I am using the tm and wordcloud packages in R 2.15.1. I am trying to make a word cloud Here is the code:
maruti_tweets = userTimeline("Maruti_suzuki", n=1000,cainfo="cacert.pem")
hyundai_tweets = userTimeline("HyundaiIndia", n=1000,cainfo="cacert.pem")
tata_tweets = userTimeline("TataMotor", n=1000,cainfo="cacert.pem")
toyota_tweets = userTimeline("Toyota_India", n=1000,cainfo="cacert.pem")
# get text
maruti_txt = sapply(maruti_tweets, function(x) x$getText())
hyundai_txt = sapply(hyundai_tweets, function(x) x$getText())
tata_txt = sapply(tata_tweets, function(x) x$getText())
toyota_txt = sapply(toyota_tweets, function(x) x$getText())
clean.text = function(x)
{
# tolower
x = tolower(x)
# remove rt
x = gsub("rt", "", x)
# remove at
x = gsub("@\\w+", "", x)
# remove punctuation
x = gsub("[[:punct:]]", "", x)
# remove numbers
x = gsub("[[:digit:]]", "", x)
# remove links http
x = gsub("http\\w+", "", x)
# remove tabs
x = gsub("[ |\t]{2,}", "", x)
# remove blank spaces at the beginning
x = gsub("^ ", "", x)
# remove blank spaces at the end
x = gsub(" $", "", x)
return(x)
}
# clean texts
maruti_clean = clean.text(maruti_txt)
hyundai_clean = clean.text(hyundai_txt)
tata_clean = clean.text(tata_txt)
toyota_clean = clean.text(toyota_txt)
maruti = paste(maruti_clean, collapse=" ")
hyundai= paste(hyundai_clean, collapse=" ")
tata= paste(tata_clean, collapse=" ")
toyota= paste(toyota_clean, collapse=" ")
# put ehyundaiything in a single vector
all = c(maruti, hyundai, tata, toyota)
# remove stop-words
all = removeWords(all,
c(stopwords("english"), "maruti", "tata", "hyundai", "toyota"))
# create corpus
corpus = Corpus(VectorSource(all))
# create term-document matrix
tdm = TermDocumentMatrix(corpus)
# convert as matrix
tdm = as.matrix(tdm)
# add column names
colnames(tdm) = c("MARUTI", "HYUNDAI", "TATA", "TOYOTA")
# comparison cloud
comparison.cloud(tdm, random.order=FALSE,colors = c("#00B2FF", "red", #FF0099","#6600CC"),max.words=500)
but getting following error
Error in strwidth(words[i], cex = size[i], ...) : invalid 'cex' value
please help
You have a typo in TataMotors twitter account. It should be spelled 'TataMotors', not 'TataMotor'. As a result, one column in your term matrix is empty and when cex is calculated it get assigned NAN.
Fix the typo and the rest of the code works fine. Good luck!