2024.12.12

# 导入必要的库
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split, cross_validate
from sklearn.naive_bayes import GaussianNB
from sklearn.metrics import make_scorer, accuracy_score, precision_score, recall_score, f1_score, classification_report

# Step 1: 加载 iris 数据集并分割为训练集和测试集
iris = load_iris()  # 加载数据集
X, y = iris.data, iris.target  # 提取特征和标签

# 留出法分割数据集，测试集占 1/3，保证同分布
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=1/3, random_state=42, stratify=y)

# Step 2: 初始化并训练朴素贝叶斯模型
gnb = GaussianNB()  # 初始化 GaussianNB 模型
gnb.fit(X_train, y_train)  # 使用训练集训练模型

# Step 3: 使用五折交叉验证评估模型性能
# 定义评估指标
scoring = {
    'accuracy': make_scorer(accuracy_score),
    'precision_macro': make_scorer(precision_score, average='macro'),
    'recall_macro': make_scorer(recall_score, average='macro'),
    'f1_macro': make_scorer(f1_score, average='macro')
}

# 五折交叉验证
cv_results = cross_validate(gnb, X_train, y_train, cv=5, scoring=scoring)

# 打印交叉验证结果
print("五折交叉验证结果：")
for metric in scoring.keys():
    mean = cv_results['test_' + metric].mean()
    std = cv_results['test_' + metric].std()
    print(f"{metric}: {mean:.4f} ± {std:.4f}")

# Step 4: 测试集评估模型性能
# 使用测试集进行预测
y_pred = gnb.predict(X_test)

# 输出分类报告
print("\n测试集性能报告：")
print(classification_report(y_test, y_pred, target_names=iris.target_names))