new tibble export

.Rbuildignore

@@ -24,8 +24,9 @@
 ^\.lintr$
 ^tests/testthat/_snaps$
 ^vignettes/AMR\.Rmd$
+^vignettes/AMR_intro\.png$
 ^vignettes/benchmarks\.Rmd$
-^vignettes/*\.not$
+^vignettes/benchmarks\.Rmd\.not$
 ^vignettes/datasets\.Rmd$
 ^vignettes/EUCAST\.Rmd$
 ^vignettes/MDR\.Rmd$

AMR.Rproj

@@ -1,7 +1,7 @@
 Version: 1.0
 
 RestoreWorkspace: No
-SaveWorkspace: Ask
+SaveWorkspace: No
 AlwaysSaveHistory: Yes
 
 EnableCodeIndexing: Yes
@@ -13,6 +13,7 @@ RnwWeave: Sweave
 LaTeX: pdfLaTeX
 
 AutoAppendNewline: Yes
+LineEndingConversion: Posix
 
 BuildType: Package
 PackageUseDevtools: Yes
@@ -20,3 +21,5 @@ PackageInstallArgs: --no-multiarch --with-keep.source
 PackageBuildArgs: --no-build-vignettes
 PackageCheckArgs: --no-build-vignettes --as-cran
 PackageRoxygenize: rd,collate,namespace
+
+UseNativePipeOperator: No

DESCRIPTION

@@ -1,35 +1,36 @@
 Package: AMR
-Version: 1.8.1.9030
+Version: 1.8.1.9031
-Date: 2022-08-26
+Date: 2022-08-27
 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
     using evidence-based methods and reliable reference data such as LPSN
     <doi:10.1099/ijsem.0.004332>.
 Authors@R: c(
-    person(c("Matthijs", "S."), "Berends", role = c("aut", "cre"), comment = c(ORCID = "0000-0001-7620-1800"), email = "m.berends@certe.nl"),
+ person(family = "Berends",     c("Matthijs", "S."), role = c("aut", "cre"), comment = c(ORCID = "0000-0001-7620-1800"), email = "m.berends@certe.nl"),
-    person(c("Christian", "F."), "Luz", role = c("aut", "ctb"), comment = c(ORCID = "0000-0001-5809-5995")),
+ person(family = "Luz",         c("Christian", "F."), role = c("aut", "ctb"), comment = c(ORCID = "0000-0001-5809-5995")),
-    person("Dennis", "Souverein", role = c("aut", "ctb"), comment = c(ORCID = "0000-0003-0455-0336")),
+ person(family = "Souverein",   c("Dennis"), role = c("aut", "ctb"), comment = c(ORCID = "0000-0003-0455-0336")),
-    person(c("Erwin", "E.", "A."), "Hassing", role = c("aut", "ctb")),
+ person(family = "Hassing",     c("Erwin", "E.", "A."), role = c("aut", "ctb")),
-    person("Casper",  "Albers", role = "ths", comment = c(ORCID = "0000-0002-9213-6743")),
+ person(family = "Albers",      c("Casper", "J."), role = "ths", comment = c(ORCID = "0000-0002-9213-6743")),
-    person("Peter",   "Dutey-Magni", role = "ctb", comment = c(ORCID = "0000-0002-8942-9836")),
+ person(family = "Dutey-Magni", c("Peter"), role = "ctb", comment = c(ORCID = "0000-0002-8942-9836")),
-    person("Judith",  "Fonville", role = "ctb"),
+ person(family = "Fonville",    c("Judith", "M"), role = "ctb"),
-    person("Alex",    "Friedrich", role = "ths", comment = c(ORCID = "0000-0003-4881-038X")),
+ person(family = "Friedrich",   c("Alex", "W."), role = "ths", comment = c(ORCID = "0000-0003-4881-038X")),
-    person("Corinna", "Glasner", role = "ths", comment = c(ORCID = "0000-0003-1241-1328")),
+ person(family = "Glasner",     c("Corinna"), role = "ths", comment = c(ORCID = "0000-0003-1241-1328")),
-    person("Eric",    "Hazenberg", role = "ctb"),
+ person(family = "Hazenberg",   c("Eric", "H.", "L.", "C.", "M."), role = "ctb"),
-    person("Gwen",    "Knight", role = "ctb", comment = c(ORCID = "0000-0002-7263-9896")),
+ person(family = "Knight",      c("Gwen"), role = "ctb", comment = c(ORCID = "0000-0002-7263-9896")),
-    person("Annick",  "Lenglet", role = "ctb", comment = c(ORCID = "0000-0003-2013-8405")),
+ person(family = "Lenglet",     c("Annick"), role = "ctb", comment = c(ORCID = "0000-0003-2013-8405")),
-    person("Bart",    "Meijer", role = "ctb"),
+ person(family = "Meijer",      c("Bart", "C."), role = "ctb"),
-    person("Anton",   "Mymrikov", role = "ctb"),
+ person(family = "Mymrikov",    c("Anton"), role = "ctb"),
-    person("Sofia",   "Ny", role = "ctb", comment = c(ORCID = "0000-0002-2017-1363")),
+ person(family = "Ny",          c("Sofia"), role = "ctb", comment = c(ORCID = "0000-0002-2017-1363")),
-    person("Rogier",  "Schade", role = "ctb"),
+ person(family = "Schade",      c("Rogier", "P."), role = "ctb"),
-    person("Bhanu",   "Sinha", role = "ths", comment = c(ORCID = "0000-0003-1634-0010")),
+ person(family = "Sinha",       c("Bhanu", "N.", "M."), role = "ths", comment = c(ORCID = "0000-0003-1634-0010")),
-    person("Anthony", "Underwood", role = "ctb", comment = c(ORCID = "0000-0002-8547-4277")))
+ person(family = "Underwood",   c("Anthony"), role = "ctb", comment = c(ORCID = "0000-0002-8547-4277")))
 Depends: R (>= 3.0.0)
 Enhances:
   cleaner,
   skimr,
   ggplot2,
+  tibble,
   tidyselect
 Suggests: 
   curl,
@@ -41,7 +42,7 @@ Suggests:
   rvest,
   tinytest,
   xml2
-VignetteBuilder: knitr,rmarkdown
+VignetteBuilder: knitr
 URL: https://msberends.github.io/AMR/, https://github.com/msberends/AMR
 BugReports: https://github.com/msberends/AMR/issues
 License: GPL-2 | file LICENSE

NEWS.md

@@ -1,8 +1,10 @@
-# AMR 1.8.1.9030
+# AMR 1.8.1.9031
 
 ### New
 * EUCAST 2022 and CLSI 2022 guidelines have been added for `as.rsi()`. EUCAST 2022 is now the new default guideline for all MIC and disks diffusion interpretations.
-* Support for the following languages: Chinese, Greek, Japanese, Polish, Turkish and Ukrainian. The `AMR` package is now available in 16 languages.
+* Support for `data.frame`-enhancing R packages, more specifically: `data.table`, `tibble`, and `tsibble`. AMR package functions that have a data set as output (such as `rsi_df()` and `bug_drug_combinations()`), will now return the same data type as the input. Furthermore, all our data sets are now in `tibble` format.
+* Our data sets are now also continually exported to Apache Feather and Apache Parquet formats. You can find more info [in this article on our website](https://msberends.github.io/AMR/articles/datasets.html).
+* Support for the following languages: Chinese, Greek, Japanese, Polish, Turkish and Ukrainian. We are very grateful for the valuable input by our colleagues from other countries. The `AMR` package is now available in 16 languages.
 
 ### Changed
 * Fix for using `as.rsi()` on certain EUCAST breakpoints for MIC values
@@ -16,11 +18,12 @@
 * Changed value in column `prevalence` of the `microorganisms` data set from 3 to 2 for these genera: *Acholeplasma*, *Alistipes*, *Alloprevotella*, *Bergeyella*, *Borrelia*, *Brachyspira*, *Butyricimonas*, *Cetobacterium*, *Chlamydia*, *Chlamydophila*, *Deinococcus*, *Dysgonomonas*, *Elizabethkingia*, *Empedobacter*, *Haloarcula*, *Halobacterium*, *Halococcus*, *Myroides*, *Odoribacter*, *Ornithobacterium*, *Parabacteroides*, *Pedobacter*, *Phocaeicola*, *Porphyromonas*, *Riemerella*, *Sphingobacterium*, *Streptobacillus*, *Tenacibaculum*, *Terrimonas*, *Victivallis*, *Wautersiella*, *Weeksella*
 * Fix for using the form `df[carbapenems() == "R", ]` using the latest `vctrs` package
 * Fix for using `info = FALSE` in `mdro()`
+* All data sets in this package are now exported as `tibble`, instead of base R `data.frame`s. Older R versions are still supported.
+* Automatic language determination will give a note once a session
 
 ### Other
 * New website to make use of the new Bootstrap 5 and pkgdown v2.0. The website now contains results for all examples and will be automatically regenerated with every change to our repository, using GitHub Actions
 * Added Peter Dutey-Magni and Anton Mymrikov as contributors, to thank them for their valuable input
-* Our data sets are now also continually exported to Apache Feather and Apache Parquet formats
 * Set up Git Large File Storage (Git LFS) for the large SAS and SPSS file formats
 
