R实战：【统计分析】词频统计

R实战系列专栏

setwd("D:/R/")
getwd()
txt<-scan("OliverTwist.txt","") #read all words in file to txt
wl<-list()
for(i in 1:length(txt))
{
wrd<-txt[i]
wl[[wrd]]<-c(wl[[wrd]],i) # for every word create a list with location list
}
nms<-names(wl)
sn<-sort(nms)
#wl[sn]
freqs<-sapply(wl,length) #for every element use length() ,and result is c([[i]] length)
wlOrder<-wl[order(freqs)]
index<-(length(wlOrder)-10):length(wlOrder)
top10<-wlOrder[index]
sapply(top10,length)
barplot(sapply(top10,length))