机器学习--基础算法--决策树

1 什么是决策树

使用决策树对鸢尾花数据集进行分类：

import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets

iris = datasets.load_iris()
x = iris.data
y = iris.target
x = x[:, 2:]

plt.scatter(x[y == 0, 0], x[y == 0, 1])
plt.scatter(x[y == 1, 0], x[y == 1, 1])
plt.scatter(x[y == 2, 0], x[y == 2, 1])
plt.show()

输出：

from sklearn.tree import DecisionTreeClassifier
dt_clf = DecisionTreeClassifier(max_depth=2, criterion='entropy')
dt_clf.fit(x, y)
>>>DecisionTreeClassifier(class_weight=None, criterion='entropy', max_depth=2,
                       max_features=None, max_leaf_nodes=None,
                       min_impurity_decrease=0.0, min_impurity_split=None,
                       min_samples_leaf=1, min_samples_split=2,
                       min_weight_fraction_leaf=0.0, presort=False,
                       random_state=None, splitter='best')

# 决策边界绘制函数
def plot_decision_boundary(model, axis):
    x0, x1 = np.meshgrid(
        np.linspace(axis[0], axis[1], int((axis[1]-axis[0])*100)).reshape(-1