在进行多项式回归分析时，用python分别实现L1正则调优和L2正则调优

好的，针对您的问题，我可以给出以下的Python代码实现：

L1正则调优：

from sklearn.linear_model import Lasso
from sklearn.preprocessing import PolynomialFeatures
from sklearn.pipeline import make_pipeline
from sklearn.model_selection import GridSearchCV
import numpy as np

# 构造数据
x = np.array([0.0, 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0])
y = np.array([0.1, 0.9, 2.8, 6.5, 12.4, 20.5, 30.8, 43.3, 58.0, 74.9])

# 构造管道
model = make_pipeline(PolynomialFeatures(degree=9), Lasso())

# 构造参数选项
param_grid = {'lasso__alpha': np.logspace(-5, 1, 50)}

# 执行交叉验证调优
grid = GridSearchCV(model, param_grid, cv=5, iid=False)
grid.fit(x[:, np.newaxis], y)

# 输出结果
print("最优参数:", grid.best_params_)
print("最优得分:", grid.best_score_)

L2正则调优：

from sklearn.linear_model import Ridge
from sklearn.preprocessing import PolynomialFeatures
from sklearn.pipeline import make_pipeline
from sklearn.model_selection import GridSearchCV
import numpy as np

# 构造数据
x = np.array([0.0, 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0])
y = np.array([0.1, 0.9, 2.8, 6.5, 12.4, 20.5, 30.8, 43.3, 58.0, 74.9])

# 构造管道
model = make_pipeline(PolynomialFeatures(degree=9), Ridge())

# 构造参数选项
param_grid = {'ridge__alpha': np.logspace(-5, 1, 50)}

# 执行交叉验证调优
grid = GridSearchCV(model, param_grid, cv=5, iid=False)
grid.fit(x[:, np.newaxis], y)

# 输出结果
print("最优参数:", grid.best_params_)
print("最优得分:", grid.best_score_)

以上就是 L1正则调优 和 L2正则调优 的Python代码实现，希望能够帮助到您。