Deal with the global variable note via utils::globalVariables()

R/measure_importance.R

@@ -8,7 +8,6 @@ measure_min_depth <- function(min_depth_frame, mean_sample){
 
 # Calculate the number of nodes split on each variable for a data frame with the whole forest
 measure_no_of_nodes <- function(forest_table){
-  `split var` <- NULL
   frame <- dplyr::group_by(forest_table, variable = variable) %>%
     dplyr::summarize(no_of_nodes = dplyr::n())
   frame <- as.data.frame(frame[!is.na(frame$variable),])
@@ -60,7 +59,6 @@ measure_vimp_ranger <- function(forest){
 
 # Calculate the number of trees using each variable for splitting
 measure_no_of_trees <- function(min_depth_frame){
-  variable <- NULL
   frame <- dplyr::group_by(min_depth_frame, variable) %>%
     dplyr::summarize(no_of_trees = n()) %>%
     as.data.frame()
@@ -69,7 +67,6 @@ measure_no_of_trees <- function(min_depth_frame){
 
 # Calculate the number of times each variable is split on the root node
 measure_times_a_root <- function(min_depth_frame){
-  variable <- NULL
   frame <- min_depth_frame[min_depth_frame$minimal_depth == 0, ] %>%
     dplyr::group_by(variable) %>%
     dplyr::summarize(times_a_root = n()) %>%
@@ -113,7 +110,6 @@ measure_importance <- function(forest, mean_sample = "top_trees", measures = NUL
 #' @importFrom data.table rbindlist
 #' @export
 measure_importance.randomForest <- function(forest, mean_sample = "top_trees", measures = NULL){
-  tree <- NULL; `split var` <- NULL; depth <- NULL
   if(is.null(measures)){
     if(forest$type %in% c("classification", "unsupervised")){
       measures <- c("mean_min_depth", "no_of_nodes", "accuracy_decrease",
@@ -177,7 +173,6 @@ measure_importance.randomForest <- function(forest, mean_sample = "top_trees", m
 #' @importFrom data.table rbindlist
 #' @export
 measure_importance.ranger <- function(forest, mean_sample = "top_trees", measures = NULL){
-  tree <- NULL; splitvarName <- NULL; depth <- NULL
   if(is.null(measures)){
     measures <- c("mean_min_depth", "no_of_nodes", forest$importance.mode, "no_of_trees", "times_a_root", "p_value")
   }
@@ -296,7 +291,6 @@ plot_multi_way_importance <- function(importance_frame, x_measure = "mean_min_de
                                       y_measure = "times_a_root", size_measure = NULL,
                                       min_no_of_trees = 0, no_of_labels = 10,
                                       main = "Multi-way importance plot"){
-  variable <- NULL
   if(any(c("randomForest", "ranger") %in% class(importance_frame))){
     importance_frame <- measure_importance(importance_frame)
   }

R/min_depth_distribution.R

@@ -14,7 +14,6 @@
 #' @import dplyr
 #' @importFrom data.table rbindlist
 min_depth_distribution <- function(forest){
-  tree <- NULL; `split var` <- NULL; depth <- NULL
   forest_table <- forest2df(forest)
   min_depth_frame <- dplyr::group_by(forest_table, tree, variable) %>%
     dplyr::summarize(minimal_depth = min(depth), .groups = "drop")
@@ -24,7 +23,6 @@ min_depth_distribution <- function(forest){
 
 # Count the trees in which each variable had a given minimal depth
 min_depth_count <- function(min_depth_frame){
-  tree <- NULL; minimal_depth <- NULL; variable <- NULL
   mean_tree_depth <- dplyr::group_by(min_depth_frame, tree) %>%
     dplyr::summarize(depth = max(minimal_depth) + 1) %>%
     as.data.frame()
@@ -45,7 +43,6 @@ min_depth_count <- function(min_depth_frame){
 
