def test_number_of_features(self):
"""Tests that the reported number of features is correct.
"""
species = [1, 8]
n_elem = len(species)
desc = ACSF(rcut=6.0, species=species)
n_features = desc.get_number_of_features()
self.assertEqual(n_features, n_elem)
desc = ACSF(rcut=6.0, species=species, g2_params=[[1, 2], [4, 5]])
n_features = desc.get_number_of_features()
self.assertEqual(n_features, n_elem * (2 + 1))
desc = ACSF(rcut=6.0, species=[1, 8], g3_params=[1, 2, 3, 4])
n_features = desc.get_number_of_features()
self.assertEqual(n_features, n_elem * (4 + 1))
desc = ACSF(rcut=6.0,
species=[1, 8],
g4_params=[[1, 2, 3], [3, 1, 4], [4, 5, 6], [7, 8, 9]])
n_features = desc.get_number_of_features()
self.assertEqual(n_features, n_elem + 4 * 3)
desc = ACSF(rcut=6.0,
species=[1, 8],
g2_params=[[1, 2], [4, 5]],
g3_params=[1, 2, 3, 4],
g4_params=[[1, 2, 3], [3, 1, 4], [4, 5, 6], [7, 8, 9]])
n_features = desc.get_number_of_features()
self.assertEqual(n_features, n_elem * (1 + 2 + 4) + 4 * 3)
def test_properties(self):
"""Used to test that changing the setup through properties works as
intended.
"""
# Test changing species
a = ACSF(
rcut=6.0,
species=[1, 8],
g2_params=[[1, 2]],
sparse=False,
)
nfeat1 = a.get_number_of_features()
vec1 = a.create(H2O)
a.species = ["C", "H", "O"]
nfeat2 = a.get_number_of_features()
vec2 = a.create(molecule("CH3OH"))
self.assertTrue(nfeat1 != nfeat2)
self.assertTrue(vec1.shape[1] != vec2.shape[1])
def test_parallel_sparse(self):
"""Tests creating sparse output parallelly.
"""
# Test indices
samples = [molecule("CO"), molecule("N2O")]
desc = ACSF(rcut=6.0,
species=[6, 7, 8],
g2_params=[[1, 2], [4, 5]],
g3_params=[1, 2, 3, 4],
g4_params=[[1, 2, 3], [3, 1, 4], [4, 5, 6], [7, 8, 9]],
g5_params=[[1, 2, 3], [3, 1, 4], [4, 5, 6], [7, 8, 9]],
sparse=True)
n_features = desc.get_number_of_features()
# Multiple systems, serial job
output = desc.create(
system=samples,
positions=[[0], [0, 1]],
n_jobs=1,
).toarray()
assumed = np.empty((3, n_features))
assumed[0, :] = desc.create(samples[0], [0]).toarray()
assumed[1, :] = desc.create(samples[1], [0]).toarray()
assumed[2, :] = desc.create(samples[1], [1]).toarray()
self.assertTrue(np.allclose(output, assumed))
# Test when position given as indices
output = desc.create(
system=samples,
positions=[[0], [0, 1]],
n_jobs=2,
).toarray()
assumed = np.empty((3, n_features))
assumed[0, :] = desc.create(samples[0], [0]).toarray()
assumed[1, :] = desc.create(samples[1], [0]).toarray()
assumed[2, :] = desc.create(samples[1], [1]).toarray()
self.assertTrue(np.allclose(output, assumed))
# Test with no positions specified
output = desc.create(
system=samples,
positions=[None, None],
n_jobs=2,
).toarray()
assumed = np.empty((2 + 3, n_features))
assumed[0, :] = desc.create(samples[0], [0]).toarray()
assumed[1, :] = desc.create(samples[0], [1]).toarray()
assumed[2, :] = desc.create(samples[1], [0]).toarray()
assumed[3, :] = desc.create(samples[1], [1]).toarray()
assumed[4, :] = desc.create(samples[1], [2]).toarray()
self.assertTrue(np.allclose(output, assumed))
def createDescriptorsACSF(
data,
metadata,
cutoff_ACSF=default_cutoff_ACSF,
g2_params=default_g2_params,
g3_params=default_g3_params,
):
# Updating metadata
# Prepping ACSF descriptor structure
acsf = ACSF(species=metadata['species'],
