unknown codes, rsi fix

This commit is contained in:
dr. M.S. (Matthijs) Berends 2019-03-02 22:47:04 +01:00
parent c5efb272fd
commit e835525cf6
31 changed files with 528 additions and 409 deletions

View File

@ -1,6 +1,6 @@
Package: AMR
Version: 0.5.0.9020
Date: 2019-03-01
Date: 2019-03-02
Title: Antimicrobial Resistance Analysis
Authors@R: c(
person(

15
NEWS.md
View File

@ -78,11 +78,18 @@ We've got a new website: [https://msberends.gitlab.io/AMR](https://msberends.git
* Functions `atc_ddd()` and `atc_groups()` have been renamed `atc_online_ddd()` and `atc_online_groups()`. The old functions are deprecated and will be removed in a future version.
* Function `guess_mo()` is now deprecated in favour of `as.mo()` and will be removed in future versions
* Function `guess_atc()` is now deprecated in favour of `as.atc()` and will be removed in future versions
* Improvements for `as.mo()`:
* Improvements for `as.mo()`:\
* Incoercible results will now be considered 'unknown', MO code `UNKNOWN`. Properties of these will be translated on foreign systems in all language already previously supported: German, Dutch, French, Italian, Spanish and Portuguese:
```r
mo_genus("qwerty", language = "es")
# Warning:
# one unique value (^= 100.0%) could not be coerced and is considered 'unknown': "qwerty". Use mo_failures() to review it.
#> [1] "(género desconocido)"
```
* Fix for vector containing only empty values
* Finds better results when input is in other languages
* Better handling for subspecies
* Better handling for *Salmonellae*
* Better handling for *Salmonellae*, especially the 'city like' serovars like *Salmonella London*
* Understanding of highly virulent *E. coli* strains like EIEC, EPEC and STEC
* There will be looked for uncertain results at default - these results will be returned with an informative warning
* Manual (help page) now contains more info about the algorithms
@ -102,7 +109,9 @@ We've got a new website: [https://msberends.gitlab.io/AMR](https://msberends.git
* New colours for `scale_rsi_colours()`
* Summaries of class `mo` will now return the top 3 and the unique count, e.g. using `summary(mo)`
* Small text updates to summaries of class `rsi` and `mic`
* Function `as.rsi()` now gives a warning when inputting MIC values
* Function `as.rsi()`:
* Now gives a warning when inputting MIC values
* Now accepts high and low resistance: `"HIGH S"` will return `S`
* Frequency tables (`freq()` function):
* Support for tidyverse quasiquotation! Now you can create frequency tables of function outcomes:
```r

View File

@ -134,7 +134,7 @@
#'
#' A data set containing the microbial taxonomy of six kingdoms from the Catalogue of Life. MO codes can be looked up using \code{\link{as.mo}}.
#' @inheritSection catalogue_of_life Catalogue of Life
#' @format A \code{\link{data.frame}} with 57,158 observations and 14 variables:
#' @format A \code{\link{data.frame}} with 59,985 observations and 15 variables:
#' \describe{
#' \item{\code{mo}}{ID of microorganism as used by this package}
#' \item{\code{col_id}}{Catalogue of Life ID}
@ -150,6 +150,7 @@
#' \item{\code{rank}}{Taxonomic rank of the microorganism, like \code{"species"} or \code{"genus"}}
#' \item{\code{ref}}{Author(s) and year of concerning scientific publication}
#' \item{\code{species_id}}{ID of the species as used by the Catalogue of Life}
#' \item{\code{prevalence}}{Prevalence of the microorganism, see \code{?as.mo}}
#' }
#' @source Catalogue of Life: Annual Checklist (public online database), \url{www.catalogueoflife.org}.
#' @details Manually added were:
@ -172,7 +173,7 @@ catalogue_of_life <- list(
#'
#' A data set containing old (previously valid or accepted) taxonomic names according to the Catalogue of Life. This data set is used internally by \code{\link{as.mo}}.
#' @inheritSection catalogue_of_life Catalogue of Life
#' @format A \code{\link{data.frame}} with 14,487 observations and 4 variables:
#' @format A \code{\link{data.frame}} with 17,069 observations and 4 variables:
#' \describe{
#' \item{\code{col_id}}{Catalogue of Life ID}
#' \item{\code{tsn_new}}{New Catalogue of Life ID}

70
R/mo.R
View File

@ -51,6 +51,8 @@
#' F (Fungi), P (Protozoa), PL (Plantae) or V (Viruses)
#' }
#'
#' Values that cannot be coered will be considered 'unknown' and have an MO code \code{UNKNOWN}.
#'
#' Use the \code{\link{mo_property}} functions to get properties based on the returned code, see Examples.
#'
#' \strong{Artificial Intelligence} \cr
@ -275,7 +277,8 @@ exec_as.mo <- function(x, Becker = FALSE, Lancefield = FALSE,
# only check the uniques, which is way faster
x <- unique(x)
# remove empty values (to later fill them in again with NAs)
x <- x[!is.na(x) & !is.null(x) & !identical(x, "")]
# ("xxx" is WHONET code for 'no growth')
x <- x[!is.na(x) & !is.null(x) & !identical(x, "") & !identical(x, "xxx")]
# conversion of old MO codes from v0.5.0 (ITIS) to later versions (Catalogue of Life)
if (any(x %like% "^[BFP]_[A-Z]{3,7}") & !all(x %in% microorganisms$mo)) {
@ -367,8 +370,6 @@ exec_as.mo <- function(x, Becker = FALSE, Lancefield = FALSE,
x_species <- paste(x, "species")
# translate to English for supported languages of mo_property
x <- gsub("(Gruppe|gruppe|groep|grupo|gruppo|groupe)", "group", x, ignore.case = TRUE)
# remove 'empty' genus and species values
x <- gsub("(no MO)", "", x, fixed = TRUE)
# remove non-text in case of "E. coli" except dots and spaces
x <- gsub("[^.a-zA-Z0-9/ \\-]+", "", x)
# replace minus by a space
@ -419,12 +420,17 @@ exec_as.mo <- function(x, Becker = FALSE, Lancefield = FALSE,
next
}
if (tolower(x_trimmed[i]) %in% c("", "xxx", "other", "none", "unknown")) {
# empty and nonsense values, ignore without warning ("xxx" is WHONET code for 'no growth')
if (any(x_trimmed[i] %in% c(NA, ""))) {
x[i] <- NA_character_
next
}
if (tolower(x_trimmed[i]) %in% c("xxx", "other", "none", "unknown")) {
# empty and nonsense values, ignore without warning
x[i] <- microorganismsDT[mo == "UNKNOWN", ..property][[1]]
next
}
if (nchar(gsub("[^a-zA-Z]", "", x_trimmed[i])) < 3) {
# check if search term was like "A. species", then return first genus found with ^A
if (x_backup[i] %like% "[a-z]+ species" | x_backup[i] %like% "[a-z] spp[.]?") {
