biomod2 from 4.2-4 to 4.2-5

Change BIOMOD_ModelingOptions to bm_ModelingOptions

DESCRIPTION

@@ -39,7 +39,7 @@ Suggests:
   rmarkdown,
   testthat (>= 3.0.0),
   covr
-RoxygenNote: 7.2.3
+RoxygenNote: 7.3.1
 VignetteBuilder: knitr
 Config/testthat/edition: 3
 LinkingTo: 

R/cv_cluster.R

@@ -183,7 +183,7 @@ cv_cluster <- function(
       train_test_table[i, which(cl %in% names(countrain))] <- countrain
       train_test_table[i, clen + which(cl %in% names(countest))] <- countest
     }
-    if(biomod2){ # creating a biomod2 data.split.table for validation
+    if(biomod2){ # creating a biomod2 CV.user.table for validation
       colm <- paste0("RUN", i)
       biomod_table[,colm] <- FALSE
       biomod_table[train_set, colm] <- TRUE

R/cv_spatial.R

@@ -60,7 +60,7 @@
 #' This argument is necessary if you choose the 'predefined' selection.
 #' @param deg_to_metre integer. The conversion rate of metres to degree. See the details section for more information.
 #' @param biomod2 logical. Creates a matrix of folds that can be directly used in the \pkg{biomod2} package as
-#' a \emph{data.split.table} for cross-validation.
+#' a \emph{CV.user.table} for cross-validation.
 #' @param offset two number between 0 and 1 to shift blocks by that proportion of block size.
 #' This option only works when \code{size} is provided.
 #' @param extend numeric; This parameter specifies the percentage by which the map's extent is
@@ -76,7 +76,7 @@
 #'
 #'
 #' @seealso \code{\link{cv_buffer}} and \code{\link{cv_cluster}}; \code{\link{cv_spatial_autocor}} and \code{\link{cv_block_size}} for selecting block size
-#' @seealso For \emph{data.split.table} see \code{\link[biomod2]{BIOMOD_cv}} in \pkg{biomod2} package
+#' @seealso For \emph{CV.user.table} see \code{\link[biomod2]{BIOMOD_Modeling}} in \pkg{biomod2} package
 #'
 #' @references Bahn, V., & McGill, B. J. (2012). Testing the predictive performance of distribution models. Oikos, 122(3), 321-331.
 #'
@@ -369,7 +369,7 @@ cv_spatial <- function(
         train_test_table[p, which(cl %in% names(countrain))] <- countrain
         train_test_table[p, clen + which(cl %in% names(countest))] <- countest
       }
-      if(biomod2){ # creating a biomod2 data.split.table for validation
+      if(biomod2){ # creating a biomod2 CV.user.table for validation
         colm <- paste0("RUN", p)
         biomod_table[, colm] <- FALSE
         biomod_table[train_set, colm] <- TRUE

inst/doc/tutorial_2.R

@@ -45,7 +45,7 @@ scv1 <- cv_spatial(
   progress = FALSE, # turn off progress bar
   biomod2 = TRUE, # also create folds for biomod2
   raster_colors = terrain.colors(10, rev = TRUE) # options from cv_plot for a better colour contrast
-) 
+)
 
 
 ## -----------------------------------------------------------------------------
@@ -85,22 +85,22 @@ cv_plot(
 #  # loading the libraries
 #  library(randomForest)
 #  library(precrec)
-#  
+#
 #  # extract the raster values for the species points as a dataframe
 #  model_data <- terra::extract(rasters, pa_data, df = TRUE, ID = FALSE)
 #  # adding species column to the dataframe
 #  model_data$occ <- as.factor(pa_data$occ)
 #  head(model_data)
-#  
+#
 #  # extract the fold indices from buffering object
 #  # created in the previous section
 #  # the folds_list works for all four blocking strategies
 #  folds <- scv2$folds_list
-#  
+#
 #  # create a data.frame to store the prediction of each fold (record)
 #  test_table <- pa_data
 #  test_table$preds <- NA
-#  
+#
 #  for(k in seq_len(length(folds))){
 #    # extracting the training and testing indices
 #    # this way works with folds_list list (but not folds_ids)
@@ -109,67 +109,67 @@ cv_plot(
 #    rf <- randomForest(occ ~ ., model_data[trainSet, ], ntree = 500) # model fitting on training set
 #    test_table$preds[testSet] <- predict(rf, model_data[testSet, ], type = "prob")[,2] # predict the test set
 #  }
-#  
+#
 #  # calculate Area Under the ROC and PR curves and plot the result
 #  precrec_obj <- evalmod(scores = test_table$preds, labels = test_table$occ)
 #  auc(precrec_obj)
-#  
+#
 
