add XPT files for SAS software

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: AMR
 Version: 2.0.0.9015
-Date: 2023-05-11
+Date: 2023-05-12
 Title: Antimicrobial Resistance Data Analysis
 Description: Functions to simplify and standardise antimicrobial resistance (AMR)
   data analysis and to work with microbial and antimicrobial properties by

NEWS.md

@@ -10,6 +10,8 @@
 * Added microbial codes for Gram-negative/positive anaerobic bacteria
 * `mo_rank()` now returns `NA` for 'unknown' microorganisms (`B_ANAER`, `B_ANAER-NEG`, `B_ANAER-POS`, `B_GRAMN`, `B_GRAMP`, `F_FUNGUS`, `F_YEAST`, and `UNKNOWN`)
 * Fixed a bug for `as.mo()` that led to coercion of `NA` values when using custom microorganism codes
+* Added SAS Transport files (file extension `.xpt`) to [our download page](https://msberends.github.io/AMR/articles/datasets.html) to use in SAS software
+
 
 # AMR 2.0.0
 

data-raw/_pre_commit_hook.R

@@ -366,7 +366,7 @@ if (changed_md5(clin_break)) {
   write_md5(clin_break)
   try(saveRDS(clin_break, "data-raw/clinical_breakpoints.rds", version = 2, compress = "xz"), silent = TRUE)
   try(write.table(clin_break, "data-raw/clinical_breakpoints.txt", sep = "\t", na = "", row.names = FALSE), silent = TRUE)
-  try(haven::write_sas(clin_break, "data-raw/clinical_breakpoints.sas"), silent = TRUE)
+  try(haven::write_xpt(clin_break, "data-raw/clinical_breakpoints.xpt"), silent = TRUE)
   try(haven::write_sav(clin_break, "data-raw/clinical_breakpoints.sav"), silent = TRUE)
   try(haven::write_dta(clin_break, "data-raw/clinical_breakpoints.dta"), silent = TRUE)
   try(openxlsx::write.xlsx(clin_break, "data-raw/clinical_breakpoints.xlsx"), silent = TRUE)
@@ -382,7 +382,7 @@ if (changed_md5(microorganisms)) {
   mo <- microorganisms
   mo$snomed <- max_50_snomed
   mo <- dplyr::mutate_if(mo, ~ !is.numeric(.), as.character)
-  try(haven::write_sas(mo, "data-raw/microorganisms.sas"), silent = TRUE)
+  try(haven::write_xpt(mo, "data-raw/microorganisms.xpt"), silent = TRUE)
   try(haven::write_sav(mo, "data-raw/microorganisms.sav"), silent = TRUE)
   try(haven::write_dta(mo, "data-raw/microorganisms.dta"), silent = TRUE)
   mo_all_snomed <- microorganisms %>% mutate_if(is.list, function(x) sapply(x, paste, collapse = ","))
@@ -397,7 +397,7 @@ if (changed_md5(ab)) {
   usethis::ui_info(paste0("Saving {usethis::ui_value('antibiotics')} to {usethis::ui_value('data-raw/')}"))
   write_md5(ab)
   try(saveRDS(antibiotics, "data-raw/antibiotics.rds", version = 2, compress = "xz"), silent = TRUE)
-  try(haven::write_sas(ab, "data-raw/antibiotics.sas"), silent = TRUE)
+  try(haven::write_xpt(ab, "data-raw/antibiotics.xpt"), silent = TRUE)
   try(haven::write_sav(ab, "data-raw/antibiotics.sav"), silent = TRUE)
   try(haven::write_dta(ab, "data-raw/antibiotics.dta"), silent = TRUE)
   ab_lists <- antibiotics %>% mutate_if(is.list, function(x) sapply(x, paste, collapse = ","))
@@ -412,7 +412,7 @@ if (changed_md5(av)) {
   usethis::ui_info(paste0("Saving {usethis::ui_value('antivirals')} to {usethis::ui_value('data-raw/')}"))
   write_md5(av)
   try(saveRDS(antivirals, "data-raw/antivirals.rds", version = 2, compress = "xz"), silent = TRUE)
-  try(haven::write_sas(av, "data-raw/antivirals.sas"), silent = TRUE)
+  try(haven::write_xpt(av, "data-raw/antivirals.xpt"), silent = TRUE)
   try(haven::write_sav(av, "data-raw/antivirals.sav"), silent = TRUE)
   try(haven::write_dta(av, "data-raw/antivirals.dta"), silent = TRUE)
   av_lists <- antivirals %>% mutate_if(is.list, function(x) sapply(x, paste, collapse = ","))
@@ -433,7 +433,7 @@ if (changed_md5(intrinsicR)) {
   write_md5(intrinsicR)
   try(saveRDS(intrinsicR, "data-raw/intrinsic_resistant.rds", version = 2, compress = "xz"), silent = TRUE)
   try(write.table(intrinsicR, "data-raw/intrinsic_resistant.txt", sep = "\t", na = "", row.names = FALSE), silent = TRUE)
-  try(haven::write_sas(intrinsicR, "data-raw/intrinsic_resistant.sas"), silent = TRUE)
+  try(haven::write_xpt(intrinsicR, "data-raw/intrinsic_resistant.xpt"), silent = TRUE)
   try(haven::write_sav(intrinsicR, "data-raw/intrinsic_resistant.sav"), silent = TRUE)
   try(haven::write_dta(intrinsicR, "data-raw/intrinsic_resistant.dta"), silent = TRUE)
   try(openxlsx::write.xlsx(intrinsicR, "data-raw/intrinsic_resistant.xlsx"), silent = TRUE)
@@ -446,7 +446,7 @@ if (changed_md5(dosage)) {
   write_md5(dosage)
   try(saveRDS(dosage, "data-raw/dosage.rds", version = 2, compress = "xz"), silent = TRUE)
   try(write.table(dosage, "data-raw/dosage.txt", sep = "\t", na = "", row.names = FALSE), silent = TRUE)
-  try(haven::write_sas(dosage, "data-raw/dosage.sas"), silent = TRUE)
+  try(haven::write_xpt(dosage, "data-raw/dosage.xpt"), silent = TRUE)
   try(haven::write_sav(dosage, "data-raw/dosage.sav"), silent = TRUE)
   try(haven::write_dta(dosage, "data-raw/dosage.dta"), silent = TRUE)
   try(openxlsx::write.xlsx(dosage, "data-raw/dosage.xlsx"), silent = TRUE)