@ -441,14 +447,14 @@ exec_as.mo <- function(x, Becker = FALSE, Lancefield = FALSE,
}
}
# fewer than 3 chars and not looked for species, add as failure
x[i] <- NA_character_
x[i] <- microorganismsDT[mo == "UNKNOWN", ..property][[1]]
failures <- c(failures, x_backup[i])
next
}
if (x_trimmed[i] %like% "virus") {
# there is no fullname like virus, so don't try to coerce it
x[i] <- NA_character_
x[i] <- microorganismsDT[mo == "UNKNOWN", ..property][[1]]
failures <- c(failures, x_backup[i])
next
}
@ -667,7 +673,7 @@ exec_as.mo <- function(x, Becker = FALSE, Lancefield = FALSE,
d.x_withspaces_start_end = x_withspaces_start_end[i],
e.x_withspaces_start_only = x_withspaces_start_only[i],
f.x_withspaces_end_only = x_withspaces_end_only[i])
if (!is.na(x[i])) {
if (!empty_result(x[i])) {
next
}
# THEN TRY PREVALENT IN HUMAN INFECTIONS ----
@ -678,7 +684,7 @@ exec_as.mo <- function(x, Becker = FALSE, Lancefield = FALSE,
d.x_withspaces_start_end = x_withspaces_start_end[i],
e.x_withspaces_start_only = x_withspaces_start_only[i],
f.x_withspaces_end_only = x_withspaces_end_only[i])
if (!is.na(x[i])) {
if (!empty_result(x[i])) {
next
}
# THEN UNPREVALENT IN HUMAN INFECTIONS ----
@ -689,7 +695,7 @@ exec_as.mo <- function(x, Becker = FALSE, Lancefield = FALSE,
d.x_withspaces_start_end = x_withspaces_start_end[i],
e.x_withspaces_start_only = x_withspaces_start_only[i],
f.x_withspaces_end_only = x_withspaces_end_only[i])
if (!is.na(x[i])) {
if (!empty_result(x[i])) {
next
}
@ -765,7 +771,7 @@ exec_as.mo <- function(x, Becker = FALSE, Lancefield = FALSE,
# (3) not yet implemented taxonomic changes in Catalogue of Life ----
found <- suppressMessages(suppressWarnings(exec_as.mo(TEMPORARY_TAXONOMY(b.x_trimmed), clear_options = FALSE, allow_uncertain = FALSE)))
if (!is.na(found)) {
if (!empty_result(found)) {
found_result <- found
found <- microorganismsDT[mo == found, ..property][[1]]
uncertainties <<- rbind(uncertainties,
@ -780,7 +786,7 @@ exec_as.mo <- function(x, Becker = FALSE, Lancefield = FALSE,
a.x_backup_stripped <- gsub("( *[(].*[)] *)", " ", a.x_backup)
a.x_backup_stripped <- trimws(gsub(" +", " ", a.x_backup_stripped))
found <- suppressMessages(suppressWarnings(exec_as.mo(a.x_backup_stripped, clear_options = FALSE, allow_uncertain = FALSE)))
if (!is.na(found) & nchar(b.x_trimmed) >= 6) {
if (!empty_result(found) & nchar(b.x_trimmed) >= 6) {
found_result <- found
found <- microorganismsDT[mo == found, ..property][[1]]
uncertainties <<- rbind(uncertainties,
@ -797,7 +803,7 @@ exec_as.mo <- function(x, Becker = FALSE, Lancefield = FALSE,
for (i in 1:(length(x_strip) - 1)) {
x_strip_collapsed <- paste(x_strip[1:(length(x_strip) - i)], collapse = " ")
found <- suppressMessages(suppressWarnings(exec_as.mo(x_strip_collapsed, clear_options = FALSE, allow_uncertain = FALSE)))
if (!is.na(found)) {
if (!empty_result(found)) {
found_result <- found
found <- microorganismsDT[mo == found, ..property][[1]]
uncertainties <<- rbind(uncertainties,
@ -816,7 +822,7 @@ exec_as.mo <- function(x, Becker = FALSE, Lancefield = FALSE,
for (i in 2:(length(x_strip))) {
x_strip_collapsed <- paste(x_strip[i:length(x_strip)], collapse = " ")
found <- suppressMessages(suppressWarnings(exec_as.mo(x_strip_collapsed, clear_options = FALSE, allow_uncertain = FALSE)))
if (!is.na(found)) {
if (!empty_result(found)) {
found_result <- found
found <- microorganismsDT[mo == found, ..property][[1]]
uncertainties <<- rbind(uncertainties,
@ -833,13 +839,15 @@ exec_as.mo <- function(x, Becker = FALSE, Lancefield = FALSE,
found <- microorganismsDT[fullname %like% f.x_withspaces_end_only]
if (nrow(found) > 0) {
found_result <- found[["mo"]]
found <- microorganismsDT[mo == found_result[1L], ..property][[1]]
uncertainties <<- rbind(uncertainties,
data.frame(uncertainty = 3,
input = a.x_backup,
fullname = microorganismsDT[mo == found_result[1L], fullname][[1]],
mo = found_result[1L]))
return(found[1L])
if (!empty_result(found_result)) {
found <- microorganismsDT[mo == found_result[1L], ..property][[1]]
uncertainties <<- rbind(uncertainties,
data.frame(uncertainty = 3,
input = a.x_backup,
fullname = microorganismsDT[mo == found_result[1L], fullname][[1]],
mo = found_result[1L]))
return(found[1L])
}
}
# didn't found in uncertain results too
@ -847,13 +855,13 @@ exec_as.mo <- function(x, Becker = FALSE, Lancefield = FALSE,
}
x[i] <- uncertain_fn(x_backup[i], x_trimmed[i], x_withspaces_start_end[i], x_withspaces_start_only[i], x_withspaces_end_only[i])
if (!is.na(x[i])) {
if (!empty_result(x[i])) {
next
}
}
# not found ----
x[i] <- NA_character_
x[i] <- microorganismsDT[mo == "UNKNOWN", ..property][[1]]
failures <- c(failures, x_backup[i])
}
}
@ -862,15 +870,15 @@ exec_as.mo <- function(x, Becker = FALSE, Lancefield = FALSE,
failures <- failures[!failures %in% c(NA, NULL, NaN)]
if (length(failures) > 0 & clear_options == TRUE) {
options(mo_failures = sort(unique(failures)))
plural <- c("value", "it")
plural <- c("value", "it", "is")
if (n_distinct(failures) > 1) {
plural <- c("values", "them")
plural <- c("values", "them", "are")
}
total_failures <- length(x_input[x_input %in% failures & !x_input %in% c(NA, NULL, NaN)])
total_n <- length(x_input[!x_input %in% c(NA, NULL, NaN)])
msg <- paste0("\n", nr2char(n_distinct(failures)), " unique input ", plural[1],
msg <- paste0("\n", nr2char(n_distinct(failures)), " unique ", plural[1],
" (^= ", percent(total_failures / total_n, round = 1, force_zero = TRUE),
") could not be coerced to a valid MO code")
") could not be coerced and ", plural[3], " considered 'unknown'")
if (n_distinct(failures) <= 10) {
msg <- paste0(msg, ": ", paste('"', unique(failures), '"', sep = "", collapse = ', '))
}
@ -887,7 +895,7 @@ exec_as.mo <- function(x, Becker = FALSE, Lancefield = FALSE,
if (NROW(uncertainties) > 1) {
plural <- c("values", "them")
}
msg <- paste0("\nResults of ", nr2char(NROW(uncertainties)), " input ", plural[1],
msg <- paste0("\nResults of ", nr2char(NROW(uncertainties)), " ", plural[1],
" was guessed with uncertainty. Use mo_uncertainties() to review ", plural[2], ".")
