Related
Everytime I open a new session in RStudio, I'm greeted with the error message:
Error: C stack usage 7953936 is too close to the limit
Based on suggestions for similar issues posted here and here, I tried using the ulimit command in terminal, but get the following error.
Isabels-MacBook-Pro ~ % ulimit -s
8176
Isabels-MacBook-Pro ~ % R --slave -e 'Cstack_info()["size"]'
Error: C stack usage 7954496 is too close to the limit
Execution halted
Yet, when I run ulimit on it's own, I get:
Isabels-MacBook-Pro ~ % ulimit
unlimited
Just to double-check, I try setting it to unlimited again:
Isabels-MacBook-Pro ~ % ulimit -s unlimited
but then get a new error:
Isabels-MacBook-Pro ~ % R --slave -e 'Cstack_info()["size"]'
Error: evaluation nested too deeply: infinite recursion / options(expressions=)?
Execution halted
I have no clue what this means in this context. Is the Cstack_info() the bit getting stuck on infinite recursion?? I'd love to get this figured out, as it's getting in the way of installing some necessary packages!
In case it's helpful, here's my session info
R version 4.1.3 (2022-03-10)
Platform: x86_64-apple-darwin17.0 (64-bit)
Running under: macOS Monterey 12.2.1
And contents of .Rprofile
# REMEMBER to restart R after you modify and save this file!
# First, execute the global .Rprofile if it exists. You may configure blogdown
# options there, too, so they apply to any blogdown projects. Feel free to
# ignore this part if it sounds too complicated to you.
if (file.exists("~/.Rprofile")) {
base::sys.source("~/.Rprofile", envir = environment())
}
# Now set options to customize the behavior of blogdown for this project. Below
# are a few sample options; for more options, see
# https://bookdown.org/yihui/blogdown/global-options.html
options(
# to automatically serve the site on RStudio startup, set this option to TRUE
blogdown.serve_site.startup = FALSE,
# to disable knitting Rmd files on save, set this option to FALSE
blogdown.knit.on_save = TRUE,
# build .Rmd to .html (via Pandoc); to build to Markdown, set this option to 'm$
blogdown.method = 'html'
)
# fix Hugo version
options(blogdown.hugo.version = "0.82.0")
Here are the contents from /Library/Frameworks/R.framework/Resources/library/base/R/Rprofile
### This is the system Rprofile file. It is always run on startup.
### Additional commands can be placed in site or user Rprofile files
### (see ?Rprofile).
### Copyright (C) 1995-2020 The R Core Team
### Notice that it is a bad idea to use this file as a template for
### personal startup files, since things will be executed twice and in
### the wrong environment (user profiles are run in .GlobalEnv).
.GlobalEnv <- globalenv()
attach(NULL, name = "Autoloads")
.AutoloadEnv <- as.environment(2)
assign(".Autoloaded", NULL, envir = .AutoloadEnv)
T <- TRUE
F <- FALSE
R.version <- structure(R.Version(), class = "simple.list")
version <- R.version # for S compatibility
## for backwards compatibility only
R.version.string <- R.version$version.string
## NOTA BENE: options() for non-base package functionality are in places like
## --------- ../utils/R/zzz.R
options(keep.source = interactive())
options(warn = 0)
# options(repos = c(CRAN="#CRAN#"))
# options(BIOC = "http://www.bioconductor.org")
## setting from an env variable added in 4.0.2
local({to <- as.integer(Sys.getenv("R_DEFAULT_INTERNET_TIMEOUT", 60))
if (is.na(to) || to <= 0) to <- 60L
options(timeout = to)
})
options(encoding = "native.enc")
options(show.error.messages = TRUE)
## keep in sync with PrintDefaults() in ../../main/print.c :
options(show.error.messages = TRUE)
## keep in sync with PrintDefaults() in ../../main/print.c :
options(scipen = 0)
options(max.print = 99999)# max. #{entries} in internal printMatrix()
options(add.smooth = TRUE)# currently only used in 'plot.lm'
if(isFALSE(as.logical(Sys.getenv("_R_OPTIONS_STRINGS_AS_FACTORS_",
"FALSE")))) {
options(stringsAsFactors = FALSE)
} else {
options(stringsAsFactors = TRUE)
}
if(!interactive() && is.null(getOption("showErrorCalls")))
options(showErrorCalls = TRUE)
local({dp <- Sys.getenv("R_DEFAULT_PACKAGES")
if(identical(dp, "")) ## it fact methods is done first
dp <- c("datasets", "utils", "grDevices", "graphics",
"stats", "methods")
else if(identical(dp, "NULL")) dp <- character(0)
else dp <- strsplit(dp, ",")[[1]]
dp <- sub("[[:blank:]]*([[:alnum:]]+)", "\\1", dp) # strip whitespace
options(defaultPackages = dp)
})
