def test_poorly_shaped_input_y_of_training_data():
y = np.zeros((5, 3, 3))
x = y.flatten()
with warnings.catch_warnings():
warnings.simplefilter("ignore")
with pytest.raises(ValueError):
_ = ExplicitTrainingData(x, y)
def test_reshaping_of_training_data():
one_dim_input = np.zeros(5)
with warnings.catch_warnings():
warnings.simplefilter("ignore")
training_data = ExplicitTrainingData(one_dim_input, one_dim_input)
assert training_data.x.ndim == 2
assert training_data.y.ndim == 2
def execute_generational_steps():
x = init_x_vals(-10, 10, 100)
y = equation_eval(x)
training_data = ExplicitTrainingData(x, y)
component_generator = ComponentGenerator(x.shape[1])
component_generator.add_operator(2)
component_generator.add_operator(3)
component_generator.add_operator(4)
crossover = AGraphCrossover(component_generator)
mutation = AGraphMutation(component_generator)
agraph_generator = AGraphGenerator(STACK_SIZE, component_generator)
fitness = ExplicitRegression(training_data=training_data)
local_opt_fitness = ContinuousLocalOptimization(fitness, algorithm='lm')
evaluator = Evaluation(local_opt_fitness)
ea = AgeFitnessEA(evaluator, agraph_generator, crossover,
mutation, 0.4, 0.4, POP_SIZE)
island = Island(ea, agraph_generator, POP_SIZE)
archipelago = SerialArchipelago(island)
opt_result = archipelago.evolve_until_convergence(max_generations=500,
fitness_threshold=1.0e-4)
if opt_result.success:
print(archipelago.get_best_individual().get_latex_string())
else:
print("Failed.")
def init_island():
np.random.seed(10)
x = init_x_vals(START, STOP, NUM_POINTS)
y = equation_eval(x)
training_data = ExplicitTrainingData(x, y)
component_generator = ComponentGenerator(
x.shape[1],
automatic_constant_optimization=False,
numerical_constant_range=10)
component_generator.add_operator("+")
component_generator.add_operator("-")
component_generator.add_operator("*")
crossover = AGraphCrossover(component_generator)
mutation = AGraphMutation(component_generator)
agraph_generator = AGraphGenerator(STACK_SIZE, component_generator)
fitness = ExplicitRegression(training_data=training_data)
evaluator = Evaluation(fitness)
ea = AgeFitnessEA(evaluator, agraph_generator, crossover, mutation,
MUTATION_PROBABILITY, CROSSOVER_PROBABILITY, POP_SIZE)
island = Island(ea, agraph_generator, POP_SIZE)
return island
def init_island():
np.random.seed(15)
x = init_x_vals(START, STOP, NUM_POINTS)
y = equation_eval(x)
training_data = ExplicitTrainingData(x, y)
component_generator = ComponentGenerator(x.shape[1])
component_generator.add_operator(2)
component_generator.add_operator(3)
component_generator.add_operator(4)
crossover = AGraphCrossover(component_generator)
mutation = AGraphMutation(component_generator)
agraph_generator = AGraphGenerator(STACK_SIZE, component_generator)
fitness = ExplicitRegression(training_data=training_data)
local_opt_fitness = ContinuousLocalOptimization(fitness, algorithm='lm')
evaluator = Evaluation(local_opt_fitness)
ea_algorithm = AgeFitnessEA(evaluator, agraph_generator, crossover,
mutation, MUTATION_PROBABILITY,
CROSSOVER_PROBABILITY, POP_SIZE)
island = Island(ea_algorithm, agraph_generator, POP_SIZE)
return island
def test_getting_subset_of_training_data(python):
data_input = np.arange(5).reshape((-1, 1))
training_data = ExplicitTrainingData(data_input, data_input) \
if python \
else bingocpp.ExplicitTrainingData(data_input, data_input)
subset_training_data = training_data[[0, 2, 3]]
expected_subset = np.array([[0], [2], [3]])
np.testing.assert_array_equal(subset_training_data.x, expected_subset)
np.testing.assert_array_equal(subset_training_data.y, expected_subset)
def execute_generational_steps():
communicator = MPI.COMM_WORLD
rank = MPI.COMM_WORLD.Get_rank()
data = pd.read_csv('./data/fp_2var_test9_py.csv').as_matrix()
x = data[:, 0:2]
y = data[:2]
if rank == 0:
x = init_x_vals(-10, 10, 100)
y = equation_eval(x)
x = MPI.COMM_WORLD.bcast(x, root=0)
y = MPI.COMM_WORLD.bcast(y, root=0)
training_data = ExplicitTrainingData(x, y)
component_generator = ComponentGenerator(x.shape[1])
component_generator.add_operator(2)
component_generator.add_operator(3)
component_generator.add_operator(4)
component_generator.add_operator(5)
component_generator.add_operator(6)
component_generator.add_operator(7)
component_generator.add_operator(10)
crossover = AGraphCrossover(component_generator)
mutation = AGraphMutation(component_generator)
agraph_generator = AGraphGenerator(STACK_SIZE, component_generator)
fitness = ExplicitRegression(training_data=training_data,
metric='root mean squared error')
local_opt_fitness = ContinuousLocalOptimization(fitness,
