from bgp.base import SymbolSet, SymbolTree
from bgp.calculation.translate import general_expr_dict, compile_context
if __name__ == "__main__":
x = np.full((10, 4), fill_value=0.1)
y = np.ones((10, ))
height = 2
hbgp = 1
# bgp
group = 2
pset = SymbolSet()
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]
# plt.show()
X = q1[:, :-1]
y = q1[:, -1]
X = np.concatenate((X, (X[:, 1] / X[:, 0]**2).reshape(-1, 1)), axis=1)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.20,
random_state=0)
store = Store()
# symbolset
pset0 = SymbolSet()
pset0.add_features(X_train, y_train)
pset0.add_constants(c=[
1,
])
pset0.add_operations(
power_categories=(2, ),
categories=("Add", "exp", "Neg"),
)
h_bgp = 3
# stop = None
# This random_state is under Linux system. For others system ,the random_state maybe different。
# try with different random_state.
stop = lambda ind: ind.fitness.values[0] >= 0.99
sl = SymbolLearning(loop='MultiMutateLoop',
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], [6, 7]],
feature_name=["Ss%i" % i for i in range(13)])
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", "ln"),
self_categories=None)
random.seed(2)
z = time.time()
sl = [SymbolTree.genGrow(pset0, 3, 4) for _ in range(500)]
a = time.time()
# sli =" MAdd(Sub(Add(Mul(x0, gx1), exp(x10)), Mul(Conv(Add(x0, gx0)), Mul(x6, MAdd(x10)))))"
# sl =["MAdd(gx1 * x11 * (-x0 + x11) * MAdd(gx1))"]
# sl = [compile_context(sli, pset0.context, pset0.gro_ter_con) for sli in sl]
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)
os.chdir(r'band_gap')
data = Call()
name_and_abbr = data.csv().name_and_abbr
SL_data = data.SL_data
si_transformer = data.si_transformer
store = Store()
x, x_dim, y, y_dim, c, c_dim, X, Y = SL_data
x_g = np.arange(x.shape[1])
x_g = list(x_g[1:])
x_g = x_g.reshape(-1, 2)
pset0 = SymbolSet()
pset0.add_features(x, y, x_dim=x_dim, y_dim=y_dim, x_group=x_g)
pset0.add_constants(c, c_dim=c_dim, c_prob=0.05)
pset0.add_operations(power_categories=(2, 3, 0.5, 1 / 3, 4, 1 / 4),
# categories=("Mul",),
categories=("Add", "Mul", "Sub", "Div", "exp", "ln"),
self_categories=None)
total_height = 3
h_bgp = 2
# This random_state is under Linux system. For others system ,the random_state maybe different,please
# try with different random_state.
for i in range(1, 10):
stop = lambda ind: ind.fitness.values[0] >= 0.95
sl = SymbolLearning(loop="MultiMutateLoop", pset=pset0, gen=20, pop=1000, hall=1, batch_size=40, re_hall=3,
n_jobs=12, mate_prob=0.9, max_value=h_bgp, initial_min=2, initial_max=h_bgp,
mutate_prob=0.8, tq=False, dim_type="coef", stop_condition=stop,
dless
]
"""preprocessing"""
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)
scal = MagnitudeTransformer(tolerate=1)
x, y = scal.fit_transform_all(x, y, group=2)
c = scal.fit_transform_constant(c)
# symbolset
pset0 = SymbolSet()
pset0.add_features(x,
y,
x_dim=x_dim,
y_dim=y_dim,
x_group=2,
feature_name=fea_name)
pset0.add_constants(c, c_dim=c_dim, c_prob=0.05)
pset0.add_operations(power_categories=(2, 3, 0.5),