## Expand R_LIBS_* environment variables.
Sys.setenv(R_LIBS_SITE =
.expand_R_libs_env_var(Sys.getenv("R_LIBS_SITE")))
Sys.setenv(R_LIBS_USER =
.expand_R_libs_env_var(Sys.getenv("R_LIBS_USER")))
local({
if(nzchar(tl <- Sys.getenv("R_SESSION_TIME_LIMIT_CPU")))
setSessionTimeLimit(cpu = tl)
if(nzchar(tl <- Sys.getenv("R_SESSION_TIME_LIMIT_ELAPSED")))
setSessionTimeLimit(elapsed = tl)
})
setSessionTimeLimit(elapsed = tl)
})
.First.sys <- function()
{
for(pkg in getOption("defaultPackages")) {
res <- require(pkg, quietly = TRUE, warn.conflicts = FALSE,
character.only = TRUE)
if(!res)
warning(gettextf('package %s in options("defaultPackages") was not found', sQuote(pkg)$
call. = FALSE, domain = NA)
}
}
## called at C level in the startup process prior to .First.sys
.OptRequireMethods <- function()
{
pkg <- "methods" # done this way to avoid R CMD check warning
if(pkg %in% getOption("defaultPackages"))
if(!require(pkg, quietly = TRUE, warn.conflicts = FALSE,
character.only = TRUE))
warning('package "methods" in options("defaultPackages") was not found',
call. = FALSE)
}
if(nzchar(Sys.getenv("R_BATCH"))) {
.Last.sys <- function()
{
cat("> proc.time()\n")
print(proc.time())
}
## avoid passing on to spawned R processes
## A system has been reported without Sys.unsetenv, so try this
try(Sys.setenv(R_BATCH=""))
}
local({
if(nzchar(rv <- Sys.getenv("_R_RNG_VERSION_")))
local({
if(nzchar(rv <- Sys.getenv("_R_RNG_VERSION_")))
suppressWarnings(RNGversion(rv))
})
.sys.timezone <- NA_character_
.First <- NULL
.Last <- NULL
###-*- R -*- Unix Specific ----
.Library <- file.path(R.home(), "library")
.Library.site <- Sys.getenv("R_LIBS_SITE")
.Library.site <- if(!nzchar(.Library.site)) file.path(R.home(), "site-library") else unlist(strspl$
.Library.site <- .Library.site[file.exists(.Library.site)]
invisible(.libPaths(c(unlist(strsplit(Sys.getenv("R_LIBS"), ":")),
unlist(strsplit(Sys.getenv("R_LIBS_USER"), ":")
))))
local({
popath <- Sys.getenv("R_TRANSLATIONS", "")
if(!nzchar(popath)) {
paths <- file.path(.libPaths(), "translations", "DESCRIPTION")
popath <- dirname(paths[file.exists(paths)][1])
}
bindtextdomain("R", popath)
bindtextdomain("R-base", popath)
assign(".popath", popath, .BaseNamespaceEnv)
})
local({
## we distinguish between R_PAPERSIZE as set by the user and by configure
papersize <- Sys.getenv("R_PAPERSIZE_USER")
if(!nchar(papersize)) {
lcpaper <- Sys.getlocale("LC_PAPER") # might be null: OK as nchar is 0
papersize <- if(nchar(lcpaper))
if(length(grep("(_US|_CA)", lcpaper))) "letter" else "a4"
else Sys.getenv("R_PAPERSIZE")
}
options(papersize = papersize,
}
options(papersize = papersize,
printcmd = Sys.getenv("R_PRINTCMD"),
dvipscmd = Sys.getenv("DVIPS", "dvips"),
texi2dvi = Sys.getenv("R_TEXI2DVICMD"),
browser = Sys.getenv("R_BROWSER"),
pager = file.path(R.home(), "bin", "pager"),
pdfviewer = Sys.getenv("R_PDFVIEWER"),
useFancyQuotes = TRUE)
})
## non standard settings for the R.app GUI of the macOS port
if(.Platform$GUI == "AQUA") {
## this is set to let RAqua use both X11 device and X11/TclTk
if (Sys.getenv("DISPLAY") == "")
Sys.setenv("DISPLAY" = ":0")
## this is to allow gfortran compiler to work
Sys.setenv("PATH" = paste(Sys.getenv("PATH"),":/usr/local/bin",sep = ""))
}## end "Aqua"
## de-dupe the environment on macOS (bug in Yosemite which affects things like PATH)
if (grepl("^darwin", R.version$os)) local({
## we have to de-dupe one at a time and re-check since the bug affects how
## environment modifications propagate
while(length(dupes <- names(Sys.getenv())[table(names(Sys.getenv())) > 1])) {
env <- dupes[1]
value <- Sys.getenv(env)
Sys.unsetenv(env) ## removes the dupes, good
.Internal(Sys.setenv(env, value)) ## wrapper requries named vector, a pain, hence internal
}
})
local({
tests_startup <- Sys.getenv("R_TESTS")
if(nzchar(tests_startup)) source(tests_startup)
})
Is there anything glaring here that could be causing the issue?
