每日总结47

from sklearn.datasets import load_iris

from sklearn.model_selection import train_test_split, cross_val_score

from sklearn.tree import DecisionTreeClassifier

from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score

 

# 加载iris数据集

iris = load_iris()

X, y = iris.data, iris.target

 

# 使用留出法留出1/3的样本作为测试集

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=1/3, random_state=42)

 

# 初始化决策树分类器，设置预剪枝参数

# 注意：scikit-learn中的DecisionTreeClassifier不直接支持C4.5算法，但可以使用信息增益作为划分标准

clf = DecisionTreeClassifier(criterion='entropy', random_state=42, max_depth=None)  # 使用信息增益，不进行预剪枝

 

# 训练模型

clf.fit(X_train, y_train)

 

# 使用五折交叉验证评估模型性能

scores = cross_val_score(clf, X_train, y_train, cv=5, scoring='accuracy')

 

# 预测测试集

y_pred = clf.predict(X_test)

 

# 计算准确度、精度、召回率和F1值

accuracy = accuracy_score(y_test, y_pred)

precision = precision_score(y_test, y_pred, average='macro')

recall = recall_score(y_test, y_pred, average='macro')

f1 = f1_score(y_test, y_pred, average='macro')

 

# 打印结果

print(f"五折交叉验证准确度: {scores.mean():.2f} +/- {scores.std():.2f}")

print(f"测试集准确度: {accuracy:.2f}")

print(f"测试集精度: {precision:.2f}")

print(f"测试集召回率: {recall:.2f}")

print(f"测试集F1值: {f1:.2f}")