R: tidytext RPJP BAPPENAS
Revision as of 12:29, 6 November 2018 by Onnowpurbo (talk | contribs)
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
original_converted <- converted %>% group_by(document) %>% ungroup() original_converted