AMR/tests/testthat/test-data.R

99 lines
4.9 KiB
R
Raw Normal View History

# ==================================================================== #
# TITLE #
# Antimicrobial Resistance (AMR) Data Analysis for R #
# #
2019-01-02 23:24:07 +01:00
# SOURCE #
2020-07-08 14:48:06 +02:00
# https://github.com/msberends/AMR #
# #
# LICENCE #
2020-12-27 00:30:28 +01:00
# (c) 2018-2021 Berends MS, Luz CF et al. #
2020-10-08 11:16:03 +02:00
# Developed at the University of Groningen, the Netherlands, in #
# collaboration with non-profit organisations Certe Medical #
# Diagnostics & Advice, and University Medical Center Groningen. #
# #
2019-01-02 23:24:07 +01:00
# 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. #
2020-10-08 11:16:03 +02:00
# #
# Visit our website for the full manual and a complete tutorial about #
# how to conduct AMR data analysis: https://msberends.github.io/AMR/ #
# ==================================================================== #
context("data.R")
test_that("data sets are valid", {
2020-07-31 10:50:08 +02:00
skip_on_cran()
2020-02-14 19:54:13 +01:00
expect_true(check_dataset_integrity()) # in misc.R
# IDs should always be unique
expect_identical(nrow(microorganisms), length(unique(microorganisms$mo)))
2020-05-19 12:08:49 +02:00
expect_identical(class(microorganisms$mo), c("mo", "character"))
2019-10-06 21:07:38 +02:00
expect_identical(nrow(antibiotics), length(unique(antibiotics$ab)))
2020-05-19 12:08:49 +02:00
expect_identical(class(antibiotics$ab), c("ab", "character"))
2019-10-06 21:07:38 +02:00
2019-05-28 16:50:40 +02:00
# check cross table reference
expect_true(all(microorganisms.codes$mo %in% microorganisms$mo))
2019-09-20 12:33:05 +02:00
expect_true(all(example_isolates$mo %in% microorganisms$mo))
expect_true(all(microorganisms.translation$mo_new %in% microorganisms$mo))
expect_true(all(rsi_translation$mo %in% microorganisms$mo))
expect_true(all(rsi_translation$ab %in% antibiotics$ab))
expect_true(all(intrinsic_resistant$microorganism %in% microorganisms$fullname)) # also important for mo_is_intrinsic_resistant()
expect_true(all(intrinsic_resistant$antibiotic %in% antibiotics$name))
expect_false(any(is.na(microorganisms.codes$code)))
expect_false(any(is.na(microorganisms.codes$mo)))
expect_false(any(microorganisms.translation$mo_old %in% microorganisms$mo))
expect_true(all(dosage$ab %in% antibiotics$ab))
expect_true(all(dosage$name %in% antibiotics$name))
2020-07-31 10:50:08 +02:00
2019-06-11 14:18:25 +02:00
# antibiotic names must always be coercible to their original AB code
expect_identical(as.ab(antibiotics$name), antibiotics$ab)
2020-07-31 10:50:08 +02:00
2019-06-11 14:18:25 +02:00
# there should be no diacritics (i.e. non ASCII) characters in the datasets (CRAN policy)
2019-04-05 18:47:39 +02:00
datasets <- data(package = "AMR", envir = asNamespace("AMR"))$results[, "Item"]
2019-10-11 17:21:02 +02:00
for (i in seq_len(length(datasets))) {
2019-04-05 18:47:39 +02:00
dataset <- get(datasets[i], envir = asNamespace("AMR"))
expect_identical(dataset_UTF8_to_ASCII(dataset), dataset, label = datasets[i])
2019-04-05 18:47:39 +02:00
}
})
2019-02-21 18:55:52 +01:00
2019-02-21 23:32:30 +01:00
test_that("creation of data sets is valid", {
2020-07-31 10:50:08 +02:00
skip_on_cran()
2021-01-22 10:55:07 +01:00
df <- AMR:::MO_lookup
2020-05-16 13:05:47 +02:00
expect_lt(nrow(df[which(df$prevalence == 1), ]), nrow(df[which(df$prevalence == 2), ]))
expect_lt(nrow(df[which(df$prevalence == 2), ]), nrow(df[which(df$prevalence == 3), ]))
2019-12-21 10:56:06 +01:00
expect_true(all(c("mo", "fullname",
"kingdom", "phylum", "class", "order", "family", "genus", "species", "subspecies",
2020-05-27 16:37:49 +02:00
"rank", "ref", "species_id", "source", "prevalence", "snomed",
2020-05-16 13:05:47 +02:00
"kingdom_index", "fullname_lower", "g_species") %in% colnames(df)))
2020-07-31 10:50:08 +02:00
2020-05-27 16:37:49 +02:00
expect_true(all(c("fullname", "fullname_new", "ref", "prevalence",
2021-01-22 10:55:07 +01:00
"fullname_lower", "g_species") %in% colnames(AMR:::MO.old_lookup)))
2020-07-31 10:50:08 +02:00
2021-01-22 10:55:07 +01:00
expect_s3_class(AMR:::MO_CONS, "mo")
2019-02-21 23:32:30 +01:00
})
2019-02-27 11:36:12 +01:00
test_that("CoL version info works", {
2020-07-31 10:50:08 +02:00
skip_on_cran()
expect_identical(class(catalogue_of_life_version()),
c("catalogue_of_life_version", "list"))
2019-05-13 14:56:23 +02:00
expect_output(print(catalogue_of_life_version()))
2019-02-27 11:36:12 +01:00
})
test_that("CoNS/CoPS are up to date", {
uncategorised <- subset(microorganisms,
genus == "Staphylococcus" &
!species %in% c("", "aureus") &
!mo %in% c(MO_CONS, MO_COPS))
expect(NROW(uncategorised) == 0,
failure_message = paste0("Staphylococcal species not categorised as CoNS/CoPS: S. ",
uncategorised$species, " (", uncategorised$mo, ")"))
})