:
#!/usr/bin/Rscript
library('tm')
library('wordcloud')
library('RColorBrewer')
twittercorpus <- system.file("stream","~/txt", package = "tm")
twittercorpus <- Corpus(DirSource("~/txt"),
readerControl=list(languageEl = "en"))
twittercorpus <- tm_map(twittercorpus, removeNumbers)
twittercorpus <- tm_map(twittercorpus,tolower)
twittercorpus <- tm_map(twittercorpus,removePunctuation)
my_stopwords <- c(stopwords("SMART"))
twittercorpus <-tm_map(twittercorpus,removeWords,my_stopwords)
mydata.dtm <- TermDocumentMatrix(twittercorpus)
내가 좋아하는 뭔가를해야합니다. 용도 :
freqmatrix <- findFreqTerms(mydata.dtm, lowfreq=mydata.dtm$nrow/100)