allow creating tar files for predicted distribution + rename argument of PrepData/Prep4HPC

Author: elgabbas

DESCRIPTION

@@ -3,7 +3,7 @@ Package: IASDT.R
 Title: Modelling the distribution of invasive alien plant species in
     Europe
 Version: 0.1.03
-Date: 2025-03-06
+Date: 2025-03-07
 Authors@R: 
     person("Ahmed", "El-Gabbas", , "ahmed.el-gabbas@ufz.de", role = c("aut", "cre"),
            comment = c(ORCID = "0000-0003-2225-088X"))

R/Mod_Postprocess.R

@@ -741,7 +741,6 @@ Mod_Prep_TF <- function(
 # Mod_Postprocess_2_CPU ----
 ## |------------------------------------------------------------------------| #
 
-
 #' @export
 #' @rdname Mod_postprocessing
 #' @name Mod_postprocessing
@@ -758,7 +757,7 @@ Mod_Postprocess_2_CPU <- function(
       "MRI-ESM2-0", "UKESM1-0-LL"),
     CC_Scenario = c("ssp126", "ssp370", "ssp585"),
     RC_NCores = 8L, Pred_Clamp = TRUE, Fix_Efforts = "q90", Fix_Rivers = "q90",
-    Pred_NewSites = TRUE) {
+    Pred_NewSites = TRUE, Tar = TRUE) {
 
   .StartTime <- lubridate::now(tzone = "CET")
 
@@ -949,10 +948,11 @@ Mod_Postprocess_2_CPU <- function(
     Path_Model = Path_Model, Hab_Abb = Hab_Abb, EnvFile = EnvFile,
     NCores = NCores, Pred_Clamp = Pred_Clamp, Fix_Efforts = Fix_Efforts,
     Fix_Rivers = Fix_Rivers, Pred_NewSites = Pred_NewSites, UseTF = UseTF,
-    TF_Environ = TF_Environ, Temp_Dir = Temp_Dir, Temp_Cleanup = Temp_Cleanup,
-    TF_use_single = TF_use_single, LF_NCores = LF_NCores, LF_Check = LF_Check,
+    TF_Environ = TF_Environ, TF_use_single = TF_use_single,
+    LF_NCores = LF_NCores, LF_Check = LF_Check,
     LF_Temp_Cleanup = LF_Temp_Cleanup, LF_Only = FALSE,
-    LF_Commands_Only = FALSE, CC_Models = CC_Models, CC_Scenario = CC_Scenario)
+    LF_Commands_Only = FALSE, Temp_Dir = Temp_Dir, Temp_Cleanup = Temp_Cleanup,
+    Tar = Tar, CC_Models = CC_Models, CC_Scenario = CC_Scenario)
 
   invisible(gc())
 

R/Mod_Predict_Maps.R

@@ -54,6 +54,8 @@
 #' @param CC_Scenario Character vector. Climate scenarios for future
 #'   predictions. Available options are: `c("ssp126", "ssp370", "ssp585")`
 #'   (default).
+#' @param Tar Logical. Whether to compress the add files into a single `*.tar`
+#'   file (without compression). Default: `TRUE`.
 #' @export
 #' @name Predict_Maps
 #' @author Ahmed El-Gabbas
@@ -68,7 +70,7 @@ Predict_Maps <- function(
     Pred_NewSites = TRUE, UseTF = TRUE, TF_Environ = NULL,
     TF_use_single = FALSE, LF_NCores = NCores, LF_Check = FALSE,
     LF_Temp_Cleanup = TRUE, LF_Only = FALSE, LF_Commands_Only = FALSE,
-    Temp_Dir = "TEMP_Pred", Temp_Cleanup = TRUE,
+    Temp_Dir = "TEMP_Pred", Temp_Cleanup = TRUE, Tar = TRUE,
     CC_Models = c(
       "GFDL-ESM4", "IPSL-CM6A-LR", "MPI-ESM1-2-HR",
       "MRI-ESM2-0", "UKESM1-0-LL"),
@@ -1399,6 +1401,36 @@ Predict_Maps <- function(
     col.names = TRUE, file = Path_Summary_txt_Shiny, quote = FALSE,
     fileEncoding = "UTF-8")
 
+  if (Tar) {
+
+    IASDT.R::CatTime("Create tar file for prediction files", Level = 1)
+
+    # Directory to save the tar file
+    TarDir <- dirname(Path_Summary_RData_Shiny)
+    # Path to the tar file
+    TarFile <- IASDT.R::Path(TarDir, "Predictions.tar")
+    # List of directories in the prediction folder. All directories will be
+    # included in the tar file
+    TarFiles <- list.dirs(
+      path = TarDir, full.names = FALSE, recursive = FALSE) %>%
+      paste(collapse = " ") %>%
+      # Add the summary files to the list
+      paste(
+        "Prediction_Summary.RData", "Prediction_Summary_Shiny.txt",
+        collapse = " ")
+
+    # Command to create the tar file
+    Command <- stringr::str_glue(
+      'cd {fs::path_abs(TarDir)}; tar -cf {basename(TarFile)} -b 2048 \\
+    {TarFiles}')
+
+    # Create tar file
+    system(Command)
+
+    # Change the permission of the tar file
+    Sys.chmod(TarFile, "755", use_umask = FALSE)
+  }
+
   # # ................................................................... ###
   # # ..................................................................... ###
 