 ## ----echo=FALSE---------------------------------------------------------------
 # to not run the model and reduce run time; result are calculated and loaded
-read.csv("../man/figures/roc_rf.csv") 
+read.csv("../man/figures/roc_rf.csv")
 
 
 ## ----eval=FALSE, fig.height=3.7, fig.width=7----------------------------------
 #  library(ggplot2)
-#  
+#
 #  autoplot(precrec_obj)
-#  
+#
 
 ## ----eval=FALSE---------------------------------------------------------------
 #  # loading the library
 #  library(biomod2)
-#  
+#
 #  # extract the raster values for the species points as a dataframe
 #  raster_values <- terra::extract(rasters, pa_data, df = TRUE, ID = FALSE)
-#  
+#
 #  # 1. Formatting Data
 #  biomod_data <- BIOMOD_FormatingData(resp.var = pa_data$occ,
 #                                      expl.var = raster_values,
 #                                      resp.xy = sf::st_coordinates(pa_data),
 #                                      resp.name = "occ",
 #                                      na.rm = TRUE)
-#  
-#  # 2. Defining the folds for data.split.table
+#
+#  # 2. Defining the folds for CV.user.table
 #  # note that biomod_table should be used here not folds
 #  # use generated folds from cv_spatial in previous section
 #  spatial_cv_folds <- scv1$biomod_table
 #  # the new update of the package biomod2 (v4.2-3 <) requires the names to be as below
-#  # and the `data.split.table` argument is depricated.
 #  colnames(spatial_cv_folds) <- paste0("_allData_RUN", 1:ncol(spatial_cv_folds))
-#  
+#
 #  # 3. Defining Models Options; using default options here. You can use your own settting here.
-#  biomod_options <- BIOMOD_ModelingOptions()
-#  
+#  biomod_options <- bm_ModelingOptions(data.type = "binary",
+#                                       strategy = "bigboss")
+#
 #  # 4. Model fitting
 #  biomod_model_out <- BIOMOD_Modeling(biomod_data,
 #                                      models = c('GLM','MARS','GBM'),
-#                                      bm.options = biomod_options,
 #                                      CV.strategy = "user.defined",
 #                                      CV.user.table	= spatial_cv_folds,
+#                                      OPT.user	= biomod_options,
 #                                      var.import = 0,
 #                                      metric.eval = c('ROC'),
 #                                      do.full.models = TRUE)
-#  
+#
 
 ## ----eval=FALSE---------------------------------------------------------------
 #  # 5. Model evaluation
 #  biomod_model_eval <- get_evaluations(biomod_model_out)
 #  biomod_model_eval[c("run", "algo", "metric.eval", "calibration", "validation")]
-#  
+#
 
 ## ----echo=FALSE---------------------------------------------------------------
 # to not run the model and reduce run time; result are calculated and loaded
-read.csv("../man/figures/evl_biomod.csv") 
+read.csv("../man/figures/evl_biomod.csv")
 
 

inst/doc/tutorial_2.Rmd

@@ -232,23 +232,22 @@ biomod_data <- BIOMOD_FormatingData(resp.var = pa_data$occ,
                                     resp.name = "occ",
                                     na.rm = TRUE)
 
-# 2. Defining the folds for data.split.table
+# 2. Defining the folds for CV.user.table
 # note that biomod_table should be used here not folds
 # use generated folds from cv_spatial in previous section
 spatial_cv_folds <- scv1$biomod_table
 # the new update of the package biomod2 (v4.2-3 <) requires the names to be as below
-# and the `data.split.table` argument is depricated.
 colnames(spatial_cv_folds) <- paste0("_allData_RUN", 1:ncol(spatial_cv_folds))
 
 # 3. Defining Models Options; using default options here. You can use your own settting here.
-biomod_options <- BIOMOD_ModelingOptions()
+biomod_options <- bm_ModelingOptions(data.type = "binary", strategy = "bigboss")
 
