机器学习

原文摘录   · · · · · ·  ( 全部 )

• # Simply returns the full text of a given email message # 获取邮件全部（每行）信息 msg.full <- function(path) { con <- file(path, open = "rt", encoding = "latin1") msg <- readLines(con) close(con) return(msg) } # Retuns the email address of the sender for a given # email message # 获得邮件寄信人信息 get.from <- function(msg.vec) { from <- msg.vec[grepl("From: ", msg.vec)] from <- strsplit(from, '[":<> ]')[[1]] from <- from[which(from != "" & from != " ")] return(from[grepl("@", from)][1]) } # Retuns the subject string for a given email message # 获得邮件主题 get.subject <- function(msg.vec) { subj <- msg.vec[grepl("Subject: ", msg.vec)] if(length(subj) > 0) { return(strsplit(subj, "Subject: ")[[1]][2]) } else { return("") } } # Similar to the function from Chapter 3, this re... (查看原文)

  windy guo 2015-06-24 09:40:33

• # here is to use the 're:' cue from the subject line to identify message threads. find.threads <- function(email.df) { response.threads <- strsplit(email.df$Subject, "re: ") #1 is.thread <- sapply(response.threads, function(subj) ifelse(subj[1] == "", TRUE, FALSE)) #2 threads <- response.threads[is.thread] #3 senders <- email.df$From.EMail[is.thread] #4 threads <- sapply(threads, function(t) paste(t[2:length(t)], collapse = "re: ")) #5 return(cbind(senders,threads)) #6 } (查看原文)

  windy guo 2015-06-24 09:40:33

> 全部原文摘录