 
@@ -210,7 +213,7 @@
 * Functions `oxazolidinones()` (an antibiotic selector function) and `filter_oxazolidinones()` (an antibiotic filter function) to select/filter on e.g. linezolid and tedizolid
   ```r
   library(dplyr)
-  x <- example_isolates %>% select(date, hospital_id, oxazolidinones())
+  x <- example_isolates %>% select(date, ward, oxazolidinones())
   #> Selecting oxazolidinones: column 'LNZ' (linezolid)
   
   x <- example_isolates %>% filter_oxazolidinones()
@@ -295,7 +298,7 @@
   ```r
   library(dplyr)
   example_isolates %>%
-    group_by(patient_id, hospital_id) %>%
+    group_by(patient_id, ward) %>%
     filter(is_new_episode(date, episode_days = 60))
   ```
 * Functions `mo_is_gram_negative()` and `mo_is_gram_positive()` as wrappers around `mo_gramstain()`. They always return `TRUE` or `FALSE` (except when the input is `NA` or the MO code is `UNKNOWN`), thus always return `FALSE` for species outside the taxonomic kingdom of Bacteria.
@@ -909,7 +912,7 @@ This software is now out of beta and considered stable. Nonetheless, this packag
       boxplot()
     # grouped boxplots:
     septic_patients %>% 
-      group_by(hospital_id) %>% 
+      group_by(ward) %>% 
       freq(age) %>%
       boxplot()
     ```
@@ -1162,13 +1165,13 @@ We've got a new website: [https://msberends.gitlab.io/AMR](https://msberends.git
   * Support for grouping variables, test with:
     ```r
     septic_patients %>% 
-      group_by(hospital_id) %>% 
+      group_by(ward) %>% 
       freq(gender)
     ```
   * Support for (un)selecting columns:
     ```r
     septic_patients %>% 
-      freq(hospital_id) %>% 
+      freq(ward) %>% 
       select(-count, -cum_count) # only get item, percent, cum_percent
     ```
   * Check for `hms::is.hms`

R/aa_helper_functions.R

@@ -565,7 +565,7 @@ return_after_integrity_check <- function(value, type, check_vector) {
   value
 }
 
-# transforms data set to data.frame with only ASCII values, to comply with CRAN policies
+# transforms data set to a tibble with only ASCII values, to comply with CRAN policies
 dataset_UTF8_to_ASCII <- function(df) {
   trans <- function(vect) {
     iconv(vect, from = "UTF-8", to = "ASCII//TRANSLIT")
@@ -587,7 +587,7 @@ dataset_UTF8_to_ASCII <- function(df) {
       df[, i] <- col
     }
   }
-  df
+  tibble::as_tibble(df)
 }
 
 # for eucast_rules() and mdro(), creates markdown output with URLs and names
@@ -711,7 +711,7 @@ meet_criteria <- function(object,
   if (!is.null(pkg_env$meet_criteria_error_txt)) {
     error_txt <- pkg_env$meet_criteria_error_txt
     pkg_env$meet_criteria_error_txt <- NULL
-    stop(error_txt, call. = FALSE) # don't use stop_() here, pkg may not be loaded yet
+    stop(error_txt, call. = FALSE) # don't use stop_() here, our pkg may not be loaded yet
   }
   pkg_env$meet_criteria_error_txt <- NULL
 
@@ -932,7 +932,7 @@ unique_call_id <- function(entire_session = FALSE, match_fn = NULL) {
 #' @param entire_session show message once per session
 message_not_thrown_before <- function(fn, ..., entire_session = FALSE) {
   # this is to prevent that messages/notes will be printed for every dplyr group or more than once per session
-  # e.g. this would show a msg 4 times: example_isolates %>% group_by(hospital_id) %>% filter(mo_is_gram_negative())
+  # e.g. this would show a msg 4 times: example_isolates %>% group_by(ward) %>% filter(mo_is_gram_negative())
   salt <- gsub("[^a-zA-Z0-9|_-]", "?", paste(c(...), sep = "|", collapse = "|"), perl = TRUE)
   not_thrown_before <- is.null(pkg_env[[paste0("thrown_msg.", fn, ".", salt)]]) ||
     !identical(pkg_env[[paste0("thrown_msg.", fn, ".", salt)]],
@@ -1153,6 +1153,19 @@ create_pillar_column <- function(x, ...) {
   new_pillar_shaft_simple(x, ...)
 }
 
+as_original_data_class <- function(df, old_class = NULL) {
+  if ("tbl_df" %in% old_class && pkg_is_available("tibble", also_load = FALSE)) {
+    fn <- import_fn("as_tibble", "tibble")
+  } else if ("tbl_ts" %in% old_class && pkg_is_available("tsibble", also_load = FALSE)) {
+    fn <- import_fn("as_tsibble", "tsibble")
+  } else if ("data.table" %in% old_class && pkg_is_available("data.table", also_load = FALSE)) {
+    fn <- import_fn("as.data.table", "data.table")
+  } else {
+    fn <- base::as.data.frame
+  }
+  fn(df)
+}
+
 # copied from vctrs::s3_register by their permission:
 # https://github.com/r-lib/vctrs/blob/05968ce8e669f73213e3e894b5f4424af4f46316/R/register-s3.R
 s3_register <- function(generic, class, method = NULL) {

R/ab.R

@@ -260,13 +260,13 @@ as.ab <- function(x, flag_multiple_results = TRUE, info = interactive(), ...) {
     }
     
     # try if name starts with it
-    found <- antibiotics[which(AB_lookup$generalised_name %like% paste0("^", x_spelling)), ]$ab
+    found <- antibiotics[which(AB_lookup$generalised_name %like% paste0("^", x_spelling)), "ab", drop = TRUE]
     if (length(found) > 0) {
       x_new[i] <- note_if_more_than_one_found(found, i, from_text)
       next
     }
     # try if name ends with it
-    found <- antibiotics[which(AB_lookup$generalised_name %like% paste0(x_spelling, "$")), ]$ab
+    found <- antibiotics[which(AB_lookup$generalised_name %like% paste0(x_spelling, "$")), "ab", drop = TRUE]
     if (nchar(x[i]) >= 4 & length(found) > 0) {
       x_new[i] <- note_if_more_than_one_found(found, i, from_text)
       next

R/ab_property.R

@@ -429,10 +429,10 @@ ab_validate <- function(x, property, ...) {
   } else {
     # try to catch an error when inputting an invalid argument
     # so the 'call.' can be set to FALSE
-    tryCatch(x[1L] %in% antibiotics[1, property],
+    tryCatch(x[1L] %in% antibiotics[1, property, drop = TRUE],
              error = function(e) stop(e$message, call. = FALSE))
     
-    if (!all(x %in% AB_lookup[, property])) {
+    if (!all(x %in% AB_lookup[, property, drop = TRUE])) {
       x <- as.ab(x, ...)
       x <- AB_lookup[match(x, AB_lookup$ab), property, drop = TRUE]
     }

R/ab_selectors.R

@@ -49,115 +49,147 @@
 #' @examples 
 #' # `example_isolates` is a data set available in the AMR package.
 #' # See ?example_isolates.
-#' df <- example_isolates[ , c("hospital_id", "mo",
+#' example_isolates
-#'                             "AMP", "AMC", "TZP", "CXM", "CRO", "GEN",
-#'                             "TOB", "COL", "IPM", "MEM", "TEC", "VAN")]
 #' 
 #' # base R ------------------------------------------------------------------
 #' 
 #' # select columns 'IPM' (imipenem) and 'MEM' (meropenem)
-#' df[, carbapenems()]
+#' example_isolates[, carbapenems()]
 #' 
 #' # select columns 'mo', 'AMK', 'GEN', 'KAN' and 'TOB'
-#' df[, c("mo", aminoglycosides())]
+#' example_isolates[, c("mo", aminoglycosides())]
 #' 
 #' # select only antibiotic columns with DDDs for oral treatment
-#' df[, administrable_per_os()]
+#' example_isolates[, administrable_per_os()]
 #' 
 #' # filter using any() or all()
-#' df[any(carbapenems() == "R"), ]
+#' example_isolates[any(carbapenems() == "R"), ]
-#' subset(df, any(carbapenems() == "R"))
+#' subset(example_isolates, any(carbapenems() == "R"))
 #' 
 #' # filter on any or all results in the carbapenem columns (i.e., IPM, MEM):
-#' df[any(carbapenems()), ]
+#' example_isolates[any(carbapenems()), ]
-#' df[all(carbapenems()), ]
+#' example_isolates[all(carbapenems()), ]
 #' 
 #' # filter with multiple antibiotic selectors using c()
-#' df[all(c(carbapenems(), aminoglycosides()) == "R"), ]
+#' example_isolates[all(c(carbapenems(), aminoglycosides()) == "R"), ]
 #' 
 #' # filter + select in one go: get penicillins in carbapenems-resistant strains
-#' df[any(carbapenems() == "R"), penicillins()]
+#' example_isolates[any(carbapenems() == "R"), penicillins()]
 #' 
 #' # You can combine selectors with '&' to be more specific. For example,
 #' # penicillins() would select benzylpenicillin ('peni G') and
 #' # administrable_per_os() would select erythromycin. Yet, when combined these
 #' # drugs are both omitted since benzylpenicillin is not administrable per os
 #' # and erythromycin is not a penicillin:
-#' df[, penicillins() & administrable_per_os()]
+#' example_isolates[, penicillins() & administrable_per_os()]
 #' 
 #' # ab_selector() applies a filter in the `antibiotics` data set and is thus very
 #' # flexible. For instance, to select antibiotic columns with an oral DDD of at
 #' # least 1 gram:
-#' df[, ab_selector(oral_ddd > 1 & oral_units == "g")]
+#' example_isolates[, ab_selector(oral_ddd > 1 & oral_units == "g")]
 #' 
 #' # dplyr -------------------------------------------------------------------
 #' \donttest{
 #' if (require("dplyr")) {
 #' 
-#'   # get AMR for all aminoglycosides e.g., per hospital:
+#'   # get AMR for all aminoglycosides e.g., per ward:
-#'   df %>%
+#'   example_isolates %>%
-#'     group_by(hospital_id) %>% 
+#'     group_by(ward) %>% 
 #'     summarise(across(aminoglycosides(), resistance))
 #'     
+#' }
+#' if (require("dplyr")) {
+#'     
 #'   # You can combine selectors with '&' to be more specific:
-#'   df %>%
+#'   example_isolates %>%
 #'     select(penicillins() & administrable_per_os())
+#'     
+#' }
+#' if (require("dplyr")) {
 #'   
 #'   # get AMR for only drugs that matter - no intrinsic resistance:
-#'   df %>%
+#'   example_isolates %>%
 #'     filter(mo_genus() %in% c("Escherichia", "Klebsiella")) %>% 
-#'     group_by(hospital_id) %>% 
+#'     group_by(ward) %>% 
 #'     summarise(across(not_intrinsic_resistant(), resistance))
 #'     
+#' }
+#' if (require("dplyr")) {
+#'     
 #'   # get susceptibility for antibiotics whose name contains "trim":
-#'   df %>%
+#'   example_isolates %>%
 #'     filter(first_isolate()) %>% 
-#'     group_by(hospital_id) %>% 
+#'     group_by(ward) %>% 
 #'     summarise(across(ab_selector(name %like% "trim"), susceptibility))
+#'     
+#' }
+#' if (require("dplyr")) {
 #' 
 #'   # this will select columns 'IPM' (imipenem) and 'MEM' (meropenem):
-#'   df %>% 
+#'   example_isolates %>% 
 #'     select(carbapenems())
 #'     
+#' }
+#' if (require("dplyr")) {
+#'     
 #'   # this will select columns 'mo', 'AMK', 'GEN', 'KAN' and 'TOB':
-#'   df %>% 
+#'   example_isolates %>% 
 #'     select(mo, aminoglycosides())
 #'     
+#' }
+#' if (require("dplyr")) {
+#'     
 #'  # any() and all() work in dplyr's filter() too:
-#'  df %>% 
+#'  example_isolates %>% 
 #'     filter(any(aminoglycosides() == "R"),
 #'            all(cephalosporins_2nd() == "R"))
 #'     
+#' }
+#' if (require("dplyr")) {
+#'     
 #'  # also works with c():
-#'  df %>% 
+#'  example_isolates %>% 
 #'     filter(any(c(carbapenems(), aminoglycosides()) == "R"))
 #'     
+#' }
+#' if (require("dplyr")) {
+#'     
 #'  # not setting any/all will automatically apply all():
-#'  df %>% 
+#'  example_isolates %>% 
 #'     filter(aminoglycosides() == "R")
 #'     
+#' }
+#' if (require("dplyr")) {
+#'     
 #'   # this will select columns 'mo' and all antimycobacterial drugs ('RIF'):
-#'   df %>% 
+#'   example_isolates %>% 
 #'     select(mo, ab_class("mycobact"))
 #'     
+#' }
+#' if (require("dplyr")) {
+#'     
 #'   # get bug/drug combinations for only glycopeptides in Gram-positives:
-#'   df %>% 
+#'   example_isolates %>% 
 #'     filter(mo_is_gram_positive()) %>% 
 #'     select(mo, glycopeptides()) %>% 
 #'     bug_drug_combinations() %>%
 #'     format()
 #'     
+#' }
+#' if (require("dplyr")) {
+#' 
 #'   data.frame(some_column = "some_value",
 #'              J01CA01 = "S") %>%   # ATC code of ampicillin
 #'     select(penicillins())         # only the 'J01CA01' column will be selected
 #'     
-#'     
+#' }
+#' if (require("dplyr")) {
+#' 
 #'   # with recent versions of dplyr this is all equal:
-#'   x <- df[carbapenems() == "R", ]
+#'   x <- example_isolates[carbapenems() == "R", ]
-#'   y <- df %>% filter(carbapenems() == "R")
+#'   y <- example_isolates %>% filter(carbapenems() == "R")
-#'   z <- df %>% filter(if_all(carbapenems(), ~.x == "R"))
+#'   z <- example_isolates %>% filter(if_all(carbapenems(), ~.x == "R"))
-#'   identical(x, y)
+#'   identical(x, y) && identical(y, z)
-#'   identical(y, z)
 #' }
 #' }
 ab_class <- function(ab_class, 

R/age.R

@@ -160,7 +160,7 @@ age <- function(x, reference = Sys.Date(), exact = FALSE, na.rm = FALSE, ...) {
 #' if (require("dplyr")) {
 #'   example_isolates %>%
 #'     filter_first_isolate() %>%
-#'     filter(mo == as.mo("E. coli")) %>%
+#'     filter(mo == as.mo("Escherichia coli")) %>%
 #'     group_by(age_group = age_groups(age)) %>%
 #'     select(age_group, CIP) %>%
 #'     ggplot_rsi(x = "age_group",

R/amr.R

@@ -52,13 +52,11 @@
 #' - Principal component analysis for AMR
 #' 
 #' @section Reference Data Publicly Available:
-#' All reference data sets (about microorganisms, antibiotics, R/SI interpretation, EUCAST rules, etc.) in this `AMR` package are publicly and freely available. We continually export our data sets to formats for use in R, SPSS, SAS, Stata and Excel. We also supply flat files that are machine-readable and suitable for input in any software program, such as laboratory information systems. Please find [all download links on our website](https://msberends.github.io/AMR/articles/datasets.html), which is automatically updated with every code change.
+#' All data sets in this `AMR` package (about microorganisms, antibiotics, R/SI interpretation, EUCAST rules, etc.) are publicly and freely available for download in the following formats: R, MS Excel, Apache Feather, Apache Parquet, SPSS, SAS, and Stata. We also provide tab-separated plain text files that are machine-readable and suitable for input in any software program, such as laboratory information systems. Please visit [our website for the download links](https://msberends.github.io/AMR/articles/datasets.html). The actual files are of course available on [our GitHub repository](https://github.com/msberends/AMR/tree/main/data-raw).
-#' @section Read more on Our Website!:
-#' On our website <https://msberends.github.io/AMR/> you can find [a comprehensive tutorial](https://msberends.github.io/AMR/articles/AMR.html) about how to conduct AMR data analysis, the [complete documentation of all functions](https://msberends.github.io/AMR/reference/) and [an example analysis using WHONET data](https://msberends.github.io/AMR/articles/WHONET.html).
 #' @section Contact Us:
-#' For suggestions, comments or questions, please contact us at:
+#' For suggestions, comments or questions, please contact us via:
 #'
-#' Matthijs S. Berends \cr
+#' Dr. Matthijs S. Berends \cr
 #' m.s.berends \[at\] umcg \[dot\] nl \cr
 #' University of Groningen
 #' Department of Medical Microbiology and Infection Prevention \cr

R/atc_online.R

@@ -180,15 +180,15 @@ atc_online_property <- function(atc_code,
       
       if (property %in% c("atc", "name")) {
         # ATC and name are only in first row
-        returnvalue[i] <- out[1, property]
+        returnvalue[i] <- out[1, property, drop = TRUE]
       } else {
-        if (!"adm.r" %in% colnames(out) | is.na(out[1, "adm.r"])) {
+        if (!"adm.r" %in% colnames(out) | is.na(out[1, "adm.r", drop = TRUE])) {
           returnvalue[i] <- NA
           next
         } else {
           for (j in seq_len(nrow(out))) {
             if (out[j, "adm.r"] == administration) {
-              returnvalue[i] <- out[j, property]
+              returnvalue[i] <- out[j, property, drop = TRUE]
             }
           }
         }

R/availability.R

@@ -36,7 +36,7 @@
 #' \donttest{
 #' if (require("dplyr")) {
 #'   example_isolates %>%
-#'     filter(mo == as.mo("E. coli")) %>%
+#'     filter(mo == as.mo("Escherichia coli")) %>%
 #'     select_if(is.rsi) %>%
 #'     availability()
 #' }
@@ -45,6 +45,8 @@ availability <- function(tbl, width = NULL) {
   meet_criteria(tbl, allow_class = "data.frame")
   meet_criteria(width, allow_class = c("numeric", "integer"), has_length = 1, allow_NULL = TRUE, is_positive = TRUE, is_finite = TRUE)
   
+  tbl <- as.data.frame(tbl, stringsAsFactors = FALSE)
+  
   x <- vapply(FUN.VALUE = double(1), tbl, function(x) {
     1 - sum(is.na(x)) / length(x) 
   })
@@ -87,7 +89,7 @@ availability <- function(tbl, width = NULL) {
                    visual_resistance = vis_resistance,
                    stringsAsFactors = FALSE)
   if (length(R[is.na(R)]) == ncol(tbl)) {
-    df[, 1:3]
+    df[, 1:3, drop = FALSE]
   } else {
     df
   }

R/bug_drug_combinations.R

@@ -51,7 +51,7 @@
 #'                       FUN = mo_gramstain)
 #'                            
 #' bug_drug_combinations(example_isolates,
-#'                       FUN = function(x) ifelse(x == as.mo("E. coli"),
+#'                       FUN = function(x) ifelse(x == as.mo("Escherichia coli"),
 #'                                                "E. coli",
 #'                                                "Others"))
 #' }
@@ -144,15 +144,12 @@ bug_drug_combinations <- function(x,
   
   if (data_has_groups) {
     out <- apply_group(x, "run_it", groups)
-    rownames(out) <- NULL
-    set_clean_class(out,
-                    new_class = c("grouped", "bug_drug_combinations", "data.frame"))
   } else {
     out <- run_it(x)
-    rownames(out) <- NULL
-    set_clean_class(out,
-                    new_class = c("bug_drug_combinations", "data.frame"))
   }
+  rownames(out) <- NULL
+  out <- as_original_data_class(out, class(x.bak))
+  structure(out, class = c("bug_drug_combinations", ifelse(data_has_groups, "grouped", character(0)), class(out)))
 }
 
 #' @method format bug_drug_combinations
@@ -180,18 +177,20 @@ format.bug_drug_combinations <- function(x,
   meet_criteria(decimal.mark, allow_class = "character", has_length = 1)
   meet_criteria(big.mark, allow_class = "character", has_length = 1)
   
+  x.bak <- x
   if (inherits(x, "grouped")) {
     # bug_drug_combinations() has been run on groups, so de-group here
     warning_("in `format()`: formatting the output of `bug_drug_combinations()` does not support grouped variables, they were ignored")
+    x <- as.data.frame(x, stringsAsFactors = FALSE)
     idx <- split(seq_len(nrow(x)), paste0(x$mo, "%%", x$ab))
     x <- data.frame(mo = gsub("(.*)%%(.*)", "\\1", names(idx)),
                     ab = gsub("(.*)%%(.*)", "\\2", names(idx)),
-                    S = sapply(idx, function(i) sum(y$S[i], na.rm = TRUE)), 
+                    S = sapply(idx, function(i) sum(x$S[i], na.rm = TRUE)), 
-                    I = sapply(idx, function(i) sum(y$I[i], na.rm = TRUE)), 
+                    I = sapply(idx, function(i) sum(x$I[i], na.rm = TRUE)), 
-                    R = sapply(idx, function(i) sum(y$R[i], na.rm = TRUE)),
+                    R = sapply(idx, function(i) sum(x$R[i], na.rm = TRUE)),
-                    total = sapply(idx, function(i) sum(y$S[i], na.rm = TRUE) + 
+                    total = sapply(idx, function(i) sum(x$S[i], na.rm = TRUE) + 
-                                     sum(y$I[i], na.rm = TRUE) +
+                                     sum(x$I[i], na.rm = TRUE) +
-                                     sum(y$R[i], na.rm = TRUE)),
+                                     sum(x$R[i], na.rm = TRUE)),
                     stringsAsFactors = FALSE)
   }
   
@@ -256,7 +255,7 @@ format.bug_drug_combinations <- function(x,
   
   # replace tidyr::pivot_wider() from here
   for (i in unique(y$mo)) {
-    mo_group <- y[which(y$mo == i), c("ab", "txt")]
+    mo_group <- y[which(y$mo == i), c("ab", "txt"), drop = FALSE]
     colnames(mo_group) <- c("ab", i)
     rownames(mo_group) <- NULL
     y <- y %pm>% 
@@ -269,7 +268,7 @@ format.bug_drug_combinations <- function(x,
     remove_NAs()
 
   select_ab_vars <- function(.data) {
-    .data[, c("ab_group", "ab_txt", colnames(.data)[!colnames(.data) %in% c("ab_group", "ab_txt", "ab")])]
+    .data[, c("ab_group", "ab_txt", colnames(.data)[!colnames(.data) %in% c("ab_group", "ab_txt", "ab")]), drop = FALSE]
   }
   
   y <- y %pm>% 
@@ -299,7 +298,7 @@ format.bug_drug_combinations <- function(x,
   }
   
   rownames(y) <- NULL
-  y
+  as_original_data_class(y, class(x.bak))
 }
 
 #' @method print bug_drug_combinations

R/catalogue_of_life.R

@@ -49,9 +49,9 @@ format_included_data_number <- function(data) {
 #' [Click here][catalogue_of_life] for more information about the included taxa. Check which versions of the CoL and LPSN were included in this package with [catalogue_of_life_version()].
 #' @section Included Taxa:
 #' Included are:
-#' - All `r format_included_data_number(microorganisms[which(microorganisms$kingdom %in% c("Archeae", "Bacteria", "Chromista", "Protozoa")), ])` (sub)species from the kingdoms of Archaea, Bacteria, Chromista and Protozoa
+#' - All `r format_included_data_number(microorganisms[which(microorganisms$kingdom %in% c("Archeae", "Bacteria", "Chromista", "Protozoa")), , drop = FALSE])` (sub)species from the kingdoms of Archaea, Bacteria, Chromista and Protozoa
-#' - All `r format_included_data_number(microorganisms[which(microorganisms$kingdom == "Fungi" & microorganisms$order %in% c("Eurotiales", "Microascales", "Mucorales", "Onygenales", "Pneumocystales", "Saccharomycetales", "Schizosaccharomycetales", "Tremellales")), ])` (sub)species from these orders of the kingdom of Fungi: Eurotiales, Microascales, Mucorales, Onygenales, Pneumocystales, Saccharomycetales, Schizosaccharomycetales and Tremellales, as well as `r format_included_data_number(microorganisms[which(microorganisms$kingdom == "Fungi" & !microorganisms$order %in% c("Eurotiales", "Microascales", "Mucorales", "Onygenales", "Pneumocystales", "Saccharomycetales", "Schizosaccharomycetales", "Tremellales")), ])` other fungal (sub)species. The kingdom of Fungi is a very large taxon with almost 300,000 different (sub)species, of which most are not microbial (but rather macroscopic, like mushrooms). Because of this, not all fungi fit the scope of this package and including everything would tremendously slow down our algorithms too. By only including the aforementioned taxonomic orders, the most relevant fungi are covered (such as all species of *Aspergillus*, *Candida*, *Cryptococcus*, *Histplasma*, *Pneumocystis*, *Saccharomyces* and *Trichophyton*).
+#' - All `r format_included_data_number(microorganisms[which(microorganisms$kingdom == "Fungi" & microorganisms$order %in% c("Eurotiales", "Microascales", "Mucorales", "Onygenales", "Pneumocystales", "Saccharomycetales", "Schizosaccharomycetales", "Tremellales")), , drop = FALSE])` (sub)species from these orders of the kingdom of Fungi: Eurotiales, Microascales, Mucorales, Onygenales, Pneumocystales, Saccharomycetales, Schizosaccharomycetales and Tremellales, as well as `r format_included_data_number(microorganisms[which(microorganisms$kingdom == "Fungi" & !microorganisms$order %in% c("Eurotiales", "Microascales", "Mucorales", "Onygenales", "Pneumocystales", "Saccharomycetales", "Schizosaccharomycetales", "Tremellales")), ])` other fungal (sub)species. The kingdom of Fungi is a very large taxon with almost 300,000 different (sub)species, of which most are not microbial (but rather macroscopic, like mushrooms). Because of this, not all fungi fit the scope of this package and including everything would tremendously slow down our algorithms too. By only including the aforementioned taxonomic orders, the most relevant fungi are covered (such as all species of *Aspergillus*, *Candida*, *Cryptococcus*, *Histplasma*, *Pneumocystis*, *Saccharomyces* and *Trichophyton*).
-#' - All `r format_included_data_number(microorganisms[which(microorganisms$kingdom == "Animalia"), ])` (sub)species from `r format_included_data_number(microorganisms[which(microorganisms$kingdom == "Animalia"), "genus"])` other relevant genera from the kingdom of Animalia (such as *Strongyloides* and *Taenia*)
+#' - All `r format_included_data_number(microorganisms[which(microorganisms$kingdom == "Animalia"), , drop = FALSE])` (sub)species from `r format_included_data_number(microorganisms[which(microorganisms$kingdom == "Animalia"), "genus", drop = TRUE])` other relevant genera from the kingdom of Animalia (such as *Strongyloides* and *Taenia*)
 #' - All `r format_included_data_number(microorganisms.old)` previously accepted names of all included (sub)species (these were taxonomically renamed)
 #' - The complete taxonomic tree of all included (sub)species: from kingdom to subspecies
 #' - The responsible author(s) and year of scientific publication
@@ -72,13 +72,13 @@ format_included_data_number <- function(data) {
 #' mo_shortname("Chlamydophila psittaci")
 #'
 #' # Get any property from the entire taxonomic tree for all included species
-#' mo_class("E. coli")
+#' mo_class("Escherichia coli")
 #'
-#' mo_family("E. coli")
+#' mo_family("Escherichia coli")
 #'
-#' mo_gramstain("E. coli") # based on kingdom and phylum, see ?mo_gramstain
+#' mo_gramstain("Escherichia coli") # based on kingdom and phylum, see ?mo_gramstain
 #'
-#' mo_ref("E. coli")
+#' mo_ref("Escherichia coli")
 #'
 #' # Do not get mistaken - this package is about microorganisms
 #' mo_kingdom("C. elegans")

R/count.R

@@ -75,7 +75,7 @@
 #' \donttest{
 #' if (require("dplyr")) {
 #'   example_isolates %>%
-#'     group_by(hospital_id) %>%
+#'     group_by(ward) %>%
 #'     summarise(R  = count_R(CIP),
 #'               I  = count_I(CIP),
 #'               S  = count_S(CIP),
@@ -86,7 +86,7 @@
 #'   # Number of available isolates for a whole antibiotic class
 #'   # (i.e., in this data set columns GEN, TOB, AMK, KAN)
 #'   example_isolates %>%
-#'     group_by(hospital_id) %>%
+#'     group_by(ward) %>%
 #'     summarise(across(aminoglycosides(), n_rsi))
 #'  
 #'   # Count co-resistance between amoxicillin/clav acid and gentamicin,
@@ -108,8 +108,8 @@
 #'  
 #'   # It also supports grouping variables
 #'   example_isolates %>%
-#'     select(hospital_id, AMX, CIP) %>%
+#'     select(ward, AMX, CIP) %>%
-#'     group_by(hospital_id) %>%
+#'     group_by(ward) %>%
 #'     count_df(translate = FALSE)
 #' }
 #' }

R/custom_eucast_rules.R

@@ -26,7 +26,7 @@
 #' Define Custom EUCAST Rules
 #' 
 #' Define custom EUCAST rules for your organisation or specific analysis and use the output of this function in [eucast_rules()].
-#' @param ... rules in [formula][`~`()] notation, see *Examples*
+#' @param ... rules in [formula][base::tilde] notation, see *Examples*
 #' @details
 #' Some organisations have their own adoption of EUCAST rules. This function can be used to define custom EUCAST rules to be used in the [eucast_rules()] function.
 #' @section How it works:

R/data.R

@@ -27,7 +27,7 @@
 #'
 #' Two data sets containing all antibiotics/antimycotics and antivirals. Use [as.ab()] or one of the [`ab_*`][ab_property()] functions to retrieve values from the [antibiotics] data set. Three identifiers are included in this data set: an antibiotic ID (`ab`, primarily used in this package) as defined by WHONET/EARS-Net, an ATC code (`atc`) as defined by the WHO, and a Compound ID (`cid`) as found in PubChem. Other properties in this data set are derived from one or more of these codes. Note that some drugs have multiple ATC codes.
 #' @format
-#' ## For the [antibiotics] data set: a [data.frame] with `r nrow(antibiotics)` observations and `r ncol(antibiotics)` variables:
+#' ## For the [antibiotics] data set: a [tibble[tibble::tibble] with `r nrow(antibiotics)` observations and `r ncol(antibiotics)` variables:
 #' - `ab`\cr Antibiotic ID as used in this package (such as `AMC`), using the official EARS-Net (European Antimicrobial Resistance Surveillance Network) codes where available
 #' - `cid`\cr Compound ID as found in PubChem
 #' - `name`\cr Official name as used by WHONET/EARS-Net or the WHO
@@ -43,7 +43,7 @@
 #' - `iv_units`\cr Units of `iv_ddd`
 #' - `loinc`\cr All LOINC codes (Logical Observation Identifiers Names and Codes) associated with the name of the antimicrobial agent. Use [ab_loinc()] to retrieve them quickly, see [ab_property()].
 #' 
-#' ## For the [antivirals] data set: a [data.frame] with `r nrow(antivirals)` observations and `r ncol(antivirals)` variables:
+#' ## For the [antivirals] data set: a [tibble[tibble::tibble] with `r nrow(antivirals)` observations and `r ncol(antivirals)` variables:
 #' - `atc`\cr ATC codes (Anatomical Therapeutic Chemical) as defined by the WHOCC
 #' - `cid`\cr Compound ID as found in PubChem
 #' - `name`\cr Official name as used by WHONET/EARS-Net or the WHO
@@ -58,24 +58,15 @@
 #' Synonyms (i.e. trade names) were derived from the Compound ID (`cid`) and consequently only available where a CID is available.
 #' 
 #' ## Direct download
-#' These data sets are available as 'flat files' for use even without \R - you can find the files here:
+#' Like all data sets in this package, these data sets are publicly available for download in the following formats: R, MS Excel, Apache Feather, Apache Parquet, SPSS, SAS, and Stata. Please visit [our website for the download links](https://msberends.github.io/AMR/articles/datasets.html). The actual files are of course available on [our GitHub repository](https://github.com/msberends/AMR/tree/main/data-raw).
-#' 
-#' * <https://github.com/msberends/AMR/raw/main/data-raw/antibiotics.txt>
-#' * <https://github.com/msberends/AMR/raw/main/data-raw/antivirals.txt>
-#' 
-#' Files in \R format (with preserved data structure) can be found here:
-#' 
-#' * <https://github.com/msberends/AMR/raw/main/data/antibiotics.rda>
-#' * <https://github.com/msberends/AMR/raw/main/data/antivirals.rda>
 #' @source World Health Organization (WHO) Collaborating Centre for Drug Statistics Methodology (WHOCC): <https://www.whocc.no/atc_ddd_index/>
 #'
 #' European Commission Public Health PHARMACEUTICALS - COMMUNITY REGISTER: <https://ec.europa.eu/health/documents/community-register/html/reg_hum_atc.htm>
-#' @inheritSection AMR Reference Data Publicly Available
 #' @inheritSection WHOCC WHOCC
 #' @seealso [microorganisms], [intrinsic_resistant]
 #' @examples
-#' head(antibiotics)
+#' antibiotics
-#' head(antivirals)
+#' antivirals
 "antibiotics"
 
 #' @rdname antibiotics
@@ -85,7 +76,7 @@
 #'
 #' A data set containing the full microbial taxonomy (**last updated: `r CATALOGUE_OF_LIFE$yearmonth_LPSN`**) of `r nr2char(length(unique(microorganisms$kingdom[!microorganisms$kingdom %like% "unknown"])))` kingdoms from the Catalogue of Life (CoL) and the List of Prokaryotic names with Standing in Nomenclature (LPSN). MO codes can be looked up using [as.mo()].
 #' @inheritSection catalogue_of_life Catalogue of Life
-#' @format A [data.frame] with `r format(nrow(microorganisms), big.mark = ",")` observations and `r ncol(microorganisms)` variables:
+#' @format A [tibble[tibble::tibble] with `r format(nrow(microorganisms), big.mark = ",")` observations and `r ncol(microorganisms)` variables:
 #' - `mo`\cr ID of microorganism as used by this package
 #' - `fullname`\cr Full name, like `"Escherichia coli"`
 #' - `kingdom`, `phylum`, `class`, `order`, `family`, `genus`, `species`, `subspecies`\cr Taxonomic rank of the microorganism
@@ -114,10 +105,7 @@
 #' - 6 families under the Enterobacterales order, according to Adeolu *et al.* (2016, PMID 27620848), that are not (yet) in the Catalogue of Life
 #' 
 #' ## Direct download
-#' This data set is available as 'flat file' for use even without \R - you can find the file here: <https://github.com/msberends/AMR/raw/main/data-raw/microorganisms.txt>. 
+#' Like all data sets in this package, this data set is publicly available for download in the following formats: R, MS Excel, Apache Feather, Apache Parquet, SPSS, SAS, and Stata. Please visit [our website for the download links](https://msberends.github.io/AMR/articles/datasets.html). The actual files are of course available on [our GitHub repository](https://github.com/msberends/AMR/tree/main/data-raw).
-#' 
-#' The file in \R format (with preserved data structure) can be found here: <https://github.com/msberends/AMR/raw/main/data/microorganisms.rda>.
-#' 
 #' @section About the Records from LPSN (see *Source*):
 #' The List of Prokaryotic names with Standing in Nomenclature (LPSN) provides comprehensive information on the nomenclature of prokaryotes. LPSN is a free to use service founded by Jean P. Euzeby in 1997 and later on maintained by Aidan C. Parte.
 #' 
@@ -137,80 +125,80 @@
 #' `r SNOMED_VERSION$current_source` as currently implemented in this `AMR` package:
 #' 
 #' * Retrieved from the `r SNOMED_VERSION$title`, OID `r SNOMED_VERSION$current_oid`, version `r SNOMED_VERSION$current_version`; url: <`r SNOMED_VERSION$url`>
-#' @inheritSection AMR Reference Data Publicly Available
 #' @seealso [as.mo()], [mo_property()], [microorganisms.codes], [intrinsic_resistant]
 #' @examples
-#' head(microorganisms)
+#' microorganisms
 "microorganisms"
 
 #' Data Set with Previously Accepted Taxonomic Names
 #'
 #' A data set containing old (previously valid or accepted) taxonomic names according to the Catalogue of Life. This data set is used internally by [as.mo()].
 #' @inheritSection catalogue_of_life Catalogue of Life
-#' @format A [data.frame] with `r format(nrow(microorganisms.old), big.mark = ",")` observations and `r ncol(microorganisms.old)` variables:
+#' @format A [tibble[tibble::tibble] with `r format(nrow(microorganisms.old), big.mark = ",")` observations and `r ncol(microorganisms.old)` variables:
 #' - `fullname`\cr Old full taxonomic name of the microorganism
 #' - `fullname_new`\cr New full taxonomic name of the microorganism
 #' - `ref`\cr Author(s) and year of concerning scientific publication
 #' - `prevalence`\cr Prevalence of the microorganism, see [as.mo()]
+#' @details 
+#' Like all data sets in this package, this data set is publicly available for download in the following formats: R, MS Excel, Apache Feather, Apache Parquet, SPSS, SAS, and Stata. Please visit [our website for the download links](https://msberends.github.io/AMR/articles/datasets.html). The actual files are of course available on [our GitHub repository](https://github.com/msberends/AMR/tree/main/data-raw).
 #' @source Catalogue of Life: Annual Checklist (public online taxonomic database), <http://www.catalogueoflife.org> (check included annual version with [catalogue_of_life_version()]).
 #' 
 #' Parte, A.C. (2018). LPSN - List of Prokaryotic names with Standing in Nomenclature (bacterio.net), 20 years on. International Journal of Systematic and Evolutionary Microbiology, 68, 1825-1829; \doi{10.1099/ijsem.0.002786}
-#' @inheritSection AMR Reference Data Publicly Available
 #' @seealso [as.mo()] [mo_property()] [microorganisms]
 #' @examples
-#' head(microorganisms.old)
+#' microorganisms.old
 "microorganisms.old"
 
 #' Data Set with `r format(nrow(microorganisms.codes), big.mark = ",")` Common Microorganism Codes
 #'
 #' A data set containing commonly used codes for microorganisms, from laboratory systems and WHONET. Define your own with [set_mo_source()]. They will all be searched when using [as.mo()] and consequently all the [`mo_*`][mo_property()] functions.
-#' @format A [data.frame] with `r format(nrow(microorganisms.codes), big.mark = ",")` observations and `r ncol(microorganisms.codes)` variables:
+#' @format A [tibble[tibble::tibble] with `r format(nrow(microorganisms.codes), big.mark = ",")` observations and `r ncol(microorganisms.codes)` variables:
 #' - `code`\cr Commonly used code of a microorganism
 #' - `mo`\cr ID of the microorganism in the [microorganisms] data set
-#' @inheritSection AMR Reference Data Publicly Available
+#' @details 
+#' Like all data sets in this package, this data set is publicly available for download in the following formats: R, MS Excel, Apache Feather, Apache Parquet, SPSS, SAS, and Stata. Please visit [our website for the download links](https://msberends.github.io/AMR/articles/datasets.html). The actual files are of course available on [our GitHub repository](https://github.com/msberends/AMR/tree/main/data-raw).
 #' @inheritSection catalogue_of_life Catalogue of Life
 #' @seealso [as.mo()] [microorganisms]
 #' @examples
-#' head(microorganisms.codes)
+#' microorganisms.codes
 "microorganisms.codes"
 
 #' Data Set with `r format(nrow(example_isolates), big.mark = ",")` Example Isolates
 #'
-#' A data set containing `r format(nrow(example_isolates), big.mark = ",")` microbial isolates with their full antibiograms. The data set reflects reality and can be used to practice AMR data analysis. For examples, please read [the tutorial on our website](https://msberends.github.io/AMR/articles/AMR.html).
+#' A data set containing `r format(nrow(example_isolates), big.mark = ",")` microbial isolates with their full antibiograms. This data set contains randomised fictitious data, but reflects reality and can be used to practise AMR data analysis. For examples, please read [the tutorial on our website](https://msberends.github.io/AMR/articles/AMR.html).
-#' @format A [data.frame] with `r format(nrow(example_isolates), big.mark = ",")` observations and `r ncol(example_isolates)` variables:
+#' @format A [tibble[tibble::tibble] with `r format(nrow(example_isolates), big.mark = ",")` observations and `r ncol(example_isolates)` variables:
-#' - `date`\cr date of receipt at the laboratory
+#' - `date`\cr Date of receipt at the laboratory
-#' - `hospital_id`\cr ID of the hospital, from A to D
+#' - `patient`\cr ID of the patient
-#' - `ward_icu`\cr [logical] to determine if ward is an intensive care unit
+#' - `age`\cr Age of the patient
-#' - `ward_clinical`\cr [logical] to determine if ward is a regular clinical ward
+#' - `gender`\cr Gender of the patient, either `r vector_or(example_isolates$gender)`
-#' - `ward_outpatient`\cr [logical] to determine if ward is an outpatient clinic
+#' - `ward`\cr Ward type where the patient was admitted, either `r vector_or(example_isolates$ward)`
-#' - `age`\cr age of the patient
+#' - `mo`\cr ID of microorganism created with [as.mo()], see also the [microorganisms] data set
-#' - `gender`\cr gender of the patient
+#' - `PEN:RIF`\cr `r sum(vapply(FUN.VALUE = logical(1), example_isolates, is.rsi))` different antibiotics with class [`rsi`] (see [as.rsi()]); these column names occur in the [antibiotics] data set and can be translated with [set_ab_names()] or [ab_name()]
-#' - `patient_id`\cr ID of the patient
+#' @details 
-#' - `mo`\cr ID of microorganism created with [as.mo()], see also [microorganisms]
+#' Like all data sets in this package, this data set is publicly available for download in the following formats: R, MS Excel, Apache Feather, Apache Parquet, SPSS, SAS, and Stata. Please visit [our website for the download links](https://msberends.github.io/AMR/articles/datasets.html). The actual files are of course available on [our GitHub repository](https://github.com/msberends/AMR/tree/main/data-raw).
-#' - `PEN:RIF`\cr `r sum(vapply(FUN.VALUE = logical(1), example_isolates, is.rsi))` different antibiotics with class [`rsi`] (see [as.rsi()]); these column names occur in the [antibiotics] data set and can be translated with [ab_name()]
-#' @inheritSection AMR Reference Data Publicly Available
 #' @examples
-#' head(example_isolates)
+#' example_isolates
 "example_isolates"
 
 #' Data Set with Unclean Data
 #'
 #' A data set containing `r format(nrow(example_isolates_unclean), big.mark = ",")` microbial isolates that are not cleaned up and consequently not ready for AMR data analysis. This data set can be used for practice.
