Corrections for the devtools::check()

Author: OlaPaluszynska

DESCRIPTION

@@ -18,6 +18,7 @@ Imports:
   GGally (>= 1.3.0),
   ggplot2 (>= 2.2.1),
   ggrepel (>= 0.6.5),
+  MASS (>= 7.3.47),
   randomForest (>= 4.6.12),
   reshape2 (>= 1.4.2),
   rmarkdown (>= 1.5)

NAMESPACE

@@ -18,3 +18,6 @@ import(ggplot2)
 import(ggrepel)
 importFrom(data.table,frankv)
 importFrom(data.table,rbindlist)
+importFrom(stats,as.formula)
+importFrom(stats,predict)
+importFrom(stats,terms)

R/explain_forest.R

@@ -16,7 +16,7 @@
 #'
 #' @examples
 #' forest <- randomForest::randomForest(Species ~ ., data = iris, localImp = TRUE)
-#' explain_forest(forest, vars = names(iris), interactions = TRUE)
+#' explain_forest(forest, vars = names(iris))
 #'
 #' @export
 explain_forest <- function(forest, interactions = FALSE, data = NULL, vars = NULL, no_of_pred_plots = 3, pred_grid = 100,

R/measure_importance.R

@@ -8,6 +8,7 @@ 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, `split var`) %>% dplyr::summarize(n())
   colnames(frame) <- c("variable", "no_of_nodes")
   frame <- as.data.frame(frame[!is.na(frame$variable),])
@@ -45,6 +46,7 @@ measure_vimp <- function(forest, only_nonlocal = FALSE){
 
 # 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(count = n()) %>% as.data.frame()
   colnames(frame)[2] <- "no_of_trees"
@@ -54,6 +56,7 @@ 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$minimal_depth == 0, ] %>%
     dplyr::group_by(variable) %>% dplyr::summarize(count = n()) %>% as.data.frame()
   colnames(frame)[2] <- "times_a_root"
@@ -65,7 +68,7 @@ measure_times_a_root <- function(min_depth_frame){
 measure_p_value <- function(importance_frame){
   total_no_of_nodes <- sum(importance_frame$no_of_nodes)
   p_value <- unlist(lapply(importance_frame$no_of_nodes,
-                  function(x) binom.test(x, total_no_of_nodes, 1/nrow(importance_frame),
+                  function(x) stats::binom.test(x, total_no_of_nodes, 1/nrow(importance_frame),
                                          alternative = "greater")$p.value))
   return(p_value)
 }
@@ -89,6 +92,7 @@ measure_p_value <- function(importance_frame){
 #'
 #' @export
 measure_importance <- function(forest, mean_sample = "top_trees", measures = NULL){
+  tree <- NULL; `split var` <- NULL; depth <- NULL
   if(is.null(measures)){
     if(forest$type == "classification"){
       measures <- c("mean_min_depth", "no_of_nodes", "accuracy_decrease",
@@ -223,6 +227,7 @@ 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("randomForest" %in% class(importance_frame)){
     importance_frame <- measure_importance(importance_frame)
   }
@@ -332,7 +337,7 @@ plot_importance_rankings <- function(importance_frame, measures =
                          apply(importance_frame[, -c(1, 2)], 2,
                                function(x) frankv(x, order = -1, ties.method = "dense")))
   plot <- ggpairs(rankings[, measures], lower = list(continuous = function(data, mapping){
-    ggplot(data = data, mapping = mapping) + geom_point() +  geom_smooth(method = loess)
+    ggplot(data = data, mapping = mapping) + geom_point() +  geom_smooth(method = "loess")
     }))+ theme_bw()
   if(!is.null(main)){
     plot <- plot + ggtitle(main)

