Skip to contents

This function prepares cross-validated Hmsc models for fitting using HPC. It handles data preparation, model initialisation, and generation of SLURM commands.

Usage

mod_CV_fit(
  path_model = NULL,
  CV_name = c("CV_Dist", "CV_Large"),
  Partitions = NULL,
  env_file = ".env",
  init_par = NULL,
  job_name = "CV_Models",
  updater = list(Gamma2 = FALSE, GammaEta = FALSE),
  align_posterior = TRUE,
  to_JSON = FALSE,
  SLURM_prepare = TRUE,
  memory_per_cpu = NULL,
  job_runtime = NULL,
  path_Hmsc = NULL,
  precision = 64,
  ...
)

Arguments

path_model

Character. Path to a saved model file (*.qs2).

CV_name

Character vector. Column name(s) in the model input data to be used to cross-validate the models (see mod_prepare_data and mod_CV_prepare). The function allows the possibility of using more than one way of assigning grid cells into cross-validation folders. If multiple names are provided, separate cross-validation models will be fitted for each cross-validation type. Currently, there are three cross-validation strategies: CV_SAC, CV_Dist, and CV_Large. Defaults to c("CV_Dist", "CV_Large").

Partitions

A vector for cross-validation created by Hmsc::createPartition or similar. Defaults to NULL, which means to use column name(s) provided in the CV_name argument. If the Partitions vector is provided, the label used in the output files will be CV_Custom.

env_file

Character. Path to the environment file containing paths to data sources. Defaults to .env.

init_par

a named list of parameter values used for initialisation of MCMC states. See Hmsc::computePredictedValues for more information. Default: NULL.

job_name

Character. Name of the submitted job(s) for SLURM. Default: CV_Models.

updater

named list. Which conditional updaters should be omitted? See Hmsc::computePredictedValues for more information. Defaults to list(Gamma2 = FALSE, GammaEta = FALSE) to disable the following warnings: setting updater$Gamma2=FALSE due to specified phylogeny matrix and setting updater$GammaEta=FALSE: not implemented for spatial methods 'GPP' and 'NNGP'.

align_posterior

Logical. Whether the posterior of each chains should be aligned. See Hmsc::computePredictedValues for more information. Default: TRUE.

to_JSON

Logical. Whether to convert unfitted models to JSON before saving to RDS file. Default: FALSE.

SLURM_prepare

Logical. Whether to prepare SLURM command files. If TRUE (default), the SLURM commands will be saved to disk using the mod_SLURM function.

memory_per_cpu

Character. Memory allocation per CPU core. Example: "32G" for 32 gigabytes. Defaults to "64G".

job_runtime

Character. Maximum allowed runtime for the job. Example: "01:00:00" for one hour. Required — if not provided, the function throws an error.

path_Hmsc

Character. Path to the Hmsc-HPC installation.

precision

Integer (either 32 or 64). Defines the floating-point precision mode for Hmsc-HPC sampling (–fp 32 or –fp 64). The default is 64, which is the default precision in Hmsc-HPC.

...

Additional arguments passed to the mod_SLURM function.

Details

The function copies part of the Hmsc::computePredictedValues function, which currently does not support performing cross-validation using Hmsc-HPC.

Author

Ahmed El-Gabbas