-#' @format A [data.frame] with `r format(nrow(example_isolates_unclean), big.mark = ",")` observations and `r ncol(example_isolates_unclean)` variables:
+#' @format A [tibble[tibble::tibble] with `r format(nrow(example_isolates_unclean), big.mark = ",")` observations and `r ncol(example_isolates_unclean)` variables:
 #' - `patient_id`\cr ID of the patient
 #' - `date`\cr date of receipt at the laboratory
 #' - `hospital`\cr ID of the hospital, from A to C
 #' - `bacteria`\cr info about microorganism that can be transformed with [as.mo()], see also [microorganisms]
 #' - `AMX:GEN`\cr 4 different antibiotics that have to be transformed with [as.rsi()]
-#' @inheritSection AMR Reference Data Publicly Available
+#' @details 
+#' Like all data sets in this package, this data set is publicly available for download in the following formats: R, MS Excel, Apache Feather, Apache Parquet, SPSS, SAS, and Stata. Please visit [our website for the download links](https://msberends.github.io/AMR/articles/datasets.html). The actual files are of course available on [our GitHub repository](https://github.com/msberends/AMR/tree/main/data-raw).
 #' @examples
-#' head(example_isolates_unclean)
+#' example_isolates_unclean
 "example_isolates_unclean"
 
 #' Data Set with `r format(nrow(WHONET), big.mark = ",")` Isolates - WHONET Example
 #'
 #' This example data set has the exact same structure as an export file from WHONET. Such files can be used with this package, as this example data set shows. The antibiotic results are from our [example_isolates] data set. All patient names are created using online surname generators and are only in place for practice purposes.
-#' @format A [data.frame] with `r format(nrow(WHONET), big.mark = ",")` observations and `r ncol(WHONET)` variables:
+#' @format A [tibble[tibble::tibble] with `r format(nrow(WHONET), big.mark = ",")` observations and `r ncol(WHONET)` variables:
 #' - `Identification number`\cr ID of the sample
 #' - `Specimen number`\cr ID of the specimen
 #' - `Organism`\cr Name of the microorganism. Before analysis, you should transform this to a valid microbial class, using [as.mo()].
@@ -237,15 +225,16 @@
 #' - `Comment`\cr Other comments
 #' - `Date of data entry`\cr [Date] this data was entered in WHONET
 #' - `AMP_ND10:CIP_EE`\cr `r sum(vapply(FUN.VALUE = logical(1), WHONET, is.rsi))` different antibiotics. You can lookup the abbreviations in the [antibiotics] data set, or use e.g. [`ab_name("AMP")`][ab_name()] to get the official name immediately. Before analysis, you should transform this to a valid antibiotic class, using [as.rsi()].
-#' @inheritSection AMR Reference Data Publicly Available
+#' @details 
+#' Like all data sets in this package, this data set is publicly available for download in the following formats: R, MS Excel, Apache Feather, Apache Parquet, SPSS, SAS, and Stata. Please visit [our website for the download links](https://msberends.github.io/AMR/articles/datasets.html). The actual files are of course available on [our GitHub repository](https://github.com/msberends/AMR/tree/main/data-raw).
 #' @examples
-#' head(WHONET)
+#' WHONET
 "WHONET"
 
 #' Data Set for R/SI Interpretation
 #'
 #' Data set containing reference data to interpret MIC and disk diffusion to R/SI values, according to international guidelines. Currently implemented guidelines are EUCAST (`r min(as.integer(gsub("[^0-9]", "", subset(rsi_translation, guideline %like% "EUCAST")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(rsi_translation, guideline %like% "EUCAST")$guideline)))`) and CLSI (`r min(as.integer(gsub("[^0-9]", "", subset(rsi_translation, guideline %like% "CLSI")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(rsi_translation, guideline %like% "CLSI")$guideline)))`). Use [as.rsi()] to transform MICs or disks measurements to R/SI values.
-#' @format A [data.frame] with `r format(nrow(rsi_translation), big.mark = ",")` observations and `r ncol(rsi_translation)` variables:
+#' @format A [tibble[tibble::tibble] with `r format(nrow(rsi_translation), big.mark = ",")` observations and `r ncol(rsi_translation)` variables:
 #' - `guideline`\cr Name of the guideline
 #' - `method`\cr Either `r vector_or(rsi_translation$method)`
 #' - `site`\cr Body site, e.g. "Oral" or "Respiratory"
@@ -258,31 +247,35 @@
 #' - `breakpoint_R`\cr Highest MIC value or lowest number of millimetres that leads to "R"
 #' - `uti`\cr A [logical] value (`TRUE`/`FALSE`) to indicate whether the rule applies to a urinary tract infection (UTI)
 #' @details 
-#' The repository of this `AMR` package contains a file comprising this exact data set: <https://github.com/msberends/AMR/blob/main/data-raw/rsi_translation.txt>. This file **allows for machine reading EUCAST and CLSI guidelines**, which is almost impossible with the Excel and PDF files distributed by EUCAST and CLSI. The file is updated automatically and the `mo` and `ab` columns have been transformed to contain the full official names instead of codes.
+#' Like all data sets in this package, this data set is publicly available for download in the following formats: R, MS Excel, Apache Feather, Apache Parquet, SPSS, SAS, and Stata. Please visit [our website for the download links](https://msberends.github.io/AMR/articles/datasets.html). The actual files are of course available on [our GitHub repository](https://github.com/msberends/AMR/tree/main/data-raw).
-#' @inheritSection AMR Reference Data Publicly Available
+#' 
+#' They **allow for machine reading EUCAST and CLSI guidelines**, which is almost impossible with the MS Excel and PDF files distributed by EUCAST and CLSI.
 #' @seealso [intrinsic_resistant]
 #' @examples
-#' head(rsi_translation)
+#' rsi_translation
 "rsi_translation"
 
 #' Data Set with Bacterial Intrinsic Resistance
 #'
 #' Data set containing defined intrinsic resistance by EUCAST of all bug-drug combinations.
-#' @format A [data.frame] with `r format(nrow(intrinsic_resistant), big.mark = ",")` observations and `r ncol(intrinsic_resistant)` variables:
+#' @format A [tibble[tibble::tibble] with `r format(nrow(intrinsic_resistant), big.mark = ",")` observations and `r ncol(intrinsic_resistant)` variables:
 #' - `mo`\cr Microorganism ID
 #' - `ab`\cr Antibiotic ID
-#' @details The repository of this `AMR` package contains a file comprising this data set with full taxonomic and antibiotic names: <https://github.com/msberends/AMR/blob/main/data-raw/intrinsic_resistant.txt>. This file **allows for machine reading EUCAST guidelines about intrinsic resistance**, which is almost impossible with the Excel and PDF files distributed by EUCAST. The file is updated automatically.
+#' @details 
-#' 
 #' This data set is based on `r format_eucast_version_nr(3.3)`.
-#' @inheritSection AMR Reference Data Publicly Available
+#' 
+#' ## Direct download
+#' Like all data sets in this package, this data set is publicly available for download in the following formats: R, MS Excel, Apache Feather, Apache Parquet, SPSS, SAS, and Stata. Please visit [our website for the download links](https://msberends.github.io/AMR/articles/datasets.html). The actual files are of course available on [our GitHub repository](https://github.com/msberends/AMR/tree/main/data-raw).
+#' 
+#' They **allow for machine reading EUCAST and CLSI guidelines**, which is almost impossible with the MS Excel and PDF files distributed by EUCAST and CLSI.
 #' @examples
-#' head(intrinsic_resistant)
+#' intrinsic_resistant
 "intrinsic_resistant"
 
 #' Data Set with Treatment Dosages as Defined by EUCAST
 #'
 #' EUCAST breakpoints used in this package are based on the dosages in this data set. They can be retrieved with [eucast_dosage()].
-#' @format A [data.frame] with `r format(nrow(dosage), big.mark = ",")` observations and `r ncol(dosage)` variables:
+#' @format A [tibble[tibble::tibble] with `r format(nrow(dosage), big.mark = ",")` observations and `r ncol(dosage)` variables:
 #' - `ab`\cr Antibiotic ID as used in this package (such as `AMC`), using the official EARS-Net (European Antimicrobial Resistance Surveillance Network) codes where available
 #' - `name`\cr Official name of the antimicrobial agent as used by WHONET/EARS-Net or the WHO
 #' - `type`\cr Type of the dosage, either `r vector_or(dosage$type)`
@@ -292,8 +285,11 @@
 #' - `notes`\cr Additional dosage notes
 #' - `original_txt`\cr Original text in the PDF file of EUCAST
 #' - `eucast_version`\cr Version number of the EUCAST Clinical Breakpoints guideline to which these dosages apply
-#' @details `r format_eucast_version_nr(11.0)` are based on the dosages in this data set.
+#' @details 
-#' @inheritSection AMR Reference Data Publicly Available
+#' This data set is based on `r format_eucast_version_nr(11.0)`.
+#' 
+#' ## Direct download
+#' Like all data sets in this package, this data set is publicly available for download in the following formats: R, MS Excel, Apache Feather, Apache Parquet, SPSS, SAS, and Stata. Please visit [our website for the download links](https://msberends.github.io/AMR/articles/datasets.html). The actual files are of course available on [our GitHub repository](https://github.com/msberends/AMR/tree/main/data-raw).
 #' @examples
-#' head(dosage)
+#' dosage
 "dosage"

R/episode.R

@@ -63,26 +63,34 @@
 #'   # episodes based on any (combination of) grouping variables:
 #'   df %>%
 #'     mutate(condition = sample(x = c("A", "B", "C"), 
-#'                               size = 2000,
+#'                               size = 200,
 #'                               replace = TRUE)) %>% 
 #'     group_by(condition) %>%
 #'     mutate(new_episode = is_new_episode(date, 365)) %>%
-#'     select(patient_id, date, condition, new_episode)
+#'     select(patient, date, condition, new_episode)
+#'     
+#' }
+#' if (require("dplyr")) {
 #'     
 #'   df %>%
-#'     group_by(hospital_id, patient_id) %>%
+#'     group_by(ward, patient) %>%
 #'     transmute(date, 
-#'               patient_id,
+#'               patient,
 #'               new_index = get_episode(date, 60),
 #'               new_logical = is_new_episode(date, 60))
+#'     
+#' }
+#' if (require("dplyr")) {
 #'   
 #'   df %>%
-#'     group_by(hospital_id) %>% 
+#'     group_by(ward) %>% 
-#'     summarise(n_patients = n_distinct(patient_id),
+#'     summarise(n_patients = n_distinct(patient),
 #'               n_episodes_365 = sum(is_new_episode(date, episode_days = 365)),
 #'               n_episodes_60  = sum(is_new_episode(date, episode_days = 60)),
 #'               n_episodes_30  = sum(is_new_episode(date, episode_days = 30)))
 #'     
+#' }
+#' if (require("dplyr")) {
 #'     
 #'   # grouping on patients and microorganisms leads to the same
 #'   # results as first_isolate() when using 'episode-based':
@@ -91,16 +99,19 @@
 #'                          method = "episode-based")
 #'     
 #'   y <- df %>%
-#'     group_by(patient_id, mo) %>%
+#'     group_by(patient, mo) %>%
 #'     filter(is_new_episode(date, 365)) %>%
 #'     ungroup()
 #'
 #'   identical(x, y)
+#'     
+#' }
+#' if (require("dplyr")) {
 #'   
 #'   # but is_new_episode() has a lot more flexibility than first_isolate(),
 #'   # since you can now group on anything that seems relevant:
 #'   df %>%
-#'     group_by(patient_id, mo, hospital_id, ward_icu) %>%
+#'     group_by(patient, mo, ward) %>%
 #'     mutate(flag_episode = is_new_episode(date, 365)) %>%
 #'     select(group_vars(.), flag_episode)
 #' }

R/eucast_rules.R

@@ -52,7 +52,7 @@ format_eucast_version_nr <- function(version, markdown = TRUE) {
 #' Apply rules for clinical breakpoints and intrinsic resistance as defined by the European Committee on Antimicrobial Susceptibility Testing (EUCAST, <https://eucast.org>), see *Source*. Use [eucast_dosage()] to get a [data.frame] with advised dosages of a certain bug-drug combination, which is based on the [dosage] data set.
 #' 
 #' To improve the interpretation of the antibiogram before EUCAST rules are applied, some non-EUCAST rules can applied at default, see *Details*.
-#' @param x data with antibiotic columns, such as `amox`, `AMX` and `AMC`
+#' @param x a data set with antibiotic columns, such as `amox`, `AMX` and `AMC`
 #' @param info a [logical] to indicate whether progress should be printed to the console, defaults to only print while in interactive sessions
 #' @param rules a [character] vector that specifies which rules should be applied. Must be one or more of `"breakpoints"`, `"expert"`, `"other"`, `"custom"`, `"all"`, and defaults to `c("breakpoints", "expert")`. The default value can be set to another value, e.g. using `options(AMR_eucastrules = "all")`. If using `"custom"`, be sure to fill in argument `custom_rules` too. Custom rules can be created with [custom_eucast_rules()].
 #' @param verbose a [logical] to turn Verbose mode on and off (default is off). In Verbose mode, the function does not apply rules to the data, but instead returns a data set in logbook form with extensive info about which rows and columns would be effected and in which way. Using Verbose mode takes a lot more time.
@@ -412,11 +412,11 @@ eucast_rules <- function(x,
   }
   
   if (any(x$genus == "Staphylococcus", na.rm = TRUE)) {
-    all_staph <- MO_lookup[which(MO_lookup$genus == "Staphylococcus"), ]
+    all_staph <- MO_lookup[which(MO_lookup$genus == "Staphylococcus"), , drop = FALSE]
     all_staph$CNS_CPS <- suppressWarnings(mo_name(all_staph$mo, Becker = "all", language = NULL))
   }
   if (any(x$genus == "Streptococcus", na.rm = TRUE)) {
-    all_strep <- MO_lookup[which(MO_lookup$genus == "Streptococcus"), ]
+    all_strep <- MO_lookup[which(MO_lookup$genus == "Streptococcus"), , drop = FALSE]
     all_strep$Lancefield <- suppressWarnings(mo_name(all_strep$mo, Lancefield = TRUE, language = NULL))
   }
   
@@ -432,7 +432,7 @@ eucast_rules <- function(x,
                          font_red(paste0("v", utils::packageDescription("AMR")$Version, ", ", 
                                          format(as.Date(utils::packageDescription("AMR")$Date), format = "%Y"))), "), see ?eucast_rules\n"))))
     }
-    ab_enzyme <- subset(antibiotics, name %like% "/")[, c("ab", "name")]
+    ab_enzyme <- subset(antibiotics, name %like% "/")[, c("ab", "name"), drop = FALSE]
     colnames(ab_enzyme) <- c("enzyme_ab", "enzyme_name")
     ab_enzyme$base_name <- gsub("^([a-zA-Z0-9]+).*", "\\1", ab_enzyme$enzyme_name)
     ab_enzyme$base_ab <- antibiotics[match(ab_enzyme$base_name, antibiotics$name), "ab", drop = TRUE]
@@ -446,7 +446,7 @@ eucast_rules <- function(x,
     amox$base_name <- ab_name("AMX", language = NULL)
     # merge and sort
     ab_enzyme <- rbind(ab_enzyme, ampi, amox)
-    ab_enzyme <- ab_enzyme[order(ab_enzyme$enzyme_name), ]
+    ab_enzyme <- ab_enzyme[order(ab_enzyme$enzyme_name), , drop = FALSE]
     
     for (i in seq_len(nrow(ab_enzyme))) {
       # check if both base and base + enzyme inhibitor are part of the data set
@@ -917,7 +917,7 @@ eucast_rules <- function(x,
   
   # Return data set ---------------------------------------------------------
   if (verbose == TRUE) {
-    verbose_info
+    as_original_data_class(verbose_info, old_attributes$class)
   } else {
     # x was analysed with only unique rows, so join everything together again
     x <- x[, c(cols_ab, ".rowid"), drop = FALSE]
@@ -925,7 +925,7 @@ eucast_rules <- function(x,
     x.bak <- x.bak %pm>% 
       pm_left_join(x, by = ".rowid")
     x.bak <- x.bak[, old_cols, drop = FALSE]
-    # reset original attributes
+    # reset original attributes, no need for as_original_data_class() here
     attributes(x.bak) <- old_attributes
     x.bak
   }
@@ -1060,15 +1060,19 @@ eucast_dosage <- function(ab, administration = "iv", version_breakpoints = 11.0)
     lst[[i]] <- list(ab = "",
                      name = "",
                      standard_dosage = ifelse("standard_dosage" %in% df$type,
-                                              df[which(df$type == "standard_dosage"), ]$original_txt, 
+                                              df[which(df$type == "standard_dosage"), "original_txt", drop = TRUE],
                                               NA_character_),
                      high_dosage = ifelse("high_dosage" %in% df$type,
-                                          df[which(df$type == "high_dosage"), ]$original_txt, 
+                                          df[which(df$type == "high_dosage"), "original_txt", drop = TRUE],
                                           NA_character_))
   }
   out <- do.call("rbind", lapply(lst, as.data.frame, stringsAsFactors = FALSE))
   rownames(out) <- NULL
   out$ab <- ab
   out$name <- ab_name(ab, language = NULL)
-  out
+  if (pkg_is_available("tibble", also_load = FALSE)) {
+    import_fn("as_tibble", "tibble")(out)
+  } else {
+    out
+  }
 }

R/first_isolate.R

@@ -32,7 +32,7 @@
 #' @param col_mo column name of the IDs of the microorganisms (see [as.mo()]), defaults to the first column of class [`mo`]. Values will be coerced using [as.mo()].
 #' @param col_testcode column name of the test codes. Use `col_testcode = NULL` to **not** exclude certain test codes (such as test codes for screening). In that case `testcodes_exclude` will be ignored.
 #' @param col_specimen column name of the specimen type or group
-#' @param col_icu column name of the logicals (`TRUE`/`FALSE`) whether a ward or department is an Intensive Care Unit (ICU)
+#' @param col_icu column name of the logicals (`TRUE`/`FALSE`) whether a ward or department is an Intensive Care Unit (ICU). This can also be a [logical] vector with the same length as rows in `x`.
 #' @param col_keyantimicrobials (only useful when `method = "phenotype-based"`) column name of the key antimicrobials to determine first isolates, see [key_antimicrobials()]. Defaults to the first column that starts with 'key' followed by 'ab' or 'antibiotics' or 'antimicrobials' (case insensitive). Use `col_keyantimicrobials = FALSE` to prevent this. Can also be the output of [key_antimicrobials()].
 #' @param episode_days episode in days after which a genus/species combination will be determined as 'first isolate' again. The default of 365 days is based on the guideline by CLSI, see *Source*. 
 #' @param testcodes_exclude a [character] vector with test codes that should be excluded (case-insensitive)
@@ -119,7 +119,7 @@
 #' @rdname first_isolate
 #' @seealso [key_antimicrobials()]
 #' @export
-#' @return A [`logical`] vector
+#' @return A [logical] vector
 #' @source Methodology of this function is strictly based on:
 #' 
 #' - **M39 Analysis and Presentation of Cumulative Antimicrobial Susceptibility Test Data, 4th Edition**, 2014, *Clinical and Laboratory Standards Institute (CLSI)*. <https://clsi.org/standards/products/microbiology/documents/m39/>.
@@ -138,36 +138,22 @@
 #'   # filter on first isolates using dplyr:
 #'   example_isolates %>%
 #'     filter(first_isolate())
+#'     
+#' }
+#' if (require("dplyr")) {
 #'  
 #'   # short-hand version:
 #'   example_isolates %>%
 #'     filter_first_isolate(info = FALSE)
 #'     
+#' }
+#' if (require("dplyr")) {
+#'     
 #'  # flag the first isolates per group:
 #'  example_isolates %>%
-#'    group_by(hospital_id) %>%
+#'    group_by(ward) %>%
 #'    mutate(first = first_isolate()) %>%
-#'    select(hospital_id, date, patient_id, mo, first)
+#'    select(ward, date, patient, mo, first)
-#'   
-#'   # now let's see if first isolates matter:
-#'   A <- example_isolates %>%
-#'     group_by(hospital_id) %>%
-#'     summarise(count = n_rsi(GEN),            # gentamicin availability
-#'               resistance = resistance(GEN))  # gentamicin resistance
-#'  
-#'   B <- example_isolates %>%
-#'     filter_first_isolate() %>%               # the 1st isolate filter
-#'     group_by(hospital_id) %>%
-#'     summarise(count = n_rsi(GEN),            # gentamicin availability
-#'               resistance = resistance(GEN))  # gentamicin resistance
-#'  
-#'   # Have a look at A and B.
-#'   A
-#'   B
-#'   
-#'   # B is more reliable because every isolate is counted only once.
-#'   # Gentamicin resistance in hospital D appears to be 4.2% higher than
-#'   # when you (erroneously) would have used all isolates for analysis.
 #' }
 #' }
 first_isolate <- function(x = NULL,
@@ -217,7 +203,15 @@ first_isolate <- function(x = NULL,
     col_specimen <- NULL
   }
   meet_criteria(col_specimen, allow_class = "character", has_length = 1, allow_NULL = TRUE, is_in = colnames(x))
-  meet_criteria(col_icu, allow_class = "character", has_length = 1, allow_NULL = TRUE, is_in = colnames(x))
+  if (is.logical(col_icu)) {
+    meet_criteria(col_icu, allow_class = "logical", has_length = c(1, nrow(x)), allow_NULL = TRUE)
+    if (length(col_icu) == 1) {
+      col_icu <- rep(col_icu, nrow(x))
+    }
+  } else {
+    meet_criteria(col_icu, allow_class = c("character", "logical"), has_length = 1, allow_NULL = TRUE, is_in = colnames(x))
+    col_icu <- x[, col_icu, drop = TRUE]
+  }
   # method
   method <- coerce_method(method)
   meet_criteria(method, allow_class = "character", has_length = 1, is_in = c("phenotype-based", "episode-based", "patient-based", "isolate-based"))
@@ -343,7 +337,6 @@ first_isolate <- function(x = NULL,
   check_columns_existance(col_patient_id)
   check_columns_existance(col_mo)
   check_columns_existance(col_testcode)
-  check_columns_existance(col_icu)
   check_columns_existance(col_keyantimicrobials)
   
   # convert dates to Date
@@ -508,10 +501,10 @@ first_isolate <- function(x = NULL,
   }
   if (!is.null(col_icu)) {
     if (icu_exclude == TRUE) {
-      message_("Excluding isolates from ICU.",
+      message_("Excluding ", format(sum(!col_icu, na.rm = TRUE), big.mark = ","), " isolates from ICU.",
                add_fn = font_black,
                as_note = FALSE)
-      x[which(as.logical(x[, col_icu, drop = TRUE])), "newvar_first_isolate"] <- FALSE
+      x[which(col_icu), "newvar_first_isolate"] <- FALSE
     } else {
       message_("Including isolates from ICU.",
                add_fn = font_black,

R/ggplot_rsi.R

@@ -66,11 +66,14 @@
 #' @export
 #' @examples
 #' \donttest{
-#' if (require("ggplot2") & require("dplyr")) {
+#' if (require("ggplot2") && require("dplyr")) {
 #'  
 #'   # get antimicrobial results for drugs against a UTI:
 #'   ggplot(example_isolates %>% select(AMX, NIT, FOS, TMP, CIP)) +
 #'     geom_rsi()
+#'     
+#' }
+#' if (require("ggplot2") && require("dplyr")) {
 #'  
 #'   # prettify the plot using some additional functions:
 #'   df <- example_isolates %>% select(AMX, NIT, FOS, TMP, CIP)
@@ -80,16 +83,25 @@
 #'     scale_rsi_colours() +
 #'     labels_rsi_count() +
 #'     theme_rsi()
+#'     
+#' }
+#' if (require("ggplot2") && require("dplyr")) {
 #'  
 #'   # or better yet, simplify this using the wrapper function - a single command:
 #'   example_isolates %>%
 #'     select(AMX, NIT, FOS, TMP, CIP) %>%
 #'     ggplot_rsi()
+#'     
+#' }
+#' if (require("ggplot2") && require("dplyr")) {
 #'  
 #'   # get only proportions and no counts:
 #'   example_isolates %>%
 #'     select(AMX, NIT, FOS, TMP, CIP) %>%
 #'     ggplot_rsi(datalabels = FALSE)
+#'     
+#' }
+#' if (require("ggplot2") && require("dplyr")) {
 #'  
 #'   # add other ggplot2 arguments as you like:
 #'   example_isolates %>%
@@ -99,11 +111,17 @@
 #'                size = 1,
 #'                linetype = 2,
 #'                alpha = 0.25)
+#'     
+#' }
+#' if (require("ggplot2") && require("dplyr")) {
 #'
 #'   # you can alter the colours with colour names:
 #'   example_isolates %>%
 #'     select(AMX) %>%
 #'     ggplot_rsi(colours = c(SI = "yellow"))
+#'     
+#' }
+#' if (require("ggplot2") && require("dplyr")) {
 #'
 #'   # but you can also use the built-in colour-blind friendly colours for
 #'   # your plots, where "S" is green, "I" is yellow and "R" is red:
@@ -113,34 +131,42 @@
 #'     ggplot() +
 #'     geom_col(aes(x = x, y = y, fill = z)) +
 #'     scale_rsi_colours(Value4 = "S", Value5 = "I", Value6 = "R")
+#'     
+#' }
+#' if (require("ggplot2") && require("dplyr")) {
 #'   
 #'   # resistance of ciprofloxacine per age group
 #'   example_isolates %>%
 #'     mutate(first_isolate = first_isolate()) %>%
 #'     filter(first_isolate == TRUE,
-#'            mo == as.mo("E. coli")) %>%
+#'            mo == as.mo("Escherichia coli")) %>%
 #'     # age_groups() is also a function in this AMR package:
 #'     group_by(age_group = age_groups(age)) %>%
 #'     select(age_group, CIP) %>%
 #'     ggplot_rsi(x = "age_group")
+#'     
+#' }
+#' if (require("ggplot2") && require("dplyr")) {
 #'   
 #'   # a shorter version which also adjusts data label colours:
 #'   example_isolates %>%
 #'     select(AMX, NIT, FOS, TMP, CIP) %>%
 #'     ggplot_rsi(colours = FALSE)
-#'
+#'     
+#' }
+#' if (require("ggplot2") && require("dplyr")) {
 #'
 #'   # it also supports groups (don't forget to use the group var on `x` or `facet`):
 #'   example_isolates %>%
-#'     filter(mo_is_gram_negative()) %>% 
+#'     filter(mo_is_gram_negative(), ward != "Outpatient") %>% 
 #'     # select only UTI-specific drugs
-#'     select(hospital_id, AMX, NIT, FOS, TMP, CIP) %>%
+#'     select(ward, AMX, NIT, FOS, TMP, CIP) %>%
-#'     group_by(hospital_id) %>%
+#'     group_by(ward) %>%
-#'     ggplot_rsi(x = "hospital_id",
+#'     ggplot_rsi(x = "ward",
 #'                facet = "antibiotic",
 #'                nrow = 1,
-#'                title = "AMR of Anti-UTI Drugs Per Hospital",
+#'                title = "AMR of Anti-UTI Drugs Per Ward",
-#'                x.title = "Hospital",
+#'                x.title = "Ward",
 #'                datalabels = FALSE)
 #' }
 #' }

R/join_microorganisms.R

@@ -42,21 +42,22 @@
 #' left_join_microorganisms(as.mo("K. pneumoniae"))
 #' left_join_microorganisms("B_KLBSL_PNMN")
 #'
+#' df <- data.frame(date = seq(from = as.Date("2018-01-01"),
+#'                             to = as.Date("2018-01-07"),
+#'                             by = 1),
+#'                  bacteria = as.mo(c("S. aureus", "MRSA", "MSSA", "STAAUR",
+#'                                     "E. coli", "E. coli", "E. coli")),
+#'                  stringsAsFactors = FALSE)
+#' colnames(df)
+#' 
+#' df_joined <- left_join_microorganisms(df, "bacteria")
+#' colnames(df_joined)
+#' 
 #' \donttest{
 #' if (require("dplyr")) {
 #'   example_isolates %>%
 #'     left_join_microorganisms() %>% 
 #'     colnames()
-#'  
-#'   df <- data.frame(date = seq(from = as.Date("2018-01-01"),
-#'                               to = as.Date("2018-01-07"),
-#'                               by = 1),
-#'                    bacteria = as.mo(c("S. aureus", "MRSA", "MSSA", "STAAUR",
-#'                                       "E. coli", "E. coli", "E. coli")),
-#'                    stringsAsFactors = FALSE)
-#'   colnames(df)
-#'   df_joined <- left_join_microorganisms(df, "bacteria")
-#'   colnames(df_joined)
 #' }
 #' }
 inner_join_microorganisms <- function(x, by = NULL, suffix = c("2", ""), ...) {
@@ -119,9 +120,14 @@ join_microorganisms <- function(type, x, by, suffix, ...) {
   check_dataset_integrity()
   
   if (!is.data.frame(x)) {
-    x <- data.frame(mo = x, stringsAsFactors = FALSE)
+    if (pkg_is_available("tibble", also_load = FALSE)) {
+      x <- import_fn("tibble", "tibble")(mo = x)
+    } else {
+      x <- data.frame(mo = x, stringsAsFactors = FALSE)
+    }
     by <- "mo"
   }
+  x.bak <- x
   if (is.null(by)) {
     by <- search_type_in_df(x, "mo", info = FALSE)
     if (is.null(by) && NCOL(x) == 1) {
@@ -171,5 +177,5 @@ join_microorganisms <- function(type, x, by, suffix, ...) {
     warning_("in `", type, "_join()`: the newly joined data set contains ", nrow(joined) - nrow(x), " rows more than the number of rows of `x`.")
   }
   
-  joined
+  as_original_data_class(joined, class(x.bak))
 }

R/like.R

@@ -59,11 +59,9 @@
 #' a[1] %like% b
 #' a %like% b[1]
 #' 
-#' # get isolates whose name start with 'Ent' or 'ent'
-#' example_isolates[which(mo_name(example_isolates$mo) %like% "^ent"), ]
 #' \donttest{
-#' # faster way, since mo_name() is context-aware:
+#' # get isolates whose name start with 'Entero' (case-insensitive)
-#' example_isolates[which(mo_name() %like% "^ent"), ]
+#' example_isolates[which(mo_name() %like% "^entero"), ]
 #' 
 #' if (require("dplyr")) {
 #'   example_isolates %>%

R/mdro.R

@@ -1740,7 +1740,7 @@ run_custom_mdro_guideline <- function(df, guideline, info) {
     out <- factor(out, levels = attributes(guideline)$values, ordered = TRUE)
   }
   
-  columns_nonsusceptible <- as.data.frame(t(df[, is.rsi(df)] == "R"))
+  columns_nonsusceptible <- as.data.frame(t(df[, is.rsi(df), drop = FALSE] == "R"))
   columns_nonsusceptible <- vapply(FUN.VALUE = character(1), 
                                    columns_nonsusceptible, 
                                    function(x) paste0(rownames(columns_nonsusceptible)[which(x)], collapse = " "))

R/mic.R

@@ -120,9 +120,16 @@ valid_mic_levels <- c(c(t(vapply(FUN.VALUE = character(9), ops,
 #' # plot MIC values, see ?plot
 #' plot(mic_data)
 #' plot(mic_data, mo = "E. coli", ab = "cipro")
-#' autoplot(mic_data, mo = "E. coli", ab = "cipro")
+#' 
-#' autoplot(mic_data, mo = "E. coli", ab = "cipro", language = "nl") # Dutch
+#' if (require("ggplot2")) {
-#' autoplot(mic_data, mo = "E. coli", ab = "cipro", language = "uk") # Ukrainian
+#'   autoplot(mic_data, mo = "E. coli", ab = "cipro")
+#' }
+#' if (require("ggplot2")) {
+#'   autoplot(mic_data, mo = "E. coli", ab = "cipro", language = "nl") # Dutch
+#' }
+#' if (require("ggplot2")) {
+#'   autoplot(mic_data, mo = "E. coli", ab = "cipro", language = "uk") # Ukrainian
+#' }
 as.mic <- function(x, na.rm = FALSE) {
   meet_criteria(x, allow_class = c("mic", "character", "numeric", "integer", "factor"), allow_NA = TRUE)
   meet_criteria(na.rm, allow_class = "logical", has_length = 1)

R/mo.R

@@ -419,7 +419,7 @@ exec_as.mo <- function(x,
       return(rep(NA_character_, length(x_input)))
     }
     
-  } else if (all(x %in% reference_df[, 1][[1]])) {
+  } else if (all(x %in% reference_df[, 1, drop = TRUE][[1]])) {
     # all in reference df
     colnames(reference_df)[1] <- "x"
     suppressWarnings(
@@ -449,7 +449,7 @@ exec_as.mo <- function(x,
                    property,
                    drop = TRUE]
     
-  } else if (!all(x %in% microorganisms[, property])) {
+  } else if (!all(x %in% microorganisms[, property, drop = TRUE])) {
     
     strip_whitespace <- function(x, dyslexia_mode) {
       # all whitespaces (tab, new lines, etc.) should be one space
@@ -669,7 +669,7 @@ exec_as.mo <- function(x,
                                           FALSE
                                         }))
           if (sum(snomed_found, na.rm = TRUE) > 0) {
-            found <- reference_data_to_use[snomed_found == TRUE, property][[1]]
+            found <- reference_data_to_use[snomed_found == TRUE, property, drop = TRUE][[1]]
             if (!is.na(found)) {
               x[i] <- found[1L]
               next
@@ -694,9 +694,9 @@ exec_as.mo <- function(x,
         
         # user-defined reference ----
         if (!is.null(reference_df)) {
-          if (x_backup[i] %in% reference_df[, 1]) {
+          if (x_backup[i] %in% reference_df[, 1, drop = TRUE]) {
             # already checked integrity of reference_df, all MOs are valid
-            ref_mo <- reference_df[reference_df[, 1] == x_backup[i], "mo"][[1L]]
+            ref_mo <- reference_df[reference_df[, 1, drop = TRUE] == x_backup[i], "mo", drop = TRUE][[1L]]
             x[i] <- lookup(mo == ref_mo)
             next
           }
@@ -1555,11 +1555,11 @@ exec_as.mo <- function(x,
     
     # nolint start
     # comment below code if all staphylococcal species are categorised as CoNS/CoPS
-    if (any(x %in% MO_lookup[which(MO_lookup$species %in% post_Becker), property])) {
+    if (any(x %in% MO_lookup[which(MO_lookup$species %in% post_Becker), property, drop = TRUE])) {
       if (message_not_thrown_before("as.mo", "becker")) {
         warning_("in `as.mo()`: Becker ", font_italic("et al."), " (2014, 2019, 2020) does not contain these species named after their publication: ",
                  font_italic(paste("S.",
-                                   sort(mo_species(unique(x[x %in% MO_lookup[which(MO_lookup$species %in% post_Becker), property]]))),
+                                   sort(mo_species(unique(x[x %in% MO_lookup[which(MO_lookup$species %in% post_Becker), property, drop = TRUE]]))),
                                    collapse = ", ")),
                  ". Categorisation to CoNS/CoPS was taken from the original scientific publication(s).",
                  immediate = TRUE)
@@ -1820,7 +1820,7 @@ summary.mo <- function(object, ...) {
   # unique and top 1-3
   x <- as.mo(object) # force again, could be mo from older pkg version
   top <- as.data.frame(table(x), responseName = "n", stringsAsFactors = FALSE)
-  top_3 <- top[order(-top$n), 1][1:3]
+  top_3 <- top[order(-top$n), 1, drop = TRUE][1:3]
   value <- c("Class" = "mo",
              "<NA>" = length(x[is.na(x)]),
              "Unique" = pm_n_distinct(x[!is.na(x)]),
@@ -2206,282 +2206,3 @@ strip_words <- function(text, n, side = "right") {
   })
   vapply(FUN.VALUE = character(1), out, paste, collapse = " ")
 }
-
-
-as.mo2 <- function(x,
-                   Becker = FALSE,
-                   Lancefield = FALSE,
-                   allow_uncertain = TRUE,
-                   reference_df = get_mo_source(),
-                   info = interactive(),
-                   property = "mo",
-                   initial_search = TRUE,
-                   dyslexia_mode = FALSE,
-                   debug = FALSE,
-                   ignore_pattern = getOption("AMR_ignore_pattern"),
-                   reference_data_to_use = MO_lookup,
-                   actual_uncertainty = 1,
-                   actual_input = NULL,
-                   language = get_AMR_locale()) {
-  meet_criteria(x, allow_class = c("mo", "data.frame", "list", "character", "numeric", "integer", "factor"), allow_NA = TRUE)
-  meet_criteria(Becker, allow_class = c("logical", "character"), has_length = 1)
-  meet_criteria(Lancefield, allow_class = c("logical", "character"), has_length = 1)
-  meet_criteria(allow_uncertain, allow_class = c("logical", "numeric", "integer"), has_length = 1)
-  meet_criteria(reference_df, allow_class = "data.frame", allow_NULL = TRUE)
-  meet_criteria(property, allow_class = "character", has_length = 1, is_in = colnames(microorganisms))
-  meet_criteria(initial_search, allow_class = "logical", has_length = 1)
-  meet_criteria(dyslexia_mode, allow_class = "logical", has_length = 1)
-  meet_criteria(debug, allow_class = "logical", has_length = 1)
-  meet_criteria(ignore_pattern, allow_class = "character", has_length = 1, allow_NULL = TRUE)
-  meet_criteria(reference_data_to_use, allow_class = "data.frame")
-  meet_criteria(actual_uncertainty, allow_class = "numeric", has_length = 1)
-  meet_criteria(actual_input, allow_class = "character", allow_NULL = TRUE)
-  meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
-  
-  check_dataset_integrity()
-  
-  if (isTRUE(debug) && initial_search == TRUE) {
-    time_start_tracking()
-  }
-  
-  lookup <- function(needle,
-                     column = property,
-                     haystack = reference_data_to_use,
-                     n = 1,
-                     debug_mode = debug,
-                     initial = initial_search,
-                     uncertainty = actual_uncertainty,
-                     input_actual = actual_input) {
-    
-    if (!is.null(input_actual)) {
-      input <- input_actual
-    } else {
-      input <- tryCatch(x_backup[i], error = function(e) "")
-    }
-    
-    # `column` can be NULL for all columns, or a selection
-    # returns a [character] (vector) - if `column` > length 1 then with columns as names
-    if (isTRUE(debug_mode)) {
-      cat(font_silver("Looking up: ", substitute(needle), collapse = ""), 
-          "\n           ", time_track())
-    }
-    if (length(column) == 1) {
-      res_df <- haystack[which(eval(substitute(needle), envir = haystack, enclos = parent.frame())), , drop = FALSE]
-      if (NROW(res_df) > 1 & uncertainty != -1) {
-        # sort the findings on matching score
-        scores <- mo_matching_score(x = input,
-                                    n = res_df[, "fullname", drop = TRUE])
-        res_df <- res_df[order(scores, decreasing = TRUE), , drop = FALSE]
-      }
-      res <- as.character(res_df[, column, drop = TRUE])
-      if (length(res) == 0) {
-        if (isTRUE(debug_mode)) {
-          cat(font_red(" (no match)\n"))
-        }
-        NA_character_
-      } else {
-        if (isTRUE(debug_mode)) {
-          cat(font_green(paste0(" MATCH (", NROW(res_df), " results)\n")))
-        }
-        if ((length(res) > n | uncertainty > 1) & uncertainty != -1) {
-          # save the other possible results as well, but not for forced certain results (then uncertainty == -1)
-          uncertainties <<- rbind(uncertainties,
-                                  format_uncertainty_as_df(uncertainty_level = uncertainty,
-                                                           input = input,
-                                                           result_mo = res_df[1, "mo", drop = TRUE],
-                                                           candidates = as.character(res_df[, "fullname", drop = TRUE])),
-                                  stringsAsFactors = FALSE)
-        }
-        res[seq_len(min(n, length(res)))]
-      }
-    } else {
-      if (is.null(column)) {
-        column <- names(haystack)
-      }
-      res <- haystack[which(eval(substitute(needle), envir = haystack, enclos = parent.frame())), , drop = FALSE]
-      res <- res[seq_len(min(n, nrow(res))), column, drop = TRUE]
-      if (NROW(res) == 0) {
-        if (isTRUE(debug_mode)) {
-          cat(font_red(" (no rows)\n"))
-        }
-        res <- rep(NA_character_, length(column))
-      } else {
-        if (isTRUE(debug_mode)) {
-          cat(font_green(paste0(" MATCH (", NROW(res), " rows)\n")))
-        }
-      }
-      res <- as.character(res)
-      names(res) <- column
-      res
-    }
-  }
-  
-  # start off with replaced language-specific non-ASCII characters with ASCII characters
-  x <- parse_and_convert(x)
-  # replace mo codes used in older package versions
-  x <- replace_old_mo_codes(x, property)
-  # ignore cases that match the ignore pattern
-  x <- replace_ignore_pattern(x, ignore_pattern)
-  
-  # WHONET: xxx = no growth
-  x[tolower(as.character(paste0(x, ""))) %in% c("", "xxx", "na", "nan")] <- NA_character_
-  # Laboratory systems: remove (translated) entries like "no growth", etc.
-  x[trimws2(x) %like% translate_into_language("no .*growth", language = language)] <- NA_character_
-  x[trimws2(x) %like% paste0("^(", translate_into_language("no|not", language = language), ") [a-z]+")] <- "UNKNOWN"
-  
-  if (initial_search == TRUE) {
-    # keep track of time - give some hints to improve speed if it takes a long time
-    start_time <- Sys.time()
-    
-    pkg_env$mo_failures <- NULL
-    pkg_env$mo_uncertainties <- NULL
-    pkg_env$mo_renamed <- NULL
-  }
-  pkg_env$mo_renamed_last_run <- NULL
-  
-  failures <- character(0)
-  uncertainty_level <- translate_allow_uncertain(allow_uncertain)
-  uncertainties <- data.frame(uncertainty = integer(0),
