Suggestion of new function: describe_missing()

Fixes #454
easystats · Nov 11, 2024 · ebaeb68 · ebaeb68
1 parent 218b7f4
commit ebaeb68
Show file tree

Hide file tree

Showing 3 changed files with 10 additions and 16 deletions.
diff --git a/R/describe_missing.R b/R/describe_missing.R
@@ -67,7 +67,7 @@
 #' describe_missing(df, scales = c("ID", "open", "extrovert", "agreeable"))
 describe_missing <- function(data, vars = NULL, scales = NULL) {
   classes <- lapply(data, class)
-  if (missing(vars) & missing(scales)) {
+  if (missing(vars) && missing(scales)) {
     vars.internal <- names(data)
   } else if (!missing(scales)) {
     vars.internal <- lapply(scales, function(x) {
@@ -81,7 +81,7 @@ describe_missing <- function(data, vars = NULL, scales = NULL) {
     vars.internal <- list(vars.internal)
   }
   na_df <- .describe_missing(data)
-  if (!missing(vars) | !missing(scales)) {
+  if (!missing(vars) || !missing(scales)) {
     na_list <- lapply(vars.internal, function(x) {
       data_subset <- data[, x, drop = FALSE]
       .describe_missing(data_subset)
@@ -93,7 +93,7 @@ describe_missing <- function(data, vars = NULL, scales = NULL) {
 }
 
 .describe_missing <- function(data) {
-  var <- paste0(names(data)[1], ":", names(data)[ncol(data)])
+  my_var <- paste0(names(data)[1], ":", names(data)[ncol(data)])
   items <- ncol(data)
   na <- sum(is.na(data))
   cells <- nrow(data) * ncol(data)
@@ -103,7 +103,7 @@ describe_missing <- function(data, vars = NULL, scales = NULL) {
   all_na <- sum(apply(data, 1, function(x) all(is.na(x))))
 
   data.frame(
-    var = var,
+    var = my_var,
     items = items,
     na = na,
     cells = cells,

diff --git a/tests/testthat/_snaps/describe_missing.md b/tests/testthat/_snaps/describe_missing.md
@@ -17,13 +17,6 @@
       2   Temp:Day     3  0   459       0.00      0           0.00      0
       3      Total     6 44   918       4.79      2          33.33      0
 
----
-
-    Code
-      df <- data.frame(ID = c("idz", NA), scale1_Q1 = fun(), scale1_Q2 = fun(),
-      scale1_Q3 = fun(), scale2_Q1 = fun(), scale2_Q2 = fun(), scale2_Q3 = fun(),
-      scale3_Q1 = fun(), scale3_Q2 = fun(), scale3_Q3 = fun())
-
 ---
 
     Code

diff --git a/tests/testthat/test-describe_missing.R b/tests/testthat/test-describe_missing.R
@@ -14,13 +14,14 @@ test_that("describe_missing", {
   fun <- function() {
     c(sample(c(NA, 1:10), replace = TRUE), NA, NA, NA)
   }
-  expect_snapshot(df <- data.frame(
+
+  # One can list the scale names directly:
+  df <- data.frame(
     ID = c("idz", NA),
     scale1_Q1 = fun(), scale1_Q2 = fun(), scale1_Q3 = fun(),
     scale2_Q1 = fun(), scale2_Q2 = fun(), scale2_Q3 = fun(),
-    scale3_Q1 = fun(), scale3_Q2 = fun(), scale3_Q3 = fun()
-  ))
-
-  # One can list the scale names directly:
+    scale3_Q1 = fun(), scale3_Q2 = fun(), scale3_Q3 = fun(),
+    stringsAsFactors = FALSE
+  )
   expect_snapshot(describe_missing(df, scales = c("ID", "scale1", "scale2", "scale3")))
 })