martyn_plummer@sourceforge.net committed [c301c7] on prototype

Use Ruppert-Polyak averaging for the step size

martyn_plummer@sourceforge.net committed [d49dce] on Code

Better monitoring of acceptance rate in StepAdapter

martyn_plummer@sourceforge.net committed [1b7168] on Code

Rename package version to 5.0.0-beta

martyn_plummer@sourceforge.net committed [300f3f] on Code

New branch for JAGS 5.0.0

martyn_plummer@sourceforge.net committed [79ae9b] on prototype

Adding JAGS versions of two examples

martyn_plummer@sourceforge.net committed [dbb8b0] on prototype

Updating research notes

martyn_plummer@sourceforge.net committed [6009b4] on Code

Added tag release-5_0_0 for changeset 9ef45ed23014

martyn_plummer@sourceforge.net committed [9ef45e] on Code

Add delayed rejection to MNormal sampler

martyn_plummer@sourceforge.net committed [98d30c] on Code

Add interface to BLAS function dtrmv

martyn_plummer@sourceforge.net committed [e5236f] on Code

Declare function cholesky

martyn_plummer@sourceforge.net committed [000679] on prototype

Prototype code for adaptive random walk Metropolis-Hastings

martyn_plummer@sourceforge.net committed [b1fbe3] on Code

Updates to random walk Metropolis-Hastings

martyn_plummer@sourceforge.net committed [42dbf7] on rjags

Fix initialization bug. Calls to initialize3 were actually calling initialize.

martyn_plummer@sourceforge.net committed [485cd5] on rjags

Update for new initialization system

martyn_plummer@sourceforge.net committed [e8e68e] on Code

New initialization system

martyn_plummer@sourceforge.net committed [b32cc7] on Code

New initialization system for back-compatibility with JAGS 4.

martyn_plummer@sourceforge.net committed [ea14da] on Code

Fail gracefully when given non-invertible matrix as argument

martyn_plummer@sourceforge.net committed [e0e6e6] on Code

Fail gracefully when given non-invertible matrix

martyn_plummer@sourceforge.net committed [17ce43] on Code

Use std::isfinite

martyn_plummer@sourceforge.net committed [73dce6] on Code

Updating R m4 macros (for updated R math library)

stefano andreon posted a comment on discussion Open Discussion

Hi, I have a huge sample (of galaxy clusters coming from the Euclid Space Telescope). Computing the likelihood iterating over the sample (as it is standard in JAGS) takes too long (I want to model the shape of each individual cluster while modeling at the same time the whole population, including the one not sampled, with a non-random and biased sampling in which even the knowledge of how many missed clusters is unknown). It could become faster if I can spread the likelihood computation over the...

martyn_plummer@sourceforge.net committed [d4221c] on Code

Updating the R math library

martyn_plummer@sourceforge.net committed [4c0227] on Code

Clarify inode depth calculations

Matt Denwood modified a comment on ticket #64

Ah yes, if I set both: FCLIBS="/opt/gfortran/lib/gcc/aarch64-apple-darwin20.0/14.2.0/libgcc.a /opt/gfortran/lib/gcc/aarch64-apple-darwin20.0/14.2.0/libquadmath.a /opt/gfortran/lib/gcc/aarch64-apple-darwin20.0/14.2.0/libgfortran.a" And: FFLAGS="-static-libgfortran -static-libquadmath" Then this prevents -lquadmath being passed to the linker. The resulting binary has no runtime dependencies on gfortran/quadmath so that should be fine. I'll add all this to the macOS specific section of the installation...

Matt Denwood posted a comment on ticket #64

Ah yes, if I set both: FCLIBS="/opt/gfortran/lib/gcc/aarch64-apple-darwin20.0/14.2.0/libgcc.a /opt/gfortran/lib/gcc/aarch64-apple-darwin20.0/14.2.0/libquadmath.a /opt/gfortran/lib/gcc/aarch64-apple-darwin20.0/14.2.0/libgfortran.a" And: FFLAGS="-static-libgfortran -static-libquadmath" Then this prevents -lquadmath being generated. The resulting binary has no runtime dependencies on gfortran/quadmath so that should be fine. I'll add all this to the macOS specific section of the installation guide,...

