In pbiecek/archivist2: Tools for Storing, Restoring and Searching for R Objects

Installation

\dontrun{

require(devtools)
require(dplyr)
if (!require(archivist)) {
  install_github("pbiecek/archivist", build_vignettes=FALSE)
}

Download plots from GitHub

summaryGithubRepo("graphGallery", "pbiecek")

(allObject <- searchInGithubRepo( list("2005-05-27", now()), 
                    user = "pbiecek", repo = "graphGallery"))

(plots <- searchInGithubRepo( "class:ggplot", 
                    user = "pbiecek", repo = "graphGallery"))

#
# example plots
loadFromGithubRepo( md5hash = "fcd70d55b874201d2bece12f591a2ec4" , 
                    user = "pbiecek", repo = "graphGallery", value=TRUE)

loadFromGithubRepo( md5hash = "b6f183dfd0efdc8c33fa89b9038716c5" , 
                    user = "pbiecek", repo = "graphGallery", value=TRUE)

Manage local repo

myRepo <- tempdir()
createEmptyRepo( myRepo )

data( iris )
saveToRepo(iris, myRepo)
# same object causes warning
saveToRepo(iris, myRepo)

searchInLocalRepo( pattern = "name:ir",  myRepo, fixed=FALSE)
searchInLocalRepo( pattern = "name:iris",  myRepo)
searchInLocalRepo( pattern = "class:data.frame",  myRepo)
searchInLocalRepo( pattern = c("2012-01-01", "2014-01-01"),  myRepo)

rm( iris )
loadFromLocalRepo( "ff575c261c949d073b2895b05d",  myRepo)
iris2 <- loadFromLocalRepo( "ff575c261c949d073b2895b05d",  myRepo, value=TRUE)

summaryLocalRepo(myRepo)

rmFromRepo( "ff575c261c949d073b2895b05d1097c3", myRepo)

# TO fix
# summaryLocalRepo(myRepo)

Let's add a plot

if (!require(eurostat)) {
  install_github("rOpenGov/eurostat")
}

library(ggplot2)

t1 <- get_eurostat("tsdtr420") %>% 
       filter(geo %in% c("UK", "SK", "FR", "PL", "ES", "PT", "LV"))
head(t1)
(pl <- ggplot(t1, aes(x = time, y = value, color=geo, group=geo, shape=geo)) +
          geom_point(size=4) + 
          geom_line() + theme_bw() + ggtitle("People killed in road accidents"))

(ob <- saveToRepo(pl, myRepo))

rmFromRepo( ob, myRepo)

deleteRepo(myRepo)

Cache

cache <- function(cacheRepo, FUN, ...) {
  tmpl <- list(...)
  tmpl$.FUN <- FUN
  outputHash <- digest(tmpl)
  isInRepo <- searchInLocalRepo(paste0("cacheId:", outputHash), cacheRepo)
  if (length(isInRepo) > 0)
    return(loadFromLocalRepo(isInRepo[1], repoDir = cacheRepo, value = TRUE))

  output <- do.call(FUN, list(...))
  attr( output, "tags") <- paste0("cacheId:", outputHash)
  attr( output, "call") <- ""
  saveToRepo(output, repoDir = cacheRepo, archiveData = TRUE, archiveMiniature = FALSE, rememberName = FALSE)
  output
}

cacheRepo <- tempdir()
createEmptyRepo( cacheRepo )

# in progress, waiting for #30
cache(cacheRepo, lm, data=iris, Petal.Length~Species)