance(dataset['structure'], dict):
structure = Structure.from_dict(dataset['structure'])
else:
structure = dataset['structure']
symbol = structure.symbol_set[0]
with ScratchDir('.'):
self.write_param(fitted_mtp=fitted_mtp,
Abinitio=0,
Driver=1,
Write_cfgs=predict_file,
Database_filename=original_file,
**kwargs)
original_file = self.write_cfg(original_file,
cfg_pool=predict_pool)
_, df_orig = self.read_cfgs(original_file, symbol=symbol)
p = subprocess.Popen([
'mlp', 'run', 'mlip.ini', '--filename={}'.format(original_file)
],
stdout=subprocess.PIPE)
stdout = p.communicate()[0]
rc = p.returncode
if rc != 0:
error_msg = 'MLP exited with return code %d' % rc
msg = stdout.decode("utf-8").split('\n')[:-1]
try:
error_line = [
i for i, m in enumerate(msg) if m.startswith('ERROR')
][0]
error_msg += ', '.join([e for e in msg[error_line:]])
except Exception:
error_msg += msg[-1]
raise RuntimeError(error_msg)
if not os.path.exists(predict_file):
predict_file = '_'.join([predict_file, '0'])
_, df_predict = self.read_cfgs(predict_file, symbol=symbol)
return df_orig, df_predict
def train(self,
train_structures,
energies=None,
forces=None,
stresses=None,
unfitted_mtp=None,
max_dist=5,
radial_basis_size=8,
max_iter=500,
energy_weight=1,
force_weight=1e-2,
stress_weight=0):
"""
Training data with moment tensor method.
Args:
train_structures ([Structure]): The list of Pymatgen Structure object.
energies ([float]): The list of total energies of each structure
in structures list.
energies ([float]): List of total energies of each structure in
structures list.
forces ([np.array]): List of (m, 3) forces array of each structure
with m atoms in structures list. m can be varied with each
single structure case.
stresses (list): List of (6, ) virial stresses of each
structure in structures list.
unfitted_mtp (str): Define the initial mtp file. Default to
the mtp file stored in .params directory.
max_dist (float): The actual radial cutoff.
radial_basis_size (int): Relevant to number of radial basis function.
max_iter (int): The number of maximum iteration.
energy_weight (float): The weight of energy.
force_weight (float): The weight of forces.
stress_weight (float): The weight of stresses.
"""
if not which('mlp'):
raise RuntimeError(
"mlp has not been found.\n",
"Please refer to http://gitlab.skoltech.ru/shapeev/mlip ",
"for further detail.")
train_pool = pool_from(train_structures, energies, forces, stresses)
atoms_filename = 'train.cfgs'
with ScratchDir('.'):
atoms_filename = self.write_cfg(filename=atoms_filename,
cfg_pool=train_pool)
if not unfitted_mtp:
raise RuntimeError("No specific potentials file provided.")
MTP_file_path = os.path.join(module_dir, 'params', unfitted_mtp)
shutil.copyfile(MTP_file_path,
os.path.join(os.getcwd(), unfitted_mtp))
with open(unfitted_mtp) as f:
template = f.read()
s = template % (max_dist, radial_basis_size)
with open(unfitted_mtp, 'w') as f:
f.write(s)
save_fitted_mtp = '.'.join([
unfitted_mtp.split('.')[0] + '_fitted',
unfitted_mtp.split('.')[1]
])
p = subprocess.Popen([
'mlp', 'train', unfitted_mtp, atoms_filename,
'--max-iter={}'.format(max_iter),
'--trained-pot-name={}'.format(save_fitted_mtp),
'--curr-pot-name={}'.format(unfitted_mtp),
'--energy-weight={}'.format(energy_weight),
'--force-weight={}'.format(force_weight),
'--stress-weight={}'.format(stress_weight),
'--init-params=same', '--auto-min-dist'
],
stdout=subprocess.PIPE)
stdout = p.communicate()[0]
rc = p.returncode
if rc != 0:
error_msg = 'MLP exited with return code %d' % rc
msg = stdout.decode("utf-8").split('\n')[:-1]
try:
error_line = [
i for i, m in enumerate(msg) if m.startswith('ERROR')
][0]
error_msg += ', '.join([e for e in msg[error_line:]])
except Exception:
error_msg += msg[-1]
raise RuntimeError(error_msg)
def load_config(filename):
param = OrderedDict()
with open(filename, 'r') as f:
lines = f.readlines()
param['safe'] = [line.rstrip() for line in lines[:-2]]
for line in lines[-2:]:
key = line.rstrip().split(' = ')[0]
value = json.loads(line.rstrip().split(' = ')[1].replace(
'{', '[').replace('}', ']'))
param[key] = value
return param
self.param = load_config(save_fitted_mtp)
return rc
def train(self,
train_structures,
energies=None,
forces=None,
stresses=None,
default_sigma=[0.0005, 0.1, 0.05, 0.01],
use_energies=True,
use_forces=True,
use_stress=False,
**kwargs):
"""
Training data with gaussian process regression.
