根据交叉验证绘制ROC曲线

import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import make_classification
from sklearn.model_selection import StratifiedKFold
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import roc_curve, auc

# 生成一个示例数据集
X, y = make_classification(n_samples=1000, n_features=20, random_state=42)

# 初始化模型
model = LogisticRegression()

# 初始化ROC曲线数据存储
tprs = []
aucs = []
mean_fpr = np.linspace(0, 1, 100)

# 分层K折交叉验证
cv = StratifiedKFold(n_splits=5)
for i, (train, test) in enumerate(cv.split(X, y)):
    model.fit(X[train], y[train])
    y_pred_proba = model.predict_proba(X[test])[:, 1]
    fpr, tpr, _ = roc_curve(y[test], y_pred_proba)
    tprs.append(np.interp(mean_fpr, fpr, tpr))
    tprs[-1][0] = 0.0
    roc_auc = auc(fpr, tpr)
    aucs.append(roc_auc)

# 计算平均ROC曲线
mean_tpr = np.mean(tprs, axis=0)
mean_tpr[-1] = 1.0
mean_auc = auc(mean_fpr, mean_tpr)
std_auc = np.std(aucs)

# 绘制ROC曲线
plt.figure(figsize=(8, 6))
plt.plot(mean_fpr, mean_tpr, color='b', label=f'Mean ROC (AUC = {mean_auc:.2f} ± {std_auc:.2f})', lw=2, alpha=.8)
for i, (fpr, tpr) in enumerate(zip(fprs, tprs)):
    plt.plot(fpr, tpr, lw=1, alpha=.3, label=f'ROC fold {i+1} (AUC = {aucs[i]:.2f})')

plt.plot([0, 1], [0, 1], linestyle='--', lw=2, color='r', label='Chance', alpha=.8)
plt.xlim([-0.05, 1.05])
plt.ylim([-0.05, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Receiver Operating Characteristic')
plt.legend(loc="lower right")
plt.show()