inst/tinytest/test-mo_property.R

@@ -96,10 +96,9 @@ expect_true(length(mo_synonyms("Candida albicans")) > 1)
 expect_inherits(mo_synonyms(c("Candida albicans", "Escherichia coli")), "list")
 expect_equal(names(mo_info("Escherichia coli")), c(
   "mo",
-  "kingdom", "phylum", "class", "order",
+  "kingdom", "phylum", "class", "order", "family", "genus", "species", "subspecies",
-  "family", "genus", "species", "subspecies",
   "status", "synonyms", "gramstain", "oxygen_tolerance",
-  "url", "ref", "snomed"
+  "url", "ref", "snomed", "lpsn", "gbif"
 ))
 expect_inherits(mo_info(c("Escherichia coli", "Staphylococcus aureus")), "list")
 

vignettes/datasets.Rmd

@@ -50,6 +50,7 @@ download_txt <- function(filename) {
   feather <- paste0(filename, ".feather")
   parquet <- paste0(filename, ".parquet")
   sas <- paste0(filename, ".sas")
+  xpt <- paste0(filename, ".xpt")
   spss <- paste0(filename, ".sav")
   stata <- paste0(filename, ".dta")
   create_txt <- function(filename, type, software, exists) {
@@ -70,6 +71,7 @@ download_txt <- function(filename) {
     file.exists(feather),
     file.exists(parquet),
     file.exists(sas),
+    file.exists(xpt),
     file.exists(spss),
     file.exists(stata)
   )) {
@@ -80,7 +82,8 @@ download_txt <- function(filename) {
       create_txt(excel, "xlsx", "Microsoft Excel workbook", file.exists(excel)),
       create_txt(feather, "feather", "Apache Feather file", file.exists(feather)),
       create_txt(parquet, "parquet", "Apache Parquet file", file.exists(parquet)),
-      create_txt(sas, "sas", "SAS data file", file.exists(sas)),
+      create_txt(sas, "sas", "SAS data (SAS) file", file.exists(sas)),
+      create_txt(xpt, "xpt", "SAS transport (XPT) file", file.exists(xpt)),
       create_txt(spss, "sav", "IBM SPSS Statistics data file", file.exists(spss)),
       create_txt(stata, "dta", "Stata DTA file", file.exists(stata))
     )
@@ -123,7 +126,7 @@ This data set is in R available as `microorganisms`, after you load the `AMR` pa
 
 `r download_txt("microorganisms")`
 
-**NOTE: The exported files for SAS, SPSS and Stata contain only the first 50 SNOMED codes per record, as their file size would otherwise exceed 100 MB; the file size limit of GitHub.** Advice? Use R instead.
+**NOTE: The exported files for SAS, SPSS and Stata contain only the first 50 SNOMED codes per record, as their file size would otherwise exceed 100 MB; the file size limit of GitHub.** Their file structures and compression techniques are very inefficient. Advice? Use R instead. It's free and much better in many ways.
 
 The tab-separated text file and Microsoft Excel workbook both contain all SNOMED codes as comma separated values.