Remove draft of response optimizer

R/doeAnalysis.R

@@ -513,43 +513,6 @@ get_levels <- function(var, num_levels, dataset) {
   levels_var[2:(num_levels + 1)]
 }
 
-# .doeResponseOptimizer <- function(jaspResults, dataset, options, ready, continuousPredictors, discretePredictors, blocks, covariates, dependent) {
-#   # get regression equation and predictors
-#   #result <- jaspResults[["doeResult"]]$object[["regression"]]
-#   result <- result$regression
-#   regressionEquation <- result$object$coefficients
-#
-#   # Define a pattern for first-order terms
-#   first_order_pattern <- paste0("^(", paste(names(result$object$model)[-1], collapse = "|"), ")$")
-#
-#   # Extract first-order coefficients
-#   first_order_coefficients <- regressionEquation[grepl(first_order_pattern, names(regressionEquation))]
-#
-#   # Print the first-order coefficients
-#   print(first_order_coefficients)
-#
-#   predictors <-
-#
-#   # get process SD
-#   Y <- result$object$model[[1]] # vector of the outcome, always first column of the model object
-#   psd <- sd(Y) # process standard deviation
-#
-#   # sample from value space of predictors
-#   nPredictors <- ncol(result$object$model) - 1 # all cols of the model, minus one for the result
-#   nSimulations <- 1000
-#   optimizationDf <- data.frame()
-#   for (sim in seq_len(nSimulations)) {
-#
-#   }
-#
-#   # what to do with blocks and covariates? just assume that block and covariate are at mean? or at zero?
-#
-#   # use regression equation to predict outcomes
-#   # get sampled value space with highest min cpk
-#   # return this optimized value set
-#
-# }
-
 .getVIF <- function(regressionFit, predictors) {
   if (ncol(regressionFit$model) < 3) {
     VIF <- rep(NA, length(regressionFit$coefficients))