使用交叉验证选择决策树预剪枝参数 max_depth

决策树树模型

MachineLearning exercises

Publish Date: 2021-02-15

Update Date: 2021-02-19

Word Count: 365

Read Times: 1 Min

Read Count:

max_depth 限制树的最大深度，超过设定深度的树枝全部剪掉。

准备数据

from sklearn import tree
from sklearn.datasets import load_wine
from sklearn.model_selection import train_test_split
wine = load_wine()
Xtrain, Xtest, Ytrain, Ytest = train_test_split(wine.data,wine.target,test_size=0.3)
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','od280/od315稀释葡萄酒','脯氨酸’]

训练模型

默认参数模型准确率

clf = tree.DecisionTreeClassifier(criterion="entropy"
                                    ,random_state=30
                                    ,splitter="random"
                                    )
clf = clf.fit(Xtrain, Ytrain)
score = clf.score(Xtest, Ytest)
print(score)

0.88

默认 max_depth 生成决策树

import graphviz
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

max_depth=3 生成决策树

clf = tree.DecisionTreeClassifier(criterion="entropy"
                                    ,random_state=30
                                    ,splitter="random"
                                    ,max_depth=3
                                #    ,min_samples_leaf=10
                                #    ,min_samples_split=25
                                    )
clf = clf.fit(Xtrain, Ytrain)
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

交叉验证学习曲线

import matplotlib.pyplot as plt
test = []
for i in range(10):
    clf = tree.DecisionTreeClassifier(max_depth=i+1
                                    ,criterion="entropy"
                                    ,random_state=30
                                    ,splitter="random"
                                    )
    clf = clf.fit(Xtrain, Ytrain)
    score = clf.score(Xtest, Ytest)
    test.append(score)
plt.plot(range(1,11),test,color="red",label="max_depth")
plt.legend()
plt.show()

交叉验证学习曲线

import matplotlib.pyplot as plt
test = []
for i in range(10):
    clf = tree.DecisionTreeClassifier(max_depth=i+1
                                    ,criterion="entropy"
                                    ,random_state=30
                                    ,splitter="random"
                                    )
    clf = clf.fit(Xtrain, Ytrain)
    score = clf.score(Xtest, Ytest)
    test.append(score)
plt.plot(range(1,11),test,color="red",label="max_depth")
plt.legend()
plt.show()

max_depth=3 时模型准确率

clf = tree.DecisionTreeClassifier(criterion="entropy",
                                    max_depth=3
                                    ,random_state=30
                                    ,splitter="random"
                                    )
clf = clf.fit(Xtrain, Ytrain)
score = clf.score(Xtest, Ytest)
score