 # 4. Model fitting
 biomod_model_out <- BIOMOD_Modeling(biomod_data,
                                     models = c('GLM','MARS','GBM'),
-                                    bm.options = biomod_options,
                                     CV.strategy = "user.defined",
                                     CV.user.table	= spatial_cv_folds,
+                                    OPT.user = biomod_options,
                                     var.import = 0,
                                     metric.eval = c('ROC'),
                                     do.full.models = TRUE)
@@ -276,6 +275,6 @@ The `validation` column shows the result of spatial cross-validation and each RU
 
 - Roberts, D.R., Bahn, V., Ciuti, S., Boyce, M.S., Elith, J., Guillera-Arroita, G., Hauenstein, S., Lahoz-Monfort, J.J., Schröder, B., Thuiller, W., others, 2017. Cross-validation strategies for data with temporal, spatial, hierarchical, or phylogenetic structure. Ecography. 40: 913-929.
 
-- Thuiller, W., Georges, D., Engler, R., & Breiner, F. (2017). biomod2: Ensemble Platform for Species Distribution Modeling. R package version 3.3-7. https://CRAN.R-project.org/package=biomod2.
+- Thuiller W, Georges D, Guéguen M, Engler R, Breiner F, Lafourcade B, Patin R, Blancheteau H (2024). biomod2: Ensemble Platform for Species Distribution Modeling. R package version 4.2-5. https://CRAN.R-project.org/package=biomod2.
 
 - Valavi R, Elith J, Lahoz-Monfort JJ, Guillera-Arroita G. **blockCV: An R package for generating spatially or environmentally separated folds for k-fold cross-validation of species distribution models**. *Methods Ecol Evol.* 2019; 10:225–232. [doi: 10.1111/2041-210X.13107](https://doi.org/10.1111/2041-210X.13107)

vignettes/tutorial_2.Rmd

@@ -232,23 +232,22 @@ biomod_data <- BIOMOD_FormatingData(resp.var = pa_data$occ,
                                     resp.name = "occ",
                                     na.rm = TRUE)
 
-# 2. Defining the folds for data.split.table
+# 2. Defining the folds for CV.user.table
 # note that biomod_table should be used here not folds
 # use generated folds from cv_spatial in previous section
 spatial_cv_folds <- scv1$biomod_table
 # the new update of the package biomod2 (v4.2-3 <) requires the names to be as below
-# and the `data.split.table` argument is depricated.
 colnames(spatial_cv_folds) <- paste0("_allData_RUN", 1:ncol(spatial_cv_folds))
 
 # 3. Defining Models Options; using default options here. You can use your own settting here.
-biomod_options <- BIOMOD_ModelingOptions()
+biomod_options <- bm_ModelingOptions(data.type = "binary", strategy = "bigboss")
 
 # 4. Model fitting
 biomod_model_out <- BIOMOD_Modeling(biomod_data,
                                     models = c('GLM','MARS','GBM'),
-                                    bm.options = biomod_options,
                                     CV.strategy = "user.defined",
                                     CV.user.table	= spatial_cv_folds,
+                                    OPT.user = biomod_options,
                                     var.import = 0,
                                     metric.eval = c('ROC'),
                                     do.full.models = TRUE)
@@ -276,6 +275,6 @@ The `validation` column shows the result of spatial cross-validation and each RU
 
 - Roberts, D.R., Bahn, V., Ciuti, S., Boyce, M.S., Elith, J., Guillera-Arroita, G., Hauenstein, S., Lahoz-Monfort, J.J., Schröder, B., Thuiller, W., others, 2017. Cross-validation strategies for data with temporal, spatial, hierarchical, or phylogenetic structure. Ecography. 40: 913-929.
 
-- Thuiller, W., Georges, D., Engler, R., & Breiner, F. (2017). biomod2: Ensemble Platform for Species Distribution Modeling. R package version 3.3-7. https://CRAN.R-project.org/package=biomod2.
+- Thuiller W, Georges D, Guéguen M, Engler R, Breiner F, Lafourcade B, Patin R, Blancheteau H (2024). biomod2: Ensemble Platform for Species Distribution Modeling. R package version 4.2-5. https://CRAN.R-project.org/package=biomod2.
 
 - Valavi R, Elith J, Lahoz-Monfort JJ, Guillera-Arroita G. **blockCV: An R package for generating spatially or environmentally separated folds for k-fold cross-validation of species distribution models**. *Methods Ecol Evol.* 2019; 10:225–232. [doi: 10.1111/2041-210X.13107](https://doi.org/10.1111/2041-210X.13107)