-                              input = character(0),
-                              fullname = character(0),
-                              renamed_to = character(0),
-                              mo = character(0),
-                              candidates = character(0),
-                              stringsAsFactors = FALSE)
-  
-  x_input <- x
-  # already strip leading and trailing spaces
-  x <- trimws(x)
-  # only check the uniques, which is way faster
-  x <- unique(x)
-  # remove empty values (to later fill them in again with NAs)
-  # ("xxx" is WHONET code for 'no growth')
-  x <- x[!is.na(x)
-         & !is.null(x)
-         & !identical(x, "")
-         & !identical(x, "xxx")]
-  
-  # defined df to check for
-  if (!is.null(reference_df)) {
-    check_validity_mo_source(reference_df)
-    reference_df <- repair_reference_df(reference_df)
-  }
-  
-  # all empty
-  if (all(identical(trimws(x_input), "") | is.na(x_input) | length(x) == 0)) {
-    if (property == "mo") {
-      return(set_clean_class(rep(NA_character_, length(x_input)),
-                             new_class = c("mo", "character")))
-    } else {
-      return(rep(NA_character_, length(x_input)))
-    }
-    
-  } else if (all(x %in% reference_df[, 1][[1]])) {
-    # all in reference df
-    colnames(reference_df)[1] <- "x"
-    suppressWarnings(
-      x <- MO_lookup[match(reference_df[match(x, reference_df$x), "mo", drop = TRUE], MO_lookup$mo), property, drop = TRUE]
-    )
-    
-  } else if (all(x %in% reference_data_to_use$mo)) {
-    x <- MO_lookup[match(x, MO_lookup$mo), property, drop = TRUE]
-    
-  } else if (all(tolower(x) %in% reference_data_to_use$fullname_lower)) {
-    # we need special treatment for very prevalent full names, they are likely!
-    # e.g. as.mo("Staphylococcus aureus")
-    x <- MO_lookup[match(tolower(x), MO_lookup$fullname_lower), property, drop = TRUE]
-    
-  } else if (all(x %in% reference_data_to_use$fullname)) {
-    # we need special treatment for very prevalent full names, they are likely!
-    # e.g. as.mo("Staphylococcus aureus")
-    x <- MO_lookup[match(x, MO_lookup$fullname), property, drop = TRUE]
-    
-  } else if (all(toupper(x) %in% microorganisms.codes$code)) {
-    # commonly used MO codes
-    x <- MO_lookup[match(microorganisms.codes[match(toupper(x),
-                                                    microorganisms.codes$code),
-                                              "mo",
-                                              drop = TRUE],
-                         MO_lookup$mo),
-                   property,
-                   drop = TRUE]
-    
-  } else if (!all(x %in% microorganisms[, property])) {
-    
-    strip_whitespace <- function(x, dyslexia_mode) {
-      # all whitespaces (tab, new lines, etc.) should be one space
-      # and spaces before and after should be left blank
-      trimmed <- trimws2(x)
-      # also, make sure the trailing and leading characters are a-z or 0-9
-      # in case of non-regex
-      if (dyslexia_mode == FALSE) {
-        trimmed <- gsub("^[^a-zA-Z0-9)(]+", "", trimmed, perl = TRUE)
-        trimmed <- gsub("[^a-zA-Z0-9)(]+$", "", trimmed, perl = TRUE)
-      }
-      trimmed
-    }
-    
-    x_backup_untouched <- x
-    x <- strip_whitespace(x, dyslexia_mode)
-    # translate 'unknown' names back to English
-    if (any(tolower(x) %like_case% "unbekannt|onbekend|desconocid|sconosciut|iconnu|desconhecid", na.rm = TRUE)) {
-      trns <- subset(TRANSLATIONS, pattern %like% "unknown")
-      langs <- LANGUAGES_SUPPORTED[LANGUAGES_SUPPORTED != "en"]
-      for (l in langs) {
-        for (i in seq_len(nrow(trns))) {
-          if (!is.na(trns[i, l, drop = TRUE])) {
-            x <- gsub(pattern = trns[i, l, drop = TRUE],
-                      replacement = trns$pattern[i],
-                      x = x,
-                      ignore.case = TRUE,
-                      perl = TRUE)
-          }
-        }
-      }
-    }
-    
-    # remove spp and species
-    x <- gsub("(^| )[ .]*(spp|ssp|ss|sp|subsp|subspecies|biovar|biotype|serovar|species)[ .]*( |$)", "", x, ignore.case = TRUE, perl = TRUE)
-    x <- strip_whitespace(x, dyslexia_mode)
-    
-    x_backup <- x
-    
-    # from here on case-insensitive
-    x <- tolower(x)
-    
-    x_backup[x %like_case% "^(fungus|fungi)$"] <- "(unknown fungus)" # will otherwise become the kingdom
-    x_backup[x_backup_untouched == "Fungi"] <- "Fungi" # is literally the kingdom
-    
-    # Fill in fullnames and MO codes directly
-    known_names <- tolower(x_backup) %in% MO_lookup$fullname_lower
-    x[known_names] <- MO_lookup[match(tolower(x_backup)[known_names], MO_lookup$fullname_lower), property, drop = TRUE]
-    known_codes_mo <- toupper(x_backup) %in% MO_lookup$mo
-    x[known_codes_mo] <- MO_lookup[match(toupper(x_backup)[known_codes_mo], MO_lookup$mo), property, drop = TRUE]
-    known_codes_lis <- toupper(x_backup) %in% microorganisms.codes$code
-    x[known_codes_lis] <- MO_lookup[match(microorganisms.codes[match(toupper(x_backup)[known_codes_lis],
-                                                                     microorganisms.codes$code), "mo", drop = TRUE],
-                                          MO_lookup$mo), property, drop = TRUE]
-    already_known <- known_names | known_codes_mo | known_codes_lis
-    
-    # now only continue where the right taxonomic output is not already known
-    if (any(!already_known)) {
-      x_unknown <- x[!already_known]
-      x_unknown <- gsub(" ?[(].*[)] ?", "", x_unknown, perl = TRUE)
-      x_unknown <- gsub("[^a-z ]", " ", x_unknown, perl = TRUE)
-      x_unknown <- gsub(" +", " ", x_unknown, perl = TRUE)
-      print(x_unknown)
-      x_search <- gsub("([a-z])[a-z]*( ([a-z])[a-z]*)?( ([a-z])[a-z]*)?", "^\\1.* \\3.* \\5.*", x_unknown, perl = TRUE)
-      x_search <- gsub("( [.][*])+$", "", x_search, perl = TRUE)
-      print(x_search)
-      for (i in seq_len(length(x_unknown))) {
-        # search first, second and third part
-        mos_to_search <- MO_lookup[which(MO_lookup$fullname_lower %like_case% x_search[i]), "fullname", drop = TRUE]
-        score <- mo_matching_score(x_unknown[i], mos_to_search)
-        out <- mos_to_search[order(score, decreasing = TRUE)][1:25] # keep first 25
-        print(score[order(score, decreasing = TRUE)][1])
-        x[!already_known][i] <- MO_lookup$mo[match(out[1], MO_lookup$fullname)]
-      }
-    }
-  }
-  x
-}

R/mo_property.R

@@ -601,7 +601,7 @@ mo_synonyms <- function(x, language = get_AMR_locale(), ...) {
   
   IDs <- mo_name(x = x, language = NULL)
   syns <- lapply(IDs, function(newname) {
-    res <- sort(microorganisms.old[which(microorganisms.old$fullname_new == newname), "fullname"])
+    res <- sort(microorganisms.old[which(microorganisms.old$fullname_new == newname), "fullname", drop = TRUE])
     if (length(res) == 0) {
       NULL
     } else {
@@ -664,7 +664,7 @@ mo_url <- function(x, open = FALSE, language = get_AMR_locale(), ...) {
   x.mo <- as.mo(x = x, language = language, ... = ...)
   metadata <- get_mo_failures_uncertainties_renamed()
   
-  df <- microorganisms[match(x.mo, microorganisms$mo), c("mo", "fullname", "source", "kingdom", "rank")]
+  df <- microorganisms[match(x.mo, microorganisms$mo), c("mo", "fullname", "source", "kingdom", "rank"), drop = FALSE]
   df$url <- ifelse(df$source == "LPSN",
                    paste0(CATALOGUE_OF_LIFE$url_LPSN, "/species/", gsub(" ", "-", tolower(df$fullname), fixed = TRUE)),
                    paste0(CATALOGUE_OF_LIFE$url_CoL, "/data/search?type=EXACT&q=", gsub(" ", "%20", df$fullname, fixed = TRUE)))

R/pca.R

@@ -114,7 +114,7 @@ pca <- function(x,
              error = function(e) warning("column names could not be set"))
     
     # keep only numeric columns
-    x <- x[, vapply(FUN.VALUE = logical(1), x, function(y) is.numeric(y))]
+    x <- x[, vapply(FUN.VALUE = logical(1), x, function(y) is.numeric(y)), drop = FALSE]
     # bind the data set with the non-numeric columns
     x <- cbind(x.bak[, vapply(FUN.VALUE = logical(1), x.bak, function(y) !is.numeric(y) & !all(is.na(y))), drop = FALSE], x)
   }
@@ -122,7 +122,7 @@ pca <- function(x,
   x <- pm_ungroup(x)  # would otherwise select the grouping vars
   x <- x[rowSums(is.na(x)) == 0, ] # remove columns containing NAs
   
-  pca_data <- x[, which(vapply(FUN.VALUE = logical(1), x, function(x) is.numeric(x)))]
+  pca_data <- x[, which(vapply(FUN.VALUE = logical(1), x, function(x) is.numeric(x))), drop = FALSE]
   
   message_("Columns selected for PCA: ", vector_and(font_bold(colnames(pca_data), collapse = NULL), quotes = TRUE),
            ". Total observations available: ", nrow(pca_data), ".")

R/proportion.R

@@ -106,12 +106,12 @@
 #' \donttest{
 #' if (require("dplyr")) {
 #'   example_isolates %>%
-#'     group_by(hospital_id) %>%
+#'     group_by(ward) %>%
 #'     summarise(r = resistance(CIP),
 #'               n = n_rsi(CIP)) # n_rsi works like n_distinct in dplyr, see ?n_rsi
 #'  
 #'   example_isolates %>%
-#'     group_by(hospital_id) %>%
+#'     group_by(ward) %>%
 #'     summarise(R  = resistance(CIP, as_percent = TRUE),
 #'               SI = susceptibility(CIP, as_percent = TRUE),
 #'               n1 = count_all(CIP),  # the actual total; sum of all three
@@ -143,7 +143,7 @@
 #'  
 #'  
 #'   example_isolates %>%
-#'     group_by(hospital_id) %>%
+#'     group_by(ward) %>%
 #'     summarise(cipro_p = susceptibility(CIP, as_percent = TRUE),
 #'               cipro_n = count_all(CIP),
 #'               genta_p = susceptibility(GEN, as_percent = TRUE),
@@ -159,8 +159,8 @@
 #'   # It also supports grouping variables
 #'   # (use rsi_df to also include the count)
 #'   example_isolates %>%
-#'     select(hospital_id, AMX, CIP) %>%
+#'     select(ward, AMX, CIP) %>%
-#'     group_by(hospital_id) %>%
+#'     group_by(ward) %>%
 #'     rsi_df(translate = FALSE)
 #' }
 #' }

R/resistance_predict.R

@@ -80,7 +80,7 @@
 #'     filter_first_isolate() %>%
 #'     filter(mo_genus(mo) == "Staphylococcus") %>%
 #'     resistance_predict("PEN", model = "binomial")
-#'   plot(x)
+#'   print(plot(x))
 #'
 #'   # get the model from the object
 #'   mymodel <- attributes(x)$model
@@ -88,7 +88,7 @@
 #' }
 #'
 #' # create nice plots with ggplot2 yourself
-#' if (require("dplyr") & require("ggplot2")) {
+#' if (require("dplyr") && require("ggplot2")) {
 #' 
 #'   data <- example_isolates %>%
 #'     filter(mo == as.mo("E. coli")) %>%
@@ -127,6 +127,9 @@ resistance_predict <- function(x,
   
   stop_if(is.null(model), 'choose a regression model with the `model` argument, e.g. resistance_predict(..., model = "binomial")')
   
+  x.bak <- x
+  x <- as.data.frame(x, stringsAsFactors = FALSE)
+  
   dots <- unlist(list(...))
   if (length(dots) != 0) {
     # backwards compatibility with old arguments
@@ -147,9 +150,6 @@ resistance_predict <- function(x,
   stop_ifnot(col_date %in% colnames(x),
              "column '", col_date, "' not found")
   
-  # no grouped tibbles
-  x <- as.data.frame(x, stringsAsFactors = FALSE)
-  
   year <- function(x) {
     # don't depend on lubridate or so, would be overkill for only this function
     if (all(grepl("^[0-9]{4}$", x))) {
@@ -173,7 +173,7 @@ resistance_predict <- function(x,
   # remove rows with NAs
   df <- subset(df, !is.na(df[, col_ab, drop = TRUE]))
   df$year <- year(df[, col_date, drop = TRUE])
-  df <- as.data.frame(rbind(table(df[, c("year", col_ab)])),
+  df <- as.data.frame(rbind(table(df[, c("year", col_ab), drop = FALSE])),
                       stringsAsFactors = FALSE)
   df$year <- as.integer(rownames(df))
   rownames(df) <- NULL
@@ -275,15 +275,15 @@ resistance_predict <- function(x,
   }
   
   df_prediction$value <- ifelse(df_prediction$value > 1, 1, ifelse(df_prediction$value < 0, 0, df_prediction$value))
-  df_prediction <- df_prediction[order(df_prediction$year), ]
+  df_prediction <- df_prediction[order(df_prediction$year), , drop = FALSE]
   
-  structure(
+  out <- as_original_data_class(df_prediction, class(x.bak))
-    .Data = df_prediction,
+  structure(out,
-    class = c("resistance_predict", "data.frame"),
+            class = c("resistance_predict", class(out)),
-    I_as_S = I_as_S,
+            I_as_S = I_as_S,
-    model_title = model,
+            model_title = model,
-    model = model_lm,
+            model = model_lm,
-    ab = col_ab
+            ab = col_ab
   )
 }
 

R/rsi_calc.R

@@ -89,7 +89,7 @@ rsi_calc <- function(...,
     x <- NULL
     try(x <- as.data.frame(dots, stringsAsFactors = FALSE), silent = TRUE)
     if (is.null(x)) {
-      # support for example_isolates %pm>% group_by(hospital_id) %pm>% summarise(amox = susceptibility(GEN, AMX))
+      # support for example_isolates %pm>% group_by(ward) %pm>% summarise(amox = susceptibility(GEN, AMX))
       x <- as.data.frame(list(...), stringsAsFactors = FALSE)
     }
   }
@@ -226,6 +226,7 @@ rsi_calc_df <- function(type, # "proportion", "count" or "both"
   
   translate_ab <- get_translate_ab(translate_ab)
   
+  data.bak <- data
   # select only groups and antibiotics
   if (is_null_or_grouped_tbl(data)) {
     data_has_groups <- TRUE
@@ -331,9 +332,9 @@ rsi_calc_df <- function(type, # "proportion", "count" or "both"
   
   if (data_has_groups) {
     # ordering by the groups and two more: "antibiotic" and "interpretation"
-   out <-  pm_ungroup(out[do.call("order", out[, seq_len(length(groups) + 2)]), ])
+   out <-  pm_ungroup(out[do.call("order", out[, seq_len(length(groups) + 2), drop = FALSE]), , drop = FALSE])
   } else {
-    out <- out[order(out$antibiotic, out$interpretation), ]
+    out <- out[order(out$antibiotic, out$interpretation), , drop = FALSE]
   }
   
   if (type == "proportion") {
@@ -344,8 +345,8 @@ rsi_calc_df <- function(type, # "proportion", "count" or "both"
   } 
   
   rownames(out) <- NULL
-  class(out) <- c("rsi_df", class(out))
+  out <- as_original_data_class(out, class(data.bak))
-  out
+  structure(out, class = c("rsi_df", class(out)))
 }
 
 get_translate_ab <- function(translate_ab) {

R/translate.R

@@ -27,13 +27,13 @@
 #'
 #' For language-dependent output of AMR functions, like [mo_name()], [mo_gramstain()], [mo_type()] and [ab_name()].
 #' @param x text to translate
-#' @param lang language to choose. Use one of these supported language names or ISO-639-1 codes: `r paste0('"', sapply(LANGUAGES_SUPPORTED_NAMES, function(x) x[[1]]), '" ("' , LANGUAGES_SUPPORTED, '")', collapse = ", ")`.
+#' @param language language to choose. Use one of these supported language names or ISO-639-1 codes: `r paste0('"', sapply(LANGUAGES_SUPPORTED_NAMES, function(x) x[[1]]), '" ("' , LANGUAGES_SUPPORTED, '")', collapse = ", ")`.
 #' @details The currently `r length(LANGUAGES_SUPPORTED)` supported languages are `r vector_and(sapply(LANGUAGES_SUPPORTED_NAMES, function(x) x[[1]]), quotes = FALSE, sort = FALSE)`. All these languages have translations available for all antimicrobial agents and colloquial microorganism names.
 #'
 #' Please read about adding or updating a language in [our Wiki](https://github.com/msberends/AMR/wiki/).
 #'
 #' ## Changing the Default Language
-#' The system language will be used at default (as returned by `Sys.getenv("LANG")` or, if `LANG` is not set, [Sys.getlocale("LC_COLLATE")]), if that language is supported. But the language to be used can be overwritten in two ways and will be checked in this order:
+#' The system language will be used at default (as returned by `Sys.getenv("LANG")` or, if `LANG` is not set, [`Sys.getlocale("LC_COLLATE")`][Sys.getlocale()]), if that language is supported. But the language to be used can be overwritten in two ways and will be checked in this order:
 #' 
 #'   1. Setting the R option `AMR_locale`, either by using `set_AMR_locale()` or by running e.g. `options(AMR_locale = "de")`.
 #'   
@@ -93,10 +93,10 @@ get_AMR_locale <- function() {
 
 #' @rdname translate
 #' @export
-set_AMR_locale <- function(lang) {
+set_AMR_locale <- function(language) {
-  lang <- validate_language(lang)
+  language <- validate_language(language)
-  options(AMR_locale = lang)
+  options(AMR_locale = language)
-  message_("Using the ", LANGUAGES_SUPPORTED_NAMES[[lang]]$exonym,  " language (", LANGUAGES_SUPPORTED_NAMES[[lang]]$endonym, ") for the AMR package for this session.")
+  message_("Using the ", LANGUAGES_SUPPORTED_NAMES[[language]]$exonym,  " language (", LANGUAGES_SUPPORTED_NAMES[[language]]$endonym, ") for the AMR package for this session.")
 }
 
 #' @rdname translate
@@ -111,6 +111,7 @@ translate_AMR <- function(x, language = get_AMR_locale()) {
   translate_into_language(x, language = language)
 }
 
+
 validate_language <- function(language, extra_txt = character(0)) {
   if (trimws(tolower(language)) %in% c("en", "english", "", "false", NA)) {
     return("en")
@@ -124,8 +125,8 @@ validate_language <- function(language, extra_txt = character(0)) {
   lang
 }
 
-find_language <- function(lang, fallback = TRUE) {
+find_language <- function(language, fallback = TRUE) {
-  lang <- Map(function(l, n, check = lang) {
+  language <- Map(function(l, n, check = language) {
     grepl(paste0("^(", l[1], "|", l[2], "|",
                  n, "(_|$)|", toupper(n), "(_|$))"),
           check,
@@ -136,12 +137,12 @@ find_language <- function(lang, fallback = TRUE) {
   LANGUAGES_SUPPORTED_NAMES,
   LANGUAGES_SUPPORTED,
   USE.NAMES = TRUE)
-  lang <- names(which(lang == TRUE))
+  language <- names(which(language == TRUE))
-  if (isTRUE(fallback) && length(lang) == 0) {
+  if (isTRUE(fallback) && length(language) == 0) {
     # other language -> set to English
-    lang <- "en"
+    language <- "en"
   }
-  lang
+  language
 }
 
 # translate strings based on inst/translations.tsv

R/zzz.R

@@ -101,9 +101,13 @@ if (utf8_supported && !is_latex) {
     }
   }, silent = TRUE)
   
+  # be sure to print tibbles as tibbles
+  if (pkg_is_available("tibble", also_load = FALSE)) {
+    loadNamespace("tibble")
+  }
   
   # reference data - they have additional columns compared to `antibiotics` and `microorganisms` to improve speed
-  # they cannott be part of R/sysdata.rda since CRAN thinks it would make the package too large (+3 MB)
+  # they cannot be part of R/sysdata.rda since CRAN thinks it would make the package too large (+3 MB)
   assign(x = "AB_lookup", value = create_AB_lookup(), envir = asNamespace("AMR"))
   assign(x = "MO_lookup", value = create_MO_lookup(), envir = asNamespace("AMR"))
   assign(x = "MO.old_lookup", value = create_MO.old_lookup(), envir = asNamespace("AMR"))
@@ -140,7 +144,7 @@ create_MO_lookup <- function() {
   MO_lookup$g_species <- gsub("^([a-z])[a-z]+ ([a-z]+) ?.*", "\\1 \\2", MO_lookup$fullname_lower, perl = TRUE)
   
   # so arrange data on prevalence first, then kingdom, then full name
-  MO_lookup[order(MO_lookup$prevalence, MO_lookup$kingdom_index, MO_lookup$fullname_lower), ]
+  MO_lookup[order(MO_lookup$prevalence, MO_lookup$kingdom_index, MO_lookup$fullname_lower), , drop = FALSE]
 }
 
 create_MO.old_lookup <- function() {
@@ -151,7 +155,7 @@ create_MO.old_lookup <- function() {
   MO.old_lookup$g_species <- trimws(gsub("^([a-z])[a-z]+ ([a-z]+) ?.*", "\\1 \\2", MO.old_lookup$fullname_lower))
   
   # so arrange data on prevalence first, then full name
-  MO.old_lookup[order(MO.old_lookup$prevalence, MO.old_lookup$fullname_lower), ]
+  MO.old_lookup[order(MO.old_lookup$prevalence, MO.old_lookup$fullname_lower), , drop = FALSE]
 }
 
 create_intr_resistance <- function() {

data-raw/Loinc.csv

@@ -71673,7 +71673,7 @@
 "7553-1","Origanum vulgare Ab.IgG","ACnc","Pt","Ser","Qn","","ALLERGY","2.27","MIN","","ACTIVE","","1","","","","","","Y","","ABS; Aby; Allergen; Allergens; ALLERGY TESTING; Antby; Anti; Antibodies; Antibody; Arbitrary concentration; Autoantibodies; Autoantibody; f283; Immune globulin G; Immunoglobulin G; Oregano; Oreganum; Point in time; QNT; Quan; Quant; Quantitative; Random; Rf283; Serum; SR","Oregano IgG Qn","Both","","","","","Oregano IgG Ab [Units/volume] in Serum","","","","","","","0","0","0","","","","","","1.0h(2)","","Oregano IgG Qn (S)"
 "75531-4","Enrollment basis","Type","Pt","^Patient","Nom","","SURVEY.PCORNET","2.50","MIN","","ACTIVE","","4","","","","","","","","Nominal; Point in time; Random; Survey; SURVEY.PCORNET; Typ","Enrollment basis","Observation","","","","","Enrollment basis","","","","","","","0","0","0","","","","","","2.50","",""
 "75532-2","Applicable accrediting agency for unit","Type","Pt","{Nursing unit}","Nom","NMMDS","SURVEY.NMMDS","2.50","MIN","Types of accreditation that are appropriate or applicable to a unit or service.  The unit may or may not have received the accreditation.","ACTIVE","","4","","","","","","","","Nominal; Nursing Management Minimum Data Set; Point in time; Random; Survey; SURVEY.NMMDS; Typ","","Observation","","","Copyright © 2006 Diane Huber and Connie Delaney. Used with permission.","","Applicable accrediting agency for unit [NMMDS]","","","","","","","0","0","0","","NMMDS","","","","2.50","",""
-"75533-0","Accreditation, certification, & licensure panel","-","Pt","{Nursing unit}","-","NMMDS","PANEL.SURVEY.NMMDS","2.52","MIN","The set of terms in this panel are used to indicate quality assurance organizations of the nursing delivery unit/service by 3 different quality measure categories: accreditation, certification and licensure. Accreditation is a seal of approval given by private, nationally recognized groups that check on the quality of care at health care facilities and organizations. Health care organizations must meet certain quality standards in order to be accredited. Certification is the formal recognition of the knowledge, skills, and experience demonstrated by the achievement of standards that are identified by the profession² (ANA, 2009). Licensure is the granting of authority to practice² (ANA, 2009). State agencies determine the requirements for licensure and examine the competency necessary to meet quality standards.","ACTIVE","","4","","","","","","","","Nursing Management Minimum Data Set; Pan; PANEL.SURVEY.NMMDS; Panl; Pnl; Point in time; Random; Survey; SURVEY.NMMDS","","","","","Copyright © 2006 Diane Huber and Connie Delaney. Used with permission.","","NMMDS accreditation, certification, and licensure panel [NMMDS]","","","","","","","0","0","0","","NMMDS","Panel","","","2.50","",""
+"75533-0","Accreditation, certification, & licensure panel","-","Pt","{Nursing unit}","-","NMMDS","PANEL.SURVEY.NMMDS","2.52","MIN","The set of terms in this panel are used to indicate quality assurance organizations of the nursing delivery unit/service by 3 different quality measure categories: accreditation, certification and licensure. Accreditation is a seal of approval given by private, nationally recognized groups that check on the quality of care at health care facilities and organizations. Health care organizations must meet certain quality standards in order to be accredited. Certification is the formal recognition of the knowledge, skills, and experience demonstrated by the achievement of standards that are identified by the profession² (ANA, 2009). Licensure is the granting of authority to practise² (ANA, 2009). State agencies determine the requirements for licensure and examine the competency necessary to meet quality standards.","ACTIVE","","4","","","","","","","","Nursing Management Minimum Data Set; Pan; PANEL.SURVEY.NMMDS; Panl; Pnl; Point in time; Random; Survey; SURVEY.NMMDS","","","","","Copyright © 2006 Diane Huber and Connie Delaney. Used with permission.","","NMMDS accreditation, certification, and licensure panel [NMMDS]","","","","","","","0","0","0","","NMMDS","Panel","","","2.50","",""
 "75534-8","Accreditation received","Type","Pt","{Nursing unit}","Nom","NMMDS","SURVEY.NMMDS","2.50","MIN","Types of accreditation obtained by a unit to demonstrate quality of care. Accreditation is a seal of approval given by private, nationally recognized groups that check on the quality of care at health care facilities and organizations. Health care organizations must meet certain quality standards in order to be accredited.","ACTIVE","","4","","","","","","","","Nominal; Nursing Management Minimum Data Set; Point in time; Random; Survey; SURVEY.NMMDS; Typ","","Observation","","","Copyright © 2006 Diane Huber and Connie Delaney. Used with permission.","","Accreditation received [NMMDS]","","","","","","","0","0","0","","NMMDS","","","","2.50","",""
 "75535-5","Certification received","Type","Pt","{Nursing unit}","Nom","NMMDS","SURVEY.NMMDS","2.50","MIN","Types of certification obtained by a unit to demonstrate quality care.","ACTIVE","","4","","","","","","","","Nominal; Nursing Management Minimum Data Set; Point in time; Random; Survey; SURVEY.NMMDS; Typ","","Observation","","","Copyright © 2006 Diane Huber and Connie Delaney. Used with permission.","","Certification received [NMMDS]","","","","","","","0","0","0","","NMMDS","","","","2.50","",""
 "75536-3","Applicable certification agency for unit","Type","Pt","{Nursing unit}","Nom","NMMDS","SURVEY.NMMDS","2.50","MIN","Types of certification that are appropriate or applicable to a unit or service.  The unit may or may not have received the certification.","ACTIVE","","4","","","","","","","","Nominal; Nursing Management Minimum Data Set; Point in time; Random; Survey; SURVEY.NMMDS; Typ","","Observation","","","Copyright © 2006 Diane Huber and Connie Delaney. Used with permission.","","Applicable certification agency for unit [NMMDS]","","","","","","","0","0","0","","NMMDS","","","","2.50","",""

data-raw/_language_update.R

@@ -55,7 +55,7 @@ lang_env$TRANSLATIONS <- utils::read.delim(file = "data-raw/translations.tsv",
                                            quote = "")
 
 lang_env$LANGUAGES_SUPPORTED_NAMES <- c(list(en = list(exonym = "English", endonym = "English")),
-                                        lapply(lang_env$TRANSLATIONS[, which(nchar(colnames(lang_env$TRANSLATIONS)) == 2)],
+                                        lapply(lang_env$TRANSLATIONS[, which(nchar(colnames(lang_env$TRANSLATIONS)) == 2), drop = FALSE],
                                                function(x) list(exonym = x[1], endonym = x[2])))
 
 lang_env$LANGUAGES_SUPPORTED <- names(lang_env$LANGUAGES_SUPPORTED_NAMES)

data-raw/ex2.R

@@ -1,13 +0,0 @@
-ex2 <- example_isolates
-for (extra_id in seq_len(50)) {
-  ex2 <- ex2 %>% 
-    bind_rows(example_isolates %>% mutate(patient_id = paste0(patient_id, extra_id)))
-}
-# randomly clear antibibiograms of 2%
-clr <- sort(sample(x = seq_len(nrow(ex2)),
-                   size = nrow(ex2) * 0.02))
-for (row in which(is.rsi(ex2))) {
-  ex2[clr, row] <- NA_rsi_
-}
-
-

data-raw/exploratory_data_analysis_test.R

@@ -1,28 +0,0 @@
-library(dplyr)
-example_isolates %>% 
-  select(mo, where(is.rsi)) %>% 
-  tidyr::pivot_longer(cols = where(is.rsi)) %>% 
-  # remove intrisic R
-  filter(!paste(mo, name) %in% AMR:::INTRINSIC_R) %>% 
-  mutate(name = as.ab(name),
-         value = ifelse(value == "R", 1, 0),
-         class = ab_group(name)) %>% 
-  group_by(mo, class) %>% 
-  summarise(n = n(),
-            res = mean(value, na.rm = TRUE)) %>% 
-  filter(n > 30, !is.na(res))
-
-
-
-df <- example_isolates
-search_mo <- "B_ESCHR_COLI"
-intrinsic_res <- INTRINSIC_R[INTRINSIC_R %like% search_mo]
-intrinsic_res <- gsub(".* (.*)", "\\1", intrinsic_res)
-
-x <- df %>%
-  select(mo, where(is.rsi)) %>% 
-  filter(mo == search_mo) %>%
-  # at least 30 results available
-  select(function(x) sum(!is.na(x)) >= 30) %>% 
-  # remove intrisic R
-  select(!matches(paste(intrinsic_res, collapse = "|")))

data-raw/pre-commit-hook.R

@@ -29,7 +29,7 @@
 library(dplyr, warn.conflicts = FALSE)
 devtools::load_all(quiet = TRUE)
 
-set_AMR_locale("en")
+suppressMessages(set_AMR_locale("en"))
 
 old_globalenv <- ls(envir = globalenv())
 
@@ -69,7 +69,7 @@ TRANSLATIONS <- utils::read.delim(file = "data-raw/translations.tsv",
                                   quote = "")
 
 LANGUAGES_SUPPORTED_NAMES <- c(list(en = list(exonym = "English", endonym = "English")),
-                               lapply(TRANSLATIONS[, which(nchar(colnames(TRANSLATIONS)) == 2)],
+                               lapply(TRANSLATIONS[, which(nchar(colnames(TRANSLATIONS)) == 2), drop = FALSE],
                                       function(x) list(exonym = x[1], endonym = x[2])))
 
 LANGUAGES_SUPPORTED <- names(LANGUAGES_SUPPORTED_NAMES)
@@ -122,7 +122,7 @@ create_MO_fullname_lower <- function() {
                                                    MO_lookup$species,
                                                    MO_lookup$subspecies)))
   ind <- MO_lookup$genus == "" | grepl("^[(]unknown ", MO_lookup$fullname, perl = TRUE)
-  MO_lookup[ind, "fullname_lower"] <- tolower(MO_lookup[ind, "fullname"])
+  MO_lookup[ind, "fullname_lower"] <- tolower(MO_lookup[ind, "fullname", drop = TRUE])
   MO_lookup$fullname_lower <- trimws(gsub("[^.a-z0-9/ \\-]+", "", MO_lookup$fullname_lower, perl = TRUE))
   MO_lookup$fullname_lower
 }
@@ -208,49 +208,50 @@ create_AB_lookup <- function() {
 AB_LOOKUP <- create_AB_lookup()
 
 # Export to package as internal data ----
-usethis::use_data(EUCAST_RULES_DF,
+usethis::ui_info(paste0("Saving {usethis::ui_value('sysdata.rda')} to {usethis::ui_value('R/')}"))
-                  TRANSLATIONS,
+suppressMessages(usethis::use_data(EUCAST_RULES_DF,
-                  LANGUAGES_SUPPORTED_NAMES,
+                                   TRANSLATIONS,
-                  LANGUAGES_SUPPORTED,
+                                   LANGUAGES_SUPPORTED_NAMES,
-                  MO_CONS,
+                                   LANGUAGES_SUPPORTED,
-                  MO_COPS,
+                                   MO_CONS,
-                  MO_STREP_ABCG,
+                                   MO_COPS,
-                  MO_FULLNAME_LOWER,
+                                   MO_STREP_ABCG,
-                  MO_PREVALENT_GENERA,
+                                   MO_FULLNAME_LOWER,
-                  AB_LOOKUP,
+                                   MO_PREVALENT_GENERA,
-                  AB_AMINOGLYCOSIDES,
+                                   AB_LOOKUP,
-                  AB_AMINOPENICILLINS,
+                                   AB_AMINOGLYCOSIDES,
-                  AB_ANTIFUNGALS,
+                                   AB_AMINOPENICILLINS,
-                  AB_ANTIMYCOBACTERIALS,
+                                   AB_ANTIFUNGALS,
-                  AB_CARBAPENEMS,
+                                   AB_ANTIMYCOBACTERIALS,
-                  AB_CEPHALOSPORINS,
+                                   AB_CARBAPENEMS,
-                  AB_CEPHALOSPORINS_1ST,
+                                   AB_CEPHALOSPORINS,
-                  AB_CEPHALOSPORINS_2ND,
+                                   AB_CEPHALOSPORINS_1ST,
-                  AB_CEPHALOSPORINS_3RD,
+                                   AB_CEPHALOSPORINS_2ND,
-                  AB_CEPHALOSPORINS_4TH,
+                                   AB_CEPHALOSPORINS_3RD,
-                  AB_CEPHALOSPORINS_5TH,
+                                   AB_CEPHALOSPORINS_4TH,
-                  AB_CEPHALOSPORINS_EXCEPT_CAZ,
+                                   AB_CEPHALOSPORINS_5TH,
-                  AB_FLUOROQUINOLONES,
+                                   AB_CEPHALOSPORINS_EXCEPT_CAZ,
-                  AB_LIPOGLYCOPEPTIDES,
+                                   AB_FLUOROQUINOLONES,
-                  AB_GLYCOPEPTIDES,
+                                   AB_LIPOGLYCOPEPTIDES,
-                  AB_GLYCOPEPTIDES_EXCEPT_LIPO,
+                                   AB_GLYCOPEPTIDES,
-                  AB_LINCOSAMIDES,
+                                   AB_GLYCOPEPTIDES_EXCEPT_LIPO,
-                  AB_MACROLIDES,
+                                   AB_LINCOSAMIDES,
-                  AB_OXAZOLIDINONES,
+                                   AB_MACROLIDES,
-                  AB_PENICILLINS,
+                                   AB_OXAZOLIDINONES,
-                  AB_POLYMYXINS,
+                                   AB_PENICILLINS,
-                  AB_QUINOLONES,
+                                   AB_POLYMYXINS,
-                  AB_STREPTOGRAMINS,
+                                   AB_QUINOLONES,
-                  AB_TETRACYCLINES,
+                                   AB_STREPTOGRAMINS,
-                  AB_TETRACYCLINES_EXCEPT_TGC,
+                                   AB_TETRACYCLINES,
-                  AB_TRIMETHOPRIMS,
+                                   AB_TETRACYCLINES_EXCEPT_TGC,
-                  AB_UREIDOPENICILLINS,
+                                   AB_TRIMETHOPRIMS,
-                  AB_BETALACTAMS,
+                                   AB_UREIDOPENICILLINS,
-                  DEFINED_AB_GROUPS,
+                                   AB_BETALACTAMS,
-                  internal = TRUE,
+                                   DEFINED_AB_GROUPS,
-                  overwrite = TRUE,
+                                   internal = TRUE,
-                  version = 2,
+                                   overwrite = TRUE,
-                  compress = "xz")
+                                   version = 2,
+                                   compress = "xz"))
 
 # Export data sets to the repository in different formats -----------------
 
@@ -285,7 +286,7 @@ rsi <- rsi_translation %>%
   mutate(mo_name = mo_name(mo, language = NULL), .after = mo) %>%
   mutate(ab_name = ab_name(ab, language = NULL), .after = ab)
 if (changed_md5(rsi)) {
-  usethis::ui_info(paste0("Saving {usethis::ui_value('rsi_translation')} to {usethis::ui_value('/data-raw/')}"))
+  usethis::ui_info(paste0("Saving {usethis::ui_value('rsi_translation')} to {usethis::ui_value('data-raw/')}"))
   write_md5(rsi)
   try(saveRDS(rsi, "data-raw/rsi_translation.rds", version = 2, compress = "xz"), silent = TRUE)
   try(write.table(rsi, "data-raw/rsi_translation.txt", sep = "\t", na = "", row.names = FALSE), silent = TRUE)
@@ -298,7 +299,7 @@ if (changed_md5(rsi)) {
 }
 
 if (changed_md5(microorganisms)) {
-  usethis::ui_info(paste0("Saving {usethis::ui_value('microorganisms')} to {usethis::ui_value('/data-raw/')}"))
+  usethis::ui_info(paste0("Saving {usethis::ui_value('microorganisms')} to {usethis::ui_value('data-raw/')}"))
   write_md5(microorganisms)
   try(saveRDS(microorganisms, "data-raw/microorganisms.rds", version = 2, compress = "xz"), silent = TRUE)
   try(write.table(mo, "data-raw/microorganisms.txt", sep = "\t", na = "", row.names = FALSE), silent = TRUE)
@@ -315,7 +316,7 @@ if (changed_md5(microorganisms)) {
 }
 
 if (changed_md5(microorganisms.old)) {
-  usethis::ui_info(paste0("Saving {usethis::ui_value('microorganisms.old')} to {usethis::ui_value('/data-raw/')}"))
+  usethis::ui_info(paste0("Saving {usethis::ui_value('microorganisms.old')} to {usethis::ui_value('data-raw/')}"))
   write_md5(microorganisms.old)
   try(saveRDS(microorganisms.old, "data-raw/microorganisms.old.rds", version = 2, compress = "xz"), silent = TRUE)
   try(write.table(microorganisms.old, "data-raw/microorganisms.old.txt", sep = "\t", na = "", row.names = FALSE), silent = TRUE)
@@ -329,7 +330,7 @@ if (changed_md5(microorganisms.old)) {
 
 ab <- dplyr::mutate_if(antibiotics, ~!is.numeric(.), as.character)
 if (changed_md5(ab)) {
-  usethis::ui_info(paste0("Saving {usethis::ui_value('antibiotics')} to {usethis::ui_value('/data-raw/')}"))
+  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(write.table(antibiotics, "data-raw/antibiotics.txt", sep = "\t", na = "", row.names = FALSE), silent = TRUE)
@@ -343,7 +344,7 @@ if (changed_md5(ab)) {
 
 av <- dplyr::mutate_if(antivirals, ~!is.numeric(.), as.character)
 if (changed_md5(av)) {
-  usethis::ui_info(paste0("Saving {usethis::ui_value('antivirals')} to {usethis::ui_value('/data-raw/')}"))
+  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(write.table(av, "data-raw/antivirals.txt", sep = "\t", na = "", row.names = FALSE), silent = TRUE)
@@ -360,7 +361,7 @@ intrinsicR <- data.frame(microorganism = mo_name(intrinsic_resistant$mo, languag
                          antibiotic = ab_name(intrinsic_resistant$ab, language = NULL),
                          stringsAsFactors = FALSE)
 if (changed_md5(intrinsicR)) {
-  usethis::ui_info(paste0("Saving {usethis::ui_value('intrinsic_resistant')} to {usethis::ui_value('/data-raw/')}"))
+  usethis::ui_info(paste0("Saving {usethis::ui_value('intrinsic_resistant')} to {usethis::ui_value('data-raw/')}"))
   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)
@@ -373,7 +374,7 @@ if (changed_md5(intrinsicR)) {
 }
 
 if (changed_md5(dosage)) {
-  usethis::ui_info(paste0("Saving {usethis::ui_value('dosage')} to {usethis::ui_value('/data-raw/')}"))
+  usethis::ui_info(paste0("Saving {usethis::ui_value('dosage')} to {usethis::ui_value('data-raw/')}"))
   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)
@@ -385,7 +386,7 @@ if (changed_md5(dosage)) {
   try(arrow::write_parquet(dosage, "data-raw/dosage.parquet"), silent = TRUE)
 }
 
-reset_AMR_locale()
+suppressMessages(reset_AMR_locale())
 
 # remove leftovers from global env
 current_globalenv <- ls(envir = globalenv())

data-raw/reproduction_of_antibiotics.R

@@ -138,7 +138,7 @@ abx2 <- abx2 %>% arrange(ab)
 seqnr <- 0
 # add follow up nrs
 for (i in 2:nrow(abx2)) {
-  if (abx2[i, "ab"] == abx2[i - 1, "ab"]) {
+  if (abx2[i, "ab", drop = TRUE] == abx2[i - 1, "ab", drop = TRUE]) {
     seqnr <- seqnr + 1
     abx2[i, "seqnr"] <- seqnr
   } else {
@@ -147,7 +147,7 @@ for (i in 2:nrow(abx2)) {
 }
 for (i in 2:nrow(abx2)) {
   if (!is.na(abx2[i, "seqnr"])) {
-    abx2[i, "ab"] <- paste0(abx2[i, "ab"], abx2[i, "seqnr"])
+    abx2[i, "ab"] <- paste0(abx2[i, "ab", drop = TRUE], abx2[i, "seqnr", drop = TRUE])
   }
 }
 abx2 <- abx2 %>% select(-seqnr) %>% arrange(name)

data-raw/reproduction_of_example_isolates_unclean.R

@@ -92,7 +92,7 @@ example_isolates_unclean <- data_a %>%
 example_isolates_unclean$patient_id <- sample(patients, size = nrow(example_isolates_unclean), replace = TRUE)
 
 example_isolates_unclean <- example_isolates_unclean %>% 
-  select(patient_id, hospital, date, bacteria, everything())
+  select(patient_id, hospital, date, bacteria, everything()) %>% 
-
+  dataset_UTF8_to_ASCII()
-usethis::use_data(example_isolates_unclean, overwrite = TRUE)
 
+usethis::use_data(example_isolates_unclean, overwrite = TRUE, internal = FALSE, version = 2, compress = "xz")

data-raw/reproduction_of_intrinsic_resistant.R

@@ -36,7 +36,7 @@ int_resis <- eucast_rules(int_resis,
                                                    is.na(have_these_values) & reference.version == 3.3),
                           info = FALSE)
 
-int_resis2 <- int_resis[, sapply(int_resis, function(x) any(!is.rsi(x) | x == "R"))] %>% 
+int_resis2 <- int_resis[, sapply(int_resis, function(x) any(!is.rsi(x) | x == "R")), drop = FALSE] %>% 
   tidyr::pivot_longer(-mo) %>%
   filter(value == "R") %>% 
   select(mo, ab = name)

index.md

@@ -65,8 +65,8 @@ library(AMR)
 library(dplyr)
 
 out <- example_isolates %>%
-  # group by hospital code:
+  # group by ward:
-  group_by(hospital_id) %>%
+  group_by(ward) %>%
   # calculate AMR using resistance(), over all aminoglycosides
   # and polymyxins:
   summarise(across(c(aminoglycosides(), polymyxins()),
@@ -74,36 +74,33 @@ out <- example_isolates %>%
 out
 ```
 
