Difference between revisions of "R: ngram dan frekuensi-nya"
Jump to navigation
Jump to search
Onnowpurbo (talk | contribs) |
Onnowpurbo (talk | contribs) |
||
| (One intermediate revision by the same user not shown) | |||
| Line 3: | Line 3: | ||
library(tau) | library(tau) | ||
library(data.table) | library(data.table) | ||
| − | + | ||
createNgram <-function(stringVector, ngramSize){ | createNgram <-function(stringVector, ngramSize){ | ||
| Line 16: | Line 16: | ||
return(ngram) | 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 <- "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 <- createNgram(text, 2) | ||
res | res | ||
| + | # sort | ||
| + | res_sort <- res[order(-freq)] | ||
| + | res_sort | ||
| + | head(res_sort,n=50) | ||
Latest revision as of 08:22, 5 November 2018
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)