def prepare_ga(dbfile='godb.db', splits={(2,): 1}, N=20):
blocks = [('Pd', 4), ('OH', 8)] # the building blocks
volume = 50. * 4 # volume in angstrom^3
l = [list(Atoms(block).numbers)*count for block, count in blocks]
stoichiometry = [item for sublist in l for item in sublist]
atom_numbers = list(set(stoichiometry))
blmin = closest_distances_generator(atom_numbers=atom_numbers,
ratio_of_covalent_radii=0.6)
blmin[(1, 8)] = blmin[(8, 1)] = 2.0
cellbounds = CellBounds(bounds={'phi': [0.2 * 180., 0.8 * 180.],
'chi': [0.2 * 180., 0.8 * 180.],
'psi': [0.2 *180., 0.8 * 180.],
'a': [2, 8], 'b': [2, 8], 'c': [2, 8]})
# create the starting population
sg = StartGenerator(blocks, blmin, volume, cellbounds=cellbounds,
splits=splits)
# create the database to store information in
da = PrepareDB(db_file_name=dbfile, stoichiometry=stoichiometry)
for i in range(N):
a = sg.get_new_candidate()
a.set_initial_magnetic_moments(magmoms=None)
niggli_reduce(a)
da.add_unrelaxed_candidate(a)
return
def do_short_relax(atoms, index=None, vc_relax=False, precon=True,
maxsteps=20):
''' Performs a (usually short) local optimization.
atoms: an Atoms object
index: index to be used as suffix for the output files
vc_relax: whether to also optimize the cell vectors
(after having run several steps with fixed cell)
precon: whether to use the preconditioned optimizers
maxsteps: maximum number of ionic steps
'''
if vc_relax:
assert precon
t = time()
label = 'opt' if index is None else 'opt_' + str(index)
logfile = '%s.log' % label
trajfile = '%s.traj' % label
traj = Trajectory(trajfile, 'a', atoms)
nsteps = 0
maxsteps_no_vc = maxsteps / 2 if vc_relax else maxsteps
fmax = 2. if vc_relax else 0.1
try:
if precon:
dyn = PreconLBFGS_My(atoms, precon=Exp(A=3), variable_cell=False,
use_armijo=True, a_min=1e-2, logfile=logfile)
else:
dyn = BFGS(atoms, maxstep=0.4, logfile=logfile)
dyn.attach(traj)
dyn.run(fmax=fmax, steps=maxsteps_no_vc)
except RuntimeError:
nsteps += dyn.get_number_of_steps()
if precon:
dyn = PreconFIRE_My(atoms, precon=Exp(A=3), variable_cell=False,
use_armijo=False, logfile=logfile,
dt=0.1, maxmove=0.5, dtmax=1.0, finc=1.1)
else:
dyn = FIRE(atoms, logfile=logfile, dt=0.1, maxmove=0.5, dtmax=1.0,
finc=1.1)
dyn.attach(traj)
steps = maxsteps_no_vc - nsteps
dyn.run(fmax=fmax, steps=steps)
nsteps += dyn.get_number_of_steps()
if vc_relax:
L = atoms.get_volume() / 4. # largest cell vector length allowed
cellbounds = CellBounds(bounds={'phi':[20., 160.], 'a':[1.5, L],
'chi':[20., 160.], 'b':[1.5, L],
'psi':[20., 160.], 'c':[1.5, L]})
try:
dyn = PreconLBFGS_My(atoms, precon=Exp(A=3), variable_cell=True,
use_armijo=True, logfile=logfile,
cellbounds=cellbounds, a_min=1e-2)
dyn.e1 = None
try:
dyn._just_reset_hessian
except AttributeError:
dyn._just_reset_hessian = True
dyn.attach(traj)
steps = maxsteps - nsteps
dyn.run(fmax=0., smax=0., steps=steps)
except RuntimeError:
nsteps += dyn.get_number_of_steps()
dyn = PreconFIRE_My(atoms, precon=Exp(A=3), variable_cell=True,
use_armijo=False, logfile=logfile,
cellbounds=cellbounds,
dt=0.1, maxmove=0.5, dtmax=1.0, finc=1.1)
dyn.attach(traj)
steps = maxsteps - nsteps
dyn.run(fmax=0., steps=steps)
name = atoms.calc.name
print('%s relaxation took %.3f seconds' % (name, time()-t))
return atoms
