Package index • cmdstanr

Package overview and global options

An overview of the package and how it differs from RStan.

cmdstanr-package cmdstanr CmdStanR: CmdStanR: the R interface to CmdStan
cmdstanr_global_options: CmdStanR global options

Installing and setting the path to CmdStan

Install CmdStan, assuming the necessary C++ toolchain.

install_cmdstan() rebuild_cmdstan() cmdstan_make_local() check_cmdstan_toolchain(): Install CmdStan or clean and rebuild an existing installation
set_cmdstan_path() cmdstan_path() cmdstan_version(): Get or set the file path to the CmdStan installation

Running CmdStan from R

Run CmdStan from R.

cmdstan_model() compile_stan_file(): Create a new CmdStanModel object
stan_build_info() print(<stan_build_info>): What is known about how a CmdStan executable was built
CmdStanModel: CmdStanModel objects
build_info(): What is known about how the model's executable was built
check_syntax() check_syntax_stan_file(): Check syntax of a Stan program
cmdstan_defaults(): Get CmdStan default argument values
diagnose(): Run Stan's diagnose method
expose_functions(): Expose Stan functions to R
format() format_stan_file(): Run stanc's auto-formatter on the model code.
generate_quantities(): Run Stan's standalone generated quantities method
is_current(): Check whether the model can run without a rebuild
laplace(): Run Stan's Laplace algorithm
model-method-model-info: Access information from a CmdStanModel object
optimize(): Run Stan's optimization algorithms
pathfinder(): Run Stan's Pathfinder Variational Inference Algorithm
sample(): Run Stan's MCMC algorithms
sample_mpi(): Run Stan's MCMC algorithms with MPI
variables() variables_stan_file(): Input and output variables of a Stan program
variational(): Run Stan's variational approximation algorithms
cmdstanr_example() print_example_program(): Fit models for use in examples

Fitted model objects and methods

CmdStanMCMC: CmdStanMCMC objects
CmdStanMLE: CmdStanMLE objects
CmdStanLaplace: CmdStanLaplace objects
CmdStanVB: CmdStanVB objects
CmdStanPathfinder: CmdStanPathfinder objects
CmdStanGQ: CmdStanGQ objects
CmdStanDiagnose: CmdStanDiagnose objects
cmdstan_summary() cmdstan_diagnose(): Run CmdStan's stansummary and diagnose utilities
code(): Return Stan code
command(): Return the command that ran CmdStan
constrain_variables(): Transform a set of unconstrained parameter values to the constrained scale
diagnostic_summary(): Sampler diagnostic summaries and warnings
draws(): Extract posterior draws
fitted_params_files(): Extract the fitted-parameter CSV files used for generated quantities
grad_log_prob(): Calculate the log-probability and the gradient w.r.t. each input for a given vector of unconstrained parameters
gradients(): Extract gradients after diagnostic mode
hessian(): Calculate the log-probability, the gradient w.r.t. each input, and the Hessian for a given vector of unconstrained parameters
init(): Extract user-specified initial values
init_model_methods(): Compile additional methods for accessing the model log-probability function and parameter constraining and unconstraining.
inv_metric(): Extract inverse metric (inverse mass matrix) after MCMC
log_prob(): Calculate the log-probability given a provided vector of unconstrained parameters.
loo(): Leave-one-out cross-validation (LOO-CV)
lp() lp_approx(): Extract log probability (target)
materialize(): Materialize model object
metadata(): Extract metadata from CmdStan CSV files
mle(): Extract point estimate after optimization
mode(): Extract the mode used for a Laplace approximation
num_chains(): Extract the number of chains
output(): Access console output
profiles(): Return profiling data
return_codes(): Extract return codes from CmdStan
sampler_diagnostics(): Extract sampler diagnostics after MCMC
save_object(): Save fitted model object to a file
save_output_files() save_latent_dynamics_files() save_profile_files() save_data_file() save_config_files() save_metric_files() output_files() profile_files() latent_dynamics_files() data_file() config_files() metric_files(): Save output and data files
summary(): Compute a summary table of estimates and diagnostics
time(): Report timing of CmdStan runs
unconstrain_draws(): Transform all parameter draws to the unconstrained scale
unconstrain_variables(): Transform a set of parameter values to the unconstrained scale
expose_functions(): Expose Stan functions to R

Other tools

read_cmdstan_csv() as_cmdstan_fit(): Read CmdStan CSV files into R
write_stan_json(): Write data to a JSON file readable by CmdStan
write_stan_file(): Write Stan code to a file
print_stan_file(): Print a Stan file with syntax highlighting in Quarto and R Markdown
draws_to_csv(): Write posterior draws objects to CSV files suitable for running standalone generated quantities with CmdStan.
as_mcmc.list(): Convert CmdStanMCMC to mcmc.list
as_draws(<CmdStanMCMC>) as_draws(<CmdStanMLE>) as_draws(<CmdStanLaplace>) as_draws(<CmdStanVB>) as_draws(<CmdStanGQ>) as_draws(<CmdStanPathfinder>): Create a draws object from a CmdStanR fitted model object
as.CmdStanMCMC() as.CmdStanMLE() as.CmdStanLaplace() as.CmdStanVB() as.CmdStanPathfinder() as.CmdStanGQ() as.CmdStanDiagnose(): Coercion methods for CmdStan objects

Using CmdStanR with knitr and R Markdown

register_knitr_engine(): Register CmdStanR's knitr engine for Stan
eng_cmdstan(): CmdStan knitr engine for Stan