corpus <- Corpus(VectorSource(data$text[1:3030]))
corpus <- tm_map(corpus, content_transformer(removePunctuation)) #quitar puntuacion
corpus <- tm_map(corpus, content_transformer(removeWords), stopwords("english")) #quitar stop words
corpus <- tm_map(corpus, removeWords, c("NUMBER","CITATION","FORMULA")) #quitar estas palabras en especifico
corpus <- tm_map(corpus, content_transformer(tolower)) #aplicamos minusculas
corpus <- tm_map(corpus, stemDocument) #dejamos la raiz de las palabras
corpus <- tm_map(corpus, stripWhitespace) #quitamos los espacios
corpus <- tm_map(corpus, content_transformer(removeNumbers)) #quitamos numeros
# corpus <- tm_map(corpus, PlainTextDocument)