warning(red(msg),
call. = FALSE,
@ -951,7 +959,7 @@ exec_as.mo <- function(x, Becker = FALSE, Lancefield = FALSE,
# Wrap up ----------------------------------------------------------------
# comply to x, which is also unique and without empty values
x_input_unique_nonempty <- unique(x_input[!is.na(x_input) & !is.null(x_input) & !identical(x_input, "")])
x_input_unique_nonempty <- unique(x_input[!is.na(x_input) & !is.null(x_input) & !identical(x_input, "") & !identical(x_input, "xxx")])
# left join the found results to the original input values (x_input)
df_found <- data.frame(input = as.character(x_input_unique_nonempty),
@ -984,6 +992,10 @@ exec_as.mo <- function(x, Becker = FALSE, Lancefield = FALSE,
x
}
empty_result <- function(x) {
x %in% c(NA, "UNKNOWN")
}
TEMPORARY_TAXONOMY <- function(x) {
x[x %like% 'Cutibacterium'] <- gsub('Cutibacterium', 'Propionibacterium', x[x %like% 'Cutibacterium'])
x

View File

@ -364,7 +364,7 @@ mo_translate <- function(x, language) {
}
x_tobetranslated <- grepl(x = x,
pattern = "(Coagulase Negative Staphylococcus|Coagulase Positive Staphylococcus|Beta-haemolytic Streptococcus|unknown Gram negatives|unknown Gram positives|CoNS|CoPS|no MO|Gram negative|Gram positive|Bacteria|Fungi|Protozoa|biogroup|biotype|vegetative|group|Group)")
pattern = "(Coagulase Negative Staphylococcus|Coagulase Positive Staphylococcus|Beta-haemolytic Streptococcus|unknown Gram negatives|unknown Gram positives|unknown name|unknown kingdom|unknown phylum|unknown class|unknown order|unknown family|unknown genus|unknown species|unknown subspecies|unknown rank|CoNS|CoPS|Gram negative|Gram positive|Bacteria|Fungi|Protozoa|biogroup|biotype|vegetative|group|Group)")
if (sum(x_tobetranslated, na.rm = TRUE) == 0) {
return(x)
@ -379,9 +379,18 @@ mo_translate <- function(x, language) {
gsub("Beta-haemolytic Streptococcus", "Beta-h\u00e4molytischer Streptococcus", ., fixed = TRUE) %>%
gsub("unknown Gram negatives", "unbekannte Gramnegativen", ., fixed = TRUE) %>%
gsub("unknown Gram positives", "unbekannte Grampositiven", ., fixed = TRUE) %>%
gsub("unknown name", "unbekannte Name", ., fixed = TRUE) %>%
gsub("unknown kingdom", "unbekanntes Reich", ., fixed = TRUE) %>%
gsub("unknown phylum", "unbekannter Stamm", ., fixed = TRUE) %>%
gsub("unknown class", "unbekannte Klasse", ., fixed = TRUE) %>%
gsub("unknown order", "unbekannte Ordnung", ., fixed = TRUE) %>%
gsub("unknown family", "unbekannte Familie", ., fixed = TRUE) %>%
gsub("unknown genus", "unbekannte Gattung", ., fixed = TRUE) %>%
gsub("unknown species", "unbekannte Art", ., fixed = TRUE) %>%
gsub("unknown subspecies", "unbekannte Unterart", ., fixed = TRUE) %>%
gsub("unknown rank", "unbekannter Rang", ., fixed = TRUE) %>%
gsub("(CoNS)", "(KNS)", ., fixed = TRUE) %>%
gsub("(CoPS)", "(KPS)", ., fixed = TRUE) %>%
gsub("(no MO)", "(kein MO)", ., fixed = TRUE) %>%
gsub("Gram negative", "Gramnegativ", ., fixed = TRUE) %>%
gsub("Gram positive", "Grampositiv", ., fixed = TRUE) %>%
gsub("Bacteria", "Bakterien", ., fixed = TRUE) %>%
@ -401,7 +410,16 @@ mo_translate <- function(x, language) {
gsub("Beta-haemolytic Streptococcus", "Beta-hemolytische Streptococcus", ., fixed = TRUE) %>%
gsub("unknown Gram negatives", "onbekende Gram-negatieven", ., fixed = TRUE) %>%
gsub("unknown Gram positives", "onbekende Gram-positieven", ., fixed = TRUE) %>%
gsub("(no MO)", "(geen MO)", ., fixed = TRUE) %>%
gsub("unknown name", "onbekende naam", ., fixed = TRUE) %>%
gsub("unknown kingdom", "onbekend koninkrijk", ., fixed = TRUE) %>%
gsub("unknown phylum", "onbekende fylum", ., fixed = TRUE) %>%
gsub("unknown class", "onbekende klasse", ., fixed = TRUE) %>%
gsub("unknown order", "onbekende orde", ., fixed = TRUE) %>%
gsub("unknown family", "onbekende familie", ., fixed = TRUE) %>%
gsub("unknown genus", "onbekend geslacht", ., fixed = TRUE) %>%
gsub("unknown species", "onbekende soort", ., fixed = TRUE) %>%
gsub("unknown subspecies", "onbekende ondersoort", ., fixed = TRUE) %>%
gsub("unknown rank", "onbekende rang", ., fixed = TRUE) %>%
gsub("(CoNS)", "(CNS)", ., fixed = TRUE) %>%
gsub("(CoPS)", "(CPS)", ., fixed = TRUE) %>%
gsub("Gram negative", "Gram-negatief", ., fixed = TRUE) %>%
@ -423,7 +441,16 @@ mo_translate <- function(x, language) {
gsub("Beta-haemolytic Streptococcus", "Streptococcus Beta-hemol\u00edtico", ., fixed = TRUE) %>%
gsub("unknown Gram negatives", "Gram negativos desconocidos", ., fixed = TRUE) %>%
gsub("unknown Gram positives", "Gram positivos desconocidos", ., fixed = TRUE) %>%
gsub("(no MO)", "(sin MO)", ., fixed = TRUE) %>%
gsub("unknown name", "nombre desconocido", ., fixed = TRUE) %>%
gsub("unknown kingdom", "reino desconocido", ., fixed = TRUE) %>%
gsub("unknown phylum", "filo desconocido", ., fixed = TRUE) %>%
gsub("unknown class", "clase desconocida", ., fixed = TRUE) %>%
gsub("unknown order", "orden desconocido", ., fixed = TRUE) %>%
gsub("unknown family", "familia desconocida", ., fixed = TRUE) %>%
gsub("unknown genus", "g\u00e9nero desconocido", ., fixed = TRUE) %>%
gsub("unknown species", "especie desconocida", ., fixed = TRUE) %>%
gsub("unknown subspecies", "subespecie desconocida", ., fixed = TRUE) %>%
gsub("unknown rank", "rango desconocido", ., fixed = TRUE) %>%
gsub("Gram negative", "Gram negativo", ., fixed = TRUE) %>%
gsub("Gram positive", "Gram positivo", ., fixed = TRUE) %>%
gsub("Bacteria", "Bacterias", ., fixed = TRUE) %>%
@ -443,7 +470,16 @@ mo_translate <- function(x, language) {
gsub("Beta-haemolytic Streptococcus", "Streptococcus Beta-emolitico", ., fixed = TRUE) %>%
gsub("unknown Gram negatives", "Gram negativi sconosciuti", ., fixed = TRUE) %>%
gsub("unknown Gram positives", "Gram positivi sconosciuti", ., fixed = TRUE) %>%
gsub("(no MO)", "(non MO)", ., fixed = TRUE) %>%
gsub("unknown name", "nome sconosciuto", ., fixed = TRUE) %>%
gsub("unknown kingdom", "regno sconosciuto", ., fixed = TRUE) %>%
gsub("unknown phylum", "phylum sconosciuto", ., fixed = TRUE) %>%
gsub("unknown class", "classe sconosciuta", ., fixed = TRUE) %>%
gsub("unknown order", "ordine sconosciuto", ., fixed = TRUE) %>%
gsub("unknown family", "famiglia sconosciuta", ., fixed = TRUE) %>%
gsub("unknown genus", "genere sconosciuto", ., fixed = TRUE) %>%
gsub("unknown species", "specie sconosciute", ., fixed = TRUE) %>%
gsub("unknown subspecies", "sottospecie sconosciute", ., fixed = TRUE) %>%
gsub("unknown rank", "grado sconosciuto", ., fixed = TRUE) %>%
gsub("Gram negative", "Gram negativo", ., fixed = TRUE) %>%
gsub("Gram positive", "Gram positivo", ., fixed = TRUE) %>%
gsub("Bacteria", "Batteri", ., fixed = TRUE) %>%
@ -462,7 +498,16 @@ mo_translate <- function(x, language) {
gsub("Beta-haemolytic Streptococcus", "Streptococcus B\u00eata-h\u00e9molytique", ., fixed = TRUE) %>%
gsub("unknown Gram negatives", "Gram n\u00e9gatifs inconnus", ., fixed = TRUE) %>%
gsub("unknown Gram positives", "Gram positifs inconnus", ., fixed = TRUE) %>%
gsub("(no MO)", "(pas MO)", ., fixed = TRUE) %>%
gsub("unknown name", "nom inconnu", ., fixed = TRUE) %>%
gsub("unknown kingdom", "r\u00e8gme inconnu", ., fixed = TRUE) %>%
gsub("unknown phylum", "embranchement inconnu", ., fixed = TRUE) %>%
gsub("unknown class", "classe inconnue", ., fixed = TRUE) %>%
gsub("unknown order", "ordre inconnu", ., fixed = TRUE) %>%
gsub("unknown family", "famille inconnue", ., fixed = TRUE) %>%
gsub("unknown genus", "genre inconnu", ., fixed = TRUE) %>%
gsub("unknown species", "esp\u00e8ce inconnue", ., fixed = TRUE) %>%
gsub("unknown subspecies", "sous-esp\u00e8ce inconnue", ., fixed = TRUE) %>%
gsub("unknown rank", "rang inconnu", ., fixed = TRUE) %>%
gsub("Gram negative", "Gram n\u00e9gatif", ., fixed = TRUE) %>%
gsub("Gram positive", "Gram positif", ., fixed = TRUE) %>%
gsub("Bacteria", "Bact\u00e9ries", ., fixed = TRUE) %>%
@ -482,7 +527,16 @@ mo_translate <- function(x, language) {
gsub("Beta-haemolytic Streptococcus", "Streptococcus Beta-hemol\u00edtico", ., fixed = TRUE) %>%
gsub("unknown Gram negatives", "Gram negativos desconhecidos", ., fixed = TRUE) %>%
gsub("unknown Gram positives", "Gram positivos desconhecidos", ., fixed = TRUE) %>%
gsub("(no MO)", "(sem MO)", ., fixed = TRUE) %>%
gsub("unknown name", "nome desconhecido", ., fixed = TRUE) %>%
gsub("unknown kingdom", "reino desconhecido", ., fixed = TRUE) %>%
gsub("unknown phylum", "filo desconhecido", ., fixed = TRUE) %>%
gsub("unknown class", "classe desconhecida", ., fixed = TRUE) %>%
gsub("unknown order", "ordem desconhecido", ., fixed = TRUE) %>%
gsub("unknown family", "fam\u00edlia desconhecida", ., fixed = TRUE) %>%
gsub("unknown genus", "g\u00eanero desconhecido", ., fixed = TRUE) %>%
gsub("unknown species", "esp\u00e9cies desconhecida", ., fixed = TRUE) %>%
gsub("unknown subspecies", "subesp\u00e9cies desconhecida", ., fixed = TRUE) %>%
gsub("unknown rank", "classifica\u00e7\u00e3o desconhecido", ., fixed = TRUE) %>%
gsub("Gram negative", "Gram negativo", ., fixed = TRUE) %>%
gsub("Gram positive", "Gram positivo", ., fixed = TRUE) %>%
gsub("Bacteria", "Bact\u00e9rias", ., fixed = TRUE) %>%

View File

@ -76,6 +76,9 @@ as.rsi <- function(x) {
x <- gsub(' +', '', x)
# remove all MIC-like values: numbers, operators and periods
x <- gsub('[0-9.,;:<=>]+', '', x)
# remove everything between brackets, and 'high' and 'low'
x <- gsub("([(].*[)])", "", x)
x <- gsub("(high|low)", "", x, ignore.case = TRUE)
# disallow more than 3 characters
x[nchar(x) > 3] <- NA
# set to capitals

View File

@ -55,6 +55,7 @@ make <- function() {
mutate(prevalence = case_when(
class == "Gammaproteobacteria"
| genus %in% c("Enterococcus", "Staphylococcus", "Streptococcus")
| mo == "UNKNOWN"
~ 1,
phylum %in% c("Proteobacteria",
"Firmicutes",

Binary file not shown.

View File

@ -192,7 +192,7 @@
<h1>How to conduct AMR analysis</h1>
<h4 class="author">Matthijs S. Berends</h4>
<h4 class="date">01 March 2019</h4>
<h4 class="date">02 March 2019</h4>
<div class="hidden name"><code>AMR.Rmd</code></div>
@ -201,7 +201,7 @@
<p><strong>Note:</strong> values on this page will change with every website update since they are based on randomly created values and the page was written in <a href="https://rmarkdown.rstudio.com/">RMarkdown</a>. However, the methodology remains unchanged. This page was generated on 01 March 2019.</p>
<p><strong>Note:</strong> values on this page will change with every website update since they are based on randomly created values and the page was written in <a href="https://rmarkdown.rstudio.com/">RMarkdown</a>. However, the methodology remains unchanged. This page was generated on 02 March 2019.</p>
<div id="introduction" class="section level1">
<h1 class="hasAnchor">
<a href="#introduction" class="anchor"></a>Introduction</h1>
@ -217,21 +217,21 @@
</tr></thead>
<tbody>
<tr class="odd">
<td align="center">2019-03-01</td>
<td align="center">2019-03-02</td>
<td align="center">abcd</td>
<td align="center">Escherichia coli</td>
<td align="center">S</td>
<td align="center">S</td>
</tr>
<tr class="even">
<td align="center">2019-03-01</td>
<td align="center">2019-03-02</td>
<td align="center">abcd</td>
<td align="center">Escherichia coli</td>
<td align="center">S</td>
<td align="center">R</td>
</tr>
<tr class="odd">
<td align="center">2019-03-01</td>
<td align="center">2019-03-02</td>
<td align="center">efgh</td>
<td align="center">Escherichia coli</td>
<td align="center">R</td>
@ -327,53 +327,9 @@
</tr></thead>
<tbody>
<tr class="odd">
<td align="center">2017-06-13</td>
<td align="center">Z3</td>
<td align="center">Hospital D</td>
<td align="center">Escherichia coli</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">F</td>
</tr>
<tr class="even">
<td align="center">2013-09-13</td>
<td align="center">A1</td>
<td align="center">Hospital D</td>
<td align="center">Escherichia coli</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">M</td>
</tr>
<tr class="odd">
<td align="center">2015-06-10</td>
<td align="center">L8</td>
<td align="center">Hospital B</td>
<td align="center">Escherichia coli</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">M</td>
</tr>
<tr class="even">
<td align="center">2010-08-05</td>
<td align="center">A7</td>
<td align="center">Hospital D</td>
<td align="center">Klebsiella pneumoniae</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">M</td>
</tr>
<tr class="odd">
<td align="center">2011-08-25</td>
<td align="center">X4</td>
<td align="center">Hospital C</td>
<td align="center">2012-06-30</td>
<td align="center">W5</td>
<td align="center">Hospital A</td>
<td align="center">Staphylococcus aureus</td>
<td align="center">S</td>
<td align="center">S</td>
@ -382,14 +338,58 @@
<td align="center">F</td>
</tr>
<tr class="even">
<td align="center">2011-03-09</td>
<td align="center">B7</td>
<td align="center">Hospital D</td>
<td align="center">2012-07-07</td>
<td align="center">T4</td>
<td align="center">Hospital B</td>
<td align="center">Escherichia coli</td>
<td align="center">R</td>
<td align="center">R</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">F</td>
</tr>
<tr class="odd">
<td align="center">2011-02-19</td>
<td align="center">H3</td>
<td align="center">Hospital B</td>
<td align="center">Escherichia coli</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">M</td>
</tr>
<tr class="even">
<td align="center">2012-12-15</td>
<td align="center">G10</td>
<td align="center">Hospital C</td>
<td align="center">Klebsiella pneumoniae</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">M</td>
</tr>
<tr class="odd">
<td align="center">2010-09-11</td>
<td align="center">L4</td>
<td align="center">Hospital D</td>
<td align="center">Staphylococcus aureus</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">M</td>
</tr>
<tr class="even">
<td align="center">2011-03-27</td>
<td align="center">H5</td>
<td align="center">Hospital A</td>
<td align="center">Escherichia coli</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">M</td>