R/Mod_Prep4HPC.R

@@ -11,16 +11,16 @@
 #' ([Tikhonov et al.](https://doi.org/10.1002/ecy.2929)), initializing models,
 #' and creating HPC execution commands. The function supports parallel
 #' processing and offers the option to include or exclude phylogenetic tree
-#' data.<br/><br/> The internal **`Mod_PrepData`** function is used to prepare
+#' data.<br/><br/> The `Mod_PrepData` function is used to prepare
 #' habitat-specific data for Hmsc models. This function processes environmental
 #' and species presence data, reads environment variables from a file, verifies
 #' paths, loads and filters species data based on habitat type and minimum
 #' presence grid cells per species, and merges various environmental layers
 #' (e.g., CHELSA Bioclimatic variables, habitat coverage, road and railway
 #' intensity, sampling efforts) into a single dataset. Processed data is saved
 #' to disk as an `*.RData` file.
-#' @param Path_Model Character. Directory path where all output files, including
-#'   the models to be fitted, will be saved.
+#' @param DirName Character. Directory name, without its parents, where the 
+#'   models will be saved. This directory will be created.
 #' @param GPP Logical. Whether to fit spatial random effect using Gaussian
 #'   Predictive Process. Defaults to `TRUE`. If `FALSE`, non-spatial models will
 #'   be fitted.
@@ -183,7 +183,7 @@
 #'   plant species
 
 Mod_Prep4HPC <- function(
-    Hab_Abb = NULL, Path_Model = NULL,
+    Hab_Abb = NULL, DirName = NULL,
     MinEffortsSp = 100L, PresPerSpecies = 80L, EnvFile = ".env",
     GPP = TRUE, GPP_Dists = NULL, GPP_Save = TRUE,
     GPP_Plot = TRUE, MinLF = NULL, MaxLF = NULL,
@@ -212,7 +212,7 @@ Mod_Prep4HPC <- function(
   .StartTime <- lubridate::now(tzone = "CET")
 
   CheckNULL <- c(
-    "Path_Model", "PresPerSpecies", "thin", "samples",
+    "DirName", "PresPerSpecies", "thin", "samples",
     "MemPerCpu", "Path_Hmsc", "Hab_Abb")
   IsNull <- purrr::map_lgl(CheckNULL, ~ is.null(get(.x)))
 
@@ -264,7 +264,7 @@ Mod_Prep4HPC <- function(
     M_Name_Fit <- Chain <- Post_Missing <- Command_HPC <- Command_WS <-
     Post_Path <- Path_ModProg <- TaxaInfoFile <- Path_Grid <- EU_Bound <-
     Path_PA <- NAME_ENGL <- NSp <- Species_File <- File <- ias_id <-
-    PA <- PA_model <- PA_file <- PA_model_file <- NULL
+    PA <- PA_model <- PA_file <- PA_model_file <- Path_Model <- NULL
 
   if (isFALSE(VerboseProgress)) {
     sink(file = nullfile())
@@ -286,6 +286,7 @@ Mod_Prep4HPC <- function(
     "TaxaInfoFile", "DP_R_Taxa_info", FALSE, TRUE,
     "EU_Bound", "DP_R_EUBound", FALSE, TRUE,
     "Path_Grid", "DP_R_Grid_processed", TRUE, FALSE,
+    "Path_Model", "DP_R_Model_path", FALSE, FALSE,
     "Path_PA", "DP_R_PA", TRUE, FALSE)
 
   # Check if Python executable exists
@@ -297,6 +298,11 @@ Mod_Prep4HPC <- function(
   IASDT.R::AssignEnvVars(EnvFile = EnvFile, EnvVarDT = EnvVars2Read)
   rm(EnvVars2Read, envir = environment())
 
+  Path_Model <- IASDT.R::Path(Path_Model, DirName)
+  if (fs::dir_exists(Path_Model)) {
+    stop("Model directory already exists: ", Path_Model, call. = FALSE)
+  }
+  fs::dir_create(Path_Model)
 
   Path_GridR <- IASDT.R::Path(Path_Grid, "Grid_10_Land_Crop.RData")
   if (!file.exists(Path_GridR)) {
@@ -319,7 +325,7 @@ Mod_Prep4HPC <- function(
     function(x) get(x, envir = parent.env(env = environment()))) %>%
     stats::setNames(AllArgs)
 
