a few more uses of colSums(is.na(data) to improve speed

njtierney · May 19, 2020 · af836b2 · af836b2
1 parent 79a12e8
commit af836b2
Show file tree

Hide file tree

Showing 2 changed files with 7 additions and 6 deletions.
diff --git a/R/gg-miss-which.R b/R/gg-miss-which.R
@@ -21,12 +21,13 @@
 
 gg_miss_which <- function(x){
 
+  col_na <- colSums(is.na(x)) == 0
+  col_na_val <- dplyr::if_else(col_na, "complete", "missing")
+
+
   # tell us which columns have missing data
-  ggobject <- x %>%
-    miss_var_summary() %>%
-    dplyr::select(variable,
-                  value = n_miss) %>%
-    dplyr::mutate(value = dplyr::if_else(value == 0, "complete", "missing")) %>%
+  ggobject <- tibble::tibble(variable = names(col_na),
+                             value = col_na_val) %>%
     dplyr::mutate(nheight = 1) %>%
     ggplot(data = .,
            aes(x = variable,

diff --git a/R/where-na.R b/R/where-na.R
@@ -79,7 +79,7 @@ miss_var_which <- function(data){
   }
 
   # else return variables that contain ANY missing values
-  na_vars <- names(which(purrr::map_lgl(data,anyNA) == TRUE))
+  na_vars <- names(which(colSums(is.na(data)) > 0))
 
   return(na_vars)