martyn_plummer@sourceforge.net committed [bc4931] on rjags

Fixes for runjags compatibility

martyn_plummer@sourceforge.net committed [528f13] on rjags

Load diag module automatically

martyn_plummer@sourceforge.net committed [2a3d1b] on rjags

Fix bug in as.mcmc.list.mcarray that drops class of return value

martyn_plummer@sourceforge.net committed [be59b4] on rjags

Fix calculation of popt in dic.samples

martyn_plummer@sourceforge.net committed [eb9d71] on rjags

Documentation updates

martyn_plummer@sourceforge.net committed [5597b2] on rjags

For backwarwd compatibility: Restore force.list argument to jags.samples

martyn_plummer@sourceforge.net committed [2af1cb] on Code

Restore dic module as a stub and pre-loaded it in the command line interface

martyn_plummer@sourceforge.net committed [5baa1d] on Code

Fixes for BinomSlicer

Martyn Plummer posted a comment on ticket #64

Last word on this before I sign off for now. If you supply FCLIBS at configure time then this will override the macro, e.g. on Linux I can do FCLIBS="-lgfortran -lm" ./configure ... and this build JAGS without linking to libquadmath (I have omitted a lot of -L/path/to/libs flags but it still seems to work). However, you can still pick up a recursive dependency on libquadmath from a linked library. For example libflexiblas is linked to libquadmath on my Linux desktop so if I rely on flexiblas for...

Matt Denwood modified a comment on ticket #64

Sorry I didn't see this reply when I posted my message just now. I think allowing FCLIBS_USER to override the autoconf macro is a good solution - at least much better than my using find/sed to remove the -lquadmath flag from all Makefiles manually. I already know what the correct linker flags are; I just can't get them to propogate through the configure script correctly. For standard compilation this is obviously a non-issue - it is just for creating portable binaries - so I think an additional environmental...

Matt Denwood posted a comment on ticket #64

Sorry I didn't see this reply when I posted my message just now. I think allowing FCLIBS_USER to override the autoconf macro is a good solution. I already know what the correct linker flags are; I just can't get them to propogate through the configure script correctly. For standard compilation this is obviously a non-issue - it is just for creating portable binaries - so I think an additional environmental variable that only I need to worry about is a good compromise. Having said that, if AC_FC_LIBRARY_LDFLAGS...

Matt Denwood posted a comment on ticket #64

We should certainly try to avoid the libgfortran and libquadmath runtime dependencies, as these are not part of a standard macOS install (they are installed as part of the GNU gfortran binary that Simon provides via https://mac.r-project.org/tools/). However, I think I am now doing that, albeit using a hack... Using the following LDLAGS and LIBS: export LDFLAGS="-static-libgfortran" export LIBS="/opt/gfortran/lib/gcc/aarch64-apple-darwin20.0/14.2.0/libgcc.a /opt/gfortran/lib/gcc/aarch64-apple-darwin20.0/14.2.0/libquadmath.a"...

Martyn Plummer posted a comment on ticket #64

Further investigation of the log file config.log shows that the original linker flags when the test Fortran program is compiled by the configure script were --as-needed -lquadmath. The --as-needed qualifier ensures that you don't link to libquadmath if you are not using any quad-precision floats. Unfortunately the qualifier doesn't make it into FCLIBS as you can see from my example above. So we get an unqualified link to libquadmath even though we are not using any quad-precision arithmetic. One...

Martyn Plummer posted a comment on ticket #64

Sorry I should have spotted the --with-included-ltdl issue, but even I'm getting rusty on the configuration options. The command line interface uses libtool-ltdl to dynamically load the modules so the jags-terminal executable must be linked to either the internally provided library (e.g. on Windows) or the system one (e.g. on Linux). This is not necessary when using JAGS with R which has its own dynamic loading mechanism. The libquadmath dependency is down to the fact that the JAGS library now includes...

Matt Denwood posted a comment on ticket #64

Update 2 The configure option --with-included-ltdl solves the libltdl dependency. There doesn't seem to be any neat way of preventing the -lquadmath flag being generated, but a manual find/sed step between configure and make resolves this (albeit in a hacky way). So the following works for static linkage to both gfortran (including libquadmath/libgcc) and openblas: export PATH="/opt/gfortran/bin/:$PATH" export LDFLAGS="-static-libgfortran" export LIBS="/opt/gfortran/lib/gcc/aarch64-apple-darwin20.0/14.2.0/libgcc.a...

