def fit(self, X=None, y=None, c=None, x_group=None, pset=None):
"""
If pset is None, one simple pset are generate with no dimension calculation, But just with x_group.\n
If need more self-definition, use one defined SymbolSet object to pset.\n
Examples:
pset = SymbolSet()\n
pset.add_features_and_constants(...)\n
pset.add_operations(...)\n
...\n
...SymbolLearning().fit(pset=pset)\n
Parameters
----------
X:np.ndarray
y:np.ndarray
c:list of float
x_group:list of list
Group of x.\n
See Also pset.add_features_and_constants
pset:SymbolSet
See Also SymbolSet
"""
if pset is None:
pset = SymbolSet()
pset.add_features_and_constants(X,
y,
c,
x_dim=1,
y_dim=1,
c_dim=1,
x_prob=None,
c_prob=None,
x_group=x_group,
feature_name=None)
pset.add_operations(power_categories=(2, 3, 0.5),
categories=("Add", "Mul", "Sub", "Div"))
self.loop = self.loop(pset, *self.args, **self.kwargs)
hall = self.loop.run()
self.best_one = hall.items[0]
try:
expr = general_expr(self.best_one.coef_expr, self.loop.cpset)
self.expr_type = "single"
except (RecursionError, RuntimeWarning):
expr = self.best_one.coef_expr
self.expr_type = "group"
self.expr = expr
self.y_dim = self.best_one.y_dim
self.fitness = self.best_one.fitness.values[0]
class MyTestbase(unittest.TestCase):
def setUp(self):
self.SymbolTree = SymbolTree
self.pset = SymbolSet()
from sklearn.datasets import load_boston
data = load_boston()
x = data["data"]
y = data["target"]
# No = Normalizer()
# y=y/max(y)
# x = No.fit_transform(x)
self.x = x
self.y = y
# self.pset.add_features(x, y, )
self.pset.add_features(x, y, x_group=[[1, 2], [4, 5]])
self.pset.add_constants([6, 3, 4],
c_dim=[dless, dless, dless],
c_prob=None)
self.pset.add_operations(power_categories=(2, 3, 0.5),
categories=("Add", "Mul", "Self", "Abs"),
self_categories=None)
from sklearn.metrics import r2_score, mean_squared_error
self.cp = CalculatePrecisionSet(self.pset,
scoring=[r2_score, mean_squared_error],
score_pen=[1, -1],
filter_warning=True)
def test_pset_passed_to_cpset_will_change(self):
cp = CalculatePrecisionSet(self.pset)
self.assertNotEqual(cp, self.cp)
def test_tree_gengrow_repr_and_str_different(self):
from numpy import random
random.seed(1)
sl = SymbolTree.genGrow(self.pset, 3, 4)
print(sl)
# self.assertNotEqual(repr(sl), str(sl))
def test_add_tree_back(self):
from numpy import random
random.seed(1)
sl = SymbolTree.genGrow(self.pset, 3, 4)
self.pset.add_tree_to_features(sl)
#
def test_barch_tree(self):
from numpy import random
random.seed(1)
for i in range(10):
sl = SymbolTree.genGrow(self.pset, 3, 4)
cpsl = self.cp.calculate_detail(sl)
self.assertIsNotNone(cpsl.y_dim)
self.assertIsNotNone(cpsl.expr)
self.assertIsNone(cpsl.p_name)
if cpsl.pre_y is not None:
self.assertIsInstance(cpsl.pre_y, numpy.ndarray)
self.assertEqual(cpsl.pre_y.shape, self.y.shape)
print(cpsl.coef_pre_y[:3])
print(cpsl.pre_y[:3])
print(cpsl.coef_score)
print(cpsl.coef_expr)
print(cpsl.pure_expr)
def test_depart_tree(self):
from numpy import random
random.seed(1)
for i in range(10):
sl = SymbolTree.genGrow(self.pset, 5, 6)
sl_departs = sl.depart()
for i in sl_departs:
cpsl = self.cp.calculate_simple(i)
self.assertIsNotNone(cpsl.y_dim)
self.assertIsNotNone(cpsl.expr)
self.assertIsNone(cpsl.p_name)
x_u = [kg] * 13
y_u = kg
c_u = [dless, dless, dless]
x, x_dim = Dim.convert_x(x, x_u, target_units=None, unit_system="SI")
y, y_dim = Dim.convert_xi(y, y_u)
c, c_dim = Dim.convert_x(c, c_u)
t = time.time()
# symbolset
pset0 = SymbolSet()
pset0.add_features(x,
y,
x_dim=x_dim,
