updates to address OM column name problem

AlisonLanski · Dec 8, 2024 · bb50534 · bb50534
1 parent b1af7c2
commit bb50534
Show file tree

Hide file tree

Showing 5 changed files with 20 additions and 1 deletion.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,6 +1,6 @@
 Package: IPEDSuploadables
 Title: Transforms Institutional Data into Text Files for IPEDS Automated Import/Upload
-Version: 2.9.1
+Version: 2.10.0
 Authors@R: c(
             person(given = "Alison", family = "Lanski", 
             role = c("aut", "cre"),

diff --git a/NEWS.md b/NEWS.md
@@ -1,3 +1,7 @@
+#IPEDSuploadables 2.10.0
+* Updating incorrect column name in Outcome Measures vignette
+* Added quality check for correct column name in OM data prep script
+
 # IPEDSuploadables 2.9.1
 * Changing data load method in vignettes to avoid error on old Mac OS checks
 * Making function documentation a bit more uniform

diff --git a/R/prep_om_data_frame.R b/R/prep_om_data_frame.R
@@ -13,6 +13,13 @@ prep_om_data_frame <- function(df) {
 
   colnames(df) <- stringr::str_to_upper(colnames(df))
 
+
+  if("EXCLUSION" %in% colnames(df) & sum(grepl(x = df$EXCLUSION, "clude")) > 1){
+    df <- df %>%
+      dplyr::rename(COHORTSTATUS = .data$EXCLUSION)
+  }
+
+
   df <- df %>%
         dplyr::mutate(UNITID = as.character(.data$UNITID),
                       EXCLUSION = dplyr::case_when(
@@ -24,6 +31,7 @@ prep_om_data_frame <- function(df) {
 
   if (sum(is.na(df$EXCLUSION)) > 0) {
     warning(paste0("Check CohortStatus: invalid values found for StudentId: ", toString(df$STUDENTID[is.na(df$EXCLUSION)])))
+    warning("Please use the CohortStatus column with values of 'Include' or 'Exclude' to indicate exclusions.")
   }
 
   return(df)

diff --git a/data/specs_OM.rda b/data/specs_OM.rda
diff --git a/tests/testthat/test-prep-scripts.R b/tests/testthat/test-prep-scripts.R
@@ -26,6 +26,11 @@ hr_df <- data.frame(unitid = 123456,
 
 om_df <- data.frame(unitid = 123456,
                     cohortstatus = c("Include", "Exclude"))
+om_df2 <- data.frame(unitid = 123456,
+                     exclusion = c("Include", "Exclude"))
+om_df3 <- data.frame(unitid = "000000",
+                 studentid = c("A", "B", "C"),
+                 exclusion = c("Include",  "Exclude", "TRUE"))
 
 
 ####
@@ -112,6 +117,7 @@ test_that("Funky data used for recoding will throw warning messages", {
   expect_warning(prep_om_data_frame(data.frame(unitid = 123456,
                                                studentid = c('AAA', 'BBB', 'CCC'),
                                                cohortstatus = c("Amy", "Bob", "Include"))), "Check CohortStatus")
+  expect_warning(prep_om_data_frame(om_df3))
 })
 
 
@@ -124,6 +130,7 @@ test_that("Funky data used for recoding will throw warning messages", {
 
 test_that("OM prep recoding comes out as expected", {
   expect_equal(prep_om_data_frame(om_df)$EXCLUSION, c(FALSE, TRUE))
+  expect_equal(prep_om_data_frame(om_df2)$EXCLUSION, c(FALSE, TRUE))
 })