mozilla-text.R

library(tm)  

docs = Corpus(VectorSource(places$title))
docs <- tm_map(docs, removePunctuation) 
docs <- tm_map(docs, tolower) 
docs <- tm_map(docs, removeWords, c("bad","words"))
docs <- tm_map(docs, removeWords, stopwords("english")) 
docs <- tm_map(docs, stripWhitespace)  
docs <- tm_map(docs, PlainTextDocument) 

dtm <- DocumentTermMatrix(docs)  
freq <- sort(colSums(as.matrix(dtm)), decreasing=TRUE)   
head(freq, 14) 

wf <- data.frame(word=names(freq), freq=freq)