Matt Denwood posted a comment on ticket #64

Update With the following: export LDFLAGS="/opt/gfortran/lib/gcc/aarch64-apple-darwin20.0/14.2.0/libgfortran.a /opt/gfortran/lib/gcc/aarch64-apple-darwin20.0/14.2.0/libgcc.a /opt/gfortran/lib/gcc/aarch64-apple-darwin20.0/14.2.0/libquadmath.a -static-libgfortran" The build succeeds, and the libgfortran.dylib dependency is gone (although I do get clang++: warning: argument unused during compilation: '-static-libgfortran' [-Wunused-command-line-argument]). Unfortunately clang doesn't like -static-libgcc...

Anonymous created ticket #64

Dynamic linkage to libgfortran and libquadmath with JAGS 5.0.0

martyn_plummer@sourceforge.net committed [d177d7] on Code

Manual updates for building on Linux

Martyn Plummer committed [982032] on Code

Describe alternatives mechanism for BLAS/LAPACK on Linux

martyn_plummer@sourceforge.net committed [4728ef] on Code

Update BLAS/LAPACK configuration and Linux build instructions

martyn_plummer@sourceforge.net committed [94e4bf] on Code

Allow static linking of test programs to libcppunit (for Windows)

martyn_plummer@sourceforge.net committed [589df0] on Code

Update manuals

martyn_plummer@sourceforge.net committed [6e5c25] on Code

Fixes for Windows build

Martyn Plummer posted a comment on ticket #21

I would do if I knew who to contact. Can you send a mail to martyn_plummer@sourceforge.net?

Martyn Plummer modified ticket #20

4.3.2 for windows - signed?

Martyn Plummer posted a comment on ticket #20

The R 4.3.2. binary is now digitally signed

JAGS: Just Another Gibbs Sampler updated /JAGS/4.x/Windows/README

JAGS: Just Another Gibbs Sampler released /JAGS/4.x/Windows/JAGS-4.3.2.exe

Martyn Plummer committed [7204a7] on Code

Remove pragma omp critical constructs from the glm module to allow parallel processing

Martyn Plummer committed [d8184f] on Code

Different chains use different cholmod_common workspaces and so can be run in parallel

martyn_plummer@sourceforge.net committed [9a7645] on Code

Moving SuiteSparse functions out of the glm module and into the main JAGS library

martyn_plummer@sourceforge.net committed [6f6382] on Code

Sampling methods in the glm module store a pointer to their own cholmod_common workspace.

martyn_plummer@sourceforge.net committed [f790bb] on Code

Updates to user manual

martyn_plummer@sourceforge.net committed [03bff1] on rjags

Bug fix drop -> drop.tags

martyn_plummer@sourceforge.net committed [0b7641] on rjags

Adding more support for mcarrays and tagged arrays

martyn_plummer@sourceforge.net committed [c8a652] on rjags

Support for getting and setting number of threads

martyn_plummer@sourceforge.net committed [fa39cd] on Code

Allow setting number of threads in a model object

martyn_plummer@sourceforge.net committed [434539] on Code

Use reversible update for random effects sampling

martyn_plummer@sourceforge.net committed [c7d2c5] on Code

Fix ancillary updating in updateSigma

martyn_plummer@sourceforge.net committed [72cc05] on Code

Fix ancillary update in updateSigma by not constraining _sigma to be positive.

martyn_plummer@sourceforge.net committed [5964bb] on Code

Tidying up

martyn_plummer@sourceforge.net committed [edb64d] on Code

Avoid overflow when sampling from truncated logistic distribution

martyn_plummer@sourceforge.net committed [1dfc52] on Code

More updates to the manual

martyn_plummer@sourceforge.net committed [b48af9] on Code

Updates to manual

martyn_plummer@sourceforge.net committed [495c9c] on Code

Updating manual

martyn_plummer@sourceforge.net committed [3965eb] on Code

Updating command line interface for changes to monitors

martyn_plummer@sourceforge.net committed [874f2e] on Code

Adding traceweight monitor

martyn_plummer@sourceforge.net committed [c7cca5] on Code

LOO monitors are inversely weighted by the likelihood

Anonymous created ticket #63

JAGS 4.3.2 misisng for Windows

Martyn Plummer committed [189432] on Code

Allow _observed_ or _observations_ to denote all observed stochastic nodes

Martyn Plummer committed [28d319] on Code

randomSample will not changes observed nodes, or the fixes parts of partly observed nodes.

Martyn Plummer committed [21a7fd] on Code

Adding logLikelihood method for partly observed multivariate normal.

Martyn Plummer committed [cb7ad5] on Code

Find weighted and total stats by computing on the string description.

Martyn Plummer committed [06c78c] on Code

Using new Node::logLikelihood method for likelihood monitors

martyn_plummer@sourceforge.net committed [1c94ff] on Code

Adding virtual Node::logLikelihood method

martyn_plummer@sourceforge.net committed [1fbc95] on Code

Documenting new monitor system

Martyn Plummer committed [acbd30] on Code

Adding infrastructure for partially observed nodes

martyn_plummer@sourceforge.net committed [49597d] on rjags

Fixes to mcarray class

Anonymous created ticket #28

Ability to add custom functions

martyn_plummer@sourceforge.net committed [19aef0] on rjags

Fixes to print method for mcarray objects

martyn_plummer@sourceforge.net committed [e93306] on rjags

Implement dimtags of an mcarray object as a separate attribute

martyn_plummer@sourceforge.net committed [b32f54] on rjags

Handle reserved names starting with underscore in parse.varnames

martyn_plummer@sourceforge.net committed [52c105] on rjags

Commit missing man page for waic.samples

martyn_plummer@sourceforge.net committed [796413] on rjags

Aligning output of waic.samples with its documentation

martyn_plummer@sourceforge.net committed [c02b9a] on rjags

Updating waic.samples

martyn_plummer@sourceforge.net committed [d4ad51] on Code

Distinguishing density and likelihood in the diag module.

Anonymous created ticket #21

Solution Vetting request

martyn_plummer@sourceforge.net committed [8cdcfa] on Code

Add value names to SArray

martyn_plummer@sourceforge.net committed [606797] on rjags

Update for API changes in the JAGS library

martyn_plummer@sourceforge.net committed [debc2f] on rjags

Updates for changes to dim tags

martyn_plummer@sourceforge.net committed [533622] on Code

Change dim tags to be an enumeration, not a string

Nick Beeton modified a comment on discussion Help

@martyn_plummer I've got JAGS 5.0.0 and rjags_5-1 running with my code... but it seems to have some strange behaviour. Even when turning the mixture-node stuff off, for some reason (among other things) it is giving detection probability p as around 0.1 to 0.2, while JAGS 4.3.0 on exactly the same code is giving a much more reasonable looking 0.75 (the vast majority of individuals, 90%+, in the capture matrix have no gaps in their capture history). After a long time the distribution is slowly creeping...

elizap posted a comment on discussion Help

Hi all, I'm transfering my project to HPC and in doing so I had to reinstall jags. I set the env variable for finding pkconfig and in the hpc terminal using my home folder installed R version, installing and loading rjags actually worked! However on my HPC they also offer interactive RStudio Server instances which I prefer for my tasks, which use the hpc-wide installation of R. But rjags didn't link. So I set environment variables (LD_LIBRARY_PATH, JAGS_HOME, PKG_CONFIG_PATH) to point to my jags...

Nick Beeton modified a comment on discussion Help

@martyn_plummer I've got JAGS 5.0.0 and rjags_5-1 running with my code... but it seems to have some strange behaviour. Even when turning the mixture-node stuff off, for some reason (among other things) it is giving detection probability p as around 0.1 to 0.2, while JAGS 4.3.0 on exactly the same code is giving a much more reasonable looking 0.75 (the vast majority of individuals, 90%+, in the capture matrix have no gaps in their capture history). After a long time the distribution is slowly creeping...

Nick Beeton posted a comment on discussion Help

@martyn_plummer I've got JAGS 5.0.0 and rjags_5-1 running with my code... but it seems to have some strange behaviour. Even when turning the mixture-node stuff off, for some reason it is giving detection probability p as around 0.1 to 0.2, while JAGS 4.3.0 on exactly the same code is giving a much more reasonable looking 0.75 (the vast majority of individuals, 90%+, in the capture matrix have no gaps in their capture history). After a long time the distribution is slowly creeping up so it may be...