stoichiometry = []
for block, count in blocks:
if type(block) == str:
stoichiometry += list(Atoms(block).numbers) * count
else:
stoichiometry += list(block.numbers) * count
atom_numbers = list(set(stoichiometry))
blmin = closest_distances_generator(atom_numbers=atom_numbers,
ratio_of_covalent_radii=1.3)
cellbounds = CellBounds(
bounds={
'phi': [30, 150],
'chi': [30, 150],
'psi': [30, 150],
'a': [3, 50],
'b': [3, 50],
'c': [3, 50]
})
sg = StartGenerator(blocks,
blmin,
volume,
cellbounds=cellbounds,
splits=splits)
# Generate 2 candidates
a1 = sg.get_new_candidate()
a1.info['confid'] = 1
a2 = sg.get_new_candidate()
def relax_one(t, kptdensity=3.5):
cellbounds = CellBounds(
bounds={
'phi': [0.1 * 180., 0.9 * 180.],
'chi': [0.1 * 180., 0.9 * 180.],
'psi': [0.1 * 180., 0.9 * 180.],
'a': [1.5, 20],
'b': [1.5, 20],
'c': [1.5, 20]
})
if not cellbounds.is_within_bounds(t.get_cell()):
print('Candidate outside cellbounds -- skipping')
finalize(t, energy=1e9, forces=None, stress=None)
return t
pos = t.get_positions()
numbers = list(set(t.get_atomic_numbers()))
blmin = closest_distances_generator(numbers, 0.5)
t = push_apart(t, blmin, variable_cell=True)
print('Starting relaxation', flush=True)
clock = time()
t.wrap()
calc = DftbPlusCalculator(t,
kpts=0.66 * kptdensity,
use_spline=True,
read_chg=True,
maximum_angular_momenta={'C': 1})
try:
t = relax_precon(t,
calc,
fmax=2e-1,
smax=1e-2,
variable_cell=True,
optimizer='LBFGS',
a_min=1e-4,
cellbounds=cellbounds,
logfile='opt_first.log',
trajfile='opt_first.traj')
except (IOError, TypeError, RuntimeError, UnboundLocalError) as err:
# SCC or geometry optimization convergence problem
print(err)
del t.constraints
t.wrap()
calc = DftbPlusCalculator(t,
kpts=kptdensity,
use_spline=True,
read_chg=True,
maximum_angular_momenta={'C': 1})
try:
t = relax_precon(t,
calc,
fmax=1e-1,
smax=5e-3,
variable_cell=True,
optimizer='LBFGS',
a_min=1e-4,
cellbounds=cellbounds,
logfile='opt.log',
trajfile='opt.traj')
except (IOError, TypeError, RuntimeError, UnboundLocalError) as err:
# SCC or geometry optimization convergence problem
print(err)
try:
t = read('opt.traj@-1')
energy = t.get_potential_energy()
forces = t.get_forces()
stress = t.get_stress()
except (FileNotFoundError, UnknownFileTypeError) as err:
print(err)
energy, forces, stress = (1e9, None, None)
finalize(t, energy=energy, forces=forces, stress=stress)
print('Relaxing took %.3f seconds.' % (time() - clock), flush=True)
os.system('mv opt_first.traj prev_first.traj')
os.system('mv opt_first.log prev_first.log')
os.system('mv opt.log prev.log')
os.system('mv opt.traj prev.traj')
penalize(t)
return t
def run_ga(n_to_test, kptdensity=3.5):
population_size = 20
da = DataConnection('godb.db')
atom_numbers_to_optimize = da.get_atom_numbers_to_optimize()
n_to_optimize = len(atom_numbers_to_optimize)
slab = da.get_slab()
all_atom_types = get_all_atom_types(slab, atom_numbers_to_optimize)
blmin = closest_distances_generator(all_atom_types, 0.05) # 0.5
# defining genetic operators:
mutation_probability = 0.75
pairing = CutAndSplicePairing(blmin,
p1=1.,
p2=0.,
minfrac=0.15,
use_tags=False)
cellbounds = CellBounds(
bounds={
'phi': [0.2 * 180., 0.8 * 180.],
'chi': [0.2 * 180., 0.8 * 180.],
'psi': [0.2 * 180., 0.8 * 180.]