</tr>
</tbody>
@ -411,8 +411,8 @@
#&gt;
#&gt; Item Count Percent Cum. Count Cum. Percent
#&gt; --- ----- ------- -------- ----------- -------------
#&gt; 1 M 10,311 51.6% 10,311 51.6%
#&gt; 2 F 9,689 48.4% 20,000 100.0%</code></pre>
#&gt; 1 M 10,433 52.2% 10,433 52.2%
#&gt; 2 F 9,567 47.8% 20,000 100.0%</code></pre>
<p>So, we can draw at least two conclusions immediately. From a data scientist perspective, the data looks clean: only values <code>M</code> and <code>F</code>. From a researcher perspective: there are slightly more men. Nothing we didnt already know.</p>
<p>The data is already quite clean, but we still need to transform some variables. The <code>bacteria</code> column now consists of text, and we want to add more variables based on microbial IDs later on. So, we will transform this column to valid IDs. The <code><a href="https://dplyr.tidyverse.org/reference/mutate.html">mutate()</a></code> function of the <code>dplyr</code> package makes this really easy:</p>
<div class="sourceCode" id="cb12"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb12-1" title="1">data &lt;-<span class="st"> </span>data <span class="op">%&gt;%</span></a>
@ -443,10 +443,10 @@
<a class="sourceLine" id="cb14-19" title="19"><span class="co">#&gt; Kingella kingae (no changes)</span></a>
<a class="sourceLine" id="cb14-20" title="20"><span class="co">#&gt; </span></a>
<a class="sourceLine" id="cb14-21" title="21"><span class="co">#&gt; EUCAST Expert Rules, Intrinsic Resistance and Exceptional Phenotypes (v3.1, 2016)</span></a>
<a class="sourceLine" id="cb14-22" title="22"><span class="co">#&gt; Table 1: Intrinsic resistance in Enterobacteriaceae (1364 changes)</span></a>
<a class="sourceLine" id="cb14-22" title="22"><span class="co">#&gt; Table 1: Intrinsic resistance in Enterobacteriaceae (1323 changes)</span></a>
<a class="sourceLine" id="cb14-23" title="23"><span class="co">#&gt; Table 2: Intrinsic resistance in non-fermentative Gram-negative bacteria (no changes)</span></a>
<a class="sourceLine" id="cb14-24" title="24"><span class="co">#&gt; Table 3: Intrinsic resistance in other Gram-negative bacteria (no changes)</span></a>
<a class="sourceLine" id="cb14-25" title="25"><span class="co">#&gt; Table 4: Intrinsic resistance in Gram-positive bacteria (2659 changes)</span></a>
<a class="sourceLine" id="cb14-25" title="25"><span class="co">#&gt; Table 4: Intrinsic resistance in Gram-positive bacteria (2834 changes)</span></a>
<a class="sourceLine" id="cb14-26" title="26"><span class="co">#&gt; Table 8: Interpretive rules for B-lactam agents and Gram-positive cocci (no changes)</span></a>
<a class="sourceLine" id="cb14-27" title="27"><span class="co">#&gt; Table 9: Interpretive rules for B-lactam agents and Gram-negative rods (no changes)</span></a>
<a class="sourceLine" id="cb14-28" title="28"><span class="co">#&gt; Table 10: Interpretive rules for B-lactam agents and other Gram-negative bacteria (no changes)</span></a>
@ -462,9 +462,9 @@
<a class="sourceLine" id="cb14-38" title="38"><span class="co">#&gt; Non-EUCAST: piperacillin/tazobactam = S where piperacillin = S (no changes)</span></a>
<a class="sourceLine" id="cb14-39" title="39"><span class="co">#&gt; Non-EUCAST: trimethoprim/sulfa = S where trimethoprim = S (no changes)</span></a>
<a class="sourceLine" id="cb14-40" title="40"><span class="co">#&gt; </span></a>
<a class="sourceLine" id="cb14-41" title="41"><span class="co">#&gt; =&gt; EUCAST rules affected 7,366 out of 20,000 rows</span></a>
<a class="sourceLine" id="cb14-41" title="41"><span class="co">#&gt; =&gt; EUCAST rules affected 7,524 out of 20,000 rows</span></a>
<a class="sourceLine" id="cb14-42" title="42"><span class="co">#&gt; -&gt; added 0 test results</span></a>
<a class="sourceLine" id="cb14-43" title="43"><span class="co">#&gt; -&gt; changed 4,023 test results (0 to S; 0 to I; 4,023 to R)</span></a></code></pre></div>
<a class="sourceLine" id="cb14-43" title="43"><span class="co">#&gt; -&gt; changed 4,157 test results (0 to S; 0 to I; 4,157 to R)</span></a></code></pre></div>
</div>
<div id="adding-new-variables" class="section level1">
<h1 class="hasAnchor">
@ -489,8 +489,8 @@
<a class="sourceLine" id="cb16-3" title="3"><span class="co">#&gt; </span><span class="al">NOTE</span><span class="co">: Using column `bacteria` as input for `col_mo`.</span></a>
<a class="sourceLine" id="cb16-4" title="4"><span class="co">#&gt; </span><span class="al">NOTE</span><span class="co">: Using column `date` as input for `col_date`.</span></a>
<a class="sourceLine" id="cb16-5" title="5"><span class="co">#&gt; </span><span class="al">NOTE</span><span class="co">: Using column `patient_id` as input for `col_patient_id`.</span></a>
<a class="sourceLine" id="cb16-6" title="6"><span class="co">#&gt; =&gt; Found 5,641 first isolates (28.2% of total)</span></a></code></pre></div>
<p>So only 28.2% is suitable for resistance analysis! We can now filter on it with the <code><a href="https://dplyr.tidyverse.org/reference/filter.html">filter()</a></code> function, also from the <code>dplyr</code> package:</p>
<a class="sourceLine" id="cb16-6" title="6"><span class="co">#&gt; =&gt; Found 5,698 first isolates (28.5% of total)</span></a></code></pre></div>
<p>So only 28.5% is suitable for resistance analysis! We can now filter on it with the <code><a href="https://dplyr.tidyverse.org/reference/filter.html">filter()</a></code> function, also from the <code>dplyr</code> package:</p>
<div class="sourceCode" id="cb17"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb17-1" title="1">data_1st &lt;-<span class="st"> </span>data <span class="op">%&gt;%</span><span class="st"> </span></a>
<a class="sourceLine" id="cb17-2" title="2"><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/filter.html">filter</a></span>(first <span class="op">==</span><span class="st"> </span><span class="ot">TRUE</span>)</a></code></pre></div>
<p>For future use, the above two syntaxes can be shortened with the <code><a href="../reference/first_isolate.html">filter_first_isolate()</a></code> function:</p>
@ -516,10 +516,10 @@
<tbody>
<tr class="odd">
<td align="center">1</td>
<td align="center">2010-01-14</td>
<td align="center">K8</td>
<td align="center">2010-01-18</td>
<td align="center">C7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
@ -527,30 +527,30 @@
</tr>
<tr class="even">
<td align="center">2</td>
<td align="center">2010-02-17</td>
<td align="center">K8</td>
<td align="center">2010-02-27</td>
<td align="center">C7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">FALSE</td>
</tr>
<tr class="odd">
<td align="center">3</td>
<td align="center">2010-03-01</td>
<td align="center">K8</td>
<td align="center">2010-04-22</td>
<td align="center">C7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">FALSE</td>
</tr>
<tr class="even">
<td align="center">4</td>
<td align="center">2010-03-11</td>
<td align="center">K8</td>
<td align="center">2010-06-09</td>
