高斯回归

# -*- coding: utf-8 -*-
import numpy as np
from sklearn.gaussian_process import GaussianProcessRegressor
from sklearn.gaussian_process.kernels import RBF,WhiteKernel, ConstantKernel as C
from sklearn.model_selection import train_test_split  # 这里是引用了交叉验证
from sklearn.metrics import mean_squared_error
from data_load import load_data
X,y = load_data()
# 训练数据
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
kernel = C(0.25, (1e-3, 1e3)) * RBF(0.5, (1e-3, 1e4)) + WhiteKernel(0.0002, (1e-23, 1e3))
reg = GaussianProcessRegressor(kernel=kernel, n_restarts_optimizer=30)
for i in range(2):
    reg.fit(X_train, y_train)
# 预测
y_pred = reg.predict(X_test)