def regressionOfFailureRate(coords,
seed=None,
population_size=None,
generations=None):
"""
Pokusí se co nejlépe proložit body \a coords vyjadřující četnost chyb.
Snaží se při tom aby výsledek byl integrovatelný, ovšem integrovatelnost nezaručuje.
"""
if population_size is None:
population_size = 1000
if generations is None:
generations = 20
# Rozdělení x-ových a y-ových souřadnic pro GpLearn
X_train, y_train = zip(*(([x], y) for (x, y) in coords))
from gplearn.genetic import SymbolicRegressor
# Kolik náhodných čísel gplearn vygeneruje? Není omezeno. Buď se dosadí funkce, proměnná nebo se vygeneruje náhodné číslo z daného intervalu.
est_gp = SymbolicRegressor( # Estimator Genetic Programming
population_size=population_size,
generations=1,
tournament_size=20,
stopping_criteria=0.0,
const_range=(0.0, 5.0),
init_depth=(2, 6),
init_method='half and half',
function_set=('add', 'mul'),
metric='mean absolute error', #metric=sum_absolute_error
parsimony_coefficient=0.001,
p_crossover=0.9,
p_subtree_mutation=0.01,
p_hoist_mutation=0.01,
p_point_mutation=0.01,
p_point_replace=0.05,
max_samples=1.0,
warm_start=False,
n_jobs=-1,
verbose=VERBOSITY,
random_state=seed)
est_gp.fit(X_train, y_train)
for p in est_gp._programs[0]:
p.program[
0] = gplearn.functions.div2 # Všechny kořeny přepíšeme na dělení
for i in range(1, generations):
for p in est_gp._programs[i - 1]:
p.get_subtree = functools.partial(
get_subtree, p) # Všem potomkům zakážeme křížení z kořene
est_gp.set_params(generations=i + 1, warm_start=True)
est_gp.fit(X_train, y_train)
best_individual = est_gp._program
return est_gp, extractExprFromGplearn(best_individual.program)
def test_run_details():
"""Check the run_details_ attribute works as expected."""
est = SymbolicRegressor(generations=5, random_state=415)
est.fit(boston.data, boston.target)
# Check generations are indexed as expected without warm_start
assert_equal(est.run_details_['generation'], list(range(5)))
est.set_params(generations=10, warm_start=True)
est.fit(boston.data, boston.target)
# Check generations are indexed as expected with warm_start
assert_equal(est.run_details_['generation'], list(range(10)))
# Check all details have expected number of elements
for detail in est.run_details_:
assert_equal(len(est.run_details_[detail]), 10)
def test_low_memory_warm_start():
"""Check the warm_start functionality works as expected with low_memory."""
est = SymbolicRegressor(generations=20, random_state=415, low_memory=True)
est.fit(boston.data, boston.target)
cold_fitness = est._program.fitness_
cold_program = est._program.__str__()
# Check warm start with low memory gets the same result
est = SymbolicRegressor(generations=10, random_state=415, low_memory=True)
est.fit(boston.data, boston.target)
est.set_params(generations=20, warm_start=True)
est.fit(boston.data, boston.target)
warm_fitness = est._program.fitness_
warm_program = est._program.__str__()
assert_almost_equal(cold_fitness, warm_fitness)
assert_equal(cold_program, warm_program)
def test_warm_start():
"""Check the warm_start functionality works as expected."""
est = SymbolicRegressor(generations=20, random_state=415)
est.fit(boston.data, boston.target)
cold_fitness = est._program.fitness_
cold_program = est._program.__str__()
# Check fitting fewer generations raises error
est.set_params(generations=5, warm_start=True)
assert_raises(ValueError, est.fit, boston.data, boston.target)
# Check fitting the same number of generations warns
est.set_params(generations=20, warm_start=True)
assert_warns(UserWarning, est.fit, boston.data, boston.target)
# Check warm starts get the same result
est = SymbolicRegressor(generations=10, random_state=415)
est.fit(boston.data, boston.target)
est.set_params(generations=20, warm_start=True)
est.fit(boston.data, boston.target)
warm_fitness = est._program.fitness_
warm_program = est._program.__str__()
assert_almost_equal(cold_fitness, warm_fitness)
assert_equal(cold_program, warm_program)
metric='rmse',
max_samples=1.0,
low_memory=True,
n_jobs=4,
verbose=1,
random_state=seed,
p_hoist_mutation=0.0)
est_gp.set_params(
paretogp_lengths=(5, 250),
paretogp=False,
complexity='length',
selection='tournament',
elitism_size=1,
tournament_size=toursize,
parsimony_coefficient=length_coefficients, # = 0.0,
p_crossover=0.1, #p_crossover,
p_subtree_mutation=0.5, #p_mutations,
p_point_mutation=0.3, #p_mutations,
p_point_replace=0.05,
p_gs_crossover=0.05,
p_gs_mutation=0.05,
gs_mutationstep=0.001)
if pgp or est_gp.get_params()['paretogp']:
est_gp.set_params(parsimony_coefficient=0.0)
if len(sys.argv) > 3:
est_gp.set_params(**args1)
est = None