Your user .Rprofile file is loading itself recursively for some reason:
if (file.exists("~/.Rprofile")) {
base::sys.source("~/.Rprofile", envir = environment())
}
From your comments it seems that these lines are inside ~/.Rprofile (~ expands to the user home directory, i.e. /Users/mycomputer in your case, assuming mycomputer is your user name).
Delete these lines (or comment them out), they don’t belong here. In fact, the file looks like it’s a template for a project-specific .Rprofile configuration. It would make sense inside a project directory, but not as the profile-wide user .Rprofile.
The logic for these files is as follows:
If there is an .Rprofile file in the current directory, R attempts to load that.
Otherwise, if the environment variable R_PROFILE_USER is set to the path of a file, R attempts to load this file.
Otherwise, if the file ~/.Rprofile exists, R attempts to load that.
Now, this implies that ~/.Rprofile is not loaded automatically if a projects-specific (= in the current working directory) .Rprofile exists. This is unfortunate, therefore many projects add lines similar to the above to their project-specific .Rprofile files to cause the user-wide ~/.Rprofile to be loaded as well. However, the above implementation ignores the R_PROFILE_USER environment variable. A better implementation would therefore look as follows:
rprofile = Sys.getenv('R_PROFILE_USER', '~/.Rprofile')
if (file.exists(rprofile)) {
base::sys.source(rprofile, envir = environment())
}
rm(rprofile)
Success! Thank you to everyone in the comment. The issue was resolved by deleting /Library/Frameworks/R.framework/Resources/library/base/R/Rprofile and re-installing R and Rstudio.
I am trying to get H2O working with Sparklyr on my spark cluster (yarn)
spark_version(sc) = 2.4.4
My spark cluster is running V2.4.4
According to this page the compatible version with my spark is 2.4.5 for Sparkling Water and the H2O release is rel-xu patch version 3. However when I install this version I am prompted to update my H2O install to the next release (REL-ZORN). Between the H2O guides and the sparklyr guides it's very confusing and contradictory at times.
Since this is a yarn deployment and not local, unfortunately I can't provide a repex to help with trobleshooting.
url <- "http://h2o-release.s3.amazonaws.com/sparkling-water/rel-2.4/5/sparkling-water-2.4.5.zip"
download.file(url = url,"sparkling-water-2.4.5.zip")
unzip("sparkling-water-2.4.5.zip")
# RUN THESE CMDs FROM THE TERMINAL
cd sparkling-water-2.4.5
bin/sparkling-shell --conf "spark.executor.memory=1g"
# RUN THESE FROM WITHIN RSTUDIO
install.packages("sparklyr")
library(sparklyr)
# REMOVE PRIOR INSTALLS OF H2O
detach("package:rsparkling", unload = TRUE)
if ("package:h2o" %in% search()) { detach("package:h2o", unload = TRUE) }
if (isNamespaceLoaded("h2o")){ unloadNamespace("h2o") }
remove.packages("h2o")
# INSTALLING REL-ZORN (3.36.0.3) WHICH IS REQUIRED FOR SPARKLING WATER 3.36.0.3
install.packages("h2o", type = "source", repos = "https://h2o-release.s3.amazonaws.com/h2o/rel-zorn/3/R")
# INSTALLING FROM S3 SINCE CRAN NO LONGER SUPPORTED
install.packages("rsparkling", type = "source", repos = "http://h2o-release.s3.amazonaws.com/sparkling-water/spark-2.4/3.36.0.3-1-2.4/R")
# AS PER THE GUIDE
options(rsparkling.sparklingwater.version = "2.4.5")
library(rsparkling)
# SPECIFY THE CONFIGURATION
config <- sparklyr::spark_config()
config[["spark.yarn.queue"]] <- "my_data_science_queue"
config[["sparklyr.backend.timeout"]] <- 36000
config[["spark.executor.cores"]] <- 32
config[["spark.driver.cores"]] <- 32
config[["spark.executor.memory"]] <- "40g"
config[["spark.executor.instances"]] <- 8
config[["sparklyr.shell.driver-memory"]] <- "16g"
config[["spark.default.parallelism"]] <- "8"
config[["spark.rpc.message.maxSize"]] <- "256"
# MAKE A SPARK CONNECTION
sc <- sparklyr::spark_connect(
master = "yarn",
spark_home = "/opt/mapr/spark/spark",
config = config,
log = "console",
version = "2.4.4"
)
When I try to establish a H2O context using the next chunk I get the following error
h2o_context(sc)
Error in h2o_context(sc) : could not find function "h2o_context"
Any pointers as to where I'm going wrong would be greatly appreciated.
