Created
May 16, 2012 14:21
-
-
Save timelyportfolio/2710706 to your computer and use it in GitHub Desktop.
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
require(twitteR) | |
require(ggplot2) | |
#get CFA12 tweets for exploration | |
#appears to limit n to 1500 | |
cfatweets.1 <- searchTwitter("#cfa12", n=1500, since="2012-05-04",until="2012-05-07") | |
cfatweets.2 <- searchTwitter("#cfa12", n=1500, since="2012-05-07",until="2012-05-08") | |
cfatweets.3 <- searchTwitter("#cfa12", n=1500, since="2012-05-08",until="2012-05-15") | |
cfatweets.df <- rbind( | |
twListToDF(cfatweets.1), | |
twListToDF(cfatweets.2), | |
twListToDF(cfatweets.3)) | |
tweeter <- as.data.frame(table(cfatweets.df$screenName),stringsAsFactors=FALSE) | |
colnames(tweeter) <- c("tweeter","count") | |
o <- order(tweeter$count,decreasing=TRUE)[1:50] | |
tweeter.ranked <- tweeter[o,] | |
tweeter.ranked$tweeter <- reorder(x=tweeter.ranked$tweeter,X=tweeter.ranked$count) | |
#credit for these charts goes to | |
#http://isomorphismes.tumblr.com/post/20362455367/twitter | |
ggplot(data=tweeter.ranked, | |
aes(y=count, x=tweeter, fill=tweeter)) + | |
geom_bar(stat="identity") + coord_flip() + | |
geom_text(aes(x=tweeter,y=0,label=paste("@",tweeter," ",count,sep=""),size=1,hjust=0)) + | |
theme_bw() + | |
opts(title="Prolific #cfa12 Tweeters", legend.position="none", | |
axis.text.y = theme_blank(), axis.ticks = theme_blank(), axis.title.y = theme_blank() ) | |
ggplot(data=tweeter.ranked, | |
aes(y=count, x=tweeter, fill=tweeter)) + coord_polar() + | |
geom_bar(stat="identity") + #coord_flip() + | |
theme_bw() + | |
opts(title="Prolific #cfa12 Tweeters", legend.position="none", | |
axis.title.y = theme_blank() ) | |
ggplot(data=cfatweets.df,aes(x=created,fill=format(cfatweets.df$created,"%Y-%m-%d"))) + | |
geom_density() + theme_bw() + | |
opts(title="#cfa12 Tweets by Time", legend.position="none", | |
axis.title.y = theme_blank() ) | |
######################do word cloud############################# | |
#all credit goes to http://blog.ouseful.info/2012/02/15/generating-twitter-wordclouds-in-r-prompted-by-an-open-learning-blogpost/ | |
#thanks for the very fine example | |
#Use a handy helper function to put the tweets into a dataframe | |
tw.df=cfatweets.df$text | |
##Note: there are some handy, basic Twitter related functions here: | |
##https://github.com/matteoredaelli/twitter-r-utils | |
#For example: | |
RemoveAtPeople <- function(tweet) { | |
gsub("@\\w+", "", tweet) | |
} | |
RemoveHash <- function(tweet) { | |
gsub("#\\w+", "", tweet) | |
} | |
#Then for example, remove @'d names | |
tweets <- as.vector(RemoveAtPeople(tw.df)) | |
tweets <- as.vector(RemoveHash(tweets)) | |
##Wordcloud - scripts available from various sources; I used: | |
#http://rdatamining.wordpress.com/2011/11/09/using-text-mining-to-find-out-what-rdatamining-tweets-are-about/ | |
#Install the textmining library | |
require(tm) | |
#Call with eg: tw.c=generateCorpus(tw.df$text) | |
generateCorpus= function(df,my.stopwords=c()){ | |
#The following is cribbed and seems to do what it says on the can | |
tw.corpus= Corpus(VectorSource(df)) | |
# remove punctuation | |
tw.corpus = tm_map(tw.corpus, removePunctuation) | |
#normalise case | |
tw.corpus = tm_map(tw.corpus, tolower) | |
# remove stopwords | |
tw.corpus = tm_map(tw.corpus, removeWords, stopwords('english')) | |
tw.corpus = tm_map(tw.corpus, removeWords, my.stopwords) | |
tw.corpus | |
} | |
twCorpus <- generateCorpus(tweets) | |
tdm <- TermDocumentMatrix(twCorpus) | |
m <- as.matrix(tdm) | |
v <- sort(rowSums(m),decreasing=TRUE) | |
d <- data.frame(word = names(v),freq=v) | |
require(wordcloud) | |
#wordcloud(d$word,d$freq,min.freq=5) | |
##### with colors ##### | |
if(require(RColorBrewer)){ | |
pal <- brewer.pal(9,"BuGn") | |
pal <- pal[-(1:4)] | |
wordcloud(d$word,d$freq,c(2,.5),min.freq=10,,FALSE,,.1,pal) | |
} | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment