For blog post

PRNGanalysis.R

library("jsonlite")
library("stringr")

oauth <- scan("yourOAuth.token", "character")

getCMD <- function(user){
  # crude system command for querying Github API
  newcmd <- paste0("curl -H 'Accept: application/vnd.github.v3.text-match+json Authorization: token ",
                   oauth, "' 'https://api.github.com/search/code?q=set.seed+in:file+language:R+user:",
                   user,"&page=1&per_page=500' | grep 'fragment' -")
  return(newcmd)
}

getPRNGseeds <- function(user){
  print(user)
  api.result <- system(getCMD(user), intern=T)
  if(is.null(attr(api.result, "status"))) {
    seeds <- cbind(user, str_match(api.result, 
                     "set\\.seed\\((\\d+)\\)")[,2])
    Sys.sleep(10)
    return(seeds)
  } else {
    cat(user, " failed")
    return(cbind(user, NA))
  }
}

# Get list of prolific R devs
names <- unique(read.csv("bigQuery_results.csv", 
                stringsAsFactors=F)[,1])
getPRNGseeds <- Vectorize(getPRNGseeds)
seedlist <- getPRNGseeds(names)

seed <- as.data.frame(do.call(rbind, seedlist))
seed <- seed[!is.na(seed$V2),]

getPalette  <-  colorRampPalette(brewer.pal(9, "Set1"))

nrow(seed)
pdf("PRNG.pdf", 6, 10)
ggplot(seed, aes(x=reorder(V2, V2, function(x)-length(x)), 
                 y=..count.., fill=user, drop=T)) +
  geom_bar(stat="bin") + scale_y_continuous(expand=c(0,0)) +
  scale_fill_manual(values=getPalette(15), 
                    guide=guide_legend(ncol=3, nrow=5)) +
  coord_flip() + theme_classic() +
  theme(legend.position=c(.7,.8)) +
  labs(list(x="PRNG seed", y="Number of appearances", 
            fill="Github username"))
dev.off()


library("wordcloud")
set.seed(42)
words <- table(seed$V2)
words <- data.frame(words=names(words), freq=words)
wordcloud(words$freq.Var1, words$freq.Freq, min.freq=1, 
          colors=brewer.pal(9, "Paired"), 
          random.color=T, scale=c(6,1))