-  CharArgs <- c("Hab_Abb", "Path_Model", "Path_Hmsc", "EnvFile", "BioVars")
+  CharArgs <- c("Hab_Abb", "DirName", "Path_Hmsc", "EnvFile", "BioVars")
   IASDT.R::CheckArgs(AllArgs = AllArgs, Args = CharArgs, Type = "character")
 
   LogicArgs <- c(
@@ -446,8 +452,7 @@ Mod_Prep4HPC <- function(
   DT_All <- IASDT.R::Mod_PrepData(
     Hab_Abb = Hab_Abb, MinEffortsSp = MinEffortsSp, ExcludeCult = ExcludeCult,
     ExcludeZeroHabitat = ExcludeZeroHabitat, PresPerSpecies = PresPerSpecies,
-    EnvFile = EnvFile, Path_Model = Path_Model,
-    VerboseProgress = VerboseProgress)
+    EnvFile = EnvFile, DirName = DirName, VerboseProgress = VerboseProgress)
 
   IASDT.R::CatSep(Rep = 1, Extra1 = 1, Extra2 = 2)
 

R/Mod_PrepData.R

@@ -9,17 +9,17 @@
 #' @author Ahmed El-Gabbas
 
 Mod_PrepData <- function(
-    Hab_Abb = NULL, MinEffortsSp = 100L, ExcludeCult = TRUE,
+    Hab_Abb = NULL, DirName = NULL, MinEffortsSp = 100L, ExcludeCult = TRUE,
     ExcludeZeroHabitat = TRUE, PresPerSpecies = 80L, EnvFile = ".env",
-    Path_Model = NULL, VerboseProgress = TRUE) {
+    VerboseProgress = TRUE) {
 
   # # ..................................................................... ###
 
   # # |||||||||||||||||||||||||||||||||||
   # Check input parameters ----
   # # |||||||||||||||||||||||||||||||||||
 
-  CheckNULL <- c("Hab_Abb", "Path_Model", "EnvFile")
+  CheckNULL <- c("Hab_Abb", "DirName", "EnvFile")
   IsNull <- purrr::map_lgl(CheckNULL, ~ is.null(get(.x)))
   if (any(IsNull)) {
     stop(
@@ -40,7 +40,7 @@ Mod_PrepData <- function(
   # https://www.r-bloggers.com/2019/08/no-visible-binding-for-global-variable/
   SpeciesID <- Species_name <- Species_File <- PA <- Path_Rivers <-
     cell <- Path_PA <- Path_Grid <- Path_Grid_Ref <- Path_CLC <-
-    Path_Roads <- Path_Rail <- Path_Bias <- Path_CHELSA <-
+    Path_Roads <- Path_Rail <- Path_Bias <- Path_CHELSA <- Path_Model <-
     EU_Bound <- SpPA <- NPres <- Grid_R <- IAS_ID <- NULL
 
   # # ..................................................................... ###
@@ -51,7 +51,7 @@ Mod_PrepData <- function(
     AllArgs,
     function(x) get(x, envir = parent.env(env = environment()))) %>%
     stats::setNames(AllArgs)
-  CharArgs <- c("EnvFile", "Hab_Abb", "Path_Model")
+  CharArgs <- c("EnvFile", "Hab_Abb", "DirName")
   IASDT.R::CheckArgs(AllArgs = AllArgs, Args = CharArgs, Type = "character")
   IASDT.R::CheckArgs(
     AllArgs = AllArgs, Args = c("MinEffortsSp", "PresPerSpecies"),
@@ -68,7 +68,6 @@ Mod_PrepData <- function(
       call. = FALSE)
   }
 
-  fs::dir_create(Path_Model)
 
   # # ..................................................................... ###
 
@@ -91,11 +90,18 @@ Mod_PrepData <- function(
     "Path_Rail", "DP_R_Railways_processed", TRUE, FALSE,
     "Path_Bias", "DP_R_Efforts_processed", TRUE, FALSE,
     "Path_Rivers", "DP_R_Rivers_processed", FALSE, TRUE,
+    "Path_Model", "DP_R_Model_path", FALSE, FALSE,
     "EU_Bound", "DP_R_EUBound", FALSE, TRUE)
   # Assign environment variables and check file and paths
   IASDT.R::AssignEnvVars(EnvFile = EnvFile, EnvVarDT = EnvVars2Read)
   rm(EnvVars2Read, envir = environment())
 
+  Path_Model <- IASDT.R::Path(Path_Model, DirName)
+  if (fs::dir_exists(Path_Model)) {
+    stop("Model directory already exists: ", Path_Model, call. = FALSE)
+  }
+  fs::dir_create(Path_Model)
+
   # # ..................................................................... ###
 
   # # |||||||||||||||||||||||||||||||||||

README.md

@@ -74,4 +74,4 @@ If you use the `IASDT.R` package, please cite it as:
 > <a href="https://biodt.eu" target="_blank">https://biodt.eu</a>.
 
 <span style="     color: grey !important;">Last update:
-2025-03-06</span>
+2025-03-07</span>