用于计算多个字段的空值的Tidyverse解决方案

Question

我试图通过计算12个不同列的空值数和响应数（值+ NA）来总结我的数据。 （为此示例重命名）

数据：

my_df <- structure(list(SCR1 = c(100, 80.2, 70.3, 
90.1, 100, 100, 100, 100, 40.6, 80.2, 80.2, 90.1, 30.7, 100, 
80.2), SCR2 = c(75.25, 75.25, 75.25, 75.25, 75.25, 75.25, 
100, 100, 50.5, 50.5, 75.25, 50.5, 50.5, 100, 50.5), SCR3 = c(100, 
100, 100, 100, 75.25, 75.25, 100, 100, 100, 75.25, 100, 100, 
NA, 100, 75.25), SCR4 = c(100, 50.5, 
50.5, 75.25, 100, 75.25, 100, 100, 100, 75.25, 50.5, 100, 100, 
100, 75.25), SCR5 = c(100, 75.25, 50.5, 
75.25, 100, 75.25, 100, 100, 50.5, 75.25, 75.25, 75.25, 25.75, 
100, 75.25), SCR6 = c(100, 25.75, 50.5, 
75.25, 100, 75.25, 100, 100, 75.25, 75.25, 75.25, 100, 50.5, 
100, 50.5), SCR7 = c(75.25, 50.5, 75.25, 
100, 50.5, 75.25, 100, 100, 75.25, 50.5, 75.25, 100, 25.75, 100, 
75.25), SCR8 = c(75.25, 75.25, 50.5, 75.25, 
75.25, 75.25, 100, 100, 75.25, 75.25, 75.25, 75.25, 50.5, 100, 
75.25), SCR9 = c(50.5, NA, NA, 25.75, 100, NA, 
NA, NA, 100, NA, NA, NA, 75.25, NA, NA), SCR10 = c(25.75, 
NA, NA, NA, NA, 1, NA, NA, NA, NA, NA, NA, NA, NA, NA), SCR11 = c(100, 
75.25, 50.5, 75.25, 100, 75.25, 100, 100, 75.25, 75.25, 75.25, 
100, 50.5, 100, 50.5), SCR12 = c(75.25, 75.25, 
50.5, NA, 75.25, 75.25, 100, 100, 75.25, NA, 75.25, 75.25, 50.5, 
100, 50.5), ID = 1:15), row.names = c(NA, 15L), class = "data.frame")

在这里，我想返回值的数量和NA的数量，然后返回百分比NA

我找到了一个计算NA数量的解决方案，但我很难添加第二/第三列的计数和百分比。

my_df %>%
  map_df(function(x) sum(is.na(x))) %>%
  gather(feature, num_nulls) %>%
  dplyr::arrange(desc(num_nulls))

如何添加计数和百分比na？我正在尝试使用tidyverse并避免使用SQL。

Answer 1

你快到了。可以使用额外的mutate语句创建额外的两列：

my_df %>%
    map_df(function(x) sum(is.na(x))) %>%
    gather(feature, num_nulls) %>%
    dplyr::arrange(desc(num_nulls)) %>%
    mutate(num_responses = nrow(my_df) - num_nulls,
        percent = num_responses/nrow(my_df))