ready to merge VII

NAMESPACE

@@ -50,4 +50,5 @@ importFrom(stats,predict)
 importFrom(stats,quantile)
 importFrom(stats,sd)
 importFrom(utils,combn)
+importFrom(utils,setTxtProgressBar)
 importFrom(utils,txtProgressBar)

R/CAST-package.R

@@ -24,7 +24,7 @@
 #'
 #' @import caret
 #' @importFrom stats sd dist na.omit lm predict quantile na.exclude complete.cases
-#' @importFrom utils combn txtProgressBar
+#' @importFrom utils combn txtProgressBar setTxtProgressBar
 #' @importFrom grDevices rainbow
 #' @importFrom graphics axis plot segments
 #' @keywords package

R/DItoErrormetric.R

@@ -248,6 +248,7 @@ multiCV <- function(model, length.out, method, useWeight, what,...){
 #' Get Preds all
 #' @param model, a model
 #' @param trainDI, a trainDI
+#' @param what Character. Which measure to use for the error metric. "DI" or "LPD"
 #'
 
 get_preds_all <- function(model, trainDI, what){

R/aoa.R

@@ -26,7 +26,7 @@
 #' @param method Character. Method used for distance calculation. Currently euclidean distance (L2) and Mahalanobis distance (MD) are implemented but only L2 is tested. Note that MD takes considerably longer.
 #' @param useWeight Logical. Only if a model is given. Weight variables according to importance in the model?
 #' @param LPD Logical. Indicates wheather the LPD should be calculated or not.
-#' @param maxLPD numeric or integer. Only if \code{LPD = TRUE}. Number of nearest neighbors to be considered for the calculation of the LPD. Either define a number between 0 and 1 to use a percentage of the number of training samples for the LPD calculation or a whole number larger than 1 and smaller than the number of training samples. CAUTION! If not all training samples are considered, a fitted relationship between LPD and error metric will not make sense (@seealso \code{\link{LPDtoErrormetri}})
+#' @param maxLPD numeric or integer. Only if \code{LPD = TRUE}. Number of nearest neighbors to be considered for the calculation of the LPD. Either define a number between 0 and 1 to use a percentage of the number of training samples for the LPD calculation or a whole number larger than 1 and smaller than the number of training samples. CAUTION! If not all training samples are considered, a fitted relationship between LPD and error metric will not make sense (@seealso \code{\link{DItoErrormetric}})
 #' @details The Dissimilarity Index (DI), the Local Data Point Density (LPD) and the corresponding Area of Applicability (AOA) are calculated.
 #' If variables are factors, dummy variables are created prior to weighting and distance calculation.
 #'

R/plot.R

@@ -392,7 +392,7 @@ plot.errorModelDI <- function(x, ...){
 
 #' @name plot
 #' @description Plot the LPD and errormetric from Cross-Validation with the modelled relationship
-#' @param x errorModelLPD, see \code{\link{LPDtoErrormetric}}
+#' @param x errorModelLPD, see \code{\link{DItoErrormetric}}
 #' @param ... other params
 #' @export
 #' @return a ggplot

inst/examples/ex_DItoErrormetric.R

@@ -38,7 +38,8 @@
   plot(expected_error_DI)
 
   # mask AOA based on new threshold from multiCV
-  mask_aoa = terra::mask(expected_error_DI, AOA$DI > attr(errormodel_DI, 'AOA_threshold'), maskvalues = 1)
+  mask_aoa = terra::mask(expected_error_DI, AOA$DI > attr(errormodel_DI, 'AOA_threshold'),
+                          maskvalues = 1)
   plot(mask_aoa)