y_dim=y_dim,
x_group=[[1, 2], [3, 4, 5]])
pset0.add_constants(c, c_dim=c_dim, c_prob=None)
pset0.add_operations(power_categories=(2, 3, 0.5),
categories=("Add", "Mul", "Sub", "Div", "exp"),
self_categories=None)
random.seed(0)
z = time.time()
sl = [SymbolTree.genGrow(pset0, 3, 4) for _ in range(100)]
a = time.time()
sl = [compile_context(sli, pset0.context, pset0.gro_ter_con) for sli in sl]
b = time.time()
print(b - a, a - z)
class MyTestgp(unittest.TestCase):
def setUp(self):
self.SymbolTree = SymbolTree
self.pset = SymbolSet()
from sklearn.datasets import load_boston
data = load_boston()
x = data["data"]
y = data["target"]
self.x = x
self.y = y
# self.pset.add_features(x, y, )
self.pset.add_features(x, y, x_group=[[1, 2], [4, 5]])
self.pset.add_constants([6, 3, 4], c_dim=[dless, dless, dless], c_prob=None)
self.pset.add_operations(power_categories=(2, 3, 0.5),
categories=("Add", "Mul", "Neg", "Abs"),
self_categories=None)
from sklearn.metrics import r2_score, mean_squared_error
self.cp = CalculatePrecisionSet(self.pset, scoring=[r2_score, mean_squared_error],
score_pen=[1, -1],dim_type=None,
filter_warning=True)
def test_gp_flow(self):
from numpy import random
random.seed(1)
cpset = self.cp
# def Tree
from deap.base import Fitness
from featurebox.tools import newclass
Fitness_ = newclass.create("Fitness_", Fitness, weights=(1, -1))
PTree_ = newclass.create("PTrees_", SymbolTree, fitness=Fitness_)
# def selection
toolbox = Toolbox()
# toolbox.register("select", selTournament, tournsize=3)
toolbox.register("select", selKbestDim, dim_type=dless)
# selBest
toolbox.register("mate", cxOnePoint)
# def mutate
toolbox.register("generate", genGrow, pset=cpset, min_=2, max_=3)
# toolbox.register("mutate", mutUniform, expr=toolbox.generate, pset=cpset)
# toolbox.register("mutate", mutNodeReplacement, pset=cpset)
toolbox.register("mutate", mutShrink,pset=cpset)
toolbox.decorate("mate", staticLimit(key=operator.attrgetter("height"), max_value=10))
toolbox.decorate("mutate", staticLimit(key=operator.attrgetter("height"), max_value=10))
# def elaluate
# toolbox.register("evaluate", cpset.parallelize_calculate, n_jobs=4, add_coef=True,
# inter_add=False, inner_add=False)
# toolbox.register("parallel", parallelize, n_jobs=1, func=toolbox.evaluate, respective=False, tq=False)
population = [PTree_.genGrow(cpset, 3, 4) for _ in range(10)]
# si = sys.getsizeof(cpset)
for i in range(5):
invalid_ind = [ind for ind in population if not ind.fitness.valid]
invalid_ind_score = cpset.parallelize_score(inds=invalid_ind)
for ind, score in zip(invalid_ind, invalid_ind_score):
ind.fitness.values = score[0]
ind.y_dim = score[1]
# si2 = sys.getsizeof(invalid_ind[0])
# invalid_ind=[i.compress() for i in invalid_ind]
# si3 = sys.getsizeof(invalid_ind[0])
# print(si3,si2,si)
population = toolbox.select(population, len(population))
offspring = varAnd(population, toolbox, 1, 1)
population[:] = offspring
pset.add_features(
x,
y,
x_group=group,
)
pset.add_accumulative_operation(categories=("MAdd", "MMul", "MSub", "MDiv",
"Conv", "Self"),
special_prob={
"MAdd": 0.16,
"MMul": 0.16,
"MSub": 0.16,
"MDiv": 0.16,
"Conv": 0.16,
"Self": 0.16
})
pset.add_operations(categories=("Add", "Mul", "Sub", "Div"))
s = pset.free_symbol[1]
ss = []
for si in s:
if isinstance(si, sympy.Symbol):
ss.append(si)
else:
ss.extend(si)
target = (ss[0] + ss[1]) * (ss[2] - ss[3])
target = sympy.simplify(target)
# a = time.time()
random.seed(4)
population = [
SymbolTree.genFull(pset, int(height - 1),