2024.11.25

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import cross_validate
from sklearn.metrics import make_scorer, accuracy_score, precision_score, recall_score, f1_score, classification_report

# 加载 iris 数据集
iris = load_iris()
X, y = iris.data, iris.target

# 留出 1/3 数据作为测试集
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=1/3, stratify=y, random_state=42)

# 初始化逻辑回归模型
model = LogisticRegression(max_iter=200, random_state=42)

# 使用训练集训练模型
model.fit(X_train, y_train)

print("逻辑回归模型训练完成")

# 定义评分指标
scoring = {
    'accuracy': make_scorer(accuracy_score),
    'precision': make_scorer(precision_score, average='weighted'),
    'recall': make_scorer(recall_score, average='weighted'),
    'f1': make_scorer(f1_score, average='weighted')
}

# 使用五折交叉验证评估
cv_results = cross_validate(model, X_train, y_train, cv=5, scoring=scoring)

# 打印评估结果
print("五折交叉验证结果：")
for metric, scores in cv_results.items():
    if metric.startswith('test_'):
        print(f"{metric}: {scores.mean():.4f} ± {scores.std():.4f}")

# 预测测试集
y_pred = model.predict(X_test)

# 打印性能报告
report = classification_report(y_test, y_pred, target_names=iris.target_names)
print("测试集性能报告：")
print(report)