R: tidytext RPJP BAPPENAS: Difference between revisions

From OnnoCenterWiki
Jump to navigationJump to search
Onnowpurbo (talk | contribs)
Created page with " install.packages("pdftools") library(pdftools) rpjp2005 <- pdf_text("RPJP_2005-2025.pdf") %>% strsplit(split = "\n") original_rpjp2005 <- rpjp2005 %>% group_by(book..."
 
Onnowpurbo (talk | contribs)
No edit summary
Line 1: Line 1:


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))


install.packages("pdftools")
library(pdftools)
rpjp2005 <- pdf_text("RPJP_2005-2025.pdf") %>% strsplit(split = "\n")
original_rpjp2005 <- rpjp2005 %>%
  group_by(book) %>%
  mutate(linenumber = row_number(),
          chapter = cumsum(str_detect(text, regex("^chapter [\\divxlc]",
                                                  ignore_case = TRUE)))) %>%
  ungroup()
original_books





Revision as of 04:36, 6 November 2018

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))


Pranala Menarik