categories=("Add", "Mul", "Sub", "Div", "exp",
"ln"),
self_categories=None)
# a = time.time()
dicts = {}
for i in range(12):
bl = MultiMutateLoop(pset=pset0,
gen=20,
pop=1000,
hall=1,
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)
sc = preprocessing.MinMaxScaler((1, 2))
x = sc.fit_transform(x)
t = time.time()
# symbolset
pset0 = SymbolSet()
pset0.add_features(x,
y,
x_dim=x_dim,
y_dim=y_dim,
x_group=2,
feature_name=["Ss%i" % i for i in range(8)])
pset0.add_constants(c, c_dim=c_dim, c_prob=None)
pset0.add_operations(power_categories=(2, 3, 4),
categories=("Add", "Mul", "Sub", "Div", "ln", "exp"),
self_categories=None)
pset0 = CalculatePrecisionSet(pset0,
scoring=None,
score_pen=(1, ),
filter_warning=True,
cal_dim=False,
dim_type=None,
fuzzy=False,
add_coef=False,
if __name__ == '__main__':
# unittest.main()
import numpy as np
x = np.array([[10, 6, 3, 4, 5, 6, 7, 8, 9, 9, 10, 9, 7, 5, 3, 1],
[1, 2, 3, 4, 4, 3, 2, 4, 5, 6, 7, 8, 9, 10, 12, 15],
[2, 3, 4, 8, 12, 16, 30, 32, 33, 30, 20, 10, 5, 3, 2, 1]]).T
x[:, 2] = x[:, 0] / x[:, 1]
y = np.zeros(x.shape[0])
x = x
y = y
pset = SymbolSet()
pset.add_features(x, y)
pset.add_operations(
categories=("Add", "Mul", "Self", "Abs"),
self_categories=None)
from sklearn.metrics import r2_score, mean_squared_error
cp = CalculatePrecisionSet(pset, scoring=[r2_score, mean_squared_error],
score_pen=[1, -1],
filter_warning=True)
x0, x1, x2 = sympy.symbols("x0, x1, x2")
# t=Function("t")
# expr00 = (x2*x1+x0*x2*2).subs(x0, t(x1))
# dv1 = sympy.diff(expr00, x1, evaluate=True)
# dv1 = dv1.subs(t(x1), x0)
# 由单位获得缩放因子和量纲
gpa_dim = Dim.convert_to_Dim(1e9 * pa, unit_system="SI")
j_d_mol_dim = Dim.convert_to_Dim(1000 * J / mol, unit_system="SI")
K_dim = Dim.convert_to_Dim(K, unit_system="SI")
kg_d_m3_dim = Dim.convert_to_Dim(kg / m**3, unit_system="SI")
# 忽视缩放因子
y_dim = dless
x_dim = [
dless, gpa_dim[1], j_d_mol_dim[1], K_dim[1], dless, kg_d_m3_dim[1]
]
# 符号集合
pset0 = SymbolSet()
pset0.add_features(x, y, x_dim=x_dim, y_dim=y_dim)
pset0.add_operations(
power_categories=(2, 3, 0.5),
categories=("Mul", "Div", "exp"),
)
# 符号回归
# 方式选择1，系数加在最外层
# sl = SymbolLearning(loop="MultiMutateLoop", pop=100, gen=2, random_state=1,pset=pset0,
# classification=True, scoring=[metrics.accuracy_score, ], score_pen=[1, ],
# cal_dim=True, n_jobs = 10,
# store =True
# )
# # 方式选择2，系数加在最外层,认定系数可以自动补全量纲
class MyTestgp(unittest.TestCase):
def setUp(self):
self.SymbolTree = SymbolTree
self.pset = SymbolSet()
from sklearn.datasets import fetch_california_housing
data = fetch_california_housing()
x = data["data"][:100]
y = data["target"][:100]
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
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
class MyTestbase(unittest.TestCase):
def setUp(self):
self.SymbolTree = SymbolTree
self.pset = SymbolSet()
from sklearn.datasets import fetch_california_housing
data = fetch_california_housing()
x = data["data"][:100]
y = data["target"][:100]
# 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)