})
strainmut = StrainMutation(blmin,
stddev=0.7,
cellbounds=cellbounds,
use_tags=False)
blmin_soft = closest_distances_generator(all_atom_types, 0.1)
softmut = SoftMutation(blmin_soft, bounds=[2., 5.], use_tags=False)
rattlemut = RattleMutation(blmin,
n_to_optimize,
rattle_prop=0.8,
rattle_strength=2.5,
use_tags=False)
mutations = OperationSelector([4., 4., 2], [softmut, strainmut, rattlemut])
if True:
# recalculate raw scores
structures = da.get_all_relaxed_candidates()
for atoms in structures:
atoms = singlepoint(atoms, kptdensity=kptdensity)
da.c.delete([atoms.info['relax_id']])
if 'data' not in atoms.info:
atoms.info['data'] = {}
da.add_relaxed_step(atoms)
print('Finished recalculating raw scores')
# relaxing the initial candidates:
while da.get_number_of_unrelaxed_candidates() > 0:
a = da.get_an_unrelaxed_candidate()
a.wrap()
a = relax_one(a, kptdensity=kptdensity)
da.add_relaxed_step(a)
# create the population
population = Population(data_connection=da,
population_size=population_size,
comparator=comparator,
logfile='log.txt')
current_pop = population.get_current_population()
strainmut.update_scaling_volume(current_pop, w_adapt=0.5, n_adapt=4)
pairing.update_scaling_volume(current_pop, w_adapt=0.5, n_adapt=4)
# Test n_to_test new candidates
ga_raw_scores = []
step = 0
for step in range(n_to_test):
print('Starting configuration number %d' % step, flush=True)
clock = time()
a3 = None
r = random()
if r > mutation_probability:
while a3 is None:
a1, a2 = population.get_two_candidates()
a3, desc = pairing.get_new_individual([a1, a2])
else:
while a3 is None:
a1 = population.get_one_candidate()
a3, desc = mutations.get_new_individual([a1])
dt = time() - clock
op = 'pairing' if r > mutation_probability else 'mutating'
print('Time for %s candidate(s): %.3f' % (op, dt), flush=True)
a3.wrap()
da.add_unrelaxed_candidate(a3, description=desc)
a3 = relax_one(a3, kptdensity=kptdensity)
da.add_relaxed_step(a3)
# Various updates:
population.update()
current_pop = population.get_current_population()
if step % 10 == 0:
strainmut.update_scaling_volume(current_pop,
w_adapt=0.5,
n_adapt=4)
pairing.update_scaling_volume(current_pop, w_adapt=0.5, n_adapt=4)
write('current_population.traj', current_pop)
# Print out information for easy analysis/plotting afterwards:
if r > mutation_probability:
print('Step %d %s %.3f %.3f %.3f' % (step, desc,\
get_raw_score(a1), get_raw_score(a2), get_raw_score(a3)))
else:
print('Step %d %s %.3f %.3f' % (step, desc,\
get_raw_score(a1), get_raw_score(a3)))
print('Step %d highest raw score in pop: %.3f' % \
(step, get_raw_score(current_pop[0])))
ga_raw_scores.append(get_raw_score(a3))
print('Step %d highest raw score generated by GA: %.3f' % \
(step, max(ga_raw_scores)))
emin = population.pop[0].get_potential_energy()
print('GA finished after step %d' % step)
print('Lowest energy = %8.3f eV' % emin, flush=True)
write('all_candidates.traj', da.get_all_relaxed_candidates())
write('current_population.traj', population.get_current_population())
stoichiometry = [
atomic_numbers[atom] for atom, count in blocks for _ in range(count)
