Initializing repository, defining arguments and loading screened dataset

.gitignore

+Data/
+.Rhistory

00_MasterTestset.R

+### Stratified sampling of n records out of screened dataset based on intensity and soil types
+# Creator: Erwin Mollenhorst
+
+## remove (almost) everything in the working environment.
+## You will get no warning, so don't do this unless you are really sure.
+rm(list = ls())
+
+# R version 4.0.2
+# RStudio 1.3.959
+
+### ipak function: install and load multiple R packages.
+### check to see if packages are installed. Install them if they are not,
+### then load them into the R session.
+IPAKCD <- function(pkg){
+  new.pkg <- pkg[!(pkg %in% installed.packages()[, "Package"])]
+  if (length(new.pkg)) 
+    install.packages(new.pkg, dependencies = TRUE)
+  sapply(pkg, library, character.only = TRUE, logical.return = TRUE)
+}
+
+#   Set working directory
+IPAKCD(c("rstudioapi", "data.table", "openxlsx", "dplyr"))
+setwd(dirname(getActiveDocumentContext()$path))
+getwd()
+
+# Define arguments
+vYear    <- 2021 # year of KLW records
+vIntLim  <- c(12.5, 17.5, 22.5)
+vNormSoil<- 1.00 # fraction of the farm that has certain soiltype, otherwise category = 'overig' (other)
+
+## Define directories
+vRoot        <- paste0("W:/PROJECTS/WLR_KringloopWijzer/data ", vYear)
+vDir_data    <- file.path(vRoot, "Screeningsresultaten")
+vDir_results <- file.path(vRoot, "TestSet")
+if (!dir.exists(vDir_results)) {dir.create(vDir_results)}
+
+# Loading screened dataset
+vList <- list.files(vDir_data)
+ifelse(length(grep(paste0("KLW", vYear,"_opgeschoond.rda"), vList)) == 1,
+       load(file = file.path(vDir_data, vList[grep(paste0("KLW", vYear,"_opgeschoond.rda"), vList)])),
+       stop("More than one or no .rda file present in vDir_data")
+       )
+rm(vList)
+