j集成学习

from sklearn.ensemble import VotingClassifier 少数服从多数投票方法的集成分类器

# 导入数据 iris鸢尾花数据

import numpy as np

import warnings ##提醒函数变动的，所以在视频演示中过滤掉

from sklearn import datasets

warnings.filterwarnings("ignore")

iris = datasets.load_iris()

X, y = iris.data[:, 1:3], iris.target

from sklearn import cross_validation

from sklearn.linear_model import LogisticRegression

from sklearn.naive_bayes import GaussianNB

from sklearn.ensemble import RandomForestClassifier

np.random.seed(21)

clf1 = LogisticRegression()

clf2 = RandomForestClassifier()

clf3 = GaussianNB()

print('5折交叉验证:\n')

##zip函数中将对象中元素打包成元祖

for clf, label in zip([clf1, clf2, clf3], ['逻辑回归', '随机森林', '朴素贝叶斯']):

    scores = cross_validation.cross_val_score(clf, X, y, cv=5, scoring='accuracy')

    print("准确率: %0.2f (+/- %0.2f) [%s]" % (scores.mean(), scores.std(), label))

from sklearn.ensemble import VotingClassifier

np.random.seed(21)

eclf1 = VotingClassifier(

    estimators=[('逻辑回归', clf1), ('随机森林', clf2), ('朴素贝叶斯', clf3)], voting='soft')

scores = cross_validation.cross_val_score(eclf1, X, y, cv=5, scoring='accuracy')

print("准确率: %0.2f (+/- %0.2f) [%s]" % (scores.mean(), scores.std(), label))