]
# Generate a dictionary with the closest allowed interatomic distances
atom_numbers = list(set(stoichiometry))
blmin = closest_distances_generator(atom_numbers=atom_numbers,
ratio_of_covalent_radii=0.5)
# Specify reasonable bounds on the minimal and maximal
# cell vector lengths (in angstrom) and angles (in degrees)
cellbounds = CellBounds(
bounds={
'phi': [35, 145],
'chi': [35, 145],
'psi': [35, 145],
'a': [3, 50],
'b': [3, 50],
'c': [3, 50]
})
# Choose an (optional) 'cell splitting' scheme which basically
# controls the level of translational symmetry (within the unit
# cell) of the randomly generated structures. Here a 1:1 ratio
# of splitting factors 2 and 1 is used:
splits = {(2, ): 1, (1, ): 1}
# There will hence be a 50% probability that a candidate
# is constructed by repeating an randomly generated Ag12
# structure along a randomly chosen axis. In the other 50%
# of cases, no cell cell splitting will be applied.
def test_bulk_operators():
h2 = Atoms('H2', positions=[[0, 0, 0], [0, 0, 0.75]])
blocks = [('H', 4), ('H2O', 3), (h2, 2)] # the building blocks
volume = 40. * sum([x[1] for x in blocks]) # cell volume in angstrom^3
splits = {(2,): 1, (1,): 1} # cell splitting scheme
stoichiometry = []
for block, count in blocks:
if type(block) == str:
stoichiometry += list(Atoms(block).numbers) * count
else:
stoichiometry += list(block.numbers) * count
atom_numbers = list(set(stoichiometry))
blmin = closest_distances_generator(atom_numbers=atom_numbers,
ratio_of_covalent_radii=1.3)
cellbounds = CellBounds(bounds={'phi': [30, 150], 'chi': [30, 150],
'psi': [30, 150], 'a': [3, 50],
'b': [3, 50], 'c': [3, 50]})
sg = StartGenerator(blocks, blmin, volume, cellbounds=cellbounds,
splits=splits)
# Generate 2 candidates
a1 = sg.get_new_candidate()
a1.info['confid'] = 1
a2 = sg.get_new_candidate()
a2.info['confid'] = 2
# Define and test genetic operators
pairing = CutAndSplicePairing(blmin, p1=1., p2=0., minfrac=0.15,
cellbounds=cellbounds, use_tags=True)
a3, desc = pairing.get_new_individual([a1, a2])
cell = a3.get_cell()
assert cellbounds.is_within_bounds(cell)
assert not atoms_too_close(a3, blmin, use_tags=True)
n_top = len(a1)
strainmut = StrainMutation(blmin, stddev=0.7, cellbounds=cellbounds,
use_tags=True)
softmut = SoftMutation(blmin, bounds=[2., 5.], used_modes_file=None,
use_tags=True)
rotmut = RotationalMutation(blmin, fraction=0.3, min_angle=0.5 * np.pi)
rattlemut = RattleMutation(blmin, n_top, rattle_prop=0.3, rattle_strength=0.5,
use_tags=True, test_dist_to_slab=False)
rattlerotmut = RattleRotationalMutation(rattlemut, rotmut)
permut = PermutationMutation(n_top, probability=0.33, test_dist_to_slab=False,
use_tags=True, blmin=blmin)
combmut = CombinationMutation(rattlemut, rotmut, verbose=True)
mutations = [strainmut, softmut, rotmut,
rattlemut, rattlerotmut, permut, combmut]
for i, mut in enumerate(mutations):
a = [a1, a2][i % 2]
a3 = None
while a3 is None:
a3, desc = mut.get_new_individual([a])
cell = a3.get_cell()
assert cellbounds.is_within_bounds(cell)
assert np.all(a3.numbers == a.numbers)
