本文共 1700 字，大约阅读时间需要 5 分钟。

#补集朴素贝叶斯-多项式朴素贝叶斯的补充，所以也是要求特征是离散的，非连续型from sklearn.naive_bayes import ComplementNBfrom time import timeimport datetime#探索补集朴素贝叶斯在不平衡数据中的处理#探索样本不均衡问题from sklearn.preprocessing import KBinsDiscretizerfrom sklearn.datasets import make_blobsfrom sklearn.naive_bayes import GaussianNB,MultinomialNB,BernoulliNBfrom sklearn.model_selection import train_test_splitfrom sklearn.metrics import brier_score_loss as bs,recall_score,roc_auc_score as auc#创建数据集class1=50000class2=500centers=[[0.0,0.0],[5.0,5.0]]std=[3,1]X,y=make_blobs(n_samples=[class1,class2names=["Multinomial","Gaussian","Bernoulli","Complement"]models=[MultinomialNB(),GaussianNB(),BernoulliNB(),ComplementNB()]for clf,name in zip(models,names):    times=time()    Xtrain,Xtest,ytrain,ytest=train_test_split(X,y,test_size=0.3,random_state=420)    if name!="Gaussian":        kbs=KBinsDiscretizer(n_bins=10,encode="onehot").fit(Xtrain)        Xtrain=kbs.transform(Xtrain)        Xtest=kbs.transform(Xtest)    clf.fit(Xtrain,ytrain)    y_pred=clf.predict(Xtest)    proba=clf.predict_proba(Xtest)[:,1]    score=clf.score(Xtest,ytest)    print(name)    print("\tBrier:{:.3f}".format(bs(ytest,proba,pos_label=1)))    print("\tAccuracy:{:.3f}".format(score))    print("\tRecall:{:.3f}".format(recall_score(ytest,y_pred)))    print("\tAUC:{:.3f}".format(auc(ytest,proba)))    print(datetime.datetime.fromtimestamp(time()-times).strftime("%M:%S:%f"))],              centers=centers,              cluster_std=std,              random_state=0,              shuffle=False)

在这里插入代码片

转载地址：http://ptrmz.baihongyu.com/