0.1.5 : add warning for old info$lambda

R/checkFunctions.R

@@ -269,6 +269,12 @@
 
 .cocons.check.info <- function(type, info, model.list, data){
 
+  if (!is.null(info$lambda)) {
+    info$lambda.reg <- info$lambda
+    warning("The regularization parameter lambda is now called lambda.reg . Seee help(coco)")
+    info$lambda <- NULL
+  }
+
   if (is.null(info$smooth.limits) & is.formula(model.list[6]$smooth)) {
     stop("smooth limits not specified.")
   }

R/cocons.R

@@ -26,7 +26,7 @@
 #' \eqn{\nu_{l}}, and \eqn{\nu_{u}} are the lower and upper bounds limiting the range of variation of the spatially-varying smoothness, and where \eqn{\boldsymbol{X}_{\ell}} relates to the design matrix defined by the specific models for each of the source of nonstationarity.
 #' 
 #' Lastly, arguments for the \code{"info"} list argument involve: \itemize{
-#' \item \code{"lambda.reg"}: (\code{numeric}) a positive scalar specifying the regularization parameter. Larger values regularize highly-smoothed long-tailed covariance functions. 
+#' \item \code{"lambda.reg"}: (\code{numeric}) a positive scalar specifying the regularization parameter. Larger values discourage highly-smoothed long-tailed covariance functions. 
 #' \item \code{"lambda.Sigma"}: (\code{numeric}) a positive scalar specifying the penalization parameter for the covariate-driven covariance parameters. 
 #' \item \code{"lambda.betas"}: (\code{numeric}) a positive scalar specifying the penalization parameter for the covariate-driven spatial mean parameters. 
 #' \item \code{"sparse.point"}: (\code{numeric}) a cutting point for which smaller coefficients in absolute value will be set to zero after the smoothed L1 penalization optimization. Used in combination with \code{lambda.Sigma} and \code{lambda.betas}. By default, it is set to \code{1e-4}.
@@ -151,7 +151,7 @@ coco <- function(type,
   }
 
   if(any(c(info$lambda.betas,info$lambda.Sigma) > 0) && (is.null(info$sparse.point))){
-    info$sparse.point <- 1e-4
+    info$sparse.point <- getOption("cocons.sparse.point")
   }
 
   if(T){

R/optim.R

@@ -382,7 +382,6 @@ cocoOptim <- function(coco.object, boundaries = list(),
       parallel::setDefaultCluster(cl = cl)
       parallel::clusterEvalQ(cl, library("cocons"))
       parallel::clusterEvalQ(cl, library("spam"))
-      #parallel::clusterEvalQ(cl, library("spam64"))
       parallel::clusterEvalQ(cl, options(spam.cholupdatesingular = "error"))
       parallel::clusterEvalQ(cl, options(spam.cholsymmetrycheck = FALSE))
 
@@ -547,7 +546,6 @@ cocoOptim <- function(coco.object, boundaries = list(),
       parallel::setDefaultCluster(cl = cl)
       parallel::clusterEvalQ(cl, library("cocons"))
       parallel::clusterEvalQ(cl, library("spam"))
-      #parallel::clusterEvalQ(cl, library("spam64"))
       parallel::clusterEvalQ(cl, options(spam.cholupdatesingular = "error"))
       parallel::clusterEvalQ(cl, options(spam.cholsymmetrycheck = FALSE))