决策树代码

以下为调api的代码，然后最后通过graphviz包对决策树进行可视化，and：包需要预先下载再导入

部署失败的话记得改路径即可orz

import numpy as np
import sklearn.tree
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier,export_graphviz
import graphviz
import pandas as pd
import matplotlib
from sklearn.tree import export_graphviz
import os # 以下这两行是手动进行环境变量配置，防止在本机的环境变量部署失败
os.environ['PATH'] = os.pathsep + r'C:Program FilesGraphvizbin'


def tree_iris():
    # 直接sklearn数据集，不需要标准化
    iris=load_iris()
    #划分数据集
    x_train,x_test,y_train,y_test=train_test_split(iris.data,iris.target,random_state=22)

    #决策树预估器 entropy 按信息增益进行分类
    estimator=DecisionTreeClassifier(criterion='entropy')
    estimator.fit(x_train,y_train)

    #模型评估
    y_predict=estimator.predict(x_test)
    print('y_predict:n',y_predict)
    print('ha:n',y_test==y_predict)

    #计算准确率
    score=estimator.score(x_test,y_test)
    print('score:n',score)

    # 决策树可视化
    dot_data=export_graphviz(estimator,out_file=None)

    #graphviz
    print(dot_data)
    graph=graphviz.Source(dot_data)
    graph.render('决策树可视化')

    return None

tree_iris()

大概这样吧