Last active
October 6, 2017 13:14
-
-
Save fedeisas/854a7de57b735baf8c97fde55ab0e404 to your computer and use it in GitHub Desktop.
Wordcloud con búsqueda de tweets
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
| # Librerias requeridas | |
| library('httr') | |
| library('jsonlite') | |
| library('tm') | |
| library('wordcloud') | |
| library('RColorBrewer') | |
| library("SnowballC") | |
| # Keys de acceso (https://apps.twitter.com/) | |
| # Cómo creo una app de Twitter: https://www.digitalocean.com/community/tutorials/how-to-create-a-twitter-app | |
| consKey <- "I4YzkwOtWfdnSwuhxzIw" | |
| consSecret <- "x9yy0SSPfstfIruterpNysda4HcAwXEPO3Foak3mdY" | |
| token <- "21232107-EGlObzhxRvqnnljexKhekANQM1lF0PY4uqAurs0Cj" | |
| tokenSecret <- "YPC4Rt7aa9tN8HdMDwanuyUnmWYuggBCsuGPTc299ITBb" | |
| # Twitter utiliza OAuth para autenticar | |
| myapp = oauth_app("twitter", key=consKey, secret=consSecret) | |
| # Me autentico y consigo una signature | |
| sig = sign_oauth1.0(myapp, token=token, token_secret=tokenSecret) | |
| # Consulto la API, traigo 100 tweets de algun topico | |
| query <- 'messi' | |
| search_url <- paste( | |
| 'https://api.twitter.com/1.1/search/tweets.json?count=100&lang=es&q=', | |
| query, | |
| sep='' | |
| ) | |
| result <- GET(search_url, sig) | |
| # Parseo el resultado de JSON | |
| json1 = httr::content(result) | |
| json2 = jsonlite::fromJSON(toJSON(json1)) | |
| statuses <- json2$statuses | |
| tweets <- unlist(statuses$text) | |
| # Elimino las URLs | |
| tweets <- gsub('(f|ht)tp\\S+\\s*', '', tweets) | |
| # Elimino los @arrobas | |
| tweets <- gsub('@\\S+\\s*', '', tweets) | |
| # Creo un corpus | |
| corpus <- Corpus(VectorSource(tweets)) | |
| # 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) | |
| # Sacar la consulta original | |
| corpus <- tm_map(corpus, removeWords, unlist(strsplit(query, " "))) | |
| # 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 = 2, | |
| 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