-| hospital_id |  GEN  |  TOB  |  AMK  |  KAN  |  COL  |
+| ward       |   GEN |   TOB |   AMK |   KAN |   COL |
-|:------------|:-----:|:-----:|:-----:|:-----:|:-----:|
+|:-----------|------:|------:|------:|------:|------:|
-| A           | 0.203 | 0.328 | 0.657 |     1 | 0.853 |
+| Clinical   | 0.229 | 0.315 | 0.626 |     1 | 0.780 |
-| B           | 0.274 | 0.367 | 0.645 |     1 | 0.845 |
+| ICU        | 0.290 | 0.400 | 0.662 |     1 | 0.857 |
-| C           | 0.212 | 0.342 | 0.582 |     1 | 0.865 |
+| Outpatient | 0.200 | 0.368 | 0.605 |    NA | 0.889 |
-| D           | 0.251 | 0.332 | 0.642 |     1 | 0.745 |
 
 ```r
 # transform the antibiotic columns to names:
 out %>% set_ab_names()
 ```
 
-| hospital_id | gentamicin | tobramycin | amikacin | kanamycin | colistin  |
+| ward       | gentamicin | tobramycin | amikacin | kanamycin | colistin  |
-|:------------|:----------:|:----------:|:---------|:---------:|:---------:|
+|:-----------|-----------:|-----------:|----------|----------:|----------:|
-| A           |   0.203    |    0.328   |   0.657  |     1     |   0.853   |
+| Clinical   | 0.229      | 0.315      | 0.626    |     1     | 0.780     |
-| B           |   0.274    |    0.367   |   0.645  |     1     |   0.845   |
+| ICU        | 0.290      | 0.400      | 0.662    |     1     | 0.857     |
-| C           |   0.212    |    0.342   |   0.582  |     1     |   0.865   |
+| Outpatient | 0.200      | 0.368      | 0.605    |    NA     | 0.889     |
-| D           |   0.251    |    0.332   |   0.642  |     1     |   0.745   |
 
 ```r
 # transform the antibiotic column to ATC codes:
 out %>% set_ab_names(property = "atc")
 ```
 