algorithm='L-BFGS-B')
evaluator = Evaluation(local_opt_fitness)
#ea = AgeFitnessEA(evaluator, agraph_generator, crossover,
# mutation, 0.4, 0.4, POP_SIZE)
ea = DeterministicCrowdingEA(evaluator, crossover, mutation, 0.4, 0.4)
island = Island(ea, agraph_generator, POP_SIZE)
archipelago = ParallelArchipelago(island)
opt_result = archipelago.evolve_until_convergence(
MAX_GENERATIONS,
fitness_threshold=FITNESS_THRESHOLD,
min_generations=MIN_GENERATIONS,
stagnation_generations=STAGNATION_LIMIT)
if opt_result.success:
if rank == 0:
print("best: ", archipelago.get_best_individual())
def explicit_regression_benchmark():
np.random.seed(15)
communicator = MPI.COMM_WORLD
rank = MPI.COMM_WORLD.Get_rank()
x = None
y = None
if rank == 0:
x = init_x_vals(-10, 10, 100)
y = equation_eval(x)
x = MPI.COMM_WORLD.bcast(x, root=0)
y = MPI.COMM_WORLD.bcast(y, root=0)
training_data = ExplicitTrainingData(x, y)
component_generator = ComponentGenerator(x.shape[1])
component_generator.add_operator(2)
component_generator.add_operator(3)
component_generator.add_operator(4)
crossover = AGraphCrossover(component_generator)
mutation = AGraphMutation(component_generator)
agraph_generator = AGraphGenerator(STACK_SIZE, component_generator)
fitness = ExplicitRegression(training_data=training_data)
local_opt_fitness = ContinuousLocalOptimization(fitness, algorithm='lm')
evaluator = Evaluation(local_opt_fitness)
ea = AgeFitnessEA(evaluator, agraph_generator, crossover, mutation, 0.4,
0.4, POP_SIZE)
island = Island(ea, agraph_generator, POP_SIZE)
archipelago = ParallelArchipelago(island)
opt_result = archipelago.evolve_until_convergence(max_generations=500,
fitness_threshold=1.0e-4)
if rank == 0:
if opt_result.success:
print("print the best indv", archipelago.get_best_individual())
else:
print("Failed.")
def test_poorly_shaped_input_x_of_training_data():
x = np.zeros((5, 3, 3))
y = x.flatten()
with pytest.raises(ValueError):
_ = ExplicitTrainingData(x, y)
def test_correct_training_data_length(python, input_size):
data_input = np.arange(input_size).reshape((-1, 1))
training_data = ExplicitTrainingData(data_input, data_input)
assert len(training_data) == input_size
def explicit_regression():
training_data = ExplicitTrainingData(TEST_X_PARTIALS, TEST_Y_ZEROS)
return ExplicitRegression(training_data)
def execute_generational_steps():
communicator = MPI.COMM_WORLD
rank = MPI.COMM_WORLD.Get_rank()
x = None
y = None
if rank == 0:
df = pd.read_csv('data/combined_clean_data.csv')
df = df.dropna()
train, test = train_test_split(df, test_size=0.2, random_state=42)
columns = df.columns
x = train.loc[:, ~columns.str.contains('Damage')]
x = x.loc[:, x.columns != 'Time']
x = x.loc[:, x.columns != 'Machine'].values
y = train.loc[:, columns.str.contains('Damage')]
y = y.iloc[:, 0].values.reshape((-1, 1))
x = MPI.COMM_WORLD.bcast(x, root=0)
y = MPI.COMM_WORLD.bcast(y, root=0)
training_data = ExplicitTrainingData(x, y)
component_generator = ComponentGenerator(x.shape[1])
component_generator.add_operator(2) # +
component_generator.add_operator(3) # -
component_generator.add_operator(4) # *
component_generator.add_operator(5) # /
# component_generator.add_operator(6) # sin
# component_generator.add_operator(7) # cos
# component_generator.add_operator(8) # exponential
# component_generator.add_operator(10) # power
# component_generator.add_operator(12) # sqrt
crossover = AGraphCrossover(component_generator)
mutation = AGraphMutation(component_generator)
agraph_generator = AGraphGenerator(STACK_SIZE, component_generator)
fitness = ExplicitRegression(training_data=training_data,
metric='mean squared error')
local_opt_fitness = ContinuousLocalOptimization(fitness, algorithm='lm')
evaluator = Evaluation(local_opt_fitness)
ea = DeterministicCrowdingEA(evaluator, crossover, mutation,
CROSSOVER_PROBABILITY, MUTATION_PROBABILITY)
island = FitnessPredictorIsland(ea,
agraph_generator,
POP_SIZE,
predictor_size_ratio=0.2)
pareto_front = ParetoFront(secondary_key=lambda ag: ag.get_complexity(),
similarity_function=agraph_similarity)
archipelago = ParallelArchipelago(island, hall_of_fame=pareto_front)
optim_result = archipelago.evolve_until_convergence(
MAX_GENERATIONS,
FITNESS_THRESHOLD,
convergence_check_frequency=CHECK_FREQUENCY,
min_generations=MIN_GENERATIONS,
checkpoint_base_name='checkpoint',
num_checkpoints=2)
if optim_result.success:
if rank == 0:
print("best: ", archipelago.get_best_individual())
if rank == 0:
print(optim_result)
print("Generation: ", archipelago.generational_age)
print_pareto_front(pareto_front)
plot_pareto_front(pareto_front)