# 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,
re_Tree=0, store=False, random_state=4, verbose=True,
# stats=None,
stats={"fitness_dim_max": ["max"], "dim_is_target": ["sum"], "h_bgp": ["mean"]},
add_coef=True, inter_add=True, out_add=True, cal_dim=True, vector_add=True,
personal_map=False)
tt.t
sl.fit()
tt.t
tt.p
score = sl.score(x, y, "r2")
print(sl.expr)
y_pre = sl.predict(x)
break
# just for shown
# y_pre = si_transformer.scale_y * y_pre
# ssc = Dim.inverse_convert(y_dim, target_units=eV)[0]
# y_pre = y_pre * ssc
#
# p = BasePlot(font=None)
# p.scatter(Y, y_pre, strx='Experimental $E_{gap}$', stry='Calculated $E_{gap}$')
# import matplotlib.pyplot as plt
#
# plt.show()
dim_type="coef",
stop_condition=stop,
re_Tree=0,
random_state=0,
verbose=True,
add_coef=True,
inter_add=True,
cal_dim=False,
inner_add=True,
personal_map=False)
# sl.fit()
print(sl.expr)
y_pre = sl.predict(X)
score_all = sl.score(X, y, "r2")
p = BasePlot(font=None)
p.scatter(y,
y_pre,
strx='Experimental $E_{gap}$',
stry='Calculated $E_{gap}$')
import matplotlib.pyplot as plt
plt.show()
y_pre = sl.predict(X_test)
score_test = sl.score(X_test, y_test, "r2")
p = BasePlot(font=None)
p.scatter(y_test,
n_jobs=16,
initial_max=2,
max_value=4,
store=True,
stats={"fitness_dim_max": ("max", )})
sl.fit(
x,
y,
x_dim=[pa_dim, dless, dless, dless, dless, dless, dless],
y_dim=pa_dim,
power_categories=(2, 3, 0.5, 0.33),
categories=("Add", "Mul", "Sub", "Div"),
)
print(sl.expr)
r2 = sl.score(x, y, "r2")
mae = sl.score(x, y, "neg_mean_absolute_error")
pre_y = sl.predict(x)
r = np.corrcoef(np.vstack((pre_y, y)))[1, 0]
error = np.mean(np.abs((y - pre_y) / y))
r2 = sl.score(x, y, "r2")
mae = sl.score(x, y, "neg_mean_absolute_error")
sl.loop.cpset.cv = 5
r2_cv = sl.cv_result(refit=False)
print("r:{},error:{},r2:{},MAE:{},r2_cv:{}".format(r, error, r2, mae,
r2_cv[0]))
data = sl.loop.top_n(20, ascending=False)