def cluster(S, tol=1.1, seed_index=0, write_poscar_from_cluster=False):
# S = Structure object
# tol = tolerance bonding
S = SpacegroupAnalyzer(S, 0.1).get_conventional_standard_structure()
if len(S) < 20: S.make_supercell(2)
Distance_matrix = S.distance_matrix
#np.fill_diagonal(Distance_matrix,100)
radii = [Elem_radius[site.species_string] for site in S.sites]
radiiT = np.array(radii)[np.newaxis].T #transpose of radii list
radii_matrix = radii + radiiT * tol
temp = Distance_matrix - radii_matrix
binary_matrix = (temp < 0).astype(int)
original = list(range(len(S)))
final = []
difference = []
counter = 0
while (len(original) != len(final)):
seed = set((np.where(binary_matrix[seed_index] == 1))[0])
cluster = seed
NEW = seed
check = True
while check:
Ss = set()
for n in NEW:
Ss.update(set(np.where(binary_matrix[n] == 1)[0]))
#print n,set(np.where( binary_matrix[n]==1 )[0])
if Ss.issubset(cluster):
check = False
else:
NEW = Ss - cluster
cluster.update(Ss)
L = []
cl = list(cluster)
sites = [S[i] for i in cl]
S.from_sites(sites).to('POSCAR', 'POSCAR{}'.format(str(counter)))
counter += 1
final = set(final)
final.update(cluster)
final = list(final)
difference = list(set(original) - set(final))
if (len(difference) > 0):
seed_index = difference[0]
def get_structure_type(structure,
tol=0.1,
seed_index=0,
write_poscar_from_cluster=False):
"""
This is a topology-scaling algorithm used to describe the
periodicity of bonded clusters in a bulk structure.
Args:
structure (structure): Pymatgen structure object to classify.
tol (float): Additional percent of atomic radii to allow
for overlap, thereby defining bonds
(0.1 = +10%, -0.1 = -10%)
seed_index (int): Atom number to start the cluster.
write_poscar_from_cluster (bool): Set to True to write a
POSCAR file from the sites in the cluster.
Returns:
string. "molecular" (0D), "chain" (1D), "layered" (2D), or
"conventional" (3D). Also includes " heterogeneous"
if the cluster's composition is not equal to that
of the overal structure.
"""
# Get conventional structure to orthogonalize the lattice as
# much as possible. A tolerance of 0.1 Angst. was suggested by
# pymatgen developers.
s = SpacegroupAnalyzer(structure,
0.1).get_conventional_standard_structure()
heterogeneous = False
noble_gases = ["He", "Ne", "Ar", "Kr", "Xe", "Rn"]
if len([e for e in structure.composition if e.symbol in noble_gases]) != 0:
type = "noble gas"
else:
# make 2x2x2 supercell to ensure sufficient number of atoms
# for cluster building.
s.make_supercell(2)
# Distance matrix (rowA, columnB) shows distance between
# atoms A and B, taking PBCs into account.
distance_matrix = s.distance_matrix
# Fill diagonal with a large number, so the code knows that
# each atom is not bonded to itself.
np.fill_diagonal(distance_matrix, 100)
# Rows (`radii`) and columns (`radiiT`) of radii.
radii = [ELEMENT_RADII[site.species_string] for site in s.sites]
radiiT = np.array(radii)[np.newaxis].T
radii_matrix = radii + radiiT * (1 + tol)
# elements of temp that have value less than 0 are bonded.
temp = distance_matrix - radii_matrix
# True (1) is placed where temp < 0, and False (0) where
# it is not.
binary_matrix = (temp < 0).astype(int)
# list of atoms bonded to the seed atom of a cluster
seed = set((np.where(binary_matrix[seed_index] == 1))[0])
cluster = seed
NEW = seed
while True:
temp_set = set()
for n in NEW:
# temp_set will have all atoms, without duplicates,
# that are connected to all atoms in NEW.
temp_set.update(set(np.where(binary_matrix[n] == 1)[0]))
if temp_set.issubset(cluster):
# if temp_set has no new atoms, the search is done.
break
else:
NEW = temp_set - cluster # List of newly discovered atoms
cluster.update(temp_set) # cluster is updated with new atoms
if len(cluster) == 0: # i.e. the cluster is a single atom.
cluster = [seed_index] # Make sure it's not empty to write POSCAR.
type = "molecular"
elif len(cluster) == len(s.sites): # i.e. all atoms are bonded.
type = "conventional"
else:
cmp = Composition.from_dict(
Counter([s[l].specie.name for l in list(cluster)]))
if cmp.reduced_formula != s.composition.reduced_formula:
# i.e. the cluster does not have the same composition
# as the overall crystal; therefore there are other
# clusters of varying composition.
heterogeneous = True
old_cluster_size = len(cluster)