 # Get a data frame with means of minimal depth calculated using sample = c("all_trees", "top_trees", "relevant_trees")
 get_min_depth_means <- function(min_depth_frame, min_depth_count_list, mean_sample){
-  .SD <- NULL; variable <- NULL
   if(mean_sample == "all_trees"){
     min_depth_count_list[[1]][is.na(min_depth_count_list[[1]]$minimal_depth), "minimal_depth"] <- min_depth_count_list[[3]]
     min_depth_means <-
@@ -89,7 +86,6 @@ get_min_depth_means <- function(min_depth_frame, min_depth_count_list, mean_samp
 plot_min_depth_distribution <- function(min_depth_frame, k = 10, min_no_of_trees = 0,
                                         mean_sample = "top_trees", mean_scale = FALSE, mean_round = 2,
                                         main = "Distribution of minimal depth and its mean"){
-  minimal_depth <- NULL; mean_minimal_depth_label <- NULL; mean_minimal_depth <- NULL
   if(any(c("randomForest", "ranger") %in% class(min_depth_frame))){
     min_depth_frame <- min_depth_distribution(min_depth_frame)
   }

R/min_depth_interactions.R

@@ -1,6 +1,5 @@
 # Calculate conditional depth in a tree with respect to all variables from vector vars
 conditional_depth <- function(frame, vars){
-  `.SD` <- NULL; depth <- NULL; splitvarName <- NULL
   index <- data.table::as.data.table(frame)[
     !is.na(variable), .SD[which.min(depth), "number"], by = variable
   ]
@@ -27,7 +26,6 @@ conditional_depth <- function(frame, vars){
 
 # Get a data frame with values of minimal depth conditional on selected variables for the whole forest
 min_depth_interactions_values <- function(forest, vars){
-  `.` <- NULL; .SD <- NULL; tree <- NULL; `split var` <- NULL
   interactions_frame <- as.data.frame(forest2df(forest))
   interactions_frame[vars] <- NA_real_
   interactions_frame <-
@@ -71,7 +69,6 @@ min_depth_interactions_values <- function(forest, vars){
 #' @export
 min_depth_interactions <- function(forest, vars = important_variables(measure_importance(forest)),
                                                 mean_sample = "top_trees", uncond_mean_sample = mean_sample){
-  variable <- NULL; `.` <- NULL; tree <- NULL; `split var` <- NULL; depth <- NULL
   ntree <- ntrees(forest)
   min_depth_interactions_frame <- min_depth_interactions_values(forest, vars)
   mean_tree_depth <- min_depth_interactions_frame[[2]]
@@ -145,7 +142,6 @@ min_depth_interactions <- function(forest, vars = important_variables(measure_im
 plot_min_depth_interactions <- function(interactions_frame, k = 30,
                                         main = paste0("Mean minimal depth for ",
                                                       paste0(k, " most frequent interactions"))){
-  mean_min_depth <- NULL; occurrences <- NULL; uncond_mean_min_depth <- NULL
   if(any(c("randomForest", "ranger") %in% class(interactions_frame))){
     interactions_frame <- min_depth_interactions(interactions_frame)
   }

R/utils.R

@@ -21,8 +21,6 @@ max_na <- function(x) {
   max(x, na.rm = TRUE)
 }
 
-utils::globalVariables(c("prediction", "variable"))
-
 # Depth of each node of a single tree.
 # The input is a matrix with left and right child nodes in 1:nrow(childs).
 tree_depth <- function(childs) {
@@ -75,6 +73,27 @@ ntrees <- function(x) {
 }
 
 # Applies tree2df() to each tree and stacks the results
+#' @importFrom data.table rbindlist
 forest2df <- function(x) {
   rbindlist(lapply(seq_len(ntrees(x)), function(i) tree2df(x, i)))
 }
+
+# Deal with the global variable note
+utils::globalVariables(
+  c(
+    ".",
+    ".SD",
+    "depth",
+    "mean_min_depth",
+    "mean_minimal_depth",
+    "mean_minimal_depth_label",
+    "minimal_depth",
+    "occurrences",
+    "prediction",
+    "split var",
+    "splitvarName",
+    "tree",
+    "uncond_mean_min_depth",
+    "variable"
+  )
+)