R: tidytext RPJP BAPPENAS

library(tidyverse)
library(tidytext)
library(tm)
directory <- "data-pdf"

# create corpus from pdfs
converted <- VCorpus(DirSource(directory), readerControl = list(reader = readPDF)) %>% 
  DocumentTermMatrix()

converted %>%
  tidy() %>%
  filter(!grepl("[0-9]+", term))
# converted adalah DocumentTermMatrix

docs <- VCorpus(DirSource("data", recursive=TRUE))
# Get the document term matrices
BigramTokenizer <- function(x) NGramTokenizer(x, Weka_control(min = 2, max = 2))
dtm_unigram <- DocumentTermMatrix(docs, control = list(tokenize="words", 
    removePunctuation = TRUE, 
    stopwords = stopwords("english"), 
    stemming = TRUE))
dtm_bigram <- DocumentTermMatrix(docs, control = list(tokenize = BigramTokenizer,
    removePunctuation = TRUE,
    stopwords = stopwords("english"),
    stemming = TRUE))

inspect(dtm_unigram)
inspect(dtm_bigram)

Pranala Menarik

• R