-| hospital_id |  J01GB03   |   J01GB01  |  J01GB06 |  J01GB04  |  J01XB01  |
+| ward       |  J01GB03   |   J01GB01  |  J01GB06 |  J01GB04  |  J01XB01  |
-|:------------|:----------:|:----------:|:---------|:---------:|:---------:|
+|:-----------|-----------:|-----------:|----------|----------:|----------:|
-| A           |   0.203    |    0.328   |   0.657  |     1     |   0.853   |
+| Clinical   | 0.229      | 0.315      | 0.626    |     1     | 0.780     |
-| B           |   0.274    |    0.367   |   0.645  |     1     |   0.845   |
+| ICU        | 0.290      | 0.400      | 0.662    |     1     | 0.857     |
-| C           |   0.212    |    0.342   |   0.582  |     1     |   0.865   |
+| Outpatient | 0.200      | 0.368      | 0.605    |    NA     | 0.889     |
-| D           |   0.251    |    0.332   |   0.642  |     1     |   0.745   |
 
 ### What else can you do with this package?
 

inst/tinytest/test-_misc.R

@@ -49,5 +49,5 @@ if (AMR:::pkg_is_available("dplyr", min_version = "1.0.0")) {
 
 # we rely on "grouped_tbl" being a class of grouped tibbles, so implement a test that checks for this:
 if (AMR:::pkg_is_available("dplyr", min_version = "1.0.0")) {
-  expect_true(AMR:::is_null_or_grouped_tbl(example_isolates %>% group_by(hospital_id)))
+  expect_true(AMR:::is_null_or_grouped_tbl(example_isolates %>% group_by(ward)))
 }

inst/tinytest/test-bug_drug_combinations.R

@@ -30,7 +30,7 @@ expect_true(is.data.frame(format(b)))
 expect_true(is.data.frame(format(b, combine_IR = TRUE, add_ab_group = FALSE)))
 if (AMR:::pkg_is_available("dplyr", min_version = "1.0.0")) {
   expect_true(example_isolates %>% 
-                group_by(hospital_id) %>% 
+                group_by(ward) %>% 
                 bug_drug_combinations(FUN = mo_gramstain) %>% 
                 is.data.frame())
 }

inst/tinytest/test-count.R

@@ -49,7 +49,7 @@ expect_error(count_susceptible("test", minimum = "test"))
 expect_error(count_susceptible("test", as_percent = "test"))
 
 expect_error(count_df(c("A", "B", "C")))
-expect_error(count_df(example_isolates[, "date"]))
+expect_error(count_df(example_isolates[, "date", drop = TRUE]))
 
 if (AMR:::pkg_is_available("dplyr", min_version = "1.0.0")) {
   expect_equal(example_isolates %>% count_susceptible(AMC), 1433)
@@ -63,7 +63,7 @@ if (AMR:::pkg_is_available("dplyr", min_version = "1.0.0")) {
   
   # count of cases
   expect_equal(example_isolates %>%
-                 group_by(hospital_id) %>%
+                 group_by(ward) %>%
                  summarise(cipro = count_susceptible(CIP),
                            genta = count_susceptible(GEN),
                            combination = count_susceptible(CIP, GEN)) %>%
@@ -89,9 +89,9 @@ if (AMR:::pkg_is_available("dplyr", min_version = "1.0.0")) {
   )
   
   # grouping in rsi_calc_df() (= backbone of rsi_df())
-  expect_true("hospital_id" %in% (example_isolates %>% 
+  expect_true("ward" %in% (example_isolates %>% 
-                                    group_by(hospital_id) %>% 
+                                    group_by(ward) %>% 
-                                    select(hospital_id, AMX, CIP, gender) %>%
+                                    select(ward, AMX, CIP, gender) %>%
                                     rsi_df() %>% 
                                     colnames()))
 }

inst/tinytest/test-data.R

@@ -45,16 +45,16 @@ expect_false(any(is.na(microorganisms.codes$mo)))
 expect_true(all(dosage$ab %in% antibiotics$ab))
 expect_true(all(dosage$name %in% antibiotics$name))
 # check valid disks/MICs
-expect_false(any(is.na(as.mic(rsi_translation[which(rsi_translation$method == "MIC"), "breakpoint_S"]))))
+expect_false(any(is.na(as.mic(rsi_translation[which(rsi_translation$method == "MIC"), "breakpoint_S", drop = TRUE]))))
-expect_false(any(is.na(as.mic(rsi_translation[which(rsi_translation$method == "MIC"), "breakpoint_R"]))))
+expect_false(any(is.na(as.mic(rsi_translation[which(rsi_translation$method == "MIC"), "breakpoint_R", drop = TRUE]))))
-expect_false(any(is.na(as.disk(rsi_translation[which(rsi_translation$method == "DISK"), "breakpoint_S"]))))
+expect_false(any(is.na(as.disk(rsi_translation[which(rsi_translation$method == "DISK"), "breakpoint_S", drop = TRUE]))))
-expect_false(any(is.na(as.disk(rsi_translation[which(rsi_translation$method == "DISK"), "breakpoint_R"]))))
+expect_false(any(is.na(as.disk(rsi_translation[which(rsi_translation$method == "DISK"), "breakpoint_R", drop = TRUE]))))
 
 # antibiotic names must always be coercible to their original AB code
 expect_identical(as.ab(antibiotics$name), antibiotics$ab)
 
 # there should be no diacritics (i.e. non ASCII) characters in the datasets (CRAN policy)
-datasets <- data(package = "AMR", envir = asNamespace("AMR"))$results[, "Item"]
+datasets <- data(package = "AMR", envir = asNamespace("AMR"))$results[, "Item", drop = TRUE]
 for (i in seq_len(length(datasets))) {
   dataset <- get(datasets[i], envir = asNamespace("AMR"))
   expect_identical(class(dataset), "data.frame")
@@ -62,8 +62,8 @@ for (i in seq_len(length(datasets))) {
 }
 
 df <- AMR:::MO_lookup
-expect_true(nrow(df[which(df$prevalence == 1), ]) < nrow(df[which(df$prevalence == 2), ]))
+expect_true(nrow(df[which(df$prevalence == 1), , drop = FALSE]) < nrow(df[which(df$prevalence == 2), , drop = FALSE]))
-expect_true(nrow(df[which(df$prevalence == 2), ]) < nrow(df[which(df$prevalence == 3), ]))
+expect_true(nrow(df[which(df$prevalence == 2), , drop = FALSE]) < nrow(df[which(df$prevalence == 3), , drop = FALSE]))
 expect_true(all(c("mo", "fullname",
                   "kingdom", "phylum", "class", "order", "family", "genus", "species", "subspecies",
                   "rank", "ref", "species_id", "source", "prevalence", "snomed",

inst/tinytest/test-episode.R

@@ -49,7 +49,7 @@ if (AMR:::pkg_is_available("dplyr", min_version = "1.0.0")) {
       mutate(out = first_isolate(., include_unknown = TRUE, method = "episode-based", info = FALSE))
   )
   y <- example_isolates %>%
-    group_by(patient_id, mo) %>%
+    group_by(patient, mo) %>%
     mutate(out = is_new_episode(date, 365))
   
   expect_identical(which(x$out), which(y$out))

inst/tinytest/test-first_isolate.R

@@ -52,8 +52,8 @@ expect_equal(
     first_isolate(example_isolates,
                   col_mo = "mo",
                   col_date = "date",
-                  col_patient_id = "patient_id",
+                  col_patient_id = "patient",
-                  col_icu = "ward_icu",
+                  col_icu = example_isolates$ward == "ICU",
                   info = TRUE,
                   icu_exclude = TRUE),
     na.rm = TRUE),
@@ -67,7 +67,7 @@ x[random_rows, "specimen"] <- "Urine"
 expect_true(
   sum(first_isolate(x = x,
                     col_date = "date",
-                    col_patient_id = "patient_id",
+                    col_patient_id = "patient",
                     col_mo = "mo",
                     col_specimen = "specimen",
                     filter_specimen = "Urine",
@@ -76,11 +76,11 @@ expect_true(
 expect_true(
   sum(first_isolate(x = x,
                     col_date = "date",
-                    col_patient_id = "patient_id",
+                    col_patient_id = "patient",
                     col_mo = "mo",
                     col_specimen = "specimen",
                     filter_specimen = "Urine",
-                    col_icu = "ward_icu",
+                    col_icu = x$ward == "ICU",
                     icu_exclude = TRUE,
                     info = TRUE), na.rm = TRUE) < 1501)
 
@@ -89,7 +89,7 @@ test_iso <- example_isolates
 test_iso$specimen <- "test"
 expect_message(first_isolate(test_iso, 
                              "date", 
-                             "patient_id",
+                             "patient",
                              col_mo = "mo",
                              col_specimen = "specimen",
                              filter_specimen = "something_unexisting",
@@ -99,13 +99,13 @@ expect_message(first_isolate(test_iso,
 expect_message(first_isolate(example_isolates,
                              col_date = "date",
                              col_mo = "mo",
-                             col_patient_id = "patient_id",
+                             col_patient_id = "patient",
                              col_testcode = "gender",
                              testcodes_exclude = "M",
                              info = TRUE))
 
 # errors
-expect_error(first_isolate("date", "patient_id", col_mo = "mo"))
+expect_error(first_isolate("date", "patient", col_mo = "mo"))
 expect_error(first_isolate(example_isolates,
                            col_date = "non-existing col",
                            col_mo = "mo"))
@@ -116,12 +116,12 @@ if (AMR:::pkg_is_available("dplyr", min_version = "1.0.0")) {
                      mutate(mo = as.character(mo)) %>%
                      first_isolate(col_date = "date",
                                    col_mo = "mo",
-                                   col_patient_id = "patient_id",
+                                   col_patient_id = "patient",
                                    info = FALSE),
                    example_isolates %>%
                      first_isolate(col_date = "date",
                                    col_mo = "mo",
-                                   col_patient_id = "patient_id",
+                                   col_patient_id = "patient",
                                    info = FALSE))
   
   # support for WHONET
@@ -133,8 +133,8 @@ if (AMR:::pkg_is_available("dplyr", min_version = "1.0.0")) {
                    first_isolate(info = TRUE))
   
   # groups
-  x <- example_isolates %>% group_by(ward_icu) %>% mutate(first = first_isolate())
+  x <- example_isolates %>% group_by(ward) %>% mutate(first = first_isolate())
-  y <- example_isolates %>% group_by(ward_icu) %>% mutate(first = first_isolate(.))
+  y <- example_isolates %>% group_by(ward) %>% mutate(first = first_isolate(.))
   expect_identical(x, y)
   
 }
@@ -146,7 +146,7 @@ expect_equal(
   sum(
     first_isolate(x = df,
                   col_date = "date",
-                  col_patient_id = "patient_id",
+                  col_patient_id = "patient",
                   col_mo = "mo",
                   info = TRUE),
     na.rm = TRUE),

inst/tinytest/test-key_antimicrobials.R

@@ -33,4 +33,4 @@ expect_false(antimicrobials_equal("SSS", "SIS", ignore_I = FALSE, type = "keyant
 expect_true(antimicrobials_equal(".SS", "SI.", ignore_I = TRUE, type = "keyantimicrobials"))
 expect_false(antimicrobials_equal(".SS", "SI.", ignore_I = FALSE, type = "keyantimicrobials"))
 
-expect_warning(key_antimicrobials(example_isolates[rep(1, 10), ]))
+expect_warning(key_antimicrobials(example_isolates[rep(1, 10), , drop = FALSE]))

inst/tinytest/test-mdro.R

@@ -235,6 +235,6 @@ expect_warning(mdro(example_isolates,
 
 # print groups
 if (AMR:::pkg_is_available("dplyr", min_version = "1.0.0")) {
-  expect_stdout(x <- mdro(example_isolates %>% group_by(hospital_id), info = TRUE))
+  expect_stdout(x <- mdro(example_isolates %>% group_by(ward), info = TRUE))
-  expect_stdout(x <- mdro(example_isolates %>% group_by(hospital_id), guideline = custom, info = TRUE))
+  expect_stdout(x <- mdro(example_isolates %>% group_by(ward), guideline = custom, info = TRUE))
 }

inst/tinytest/test-mo.R

@@ -147,7 +147,8 @@ expect_identical(as.character(as.mo("S. salivarius",  Lancefield = TRUE)),  "B_S
 if (AMR:::pkg_is_available("dplyr", min_version = "1.0.0")) {
   # select with one column
   expect_identical(
-    example_isolates[1:10, ] %>%
+    example_isolates %>%
+      slice(1:10) %>%
       left_join_microorganisms() %>%
       select(genus) %>%
       as.mo() %>%
@@ -157,9 +158,11 @@ if (AMR:::pkg_is_available("dplyr", min_version = "1.0.0")) {
   
   # select with two columns
   expect_identical(
-    example_isolates[1:10, ] %>%
+    example_isolates %>%
+      slice(1:10) %>%
       pull(mo),
-    example_isolates[1:10, ] %>%
+    example_isolates %>%
+      slice(1:10) %>%
       left_join_microorganisms() %>%
       select(genus, species) %>%
       as.mo())

inst/tinytest/test-proportion.R

@@ -48,7 +48,7 @@ if (AMR:::pkg_is_available("dplyr", min_version = "1.0.0")) {
   
   # percentages
   expect_equal(example_isolates %>%
-                 group_by(hospital_id) %>%
+                 group_by(ward) %>%
                  summarise(R = proportion_R(CIP, as_percent = TRUE),
                            I = proportion_I(CIP, as_percent = TRUE),
                            S = proportion_S(CIP, as_percent = TRUE),
@@ -60,7 +60,7 @@ if (AMR:::pkg_is_available("dplyr", min_version = "1.0.0")) {
   
   # count of cases
   expect_equal(example_isolates %>%
-                 group_by(hospital_id) %>%
+                 group_by(ward) %>%
                  summarise(cipro_p = proportion_SI(CIP, as_percent = TRUE),
                            cipro_n = n_rsi(CIP),
                            genta_p = proportion_SI(GEN, as_percent = TRUE),
@@ -122,4 +122,4 @@ expect_warning(proportion_R(as.character(example_isolates$GEN)))
 expect_warning(proportion_I(as.character(example_isolates$GEN)))
 expect_warning(proportion_S(example_isolates$AMC, as.character(example_isolates$GEN)))
 expect_error(proportion_df(c("A", "B", "C")))
-expect_error(proportion_df(example_isolates[, "date"]))
+expect_error(proportion_df(example_isolates[, "date", drop = TRUE]))

man/AMR.Rd

@@ -35,19 +35,14 @@ This package can be used for:
 }
 \section{Reference Data Publicly Available}{
 
