R 实现朴素贝叶斯算法

摘要: 朴素贝叶斯分类算法是一种常用的分类方法，应用非常广泛，譬如垃圾邮件判断，电子商务反作弊（作弊卖家等等）。 # 数据集来自Tom Mitchell's book "Machine Learning". #定义数据矩阵matrix，matrix(vector, nro ...

朴素贝叶斯分类算法是一种常用的分类方法，应用非常广泛，譬如垃圾邮件判断，电子商务反作弊（作弊卖家等等）。 # 数据集来自Tom Mitchell's book "Machine Learning". #定义数据矩阵matrix，matrix(vector, nrow=r, ncol=c, byrow=logical_value,  dimnames=list(char_vector_rownames, char_vector_colnames)) #nrow表示行数 #ncol表示列数 #byrow表示矩阵组织方式，按行或者按列 #dimnames表示行标识，列标识 data <- matrix(c("sunny","hot","high","weak","no",                  "sunny","hot","high","strong","no",                  "overcast","hot","high","weak","yes",                  "rain","mild","high","weak","yes",                  "rain","cool","normal","weak","yes",                  "rain","cool","normal","strong","no",                  "overcast","cool","normal","strong","yes",                  "sunny","mild","high","weak","no",                  "sunny","cool","normal","weak","yes",                  "rain","mild","normal","weak","yes",                  "sunny","mild","normal","strong","yes",                  "overcast","mild","high","strong","yes",                  "overcast","hot","normal","weak","yes",                  "rain","mild","high","strong","no"), byrow = TRUE,                dimnames = list(day = c(),                  condition = c("outlook","temperature",                    "humidity","wind","playtennis")), nrow=14, ncol=5);   #统计yes，no出现的概率                  prior.yes = sum(data[,5] == "yes") / length(data[,5]); prior.no = sum(data[,5] == "no") / length(data[,5]); #输入条件向量 ################################################### naive.bayes.prediction <- function(condition.vec) { ###################################################   # Calculate unnormlized posterior probability for playtennis = yes.   playtennis.yes <-     sum((data[,1] == condition.vec[1]) & (data[,5] == "yes")) / sum(data[,5] == "yes") * # P(outlook = f_1 | playtennis = yes)     sum((data[,2] == condition.vec[2]) & (data[,5] == "yes")) / sum(data[,5] == "yes") * # P(temperature = f_2 | playtennis = yes)     sum((data[,3] == condition.vec[3]) & (data[,5] == "yes")) / sum(data[,5] == "yes") * # P(humidity = f_3 | playtennis = yes)     sum((data[,4] == condition.vec[4]) & (data[,5] == "yes")) / sum(data[,5] == "yes") * # P(wind = f_4 | playtennis = yes)       prior.yes; # P(playtennis = yes)   # Calculate unnormlized posterior probability for playtennis = no.   playtennis.no <-     sum((data[,1] == condition.vec[1]) & (data[,5] == "no")) / sum(data[,5] == "no") * # P(outlook = f_1 | playtennis = no)     sum((data[,2] == condition.vec[2]) & (data[,5] == "no")) / sum(data[,5] == "no") * # P(temperature = f_2 | playtennis = no)     sum((data[,3] == condition.vec[3]) & (data[,5] == "no")) / sum(data[,5] == "no") * # P(humidity = f_3 | playtennis = no)     sum((data[,4] == condition.vec[4]) & (data[,5] == "no")) / sum(data[,5] == "no") * # P(wind = f_4 | playtennis = no)       prior.no; # P(playtennis = no)   return(list(post.pr.yes = playtennis.yes,               post.pr.no = playtennis.no,               prediction = ifelse(playtennis.yes >=                 playtennis.no, "yes", "no"))); } naive.bayes.prediction(c("rain","hot","high","strong")); naive.bayes.prediction(c("sunny","mild","normal","weak")); naive.bayes.prediction(c("overcast","mild","normal","weak"));   执行后，输出结果： > naive.bayes.prediction(c("rain","hot","high","strong")); $post.pr.yes [1] 0.005291005 $post.pr.no [1] 0.02742857 $prediction [1] "no" > naive.bayes.prediction(c("sunny","mild","normal","weak")); $post.pr.yes [1] 0.02821869 $post.pr.no [1] 0.006857143 $prediction [1] "yes" > naive.bayes.prediction(c("overcast","mild","normal","weak")); $post.pr.yes [1] 0.05643739 $post.pr.no [1] 0 $prediction [1] "yes" 本文转载自：http://blog.sina.com.cn/s/blog_61c4630901013qoj.html