# Increase structure to determine whether it is
# layered or molecular, then perform the same kind
# of cluster search as before.
s.make_supercell(2)
distance_matrix = s.distance_matrix
np.fill_diagonal(distance_matrix, 100)
radii = [ELEMENT_RADII[site.species_string] for site in s.sites]
radiiT = np.array(radii)[np.newaxis].T
radii_matrix = radii + radiiT * (1 + tol)
temp = distance_matrix - radii_matrix
binary_matrix = (temp < 0).astype(int)
seed = set((np.where(binary_matrix[seed_index] == 1))[0])
cluster = seed
NEW = seed
check = True
while check:
temp_set = set()
for n in NEW:
temp_set.update(set(np.where(binary_matrix[n] == 1)[0]))
if temp_set.issubset(cluster):
check = False
else:
NEW = temp_set - cluster
cluster.update(temp_set)
if len(cluster) != 4 * old_cluster_size:
type = "molecular"
else:
type = "layered"
if heterogeneous:
type += " heterogeneous"
cluster_sites = [s.sites[n] for n in cluster]
if write_poscar_from_cluster:
s.from_sites(cluster_sites).get_primitive_structure().to(
"POSCAR", "POSCAR")
return type
def get_structure_type(structure, tol=0.1, seed_index=0,
write_poscar_from_cluster=False):
"""
This is a topology-scaling algorithm used to describe the
periodicity of bonded clusters in a bulk structure.
Args:
structure (structure): Pymatgen structure object to classify.
tol (float): Additional percent of atomic radii to allow
for overlap, thereby defining bonds
(0.1 = +10%, -0.1 = -10%)
seed_index (int): Atom number to start the cluster.
write_poscar_from_cluster (bool): Set to True to write a
POSCAR file from the sites in the cluster.
Returns:
string. "molecular" (0D), "chain" (1D), "layered" (2D), or
"conventional" (3D). Also includes " heterogeneous"
if the cluster's composition is not equal to that
of the overal structure.
"""
# Get conventional structure to orthogonalize the lattice as
# much as possible. A tolerance of 0.1 Angst. was suggested by
# pymatgen developers.
s = SpacegroupAnalyzer(structure, 0.1).get_conventional_standard_structure()
heterogeneous = False
noble_gases = ["He", "Ne", "Ar", "Kr", "Xe", "Rn"]
if len([e for e in structure.composition if e.symbol in noble_gases]) != 0:
type = "noble gas"
else:
# make 2x2x2 supercell to ensure sufficient number of atoms
# for cluster building.
s.make_supercell(2)
# Distance matrix (rowA, columnB) shows distance between
# atoms A and B, taking PBCs into account.
distance_matrix = s.distance_matrix
# Fill diagonal with a large number, so the code knows that
# each atom is not bonded to itself.
np.fill_diagonal(distance_matrix, 100)
# Rows (`radii`) and columns (`radiiT`) of radii.
radii = [ELEMENT_RADII[site.species_string] for site in s.sites]
radiiT = np.array(radii)[np.newaxis].T
radii_matrix = radii + radiiT*(1+tol)
# elements of temp that have value less than 0 are bonded.
temp = distance_matrix - radii_matrix
# True (1) is placed where temp < 0, and False (0) where
# it is not.
binary_matrix = (temp < 0).astype(int)
# list of atoms bonded to the seed atom of a cluster
seed = set((np.where(binary_matrix[seed_index]==1))[0])
cluster = seed
NEW = seed
while True:
temp_set = set()
for n in NEW:
# temp_set will have all atoms, without duplicates,
# that are connected to all atoms in NEW.
temp_set.update(set(np.where(binary_matrix[n]==1)[0]))
if temp_set.issubset(cluster):
# if temp_set has no new atoms, the search is done.
break
else:
NEW = temp_set - cluster # List of newly discovered atoms
cluster.update(temp_set) # cluster is updated with new atoms
if len(cluster) == 0: # i.e. the cluster is a single atom.
cluster = [seed_index] # Make sure it's not empty to write POSCAR.
type = "molecular"
elif len(cluster) == len(s.sites): # i.e. all atoms are bonded.
type = "conventional"
else:
cmp = Composition.from_dict(Counter([s[l].specie.name for l in
list(cluster)]))
if cmp.reduced_formula != s.composition.reduced_formula:
# i.e. the cluster does not have the same composition
# as the overall crystal; therefore there are other
# clusters of varying composition.
heterogeneous = True
old_cluster_size = len(cluster)
# Increase structure to determine whether it is
# layered or molecular, then perform the same kind
# of cluster search as before.
s.make_supercell(2)
distance_matrix = s.distance_matrix
np.fill_diagonal(distance_matrix,100)
radii = [ELEMENT_RADII[site.species_string] for site in s.sites]
radiiT = np.array(radii)[np.newaxis].T
radii_matrix = radii + radiiT*(1+tol)
temp = distance_matrix-radii_matrix
binary_matrix = (temp < 0).astype(int)
seed = set((np.where(binary_matrix[seed_index]==1))[0])
cluster = seed
NEW = seed
check = True
while check:
temp_set = set()
for n in NEW:
temp_set.update(set(np.where(binary_matrix[n]==1)[0]))
if temp_set.issubset(cluster):
check = False
else:
NEW = temp_set - cluster
cluster.update(temp_set)
if len(cluster) != 4 * old_cluster_size:
type = "molecular"
else:
type = "layered"
if heterogeneous:
type += " heterogeneous"
cluster_sites = [s.sites[n] for n in cluster]
if write_poscar_from_cluster:
s.from_sites(cluster_sites).get_primitive_structure().to("POSCAR",
"POSCAR")
return type