rcut=metadata['cutoff_acsf'],
g2_params=metadata['g2_params'],
g4_params=metadata['g3_params'])
metadata['n_features'] = acsf.get_number_of_features()
# Computing descriptors
descriptors = []
for index_atom in tqdm.tqdm(range(metadata['n_atoms'])):
descriptors_loc = np.empty((np.shape(data)[0], metadata['n_features']))
for index_structure in range(metadata['train_set_size']):
descriptors_loc[index_structure, :] = acsf.create(
data[index_structure], positions=[index_atom])
descriptors.append(descriptors_loc)
return metadata, descriptors
def create_data_ACSF(data, metadata):
particles, scaler, test_size, rcut, nmax, lmax, N_PCA, sigma_SOAP = [
metadata[x] for x in [
'particles', 'scaler', 'test_size', 'rcut', 'nmax', 'lmax',
'N_PCA', 'sigma_SOAP'
]
]
acsf = ACSF(species=["H", "O"],
rcut=9.0,
g2_params=[[1, 0], [0.1, 0], [0.01, 0], [0.01, 0], [0.001, 0]],
g4_params=[[1, 1, 1], [1, 2, 1], [1, 1, -1], [1, 2, -1],
[0.1, 1, 1], [0.1, 2, 1], [0.1, 1, -1],
[0.1, 2, -1], [0.01, 1, 1], [0.01, 2, 1],
[0.01, 1, -1], [0.01, 2, -1]])
nb_features = acsf.get_number_of_features()
descriptors = pd.np.empty(
(data.index.max() + 1, len(particles), nb_features))
for i_time in tqdm.tqdm(range(data.index.max() + 1)):
descriptors[i_time] = acsf.create(data['molec'][i_time],
positions=np.arange(len(particles)))
#create training set
try:
data['is_train']
except KeyError:
data['is_train'] = create_is_train(data.index.max() + 1)
else:
pass
#selecting best params
if N_PCA:
try:
metadata['PCAs']
except KeyError:
PCAs = select_best_params(descriptors[data['is_train'].values],
nb_features, N_PCA)
new_descriptors = pd.np.empty(
(data.index.max() + 1, len(particles), N_PCA))
new_descriptors[:, :2, :] = PCAs[0].transform(
descriptors[:, :2, :].reshape(
descriptors[:, :2, :].shape[0] * 2,
nb_features)).reshape(descriptors.shape[0], 2, N_PCA)
new_descriptors[:, 2:, :] = PCAs[1].transform(
descriptors[:, 2:, :].reshape(
descriptors[:, 2:, :].shape[0] * 5,
nb_features)).reshape(descriptors.shape[0], 5, N_PCA)
descriptors = new_descriptors
metadata['old_N_feature'] = nb_features
nb_features = N_PCA
metadata['PCAs'] = PCAs
else:
PCAs = metadata['PCAs']
new_descriptors = pd.np.empty(
(data.index.max() + 1, len(particles), N_PCA))
new_descriptors[:, :2, :] = PCAs[0].transform(
descriptors[:, :2, :].reshape(
descriptors[:, :2, :].shape[0] * 2,
nb_features)).reshape(descriptors.shape[0], 2, N_PCA)
new_descriptors[:, 2:, :] = PCAs[1].transform(
descriptors[:, 2:, :].reshape(
descriptors[:, 2:, :].shape[0] * 5,
nb_features)).reshape(descriptors.shape[0], 5, N_PCA)
descriptors = new_descriptors
nb_features = N_PCA
else:
pass
#scaling
if scaler == False:
pass
elif type(scaler) == type(None):
descriptors, scaler = scale_descriptors(data, descriptors)
else:
descriptors[:, 0:2, :] = scaler[0].transform(
descriptors[:, 0:2, :].reshape(descriptors[:, 0:2, :].shape[0] * 2,
nb_features)).reshape(
descriptors.shape[0], 2,
nb_features)
descriptors[:,
2:, :] = scaler[1].transform(descriptors[:, 2:, :].reshape(
descriptors[:, 2:, :].shape[0] * 5,
nb_features)).reshape(descriptors.shape[0], 5,
nb_features)
metadata['scaler'] = scaler
return data.join(pd.DataFrame({'descriptor': list(descriptors)})), metadata