from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score
from sklearn.tree import export_graphviz
import graphviz


# 加载鸢尾花数据集
iris = load_iris()
X = iris.data
y = iris.target

# 将数据集分为训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

# 创建决策树分类器
clf = DecisionTreeClassifier()

# 训练模型
clf.fit(X_train, y_train)

# 对测试集进行预测
y_pred = clf.predict(X_test)

# 计算准确率
accuracy = accuracy_score(y_test, y_pred)
print(f"模型准确率: {accuracy:.2f}")

# 导出决策树为dot文件
dot_data = export_graphviz(clf, out_file=None,
                           feature_names=iris.feature_names,  
                           class_names=iris.target_names,  
                           filled=True, rounded=True,  
                           special_characters=True)

# 使用graphviz渲染决策树
graph = graphviz.Source(dot_data)
graph.render("iris_decision_tree")  # 保存为PDF文件
graph.view()  # 在浏览器中查看