恳求大家看看我的代码，这样先打乱数据集，再随机划分测试集的方式可行吗（回归预测问题）

Question

x0=data[3:18000,:]
y0=data[3:18000,-1]

sc = MinMaxScaler(feature_range=(0, 1))  
x = sc.fit_transform(x0)

y0=y0.reshape(-1,1)
scc = MinMaxScaler(feature_range=(0, 1))  
y = scc.fit_transform(y0)

x_t = []
y_t = []
x_train = []
y_train = []
x_test = []
y0_test = []

num_his_input=5
num_predmax_output=1
num_input=65

for i in range(num_his_input, len(y)-num_predmax_output):
    x_t.append(x[i - num_his_input:i,:])
    y_t.append(y[i:i+num_predmax_output,:])
x_t, y_t = np.array(x_t), np.array(y_t)#预测当前值t

x_t = np.reshape(x_t, (x_t.shape[0], num_his_input, num_input))
y_t=y_t.reshape(-1,num_predmax_output)

x_train=x_t[0:16000,:]
y_train=y_t[0:16000,:]
x_test=x_t[16000:17000,:]
y0_test=y_t[16000:17000,:]

np.random.seed(7)
np.random.shuffle(x_train)
np.random.seed(7)
np.random.shuffle(y_train)
tf.random.set_seed(7)

Answer 1

可以，验证能否可行，可以直接拿去测试模型，看看预测结果