R: ngram dan frekuensi-nya
Revision as of 07:38, 5 November 2018 by Onnowpurbo (talk | contribs) (Created page with " library(tau) library(data.table) # given a string vector and size of ngrams this function returns word ngrams with corresponding frequencies createNgram <-function...")
library(tau) library(data.table) # given a string vector and size of ngrams this function returns word ngrams with corresponding frequencies
createNgram <-function(stringVector, ngramSize){
ngram <- data.table()
ng <- textcnt(stringVector, method = "string", n=ngramSize, tolower = FALSE)
if(ngramSize==1){
ngram <- data.table(w1 = names(ng), freq = unclass(ng), length=nchar(names(ng)))
}
else {
ngram <- data.table(w1w2 = names(ng), freq = unclass(ng), length=nchar(names(ng)))
}
return(ngram)
}
text <- "This is my little R text example and I want to count the frequency of some pattern (and - is - my - of). This is my little R text example and I want to count the frequency of some patter." res <- createNgram(text, 2) res