topmaintainers.R

library(tidyverse)
library(stringr)
library(stringi)
simplify_name <- function(n)
 ## Extract just the name, removing any quotes, and normalize accented characters 
 stri_trans_general(str_trim(str_match(n,"^[\'\"]?([^\'\",(<]+).*<")[,2]),"latin-ascii")       
pkglist <- tools::CRAN_package_db()
pkglist <- tbl_df(pkglist[-40]) ## remove duplicate MD5sum column
pkglist %>% 
 select(Maintainer, Author, Package) %>% 
 arrange(Maintainer) -> authors
authors %>% 
 transmute(Maint = simplify_name(Maintainer)) %>% 
 group_by(Maint) %>% 
 tally %>% arrange(desc(n)) -> topauthors
as.data.frame(head(topauthors,20))