See this tutorial please. The newer versions of Rsparkling use {H2OContext.getOrCreate(h2oConf)} instead of {h2o_context(sc)}.
When install_mlflow() is called to install mlflow for R, the following error is encountered.
Attempting uninstall: certifi
Found existing installation: certifi 2018.4.16
ERROR: Cannot uninstall 'certifi'. It is a distutils installed project and thus we cannot accurately determine which files belong to it which would lead to only a partial uninstall.
Note: The above is using miniconda installed using install_miniconda() command.
P.S. Posting question & answer for everyone's benefit (I spend 2 days on this).
Root cause:
The function install_mlflow()calls reticulate::conda_install() function with the default value for pip_ignore_installed which turns out to be FALSE.
💡 Hint: Click any function in the script while holding down cmd key to view the source code.
Workaround:
You can work around this issue by calling the function with pip_ignore_installed = TRUE. I've recreated the install_mlflow() function in the below script for convenience.
The script also checks and installs miniconda if not installed.
library(reticulate)
library(mlflow)
# Installing minicoda if not installed
if (!dir.exists(miniconda_path()))
install_miniconda(path = miniconda_path(), update = TRUE, force = TRUE)
# install_mlflow() # This doesn't work so we use the alt fn below.
install_mlflow_alt <- function() {
mlflow_version <- utils::packageVersion("mlflow")
packages <- c(paste("mlflow", "==", mlflow_version, sep = ""))
# Geting mlflow conda bin
conda_home <- Sys.getenv("MLFLOW_CONDA_HOME", NA)
conda <- if (!is.na(conda_home)) {
paste(conda_home, "bin", "conda", sep = "/")
} else {
"auto"
}
conda_try <- try(conda_binary(conda = conda), silent = TRUE)
if (class(conda_try) == "try-error") {
msg <- paste(attributes(conda_try)$condition$message,
paste(" If you are not using conda, you can set the environment variable",
"MLFLOW_PYTHON_BIN to the path of your python executable."),
sep = "\n")
stop(msg)
}
conda <- conda_try
# Installing mlflow
mlflow_conda_env_name <- paste("r-mlflow", mlflow_version, sep = "-")
conda_install(packages, envname = mlflow_conda_env_name,
pip = TRUE, conda = conda, pip_ignore_installed = TRUE)
}
# NOTE: Run the following command in terminal (use pip3 for python 3)
# before calling the install_mlflow_alt() function below
# paste("pip install -U mlflow==", mlflow:::mlflow_version(), sep="")
install_mlflow_alt()
I'm setting up a new laptop running Gentoo and wish to install R (as I do on all of my computers!).
However, I've hit a bit of a problem when it comes to installing packages.
I first tried to:
> install.packages(c("ggplot2", "plyr", "reshape2"))
And it duly downloaded all of the packages and its dependencies. However they didn't install reporting.
Error in library(data.table) : there is no package called ‘data.table’
Calls: .First -> library
Execution halted
Error in library(data.table) : there is no package called ‘data.table’
Calls: .First -> library
Execution halted
Error in library(data.table) : there is no package called ‘data.table’
Calls: .First -> library
Execution halted
Error in library(data.table) : there is no package called ‘data.table’
Calls: .First -> library
Execution halted
Error in library(data.table) : there is no package called ‘data.table’
Calls: .First -> library
Execution halted
Error in library(data.table) : there is no package called ‘data.table’
Calls: .First -> library
Execution halted
Error in library(data.table) : there is no package called ‘data.table’
Calls: .First -> library
Execution halted
Error in library(data.table) : there is no package called ‘data.table’
Calls: .First -> library
Not a problem I'll just install the data.table package, unfortunately...
> install.packages("data.table")
trying URL 'http://cran.uk.r-project.org/src/contrib/data.table_1.8.2.tar.gz'
Content type 'application/x-gzip' length 818198 bytes (799 Kb)
opened URL
==================================================
downloaded 799 Kb
Error in library(data.table) : there is no package called ‘data.table’
Calls: .First -> library
Execution halted
The downloaded source packages are in
‘/tmp/RtmpbQtALj/downloaded_packages’
Updating HTML index of packages in '.Library'
Making packages.html ... done
Warning message:
In install.packages("data.table") :
installation of package ‘data.table’ had non-zero exit status
And there is no indication of why installation failed at all, so I've no idea how to go about solving this? A traceback() isn't available either.
GCC is installed and configured as the output of gcc-config shows (and the fact that I can install other software from source no problem).