assert not atoms_too_close(a3, blmin, use_tags=True)
modes_file = 'modes.txt'
softmut_with = SoftMutation(blmin, bounds=[2., 5.], use_tags=True,
used_modes_file=modes_file)
no_muts = 3
for _ in range(no_muts):
softmut_with.get_new_individual([a1])
softmut_with.read_used_modes(modes_file)
assert len(list(softmut_with.used_modes.values())[0]) == no_muts
os.remove(modes_file)
comparator = OFPComparator(recalculate=True)
gold = bulk('Au') * (2, 2, 2)
assert comparator.looks_like(gold, gold)
# This move should not exceed the default threshold
gc = gold.copy()
gc[0].x += .1
assert comparator.looks_like(gold, gc)
# An additional step will exceed the threshold
gc[0].x += .2
assert not comparator.looks_like(gold, gc)
def relax_one(t, kptdensity=3.5):
cellbounds = CellBounds(bounds={'phi': [0.1 * 180., 0.9 * 180.],
'chi': [0.1 * 180., 0.9 * 180.],
'psi': [0.1 * 180., 0.9 * 180.],
'a': [1.5, 20], 'b': [1.5, 20],
'c':[1.5, 20]})
if not cellbounds.is_within_bounds(t.get_cell()):
print('Candidate outside cellbounds -- skipping')
finalize(t, energy=1e9, forces=None, stress=None)
return t
tags = t.get_tags()
pos = t.get_positions()
pairs = []
for tag in list(set(tags)):
indices = list(np.where(tags == tag)[0])
if len(indices) == 2:
pairs.append(indices)
c = FixBondLengths(pairs)
t.set_constraint(c)
blmin = {(1, 1): 1.8, (1, 8): 0.9, (1, 46): 1.8, (8, 8): 2.0,
(8, 46): 1.5, (46, 46): 1.5}
t = push_apart(t, blmin, variable_cell=True)
del t.constraints
oh_bondlength = 0.97907
for (o_atom, h_atom) in pairs:
vec = t.get_distance(o_atom, h_atom, mic=True, vector=True)
pos[h_atom] = pos[o_atom] + vec * oh_bondlength / np.linalg.norm(vec)
t.set_positions(pos)
print('Starting relaxation', flush=True)
clock = time()
t.wrap()
calc = DftbPlusCalculator(t, kpts=0.66*kptdensity,
use_spline=True, read_chg=True,
maximum_angular_momenta={'Pd': 2, 'H': 0, 'O': 1})
try:
t = relax_precon(t, calc, fmax=2e-1, smax=1e-2, variable_cell=True,
optimizer='LBFGS', a_min=1e-4, cellbounds=cellbounds,
fix_bond_lengths_pairs=pairs, logfile='opt_first.log',
trajfile='opt_first.traj')
except (IOError, TypeError, RuntimeError, UnboundLocalError) as err:
# SCC or geometry optimization convergence problem
print(err)
if isinstance(t, Filter):
t = t.atoms
del t.constraints
t.wrap()
calc = DftbPlusCalculator(t, kpts=kptdensity,
use_spline=True, read_chg=True,
maximum_angular_momenta={'Pd': 2, 'H': 0, 'O': 1})
try:
t = relax_precon(t, calc, fmax=1e-1, smax=5e-3, variable_cell=True,
optimizer='LBFGS', a_min=1e-4, cellbounds=cellbounds,
fix_bond_lengths_pairs=pairs, logfile='opt.log',
trajfile='opt.traj')
except (IOError, TypeError, RuntimeError, UnboundLocalError) as err:
# SCC or geometry optimization convergence problem
print(err)
try:
t = read('opt.traj@-1')
energy = t.get_potential_energy()
forces = t.get_forces()
stress = t.get_stress()
except (FileNotFoundError, UnknownFileTypeError) as err:
print(err)
energy, forces, stress = (1e9, None, None)
if isinstance(t, Filter):
t = t.atoms
finalize(t, energy=energy, forces=forces, stress=stress)