-All reference data sets (about microorganisms, antibiotics, R/SI interpretation, EUCAST rules, etc.) in this \code{AMR} package are publicly and freely available. We continually export our data sets to formats for use in R, SPSS, SAS, Stata and Excel. We also supply flat files that are machine-readable and suitable for input in any software program, such as laboratory information systems. Please find \href{https://msberends.github.io/AMR/articles/datasets.html}{all download links on our website}, which is automatically updated with every code change.
+All data sets in this \code{AMR} package (about microorganisms, antibiotics, R/SI interpretation, EUCAST rules, etc.) are publicly and freely available for download in the following formats: R, MS Excel, Apache Feather, Apache Parquet, SPSS, SAS, and Stata. We also provide tab-separated plain text files that are machine-readable and suitable for input in any software program, such as laboratory information systems. Please visit \href{https://msberends.github.io/AMR/articles/datasets.html}{our website for the download links}. The actual files are of course available on \href{https://github.com/msberends/AMR/tree/main/data-raw}{our GitHub repository}.
-}
-
-\section{Read more on Our Website!}{
-
-On our website \url{https://msberends.github.io/AMR/} you can find \href{https://msberends.github.io/AMR/articles/AMR.html}{a comprehensive tutorial} about how to conduct AMR data analysis, the \href{https://msberends.github.io/AMR/reference/}{complete documentation of all functions} and \href{https://msberends.github.io/AMR/articles/WHONET.html}{an example analysis using WHONET data}.
 }
 
 \section{Contact Us}{
 
-For suggestions, comments or questions, please contact us at:
+For suggestions, comments or questions, please contact us via:
 
-Matthijs S. Berends \cr
+Dr. Matthijs S. Berends \cr
 m.s.berends [at] umcg [dot] nl \cr
 University of Groningen
 Department of Medical Microbiology and Infection Prevention \cr

man/WHONET.Rd

@@ -5,7 +5,7 @@
 \alias{WHONET}
 \title{Data Set with 500 Isolates - WHONET Example}
 \format{
-A \link{data.frame} with 500 observations and 53 variables:
+A [tibble\link[tibble:tibble]{tibble::tibble} with 500 observations and 53 variables:
 \itemize{
 \item \verb{Identification number}\cr ID of the sample
 \item \verb{Specimen number}\cr ID of the specimen
@@ -41,12 +41,10 @@ WHONET
 \description{
 This example data set has the exact same structure as an export file from WHONET. Such files can be used with this package, as this example data set shows. The antibiotic results are from our \link{example_isolates} data set. All patient names are created using online surname generators and are only in place for practice purposes.
 }
-\section{Reference Data Publicly Available}{
+\details{
-
+Like all data sets in this package, this data set is publicly available for download in the following formats: R, MS Excel, Apache Feather, Apache Parquet, SPSS, SAS, and Stata. Please visit \href{https://msberends.github.io/AMR/articles/datasets.html}{our website for the download links}. The actual files are of course available on \href{https://github.com/msberends/AMR/tree/main/data-raw}{our GitHub repository}.
-All reference data sets (about microorganisms, antibiotics, R/SI interpretation, EUCAST rules, etc.) in this \code{AMR} package are publicly and freely available. We continually export our data sets to formats for use in R, SPSS, SAS, Stata and Excel. We also supply flat files that are machine-readable and suitable for input in any software program, such as laboratory information systems. Please find \href{https://msberends.github.io/AMR/articles/datasets.html}{all download links on our website}, which is automatically updated with every code change.
 }
-
 \examples{
-head(WHONET)
+WHONET
 }
 \keyword{datasets}

man/ab_property.Rd

@@ -104,7 +104,7 @@ European Commission Public Health PHARMACEUTICALS - COMMUNITY REGISTER: \url{htt
 
 \section{Reference Data Publicly Available}{
 
-All reference data sets (about microorganisms, antibiotics, R/SI interpretation, EUCAST rules, etc.) in this \code{AMR} package are publicly and freely available. We continually export our data sets to formats for use in R, SPSS, SAS, Stata and Excel. We also supply flat files that are machine-readable and suitable for input in any software program, such as laboratory information systems. Please find \href{https://msberends.github.io/AMR/articles/datasets.html}{all download links on our website}, which is automatically updated with every code change.
+All data sets in this \code{AMR} package (about microorganisms, antibiotics, R/SI interpretation, EUCAST rules, etc.) are publicly and freely available for download in the following formats: R, MS Excel, Apache Feather, Apache Parquet, SPSS, SAS, and Stata. We also provide tab-separated plain text files that are machine-readable and suitable for input in any software program, such as laboratory information systems. Please visit \href{https://msberends.github.io/AMR/articles/datasets.html}{our website for the download links}. The actual files are of course available on \href{https://github.com/msberends/AMR/tree/main/data-raw}{our GitHub repository}.
 }
 
 \examples{

man/age_groups.Rd

@@ -59,7 +59,7 @@ age_groups(ages, "children")
 if (require("dplyr")) {
   example_isolates \%>\%
     filter_first_isolate() \%>\%
-    filter(mo == as.mo("E. coli")) \%>\%
+    filter(mo == as.mo("Escherichia coli")) \%>\%
     group_by(age_group = age_groups(age)) \%>\%
     select(age_group, CIP) \%>\%
     ggplot_rsi(x = "age_group",

man/antibiotic_class_selectors.Rd

@@ -166,121 +166,153 @@ The \code{\link[=not_intrinsic_resistant]{not_intrinsic_resistant()}} function c
 
 \section{Reference Data Publicly Available}{
 
-All reference data sets (about microorganisms, antibiotics, R/SI interpretation, EUCAST rules, etc.) in this \code{AMR} package are publicly and freely available. We continually export our data sets to formats for use in R, SPSS, SAS, Stata and Excel. We also supply flat files that are machine-readable and suitable for input in any software program, such as laboratory information systems. Please find \href{https://msberends.github.io/AMR/articles/datasets.html}{all download links on our website}, which is automatically updated with every code change.
+All data sets in this \code{AMR} package (about microorganisms, antibiotics, R/SI interpretation, EUCAST rules, etc.) are publicly and freely available for download in the following formats: R, MS Excel, Apache Feather, Apache Parquet, SPSS, SAS, and Stata. We also provide tab-separated plain text files that are machine-readable and suitable for input in any software program, such as laboratory information systems. Please visit \href{https://msberends.github.io/AMR/articles/datasets.html}{our website for the download links}. The actual files are of course available on \href{https://github.com/msberends/AMR/tree/main/data-raw}{our GitHub repository}.
 }
 
 \examples{
 # `example_isolates` is a data set available in the AMR package.
 # See ?example_isolates.
-df <- example_isolates[ , c("hospital_id", "mo",
+example_isolates
-                            "AMP", "AMC", "TZP", "CXM", "CRO", "GEN",
-                            "TOB", "COL", "IPM", "MEM", "TEC", "VAN")]
 
 # base R ------------------------------------------------------------------
 
 # select columns 'IPM' (imipenem) and 'MEM' (meropenem)
-df[, carbapenems()]
+example_isolates[, carbapenems()]
 
 # select columns 'mo', 'AMK', 'GEN', 'KAN' and 'TOB'
-df[, c("mo", aminoglycosides())]
+example_isolates[, c("mo", aminoglycosides())]
 
 # select only antibiotic columns with DDDs for oral treatment
-df[, administrable_per_os()]
+example_isolates[, administrable_per_os()]
 
 # filter using any() or all()
-df[any(carbapenems() == "R"), ]
+example_isolates[any(carbapenems() == "R"), ]
-subset(df, any(carbapenems() == "R"))
+subset(example_isolates, any(carbapenems() == "R"))
 
 # filter on any or all results in the carbapenem columns (i.e., IPM, MEM):
-df[any(carbapenems()), ]
+example_isolates[any(carbapenems()), ]
-df[all(carbapenems()), ]
+example_isolates[all(carbapenems()), ]
 
 # filter with multiple antibiotic selectors using c()
-df[all(c(carbapenems(), aminoglycosides()) == "R"), ]
+example_isolates[all(c(carbapenems(), aminoglycosides()) == "R"), ]
 
 # filter + select in one go: get penicillins in carbapenems-resistant strains
-df[any(carbapenems() == "R"), penicillins()]
+example_isolates[any(carbapenems() == "R"), penicillins()]
 
 # You can combine selectors with '&' to be more specific. For example,
 # penicillins() would select benzylpenicillin ('peni G') and
 # administrable_per_os() would select erythromycin. Yet, when combined these
 # drugs are both omitted since benzylpenicillin is not administrable per os
 # and erythromycin is not a penicillin:
-df[, penicillins() & administrable_per_os()]
+example_isolates[, penicillins() & administrable_per_os()]
 
 # ab_selector() applies a filter in the `antibiotics` data set and is thus very
 # flexible. For instance, to select antibiotic columns with an oral DDD of at
 # least 1 gram:
-df[, ab_selector(oral_ddd > 1 & oral_units == "g")]
+example_isolates[, ab_selector(oral_ddd > 1 & oral_units == "g")]
 
 # dplyr -------------------------------------------------------------------
 \donttest{
 if (require("dplyr")) {
 
-  # get AMR for all aminoglycosides e.g., per hospital:
+  # get AMR for all aminoglycosides e.g., per ward:
-  df \%>\%
+  example_isolates \%>\%
-    group_by(hospital_id) \%>\% 
+    group_by(ward) \%>\% 
     summarise(across(aminoglycosides(), resistance))
     
+}
+if (require("dplyr")) {
+    
   # You can combine selectors with '&' to be more specific:
-  df \%>\%
+  example_isolates \%>\%
     select(penicillins() & administrable_per_os())
+    
+}
+if (require("dplyr")) {
   
   # get AMR for only drugs that matter - no intrinsic resistance:
-  df \%>\%
+  example_isolates \%>\%
     filter(mo_genus() \%in\% c("Escherichia", "Klebsiella")) \%>\% 
-    group_by(hospital_id) \%>\% 
+    group_by(ward) \%>\% 
     summarise(across(not_intrinsic_resistant(), resistance))
     
+}
+if (require("dplyr")) {
+    
   # get susceptibility for antibiotics whose name contains "trim":
-  df \%>\%
+  example_isolates \%>\%
     filter(first_isolate()) \%>\% 
-    group_by(hospital_id) \%>\% 
+    group_by(ward) \%>\% 
     summarise(across(ab_selector(name \%like\% "trim"), susceptibility))
+    
+}
+if (require("dplyr")) {
 
   # this will select columns 'IPM' (imipenem) and 'MEM' (meropenem):
-  df \%>\% 
+  example_isolates \%>\% 
     select(carbapenems())
     
+}
+if (require("dplyr")) {
+    
   # this will select columns 'mo', 'AMK', 'GEN', 'KAN' and 'TOB':
-  df \%>\% 
+  example_isolates \%>\% 
     select(mo, aminoglycosides())
     
+}
+if (require("dplyr")) {
+    
  # any() and all() work in dplyr's filter() too:
- df \%>\% 
+ example_isolates \%>\% 
     filter(any(aminoglycosides() == "R"),
            all(cephalosporins_2nd() == "R"))
     
+}
+if (require("dplyr")) {
+    
  # also works with c():
- df \%>\% 
+ example_isolates \%>\% 
     filter(any(c(carbapenems(), aminoglycosides()) == "R"))
     
+}
+if (require("dplyr")) {
+    
  # not setting any/all will automatically apply all():
- df \%>\% 
+ example_isolates \%>\% 
     filter(aminoglycosides() == "R")
     
+}
+if (require("dplyr")) {
+    
   # this will select columns 'mo' and all antimycobacterial drugs ('RIF'):
-  df \%>\% 
+  example_isolates \%>\% 
     select(mo, ab_class("mycobact"))
     
+}
+if (require("dplyr")) {
+    
   # get bug/drug combinations for only glycopeptides in Gram-positives:
-  df \%>\% 
+  example_isolates \%>\% 
     filter(mo_is_gram_positive()) \%>\% 
     select(mo, glycopeptides()) \%>\% 
     bug_drug_combinations() \%>\%
     format()
     
+}
+if (require("dplyr")) {
+
   data.frame(some_column = "some_value",
              J01CA01 = "S") \%>\%   # ATC code of ampicillin
     select(penicillins())         # only the 'J01CA01' column will be selected
     
-    
+}
+if (require("dplyr")) {
+
   # with recent versions of dplyr this is all equal:
-  x <- df[carbapenems() == "R", ]
+  x <- example_isolates[carbapenems() == "R", ]
-  y <- df \%>\% filter(carbapenems() == "R")
+  y <- example_isolates \%>\% filter(carbapenems() == "R")
-  z <- df \%>\% filter(if_all(carbapenems(), ~.x == "R"))
+  z <- example_isolates \%>\% filter(if_all(carbapenems(), ~.x == "R"))
-  identical(x, y)
+  identical(x, y) && identical(y, z)
-  identical(y, z)
 }
 }
 }

man/antibiotics.Rd

@@ -6,7 +6,7 @@
 \alias{antivirals}
 \title{Data Sets with 566 Antimicrobial Drugs}
 \format{
-\subsection{For the \link{antibiotics} data set: a \link{data.frame} with 464 observations and 14 variables:}{
+\subsection{For the \link{antibiotics} data set: a [tibble\link[tibble:tibble]{tibble::tibble} with 464 observations and 14 variables:}{
 \itemize{
 \item \code{ab}\cr Antibiotic ID as used in this package (such as \code{AMC}), using the official EARS-Net (European Antimicrobial Resistance Surveillance Network) codes where available
 \item \code{cid}\cr Compound ID as found in PubChem
@@ -25,7 +25,7 @@
 }
 }
 
-\subsection{For the \link{antivirals} data set: a \link{data.frame} with 102 observations and 9 variables:}{
+\subsection{For the \link{antivirals} data set: a [tibble\link[tibble:tibble]{tibble::tibble} with 102 observations and 9 variables:}{
 \itemize{
 \item \code{atc}\cr ATC codes (Anatomical Therapeutic Chemical) as defined by the WHOCC
 \item \code{cid}\cr Compound ID as found in PubChem
@@ -39,7 +39,7 @@
 }
 }
 
-An object of class \code{data.frame} with 102 rows and 9 columns.
+An object of class \code{tbl_df} (inherits from \code{tbl}, \code{data.frame}) with 102 rows and 9 columns.
 }
 \source{
 World Health Organization (WHO) Collaborating Centre for Drug Statistics Methodology (WHOCC): \url{https://www.whocc.no/atc_ddd_index/}
@@ -60,24 +60,9 @@ Properties that are based on an ATC code are only available when an ATC is avail
 Synonyms (i.e. trade names) were derived from the Compound ID (\code{cid}) and consequently only available where a CID is available.
 \subsection{Direct download}{
 
-These data sets are available as 'flat files' for use even without \R - you can find the files here:
+Like all data sets in this package, these data sets are publicly available for download in the following formats: R, MS Excel, Apache Feather, Apache Parquet, SPSS, SAS, and Stata. Please visit \href{https://msberends.github.io/AMR/articles/datasets.html}{our website for the download links}. The actual files are of course available on \href{https://github.com/msberends/AMR/tree/main/data-raw}{our GitHub repository}.
-\itemize{
-\item \url{https://github.com/msberends/AMR/raw/main/data-raw/antibiotics.txt}
-\item \url{https://github.com/msberends/AMR/raw/main/data-raw/antivirals.txt}
-}
-
-Files in \R format (with preserved data structure) can be found here:
-\itemize{
-\item \url{https://github.com/msberends/AMR/raw/main/data/antibiotics.rda}
-\item \url{https://github.com/msberends/AMR/raw/main/data/antivirals.rda}
 }
 }
-}
-\section{Reference Data Publicly Available}{
-
-All reference data sets (about microorganisms, antibiotics, R/SI interpretation, EUCAST rules, etc.) in this \code{AMR} package are publicly and freely available. We continually export our data sets to formats for use in R, SPSS, SAS, Stata and Excel. We also supply flat files that are machine-readable and suitable for input in any software program, such as laboratory information systems. Please find \href{https://msberends.github.io/AMR/articles/datasets.html}{all download links on our website}, which is automatically updated with every code change.
-}
-
 \section{WHOCC}{
 
 \if{html}{\figure{logo_who.png}{options: height="60" style=margin-bottom:"5"} \cr}
@@ -91,8 +76,8 @@ The WHOCC is located in Oslo at the Norwegian Institute of Public Health and fun
 }
 
 \examples{
-head(antibiotics)
+antibiotics
-head(antivirals)
+antivirals
 }
 \seealso{
 \link{microorganisms}, \link{intrinsic_resistant}

man/as.ab.Rd

@@ -61,7 +61,7 @@ The WHOCC is located in Oslo at the Norwegian Institute of Public Health and fun
 
 \section{Reference Data Publicly Available}{
 
-All reference data sets (about microorganisms, antibiotics, R/SI interpretation, EUCAST rules, etc.) in this \code{AMR} package are publicly and freely available. We continually export our data sets to formats for use in R, SPSS, SAS, Stata and Excel. We also supply flat files that are machine-readable and suitable for input in any software program, such as laboratory information systems. Please find \href{https://msberends.github.io/AMR/articles/datasets.html}{all download links on our website}, which is automatically updated with every code change.
+All data sets in this \code{AMR} package (about microorganisms, antibiotics, R/SI interpretation, EUCAST rules, etc.) are publicly and freely available for download in the following formats: R, MS Excel, Apache Feather, Apache Parquet, SPSS, SAS, and Stata. We also provide tab-separated plain text files that are machine-readable and suitable for input in any software program, such as laboratory information systems. Please visit \href{https://msberends.github.io/AMR/articles/datasets.html}{our website for the download links}. The actual files are of course available on \href{https://github.com/msberends/AMR/tree/main/data-raw}{our GitHub repository}.
 }
 
 \examples{

man/as.mic.Rd

@@ -103,9 +103,16 @@ as.rsi(x = as.mic(c(0.01, 2, 4, 8)),
 # plot MIC values, see ?plot
 plot(mic_data)
 plot(mic_data, mo = "E. coli", ab = "cipro")
-autoplot(mic_data, mo = "E. coli", ab = "cipro")
+
-autoplot(mic_data, mo = "E. coli", ab = "cipro", language = "nl") # Dutch
+if (require("ggplot2")) {
-autoplot(mic_data, mo = "E. coli", ab = "cipro", language = "uk") # Ukrainian
+  autoplot(mic_data, mo = "E. coli", ab = "cipro")
+}
+if (require("ggplot2")) {
+  autoplot(mic_data, mo = "E. coli", ab = "cipro", language = "nl") # Dutch
+}
+if (require("ggplot2")) {
+  autoplot(mic_data, mo = "E. coli", ab = "cipro", language = "uk") # Ukrainian
+}
 }
 \seealso{
 \code{\link[=as.rsi]{as.rsi()}}

man/as.mo.Rd

@@ -173,7 +173,7 @@ This package contains the complete taxonomic tree of almost all microorganisms (
 
 \section{Reference Data Publicly Available}{
 
-All reference data sets (about microorganisms, antibiotics, R/SI interpretation, EUCAST rules, etc.) in this \code{AMR} package are publicly and freely available. We continually export our data sets to formats for use in R, SPSS, SAS, Stata and Excel. We also supply flat files that are machine-readable and suitable for input in any software program, such as laboratory information systems. Please find \href{https://msberends.github.io/AMR/articles/datasets.html}{all download links on our website}, which is automatically updated with every code change.
+All data sets in this \code{AMR} package (about microorganisms, antibiotics, R/SI interpretation, EUCAST rules, etc.) are publicly and freely available for download in the following formats: R, MS Excel, Apache Feather, Apache Parquet, SPSS, SAS, and Stata. We also provide tab-separated plain text files that are machine-readable and suitable for input in any software program, such as laboratory information systems. Please visit \href{https://msberends.github.io/AMR/articles/datasets.html}{our website for the download links}. The actual files are of course available on \href{https://github.com/msberends/AMR/tree/main/data-raw}{our GitHub repository}.
 }
 
 \examples{

man/as.rsi.Rd

@@ -156,7 +156,7 @@ This AMR package honours this (new) insight. Use \code{\link[=susceptibility]{su
 
 \section{Reference Data Publicly Available}{
 
-All reference data sets (about microorganisms, antibiotics, R/SI interpretation, EUCAST rules, etc.) in this \code{AMR} package are publicly and freely available. We continually export our data sets to formats for use in R, SPSS, SAS, Stata and Excel. We also supply flat files that are machine-readable and suitable for input in any software program, such as laboratory information systems. Please find \href{https://msberends.github.io/AMR/articles/datasets.html}{all download links on our website}, which is automatically updated with every code change.
+All data sets in this \code{AMR} package (about microorganisms, antibiotics, R/SI interpretation, EUCAST rules, etc.) are publicly and freely available for download in the following formats: R, MS Excel, Apache Feather, Apache Parquet, SPSS, SAS, and Stata. We also provide tab-separated plain text files that are machine-readable and suitable for input in any software program, such as laboratory information systems. Please visit \href{https://msberends.github.io/AMR/articles/datasets.html}{our website for the download links}. The actual files are of course available on \href{https://github.com/msberends/AMR/tree/main/data-raw}{our GitHub repository}.
 }
 
 \examples{

man/availability.Rd

@@ -25,7 +25,7 @@ availability(example_isolates)
 \donttest{
 if (require("dplyr")) {
   example_isolates \%>\%
-    filter(mo == as.mo("E. coli")) \%>\%
+    filter(mo == as.mo("Escherichia coli")) \%>\%
     select_if(is.rsi) \%>\%
     availability()
 }

man/bug_drug_combinations.Rd

@@ -25,7 +25,7 @@ bug_drug_combinations(x, col_mo = NULL, FUN = mo_shortname, ...)
 )
 }
 \arguments{
-\item{x}{data with antibiotic columns, such as \code{amox}, \code{AMX} and \code{AMC}}
+\item{x}{a data set with antibiotic columns, such as \code{amox}, \code{AMX} and \code{AMC}}
 
 \item{col_mo}{column name of the IDs of the microorganisms (see \code{\link[=as.mo]{as.mo()}}), defaults to the first column of class \code{\link{mo}}. Values will be coerced using \code{\link[=as.mo]{as.mo()}}.}
 
@@ -74,7 +74,7 @@ bug_drug_combinations(example_isolates,
                       FUN = mo_gramstain)
                            
 bug_drug_combinations(example_isolates,
-                      FUN = function(x) ifelse(x == as.mo("E. coli"),
+                      FUN = function(x) ifelse(x == as.mo("Escherichia coli"),
                                                "E. coli",
                                                "Others"))
 }

man/catalogue_of_life.Rd

@@ -40,13 +40,13 @@ catalogue_of_life_version()
 mo_shortname("Chlamydophila psittaci")
 
 # Get any property from the entire taxonomic tree for all included species
-mo_class("E. coli")
+mo_class("Escherichia coli")
 
-mo_family("E. coli")
+mo_family("Escherichia coli")
 
-mo_gramstain("E. coli") # based on kingdom and phylum, see ?mo_gramstain
+mo_gramstain("Escherichia coli") # based on kingdom and phylum, see ?mo_gramstain
 
-mo_ref("E. coli")
+mo_ref("Escherichia coli")
 
 # Do not get mistaken - this package is about microorganisms
 mo_kingdom("C. elegans")

man/count.Rd

@@ -155,7 +155,7 @@ susceptibility(example_isolates$AMX) * n_rsi(example_isolates$AMX)
 \donttest{
 if (require("dplyr")) {
   example_isolates \%>\%
-    group_by(hospital_id) \%>\%
+    group_by(ward) \%>\%
     summarise(R  = count_R(CIP),
               I  = count_I(CIP),
               S  = count_S(CIP),
@@ -166,7 +166,7 @@ if (require("dplyr")) {
   # Number of available isolates for a whole antibiotic class
   # (i.e., in this data set columns GEN, TOB, AMK, KAN)
   example_isolates \%>\%
-    group_by(hospital_id) \%>\%
+    group_by(ward) \%>\%
     summarise(across(aminoglycosides(), n_rsi))
  
   # Count co-resistance between amoxicillin/clav acid and gentamicin,
@@ -188,8 +188,8 @@ if (require("dplyr")) {
  
   # It also supports grouping variables
   example_isolates \%>\%
-    select(hospital_id, AMX, CIP) \%>\%
+    select(ward, AMX, CIP) \%>\%
-    group_by(hospital_id) \%>\%
+    group_by(ward) \%>\%
     count_df(translate = FALSE)
 }
 }

man/custom_eucast_rules.Rd

@@ -7,7 +7,7 @@
 custom_eucast_rules(...)
 }
 \arguments{
-\item{...}{rules in \link[=`~`]{formula} notation, see \emph{Examples}}
+\item{...}{rules in \link[base:tilde]{formula} notation, see \emph{Examples}}
 }
 \value{
 A \link{list} containing the custom rules

man/dosage.Rd

@@ -5,7 +5,7 @@
 \alias{dosage}
 \title{Data Set with Treatment Dosages as Defined by EUCAST}
 \format{
-A \link{data.frame} with 169 observations and 9 variables:
+A [tibble\link[tibble:tibble]{tibble::tibble} with 169 observations and 9 variables:
 \itemize{
 \item \code{ab}\cr Antibiotic ID as used in this package (such as \code{AMC}), using the official EARS-Net (European Antimicrobial Resistance Surveillance Network) codes where available
 \item \code{name}\cr Official name of the antimicrobial agent as used by WHONET/EARS-Net or the WHO
@@ -25,14 +25,13 @@ dosage
 EUCAST breakpoints used in this package are based on the dosages in this data set. They can be retrieved with \code{\link[=eucast_dosage]{eucast_dosage()}}.
 }
 \details{
-\href{https://www.eucast.org/clinical_breakpoints/}{'EUCAST Clinical Breakpoint Tables' v11.0} (2021) are based on the dosages in this data set.
+This data set is based on \href{https://www.eucast.org/clinical_breakpoints/}{'EUCAST Clinical Breakpoint Tables' v11.0} (2021).
-}
+\subsection{Direct download}{
-\section{Reference Data Publicly Available}{
 
