How to delete columns that contain ONLY NAs?

Question

I have a data.frame containing some columns with all NA values, how can I delete them from the data.frame.

Can I use the function

na.omit(...) 
         


        

Answer 1

Because performance was really important for me, I benchmarked all the functions above.

NOTE: Data from @Simon O'Hanlon's post. Only with size 15000 instead of 10.

library(tidyverse)
library(microbenchmark)

set.seed(123)
df <- data.frame(id = 1:15000,
                 nas = rep(NA, 15000), 
                 vals = sample(c(1:3, NA), 15000,
                               repl = TRUE))
df

MadSconeF1 <- function(x) x[, colSums(is.na(x)) != nrow(x)]

MadSconeF2 <- function(x) x[colSums(!is.na(x)) > 0]

BradCannell <- function(x) x %>% select_if(~sum(!is.na(.)) > 0)

SimonOHanlon <- function(x) x[ , !apply(x, 2 ,function(y) all(is.na(y)))]

jsta <- function(x) janitor::remove_empty(x)

SiboJiang <- function(x) x %>% dplyr::select_if(~!all(is.na(.)))

akrun <- function(x) Filter(function(y) !all(is.na(y)), x)

mbm <- microbenchmark(
  "MadSconeF1" = {MadSconeF1(df)},
  "MadSconeF2" = {MadSconeF2(df)},
  "BradCannell" = {BradCannell(df)},
  "SimonOHanlon" = {SimonOHanlon(df)},
  "SiboJiang" = {SiboJiang(df)},
  "jsta" = {jsta(df)}, 
  "akrun" = {akrun(df)},
  times = 1000)

mbm

Results:

Unit: microseconds
         expr    min      lq      mean  median      uq      max neval  cld
   MadSconeF1  154.5  178.35  257.9396  196.05  219.25   5001.0  1000 a   
   MadSconeF2  180.4  209.75  281.2541  226.40  251.05   6322.1  1000 a   
  BradCannell 2579.4 2884.90 3330.3700 3059.45 3379.30  33667.3  1000    d
 SimonOHanlon  511.0  565.00  943.3089  586.45  623.65 210338.4  1000  b  
    SiboJiang 2558.1 2853.05 3377.6702 3010.30 3310.00  89718.0  1000    d
         jsta 1544.8 1652.45 2031.5065 1706.05 1872.65  11594.9  1000   c 
        akrun   93.8  111.60  139.9482  121.90  135.45   3851.2  1000 a


autoplot(mbm)

mbm %>% 
  tbl_df() %>%
  ggplot(aes(sample = time)) + 
  stat_qq() + 
  stat_qq_line() +
  facet_wrap(~expr, scales = "free")