1
0
mirror of https://github.com/msberends/AMR.git synced 2026-05-14 05:10:46 +02:00
Files
AMR/tests/testthat/test-data.R
Matthijs Berends 24f24ecaf8 Generalise interpretive rules for multi-guideline support (#268) (#283)
* Generalise interpretive rules for multi-guideline support (#268)

- Rename data-raw/eucast_rules.tsv → interpretive_rules.tsv; add rule.provider
  column (value: "EUCAST") to distinguish future CLSI rows
- Rename EUCAST_RULES_DF → INTERPRETIVE_RULES_DF in _pre_commit_checks.R;
  filter by rule.provider == guideline when applying rules in interpretive_rules()
- Rename custom_eucast_rules() → custom_interpretive_rules() with new S3 class
  "custom_interpretive_rules"; old function becomes a deprecated wrapper in
  zz_deprecated.R; backward-compat S3 dispatch shims added for old class
- Remove stop_if(guideline == "CLSI", ...) so clsi_rules() no longer errors
- Add .onLoad shim in zzz.R to create INTERPRETIVE_RULES_DF from EUCAST_RULES_DF
  for transitional compatibility until sysdata.rda is regenerated

https://claude.ai/code/session_01D46BTsfJSPo3HnLWp3PRkP

* Fix namespace load failure: remove assignInNamespace from .onLoad (#268)

assignInNamespace cannot add NEW bindings to a locked package namespace
(R locks namespace bindings before .onLoad runs). Replace the .onLoad
shim with a runtime fallback inside interpretive_rules(): if
INTERPRETIVE_RULES_DF is absent (pre-regeneration sysdata.rda), derive
it from EUCAST_RULES_DF by adding the rule.provider column. This also
fixes the screening_abx line to reuse the already-resolved
interpretive_rules_df_total instead of a bare INTERPRETIVE_RULES_DF
reference.

