sklearn中的朴素贝叶斯模型及其应用
1.使用朴素贝叶斯模型对iris数据集进行花分类
尝试使用3种不同类型的朴素贝叶斯:
高斯分布型
多项式型
伯努利型
2.使用sklearn.model_selection.cross_val_score(),对模型进行验证。
#高斯模型验证 from sklearn.naive_bayes import GaussianNB from sklearn.model_selection import cross_val_score gnb=GaussianNB() scores=cross_val_score(gnb,iris.data,iris.target,cv=10) print("Accuracy:%.3f"%scores.mean()) #多项式模型验证 from sklearn.naive_bayes import MultinomialNB from sklearn.model_selection import cross_val_score gnb=MultinomialNB() scores=cross_val_score(gnb,iris.data,iris.target,cv=10) print("Accuracy:%.3f"%scores.mean()) #伯努利模型验证 from sklearn.naive_bayes import BernoulliNB from sklearn.model_selection import cross_val_score gnb=BernoulliNB() scores=cross_val_score(gnb,iris.data,iris.target,cv=10) print("Accuracy:%.3f"%scores.mean())
运行截图
import csv file_path=r'F:SMSSpamCollectionjs.txt' sms=open(file_path,'r',encoding='utf-8') sms_data=[] sms_label=[] csv_reader=csv.reader(sms,delimiter='\t') for line in csv_reader: sms_label.append(line[0]) sms_data.append(line[1]) sms.close() sms_label sms_data=str(sms_data) sms_data=sms_data.lower() sms_data=sms_data.split() sms_newdata=[] i=0 #去掉长度小于3的词 for i in sms_data: if len(i)>4: sms_newdata.append(i) continue sms_newdata
截图