Args:
train_structures ([Structure]): The list of Pymatgen Structure object.
energies ([float]): The list of total energies of each structure
in structures list.
energies ([float]): List of total energies of each structure in
structures list.
forces ([np.array]): List of (m, 3) forces array of each structure
with m atoms in structures list. m can be varied with each
single structure case.
stresses (list): List of (6, ) virial stresses of each
structure in structures list.
default_sigma (list): Error criteria in energies, forces, stress
and hessian. Should have 4 numbers.
use_energies (bool): Whether to use dft total energies for training.
Default to True.
use_forces (bool): Whether to use dft atomic forces for training.
Default to True.
use_stress (bool): Whether to use dft virial stress for training.
Default to False.
kwargs:
l_max (int): Parameter to configure GAP. The band limit of
spherical harmonics basis function. Default to 12.
n_max (int): Parameter to configure GAP. The number of radial basis
function. Default to 10.
atom_sigma (float): Parameter to configure GAP. The width of gaussian
atomic density. Default to 0.5.
zeta (float): Present when covariance function type is do product.
Default to 4.
cutoff (float): Parameter to configure GAP. The cutoff radius.
Default to 4.0.
cutoff_transition_width (float): Parameter to configure GAP.
The transition width of cutoff radial. Default to 0.5.
delta (float): Parameter to configure Sparsification.
The signal variance of noise. Default to 1.
f0 (float): Parameter to configure Sparsification.
The signal mean of noise. Default to 0.0.
n_sparse (int): Parameter to configure Sparsification.
Number of sparse points.
covariance_type (str): Parameter to configure Sparsification.
The type of convariance function. Default to dot_product.
sparse_method (str): Method to perform clustering in sparsification.
Default to 'cur_points'.
sparse_jitter (float): Intrisic error of atomic/bond energy,
used to regularise the sparse covariance matrix.
Default to 1e-8.
e0 (float): Atomic energy value to be subtracted from energies
before fitting. Default to 0.0.
e0_offset (float): Offset of baseline. If zero, the offset is
the average atomic energy of the input data or the e0
specified manually. Default to 0.0.
"""
if not which('gap_fit'):
raise RuntimeError(
"gap_fit has not been found.\n",
"Please refer to https://github.com/libAtoms/QUIP for ",
"further detail.")
atoms_filename = 'train.xyz'
xml_filename = 'train.xml'
train_pool = pool_from(train_structures, energies, forces, stresses)
exe_command = ["gap_fit"]
exe_command.append('at_file={}'.format(atoms_filename))
gap_configure_params = [
'l_max', 'n_max', 'atom_sigma', 'zeta', 'cutoff',
'cutoff_transition_width', 'delta', 'f0', 'n_sparse',
'covariance_type', 'sparse_method'
]
preprocess_params = ['sparse_jitter', 'e0', 'e0_offset']
if len(default_sigma) != 4:
raise ValueError(
"The default sigma is supposed to have 4 numbers.")
gap_command = ['soap']
for param_name in gap_configure_params:
param = kwargs.get(param_name) if kwargs.get(param_name) \
else soap_params.get(param_name)
gap_command.append(param_name + '=' + '{}'.format(param))
exe_command.append("gap=" + "{" + "{}".format(' '.join(gap_command)) +
"}")
for param_name in preprocess_params:
param = kwargs.get(param_name) if kwargs.get(param_name) \
else soap_params.get(param_name)
exe_command.append(param_name + '=' + '{}'.format(param))
default_sigma = [str(f) for f in default_sigma]
exe_command.append("default_sigma={%s}" % (' '.join(default_sigma)))
if use_energies:
exe_command.append('energy_parameter_name=dft_energy')
if use_forces:
exe_command.append('force_parameter_name=dft_force')
if use_stress:
exe_command.append('virial_parameter_name=dft_virial')
exe_command.append('gp_file={}'.format(xml_filename))
with ScratchDir('.'):
self.write_cfgs(filename=atoms_filename, cfg_pool=train_pool)
p = subprocess.Popen(exe_command, stdout=subprocess.PIPE)
stdout = p.communicate()[0]
rc = p.returncode
if rc != 0:
error_msg = 'QUIP exited with return code %d' % rc
msg = stdout.decode("utf-8").split('\n')[:-1]
try:
error_line = [
i for i, m in enumerate(msg) if m.startswith('ERROR')
][0]
error_msg += ', '.join([e for e in msg[error_line:]])
except Exception:
error_msg += msg[-1]
raise RuntimeError(error_msg)
def get_xml(xml_file):
tree = ET.parse(xml_file)
root = tree.getroot()
potential_label = root.tag
gpcoordinates = list(root.iter('gpCoordinates'))[0]
param_file = gpcoordinates.get('sparseX_filename')
param = np.loadtxt(param_file)
return tree, param, potential_label
tree, param, potential_label = get_xml(xml_filename)
self.param['xml'] = tree
self.param['param'] = param
self.param['potential_label'] = potential_label
return rc