（自学）sklearn决策树基础知识|解决centos7.8 graphviz报错不能画图的问题

sklearn常规流程：

from sklearn import tree          #导入需要的模块
clf = tree.DecisionTreeClassifier()#实例化
clf = clf.fit(x_train,y_train)     #用训练集训练模型
result = clf.score(x_test,y_test)  #导入测试集，从接口中调用需要的信息

DecisionTreeClassifier

重要参数

criterion

• criterion这个参数是用于决定不纯度的计算方法的，不纯度越小效果越好，sklearn提供了两种选择

1. entropy:信息熵
2. gini:基尼系数

实例：建立一棵树

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()
pd.concat([pd.DataFrame(wine.data),pd.DataFrame(wine.target)],axis=1)

	0	1	2	3	4	5	6	7	8	9	10	11	12	0
0	14.23	1.71	2.43	15.6	127.0	2.80	3.06	0.28	2.29	5.64	1.04	3.92	1065.0	0
1	13.20	1.78	2.14	11.2	100.0	2.65	2.76	0.26	1.28	4.38	1.05	3.40	1050.0	0
2	13.16	2.36	2.67	18.6	101.0	2.80	3.24	0.30	2.81	5.68	1.03	3.17	1185.0	0
3	14.37	1.95	2.50	16.8	113.0	3.85	3.49	0.24	2.18	7.80	0.86	3.45	1480.0	0
4	13.24	2.59	2.87	21.0	118.0	2.80	2.69	0.39	1.82	4.32	1.04	2.93	735.0	0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
173	13.71	5.65	2.45	20.5	95.0	1.68	0.61	0.52	1.06	7.70	0.64	1.74	740.0	2
174	13.40	3.91	2.48	23.0	102.0	1.80	0.75	0.43	1.41	7.30	0.70	1.56	750.0	2
175	13.27	4.28	2.26	20.0	120.0	1.59	0.69	0.43	1.35	10.20	0.59	1.56	835.0	2
176	13.17	2.59	2.37	20.0	120.0	1.65	0.68	0.53	1.46	9.30	0.60	1.62	840.0	2
177	14.13	4.10	2.74	24.5	96.0	2.05	0.76	0.56	1.35	9.20	0.61	1.60	560.0	2

178 rows × 14 columns

wine.feature_names #特征的名字

['alcohol',
 'malic_acid',
 'ash',
 'alcalinity_of_ash',
 'magnesium',
 'total_phenols',
 'flavanoids',
 'nonflavanoid_phenols',
 'proanthocyanins',
 'color_intensity',
 'hue',
 'od280/od315_of_diluted_wines',
 'proline']

#划分训练集和测试集
xtrain,xtest,ytrain,ytest = train_test_split(wine.data,wine.target,test_size=0.3)
# 建模
clf = tree.DecisionTreeClassifier(criterion='entropy')
clf = clf.fit(xtrain,ytrain)
score = clf.score(xtest,ytest)

import graphviz

记录Linux centos 7.8 解决决策树graphviz不能绘图的问题

• 网上百度到的大多都是windows系统的解决方案，由于本人也是编程小白，在此记录一下自己的解决历程
• 命令行运行 yum -y install graphviz 安装dot
• 再安装graphviz 和python-graphviz
• 问题得到解决

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']
dot_data = tree.export_graphviz(clf,
                               feature_names=feature_name,
                               class_names=['琴酒','雪莉','贝尔摩德'],
                               filled=True,
                               rounded=True)
graph = graphviz.Source(dot_data)
graph

clf.feature_importances_  #查看各特征的重要性

array([0.        , 0.06776584, 0.        , 0.        , 0.        ,
       0.        , 0.17665173, 0.        , 0.        , 0.25465528,
       0.        , 0.03491509, 0.46601206])

[*zip(feature_name,clf.feature_importances_)]# 查看特征对应的重要性

[('酒精', 0.0),
 ('苹果酸', 0.0677658377725383),
 ('灰', 0.0),
 ('灰的碱性', 0.0),
 ('镁', 0.0),
 ('总酚', 0.0),
 ('类黄酮', 0.17665173372492327),
 ('非黄烷类酚类', 0.0),
 ('花青素', 0.0),
 ('颜色强度', 0.254655282950384),
 ('色调', 0.0),
 ('稀释葡萄酒', 0.03491508994608114),
 ('脯氨酸', 0.4660120556060733)]

通过增加参数random_state=int,splitter='random’优化过拟合

clf = tree.DecisionTreeClassifier(criterion='entropy'，
                                 random_state=30,
                                 splitter='random')

剪枝

• max_depth常从3开始尝试
• min_samples_leaf & min_sample_split 一般搭配max_depth使用，建议从5开始尝试
• max_features & min_impurity_decrease 强行设置分支时考虑的特征个数，超过限制的分支都会被舍弃，不是很推荐，想降维的话建议使用PCA、ICA等方法

# 该方法适用于二分类，可以快速绘制ROC曲线，但在该三分类问题上会报错
from sklearn.metrics import RocCurveDisplay
RocCurveDisplay.from_estimator(clf, xtest, ytest)

---------------------------------------------------------------------------

ValueError                                Traceback (most recent call last)

/tmp/ipykernel_19198/571040821.py in 
      1 from sklearn.metrics import RocCurveDisplay
----> 2 RocCurveDisplay.from_estimator(clf, xtest, ytest)


~/anaconda3/envs/pytorch/lib/python3.7/site-packages/sklearn/metrics/_plot/roc_curve.py in from_estimator(cls, estimator, X, y, sample_weight, drop_intermediate, response_method, pos_label, name, ax, **kwargs)
    233             estimator,
    234             response_method=response_method,
--> 235             pos_label=pos_label,
    236         )
    237 


~/anaconda3/envs/pytorch/lib/python3.7/site-packages/sklearn/metrics/_plot/base.py in _get_response(X, estimator, response_method, pos_label)
    107         if y_pred_shape != 2:
    108             raise ValueError(
--> 109                 f"{classification_error} fit on multiclass ({y_pred_shape} classes)"
    110                 " data"
    111             )


ValueError: Expected 'estimator' to be a binary classifier, but got DecisionTreeClassifier fit on multiclass (3 classes) data

#apply 返回每个测试样本所在的叶子结点的索引
clf.apply(xtest)

array([12,  6,  8,  3,  8,  3,  8,  3,  3,  3,  6, 12,  4,  3, 12,  3,  6,
        3, 11,  6,  6,  6, 12,  6,  3,  8,  3,  6,  8,  6,  3,  3, 12,  3,
        3, 12,  6, 12, 12,  6,  6, 10,  6,  8,  6,  6,  3, 12, 12,  3,  3,
        8, 12,  3])

#predict 返回每个测试样本的分类回归结果
clf.predict(xtest)

array([0, 2, 1, 1, 1, 1, 1, 1, 1, 1, 2, 0, 0, 1, 0, 1, 2, 1, 0, 2, 2, 2,
       0, 2, 1, 1, 1, 2, 1, 2, 1, 1, 0, 1, 1, 0, 2, 0, 0, 2, 2, 2, 2, 1,
       2, 2, 1, 0, 0, 1, 1, 1, 0, 1])