From 7f344836ea3d7ddefa521361fc33460a0cdbce58 Mon Sep 17 00:00:00 2001 From: Matthijs Berends Date: Tue, 16 Jul 2024 15:55:58 +0200 Subject: [PATCH] (v2.1.1.9064) unit tests --- .github/prehooks/pre-commit | 38 ++++++++++++++++++++++++++++++++ DESCRIPTION | 2 +- NEWS.md | 2 +- R/mo.R | 19 ++++++++++------ data-raw/_pre_commit_checks.R | 3 ++- inst/tinytest/test-mo.R | 2 +- inst/tinytest/test-mo_property.R | 9 ++++---- 7 files changed, 60 insertions(+), 15 deletions(-) create mode 100755 .github/prehooks/pre-commit diff --git a/.github/prehooks/pre-commit b/.github/prehooks/pre-commit new file mode 100755 index 00000000..8eaf689f --- /dev/null +++ b/.github/prehooks/pre-commit @@ -0,0 +1,38 @@ +#!/bin/bash + +# ==================================================================== # +# 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://msberends.github.io/AMR/ # +# ==================================================================== # + +# always add these: +git add data-raw/* +git add man/* +git add R/sysdata.rda +git add NAMESPACE +git add DESCRIPTION +git add NEWS.md diff --git a/DESCRIPTION b/DESCRIPTION index 76216186..47e42232 100644 --- a/DESCRIPTION +++ b/DESCRIPTION @@ -1,5 +1,5 @@ Package: AMR -Version: 2.1.1.9063 +Version: 2.1.1.9064 Date: 2024-07-16 Title: Antimicrobial Resistance Data Analysis Description: Functions to simplify and standardise antimicrobial resistance (AMR) diff --git a/NEWS.md b/NEWS.md index fc178779..aa5646a7 100644 --- a/NEWS.md +++ b/NEWS.md @@ -1,4 +1,4 @@ -# AMR 2.1.1.9063 +# AMR 2.1.1.9064 *(this beta version will eventually become v3.0. We're happy to reach a new major milestone soon, which will be all about the new One Health support! Install this beta using [the instructions here](https://msberends.github.io/AMR/#latest-development-version).)* diff --git a/R/mo.R b/R/mo.R index d5697dfd..94352a5d 100755 --- a/R/mo.R +++ b/R/mo.R @@ -420,17 +420,21 @@ as.mo <- function(x, # Keep or replace synonyms ---- lpsn_matches <- AMR_env$MO_lookup$lpsn_renamed_to[match(out, AMR_env$MO_lookup$mo)] lpsn_matches[!lpsn_matches %in% AMR_env$MO_lookup$lpsn] <- NA - # GBIF only for non-bacteria, since we use LPSN as primary source for bacteria + mycobank_matches <- AMR_env$MO_lookup$mycobank_renamed_to[match(out, AMR_env$MO_lookup$mo)] + mycobank_matches[!mycobank_matches %in% AMR_env$MO_lookup$mycobank] <- NA + # GBIF only for non-bacteria and non-fungi, since we use LPSN as primary source for bacteria and MycoBank for fungi # (an example is Strep anginosus, renamed according to GBIF, not according to LPSN) - gbif_matches <- AMR_env$MO_lookup$gbif_renamed_to[AMR_env$MO_lookup$kingdom != "Bacteria"][match(out, AMR_env$MO_lookup$mo[AMR_env$MO_lookup$kingdom != "Bacteria"])] + gbif_matches <- AMR_env$MO_lookup$gbif_renamed_to[!AMR_env$MO_lookup$kingdom %in% c("Bacteria", "Fungi")][match(out, AMR_env$MO_lookup$mo[!AMR_env$MO_lookup$kingdom %in% c("Bacteria", "Fungi")])] gbif_matches[!gbif_matches %in% AMR_env$MO_lookup$gbif] <- NA AMR_env$mo_renamed <- list( - old = out[!is.na(gbif_matches) | !is.na(lpsn_matches)], - gbif_matches = gbif_matches[!is.na(gbif_matches) | !is.na(lpsn_matches)], - lpsn_matches = lpsn_matches[!is.na(gbif_matches) | !is.na(lpsn_matches)] + old = out[!is.na(gbif_matches) | !is.na(lpsn_matches) | !is.na(mycobank_matches)], + gbif_matches = gbif_matches[!is.na(gbif_matches) | !is.na(lpsn_matches) | !is.na(mycobank_matches)], + mycobank_matches = mycobank_matches[!is.na(gbif_matches) | !is.na(lpsn_matches) | !is.na(mycobank_matches)], + lpsn_matches = lpsn_matches[!is.na(gbif_matches) | !is.na(lpsn_matches) | !is.na(mycobank_matches)] ) if (isFALSE(keep_synonyms)) { out[which(!is.na(gbif_matches))] <- AMR_env$MO_lookup$mo[match(gbif_matches[which(!is.na(gbif_matches))], AMR_env$MO_lookup$gbif)] + out[which(!is.na(mycobank_matches))] <- AMR_env$MO_lookup$mo[match(mycobank_matches[which(!is.na(mycobank_matches))], AMR_env$MO_lookup$mycobank)] out[which(!is.na(lpsn_matches))] <- AMR_env$MO_lookup$mo[match(lpsn_matches[which(!is.na(lpsn_matches))], AMR_env$MO_lookup$lpsn)] if (isTRUE(info) && length(AMR_env$mo_renamed$old) > 0) { print(mo_renamed(), extra_txt = " (use `keep_synonyms = TRUE` to leave uncorrected)") @@ -1040,13 +1044,14 @@ convert_colloquial_input <- function(x) { out[x %like_case% "anaerob[a-z]+ .*gram[ -]?neg.*"] <- "B_ANAER-NEG" out[x %like_case% "anaerob[a-z]+ .*gram[ -]?pos.*"] <- "B_ANAER-POS" out[is.na(out) & x %like_case% "anaerob[a-z]+ (micro)?.*organism"] <- "B_ANAER" + out[is.na(out) & x %like_case% "anaerob[a-z]+ bacter"] <- "B_ANAER" # coryneform bacteria out[x %like_case% "^coryneform"] <- "B_CORYNF" # yeasts and fungi - out[x %like_case% "^yeast?"] <- "F_YEAST" - out[x %like_case% "^fung(us|i)"] <- "F_FUNGUS" + out[x %like_case% "(^| )yeast?"] <- "F_YEAST" + out[x %like_case% "(^| )fung(us|i)"] <- "F_FUNGUS" # trivial names known to the field out[x %like_case% "meningo[ck]o[ck]"] <- "B_NESSR_MNNG" diff --git a/data-raw/_pre_commit_checks.R b/data-raw/_pre_commit_checks.R index 5af76f86..5c6066e3 100644 --- a/data-raw/_pre_commit_checks.R +++ b/data-raw/_pre_commit_checks.R @@ -122,7 +122,8 @@ create_species_cons_cops <- function(type = c("CoNS", "CoPS")) { "vitulinus", "vitulus", "warneri", "xylosus", "caledonicus", "canis", "durrellii", "lloydii", - "ratti", "taiwanensis", "veratri", "urealyticus" + "ratti", "taiwanensis", "veratri", "urealyticus", + "americanisciuri", "marylandisciuri", "shinii", "brunensis" ) | # old, now renamed to S. schleiferi (but still as synonym in our data of course): (MO_staph$species == "schleiferi" & MO_staph$subspecies %in% c("schleiferi", ""))), diff --git a/inst/tinytest/test-mo.R b/inst/tinytest/test-mo.R index e7fdc607..c3d386c1 100644 --- a/inst/tinytest/test-mo.R +++ b/inst/tinytest/test-mo.R @@ -265,7 +265,7 @@ expect_equal( "Raoultella (here some text) terrigena" ) ))), - c("B_MCRBC_PRXY", "B_STRPT_SUIS", "B_RLTLL_TRRG") + c("B_MCRBC_PRXY", "B_STRPT_SUIS", "B_KLBSL_TRRG") ) expect_stdout(print(mo_uncertainties())) x <- as.mo("Sta. aur") diff --git a/inst/tinytest/test-mo_property.R b/inst/tinytest/test-mo_property.R index e4c5dd48..9d2659e0 100644 --- a/inst/tinytest/test-mo_property.R +++ b/inst/tinytest/test-mo_property.R @@ -104,10 +104,10 @@ expect_true(length(mo_group_members("B_HACEK")) > 1) expect_inherits(mo_group_members(c("Candida albicans", "Escherichia coli")), "list") expect_identical(mo_oxygen_tolerance(c("Klebsiella pneumoniae", "Clostridioides difficile")), - c("aerobe", "anaerobe")) + c("facultative anaerobe", "anaerobe")) expect_equal(as.character(table(mo_pathogenicity(example_isolates$mo))), - c("1874", "109", "1", "16")) + c("1911", "72", "1", "16")) expect_equal(mo_ref("Escherichia coli"), "Castellani et al., 1919") expect_equal(mo_authors("Escherichia coli"), "Castellani et al.") @@ -116,8 +116,9 @@ expect_equal(mo_year("Escherichia coli"), 1919) expect_true(mo_url("Candida albicans") %like% "gbif.org") expect_true(mo_url("Escherichia coli") %like% "lpsn.dsmz.de") -# test integrity -expect_identical(microorganisms$fullname, mo_fullname(microorganisms$fullname, language = "en", keep_synonyms = TRUE)) +# test integrity of getting back full names +expect_identical(microorganisms$fullname[microorganisms$fullname %unlike% "(Fungi|{)"], + suppressWarnings(mo_fullname(microorganisms$fullname[microorganisms$fullname %unlike% "(Fungi|{)"], language = "en", keep_synonyms = TRUE))) # check languages expect_equal(mo_type("Escherichia coli", language = "de"), "Bakterien")