DT

    path ='iris.data'  # 数据文件路径
    data = pd.read_csv(path, header=None)
    x = data[[0, 1]]
    # y = pd.Categorical(data[4]).codes
    y = LabelEncoder().fit_transform(data[4])
    # 为了可视化，仅使用前两列特征
    x = x.iloc[:, :2]
    # x = x[[0,1]]
    x_train, x_test, y_train, y_test = train_test_split(x, y, train_size=0.7, random_state=1)

    # 决策树参数估计
    # min_samples_split = 10：如果该结点包含的样本数目大于10，则(有可能)对其分支
    # min_samples_leaf = 10：若将某结点分支后，得到的每个子结点样本数目都大于10，则完成分支；否则，不进行分支
    model = DecisionTreeClassifier(criterion='entropy', min_samples_leaf=3)
    model.fit(x_train, y_train)
    y_test_hat = model.predict(x_test)      # 测试数据
    print('accuracy_score:', accuracy_score(y_test, y_test_hat))