def test_ads_fp_gen(self):
"""Test the feature generation."""
images = self.setup_atoms()
images = autogen_info(images)
print(str(len(images)) + ' training examples.')
gen = FeatureGenerator()
train_fpv = [
gen.mean_chemisorbed_atoms,
gen.count_chemisorbed_fragment,
gen.count_ads_atoms,
gen.count_ads_bonds,
gen.mean_site,
gen.sum_site,
gen.mean_surf_ligands,
gen.term,
gen.bulk,
gen.strain,
gen.en_difference,
# gen.ads_av,
# gen.ads_sum,
]
matrix = gen.return_vec(images, train_fpv)
labels = gen.return_names(train_fpv)
print(np.shape(matrix), type(matrix))
if __name__ == '__main__':
for i, l in enumerate(labels):
print(i, l)
self.assertTrue(len(labels) == np.shape(matrix)[1])
def predict_catkit_demo(images):
"""Return a prediction of adsorption energies for structures generated with
CatKitDemo.
Parameters
----------
images : list
List of atoms objects representing adsorbate-surface structures.
model : str
Path and filename of Catlearn model pickle.
"""
model_ref = {'H': 'H2', 'O': 'H2O, H2', 'C': 'CH4, H2'}
# Make list of strings showing the references.
display_ref = []
for atoms in images:
try:
initial_state = [
model_ref[s] for s in ase.atoms.string2symbols(
atoms.info['key_value_pairs']['species'])
]
except KeyError:
return {}
display_ref.append('*, ' + ', '.join(list(np.unique(initial_state))))
images = autogen_info(images)
gen = FeatureGenerator(nprocs=1)
train_fpv = default_fingerprinters(gen, 'adsorbates')
train_fpv = [
gen.mean_chemisorbed_atoms, gen.count_chemisorbed_fragment,
gen.count_ads_atoms, gen.count_ads_bonds, gen.ads_av, gen.ads_sum,
gen.bulk, gen.term, gen.strain, gen.mean_surf_ligands, gen.mean_site,
gen.median_site, gen.max_site, gen.min_site, gen.sum_site,
gen.generalized_cn, gen.en_difference_ads, gen.en_difference_chemi,
gen.en_difference_active, gen.db_size, gen.delta_energy
]
matrix = gen.return_vec(images, train_fpv)
feature_index = np.load(clean_index_name)
clean_feature_mean = np.load(clean_mean)
impute = SimpleImputer(strategy='mean')
impute.statistics_ = clean_feature_mean
new_data = impute.transform(matrix[:, feature_index])
prediction = gp.predict(new_data,
get_validation_error=False,
get_training_error=False,
uncertainty=True)
output = {
'mean': list(prediction['prediction']),
'uncertainty': list(prediction['uncertainty']),
'references': display_ref
}
return output
def test_recontruction(self):
images = self.setup_atoms()
slabs = []
for atoms in images:
slab = atoms.copy()
slab.pop(-1)
slabs.append(slab)
images = autogen_info(images)
slabs = images_connectivity(slabs)
image_pairs = zip(images, slabs)
reconstructed = check_reconstructions(image_pairs)
self.assertTrue(len(reconstructed) == 0)
def test_tags(self):
"""Test the feature generation."""
images = self.setup_atoms()
images = autogen_info(images)
print(str(len(images)) + ' training examples.')
gen = FeatureGenerator(nprocs=1)
train_fpv = default_fingerprinters(gen, 'adsorbates')
matrix = gen.return_vec(images, train_fpv)
labels = gen.return_names(train_fpv)
print(np.shape(matrix), type(matrix))
if __name__ == '__main__':
for i, l in enumerate(labels):
print(i, l)
self.assertTrue(len(labels) == np.shape(matrix)[1])
def test_recontruction(self):
images = database_to_list('data/ads_example.db')
slabs = []
for atoms in images:
slab = atoms.copy()
slab.pop(-1)
slabs.append(slab)
images = autogen_info(images)
slabs = images_connectivity(slabs)
image_pairs = zip(images, slabs)
reconstructed = check_reconstructions(image_pairs)
for i in range(len(images)):
species = images[i].info['key_value_pairs']['species']
connectivity2ads_index(images[i], species)
self.assertTrue(len(reconstructed) == 0)
def test_db_ads(self):
"""Test the feature generation."""
images = database_to_list('data/ads_example.db')
images = autogen_info(images)
print(str(len(images)) + ' training examples.')
gen = FeatureGenerator(nprocs=1)
train_fpv = default_fingerprinters(gen, 'adsorbates')
train_fpv += [gen.db_size, gen.ctime, gen.dbid, gen.delta_energy]
matrix = gen.return_vec(images, train_fpv)
labels = gen.return_names(train_fpv)
print(np.shape(matrix), type(matrix))
if __name__ == '__main__':
for i, l in enumerate(labels):
print(i, l)
self.assertTrue(len(labels) == np.shape(matrix)[1])
def test_db_ads(self):
"""Test the feature generation."""
images = database_to_list('data/ads_example.db')
[atoms.set_tags(np.zeros(len(atoms))) for atoms in images]
images = autogen_info(images)
print(str(len(images)) + ' training examples.')
gen = FeatureGenerator(nprocs=1)
train_fpv = default_fingerprinters(gen, 'adsorbates')
# Test db specific functions.
train_fpv += [gen.db_size, gen.ctime, gen.dbid, gen.delta_energy]
# Old CatApp AxBy fingerprints.
train_fpv += [gen.catapp_AB]
matrix = gen.return_vec(images, train_fpv)
labels = gen.return_names(train_fpv)
print(np.shape(matrix), type(matrix))
if __name__ == '__main__':
for i, l in enumerate(labels):
print(i, l)
self.assertTrue(len(labels) == np.shape(matrix)[1])
def test_constrained_ads(self):
"""Test the feature generation."""
images = self.setup_atoms()
for atoms in images:
c_atoms = [
a.index for a in atoms if a.z < atoms.cell[2, 2] / 2. + 0.1
]
atoms.set_constraint(FixAtoms(c_atoms))
images = autogen_info(images)
print(str(len(images)) + ' training examples.')
gen = FeatureGenerator(nprocs=1)
train_fpv = default_fingerprinters(gen, 'adsorbates')
matrix = gen.return_vec(images, train_fpv)
labels = gen.return_names(train_fpv)
print(np.shape(matrix), type(matrix))
if __name__ == '__main__':
for i, l in enumerate(labels):
print(i, l)
self.assertTrue(len(labels) == np.shape(matrix)[1])