Difference between revisions of "R: tidytext RPJP BAPPENAS"
Jump to navigation
Jump to search
Onnowpurbo (talk | contribs) |
Onnowpurbo (talk | contribs) |
||
| Line 12: | Line 12: | ||
tidy() %>% | tidy() %>% | ||
filter(!grepl("[0-9]+", term)) | filter(!grepl("[0-9]+", term)) | ||
| + | # converted adalah DocumentTermMatrix | ||
| + | |||
| + | |||
| + | |||
| + | original_converted <- converted %>% | ||
| + | group_by(document) %>% | ||
| + | ungroup() | ||
| + | original_converted | ||
Revision as of 12:29, 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))
# converted adalah DocumentTermMatrix
original_converted <- converted %>% group_by(document) %>% ungroup() original_converted