Last active
February 8, 2021 08:49
-
-
Save chr1swallace/d4b54bf273006ea0acc1 to your computer and use it in GitHub Desktop.
make a word cloud from an orcid id
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
## install packages using the following | |
## install.packages("devtools") | |
## library(devtools) | |
## install_github("ropensci/rorcid") | |
## install.packages(c("tm","wordcloud")) | |
## load libraries | |
library(rorcid) | |
library(wordcloud) | |
## functions | |
get.years <- function(x) {as.numeric(x[["works"]][["publication-date.year.value"]])} | |
get.titles <- function(x) {x[["works"]][["title.title.value"]]} | |
get.authors <- function(x,surnames=FALSE) { | |
all <- x[["works"]][["work-contributors.contributor"]] | |
all <- lapply(all,"[[","credit-name.value") | |
if(surnames) { | |
all <- lapply(all,function(x) sub(",.*","",x)) | |
all <- lapply(all,function(x) sub(".* ","",x)) | |
} else { | |
all <- lapply(all, function(x) sub(" ",",",x)) | |
} | |
return(all) | |
} | |
## adapted this function from http://entrenchant.blogspot.co.uk/2013/06/english-word-clouds-in-r.html | |
aggregate.plurals <- function (m) { | |
words <- rownames(m) | |
mind <- vector("list",length(words)) | |
for (i in seq_along(words)) { | |
if(i %in% unlist(mind)) | |
next | |
mind[[i]] <- i | |
if(i==length(words)) | |
next | |
plurals <- paste0(words[[i]], c("s","es")) | |
wh <- which(words[-c(1:i)] %in% plurals) + i | |
if(length(wh)) | |
mind[[i]] <- c(mind[[i]],wh) | |
} | |
mind.l <- sapply(mind,length) | |
for(i in which(mind.l>1)) { | |
m[i,] <- colSums(m[mind[[i]],,drop=FALSE]) | |
} | |
m <- m[mind.l>0,,drop=FALSE] | |
return(m) | |
} | |
mystopwords <- c("using","near","one","two","three","ten","without") | |
make.cloud <- function(text,by=NULL,group=NULL,min.freq=3) { | |
if(!is.null(group) && !is.null(by)) | |
by <- group * (as.numeric(by) %/% group) | |
if(!is.null(by)) { | |
text <- tapply(text,by,paste,collapse=" ") | |
} | |
corp <- VCorpus(VectorSource(text)) | |
corp <- tm_map(corp, content_transformer(tolower)) | |
corp <- tm_map(corp,removePunctuation) | |
corp <- tm_map(corp,removeNumbers) | |
corp <- tm_map(corp, removeWords, c(stopwords("english"),mystopwords)) | |
tdm <- TermDocumentMatrix(corp) | |
m <- as.matrix(tdm) | |
colnames(m) <- names(text) | |
m <- aggregate.plurals(m) | |
m <- m[order(rowSums(m),decreasing=TRUE),,drop=FALSE ] | |
## for(i in 1:ncol(m)) | |
## m[,i] <- m[,i]/sum(m[,i]) | |
m <- m[rowSums(m)>=min.freq, ,drop=FALSE] | |
pal <- brewer.pal(6,"Dark2") | |
pal <- pal[-1] | |
if(is.null(by)) { | |
v <- sort(rowSums(m),decreasing=TRUE) | |
d <- data.frame(word = names(v),freq=v) | |
return(wordcloud(d$word,d$freq,colors=brewer.pal(6,"Dark2"),random.order=FALSE)) | |
} | |
comparison.cloud(m) | |
} | |
orcid.cloud <- function(data,what="titles") { | |
switch(what, | |
"titles" = make.cloud(get.titles(data[[1]])), | |
"authors" = make.cloud(get.authors(data[[1]],surnames=TRUE)), | |
"years" = hist(get.years(data[[1]])), | |
message(what," not recognised")) | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
See https://cwcode.wordpress.com/2015/02/17/wordclouds-from-orcid/ for the post which supported this. But I'm afraid the code may be a bit out of date.