（实战）Stacking和Voting介绍与使用

Stacking

from sklearn import datasets  
from sklearn import model_selection  
from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier  
from sklearn.tree import DecisionTreeClassifier
from mlxtend.classifier import StackingClassifier # pip install mlxtend
import numpy as np  

# 载入数据集
iris = datasets.load_iris()  
# 只要第1,2列的特征
x_data, y_data = iris.data[:, 1:3], iris.target  

# 定义三个不同的分类器
clf1 = KNeighborsClassifier(n_neighbors=1)  #KNN
clf2 = DecisionTreeClassifier() #决策树
clf3 = LogisticRegression()  #逻辑回归
 
# 定义一个次级分类器
lr = LogisticRegression()  
#调用stacking的分类器
sclf = StackingClassifier(classifiers=[clf1, clf2, clf3],   
                          meta_classifier=lr)

#将每个分类器和它的名字做一个打包  
for clf,label in zip([clf1, clf2, clf3, sclf],
                      ['KNN','Decision Tree','LogisticRegression','StackingClassifier']):
    #cv=3训练集分成3个部分，一个部分作为测试集，两个部分作为训练集
    scores = model_selection.cross_val_score(clf, x_data, y_data, cv=3, scoring='accuracy')  
    print("Accuracy: %0.2f [%s]" % (scores.mean(), label)) 

Voting

跟上面不同的是，它没有次级分类器，是进行投票，结果比较高的那个做出结果。

投票还是根据权重来取训练结果，并不是完全相信某个分类器

from sklearn import datasets  
from sklearn import model_selection  
from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier  
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import VotingClassifier #投票的分类器
import numpy as np

# 载入数据集
iris = datasets.load_iris()  
# 只要第1,2列的特征
x_data, y_data = iris.data[:, 1:3], iris.target  

# 定义三个不同的分类器
clf1 = KNeighborsClassifier(n_neighbors=1)  
clf2 = DecisionTreeClassifier() 
clf3 = LogisticRegression()  

#list里面的每队元组，都是名字与算法一一对应
sclf = VotingClassifier([('knn',clf1),('dtree',clf2), ('lr',clf3)])   


for clf, label in zip([clf1, clf2, clf3, sclf],
                      ['KNN','Decision Tree','LogisticRegression','VotingClassifier']):  
  
    scores = model_selection.cross_val_score(clf, x_data, y_data, cv=3, 
                                             scoring='accuracy')  
    print("Accuracy: %0.2f [%s]" % (scores.mean(), label))