模拟数据最佳子集选择

import numpy as np
import pandas as pd
from sklearn.preprocessing import PolynomialFeatures
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error
np.random.seed(1)
X = np.random.randn(100)
eps = np.random.randn(100)
Y = 3 + 4*X + 2*X**2 + X**3 + eps
poly = PolynomialFeatures(10, include_bias=False)
X_poly = poly.fit_transform(X.reshape(-1, 1))
print('X的多项式特征形状:', X_poly.shape)
print('真实模型包含X, X^2, X^3项')