def _get_case_data_1() -> CaseData:
topology_graph = stk.polymer.Linear(
building_blocks=(stk.BuildingBlock('BrCCBr', [stk.BromoFactory()]), ),
repeating_unit='A',
num_repeating_units=2,
)
return CaseData(
fitness_normalizer=stk.Sum(filter=lambda population, record: record.
get_fitness_value() is not None,
),
population=(
stk.MoleculeRecord(
topology_graph=topology_graph, ).with_fitness_value(
(1, -5, 5)),
stk.MoleculeRecord(
topology_graph=topology_graph, ).with_fitness_value(
(3, -10, 2)),
stk.MoleculeRecord(
topology_graph=topology_graph, ).with_fitness_value(
(2, 20, 1)),
stk.MoleculeRecord(topology_graph),
),
normalized=(
stk.MoleculeRecord(
topology_graph=topology_graph, ).with_fitness_value(1),
stk.MoleculeRecord(
topology_graph=topology_graph, ).with_fitness_value(-5),
stk.MoleculeRecord(
topology_graph=topology_graph, ).with_fitness_value(23),
stk.MoleculeRecord(topology_graph),
),
)
def _get_case_data_1() -> CaseData:
topology_graph = stk.polymer.Linear(
building_blocks=(stk.BuildingBlock('BrCCBr', [stk.BromoFactory()]), ),
repeating_unit='A',
num_repeating_units=2,
)
return CaseData(
fitness_normalizer=stk.NormalizerSequence(fitness_normalizers=(
stk.Multiply(
coefficient=(1, 2, 4),
filter=lambda population, record: record.get_fitness_value() is
not None,
),
stk.Sum(filter=lambda population, record: record.get_fitness_value(
) is not None,
),
), ),
population=(
stk.MoleculeRecord(
topology_graph=topology_graph, ).with_fitness_value(
(4, 10, 1)),
stk.MoleculeRecord(
topology_graph=topology_graph, ).with_fitness_value(
(9, 20, 2)),
stk.MoleculeRecord(
topology_graph=topology_graph, ).with_fitness_value(
(16, 30, 4)),
stk.MoleculeRecord(topology_graph),
),
normalized=(
stk.MoleculeRecord(
topology_graph=topology_graph, ).with_fitness_value(28),
stk.MoleculeRecord(
topology_graph=topology_graph, ).with_fitness_value(57),
stk.MoleculeRecord(
topology_graph=topology_graph, ).with_fitness_value(92),
stk.MoleculeRecord(topology_graph),
),
)
elif isinstance(f, list):
return None not in population.get_fitness_values()[mol]
else:
return False
# Minimize synthetic accessibility and asymmetry.
# Maximise pore volume and window size.
fitness_normalizer = stk.TryCatch(
stk.Sequence(
save_fitness,
stk.Power([1, 1, -1, -1], filter=valid_fitness),
stk.DivideByMean(filter=valid_fitness),
stk.Multiply([5, 1, 10, 10], filter=valid_fitness),
stk.Sum(filter=valid_fitness),
# Replace all fitness values that are lists or None with
# a small value.
stk.ReplaceFitness(replacement_fn=lambda population: 1e-8,
filter=lambda p, m: isinstance(
p.get_fitness_values()[m],
(list, type(None)),
)),
),
stk.ReplaceFitness(replacement_fn=lambda population: 1e-8, ))
# #####################################################################
# Exit condition.
# #####################################################################
terminator = stk.NumGenerations(50)
def num_atoms(mol):
return len(mol.atoms)
fitness_calculator = stk.PropertyVector(num_atoms)
# #####################################################################
# Fitness normalizer.
# #####################################################################
# The PropertyVector fitness calculator will set the fitness as
# [n_atoms] use the Sum() fitness normalizer to convert the fitness to
# just n_atoms^0.5. The sqrt is because we use the Power normalizer.
fitness_normalizer = stk.NormalizerSequence(stk.Power(0.5), stk.Sum())
# #####################################################################
# Exit condition.
# #####################################################################
terminator = stk.NumGenerations(25)
# #####################################################################
# Make plotters.
# #####################################################################
plotters = [
stk.ProgressPlotter(
filename='fitness_plot',
property_fn=lambda mol: mol.fitness,
building_blocks=(stk.BuildingBlock('BrCCBr', [stk.BromoFactory()]), ),
repeating_unit='A',
num_repeating_units=2,
)
@pytest.fixture(
params=(CaseData(
fitness_normalizer=stk.NormalizerSequence(fitness_normalizers=(
stk.Multiply(
coefficient=(1, 2, 4),
filter=lambda population, record: record.get_fitness_value() is
not None,
),
stk.Sum(filter=lambda population, record: record.get_fitness_value(
) is not None,
),
), ),
population=(
stk.MoleculeRecord(
topology_graph=topology_graph, ).with_fitness_value(
(4, 10, 1)),
stk.MoleculeRecord(
topology_graph=topology_graph, ).with_fitness_value(
(9, 20, 2)),
stk.MoleculeRecord(
topology_graph=topology_graph, ).with_fitness_value(
(16, 30, 4)),
stk.MoleculeRecord(topology_graph),
),
normalized=(
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--mongodb_uri',
help='The MongoDB URI for the database to connect to.',
default='mongodb://localhost:27017/')
args = parser.parse_args()
logging.basicConfig(level=logging.INFO)
# Use a random seed to get reproducible results.
random_seed = 4
generator = np.random.RandomState(random_seed)
logger.info('Making building blocks.')