<td align="center">C7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">S</td>
@ -560,54 +560,54 @@
</tr>
<tr class="odd">
<td align="center">5</td>
<td align="center">2010-04-13</td>
<td align="center">K8</td>
<td align="center">2011-04-13</td>
<td align="center">C7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">R</td>
<td align="center">FALSE</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">TRUE</td>
</tr>
<tr class="even">
<td align="center">6</td>
<td align="center">2010-08-30</td>
<td align="center">K8</td>
<td align="center">2011-04-25</td>
<td align="center">C7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">FALSE</td>
</tr>
<tr class="odd">
<td align="center">7</td>
<td align="center">2010-11-05</td>
<td align="center">K8</td>
<td align="center">2011-08-02</td>
<td align="center">C7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">FALSE</td>
</tr>
<tr class="even">
<td align="center">8</td>
<td align="center">2010-12-21</td>
<td align="center">K8</td>
<td align="center">2011-10-19</td>
<td align="center">C7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">I</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">FALSE</td>
</tr>
<tr class="odd">
<td align="center">9</td>
<td align="center">2010-12-21</td>
<td align="center">K8</td>
<td align="center">2011-10-23</td>
<td align="center">C7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
@ -615,14 +615,14 @@
</tr>
<tr class="even">
<td align="center">10</td>
<td align="center">2011-03-20</td>
<td align="center">K8</td>
<td align="center">2011-11-10</td>
<td align="center">C7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">TRUE</td>
<td align="center">FALSE</td>
</tr>
</tbody>
</table>
@ -637,7 +637,7 @@
<a class="sourceLine" id="cb19-7" title="7"><span class="co">#&gt; </span><span class="al">NOTE</span><span class="co">: Using column `patient_id` as input for `col_patient_id`.</span></a>
<a class="sourceLine" id="cb19-8" title="8"><span class="co">#&gt; </span><span class="al">NOTE</span><span class="co">: Using column `keyab` as input for `col_keyantibiotics`. Use col_keyantibiotics = FALSE to prevent this.</span></a>
<a class="sourceLine" id="cb19-9" title="9"><span class="co">#&gt; [Criterion] Inclusion based on key antibiotics, ignoring I.</span></a>
<a class="sourceLine" id="cb19-10" title="10"><span class="co">#&gt; =&gt; Found 15,738 first weighted isolates (78.7% of total)</span></a></code></pre></div>
<a class="sourceLine" id="cb19-10" title="10"><span class="co">#&gt; =&gt; Found 15,826 first weighted isolates (79.1% of total)</span></a></code></pre></div>
<table class="table">
<thead><tr class="header">
<th align="center">isolate</th>
@ -654,10 +654,10 @@
<tbody>
<tr class="odd">
<td align="center">1</td>
<td align="center">2010-01-14</td>
<td align="center">K8</td>
<td align="center">2010-01-18</td>
<td align="center">C7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
@ -666,94 +666,94 @@
</tr>
<tr class="even">
<td align="center">2</td>
<td align="center">2010-02-17</td>
<td align="center">K8</td>
<td align="center">2010-02-27</td>
<td align="center">C7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">FALSE</td>
<td align="center">TRUE</td>
<td align="center">FALSE</td>
</tr>
<tr class="odd">
<td align="center">3</td>
<td align="center">2010-03-01</td>
<td align="center">K8</td>
<td align="center">2010-04-22</td>
<td align="center">C7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">FALSE</td>
<td align="center">TRUE</td>
<td align="center">FALSE</td>
</tr>
<tr class="even">
<td align="center">4</td>
<td align="center">2010-03-11</td>
<td align="center">K8</td>
<td align="center">2010-06-09</td>
<td align="center">C7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">FALSE</td>
<td align="center">TRUE</td>
<td align="center">FALSE</td>
</tr>
<tr class="odd">
<td align="center">5</td>
<td align="center">2010-04-13</td>
<td align="center">K8</td>
<td align="center">2011-04-13</td>
<td align="center">C7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">R</td>
<td align="center">FALSE</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">TRUE</td>
<td align="center">TRUE</td>
</tr>
<tr class="even">
<td align="center">6</td>
<td align="center">2010-08-30</td>
<td align="center">K8</td>
<td align="center">2011-04-25</td>
<td align="center">C7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">FALSE</td>
<td align="center">TRUE</td>
</tr>
<tr class="odd">
<td align="center">7</td>
<td align="center">2010-11-05</td>
<td align="center">K8</td>
<td align="center">2011-08-02</td>
<td align="center">C7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">FALSE</td>
<td align="center">TRUE</td>
</tr>
<tr class="even">
<td align="center">8</td>
<td align="center">2010-12-21</td>
<td align="center">K8</td>
<td align="center">2011-10-19</td>
<td align="center">C7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">I</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">FALSE</td>
<td align="center">FALSE</td>
<td align="center">TRUE</td>
</tr>
<tr class="odd">
<td align="center">9</td>
<td align="center">2010-12-21</td>
<td align="center">K8</td>
<td align="center">2011-10-23</td>
<td align="center">C7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
@ -762,23 +762,23 @@
</tr>
<tr class="even">
<td align="center">10</td>
<td align="center">2011-03-20</td>
<td align="center">K8</td>
<td align="center">2011-11-10</td>
<td align="center">C7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">TRUE</td>
<td align="center">FALSE</td>
<td align="center">TRUE</td>
</tr>
</tbody>
</table>
<p>Instead of 2, now 9 isolates are flagged. In total, 78.7% of all isolates are marked first weighted - 50.5% more than when using the CLSI guideline. In real life, this novel algorithm will yield 5-10% more isolates than the classic CLSI guideline.</p>
<p>Instead of 2, now 7 isolates are flagged. In total, 79.1% of all isolates are marked first weighted - 50.6% more than when using the CLSI guideline. In real life, this novel algorithm will yield 5-10% more isolates than the classic CLSI guideline.</p>
<p>As with <code><a href="../reference/first_isolate.html">filter_first_isolate()</a></code>, theres a shortcut for this new algorithm too:</p>
<div class="sourceCode" id="cb20"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb20-1" title="1">data_1st &lt;-<span class="st"> </span>data <span class="op">%&gt;%</span><span class="st"> </span></a>
<a class="sourceLine" id="cb20-2" title="2"><span class="st"> </span><span class="kw"><a href="../reference/first_isolate.html">filter_first_weighted_isolate</a></span>()</a></code></pre></div>
<p>So we end up with 15,738 isolates for analysis.</p>
<p>So we end up with 15,826 isolates for analysis.</p>
<p>We can remove unneeded columns:</p>
<div class="sourceCode" id="cb21"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb21-1" title="1">data_1st &lt;-<span class="st"> </span>data_1st <span class="op">%&gt;%</span><span class="st"> </span></a>