-All reference data sets (about microorganisms, antibiotics, R/SI interpretation, EUCAST rules, etc.) in this \code{AMR} package are publicly and freely available. We continually export our data sets to formats for use in R, SPSS, SAS, Stata and Excel. We also supply flat files that are machine-readable and suitable for input in any software program, such as laboratory information systems. Please find \href{https://msberends.github.io/AMR/articles/datasets.html}{all download links on our website}, which is automatically updated with every code change.
+Like all data sets in this package, this data set is publicly available for download in the following formats: R, MS Excel, Apache Feather, Apache Parquet, SPSS, SAS, and Stata. Please visit \href{https://msberends.github.io/AMR/articles/datasets.html}{our website for the download links}. The actual files are of course available on \href{https://github.com/msberends/AMR/tree/main/data-raw}{our GitHub repository}.
+}
 }
-
 \examples{
-head(dosage)
+dosage
 }
 \keyword{datasets}

man/eucast_rules.Rd

@@ -36,7 +36,7 @@ eucast_rules(
 eucast_dosage(ab, administration = "iv", version_breakpoints = 11)
 }
 \arguments{
-\item{x}{data with antibiotic columns, such as \code{amox}, \code{AMX} and \code{AMC}}
+\item{x}{a data set with antibiotic columns, such as \code{amox}, \code{AMX} and \code{AMC}}
 
 \item{col_mo}{column name of the IDs of the microorganisms (see \code{\link[=as.mo]{as.mo()}}), defaults to the first column of class \code{\link{mo}}. Values will be coerced using \code{\link[=as.mo]{as.mo()}}.}
 
@@ -83,26 +83,26 @@ Custom rules can be created using \code{\link[=custom_eucast_rules]{custom_eucas
                          AMC == "I" & genus == "Klebsiella" ~ aminopenicillins == "I")
 
 eucast_rules(example_isolates, rules = "custom", custom_rules = x, info = FALSE)
-#> # A tibble: 2,000 x 49
+#> # A tibble: 2,000 x 46
-#>    date       hospit~1 ward_~2 ward_~3 ward_~4   age gender patie~5 mo          
+#>    date       patient   age gender ward     mo           PEN   OXA   FLC   AMX  
-#>  * <date>     <fct>    <lgl>   <lgl>   <lgl>   <dbl> <chr>  <chr>   <mo>        
+#>  * <date>     <chr>   <dbl> <chr>  <chr>    <mo>         <rsi> <rsi> <rsi> <rsi>
-#>  1 2002-01-02 D        FALSE   TRUE    FALSE      65 F      A77334  B_ESCHR_COLI
+#>  1 2002-01-02 A77334     65 F      Clinical B_ESCHR_COLI R     NA    NA    NA   
-#>  2 2002-01-03 D        FALSE   TRUE    FALSE      65 F      A77334  B_ESCHR_COLI
+#>  2 2002-01-03 A77334     65 F      Clinical B_ESCHR_COLI R     NA    NA    NA   
-#>  3 2002-01-07 B        TRUE    FALSE   FALSE      45 F      067927  B_STPHY_EPDR
+#>  3 2002-01-07 067927     45 F      ICU      B_STPHY_EPDR R     NA    R     NA   
-#>  4 2002-01-07 B        TRUE    FALSE   FALSE      45 F      067927  B_STPHY_EPDR
+#>  4 2002-01-07 067927     45 F      ICU      B_STPHY_EPDR R     NA    R     NA   
-#>  5 2002-01-13 B        TRUE    FALSE   FALSE      45 F      067927  B_STPHY_EPDR
+#>  5 2002-01-13 067927     45 F      ICU      B_STPHY_EPDR R     NA    R     NA   
-#>  6 2002-01-13 B        TRUE    FALSE   FALSE      45 F      067927  B_STPHY_EPDR
+#>  6 2002-01-13 067927     45 F      ICU      B_STPHY_EPDR R     NA    R     NA   
-#>  7 2002-01-14 D        FALSE   TRUE    FALSE      78 M      462729  B_STPHY_AURS
+#>  7 2002-01-14 462729     78 M      Clinical B_STPHY_AURS R     NA    S     R    
-#>  8 2002-01-14 D        FALSE   TRUE    FALSE      78 M      462729  B_STPHY_AURS
+#>  8 2002-01-14 462729     78 M      Clinical B_STPHY_AURS R     NA    S     R    
-#>  9 2002-01-16 B        TRUE    FALSE   FALSE      45 F      067927  B_STPHY_EPDR
+#>  9 2002-01-16 067927     45 F      ICU      B_STPHY_EPDR R     NA    R     NA   
-#> 10 2002-01-17 B        TRUE    FALSE   FALSE      79 F      858515  B_STPHY_EPDR
+#> 10 2002-01-17 858515     79 F      ICU      B_STPHY_EPDR R     NA    S     NA   
-#> # ... with 1,990 more rows, 40 more variables: PEN <rsi>, OXA <rsi>, FLC <rsi>,
+#> # ... with 1,990 more rows, and 36 more variables: AMC <rsi>, AMP <rsi>,
-#> #   AMX <rsi>, AMC <rsi>, AMP <rsi>, TZP <rsi>, CZO <rsi>, FEP <rsi>,
+#> #   TZP <rsi>, CZO <rsi>, FEP <rsi>, CXM <rsi>, FOX <rsi>, CTX <rsi>,
-#> #   CXM <rsi>, FOX <rsi>, CTX <rsi>, CAZ <rsi>, CRO <rsi>, GEN <rsi>,
+#> #   CAZ <rsi>, CRO <rsi>, GEN <rsi>, TOB <rsi>, AMK <rsi>, KAN <rsi>,
-#> #   TOB <rsi>, AMK <rsi>, KAN <rsi>, TMP <rsi>, SXT <rsi>, NIT <rsi>,
+#> #   TMP <rsi>, SXT <rsi>, NIT <rsi>, FOS <rsi>, LNZ <rsi>, CIP <rsi>,
-#> #   FOS <rsi>, LNZ <rsi>, CIP <rsi>, MFX <rsi>, VAN <rsi>, TEC <rsi>,
+#> #   MFX <rsi>, VAN <rsi>, TEC <rsi>, TCY <rsi>, TGC <rsi>, DOX <rsi>,
-#> #   TCY <rsi>, TGC <rsi>, DOX <rsi>, ERY <rsi>, CLI <rsi>, AZM <rsi>,
+#> #   ERY <rsi>, CLI <rsi>, AZM <rsi>, IPM <rsi>, MEM <rsi>, MTR <rsi>,
-#> #   IPM <rsi>, MEM <rsi>, MTR <rsi>, CHL <rsi>, COL <rsi>, MUP <rsi>, ...
+#> #   CHL <rsi>, COL <rsi>, MUP <rsi>, RIF <rsi>
 #> # i Use `print(n = ...)` to see more rows, and `colnames()` to see all variable names
 }\if{html}{\out{</div>}}
 }
@@ -131,7 +131,7 @@ Amikacin (\code{AMK}, \href{https://www.whocc.no/atc_ddd_index/?code=J01GB06&sho
 
 \section{Reference Data Publicly Available}{
 
-All reference data sets (about microorganisms, antibiotics, R/SI interpretation, EUCAST rules, etc.) in this \code{AMR} package are publicly and freely available. We continually export our data sets to formats for use in R, SPSS, SAS, Stata and Excel. We also supply flat files that are machine-readable and suitable for input in any software program, such as laboratory information systems. Please find \href{https://msberends.github.io/AMR/articles/datasets.html}{all download links on our website}, which is automatically updated with every code change.
+All data sets in this \code{AMR} package (about microorganisms, antibiotics, R/SI interpretation, EUCAST rules, etc.) are publicly and freely available for download in the following formats: R, MS Excel, Apache Feather, Apache Parquet, SPSS, SAS, and Stata. We also provide tab-separated plain text files that are machine-readable and suitable for input in any software program, such as laboratory information systems. Please visit \href{https://msberends.github.io/AMR/articles/datasets.html}{our website for the download links}. The actual files are of course available on \href{https://github.com/msberends/AMR/tree/main/data-raw}{our GitHub repository}.
 }
 
 \examples{

man/example_isolates.Rd

@@ -5,32 +5,27 @@
 \alias{example_isolates}
 \title{Data Set with 2,000 Example Isolates}
 \format{
-A \link{data.frame} with 2,000 observations and 49 variables:
+A [tibble\link[tibble:tibble]{tibble::tibble} with 2,000 observations and 46 variables:
 \itemize{
-\item \code{date}\cr date of receipt at the laboratory
+\item \code{date}\cr Date of receipt at the laboratory
-\item \code{hospital_id}\cr ID of the hospital, from A to D
+\item \code{patient}\cr ID of the patient
-\item \code{ward_icu}\cr \link{logical} to determine if ward is an intensive care unit
+\item \code{age}\cr Age of the patient
-\item \code{ward_clinical}\cr \link{logical} to determine if ward is a regular clinical ward
+\item \code{gender}\cr Gender of the patient, either "F" or "M"
-\item \code{ward_outpatient}\cr \link{logical} to determine if ward is an outpatient clinic
+\item \code{ward}\cr Ward type where the patient was admitted, either "Clinical", "ICU" or "Outpatient"
-\item \code{age}\cr age of the patient
+\item \code{mo}\cr ID of microorganism created with \code{\link[=as.mo]{as.mo()}}, see also the \link{microorganisms} data set
-\item \code{gender}\cr gender of the patient
+\item \code{PEN:RIF}\cr 40 different antibiotics with class \code{\link{rsi}} (see \code{\link[=as.rsi]{as.rsi()}}); these column names occur in the \link{antibiotics} data set and can be translated with \code{\link[=set_ab_names]{set_ab_names()}} or \code{\link[=ab_name]{ab_name()}}
-\item \code{patient_id}\cr ID of the patient
-\item \code{mo}\cr ID of microorganism created with \code{\link[=as.mo]{as.mo()}}, see also \link{microorganisms}
-\item \code{PEN:RIF}\cr 40 different antibiotics with class \code{\link{rsi}} (see \code{\link[=as.rsi]{as.rsi()}}); these column names occur in the \link{antibiotics} data set and can be translated with \code{\link[=ab_name]{ab_name()}}
 }
 }
 \usage{
 example_isolates
 }
 \description{
-A data set containing 2,000 microbial isolates with their full antibiograms. The data set reflects reality and can be used to practice AMR data analysis. For examples, please read \href{https://msberends.github.io/AMR/articles/AMR.html}{the tutorial on our website}.
+A data set containing 2,000 microbial isolates with their full antibiograms. This data set contains randomised fictitious data, but reflects reality and can be used to practise AMR data analysis. For examples, please read \href{https://msberends.github.io/AMR/articles/AMR.html}{the tutorial on our website}.
 }
-\section{Reference Data Publicly Available}{
+\details{
-
+Like all data sets in this package, this data set is publicly available for download in the following formats: R, MS Excel, Apache Feather, Apache Parquet, SPSS, SAS, and Stata. Please visit \href{https://msberends.github.io/AMR/articles/datasets.html}{our website for the download links}. The actual files are of course available on \href{https://github.com/msberends/AMR/tree/main/data-raw}{our GitHub repository}.
-All reference data sets (about microorganisms, antibiotics, R/SI interpretation, EUCAST rules, etc.) in this \code{AMR} package are publicly and freely available. We continually export our data sets to formats for use in R, SPSS, SAS, Stata and Excel. We also supply flat files that are machine-readable and suitable for input in any software program, such as laboratory information systems. Please find \href{https://msberends.github.io/AMR/articles/datasets.html}{all download links on our website}, which is automatically updated with every code change.
 }
-
 \examples{
-head(example_isolates)
+example_isolates
 }
 \keyword{datasets}

man/example_isolates_unclean.Rd

@@ -5,7 +5,7 @@
 \alias{example_isolates_unclean}
 \title{Data Set with Unclean Data}
 \format{
-A \link{data.frame} with 3,000 observations and 8 variables:
+A [tibble\link[tibble:tibble]{tibble::tibble} with 3,000 observations and 8 variables:
 \itemize{
 \item \code{patient_id}\cr ID of the patient
 \item \code{date}\cr date of receipt at the laboratory
@@ -20,12 +20,10 @@ example_isolates_unclean
 \description{
 A data set containing 3,000 microbial isolates that are not cleaned up and consequently not ready for AMR data analysis. This data set can be used for practice.
 }
-\section{Reference Data Publicly Available}{
+\details{
-
+Like all data sets in this package, this data set is publicly available for download in the following formats: R, MS Excel, Apache Feather, Apache Parquet, SPSS, SAS, and Stata. Please visit \href{https://msberends.github.io/AMR/articles/datasets.html}{our website for the download links}. The actual files are of course available on \href{https://github.com/msberends/AMR/tree/main/data-raw}{our GitHub repository}.
-All reference data sets (about microorganisms, antibiotics, R/SI interpretation, EUCAST rules, etc.) in this \code{AMR} package are publicly and freely available. We continually export our data sets to formats for use in R, SPSS, SAS, Stata and Excel. We also supply flat files that are machine-readable and suitable for input in any software program, such as laboratory information systems. Please find \href{https://msberends.github.io/AMR/articles/datasets.html}{all download links on our website}, which is automatically updated with every code change.
 }
-
 \examples{
-head(example_isolates_unclean)
+example_isolates_unclean
 }
 \keyword{datasets}

man/first_isolate.Rd

@@ -58,7 +58,7 @@ filter_first_isolate(
 
 \item{col_specimen}{column name of the specimen type or group}
 
-\item{col_icu}{column name of the logicals (\code{TRUE}/\code{FALSE}) whether a ward or department is an Intensive Care Unit (ICU)}
+\item{col_icu}{column name of the logicals (\code{TRUE}/\code{FALSE}) whether a ward or department is an Intensive Care Unit (ICU). This can also be a \link{logical} vector with the same length as rows in \code{x}.}
 
 \item{col_keyantimicrobials}{(only useful when \code{method = "phenotype-based"}) column name of the key antimicrobials to determine first isolates, see \code{\link[=key_antimicrobials]{key_antimicrobials()}}. Defaults to the first column that starts with 'key' followed by 'ab' or 'antibiotics' or 'antimicrobials' (case insensitive). Use \code{col_keyantimicrobials = FALSE} to prevent this. Can also be the output of \code{\link[=key_antimicrobials]{key_antimicrobials()}}.}
 
@@ -87,7 +87,7 @@ filter_first_isolate(
 \item{...}{arguments passed on to \code{\link[=first_isolate]{first_isolate()}} when using \code{\link[=filter_first_isolate]{filter_first_isolate()}}, otherwise arguments passed on to \code{\link[=key_antimicrobials]{key_antimicrobials()}} (such as \code{universal}, \code{gram_negative}, \code{gram_positive})}
 }
 \value{
-A \code{\link{logical}} vector
+A \link{logical} vector
 }
 \description{
 Determine first isolates of all microorganisms of every patient per episode and (if needed) per specimen type. These functions support all four methods as summarised by Hindler \emph{et al.} in 2007 (\doi{10.1086/511864}). To determine patient episodes not necessarily based on microorganisms, use \code{\link[=is_new_episode]{is_new_episode()}} that also supports grouping with the \code{dplyr} package.
@@ -177,36 +177,22 @@ if (require("dplyr")) {
   # filter on first isolates using dplyr:
   example_isolates \%>\%
     filter(first_isolate())
+    
+}
+if (require("dplyr")) {
  
   # short-hand version:
   example_isolates \%>\%
     filter_first_isolate(info = FALSE)
     
+}
+if (require("dplyr")) {
+    
  # flag the first isolates per group:
  example_isolates \%>\%
-   group_by(hospital_id) \%>\%
+   group_by(ward) \%>\%
    mutate(first = first_isolate()) \%>\%
-   select(hospital_id, date, patient_id, mo, first)
+   select(ward, date, patient, mo, first)
-  
-  # now let's see if first isolates matter:
-  A <- example_isolates \%>\%
-    group_by(hospital_id) \%>\%
-    summarise(count = n_rsi(GEN),            # gentamicin availability
-              resistance = resistance(GEN))  # gentamicin resistance
- 
-  B <- example_isolates \%>\%
-    filter_first_isolate() \%>\%               # the 1st isolate filter
-    group_by(hospital_id) \%>\%
-    summarise(count = n_rsi(GEN),            # gentamicin availability
-              resistance = resistance(GEN))  # gentamicin resistance
- 
-  # Have a look at A and B.
-  A
-  B
-  
-  # B is more reliable because every isolate is counted only once.
-  # Gentamicin resistance in hospital D appears to be 4.2\% higher than
-  # when you (erroneously) would have used all isolates for analysis.
 }
 }
 }

man/get_episode.Rd

@@ -54,26 +54,34 @@ if (require("dplyr")) {
   # episodes based on any (combination of) grouping variables:
   df \%>\%
     mutate(condition = sample(x = c("A", "B", "C"), 
-                              size = 2000,
+                              size = 200,
                               replace = TRUE)) \%>\% 
     group_by(condition) \%>\%
     mutate(new_episode = is_new_episode(date, 365)) \%>\%
-    select(patient_id, date, condition, new_episode)
+    select(patient, date, condition, new_episode)
+    
+}
+if (require("dplyr")) {
     
   df \%>\%
-    group_by(hospital_id, patient_id) \%>\%
+    group_by(ward, patient) \%>\%
     transmute(date, 
-              patient_id,
+              patient,
               new_index = get_episode(date, 60),
               new_logical = is_new_episode(date, 60))
+    
+}
+if (require("dplyr")) {
   
   df \%>\%
-    group_by(hospital_id) \%>\% 
+    group_by(ward) \%>\% 
-    summarise(n_patients = n_distinct(patient_id),
+    summarise(n_patients = n_distinct(patient),
               n_episodes_365 = sum(is_new_episode(date, episode_days = 365)),
               n_episodes_60  = sum(is_new_episode(date, episode_days = 60)),
               n_episodes_30  = sum(is_new_episode(date, episode_days = 30)))
     
+}
+if (require("dplyr")) {
     
   # grouping on patients and microorganisms leads to the same
   # results as first_isolate() when using 'episode-based':
@@ -82,16 +90,19 @@ if (require("dplyr")) {
                          method = "episode-based")
     
   y <- df \%>\%
-    group_by(patient_id, mo) \%>\%
+    group_by(patient, mo) \%>\%
     filter(is_new_episode(date, 365)) \%>\%
     ungroup()
 
   identical(x, y)
+    
+}
+if (require("dplyr")) {
   
   # but is_new_episode() has a lot more flexibility than first_isolate(),
   # since you can now group on anything that seems relevant:
   df \%>\%
-    group_by(patient_id, mo, hospital_id, ward_icu) \%>\%
+    group_by(patient, mo, ward) \%>\%
     mutate(flag_episode = is_new_episode(date, 365)) \%>\%
     select(group_vars(.), flag_episode)
 }

man/ggplot_rsi.Rd

@@ -142,11 +142,14 @@ At default, the names of antibiotics will be shown on the plots using \code{\lin
 }
 \examples{
 \donttest{
-if (require("ggplot2") & require("dplyr")) {
+if (require("ggplot2") && require("dplyr")) {
  
   # get antimicrobial results for drugs against a UTI:
   ggplot(example_isolates \%>\% select(AMX, NIT, FOS, TMP, CIP)) +
     geom_rsi()
+    
+}
+if (require("ggplot2") && require("dplyr")) {
  
   # prettify the plot using some additional functions:
   df <- example_isolates \%>\% select(AMX, NIT, FOS, TMP, CIP)
@@ -156,16 +159,25 @@ if (require("ggplot2") & require("dplyr")) {
     scale_rsi_colours() +
     labels_rsi_count() +
     theme_rsi()
+    
+}
+if (require("ggplot2") && require("dplyr")) {
  
   # or better yet, simplify this using the wrapper function - a single command:
   example_isolates \%>\%
     select(AMX, NIT, FOS, TMP, CIP) \%>\%
     ggplot_rsi()
+    
+}
+if (require("ggplot2") && require("dplyr")) {
  
   # get only proportions and no counts:
   example_isolates \%>\%
     select(AMX, NIT, FOS, TMP, CIP) \%>\%
     ggplot_rsi(datalabels = FALSE)
+    
+}
+if (require("ggplot2") && require("dplyr")) {
  
   # add other ggplot2 arguments as you like:
   example_isolates \%>\%
@@ -175,11 +187,17 @@ if (require("ggplot2") & require("dplyr")) {
                size = 1,
                linetype = 2,
                alpha = 0.25)
+    
+}
+if (require("ggplot2") && require("dplyr")) {
 
   # you can alter the colours with colour names:
   example_isolates \%>\%
     select(AMX) \%>\%
     ggplot_rsi(colours = c(SI = "yellow"))
+    
+}
+if (require("ggplot2") && require("dplyr")) {
 
   # but you can also use the built-in colour-blind friendly colours for
   # your plots, where "S" is green, "I" is yellow and "R" is red:
@@ -189,34 +207,42 @@ if (require("ggplot2") & require("dplyr")) {
     ggplot() +
     geom_col(aes(x = x, y = y, fill = z)) +
     scale_rsi_colours(Value4 = "S", Value5 = "I", Value6 = "R")
+    
+}
+if (require("ggplot2") && require("dplyr")) {
   
   # resistance of ciprofloxacine per age group
   example_isolates \%>\%
     mutate(first_isolate = first_isolate()) \%>\%
     filter(first_isolate == TRUE,
-           mo == as.mo("E. coli")) \%>\%
+           mo == as.mo("Escherichia coli")) \%>\%
     # age_groups() is also a function in this AMR package:
     group_by(age_group = age_groups(age)) \%>\%
     select(age_group, CIP) \%>\%
     ggplot_rsi(x = "age_group")
+    
+}
+if (require("ggplot2") && require("dplyr")) {
   
   # a shorter version which also adjusts data label colours:
   example_isolates \%>\%
     select(AMX, NIT, FOS, TMP, CIP) \%>\%
     ggplot_rsi(colours = FALSE)
-
+    
+}
+if (require("ggplot2") && require("dplyr")) {
 
   # it also supports groups (don't forget to use the group var on `x` or `facet`):
   example_isolates \%>\%
-    filter(mo_is_gram_negative()) \%>\% 
+    filter(mo_is_gram_negative(), ward != "Outpatient") \%>\% 
     # select only UTI-specific drugs
-    select(hospital_id, AMX, NIT, FOS, TMP, CIP) \%>\%
+    select(ward, AMX, NIT, FOS, TMP, CIP) \%>\%
-    group_by(hospital_id) \%>\%
+    group_by(ward) \%>\%
-    ggplot_rsi(x = "hospital_id",
+    ggplot_rsi(x = "ward",
                facet = "antibiotic",
                nrow = 1,
-               title = "AMR of Anti-UTI Drugs Per Hospital",
+               title = "AMR of Anti-UTI Drugs Per Ward",
-               x.title = "Hospital",
+               x.title = "Ward",
                datalabels = FALSE)
 }
 }

man/intrinsic_resistant.Rd

@@ -5,7 +5,7 @@
 \alias{intrinsic_resistant}
 \title{Data Set with Bacterial Intrinsic Resistance}
 \format{
-A \link{data.frame} with 134,956 observations and 2 variables:
+A [tibble\link[tibble:tibble]{tibble::tibble} with 134,956 observations and 2 variables:
 \itemize{
 \item \code{mo}\cr Microorganism ID
 \item \code{ab}\cr Antibiotic ID
@@ -18,16 +18,15 @@ intrinsic_resistant
 Data set containing defined intrinsic resistance by EUCAST of all bug-drug combinations.
 }
 \details{
-The repository of this \code{AMR} package contains a file comprising this data set with full taxonomic and antibiotic names: \url{https://github.com/msberends/AMR/blob/main/data-raw/intrinsic_resistant.txt}. This file \strong{allows for machine reading EUCAST guidelines about intrinsic resistance}, which is almost impossible with the Excel and PDF files distributed by EUCAST. The file is updated automatically.
-
 This data set is based on \href{https://www.eucast.org/expert_rules_and_expected_phenotypes/}{'EUCAST Expert Rules' and 'EUCAST Intrinsic Resistance and Unusual Phenotypes' v3.3} (2021).
-}
+\subsection{Direct download}{
-\section{Reference Data Publicly Available}{
 
-All reference data sets (about microorganisms, antibiotics, R/SI interpretation, EUCAST rules, etc.) in this \code{AMR} package are publicly and freely available. We continually export our data sets to formats for use in R, SPSS, SAS, Stata and Excel. We also supply flat files that are machine-readable and suitable for input in any software program, such as laboratory information systems. Please find \href{https://msberends.github.io/AMR/articles/datasets.html}{all download links on our website}, which is automatically updated with every code change.
+Like all data sets in this package, this data set is publicly available for download in the following formats: R, MS Excel, Apache Feather, Apache Parquet, SPSS, SAS, and Stata. Please visit \href{https://msberends.github.io/AMR/articles/datasets.html}{our website for the download links}. The actual files are of course available on \href{https://github.com/msberends/AMR/tree/main/data-raw}{our GitHub repository}.
-}
 
+They \strong{allow for machine reading EUCAST and CLSI guidelines}, which is almost impossible with the MS Excel and PDF files distributed by EUCAST and CLSI.
+}
+}
 \examples{
-head(intrinsic_resistant)
+intrinsic_resistant
 }
 \keyword{datasets}