first commit.

Author: marcnadon

.Rbuildignore

@@ -0,0 +1,2 @@
+^.*\.Rproj$
+^\.Rproj\.user$

.gitignore

@@ -0,0 +1,4 @@
+.Rproj.user
+.Rhistory
+.RData
+.Ruserdata

Calibr.Rproj

@@ -0,0 +1,21 @@
+Version: 1.0
+
+RestoreWorkspace: Default
+SaveWorkspace: Default
+AlwaysSaveHistory: Default
+
+EnableCodeIndexing: Yes
+UseSpacesForTab: Yes
+NumSpacesForTab: 2
+Encoding: UTF-8
+
+RnwWeave: knitr
+LaTeX: pdfLaTeX
+
+AutoAppendNewline: Yes
+StripTrailingWhitespace: Yes
+
+BuildType: Package
+PackageUseDevtools: Yes
+PackageInstallArgs: --no-multiarch --with-keep.source
+PackageRoxygenize: rd,collate,namespace

DESCRIPTION

@@ -0,0 +1,25 @@
+Package: Calibr
+Type: Package
+Title: Standardization of population abundance datasets
+Version: 0.0.10
+Author: Eric Fletcher, Marc Nadon
+Maintainer: The package maintainer <[email protected]>
+Description: More about what it does (maybe more than one line)
+    Use four spaces when indenting paragraphs within the Description.
+License: file LICENSE
+Encoding: UTF-8
+LazyData: true
+Depends:
+    R (>= 3.0.0),
+Imports:
+    MASS,
+    methods,
+    utils,
+    plyr,
+    dplyr,
+    data.table,
+    boot,
+    glmmTMB,
+    pbapply,
+    parallel
+RoxygenNote: 6.0.1

LICENSE

@@ -0,0 +1,5 @@
+Software code created by U.S. Government employees is not subject to copyright in the United States (17 U.S.C.
+§105). The United States/Department of Commerce reserve all rights to seek and obtain copyright protection in
+countries other than the United States for Software authored in its entirety by the Department of Commerce. To
+this end, the Department of Commerce hereby grants to Recipient a royalty-free, nonexclusive license to use,
+copy, and create derivative works of the Software outside of the United States.

NAMESPACE

@@ -0,0 +1,31 @@
+# Generated by roxygen2: do not edit by hand
+
+export(calibrate_dataset)
+export(export_results)
+export(gcf_glm)
+export(gcf_glm_apply)
+export(gcf_glmm)
+export(load_dataset)
+export(rep_summary)
+export(run_calibr)
+import(data.table)
+import(methods)
+import(stats)
+importFrom(MASS,mvrnorm)
+importFrom(boot,inv.logit)
+importFrom(boot,logit)
+importFrom(dplyr,arrange_)
+importFrom(glmmTMB,glmmTMB)
+importFrom(glmmTMB,ranef)
+importFrom(parallel,clusterEvalQ)
+importFrom(parallel,detectCores)
+importFrom(parallel,makeCluster)
+importFrom(parallel,parLapply)
+importFrom(parallel,stopCluster)
+importFrom(pbapply,pblapply)
+importFrom(pbapply,pboptions)
+importFrom(plyr,.)
+importFrom(plyr,daply)
+importFrom(plyr,ddply)
+importFrom(utils,read.csv)
+importFrom(utils,write.csv)

R/calibr.R

@@ -0,0 +1,11 @@
+#' Calibr: A tool to standardize species population aboundance.
+#'
+#' Calibr is a R-Package designed to process highly diverse coral reef species datasets and to
+#' analyse with Generalized Linear Models (GLM) to obtian standarization factors.
+#'
+#' @import methods
+#' @importFrom utils read.csv
+#'
+#' @docType package
+#' @name Calibr
+NULL

