决策树算法

from sklearn import tree
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
import numpy as np

if __name__ == "__main__":
    # 加载数据
    dataset = load_iris()

    # 提取属性数据
    X = dataset.data
    # 提取标签数据
    y = dataset.target

    # train_test_split函数用于划分数据集为训练集和测试集，其中参数test_size默认为0.25,表示将25%的数据划分为测试集
    Xd_train, Xd_test, y_train, y_test = train_test_split(X, y, random_state=14)

    # 创建决策树分类器
    clf = tree.DecisionTreeClassifier()
    # 训练分类器模型
    clf = clf.fit(Xd_train, y_train)

    y_predicted = clf.predict(Xd_test)

    # 计算预测准确率
    accuracy = np.mean(y_predicted == y_test) * 100

    print("y_test     {}", y_test)
    print("y_predicted", y_predicted)
    print("accuracy:", accuracy)