<a class="sourceLine" id="cb21-2" title="2"><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/select.html">select</a></span>(<span class="op">-</span><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/c">c</a></span>(first, keyab))</a></code></pre></div>
@ -803,14 +803,14 @@
</tr></thead>
<tbody>
<tr class="odd">
<td>1</td>
<td align="center">2017-06-13</td>
<td align="center">Z3</td>
<td align="center">Hospital D</td>
<td>2</td>
<td align="center">2012-07-07</td>
<td align="center">T4</td>
<td align="center">Hospital B</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">F</td>
<td align="center">Gram negative</td>
@ -820,12 +820,12 @@
</tr>
<tr class="even">
<td>3</td>
<td align="center">2015-06-10</td>
<td align="center">L8</td>
<td align="center">2011-02-19</td>
<td align="center">H3</td>
<td align="center">Hospital B</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">M</td>
@ -835,69 +835,69 @@
<td align="center">TRUE</td>
</tr>
<tr class="odd">
<td>6</td>
<td align="center">2011-03-09</td>
<td align="center">B7</td>
<td align="center">Hospital D</td>
<td align="center">B_ESCHR_COL</td>
<td>4</td>
<td align="center">2012-12-15</td>
<td align="center">G10</td>
<td align="center">Hospital C</td>
<td align="center">B_KLBSL_PNE</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">M</td>
<td align="center">Gram negative</td>
<td align="center">Klebsiella</td>
<td align="center">pneumoniae</td>
<td align="center">TRUE</td>
</tr>
<tr class="even">
<td>6</td>
<td align="center">2011-03-27</td>
<td align="center">H5</td>
<td align="center">Hospital A</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">M</td>
<td align="center">Gram negative</td>
<td align="center">Escherichia</td>
<td align="center">coli</td>
<td align="center">TRUE</td>
</tr>
<tr class="even">
<td>8</td>
<td align="center">2015-03-15</td>
<td align="center">O1</td>
<tr class="odd">
<td>7</td>
<td align="center">2012-06-22</td>
<td align="center">Q8</td>
<td align="center">Hospital A</td>
<td align="center">B_STPHY_AUR</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">R</td>
<td align="center">I</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">F</td>
<td align="center">Gram positive</td>
<td align="center">Staphylococcus</td>
<td align="center">aureus</td>
<td align="center">TRUE</td>
</tr>
<tr class="odd">
<td>9</td>
<td align="center">2012-09-07</td>
<td align="center">K5</td>
<td align="center">Hospital C</td>
<tr class="even">
<td>8</td>
<td align="center">2015-06-27</td>
<td align="center">Q2</td>
<td align="center">Hospital B</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">M</td>
<td align="center">F</td>
<td align="center">Gram negative</td>
<td align="center">Escherichia</td>
<td align="center">coli</td>
<td align="center">TRUE</td>
</tr>
<tr class="even">
<td>10</td>
<td align="center">2015-08-09</td>
<td align="center">R5</td>
<td align="center">Hospital D</td>
<td align="center">B_STRPT_PNE</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">F</td>
<td align="center">Gram positive</td>
<td align="center">Streptococcus</td>
<td align="center">pneumoniae</td>
<td align="center">TRUE</td>
</tr>
</tbody>
</table>
<p>Time for the analysis!</p>
@ -915,9 +915,9 @@
<div class="sourceCode" id="cb23"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb23-1" title="1"><span class="kw"><a href="../reference/freq.html">freq</a></span>(<span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/paste">paste</a></span>(data_1st<span class="op">$</span>genus, data_1st<span class="op">$</span>species))</a></code></pre></div>
<p>Or can be used like the <code>dplyr</code> way, which is easier readable:</p>
<div class="sourceCode" id="cb24"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb24-1" title="1">data_1st <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="../reference/freq.html">freq</a></span>(genus, species)</a></code></pre></div>
<p><strong>Frequency table of <code>genus</code> and <code>species</code> from a <code>data.frame</code> (15,738 x 13)</strong></p>
<p><strong>Frequency table of <code>genus</code> and <code>species</code> from a <code>data.frame</code> (15,826 x 13)</strong></p>
<p>Columns: 2<br>
Length: 15,738 (of which NA: 0 = 0.00%)<br>
Length: 15,826 (of which NA: 0 = 0.00%)<br>
Unique: 4</p>
<p>Shortest: 16<br>
Longest: 24</p>
@ -934,33 +934,33 @@ Longest: 24</p>
<tr class="odd">
<td align="left">1</td>
<td align="left">Escherichia coli</td>
<td align="right">7,875</td>
<td align="right">50.0%</td>
<td align="right">7,875</td>
<td align="right">50.0%</td>
<td align="right">7,714</td>
<td align="right">48.7%</td>
<td align="right">7,714</td>
<td align="right">48.7%</td>
</tr>
<tr class="even">
<td align="left">2</td>
<td align="left">Staphylococcus aureus</td>
<td align="right">3,897</td>
<td align="right">24.8%</td>
<td align="right">11,772</td>
<td align="right">74.8%</td>
<td align="right">3,977</td>
<td align="right">25.1%</td>
<td align="right">11,691</td>
<td align="right">73.9%</td>
</tr>
<tr class="odd">
<td align="left">3</td>
<td align="left">Streptococcus pneumoniae</td>
<td align="right">2,400</td>
<td align="right">15.2%</td>
<td align="right">14,172</td>
<td align="right">90.0%</td>
<td align="right">2,514</td>
<td align="right">15.9%</td>
<td align="right">14,205</td>
<td align="right">89.8%</td>
</tr>
<tr class="even">
<td align="left">4</td>
<td align="left">Klebsiella pneumoniae</td>
<td align="right">1,566</td>
<td align="right">10.0%</td>
<td align="right">15,738</td>
<td align="right">1,621</td>
<td align="right">10.2%</td>
<td align="right">15,826</td>
<td align="right">100.0%</td>
</tr>
</tbody>
@ -971,7 +971,7 @@ Longest: 24</p>
<a href="#resistance-percentages" class="anchor"></a>Resistance percentages</h2>
<p>The functions <code><a href="../reference/portion.html">portion_R()</a></code>, <code>portion_RI()</code>, <code><a href="../reference/portion.html">portion_I()</a></code>, <code>portion_IS()</code> and <code><a href="../reference/portion.html">portion_S()</a></code> can be used to determine the portion of a specific antimicrobial outcome. They can be used on their own:</p>
<div class="sourceCode" id="cb25"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb25-1" title="1">data_1st <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="../reference/portion.html">portion_IR</a></span>(amox)</a>
<a class="sourceLine" id="cb25-2" title="2"><span class="co">#&gt; [1] 0.4757911</span></a></code></pre></div>
<a class="sourceLine" id="cb25-2" title="2"><span class="co">#&gt; [1] 0.4830027</span></a></code></pre></div>
<p>Or can be used in conjuction with <code><a href="https://dplyr.tidyverse.org/reference/group_by.html">group_by()</a></code> and <code><a href="https://dplyr.tidyverse.org/reference/summarise.html">summarise()</a></code>, both from the <code>dplyr</code> package:</p>