R/calibrate_dataset.R

@@ -0,0 +1,63 @@
+#Bindings for "global variables" used in calibrate_dataset
+if(getRversion() >= "2.15.1")  {
+  utils::globalVariables(c("GCF.SOURCE",
+                           "GROUP",
+                           "OPUE",
+                           "OPUE.CAL",
+                           "POS",
+                           "POS.CAL",
+                           "POS.GCF",
+                           "PRES",
+                           "PRES.CAL",
+                           "PRES.GCF"))
+}
+
+#' Convert original dataset using the calculated GCFs
+#'
+#' @param ORIG Original Survey Dataset
+#' @param GCFs Gear calibration factors obtained from gcf_glmm function.
+#' @param std_method Standard gear METHOD
+#'
+#' @import data.table
+#' @importFrom boot inv.logit
+#'
+#' @export
+calibrate_dataset <- function (ORIG,std_method, GCFs) {
+
+  D <- data.table(ORIG)
+  GCFs <- data.table(GCFs,keep.rownames=T)
+  colnames(GCFs) <- c("GROUP","PRES.GCF","POS.GCF")
+
+  S.pres  <- D[,list(PRES=mean(PRESENCE)),by=list(GROUP,METHOD,BLOCK)]
+  S.pres  <- S.pres[,list(PRES=mean(PRES)),by=list(GROUP,METHOD)]
+
+  S.pos   <- D[PRESENCE>0,list(POS=mean(DENSITY)),by=list(GROUP,METHOD,BLOCK)]
+  S.pos   <- S.pos[,list(POS=mean(POS)),by=list(GROUP,METHOD)]
+
+  S       <- merge(S.pres,S.pos)
+  S$OPUE  <- S$PRES*S$POS
+
+  S$PRES.CAL <- S$PRES
+  S$POS.CAL  <- S$POS
+  S$OPUE.CAL <- S$OPUE
+
+  S <- merge(S,GCFs,by="GROUP",all.x=T)
+  S <- data.table(S)
+
+  # Fill GROUPs with no GCF with the Global ones
+  S$GCF.SOURCE <-"Group-specific"
+  S[is.na(PRES.GCF)]$GCF.SOURCE <- "Global"
+  S[is.na(PRES.GCF)]$PRES.GCF <- GCFs[1,]$PRES.GCF
+  S[is.na(POS.GCF)]$POS.GCF <- GCFs[1,]$POS.GCF
+
+  S[METHOD!=std_method]$PRES.CAL <- inv.logit(S[METHOD!=std_method]$PRES.GCF+logit(S[METHOD!=std_method]$PRES ))
+  S[METHOD!=std_method]$POS.CAL  <- S[METHOD!=std_method]$POS/S[METHOD!=std_method]$POS.GCF
+  S[METHOD!=std_method]$OPUE.CAL <- S[METHOD!=std_method]$PRES.CAL*S[METHOD!=std_method]$POS.CAL
+
+  # Re-organize
+  S <- subset(S,select=c(GROUP,METHOD,GCF.SOURCE,PRES.GCF,POS.GCF,PRES,PRES.CAL,POS,POS.CAL,OPUE,OPUE.CAL))
+  S[,4:ncol(S)] <- round(S[,4:ncol(S)],2)
+
+  return(S)
+
+}

R/data.R

@@ -0,0 +1,37 @@
+
+#'NOAA Pacific RAMP, Small Belt Transect, 2002-2010
+#'
+#'Dataset from Coral Reef Fish Surveys, conducted by the NOAA Pacific Reef
+#'Assessment and Monitoring Program (RAMP). The survey area includes the
+#'Main and Northwest Hawaiian Islands, the Mariana Archipelago, and various
+#'remote islands in the central pacific.
+#'
+#'@format A data.frame with 263580 rows, and 6 fields:
+#'\describe{
+#'  \item{BLOCK}{Spacetime temporial strata.}
+#'  \item{REP}{Replicate, survey site.}
+#'  \item{GROUP}{Species or taxinominal grouping.}
+#'  \item{METHOD}{Survey method used.}
+#'  \item{DENSITY}{Group abundance of positive observations.}
+#'  \item{PRESENCE}{Proportion of presence over absence of a group at a survey site.}
+#'}
+#'
+#'@source \url{https://www.pifsc.noaa.gov/library/pubs/admin/PIFSC_Admin_Rep_11-08.pdf}
+"SMALL_UNPAIR"
+
+#'SIMDATA: Simulation data
+#'
+#'Description Of SIMDATA
+#'
+#'@format A data.frame with 4586 rows, and 6 fields:
+#'\describe{
+#'  \item{GROUP}{Species or taxinominal grouping.}
+#'  \item{BLOCK}{Spacetime temporial strata.}
+#'  \item{REP}{Replicate, survey site.}
+#'  \item{METHOD}{Survey method used.}
+#'  \item{DENSITY}{Group abundance of positive observations.}
+#'  \item{PRESENCE}{Proportion of presence over absence of a group at a survey site.}
+#'}
+#'
+#'@source \url{https://www.pifsc.noaa.gov/library/pubs/admin/PIFSC_Admin_Rep_11-08.pdf}
+"SIMDATA"

