def centre_of_mass(symbols, coordinates):
"""
Calculates the centre of mass (COM) for a set of atomic positions, based on:
COM_x = m1x1 + m2x2 + ... + mnxn / m1 + m2 + ... + mn
COM_y = m1y1 + m2y2 + ... + mnyn / m1 + m2 + ... + mn
COM_z = m1z1 + m2z2 + ... + mnzn / m1 + m2 + ... + mn
Parameters
----------
symbols: List of strings
List of elemental symbols
coordinates: Nx3 array of floats
Array of x,y,z coordinates
Returns
----------
COM: np.array
Array of x,y,z component of COM
"""
if len(symbols) != len(coordinates):
exit("Inputs not of the same dimension!")
masses = np.array([elements.element(i).mass for i in symbols])
mass_sum = np.sum(masses)
x_coords = coordinates[:, 0]
y_coords = coordinates[:, 1]
z_coords = coordinates[:, 2]
x_numerator = np.sum(np.dot(masses, x_coords))
y_numerator = np.sum(np.dot(masses, y_coords))
z_numerator = np.sum(np.dot(masses, z_coords))
COM_x = x_numerator / mass_sum
COM_y = y_numerator / mass_sum
COM_z = z_numerator / mass_sum
return np.array([COM_x, COM_y, COM_z])
def read_xyz(g09_file):
"""
Opens a g09 log file and returns the first geometry in Input orientation.
Iterators are used so that the file is not all loaded into memory, which
can be expensive.
The function searches for the following text pattern in the log file:
> Input orientation:
> ---------------------------------------------------------------------
> Center Atomic Atomic Coordinates (Angstroms)
> Number Number Type X Y Z
> ---------------------------------------------------------------------
And will save the coordinates and the atomic symbols succeeding it
Parameters
----------
g09_file: Path to g09 log file
File path
Returns
-------
coordinates: List of lists
Outer list is whole xyz file, each inner list is a line of the file containing
the symbol and x,y,z coordinates
"""
with open(g09_file) as f:
# Get the number of atoms so we can iterate without loading the file into memory
for line in f:
# Ensures line is not blank
if line.strip():
if line.split()[0] == "NAtoms=":
natoms = (int(line.split()[3]))
break
# Will hold the coordinates and symbols
coordinates = []
# Reset the iterator to the top of the file
f.seek(0)
for line in f:
if line.strip():
if "Input orientation:" in line:
for i in range(5):
# Skip 5 lines to start of coordinates
line = next(f)
for i in range(natoms):
linesplit = line.split()
symb = str(elements.element(int(linesplit[1])).symbol)
x = float(linesplit[3])
y = float(linesplit[4])
z = float(linesplit[5])
coordinates.append([symb, x, y, z])
line = next(f)
break
return coordinates
def read_NTO(g09_file, natoms):
"""
Reads a G09 logfile and returns the atomic centred Natural Transition Charges, obtained
via the G09 input line:
td=(nstates=1) nosymm Pop=NTO Density=(Transition=1)
Parameters
----------
g09_file: Path to g09 log file
File path
natoms: Integer
Number of atoms
Returns
-------
NTO: np.array
N array of NTO charges in order of atomic positions
"""
NTO = np.zeros(natoms)
with open(g09_file) as f:
# Get the number of atoms so we can iterate without loading the file into memory
for line in f:
# Ensures line is not blank
if line.strip():
if " Mulliken charges:" in line:
next(f)
line = next(f)
for i in range(natoms):
charge_line = line.split()
symbol = charge_line[1]
charge = float(charge_line[2])
# NTO charge is atomic number - charge
NTO[i] = elements.element(symbol).atomic - float(
charge)
line = next(f)
f.close()
return NTO