# Load the building block databases.
fluoros = tuple(
get_building_blocks(
path=pathlib.Path(__file__).parent / 'fluoros.txt',
functional_group_factory=stk.FluoroFactory(),
))
bromos = tuple(
get_building_blocks(
path=pathlib.Path(__file__).parent / 'bromos.txt',
functional_group_factory=stk.BromoFactory(),
))
initial_population = tuple(get_initial_population(fluoros, bromos))
# Write the initial population.
for i, record in enumerate(initial_population):
write(record.get_molecule(), f'initial_{i}.mol')
client = pymongo.MongoClient(args.mongodb_uri)
db = stk.ConstructedMoleculeMongoDb(client)
fitness_db = stk.ValueMongoDb(client, 'fitness_values')
# Plot selections.
generation_selector = stk.Best(
num_batches=25,
duplicate_molecules=False,
)
stk.SelectionPlotter('generation_selection', generation_selector)
mutation_selector = stk.Roulette(
num_batches=5,
random_seed=generator.randint(0, 1000),
)
stk.SelectionPlotter('mutation_selection', mutation_selector)
crossover_selector = stk.Roulette(
num_batches=3,
batch_size=2,
random_seed=generator.randint(0, 1000),
)
stk.SelectionPlotter('crossover_selection', crossover_selector)
fitness_calculator = stk.PropertyVector(
property_functions=(
get_num_rotatable_bonds,
get_complexity,
get_num_bad_rings,
),
input_database=fitness_db,
output_database=fitness_db,
)
fitness_normalizer = stk.NormalizerSequence(
fitness_normalizers=(
# Prevent division by 0 error in DivideByMean, by ensuring
# a value of each property to be at least 1.
stk.Add((1, 1, 1)),
stk.DivideByMean(),
# Obviously, because all coefficients are equal, the
# Multiply normalizer does not need to be here. However,
# it's here to show that you can easily change the relative
# importance of each component of the fitness value, by
# changing the values of the coefficients.
stk.Multiply((1, 1, 1)),
stk.Sum(),
stk.Power(-1),
), )
ea = stk.EvolutionaryAlgorithm(
num_processes=1,
initial_population=initial_population,
fitness_calculator=fitness_calculator,
mutator=stk.RandomMutator(
mutators=(
stk.RandomBuildingBlock(
building_blocks=fluoros,
is_replaceable=is_fluoro,
random_seed=generator.randint(0, 1000),
),
stk.SimilarBuildingBlock(
building_blocks=fluoros,
is_replaceable=is_fluoro,
random_seed=generator.randint(0, 1000),
),
stk.RandomBuildingBlock(
building_blocks=bromos,
is_replaceable=is_bromo,
random_seed=generator.randint(0, 1000),
),
stk.SimilarBuildingBlock(
building_blocks=bromos,
is_replaceable=is_bromo,
random_seed=generator.randint(0, 1000),
),
),
random_seed=generator.randint(0, 1000),
),
crosser=stk.GeneticRecombination(get_gene=get_functional_group_type, ),
generation_selector=generation_selector,
mutation_selector=mutation_selector,
crossover_selector=crossover_selector,
fitness_normalizer=fitness_normalizer,
)
logger.info('Starting EA.')
generations = []
for generation in ea.get_generations(50):
for record in generation.get_molecule_records():
db.put(record.get_molecule())
generations.append(generation)
# Write the final population.
for i, record in enumerate(generation.get_molecule_records()):
write(record.get_molecule(), f'final_{i}.mol')
logger.info('Making fitness plot.')
# Normalize the fitness values across the entire EA before
# plotting the fitness values.
generations = tuple(
normalize_generations(
fitness_calculator=fitness_calculator,
fitness_normalizer=fitness_normalizer,
generations=generations,
))
fitness_progress = stk.ProgressPlotter(
generations=generations,
get_property=lambda record: record.get_fitness_value(),
y_label='Fitness Value',
)
fitness_progress.write('fitness_progress.png')
fitness_progress.get_plot_data().to_csv('fitness_progress.csv')
logger.info('Making rotatable bonds plot.')
rotatable_bonds_progress = stk.ProgressPlotter(
generations=generations,
get_property=lambda record: get_num_rotatable_bonds(record.
get_molecule()),
y_label='Number of Rotatable Bonds',
)
rotatable_bonds_progress.write('rotatable_bonds_progress.png')
