R: ngram dan frekuensi-nya

From OnnoWiki
Revision as of 08:22, 5 November 2018 by Onnowpurbo (talk | contribs)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search


library(tau) 
library(data.table)


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."
#
text <- readtext("out.txt")
res <- createNgram(text, 2)
res
# sort
res_sort <- res[order(-freq)]
res_sort
head(res_sort,n=50)


Pranala Menarik