R/export_results.R

@@ -0,0 +1,101 @@
+
+#' Export results to saved files.
+#'
+#' Option to export grouped survey datasets, the GCF/OPUE Summary Table, and REP summaries in
+#' seperate data files.
+#'
+#' @details These following datalist objects will be written to the location, defined by \code{outdir}.
+#' \itemize{
+#'   \item The Grouped survey dataset object will be as saved as \code{reeffish_grouped.Rds}.
+#'   \item The GCF and OPUE summaries will be saved as \code{summary_table.csv}.
+#'   \item The \code{REP} count by species group summary will be saved as \code{REP_summary.csv}.
+#' }
+#'
+#' If the user doesn't specify a output directory, then a new directory will be generated from the user's HOME location.
+#'
+#' @param datalist List containing the Grouped dataset and summaries from \code{\link{load_dataset}}
+#' @param outdir Location to export data and summaries to. Default location is user's \code{HOME} directory
+#'
+#' @importFrom utils write.csv
+#'
+#' @export
+export_results <- function(datalist,outdir=Sys.getenv("HOME")){
+
+  tryCatch(
+    {
+      #If dir is default, create an output subdirectory from the user's HOME location.
+      if(outdir == Sys.getenv("HOME")){
+        calibr_home <- file.path(outdir, "Calibr")
+
+        if(!dir.exists(calibr_home)){
+          message("Creating directory for Calibr runs: ", calibr_home ," ...")
+          dir.create(calibr_home)
+        }
+
+        outdir <- file.path(calibr_home,basename(tempfile(pattern="CalibrRun_")))
+        message("Creating output directory: ", outdir ," ...")
+        dir.create(outdir)
+      }else{
+        #check if outdir exists in user's system. If not return error message
+        if(!(dir.exists(outdir))){
+          stop("Location of output directory was not found or inaccessible : \n",outdir)
+        }
+        message("Output Directory: ", outdir)
+      }
+    },
+    error=function(cond){
+      message(cond)
+      return(NULL)
+    }
+  )
+
+  message("Exporting grouped data and summary tables to output directory ...")
+
+
+
+
+
+  #Check datalist is a list
+  if(class(datalist) != "list"){
+    stop("Parameter datalist not a list object.")
+  }
+
+  #Check datalist contents have the appropriate data structures.
+  str.datalist <- list("list",
+                       c("data.table","data.frame"),
+                       "data.frame")
+  if(!all(sapply(datalist,class) %in% str.datalist)){
+    index_mismatch_classes <- !(sapply(datalist,class) %in% str.datalist)
+    mismatched_classes <- sapply(datalist,class)[index_mismatch_classes]
+    count_mismatches<- length(which(index_mismatch_classes))
+
+    mismatch_datalist_obj <- names(datalist)[index_mismatch_classes]
+    stop("Datalist object(s) ", paste(mismatch_datalist_obj, collapse=", ")
+         , "has an invalid object class:", paste(mismatched_classes,collapse=", "))
+
+  }
+
+  #Check if datalist has the names "LGROUP", "SUMMARY", and "REP_SUMMARY" in datalist
+  if(!all(names(datalist) %in% c("LGROUP", "SUMMARY", "REP_SUMMARY" ))){
+     missing_listNames <-names(datalist)[!(names(datalist) %in% c("LGROUP", "SUMMARY", "REP_SUMMARY" ))]
+     stop("Invalid reef datalist fields: ", paste(missing_listNames,collapse = ", "))
+  }
+
+
+  #LGROUP
+  message("Saving Grouped Coral Reef Data ...")
+  reeffish_grouped_datalist <- datalist[["LGROUP"]]
+  saveRDS(reeffish_grouped_datalist, file = file.path(outdir,"reeffish_grouped.Rds"))
+
+  #SUMMARY
+  message("Saving GCF and OPUE Summaries to file ...")
+  write.csv(datalist[["SUMMARY"]], file = file.path(outdir,"summary_table.csv"), row.names = FALSE)
+
+  #REP_SUMMARY
+  message("Saving REP Summary Table to file ...")
+  write.csv(datalist[["REP_SUMMARY"]], file = file.path(outdir,"REP_summary.csv"), row.names = FALSE)
+
+  message("Done.")
+  message("Grouped data and summary tables have been to:\n", outdir)
+
+}