# gcc-config -l
[1] x86_64-pc-linux-gnu-4.6.3 *
Stumped as to how to go about solving this one. Any thoughts or ideas on how to get more information out of install.packages() welcome.
EDIT : contents of .First as requested....
> .First
function ()
{
library(data.table)
library(foreign)
library(ggplot2)
library(Hmisc)
library(lattice)
library(plyr)
library(rms)
library(xtable)
cat("\nWelcome at", date(), "\n")
}
EDIT 2 : No Rprofile.site but there is /usr/lib64/R/library/base/R/Rprofile which has....
# cat /usr/lib64/R/library/base/R/Rprofile
### This is the system Rprofile file. It is always run on startup.
### Additional commands can be placed in site or user Rprofile files
### (see ?Rprofile).
### Notice that it is a bad idea to use this file as a template for
### personal startup files, since things will be executed twice and in
### the wrong environment (user profiles are run in .GlobalEnv).
.GlobalEnv <- globalenv()
attach(NULL, name = "Autoloads")
.AutoloadEnv <- as.environment(2)
assign(".Autoloaded", NULL, envir = .AutoloadEnv)
T <- TRUE
F <- FALSE
R.version <- structure(R.Version(), class = "simple.list")
version <- R.version # for S compatibility
## for backwards compatibility only
R.version.string <- R.version$version.string
## NOTA BENE: options() for non-base package functionality are in places like
## --------- ../utils/R/zzz.R
options(keep.source = interactive())
options(warn = 0)
# options(repos = c(CRAN="#CRAN#"))
# options(BIOC = "http://www.bioconductor.org")
options(timeout = 60)
options(encoding = "native.enc")
options(show.error.messages = TRUE)
## keep in sync with PrintDefaults() in ../../main/print.c :
options(scipen = 0)
options(max.print = 99999)# max. #{entries} in internal printMatrix()
options(add.smooth = TRUE)# currently only used in 'plot.lm'
options(stringsAsFactors = TRUE)
if(!interactive() && is.null(getOption("showErrorCalls")))
options(showErrorCalls = TRUE)
local({dp <- Sys.getenv("R_DEFAULT_PACKAGES")
if(identical(dp, "")) # marginally faster to do methods last
dp <- c("datasets", "utils", "grDevices", "graphics",
"stats", "methods")
else if(identical(dp, "NULL")) dp <- character(0)
else dp <- strsplit(dp, ",")[[1]]
dp <- sub("[[:blank:]]*([[:alnum:]]+)", "\\1", dp) # strip whitespace
options(defaultPackages = dp)
})
## Expand R_LIBS_* environment variables.
Sys.setenv(R_LIBS_SITE =
.expand_R_libs_env_var(Sys.getenv("R_LIBS_SITE")))
Sys.setenv(R_LIBS_USER =
.expand_R_libs_env_var(Sys.getenv("R_LIBS_USER")))
.First.sys <- function()
{
for(pkg in getOption("defaultPackages")) {
res <- require(pkg, quietly = TRUE, warn.conflicts = FALSE,
character.only = TRUE)
if(!res)
warning(gettextf('package %s in options("defaultPackages") was not found', sQuote(pkg)),
call.=FALSE, domain = NA)
}
}
.OptRequireMethods <- function()
{
if("methods" %in% getOption("defaultPackages")) {
res <- require("methods", quietly = TRUE, warn.conflicts = FALSE,
character.only = TRUE)
if(!res)
warning('package "methods" in options("defaultPackages") was not found', call.=FALSE)
}
}
if(nzchar(Sys.getenv("R_BATCH"))) {
.Last.sys <- function()
{
cat("> proc.time()\n")
print(proc.time())
}
## avoid passing on to spawned R processes
## A system has been reported without Sys.unsetenv, so try this
try(Sys.setenv(R_BATCH=""))
}
###-*- R -*- Unix Specific ----
.Library <- file.path(R.home(), "library")
.Library.site <- Sys.getenv("R_LIBS_SITE")
.Library.site <- if(!nchar(.Library.site)) file.path(R.home(), "site-library") else unlist(strsplit(.Library.site, ":"))
.Library.site <- .Library.site[file.exists(.Library.site)]
invisible(.libPaths(c(unlist(strsplit(Sys.getenv("R_LIBS"), ":")),
unlist(strsplit(Sys.getenv("R_LIBS_USER"), ":")
))))
local({
## we distinguish between R_PAPERSIZE as set by the user and by configure
papersize <- Sys.getenv("R_PAPERSIZE_USER")
if(!nchar(papersize)) {
lcpaper <- Sys.getlocale("LC_PAPER") # might be null: OK as nchar is 0
papersize <- if(nchar(lcpaper))
if(length(grep("(_US|_CA)", lcpaper))) "letter" else "a4"
else Sys.getenv("R_PAPERSIZE")
}
options(papersize = papersize,
printcmd = Sys.getenv("R_PRINTCMD"),
dvipscmd = Sys.getenv("DVIPS", "dvips"),
texi2dvi = Sys.getenv("R_TEXI2DVICMD"),
browser = Sys.getenv("R_BROWSER"),
pager = file.path(R.home(), "bin", "pager"),
pdfviewer = Sys.getenv("R_PDFVIEWER"),
useFancyQuotes = TRUE)
})
## non standard settings for the R.app GUI of the Mac OS X port
if(.Platform$GUI == "AQUA") {
## this is set to let RAqua use both X11 device and X11/TclTk
if (Sys.getenv("DISPLAY") == "")
Sys.setenv("DISPLAY" = ":0")
## this is to allow gfortran compiler to work
Sys.setenv("PATH" = paste(Sys.getenv("PATH"),":/usr/local/bin",sep = ""))
}## end "Aqua"
local({
tests_startup <- Sys.getenv("R_TESTS")
if(nzchar(tests_startup)) source(tests_startup)
})
Looks like data.table is not installed for the user that is running the install.packages command. I think wrapping that .First function in if (interactive()) { } would be a good idea in general. Otherwise, you need to install data.table and any other packages that load at startup since install.packages runs the .Rprofile file when starting
WARNING: You're using a non-UTF8 locale, therefore only ASCII characters will work.
Please read R for Mac OS X FAQ (see Help) section 9 and adjust your system preferences accordingly.
[History restored from /Users/carlosaburto/.Rapp.history]
defaults write org.R-project.R force.LANG en_US.UTF-8
Error: unexpected symbol in "defaults write"
starting httpd help server ... done
This question already has answers here:
Elegant way to check for missing packages and install them?
(33 answers)
Closed 5 years ago.
I have an R script that is shared with several users on different computers. One of its lines contains the install.packages("xtable") command.
The problem is that every time someone runs the script, R spends a great deal of time apparently reinstalling the package (it actually does take some time, since the real case has vector of several packages).
How can I make first check if the packages are installed and then only run install.packages() for the ones that are not?
try: require("xtable") or "xtable" %in% rownames(installed.packages())
If you want to do it as simply as possible:
packages <- c("ggplot2", "dplyr", "Hmisc", "lme4", "arm", "lattice", "lavaan")
install.packages(setdiff(packages, rownames(installed.packages())))
Replace the packages listed on the first line by those needed to run your code, and voilà!
Note: Edited to remove conditional wrapper thanks to Artem's comment below.
This is a function I often used to check for a package, install it otherwise and load again:
pkgTest <- function(x)
{
if (!require(x,character.only = TRUE))
{
install.packages(x,dep=TRUE)
if(!require(x,character.only = TRUE)) stop("Package not found")
}
}
Works like pkgTest("xtable"). It only works if the mirror is set though, but you could enter that in the require calls.
I suggest a more lightweight solution using system.file.
is_inst <- function(pkg) {
nzchar(system.file(package = pkg))
}
is_inst2 <- function(pkg) {
pkg %in% rownames(installed.packages())
}
library(microbenchmark)
microbenchmark(is_inst("aaa"), is_inst2("aaa"))
## Unit: microseconds
## expr min lq mean median uq max neval
## is_inst("aaa") 22.284 24.6335 42.84806 34.6815 47.566 252.568 100
## is_inst2("aaa") 1099.334 1220.5510 1778.57019 1401.5095 1829.973 17653.148 100
microbenchmark(is_inst("ggplot2"), is_inst2("ggplot2"))
## Unit: microseconds
## expr min lq mean median uq max neval
## is_inst("ggplot2") 336.845 386.660 459.243 431.710 483.474 867.637 100
## is_inst2("ggplot2") 1144.613 1276.847 1507.355 1410.054 1656.557 2747.508 100
There's also the CRAN package pacman which has the p_load function to install one or more packages (but only if necessary) and then load them.
requiredPackages = c('plyr','ggplot2','ggtern')
for(p in requiredPackages){
if(!require(p,character.only = TRUE)) install.packages(p)
library(p,character.only = TRUE)
}
# Function to check whether package is installed
is.installed <- function(mypkg){
is.element(mypkg, installed.packages()[,1])
}
# check if package "hydroGOF" is installed
if (!is.installed("hydroGOF")){
install.packages("hydroGOF")
}
I found a packages script somewhere that I always put in every script to load my libraries. It will do all your library handling (downloading, installing and loading), and only when needed.
# Install function for packages
packages<-function(x){
x<-as.character(match.call()[[2]])
if (!require(x,character.only=TRUE)){
install.packages(pkgs=x,repos="http://cran.r-project.org")
require(x,character.only=TRUE)
}
}
packages(ggplot2)
packages(reshape2)
packages(plyr)
# etc etc
I have implemented the function to install and load required R packages silently. Hope might help. Here is the code:
# Function to Install and Load R Packages
Install_And_Load <- function(Required_Packages)
{
Remaining_Packages <- Required_Packages[!(Required_Packages %in% installed.packages()[,"Package"])];
if(length(Remaining_Packages))
{
install.packages(Remaining_Packages);
}
for(package_name in Required_Packages)
{
library(package_name,character.only=TRUE,quietly=TRUE);
}
}
# Specify the list of required packages to be installed and load
Required_Packages=c("ggplot2", "Rcpp");
# Call the Function
Install_And_Load(Required_Packages);
The solution I used derived from Sacha Epskamp and Shuguang's input. Here's the function:
instalaPacotes <- function(pacote) {
if (!pacote %in% installed.packages()) install.packages(pacote)
}
It works silently, echoing nothing if package "pacote" is already installed and installing it otherwise. Don't forget to write the name of the package between quotes!
Or a massively overticked example from drknexus/repsych on github, glibrary. There are almost certainly more efficient and better ways to to do this, but I programmed it a long while back and it basically works.
It works even if a repo hasn't been selected by taking the default cloud option if available. If you are on an older version of R it will roll back and pick a mirror based on country code.
It tries to load the library (this step could be made more efficient using some of the methods above)
If it fails, it will try to install it
If the install fails it will notify you which packages failed to install
That is right, packages, multiple packages can be loaded/installed in a single pass along with their dependencies (at least usually, there may be a bug here).
e.g.: glibrary(xtable,sos,data.table) but I don't think it will freak out if you call glibrary("xtable","sos","data.table") instead. Pushes/pulls/forks welcome.
Code for the function:
#' Try to load a library, if that fails, install it, then load it.
#'
#' glibrary short for (get)library.
#' The primary aim of this function is to make loading packages more transparent. Given that we know we want to load a given package, actually fetching it is a formality. glibrary skims past this formality to install the requested package.
#'
#' #export
#' #param ... comma seperated package names
#' #param lib.loc See \code{\link{require}}
#' #param quietly See \code{\link{require}}
#' #param warn.conflicts See \code{\link{require}}
#' #param pickmirror If TRUE, glibrary allows the user to select the mirror, otherwise it auto-selects on the basis of the country code
#' #param countrycode This option is ignored and the first mirror with the substring "Cloud", e.g. the RStudio cloud, is selected. If no mirrors with that substring are identified, glibrary compares this value to results from getCRANmirrors() to select a mirror in the specified country.
#' #return logical; TRUE if glibrary was a success, an error if a package failed to load
#' #note keep.source was an arguement to require that was deprecated in R 2.15
#' #note This warning \code{Warning in install.packages: InternetOpenUrl failed: 'The operation timed out'} indicates that the randomly selected repository is not available. Check your internet connection. If your internet connection is fine, set pickmirror=TRUE and manually select an operational mirror.
#' #examples
#' #glibrary(lattice,MASS) #not run to prevent needless dependency
glibrary <- function(..., lib.loc = NULL, quietly = FALSE, warn.conflicts = TRUE, pickmirror = FALSE, countrycode = "us") {
warningHandle <- function(w) {
if (grepl("there is no package called",w$message,fixed=TRUE)) {
return(FALSE) #not-loadable
} else {
return(TRUE) #loadable
}
}
character.only <- TRUE #this value is locked to TRUE so that the function passes the character value to require and not the variable name thislib
librarynames <- unlist(lapply(as.list(substitute(.(...)))[-1],as.character))
#if package already loaded, remove it from librarynames before processing further
si.res <- sessionInfo()
cur.loaded <- c(si.res$basePkgs,names(si.res$otherPkgs)) #removed names(si.res$loadedOnly) because those are loaded, but not attached, so glibrary does need to handle them.
librarynames <- librarynames[librarynames %!in% cur.loaded]
success <- vector("logical", length(librarynames))
if (length(success)==0) {return(invisible(TRUE))} #everything already loaded, end.
alreadyInstalled <- installed.packages()[,"Package"]
needToInstall <- !librarynames %in% alreadyInstalled
if (any(needToInstall)) {
if (pickmirror) {chooseCRANmirror()}
if (getOption("repos")[["CRAN"]] == "#CRAN#") {
#Select the first "Cloud" if available
m <- getCRANmirrors(all = FALSE, local.only = FALSE)
URL <- m[grepl("Cloud",m$Name),"URL"][1] #get the first repos with "cloud" in the name
if (is.na(URL)) { #if we did not find the cloud,
#Fall back and use the previous method
message("\nIn repsych:glibrary: Now randomly selecting a CRAN mirror. You may reselect your CRAN mirror with chooseCRANmirror().\n")
#if there is no repository set pick a random one by country code
getCRANmirrors.res <- getCRANmirrors()
foundone <- FALSE #have we found a CRAN mirror yet?
#is it a valid country code?
if (!countrycode %in% getCRANmirrors.res$CountryCode) {
stop("In repsych::glibrary: Invalid countrycode argument")
}
ticker <- 0
while (!foundone) {
ticker <- ticker + 1
URL <- getCRANmirrors.res$URL[sample(grep(countrycode, getCRANmirrors.res$CountryCode), 1)]
host.list <- strsplit(URL, "/")
host.clean <- unlist(lapply(host.list, FUN = function(x) {return(x[3])}))
#make sure we can actually access the package list
if (nrow(available.packages(contrib.url(URL)))!=0) {foundone <- TRUE}
if (ticker > 5) {stop("In repsych::glibrary: Unable to access valid repository. Is the internet connection working?")}
} #end while
} #end else
repos <- getOption("repos")
repos["CRAN"] <- gsub("/$", "", URL[1L])
options(repos = repos)
} #done setting CRAN mirror
#installing packages
installResults <- sapply(librarynames[needToInstall],install.packages)
#checking for successful install
needToInstall <- !librarynames %in% installed.packages()[,"Package"]
if (any(needToInstall)) {
stop(paste("In repsych::glibrary: Could not download and/or install: ",paste(librarynames[needToInstall],collapse=", "),"... glibrary stopped.",sep=""))
} # done reporting any failure to install
} #done if any needed to install
#message("In repsych::glibrary: Attempting to load requested packages...\n")
#success <- tryCatch(
success <- sapply(librarynames,require, lib.loc = lib.loc, quietly = FALSE, warn.conflicts = warn.conflicts, character.only = TRUE)
#, warning=warningHandle) #end tryCatch
if(length(success) != length(librarynames)) {stop("A package failed to return a success in glibrary.")}
if (all(success)) {
#message("In repsych::glibrary: Success!")
return(invisible(TRUE))
} else {
stop(paste("\nIn repsych::glibrary, unable to load: ", paste(librarynames[!success]),
collapse = " "))
}
stop("A problem occured in glibrary") #shouldn't get this far down, all returns should be made.
}
NULL
How about trying this?
#will install the pROC library if you don't have it
if(!is.element('pROC', installed.packages()[,1]))
{install.packages('pROC')
}else {print("pROC library already installed")}
This should do it. You can make required.packages a vector if you need to check for more than one.
required.packages <- "data.table"
new.packages <- required.packages[!(required.packages %in% installed.packages()[,"Package"])]
if(length(new.packages)) install.packages(new.packages)
Reading everyone's responses, I took some hints here and there and created mine. Actually very similar to most though.
## These codes are used for installing packages
# function for installing needed packages
installpkg <- function(x){
if(x %in% rownames(installed.packages())==FALSE) {
if(x %in% rownames(available.packages())==FALSE) {
paste(x,"is not a valid package - please check again...")
} else {
install.packages(x)
}
} else {
paste(x,"package already installed...")
}
}
# install necessary packages
required_packages <- c("sqldf","car")
lapply(required_packages,installpkg)
Looked at my old function, updated it using tips above and this is what i got.
# VERSION 1.0
assign("installP", function(pckgs){
ins <- function(pckg, mc){
add <- paste(c(" ", rep("-", mc+1-nchar(pckg)), " "), collapse = "");
if( !require(pckg,character.only=TRUE) ){
reps <- c("http://lib.stat.cmu.edu/R/CRAN","http://cran.uk.R-project.org");
for (r in reps) try(utils::install.packages(pckg, repos=r), silent=TRUE);
if(!require(pckg,character.only = TRUE)){ cat("Package: ",pckg,add,"not found.\n",sep="");
}else{ cat("Package: ",pckg,add,"installed.\n",sep="");}
}else{ cat("Package: ",pckg,add,"is loaded.\n",sep=""); } }
invisible(suppressMessages(suppressWarnings(lapply(pckgs,ins, mc=max(nchar(pckgs)))))); cat("\n");
}, envir=as.environment("dg_base"))
installP(c("base","a","TFX"))
Package: base ------------------- is loaded.
Package: a ---------------------- not found.
Package: TFX -------------------- installed.
Why not just delete the line from the script? If the end-user doesn't have the smarts to install xtable as needed, you've got bigger problems :-( .
That said, check out installed.packages()
Edit: dang, Ninja'd by ONE minute!
Edit: a general suggestion: load the package sos , and you'll find it very easy to get answers to a lot of "is there a function that does XXXXX" questions.