Grouped report_participants() does not report gender unless argument gender is capitalized (#378)

* Grouped `report_participants()` does not report gender unless argument `gender` is capitalized
Fixes #377

* fix lints

* last lint

* styler

---------

Co-authored-by: rempsyc <[email protected]>

Author: strengejacke

.lintr

@@ -12,6 +12,6 @@ linters: linters_with_defaults(
     todo_comment_linter = NULL,
     undesirable_function_linter(c("mapply" = NA, "sapply" = NA, "setwd" = NA)),
     undesirable_operator_linter = NULL,
-    unneeded_concatenation_linter(allow_single_expression = FALSE),
+    unnecessary_concatenation_linter(allow_single_expression = FALSE),
     defaults = linters_with_tags(tags = NULL)
   )

DESCRIPTION

@@ -1,7 +1,7 @@
 Type: Package
 Package: report
 Title: Automated Reporting of Results and Statistical Models
-Version: 0.5.7.9
+Version: 0.5.7.10
 Authors@R:
     c(person(given = "Dominique",
              family = "Makowski",

NEWS.md

@@ -22,6 +22,9 @@ Minor changes
 
 Bug fixes
 
+* Fixed issue in `report_participants`, which did not print the `"gender"`
+  category for grouped output when that argument was written in lower-case.
+
 * Fixed printing issue for intercept-only models.
 
 # report 0.5.7

R/report_participants.R

@@ -129,11 +129,11 @@ report_participants <- function(data,
                                 threshold = 10,
                                 ...) {
   # Convert empty strings to NA
-  data.list <- lapply(data, function(x) {
+  data_list <- lapply(data, function(x) {
     x[which(x == "")] <- NA
     x
   })
-  data <- as.data.frame(data.list)
+  data <- as.data.frame(data_list)
 
   # find age variable automatically
   if (is.null(age)) {
@@ -173,6 +173,7 @@ report_participants <- function(data,
         i,
         age = age,
         sex = sex,
+        gender = gender,
         education = education,
         country = country,
         race = race,
@@ -245,8 +246,8 @@ report_participants <- function(data,
                                  threshold = 10,
                                  ...) {
   # Sanity checks
-  demo.names <- c("Age", "Sex", "Gender", "Education", "Country", "Race")
-  data <- .check_df_names(data, names = demo.names)
+  demo_names <- c("Age", "Sex", "Gender", "Education", "Country", "Race")
+  data <- .check_df_names(data, names = demo_names)
 
   age <- .replace_names(data, age)
   sex <- .replace_names(data, sex)
@@ -404,15 +405,15 @@ report_participants <- function(data,
   } else {
     data[[country]] <- as.character(data[[country]])
     data[which(data[[country]] %in% c(NA, "NA")), country] <- "missing"
-    frequency.table <- as.data.frame(datawizard::data_tabulate(data[[country]]))[c(2, 4)]
-    names(frequency.table)[2] <- "Percent"
-    frequency.table <- frequency.table[-which(is.na(frequency.table$Value)), ]
-    frequency.table <- frequency.table[order(-frequency.table$Percent), ]
-    upper <- frequency.table[which(frequency.table$Percent >= threshold), ]
-    lower <- frequency.table[which(frequency.table$Percent < threshold), ]
+    frequency_table <- as.data.frame(datawizard::data_tabulate(data[[country]]))[c(2, 4)]
+    names(frequency_table)[2] <- "Percent"
+    frequency_table <- frequency_table[-which(is.na(frequency_table$Value)), ]
+    frequency_table <- frequency_table[order(-frequency_table$Percent), ]
+    upper <- frequency_table[which(frequency_table$Percent >= threshold), ]
+    lower <- frequency_table[which(frequency_table$Percent < threshold), ]
     if (nrow(lower) > 0) {
-      lower.sum <- data.frame(Value = "other", Percent = sum(lower$Percent), stringsAsFactors = FALSE)
-      combined <- rbind(upper, lower.sum)
+      lower_sum <- data.frame(Value = "other", Percent = sum(lower$Percent), stringsAsFactors = FALSE)
+      combined <- rbind(upper, lower_sum)
     } else {
       combined <- upper
     }
@@ -426,15 +427,15 @@ report_participants <- function(data,
   } else {
     data[[race]] <- as.character(data[[race]])
     data[which(data[[race]] %in% c(NA, "NA")), race] <- "missing"
-    frequency.table <- as.data.frame(datawizard::data_tabulate(data[[race]]))[c(2, 4)]
-    names(frequency.table)[2] <- "Percent"
-    frequency.table <- frequency.table[-which(is.na(frequency.table$Value)), ]
-    frequency.table <- frequency.table[order(-frequency.table$Percent), ]
-    upper <- frequency.table[which(frequency.table$Percent >= threshold), ]
-    lower <- frequency.table[which(frequency.table$Percent < threshold), ]
+    frequency_table <- as.data.frame(datawizard::data_tabulate(data[[race]]))[c(2, 4)]
+    names(frequency_table)[2] <- "Percent"
+    frequency_table <- frequency_table[-which(is.na(frequency_table$Value)), ]
+    frequency_table <- frequency_table[order(-frequency_table$Percent), ]
+    upper <- frequency_table[which(frequency_table$Percent >= threshold), ]
+    lower <- frequency_table[which(frequency_table$Percent < threshold), ]
     if (nrow(lower) > 0) {
-      lower.sum <- data.frame(Value = "other", Percent = sum(lower$Percent), stringsAsFactors = FALSE)
-      combined <- rbind(upper, lower.sum)
+      lower_sum <- data.frame(Value = "other", Percent = sum(lower$Percent), stringsAsFactors = FALSE)
+      combined <- rbind(upper, lower_sum)
     } else {
       combined <- upper
     }

tests/testthat/test-report_participants.R

@@ -1,3 +1,44 @@
+test_that("report_participants, argument gender works", {
+  # Works when capitalized
+  data <- data.frame(
+    "Age" = c(22, 22, 54, 54, 8, 8, 42, 42),
+    "Gender" = c("N", "N", "W", "M", "M", "M", "Non-Binary", "Non-Binary"),
+    "Condition" = c("A", "A", "A", "A", "B", "B", "B", "B"),
+    stringsAsFactors = FALSE
+  )
+  out <- report_participants(data)
+  expect_identical(
+    out,
+    paste(
+      "8 participants (Mean age = 31.5, SD = 19.0, range: [8, 54];",
+      "Gender: 12.5% women, 37.5% men, 50.00% non-binary)"
+    )
+  )
+  out <- report_participants(data, group = "Condition")
+  expect_identical(
+    out,
+    paste(
+      "For the 'Condition - A' group: 4 participants (Mean age = 38.0,",
+      "SD = 18.5, range: [22, 54]; Gender: 25.0% women, 25.0% men,",
+      "50.00% non-binary) and for the 'Condition - B' group: 4 participants",
+      "(Mean age = 25.0, SD = 19.6, range: [8, 42]; Gender: 0.0% women,",
+      "50.0% men, 50.00% non-binary)"
+    )
+  )
+  # works when lowercase
+  out <- report_participants(data, group = "Condition")
+  expect_identical(
+    out,
+    paste(
+      "For the 'Condition - A' group: 4 participants (Mean age = 38.0,",
+      "SD = 18.5, range: [22, 54]; Gender: 25.0% women, 25.0% men,",
+      "50.00% non-binary) and for the 'Condition - B' group: 4 participants",
+      "(Mean age = 25.0, SD = 19.6, range: [8, 42]; Gender: 0.0% women,",
+      "50.0% men, 50.00% non-binary)"
+    )
+  )
+})
+
 test_that("report_participants", {
   data <- data.frame(
     "Age" = c(22, 22, 54, 54, 8, 8),
@@ -9,14 +50,24 @@ test_that("report_participants", {
 
   expect_snapshot(
     variant = "windows",
-    report_participants(data, age = "Age", sex = "Sex", participant = "Participant")
+    report_participants(data,
+      age = "Age", sex = "Sex",
+      participant = "Participant"
+    )
   )
   expect_snapshot(
     variant = "windows",
     report_participants(data, participant = "Participant", spell_n = TRUE)
   )
 
-  expect_equal(nchar(report_participants(data, participant = "Participant", spell_n = TRUE)), 160, ignore_attr = TRUE)
+  expect_equal(
+    nchar(report_participants(data,
+      participant = "Participant",
+      spell_n = TRUE
+    )),
+    160,
+    ignore_attr = TRUE
+  )
 
   data2 <- data.frame(
     "Age" = c(22, 22, 54, 54, 8, 8),
@@ -45,7 +96,10 @@ test_that("report_participants", {
   # Add tests for education, country, race
   data4 <- data.frame(
     "Education" = c(0, 8, -3, -5, 3, 5, NA),
-    "Education2" = c("Bachelor", "PhD", "Highschool", "Highschool", "Bachelor", "Bachelor", NA),
+    "Education2" = c(
+      "Bachelor", "PhD", "Highschool", "Highschool",
+      "Bachelor", "Bachelor", NA
+    ),
     "Country" = c("USA", "Canada", "Canada", "India", "Germany", "USA", NA),
     "Race" = c("Black", NA, "White", "Asian", "Black", "Black", "White"),
     stringsAsFactors = FALSE