Last active
October 13, 2015 05:37
-
-
Save tts/4147093 to your computer and use it in GitHub Desktop.
Word cloud from Aalto People jobtitles
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
############################################################### | |
# | |
# Word cloud from Aalto People jobtitles | |
# | |
# Data from Linked Open Aalto Data Service | |
# http://data.aalto.fi/ | |
# | |
# R code below is only slightly adapted from the second example at | |
# http://onertipaday.blogspot.fi/2011/07/word-cloud-in-r.html | |
# | |
# Tuija Sonkkila 25.11.2012, 18.5.2013 | |
# | |
# | |
# Note that only a fraction of Aalto University staff | |
# has an open Aalto People profile. Again, from those that have, | |
# not everyone has mentioned a title. | |
# | |
# | |
############################################################### | |
library(tm) | |
library(wordcloud) | |
library(RColorBrewer) | |
library(SPARQL) | |
endpoint <- "http://data.aalto.fi/sparql" | |
q <- "SELECT ?onlyTitle | |
WHERE { | |
GRAPH <http://data.aalto.fi/id/people/> | |
{ | |
?person <http://schema.org/jobtitle> ?title | |
} | |
FILTER (langMatches(lang(?title), 'en' )) | |
BIND (str(?title) AS ?onlyTitle) | |
} | |
ORDER BY ?onlyTitle" | |
res <- SPARQL(url=endpoint, q)$results | |
dim(res) | |
# EDIT 18.5.2013 the dimension of res has changed | |
# res.corpus <- Corpus(DataframeSource(res[1:404])) | |
res.corpus <- Corpus(DataframeSource(res[1])) | |
res.corpus <- tm_map(res.corpus, removePunctuation) | |
res.corpus <- tm_map(res.corpus, tolower) | |
res.corpus <- tm_map(res.corpus, function(x) removeWords(x, stopwords("english"))) | |
tdm <- TermDocumentMatrix(res.corpus) | |
m <- as.matrix(tdm) | |
v <- sort(rowSums(m),decreasing=TRUE) | |
d <- data.frame(word = names(v),freq=v) | |
table(d$freq) | |
pal2 <- brewer.pal(8, "Dark2") | |
png("wordcloudtitles.png", width=1280,height=800) | |
wordcloud(d$word,d$freq, scale=c(8,.2),min.freq=3,max.words=Inf, random.order=FALSE, rot.per=.15, colors=pal2) | |
dev.off() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment