Lasso 和 Elastic Net (弹性网络) 在稀疏信号上的表现
优质
小牛编辑
132浏览
2023-12-01
评估了 Lasso 回归模型和弹性网络回归模型在手动生成的,并附加噪声的稀疏信号上的表现,并将回归系数与真实值进行了比较。
import numpy as np
import matplotlib.pyplot as plt
from sklearn.metrics import r2_score
# 产生一些稀疏值
np.random.seed(42)
n_samples, n_features = 50, 100
X = np.random.randn(n_samples, n_features)
# 减少交替出现的符号以使其便于可视化
idx = np.arange(n_features)
coef = (-1) ** idx * np.exp(-idx / 10)
coef[10:] = 0 # sparsify coef
y = np.dot(X, coef)
# 添加噪音
y += 0.01 * np.random.normal(size=n_samples)
# 划分测试,训练集
n_samples = X.shape[0]
X_train, y_train = X[:n_samples // 2], y[:n_samples // 2]
X_test, y_test = X[n_samples // 2:], y[n_samples // 2:]
# Lasso
from sklearn.linear_model import Lasso
alpha = 0.1
lasso = Lasso(alpha=alpha)
y_pred_lasso = lasso.fit(X_train, y_train).predict(X_test)
r2_score_lasso = r2_score(y_test, y_pred_lasso)
print(lasso)
print("r^2 on test data : %f" % r2_score_lasso)
Lasso(alpha=0.1, copy_X=True, fit_intercept=True, max_iter=1000,
normalize=False, positive=False, precompute=False, random_state=None,
selection='cyclic', tol=0.0001, warm_start=False)
r^2 on test data : 0.658064
# 弹性网络(ElasticNet)
from sklearn.linear_model import ElasticNet
enet = ElasticNet(alpha=alpha, l1_ratio=0.7)
y_pred_enet = enet.fit(X_train, y_train).predict(X_test)
r2_score_enet = r2_score(y_test, y_pred_enet)
print(enet)
print("r^2 on test data : %f" % r2_score_enet)
ElasticNet(alpha=0.1, copy_X=True, fit_intercept=True, l1_ratio=0.7,
max_iter=1000, normalize=False, positive=False, precompute=False,
random_state=None, selection='cyclic', tol=0.0001, warm_start=False)
r^2 on test data : 0.642515
m, s, _ = plt.stem(np.where(enet.coef_)[0], enet.coef_[enet.coef_ != 0],
markerfmt='x', label='Elastic net系数')
plt.setp([m, s], color="#2ca02c")
m, s, _ = plt.stem(np.where(lasso.coef_)[0], lasso.coef_[lasso.coef_ != 0],
markerfmt='x', label='Lasso系数')
plt.setp([m, s], color='#ff7f0e')
plt.stem(np.where(coef)[0], coef[coef != 0], label='真实系数',
markerfmt='bx')
plt.legend(loc='best')
plt.title("Lasso $R^2$: %.3f, Elastic Net $R^2$: %.3f"
% (r2_score_lasso, r2_score_enet))
plt.show()