使用交叉验证和ROC度量来测量分类器

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

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

# 初始化分类器
clf = LogisticRegression(max_iter=10000)

# 使用StratifiedKFold进行5折交叉验证
cv = StratifiedKFold(n_splits=5)
y_pred_proba = cross_val_predict(clf, X, y, cv=cv, method='predict_proba')[:, 1]

# 计算ROC曲线
fpr, tpr, thresholds = roc_curve(y, y_pred_proba)
roc_auc = auc(fpr, tpr)

# 绘制ROC曲线
plt.figure()
lw = 2
plt.plot(fpr, tpr, color='darkorange', lw=lw, label='ROC curve (area = %0.2f)' % roc_auc)
plt.plot([0, 1], [0, 1], color='navy', lw=lw, linestyle='--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Receiver Operating Characteristic')
plt.legend(loc="lower right")
plt.show()