R/min_depth_distribution.R

@@ -30,6 +30,7 @@ calculate_tree_depth <- function(frame){
 #'
 #' @export
 min_depth_distribution <- function(forest){
+  tree <- NULL; `split var` <- NULL; depth <- NULL
   forest_table <-
     lapply(1:forest$ntree, function(i) randomForest::getTree(forest, k = i, labelVar = T) %>%
              calculate_tree_depth() %>% cbind(tree = i)) %>% rbindlist()
@@ -42,6 +43,7 @@ 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()
   mean_tree_depth <- mean(mean_tree_depth$depth)
@@ -60,18 +62,19 @@ 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]]$minimal_depth), "minimal_depth"] <- min_depth_count_list[[3]]
     min_depth_means <-
-      data.table::as.data.table(min_depth_count_list[[1]])[, weighted.mean(.SD[["minimal_depth"]], .SD[["count"]]),
+      data.table::as.data.table(min_depth_count_list[[1]])[, stats::weighted.mean(.SD[["minimal_depth"]], .SD[["count"]]),
                                                by = variable] %>% as.data.frame()
   } else if(mean_sample == "top_trees"){
     min_depth_count_list[[1]][is.na(min_depth_count_list[[1]]$minimal_depth), "count"] <-
       min_depth_count_list[[1]][is.na(min_depth_count_list[[1]]$minimal_depth), "count"] -
       min(min_depth_count_list[[1]][is.na(min_depth_count_list[[1]]$minimal_depth), "count"])
     min_depth_count_list[[1]][is.na(min_depth_count_list[[1]]$minimal_depth), "minimal_depth"] <- min_depth_count_list[[3]]
     min_depth_means <-
-      data.table::as.data.table(min_depth_count_list[[1]])[, weighted.mean(.SD[["minimal_depth"]], .SD[["count"]]),
+      data.table::as.data.table(min_depth_count_list[[1]])[, stats::weighted.mean(.SD[["minimal_depth"]], .SD[["count"]]),
                                                by = variable] %>% as.data.frame()
   } else if(mean_sample == "relevant_trees"){
     min_depth_means <- stats::aggregate(minimal_depth ~ variable, data = min_depth_frame, mean)
@@ -103,6 +106,7 @@ 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("randomForest" %in% class(min_depth_frame)){
     min_depth_frame <- min_depth_distribution(min_depth_frame)
   }

R/min_depth_interactions.R

@@ -1,5 +1,6 @@
 # Calculate conditional depth in a tree with respect to all variables from vector vars
 conditional_depth <- function(frame, vars){
+  `.SD` <- NULL; depth <- NULL; `split var` <- NULL
   index <- data.table::as.data.table(frame)[, .SD[which.min(depth), "number"], by = `split var`]
   index <- index[!is.na(index$`split var`), ]
   if(any(index$`split var` %in% vars)){
@@ -26,6 +27,7 @@ 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 <-
     lapply(1:forest$ntree, function(i) randomForest::getTree(forest, k = i, labelVar = T) %>%
              calculate_tree_depth() %>% cbind(., tree = i, number = 1:nrow(.))) %>%
@@ -62,12 +64,13 @@ min_depth_interactions_values <- function(forest, vars){
 #' @importFrom data.table rbindlist
 #'
 #' @examples
-#' forest <- randomForest::randomForest(Species ~ ., data = iris)
+#' forest <- randomForest::randomForest(Species ~ ., data = iris, ntree = 200)
 #' min_depth_interactions(forest, names(iris))
 #'
 #' @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
   min_depth_interactions_frame <- min_depth_interactions_values(forest, vars)
   mean_tree_depth <- min_depth_interactions_frame[[2]]
   min_depth_interactions_frame <- min_depth_interactions_frame[[1]]
@@ -122,13 +125,14 @@ min_depth_interactions <- function(forest, vars = important_variables(measure_im
 #' @import ggplot2
 #'
 #' @examples
-#' forest <- randomForest::randomForest(Species ~ ., data = iris)
+#' forest <- randomForest::randomForest(Species ~ ., data = iris, ntree = 200)
 #' plot_min_depth_interactions(min_depth_interactions(forest, names(iris)))
 #'
 #' @export
 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("randomForest" %in% class(interactions_frame)){
     interactions_frame <- min_depth_interactions(interactions_frame)
   }
@@ -165,6 +169,9 @@ plot_min_depth_interactions <- function(interactions_frame, k = 30,
 #' @return A ggplot2 object
 #'
 #' @import ggplot2
+#' @importFrom stats predict
+#' @importFrom stats terms
+#' @importFrom stats as.formula
 #'
 #' @examples
 #' forest <- randomForest::randomForest(Species ~., data = iris)