https://claude.ai/code/session_01D46BTsfJSPo3HnLWp3PRkP

* fixes

* fixes

---------

Co-authored-by: Claude <noreply@anthropic.com>
2026-05-01 18:38:51 +01:00

144 lines
6.8 KiB
R

# ==================================================================== #
# TITLE: #
# AMR: An R Package for Working with Antimicrobial Resistance Data #
# #
# SOURCE CODE: #
# https://github.com/msberends/AMR #
# #
# PLEASE CITE THIS SOFTWARE AS: #
# Berends MS, Luz CF, Friedrich AW, et al. (2022). #
# AMR: An R Package for Working with Antimicrobial Resistance Data. #
# Journal of Statistical Software, 104(3), 1-31. #
# https://doi.org/10.18637/jss.v104.i03 #
# #
# Developed at the University of Groningen and the University Medical #
# Center Groningen in The Netherlands, in collaboration with many #
# colleagues from around the world, see our website. #
# #
# This R package is free software; you can freely use and distribute #
# it for both personal and commercial purposes under the terms of the #
# GNU General Public License version 2.0 (GNU GPL-2), as published by #
# the Free Software Foundation. #
# We created this package for both routine data analysis and academic #
# research and it was publicly released in the hope that it will be #
# useful, but it comes WITHOUT ANY WARRANTY OR LIABILITY. #
# #
# Visit our website for the full manual and a complete tutorial about #
# how to conduct AMR data analysis: https://amr-for-r.org #
# ==================================================================== #
test_that("test-data.R", {
skip_on_cran()
# IDs should always be unique
expect_identical(nrow(microorganisms), length(unique(microorganisms$mo)))
expect_identical(class(microorganisms$mo), c("mo", "character"))
expect_identical(nrow(antimicrobials), length(unique(AMR::antimicrobials$ab)))
expect_identical(class(AMR::antimicrobials$ab), c("ab", "character"))
expect_identical(
nrow(antimicrobials[!is.na(antimicrobials$cid), ]),
length(unique(AMR::antimicrobials$cid[!is.na(antimicrobials$cid)]))
)
# check cross table reference
expect_true(all(microorganisms.codes$mo %in% microorganisms$mo))
expect_true(all(example_isolates$mo %in% microorganisms$mo))
expect_true(all(microorganisms.groups$mo %in% microorganisms$mo))
expect_true(all(microorganisms.groups$mo_group %in% microorganisms$mo))
expect_true(all(clinical_breakpoints$mo %in% microorganisms$mo))
expect_true(all(clinical_breakpoints$ab %in% AMR::antimicrobials$ab))
expect_true(all(intrinsic_resistant$mo %in% microorganisms$mo))
expect_true(all(intrinsic_resistant$ab %in% AMR::antimicrobials$ab))
expect_false(anyNA(microorganisms.codes$code))
expect_false(anyNA(microorganisms.codes$mo))
expect_true(all(dosage$ab %in% AMR::antimicrobials$ab))
expect_true(all(dosage$name %in% AMR::antimicrobials$name))
interpretive_abx <- AMR:::INTERPRETIVE_RULES_DF$and_these_antibiotics
interpretive_abx <- unique(unlist(strsplit(interpretive_abx[!is.na(interpretive_abx)], ", +")))
expect_true(all(interpretive_abx %in% AMR::antimicrobials$ab),
info = paste0(
"Missing in `antimicrobials` data set: ",
toString(interpretive_abx[which(!interpretive_abx %in% AMR::antimicrobials$ab)])
)
)
# check valid disks/MICs
expect_false(anyNA(as.mic(clinical_breakpoints[which(clinical_breakpoints$method == "MIC" & clinical_breakpoints$ref_tbl != "ECOFF"), "breakpoint_S", drop = TRUE])))
expect_true(anyNA(as.mic(clinical_breakpoints[which(clinical_breakpoints$method == "MIC" & clinical_breakpoints$ref_tbl != "ECOFF"), "breakpoint_R", drop = TRUE])))
expect_false(anyNA(as.disk(clinical_breakpoints[which(clinical_breakpoints$method == "DISK" & clinical_breakpoints$ref_tbl != "ECOFF"), "breakpoint_S", drop = TRUE])))
expect_true(anyNA(as.disk(clinical_breakpoints[which(clinical_breakpoints$method == "DISK" & clinical_breakpoints$ref_tbl != "ECOFF"), "breakpoint_R", drop = TRUE])))
# antibiotic names must always be coercible to their original AB code
expect_identical(as.ab(AMR::antimicrobials$name), AMR::antimicrobials$ab)
if (AMR:::pkg_is_available("tibble")) {
# there should be no diacritics (i.e. non ASCII) characters in the datasets (CRAN policy)
datasets <- data(package = "AMR", envir = asNamespace("AMR"))$results[, "Item", drop = TRUE]
datasets <- datasets[datasets != "antibiotics"]
for (i in seq_len(length(datasets))) {
dataset <- get(datasets[i], envir = asNamespace("AMR"))
expect_identical(AMR:::dataset_UTF8_to_ASCII(dataset), dataset, info = datasets[i])
}
}
df <- AMR:::AMR_env$MO_lookup
expect_true(all(c(
"mo", "fullname", "status", "kingdom", "phylum", "class", "order",
"family", "genus", "species", "subspecies", "rank", "ref", "source",
"lpsn", "lpsn_parent", "lpsn_renamed_to", "gbif", "gbif_parent", "gbif_renamed_to", "prevalence",
"snomed", "kingdom_index", "fullname_lower", "full_first", "species_first"
) %in% colnames(df)))
expect_inherits(AMR:::MO_CONS, "mo")
uncategorised <- subset(
microorganisms,
genus == "Staphylococcus" &
!species %in% c("", "aureus") &
!mo %in% c(AMR:::MO_CONS, AMR:::MO_COPS)
)
expect_true(NROW(uncategorised) == 0,
info = ifelse(NROW(uncategorised) == 0,
"All staphylococcal species categorised as CoNS/CoPS.",
paste0(
"Staphylococcal species not categorised as CoNS/CoPS: S. ",
uncategorised$species, " (", uncategorised$mo, ")",
collapse = "\n"
)
)
)
# THIS WILL CHECK NON-ASCII STRINGS IN ALL FILES:
# check_non_ascii <- function() {
# purrr::map_df(
# .id = "file",
# # list common text files
# .x = fs::dir_ls(
# recurse = TRUE,
# type = "file",
# # ignore images, compressed
# regexp = "\\.(png|ico|rda|ai|tar.gz|zip|xlsx|csv|pdf|psd)$",
# invert = TRUE
# ),
# .f = function(path) {
# x <- readLines(path, warn = FALSE)
# # from tools::showNonASCII()
# asc <- iconv(x, "latin1", "ASCII")
# ind <- is.na(asc) | asc != x
# # make data frame
# if (any(ind)) {
# tibble::tibble(
# row = which(ind),
# line = iconv(x[ind], "latin1", "ASCII", sub = "byte")
# )
# } else {
# tibble::tibble()
# }
# }
# )
# }
# x <- check_non_ascii() %>%
# filter(file %unlike% "^(data-raw|docs|git_)")
})