def toASE(molecule):
"""Convert a PLAMS |Molecule| to an ASE molecule (``ase.Atoms`` instance). Translate coordinates, atomic numbers, and lattice vectors (if present). The order of atoms is preserved."""
aseMol = aseAtoms()
#iterate over PLAMS atoms
for atom in molecule:
#check if coords only consists of floats or ints
if not all(isinstance(x, (int,float)) for x in atom.coords):
raise ValueError("Non-Number in Atomic Coordinates, not compatible with ASE")
#append atom to aseMol
aseMol.append(aseAtom(atom.atnum, atom.coords))
#get lattice info if any
lattice = npz((3,3))
pbc = [False,False,False]
for i,vec in enumerate(molecule.lattice):
#check if lattice only consists of floats or ints
if not all(isinstance(x, (int,float)) for x in vec):
raise ValueError("Non-Number in Lattice Vectors, not compatible with ASE")
pbc[i] = True
lattice[i] = npa(vec)
#save lattice info to aseMol
if any(pbc):
aseMol.set_pbc(pbc)
aseMol.set_cell(lattice)
return aseMol
def get_vocabulary(self, docs, nWords):
from numpy import zeros as npz
print("===========================")
print("CORPUS VOCABULARY DISTRIBUTION")
print("===========================")
message = "Words\t\tCount"
words = self.vectorizer.get_feature_names()
total_counts = npz(len(words))
for t in self.vector:
total_counts += t.toarray()[0]
count_dict = zip(words, total_counts)
count_dict = sorted(count_dict, key=lambda x: x[1],
reverse=True)[0:nWords]
print_list(count_dict, message)
print("\n")
return self.vectorizer.vocabulary_
def toASE(molecule):
"""
Converts a PLAMS molecule to an ASE molecule. The following attributes are converted, conserving the order of atoms:
-Coordinates
-Atomic Number (Symbol is derived automaticaly)
-Periodicity and Cell Vectors
"""
aseMol = aseAtoms()
#iterate over PLAMS atoms
for atom in molecule:
#check if coords only consists of floats or ints
if not all(isinstance(x, (int, float)) for x in atom.coords):
raise ValueError(
"Non-Number in Atomic Coordinates, not compatible with ASE")
#append atom to aseMol
aseMol.append(aseAtom(atom.atnum, atom.coords))
#get lattice info if any
lattice = npz((3, 3))
pbc = [False, False, False]
for i, vec in enumerate(molecule.lattice):
#check if lattice only consists of floats or ints
if not all(isinstance(x, (int, float)) for x in vec):
raise ValueError(
"Non-Number in Lattice Vectors, not compatible with ASE")
pbc[i] = True
lattice[i] = npa(vec)
#save lattice info to aseMol
if any(pbc):
aseMol.set_pbc(pbc)
aseMol.set_cell(lattice)
return aseMol