Created
July 5, 2016 19:44
-
-
Save ottlngr/c8cac68997abe8875ce4f4d5fdc7d996 to your computer and use it in GitHub Desktop.
Make a wordcloud straight from a .tex file using R
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| library(stringr) | |
| library(tm) | |
| library(wordcloud) | |
| library(SnowballC) | |
| file <- "./file.tex" | |
| txt <- readChar(file, file.info(file)$size) | |
| txt <- str_replace_all(txt, "\\n", " ") | |
| txt <- str_replace_all(txt, "\\\\documentclass.*\\}.*\\\\begin\\{document\\}", "") | |
| txt <- str_replace_all(txt, "\\\\[a-zA-Z]*\\s", "") | |
| txt <- str_replace_all(txt, "\\\\[a-zA-Z]*\\{.*?\\}", "") | |
| txt <- str_replace_all(txt, "\\{.*?\\}", "") | |
| txt <- str_replace_all(txt, "\\s[^a-zA-Z0-9]*\\s", "") | |
| txt <- str_replace_all(txt, "[^a-zA-Z\\s]", "") | |
| cor <- Corpus(VectorSource(txt)) | |
| cor <- tm_map(cor, stripWhitespace) | |
| cor <- tm_map(cor, removeWords, stopwords("english")) | |
| cor <- tm_map(cor, tolower) | |
| cor <- tm_map(cor, stemDocument) | |
| cor <- tm_map(cor, PlainTextDocument) | |
| wordcloud(cor) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment