Y = y_frame.values
X, Y = shuffle(X, Y, random_state=5)
x, y = X, Y
# y_unit
from sympy.physics.units import eV, elementary_charge, m, pm
y_u = eV
# c_unit
c = [1, 5.290 * 10**-11, 1.74, 2, 3, 4, 1 / 2, 1 / 3, 1 / 4]
c_u = [
elementary_charge, m, dless, dless, dless, dless, dless, dless, dless
]
"""preprocessing"""
dims = [
Dim.convert_to_Dim(i, target_units=None, unit_system="SI") for i in x_u
]
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)
group = 2
n = X.shape[1]
indexes = [_ for _ in range(n)]
group = [indexes[i:i + group] for i in range(2, len(indexes), group)]
x, y = scal.fit_transform_all(x, y, group=group)
c = scal.fit_transform_constant(c)
store.to_pkl_pd(scal, "si_transformer")
from bgp.skflow import SymbolLearning
if __name__ == "__main__":
# 数据
data = pd.read_csv("204-6.csv")
data_np = data.values
x = data_np[:, 1:]
y = data_np[:, 0]
# 量纲
from sympy.physics.units import kg, m, pa, J, mol, K
from bgp.functions.dimfunc import Dim, dless
# 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),