VotingClassifier用法

"""
一、Hard Voting 与 Soft Voting 的对比
1）使用方式
voting = 'hard'：表示最终决策方式为 Hard Voting Classifier；
voting = 'soft'：表示最终决策方式为 Soft Voting Classifier；
 

2）思想
Hard Voting Classifier：根据少数服从多数来定最终结果；
Soft Voting Classifier：将所有模型预测样本为某一类别的概率的平均值作为标准，概率最高的对应的类型为最终的预测结果；

"""

import numpy as np
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier

from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import VotingClassifier
from xgboost import XGBClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC
from sklearn.model_selection import train_test_split
from sklearn.datasets import make_moons
from sklearn.metrics import accuracy_score,roc_auc_score
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import StratifiedKFold

iris = datasets.load_iris()

x=iris.data
y=iris.target
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.3)

clf1 = XGBClassifier(learning_rate=0.1, n_estimators=150, max_depth=3, min_child_weight=2, subsample=0.7,
                     colsample_bytree=0.6, objective='binary:logistic')
clf2 = RandomForestClassifier(n_estimators=50, max_depth=1, min_samples_split=4,
                              min_samples_leaf=63,oob_score=True)
clf3 = SVC(C=0.1)

# 硬投票
eclf = VotingClassifier(estimators=[('xgb', clf1), ('rf', clf2), ('svc', clf3)], voting='hard')
for clf, label in zip([clf1, clf2, clf3, eclf], ['XGBBoosting', 'Random Forest', 'SVM', 'Ensemble']):
    scores = cross_val_score(clf, x, y, cv=5, scoring='accuracy')
    print("Accuracy: %0.2f (+/- %0.2f) [%s]" % (scores.mean(), scores.std(), label))

结果：
Accuracy: 0.96 (+/- 0.02) [XGBBoosting]
Accuracy: 0.33 (+/- 0.00) [Random Forest]
Accuracy: 0.92 (+/- 0.03) [SVM]
Accuracy: 0.92 (+/- 0.03) [Ensemble]

x=iris.data
y=iris.target
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.3)

clf1 = XGBClassifier(learning_rate=0.1, n_estimators=150, max_depth=3, min_child_weight=2, subsample=0.8,
                     colsample_bytree=0.8, objective='binary:logistic')
clf2 = RandomForestClassifier(n_estimators=50, max_depth=1, min_samples_split=4,
                              min_samples_leaf=63,oob_score=True)
clf3 = SVC(C=0.1, probability=True)

# 软投票
eclf = VotingClassifier(estimators=[('xgb', clf1), ('rf', clf2), ('svc', clf3)], voting='soft', weights=[2, 1, 1])
clf1.fit(x_train, y_train)

for clf, label in zip([clf1, clf2, clf3, eclf], ['XGBBoosting', 'Random Forest', 'SVM', 'Ensemble']):
    scores = cross_val_score(clf, x, y, cv=5, scoring='accuracy')
    print("Accuracy: %0.2f (+/- %0.2f) [%s]" % (scores.mean(), scores.std(), label))

结果：
Accuracy: 0.96 (+/- 0.02) [XGBBoosting]
Accuracy: 0.33 (+/- 0.00) [Random Forest]
Accuracy: 0.92 (+/- 0.03) [SVM]
Accuracy: 0.96 (+/- 0.02) [Ensemble]