11.29日报

今天完成机器学习B的实验，以下为实验部分代码：

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, classification_report, confusion_matrix

# 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没有直接的后剪枝参数，但我们可以通过设置max_depth来控制树的深度
dt = DecisionTreeClassifier(
    criterion='gini',  # 选择分割质量的测量标准，默认为'gini'
    splitter='best',  # 选择属性的分割策略，默认为'best'，可选'random'
    max_depth=3,  # 树的最大深度，这里设置为3来进行预剪枝
    min_samples_split=2,  # 节点划分时所需的最小样本数，默认为2
    min_samples_leaf=1,  # 叶节点所需的最小样本数，默认为1
    random_state=42  # 随机数生成器的种子
)

# 训练模型
dt.fit(X_train, y_train)

# 预测训练集和测试集
y_train_pred = dt.predict(X_train)
y_pred = dt.predict(X_test)

# 评估训练集和测试集的性能
train_accuracy = accuracy_score(y_train, y_train_pred)
test_accuracy = accuracy_score(y_test, y_pred)
train_precision = precision_score(y_train, y_train_pred, average='macro')
test_precision = precision_score(y_test, y_pred, average='macro')
train_recall = recall_score(y_train, y_train_pred, average='macro')
test_recall = recall_score(y_test, y_pred, average='macro')
train_f1 = f1_score(y_train, y_train_pred, average='macro')
test_f1 = f1_score(y_test, y_pred, average='macro')

# 打印性能评估结果
print("Training Set Performance:")
print(f"Accuracy: {train_accuracy:.4f}")
print(f"Precision: {train_precision:.4f}")
print(f"Recall: {train_recall:.4f}")
print(f"F1 Score: {train_f1:.4f}\n")

print("Test Set Performance:")
print(f"Accuracy: {test_accuracy:.4f}")
print(f"Precision: {test_precision:.4f}")
print(f"Recall: {test_recall:.4f}")
print(f"F1 Score: {test_f1:.4f}\n")

# 使用五折交叉验证评估模型性能
cross_val_scores = cross_val_score(dt, X_train, y_train, cv=5, scoring='accuracy')
print(f"Cross-validation scores: {cross_val_scores}")
print(f"Mean accuracy: {cross_val_scores.mean():.4f}")
print(f"Standard deviation: {cross_val_scores.std():.4f}\n")

# 打印分类报告和混淆矩阵
print("Classification Report:\n", classification_report(y_test, y_pred, target_names=iris.target_names))
print("Confusion Matrix:\n", confusion_matrix(y_test, y_pred))