In neuropsychology/psycho.R: Efficient and Publishing-Oriented Workflow for Psychological Science

library(knitr)

Download data

# load packages & custom functions ---------------------------------------------

library(tidyverse)
library(httr)
library(cranlogs)
library(XML)
library(ggrepel)
library(scales)
library(knitr)
library(stringr)

gh_from_url <- function(x){
  if(!grepl(',', x)){
    x <- strsplit(x, " ")[[1]]
    x <- trimws(x[min(which(grepl(pattern='http://github.com|https://github.com|http://www.github.com', x, ignore.case=TRUE)))])    
  } else {
    x <- strsplit(x, ",")[[1]]
    x <- trimws(x[min(which(grepl(pattern='http://github.com|https://github.com|http://www.github.com', x, ignore.case=TRUE)))])    
  }
  x <- gsub("http://", "https://", tolower(x))
  x <- gsub("www\\.github\\.com", "github.com", x)
  x <- gsub("/$", "", x)
  x <- gsub("^github.com", "https://github.com", x)
  x <- gsub("/issues", "", x)
  x <- gsub("\\.git", "", x)
  return(x)
}

aut_maintainer_from_details <- function(x){
  x <- gsub("'|\"", "", x)
  if(grepl(',', x)){
    x <- strsplit(x, "\\],")[[1]]
    aut_cre_ind <- grepl(pattern='\\[aut, cre|\\[cre, aut|\\[cre', x, ignore.case=TRUE)
    if(any(aut_cre_ind)){
      x <- x[min(which(aut_cre_ind))]
      x <- gsub("\\[aut, cre|\\[cre, aut|\\[cre", "", x)
    }
    x <- strsplit(x, ",")[[1]][1]
    x <- trimws(gsub("\\]", "", x))
    x <- trimws(gsub(" \\[aut", "", x))
  }
  return(x)
}

gh_star_count <- function(url){
  stars  <- tryCatch({
    this_url <- gsub("https://github.com/", "https://api.github.com/repos/", url)
    req <- GET(this_url, gtoken)
    stop_for_status(req)
    cont <- content(req)
    cont$stargazers_count  
  }, error = function(e){
    return(NA_integer_)
  })
  return(stars)
}



# authenticate to github -------------------------------------------------------
# use Hadley's key and secret
myapp <- oauth_app("github",
                   key = "56b637a5baffac62cad9",
                   secret = "8e107541ae1791259e9987d544ca568633da2ebf")
github_token <- oauth2.0_token(oauth_endpoints("github"), myapp)
gtoken <- config(token = github_token)

# pull list of packages --------------------------------------------------------

# get list of currently available packages on CRAN
pkgs <- readHTMLTable(readLines(file.path('https://cran.rstudio.com/src/contrib')),
                      which = 1, 
                      stringsAsFactors = FALSE)[,-1]

# filter out lines that aren't really packages
pkgs <- pkgs %>% 
  filter(Size != "-", 
         grepl('tar.gz$', Name)) %>%
  mutate(Name = sub('^([a-zA-Z0-9\\.]*).*', '\\1', Name)) %>%
  distinct(Name, .keep_all = TRUE)

# get details for each package -------------------------------------------------

all_pkg_details <- NULL

# old fashioned looping! 
# WARNING: This takes awhile to complete
for(i in 1:nrow(pkgs)){

  if(i %% 100 == 0){
    message(sprintf("Processing package #%s out of %s", i, nrow(pkgs)))
  }

  pkg_details <- readHTMLTable(readLines(file.path(sprintf('https://cran.r-project.org/package=%s', pkgs[i,]$Name))), 
                               header=FALSE, 
                               which = 1, 
                               stringsAsFactors = FALSE)
  pkg_details <- pkg_details %>%
    mutate(V1 = gsub(":", "", V1)) %>%
    spread(V1, V2)

  this_url <- pkg_details$URL
  on_github <- FALSE
  this_github_url <- NA_character_
  gh_stars <- NA_integer_
  if(!is.null(this_url)){
    on_github <- grepl('http://github.com|https://github.com|http://www.github.com', this_url)
    if(on_github){
      this_github_url <- gh_from_url(this_url)
      gh_stars <- gh_star_count(this_github_url)
    } else {
      # check the BugReports URL as a backup (e.g. shiny package references GitHub this way)
      issues_on_github <- grepl('http://github.com|https://github.com|http://www.github.com', pkg_details$BugReports)
      if(length(issues_on_github) == 0 || !issues_on_github){
        this_github_url <- NA_character_
      } else {
        this_github_url <- gh_from_url(pkg_details$BugReports)
        gh_stars <- gh_star_count(this_github_url)  
        on_github <- TRUE
      }
    }
  } else {
    this_url <- NA_character_
  }

  downloads <- cran_downloads(pkgs[i,]$Name, from = "2014-01-01", to = "2018-06-15")

  all_pkg_details <- rbind(all_pkg_details, 
                           tibble(name = pkgs[i,]$Name, 
                                  published = pkg_details$Published,
                                  author = aut_maintainer_from_details(pkg_details$Author),
                                  url = this_url,
                                  github_ind = on_github, 
                                  github_url = this_github_url,
                                  downloads = sum(downloads$count),
                                  stars = gh_stars
                           )
  )
}

# basic summary stats ----------------------------------------------------------

# remove observations where the GitHub URL refers to a repository that 
# is not specific to R and therefore might have an inflated star count
all_pkg_details_clean <- all_pkg_details %>% 
  filter(!(name %in% c('xgboost', 'h2o', 'feather'))) %>% 
  mutate(downloads_per_star = downloads / stars, 
         downloads_per_star = ifelse(!is.finite(downloads_per_star), NA_real_, downloads_per_star))

Credits

This package helped you? Don't forget to cite the various packages you used :)

You can cite psycho as follows:

• Makowski, (2018). The psycho Package: an Efficient and Publishing-Oriented Workflow for Psychological Science. Journal of Open Source Software, 3(22), 470. https://doi.org/10.21105/joss.00470

neuropsychology/psycho.R documentation built on Jan. 25, 2021, 7:59 a.m.