【机器学习西瓜书阅读笔记】（四）决策树+sklearn样例代码实现

桃扇骨 2022-12-13 04:11 139阅读 0赞

### 目录 ###

*   *  思维导图
     *  sklearn样例实现
     *  参考

> PS：本篇博客提供基本思维导图和sklearn样例实现

## 思维导图 ##

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dfbGludXg_size_16_color_FFFFFF_t_70_pic_center]

## sklearn样例实现 ##

> 在jupyter下运行

from sklearn import tree
    from sklearn.datasets import load_wine
    from sklearn.model_selection import train_test_split
    import pandas as pd
    wine = load_wine()#红酒数据
    pd.concat([pd.DataFrame(wine.data),pd.DataFrame(wine.target)],axis=1)
    Xtrain,Xtest,Ytrain,Ytest = train_test_split(wine.data,wine.target,test_size=0.3)#特征、标签、测试样本的尺寸0.3（测试集30%，训练集70%）
    
    '''建立模型'''
    clf = tree.DecisionTreeClassifier(criterion="entropy")#实例化、分类树
    clf = clf.fit(Xtrain,Ytrain)#训练集训练模型
    score = clf.score(Xtest,Ytest)#测试集测试，返回预测的准确度
    score#查看得分
    feature_name = ['酒精','苹果酸','灰','灰的碱性','镁','总酚','类黄酮','非黄烷类酚类','花青素','颜色强度','色调','稀释葡萄酒','脯氨酸']
    import graphviz
    dot_data = tree.export_graphviz(clf#模型实例
                                   ,feature_names = feature_name#特征
                                   ,class_names=["哈尔滨酒","青岛酒","广西酒"]#类别
                                   ,filled=True#填充颜色
                                   ,rounded = True )
                                   
    graph = graphviz.Source(dot_data)
    score#查看得分
    graph#查看决策树

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dfbGludXg_size_16_color_FFFFFF_t_70_pic_center 1]

## 参考 ##

1、《机器学习》周志华著  
2、菜菜的机器学习

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dfbGludXg_size_16_color_FFFFFF_t_70_pic_center]: /images/20221123/e4328fd1e29c411080ffb833bcc34afb.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dfbGludXg_size_16_color_FFFFFF_t_70_pic_center 1]: /images/20221123/a570e79228b649018f688879029e9984.png