sklearn代码12 2-决策树的使用及原理

import numpy as np

from sklearn.tree import DecisionTreeClassifier

from sklearn import datasets

import matplotlib.pyplot as plt
%matplotlib inline

from sklearn import tree

from sklearn.model_selection import train_test_split

iris = datasets.load_iris()

X = iris['data']

y = iris['target']

feature_names = iris.feature_names

X_train,X_test,y_train,y_test = train_test_split(X,y,test_size = 0.2,random_state = 1024)

# 数据清洗,即X,y

# 特征工程

# 使用模型进行训练

# 模型参数调优

# sklearn所有算法封装好了
# 直接用,使用规则如下

clf = DecisionTreeClassifier(criterion='entropy')

clf.fit(X_train,y_train)

y_ = clf.predict(X_test)

from sklearn.metrics import accuracy_score

accuracy_score(y_test,y_)

1.0

39/120*np.log2(120/39)+42/120*np.log2(120/42)+39/120*np.log2(120/39)

1.5840680553754911

42/81*np.log2(81/42)+ 39/81*np.log2(81/39)

0.99901027088048133

# 调整大小
plt.figure(figsize=(18,12))
_ = tree.plot_tree(clf,filled=True,feature_names=feature_names)   #绘制树形图 filled调整颜色
plt.savefig('./tree.jpg')

%%time
clf = DecisionTreeClassifier(criterion='gini',max_depth=2)  #深度为1

clf.fit(X_train,y_train)

y_ = clf.predict(X_test)

from sklearn.metrics import accuracy_score

print(accuracy_score(y_test,y_))

plt.figure(figsize=(18,12))

_ = tree.plot_tree(clf,filled=True,feature_names=feature_names)

0.966666666667
Wall time: 45.9 ms

$$\sum _{i=0}^{n}p(xi)\ast (1-p(xi))$$

# 39/120*(1- 39/120)
39/120*(1 -39/120)*2+42/120*(1-42/120)

0.66625