runjags: write.jagsfile – R documentation

Become an expert in R — Interactive courses, Cheat Sheets, certificates and more!

write.jagsfile

Write a complete JAGS model to a text file

Description

Writes the JAGS model, data, initial values and monitored variables etc to a file. The model can then be run using a call to link{run.jags} with the filename as the model argument.

Usage

write.jagsfile(
  runjags.object,
  file,
  remove.tags = TRUE,
  write.data = TRUE,
  write.inits = TRUE
)

write.JAGSfile(
  runjags.object,
  file,
  remove.tags = TRUE,
  write.data = TRUE,
  write.inits = TRUE
)

Arguments

`runjags.object`	a valid (but not necessarily updated) runjags object to be saved to file. No default.
`file`	a filename to which the model will be written. Note that any files already existing in that location will be overwritten with no warning (see `new_unique` for a way to generate unique filenames). No default.
`remove.tags`	should the runjags tags #data#, #inits#, #monitors#, #modules#, #factories#, #residual#, #fitted# and #response# be removed from the original model code before writing it to file? If left in, these may create conflicts with the tags automatically added to the new file.
`write.data`	should the data also be written to file? If FALSE, the model may not run from the file without specifying a new source of data.
`write.inits`	should the data also be written to file? If FALSE, the model may not run from the file without specifying new initial values.

Value

Returns the filename that the model was saved to (invisibly)

References

Lunn D, Jackson C, Best N, Thomas A, Spiegelhalter D (2012). The BUGS book: A practical introduction to Bayesian analysis. CRC press; and Matthew J. Denwood (2016). runjags: An R Package Providing Interface Utilities, Model Templates, Parallel Computing Methods and Additional Distributions for MCMC Models in JAGS. Journal of Statistical Software, 71(9), 1-25. doi:10.18637/jss.v071.i09

Examples

# Set up a model:
# y = m x + c, assuming normal observation errors for y:

# Simulate the data
X <- 1:100
Y <- rnorm(length(X), 2*X + 10, 1)

# Model in the JAGS format
model <- "model { 
for(i in 1 : N){ 
	Y[i] ~ dnorm(true.y[i], precision);
	true.y[i] <- (m * X[i]) + c
} 
m ~ dunif(-1000,1000)
c ~ dunif(-1000,1000) 
precision ~ dexp(1)
}"

# Data and initial values in a named list format, 
# with explicit control over the random number
# generator used for each chain (optional): 
data <- list(X=X, Y=Y, N=length(X))
inits1 <- list(m=1, c=1, precision=1,
.RNG.name="base::Super-Duper", .RNG.seed=1)
inits2 <- list(m=0.1, c=10, precision=1,
.RNG.name="base::Wichmann-Hill", .RNG.seed=2)

## Not run: 
# Compile the model but don't update it (sample=0):
compiled <- run.jags(model=model, monitor=c("m", "c", "precision"), 
data=data, n.chains=2, inits=list(inits1,inits2), sample=0)

# Save the complete model to a file:
filepath <- write.jagsfile(compiled, file='model.txt')

# And run the model from the file:
results <- run.jags(filepath)


## End(Not run)

runjags

Interface Utilities, Model Templates, Parallel Computing Methods and Additional Distributions for MCMC Models in JAGS

v2.2.0-2

GPL-2

Authors

Matthew Denwood [aut, cre], Martyn Plummer [cph] (Copyright holder of the code in src/distributions/DPar1.*, configure.ac, R/rjags_functions.R, and original copyright holder of some modified code where indicated)

Initial release

2021-03-01