AMR/inst/tinytest/test-data.R

128 lines
6.1 KiB
R
Raw Normal View History

2021-05-15 21:36:22 +02:00
# ==================================================================== #
# TITLE: #
2022-10-05 09:12:22 +02:00
# AMR: An R Package for Working with Antimicrobial Resistance Data #
2021-05-15 21:36:22 +02:00
# #
# SOURCE CODE: #
2021-05-15 21:36:22 +02:00
# 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. #
2023-05-27 10:39:22 +02:00
# https://doi.org/10.18637/jss.v104.i03 #
2022-10-05 09:12:22 +02:00
# #
2022-12-27 15:16:15 +01:00
# 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. #
2021-05-15 21:36:22 +02:00
# #
# 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://msberends.github.io/AMR/ #
# ==================================================================== #
# IDs should always be unique
expect_identical(nrow(microorganisms), length(unique(microorganisms$mo)))
expect_identical(class(microorganisms$mo), c("mo", "character"))
expect_identical(nrow(antibiotics), length(unique(antibiotics$ab)))
expect_true(all(is.na(antibiotics$atc[duplicated(antibiotics$atc)])))
2021-05-15 21:36:22 +02:00
expect_identical(class(antibiotics$ab), c("ab", "character"))
2021-05-15 21:36:22 +02:00
# check cross table reference
expect_true(all(microorganisms.codes$mo %in% microorganisms$mo))
expect_true(all(example_isolates$mo %in% microorganisms$mo))
2023-07-11 09:50:45 +02:00
expect_true(all(microorganisms.groups$mo %in% microorganisms$mo))
expect_true(all(microorganisms.groups$mo_group %in% microorganisms$mo))
2023-01-21 23:47:20 +01:00
expect_true(all(clinical_breakpoints$mo %in% microorganisms$mo))
expect_true(all(clinical_breakpoints$ab %in% antibiotics$ab))
2021-12-14 21:47:14 +01:00
expect_true(all(intrinsic_resistant$mo %in% microorganisms$mo))
expect_true(all(intrinsic_resistant$ab %in% antibiotics$ab))
2021-05-15 21:36:22 +02:00
expect_false(any(is.na(microorganisms.codes$code)))
expect_false(any(is.na(microorganisms.codes$mo)))
expect_true(all(dosage$ab %in% antibiotics$ab))
expect_true(all(dosage$name %in% antibiotics$name))
2021-12-13 11:57:34 +01:00
# check valid disks/MICs
expect_false(any(is.na(as.mic(clinical_breakpoints[which(clinical_breakpoints$method == "MIC" & clinical_breakpoints$ref_tbl != "ECOFF"), "breakpoint_S", drop = TRUE]))))
expect_false(any(is.na(as.mic(clinical_breakpoints[which(clinical_breakpoints$method == "MIC" & clinical_breakpoints$ref_tbl != "ECOFF"), "breakpoint_R", drop = TRUE]))))
expect_false(any(is.na(as.disk(clinical_breakpoints[which(clinical_breakpoints$method == "DISK" & clinical_breakpoints$ref_tbl != "ECOFF"), "breakpoint_S", drop = TRUE]))))
expect_false(any(is.na(as.disk(clinical_breakpoints[which(clinical_breakpoints$method == "DISK" & clinical_breakpoints$ref_tbl != "ECOFF"), "breakpoint_R", drop = TRUE]))))
2021-05-15 21:36:22 +02:00
# antibiotic names must always be coercible to their original AB code
expect_identical(as.ab(antibiotics$name), antibiotics$ab)
2023-02-18 14:56:06 +01:00
if (AMR:::pkg_is_available("tibble")) {
2022-08-28 19:34:04 +02:00
# there should be no diacritics (i.e. non ASCII) characters in the datasets (CRAN policy)
datasets <- data(package = "AMR", envir = asNamespace("AMR"))$results[, "Item", drop = TRUE]
for (i in seq_len(length(datasets))) {
dataset <- get(datasets[i], envir = asNamespace("AMR"))
expect_identical(AMR:::dataset_UTF8_to_ASCII(dataset), dataset, info = datasets[i])
}
2021-05-15 21:36:22 +02:00
}
2022-10-14 13:02:50 +02:00
df <- AMR:::AMR_env$MO_lookup
2022-08-28 10:31:50 +02:00
expect_true(all(c(
2022-10-05 09:12:22 +02:00
"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"
2022-08-28 10:31:50 +02:00
) %in% colnames(df)))
2021-05-15 21:36:22 +02:00
expect_inherits(AMR:::MO_CONS, "mo")
2022-08-28 10:31:50 +02:00
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. ",
2022-10-05 09:12:22 +02:00
uncategorised$species, " (", uncategorised$mo, ")",
collapse = "\n"
2022-08-28 10:31:50 +02:00
)
)
)
# 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()
# }
# }
# )
# }
2022-08-28 10:31:50 +02:00
# x <- check_non_ascii() %>%
# filter(file %unlike% "^(data-raw|docs|git_)")