# L1正则
import numpy as np
from sklearn.linear_model import Lasso
from sklearn.linear_model import SGDRegressor
X = 2 * np.random.rand(100, 1)
y = 4 + 3 * X + np.random.randn(100, 1)
lasso_reg = Lasso(alpha=0.15)
lasso_reg.fit(X, y)
print(lasso_reg.predict(1.5))
sgd_reg = SGDRegressor(penalty='l1')
sgd_reg.fit(X, y.ravel())
print(sgd_reg.predict(1.5))
# L2正则
import numpy as np
from sklearn.linear_model import Ridge
from sklearn.linear_model import SGDRegressor
X = 2 * np.random.rand(100, 1)
y = 4 + 3 * X + np.random.randn(100, 1)
#两种方式第一种岭回归
ridge_reg = Ridge(alpha=1, solver='auto')
ridge_reg.fit(X, y)
print(ridge_reg.predict(1.5))#预测1.5的值
#第二种 使用随机梯度下降中L2正则
sgd_reg = SGDRegressor(penalty='l2')
sgd_reg.fit(X, y.ravel())
print(sgd_reg.predict(1.5))
1 # elastic_net函数
2 import numpy as np
3 from sklearn.linear_model import ElasticNet
4 from sklearn.linear_model import SGDRegressor
5
6
7 X = 2 * np.random.rand(100, 1)
8 y = 4 + 3 * X + np.random.randn(100, 1)
9 #两种方式实现Elastic_net
10 elastic_net = ElasticNet(alpha=0.1, l1_ratio=0.5)
11 elastic_net.fit(X, y)
12 print(elastic_net.predict(1.5))
13
14 sgd_reg = SGDRegressor(penalty='elasticnet')
15 sgd_reg.fit(X, y.ravel())
16 print(sgd_reg.predict(1.5))
