Created
May 13, 2016 13:09
-
-
Save leobarone/866c044d5db1e8adf352f85bf78a901c to your computer and use it in GitHub Desktop.
Wordcloud ponte para o futuro
This file contains 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(tm) | |
| library(SnowballC) | |
| library(wordcloud) | |
| getwd() | |
| pdfToText <- function(arquivo){ | |
| texto <- readPDF(control = list(text = "-layout"))(elem = list(uri = arquivo), | |
| language = "pt", id = "id1") | |
| texto <- as.character(texto) | |
| return(texto) | |
| } | |
| download.file("http://pmdb.org.br/wp-content/uploads/2015/10/RELEASE-TEMER_A4-28.10.15-Online.pdf", "~/ponte.pdf") | |
| texto <- pdfToText("ponte.pdf") | |
| dir.create("ponte") | |
| writeLines(texto, "~/ponte/ponte.txt") | |
| file.remove("ponte.pdf") | |
| ponteCorpus <- VCorpus(DirSource("~/ponte"), readerControl = list(language = "por")) | |
| inspect(ponteCorpus) | |
| ponteCorpus <- tm_map(ponteCorpus, stripWhitespace) | |
| ponteCorpus <- tm_map(ponteCorpus, content_transformer(tolower)) | |
| ponteCorpus <- tm_map(ponteCorpus, removeWords, stopwords("portuguese")) | |
| ponteCorpus <- tm_map(ponteCorpus, removePunctuation) | |
| ponteCorpus <- tm_map(ponteCorpus, removeNumbers) | |
| as.character(ponteCorpus[[1]]) | |
| wordcloud(ponteCorpus, max.words = 100, random.order = FALSE) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment