Last active
October 4, 2017 20:03
-
-
Save fedeisas/2562bee6354bbcaab2e48cdf62c789b8 to your computer and use it in GitHub Desktop.
Wordcloud de letras de canciones
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
# Cargo las librerias necesarias | |
library('rvest') # Para scrapear paginas | |
library('tm') # Text Mining | |
library('wordcloud') | |
library('RColorBrewer') # Paletas de colores | |
library('SnowballC') # Stemming | |
library('GetoptLong') # qq() permite interpolar strings | |
# Seteo locale para no tener problemas de acentos | |
Sys.setlocale('LC_CTYPE', 'en_US.UTF-8') | |
artist <- 'damas-gratis' | |
#artist <- 'patricio-rey-y-sus-redonditos-de-ricota' | |
url <- qq('https://www.letras.com/@{artist}/') | |
webpage <- read_html(url) | |
links <- html_nodes(webpage, '.cnt-list li a') | |
urls <- html_attr(links, 'href') | |
# Agrego el dominio a las URLs relativas | |
urls <- paste( | |
'https://www.letras.com', | |
urls[startsWith(urls, qq('/@{artist}/'))], | |
sep='' | |
) | |
# Dejar solo las URLs unicas | |
urls <- unique(urls) | |
# Tomar una muestra | |
urls <- sample(urls, 50) | |
# Bajar los documentos | |
documents <- lapply(urls, read_html) | |
# Extraigo la letra de cada documento | |
clean_articles <- sapply(documents, function (d) { | |
return( | |
html_text(html_node(d, '.cnt-letra article'), trim=TRUE) | |
) | |
}) | |
# Creo un corpus | |
corpus <- Corpus(VectorSource(clean_articles)) | |
# Convertir a minusculas | |
corpus <- tm_map(corpus, content_transformer(tolower)) | |
# Sacar numeros | |
corpus <- tm_map(corpus, removeNumbers) | |
# Sacar palabras comunes | |
corpus <- tm_map(corpus, removeWords, stopwords('spanish')) | |
# Sacar puntiacion | |
corpus <- tm_map(corpus, removePunctuation) | |
# Sacar espacios | |
corpus <- tm_map(corpus, stripWhitespace) | |
# Stemming | |
#corpus <- tm_map(corpus, stemDocument) | |
# Creo matriz de documentos | |
dtm <- TermDocumentMatrix(corpus) | |
m <- as.matrix(dtm) | |
# Frecuencias | |
v <- sort(rowSums(m), decreasing=TRUE) | |
# Creo un DF con las frecuencias de cada palabra | |
d <- data.frame(word = names(v), freq=v) | |
# Dibujo la nube de palabras | |
wordcloud(words = d$word, freq = d$freq, min.freq = 1, | |
max.words=200, random.order=FALSE, rot.per=0.35, | |
colors=brewer.pal(8, 'Dark2')) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment