I am completely new to stan and recently attended an rstan workshop with amongst others @paul.buerkner demonstrating his brms package.
My problems in a nutshell is that R and RStudio crashes during sampling phase of the stan execution when running the following code.
library(brms)
# options(mc.cores = parallel::detectCores())
# rstan_options(auto_write = TRUE)
url <- "https://raw.githubusercontent.com/mages/diesunddas/master/Data/ClarkTriangle.csv"
loss <- read.csv(url)
loss$LR = with(loss, cum / premium)
head(loss)
fit_loss <- brm(
bf(LR ~ ult * (1 - exp(-(dev/theta)^omega)),
ult ~ 1 + (1|AY), omega ~ 1, theta ~ 1,
nl = TRUE),
data = loss, family = gaussian(),
prior = c(
prior(lognormal(log(0.5), 0.3), nlpar = "ult", lb = 0),
prior(normal(1, 2), nlpar = "omega", lb = 0),
prior(normal(45, 10), nlpar = "theta", lb = 0)
),
cores = 1, chains = 1
# control = list(adapt_delta = 0.9)
)
When running the code, I can see that the stan model is being compiled and the first SAMPLING FOR MODEL … (Chain 1) is started.
Within about 20 seconds of this happening RStudio aborts the session. If I run the same code within the native R console, I get to the same execution point, but the R console just hangs as if the code fails silently in the background.
@paul.buerkner suggested a variety of simplifications to the code, such as setting cores = 1, and chains = 1
This is what is output to the console:
Compiling the C++ model
Start sampling
SAMPLING FOR MODEL 'gaussian brms-model' NOW (CHAIN 1).
Gradient evaluation took 0 seconds
1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
Adjust your expectations accordingly!
Iteration: 1 / 2000 [ 0%] (Warmup)
-
I have tried this in 3 different windows environments, a windows laptop (Windows 8), a windows PC (windows 8) and finally a windows server 2012 all exhibiting the same problem.
The session info is for the windows server, as this has the highest spec (2.3 GHz, 24 cores, 512Gb RAM) -
I have tried this using rstan version 2.17.3 on all 3.
-
I have also tried to download the binaries and install rstan (2.17.2) on the server and laptop
-
All 3 environments have differnt versions of R and corresponding versions of RTools.
- Windows Laptop: R version 3.5.1 (2018-07-02)
- Windows PC: R version 3.4.0 Patched (2017-05-08 r72665)
- Windows Server: R version 3.4.3 (2017-11-30)
-
I can successfully run a simple stan models such as:
library(rstan) rstan_options(auto_write = TRUE) options(mc.cores = parallel::detectCores()) scode <- " parameters { real y[2]; } model { y[1] ~ normal(0, 1); y[2] ~ double_exponential(0, 2); } " fit1 <- stan(model_code = scode, iter = 10, verbose = FALSE) print(fit1)
And get the following output:
In file included from C:/Users/my_user/Documents/R/win-library/3.4/BH/include/boost/config.hpp:39:0,
from C:/Users/my_user/Documents/R/win-library/3.4/BH/include/boost/math/tools/config.hpp:13,
from C:/Users/my_user/Documents/R/win-library/3.4/StanHeaders/include/stan/math/rev/core/var.hpp:7,
from C:/Users/my_user/Documents/R/win-library/3.4/StanHeaders/include/stan/math/rev/core/gevv_vvv_vari.hpp:5,
from C:/Users/my_user/Documents/R/win-library/3.4/StanHeaders/include/stan/math/rev/core.hpp:12,
from C:/Users/my_user/Documents/R/win-library/3.4/StanHeaders/include/stan/math/rev/mat.hpp:4,
from C:/Users/my_user/Documents/R/win-library/3.4/StanHeaders/include/stan/math.hpp:4,
from C:/Users/my_user/Documents/R/win-library/3.4/StanHeaders/include/src/stan/model/model_header.hpp:4,
from file3e3412e77ce8.cpp:8:
C:/Users/my_user/Documents/R/win-library/3.4/BH/include/boost/config/compiler/gcc.hpp:186:0: warning: "BOOST_NO_CXX11_RVALUE_REFERENCES" redefined
# define BOOST_NO_CXX11_RVALUE_REFERENCES
^
<command-line>:0:0: note: this is the location of the previous definition
cc1plus.exe: warning: unrecognized command line option "-Wno-ignored-attributes"
Loading required namespace: rstudioapi
> print(fit1)
Inference for Stan model: 0f459bda2e2707c0379d5ca819627502.
4 chains, each with iter=10; warmup=5; thin=1;
post-warmup draws per chain=5, total post-warmup draws=20.
mean se_mean sd 2.5% 25% 50% 75% 97.5% n_eff Rhat
y[1] 0.21 0.31 1.38 -1.74 -0.97 0.42 1.22 2.35 20 1.00
y[2] 0.17 0.82 1.67 -2.62 -0.75 0.18 1.31 2.97 4 1.23
lp__ -1.63 0.27 0.85 -3.43 -1.94 -1.46 -0.98 -0.61 10 1.18
Samples were drawn using NUTS(diag_e) at Wed Jul 18 10:36:20 2018.
For each parameter, n_eff is a crude measure of effective sample size,
and Rhat is the potential scale reduction factor on split chains (at
convergence, Rhat=1).
-
Operating System: Windows Server 2012
-
RStan Version: 2.17.3 and (2.17.2 also tried)
-
Output of
writeLines(readLines(file.path(Sys.getenv("HOME"), ".R/Makevars")))
writeLines(readLines(file.path(Sys.getenv("HOME"), ".R/Makevars"))) CXXFLAGS=-O3 -mtune=native -march=native -Wno-unused-variable -Wno-unused-function CXXFLAGS += -Wno-ignored-attributes -Wno-deprecated-declarations
-
Output of
devtools::session_info("rstan")
devtools::session_info("rstan") Session info --------------------------------------------------------------------------------------------------------------------- setting value version R version 3.4.3 (2017-11-30) system x86_64, mingw32 ui RStudio (1.1.423) language (EN) collate English_United Kingdom.1252 tz Europe/London date 2018-07-17 Packages ------------------------------------------------------------------------------------------------------------------------- package * version date source assertthat 0.2.0 2017-04-11 CRAN (R 3.4.2) BH 1.65.0-1 2017-08-24 CRAN (R 3.4.1) cli 1.0.0 2017-11-05 CRAN (R 3.4.3) colorspace 1.3-2 2016-12-14 CRAN (R 3.4.2) crayon 1.3.4 2017-09-16 CRAN (R 3.4.2) dichromat 2.0-0 2013-01-24 CRAN (R 3.4.1) digest 0.6.13 2017-12-14 CRAN (R 3.4.3) ggplot2 * 2.2.1 2016-12-30 CRAN (R 3.4.3) graphics * 3.4.3 2018-01-10 local grDevices * 3.4.3 2018-01-10 local grid 3.4.3 2018-01-10 local gridExtra 2.3 2017-09-09 CRAN (R 3.4.2) gtable 0.2.0 2016-02-26 CRAN (R 3.4.2) inline 0.3.14 2015-04-13 CRAN (R 3.4.3) labeling 0.3 2014-08-23 CRAN (R 3.4.1) lattice 0.20-35 2017-03-25 CRAN (R 3.4.3) lazyeval 0.2.1 2017-10-29 CRAN (R 3.4.3) magrittr 1.5 2014-11-22 CRAN (R 3.4.2) MASS 7.3-47 2017-02-26 CRAN (R 3.4.3) Matrix 1.2-12 2017-11-20 CRAN (R 3.4.3) methods * 3.4.3 2018-01-10 local munsell 0.4.3 2016-02-13 CRAN (R 3.4.2) pillar 1.0.1 2017-11-27 CRAN (R 3.4.3) plyr 1.8.4 2016-06-08 CRAN (R 3.4.2) R6 2.2.2 2017-06-17 CRAN (R 3.4.2) RColorBrewer 1.1-2 2014-12-07 CRAN (R 3.4.1) Rcpp * 0.12.14 2017-11-23 CRAN (R 3.4.3) RcppEigen 0.3.3.3.1 2017-11-20 CRAN (R 3.4.3) reshape2 1.4.3 2017-12-11 CRAN (R 3.4.3) rlang 0.1.6 2017-12-21 CRAN (R 3.4.3) rstan 2.17.2 2017-12-21 CRAN (R 3.4.3) scales 0.5.0 2017-08-24 CRAN (R 3.4.2) StanHeaders 2.17.1 2017-12-20 CRAN (R 3.4.3) stats * 3.4.3 2018-01-10 local stats4 3.4.3 2018-01-10 local stringi 1.1.6 2017-11-17 CRAN (R 3.4.2) stringr 1.2.0 2017-02-18 CRAN (R 3.4.2) tibble 1.4.1 2017-12-25 CRAN (R 3.4.3) tools 3.4.3 2018-01-10 local utf8 1.1.2 2017-12-14 CRAN (R 3.4.3) utils * 3.4.3 2018-01-10 local viridisLite 0.2.0 2017-03-24 CRAN (R 3.4.2)
Thanks in advance