Win 10+py36 安装 graphviz-2.38 和 pygraphviz-1.6

1 下载 graphviz-2.38.msi 和 pygraphviz-1.6（python其他版本）

2 安装 graphviz-2.38.msi

    可用其默认安装地址。我是 C:\Program Files (x86)\Graphviz2.38

3.添加环境变量

将C:\Program Files (x86)\Graphviz2.38\bin 添加到系统变量path中

4  查看graphviz-2.38是否安装成功

终端，输入dot -version 显示如下则配置成功

5 安装pygraphviz-1.6

6.测试效果

6.1 实验代码mytree.py

from sklearn.datasets import fetch_20newsgroups
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import classification_report
from sklearn.feature_extraction import DictVectorizer
from sklearn.tree import DecisionTreeClassifier, export_graphviz
import pandas as pd


def decision():
    """
    决策树对泰坦尼克号进行生死预测
    :return:None
    """
    titan = pd.read_csv("http://biostat.mc.vanderbilt.edu/wiki/pub/Main/DataSets/titanic.txt")
    # 处理数据
    x = titan[['pclass', 'age', 'sex']]
    y = titan['survived']
    # print(x)

    # 缺失值处理
    x['age'].fillna(x['age'].mean(), inplace=True)

    # 先分割数据集到训练集和测试集
    x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.25)

    # 进行处理one_hot编码
    dict = DictVectorizer(sparse=False)
    x_train = dict.fit_transform(x_train.to_dict(orient='records'))
    print(dict.get_feature_names())
    x_test = dict.transform(x_test.to_dict(orient='records'))
    # print(x_test)

    # 决策树预测
    dec = DecisionTreeClassifier()
    dec.fit(x_train, y_train)
    # 预测准确率
    print("预测准确率：", dec.score(x_test, y_test))
    # 导出决策树结构
    export_graphviz(dec, out_file="./tree.dot",
                    feature_names=['年龄', 'pclass=1st', 'pclass=2nd',
                                   'pclass=3rd', '女性', '男性'] )


if __name__ == '__main__':
    decision()

6.2 运行如下：

6.3 在D:\Jeff路径下生成 文件 tree.dot

6.4 终端上切换到文件路径，输入dot -Tpng tree.dot -o tree.png

路径D:\Jeff 下生成 tree.png

参考：https://blog.csdn.net/weixin_45170058/article/details/102575418