print('Relaxing took %.3f seconds.' % (time() - clock), flush=True)
os.system('mv opt_first.traj prev_first.traj')
os.system('mv opt_first.log prev_first.log')
os.system('mv opt.log prev.log')
os.system('mv opt.traj prev.traj')
penalize(t)
return t
def relax_one(t, kptdensity=1.5):
cellbounds = CellBounds(
bounds={
'phi': [0.1 * 180., 0.9 * 180.],
'chi': [0.1 * 180., 0.9 * 180.],
'psi': [0.1 * 180., 0.9 * 180.],
'a': [1.5, 20],
'b': [1.5, 20],
'c': [1.5, 20]
})
if not cellbounds.is_within_bounds(t.get_cell()):
print('Candidate outside cellbounds -- skipping')
finalize(t, energy=1e9, forces=None, stress=None)
return t
pos = t.get_positions()
numbers = list(set(t.get_atomic_numbers()))
blmin = closest_distances_generator(numbers, 0.5)
t = push_apart(t, blmin, variable_cell=True)
print('Starting relaxation', flush=True)
clock = time()
t.wrap()
calc = DftbPlusCalc(t,
kpts=0.66 * kptdensity,
use_spline=True,
read_chg=True)
try:
t = relax_precon(t,
calc,
fmax=5e-1,
smax=5e-2,
variable_cell=True,
optimizer='LBFGS',
a_min=1e-4,
cellbounds=cellbounds,
logfile='opt_first.log',
trajfile='opt_first.traj')
except IOError as err:
# probably convergence problem
print(err.message)
except TypeError as err:
if 'Cannot cast array data' in err.message:
# Rare precon failure
print(err.message)
else:
raise
except RuntimeError as err:
print(err.message)
del t.constraints
t.wrap()
calc = DftbPlusCalc(t, kpts=kptdensity, use_spline=True, read_chg=True)
try:
t = relax_precon(t,
calc,
fmax=5e-1,
smax=5e-2,
variable_cell=True,
optimizer='LBFGS',
a_min=1e-4,
cellbounds=cellbounds,
logfile='opt.log',
trajfile='opt.traj')
except (IOError, TypeError, RuntimeError) as err:
# probably convergence problem
print(err.message)
if isinstance(err, TypeError):
if 'Cannot cast array data' not in err.message:
raise
elif isinstance(err, RuntimeError):
if 'dftb_my in . returned an error:' not in err.message:
raise
try:
t = read('opt.traj@-1')
energy = t.get_potential_energy()
forces = t.get_forces()
stress = t.get_stress()
except UnknownFileTypeError as err:
print(err.message)
energy, forces, stress = (1e9, None, None)
finalize(t, energy=energy, forces=forces, stress=stress)
print('Relaxing took %.3f seconds.' % (time() - clock), flush=True)
os.system('mv opt_first.traj prev_first.traj')
os.system('mv opt_first.log prev_first.log')
os.system('mv opt.log prev.log')
os.system('mv opt.traj prev.traj')
penalize(t)
return t
rcut=10.,
binwidth=0.05,
pbc=[True, True, True],
sigma=0.05,
nsigma=4,
recalculate=False)
# Define the cell and interatomic distance bounds
# that the candidates must obey
blmin = closest_distances_generator(atom_numbers_to_optimize, 0.5)
cellbounds = CellBounds(
bounds={
'phi': [20, 160],
'chi': [20, 160],
'psi': [20, 160],
'a': [2, 60],
'b': [2, 60],
'c': [2, 60]
})
# Define a pairing operator with 100% (0%) chance that the first
# (second) parent will be randomly translated, and with each parent
# contributing to at least 15% of the child's scaled coordinates
pairing = CutAndSplicePairing(blmin,
p1=1.,
p2=0.,
minfrac=0.15,
cellbounds=cellbounds,
use_tags=False)