Difference between revisions of "R: tidytext RPJP BAPPENAS"
Jump to navigation
Jump 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) |
||
| 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)) | ||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
Revision as of 11:36, 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))