<div class="sourceCode" id="cb26"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb26-1" title="1">data_1st <span class="op">%&gt;%</span><span class="st"> </span></a>
<a class="sourceLine" id="cb26-2" title="2"><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/group_by.html">group_by</a></span>(hospital) <span class="op">%&gt;%</span><span class="st"> </span></a>
@ -984,19 +984,19 @@ Longest: 24</p>
<tbody>
<tr class="odd">
<td align="center">Hospital A</td>
<td align="center">0.4800594</td>
<td align="center">0.4798820</td>
</tr>
<tr class="even">
<td align="center">Hospital B</td>
<td align="center">0.4737983</td>
<td align="center">0.4792835</td>
</tr>
<tr class="odd">
<td align="center">Hospital C</td>
<td align="center">0.4763514</td>
<td align="center">0.4863714</td>
</tr>
<tr class="even">
<td align="center">Hospital D</td>
<td align="center">0.4724536</td>
<td align="center">0.4915730</td>
</tr>
</tbody>
</table>
@ -1014,23 +1014,23 @@ Longest: 24</p>
<tbody>
<tr class="odd">
<td align="center">Hospital A</td>
<td align="center">0.4800594</td>
<td align="center">4714</td>
<td align="center">0.4798820</td>
<td align="center">4747</td>
</tr>
<tr class="even">
<td align="center">Hospital B</td>
<td align="center">0.4737983</td>
<td align="center">5534</td>
<td align="center">0.4792835</td>
<td align="center">5527</td>
</tr>
<tr class="odd">
<td align="center">Hospital C</td>
<td align="center">0.4763514</td>
<td align="center">2368</td>
<td align="center">0.4863714</td>
<td align="center">2348</td>
</tr>
<tr class="even">
<td align="center">Hospital D</td>
<td align="center">0.4724536</td>
<td align="center">3122</td>
<td align="center">0.4915730</td>
<td align="center">3204</td>
</tr>
</tbody>
</table>
@ -1050,27 +1050,27 @@ Longest: 24</p>
<tbody>
<tr class="odd">
<td align="center">Escherichia</td>
<td align="center">0.7283810</td>
<td align="center">0.9015873</td>
<td align="center">0.9751111</td>
<td align="center">0.7313975</td>
<td align="center">0.8940887</td>
<td align="center">0.9752398</td>
</tr>
<tr class="even">
<td align="center">Klebsiella</td>
<td align="center">0.7311622</td>
<td align="center">0.9157088</td>
<td align="center">0.9750958</td>
<td align="center">0.7143738</td>
<td align="center">0.8994448</td>
<td align="center">0.9697717</td>
</tr>
<tr class="odd">
<td align="center">Staphylococcus</td>
<td align="center">0.7251732</td>
<td align="center">0.9230177</td>
<td align="center">0.9799846</td>
<td align="center">0.7301986</td>
<td align="center">0.9104853</td>
<td align="center">0.9786271</td>
</tr>
<tr class="even">
<td align="center">Streptococcus</td>
<td align="center">0.7345833</td>
<td align="center">0.7430390</td>
<td align="center">0.0000000</td>
<td align="center">0.7345833</td>
<td align="center">0.7430390</td>
</tr>
</tbody>
</table>

Binary file not shown.

Before

Width:  |  Height:  |  Size: 35 KiB

After

Width:  |  Height:  |  Size: 35 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 21 KiB

After

Width:  |  Height:  |  Size: 21 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 68 KiB

After

Width:  |  Height:  |  Size: 68 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 50 KiB

After

Width:  |  Height:  |  Size: 50 KiB

View File

@ -192,7 +192,7 @@
<h1>How to apply EUCAST rules</h1>
<h4 class="author">Matthijs S. Berends</h4>
<h4 class="date">01 March 2019</h4>
<h4 class="date">02 March 2019</h4>
<div class="hidden name"><code>EUCAST.Rmd</code></div>

View File

@ -192,7 +192,7 @@
<h1>How to use the <em>G</em>-test</h1>
<h4 class="author">Matthijs S. Berends</h4>
<h4 class="date">01 March 2019</h4>
<h4 class="date">02 March 2019</h4>
<div class="hidden name"><code>G_test.Rmd</code></div>

View File

@ -192,7 +192,7 @@
<h1>How to work with WHONET data</h1>
<h4 class="author">Matthijs S. Berends</h4>
<h4 class="date">01 March 2019</h4>
<h4 class="date">02 March 2019</h4>
<div class="hidden name"><code>WHONET.Rmd</code></div>

View File

@ -192,7 +192,7 @@
<h1>How to get properties of an antibiotic</h1>
<h4 class="author">Matthijs S. Berends</h4>
<h4 class="date">01 March 2019</h4>
<h4 class="date">02 March 2019</h4>
<div class="hidden name"><code>atc_property.Rmd</code></div>

View File

@ -192,7 +192,7 @@
<h1>Benchmarks</h1>
<h4 class="author">Matthijs S. Berends</h4>
<h4 class="date">01 March 2019</h4>
<h4 class="date">02 March 2019</h4>
<div class="hidden name"><code>benchmarks.Rmd</code></div>
@ -217,14 +217,14 @@
<a class="sourceLine" id="cb2-8" title="8"> <span class="dt">times =</span> <span class="dv">10</span>)</a>
<a class="sourceLine" id="cb2-9" title="9"><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/print">print</a></span>(S.aureus, <span class="dt">unit =</span> <span class="st">"ms"</span>, <span class="dt">signif =</span> <span class="dv">3</span>)</a>
<a class="sourceLine" id="cb2-10" title="10"><span class="co">#&gt; Unit: milliseconds</span></a>
<a class="sourceLine" id="cb2-11" title="11"><span class="co">#&gt; expr min lq mean median uq max neval</span></a>
<a class="sourceLine" id="cb2-12" title="12"><span class="co">#&gt; as.mo("sau") 16.6 16.70 25.10 16.70 18.30 58.00 10</span></a>
<a class="sourceLine" id="cb2-13" title="13"><span class="co">#&gt; as.mo("stau") 31.8 31.90 36.20 31.90 31.90 74.90 10</span></a>
<a class="sourceLine" id="cb2-14" title="14"><span class="co">#&gt; as.mo("staaur") 16.7 16.80 30.70 16.90 57.80 72.20 10</span></a>
<a class="sourceLine" id="cb2-15" title="15"><span class="co">#&gt; as.mo("STAAUR") 16.7 16.70 16.80 16.80 16.80 17.30 10</span></a>
<a class="sourceLine" id="cb2-16" title="16"><span class="co">#&gt; as.mo("S. aureus") 24.6 24.70 33.60 24.70 25.00 70.40 10</span></a>
<a class="sourceLine" id="cb2-17" title="17"><span class="co">#&gt; as.mo("S. aureus") 24.6 24.70 29.10 24.70 24.80 67.20 10</span></a>
<a class="sourceLine" id="cb2-18" title="18"><span class="co">#&gt; as.mo("Staphylococcus aureus") 7.5 7.51 7.67 7.58 7.91 7.97 10</span></a></code></pre></div>
<a class="sourceLine" id="cb2-11" title="11"><span class="co">#&gt; expr min lq mean median uq max neval</span></a>
<a class="sourceLine" id="cb2-12" title="12"><span class="co">#&gt; as.mo("sau") 16.60 16.70 16.90 16.70 16.80 18.20 10</span></a>
<a class="sourceLine" id="cb2-13" title="13"><span class="co">#&gt; as.mo("stau") 31.80 32.00 44.30 32.10 72.40 73.60 10</span></a>
<a class="sourceLine" id="cb2-14" title="14"><span class="co">#&gt; as.mo("staaur") 16.70 16.70 16.80 16.70 16.80 17.30 10</span></a>
<a class="sourceLine" id="cb2-15" title="15"><span class="co">#&gt; as.mo("STAAUR") 16.70 16.80 35.20 18.60 58.00 73.00 10</span></a>
<a class="sourceLine" id="cb2-16" title="16"><span class="co">#&gt; as.mo("S. aureus") 24.60 24.60 33.50 24.70 24.90 68.70 10</span></a>
<a class="sourceLine" id="cb2-17" title="17"><span class="co">#&gt; as.mo("S. aureus") 24.50 24.70 25.30 24.90 26.00 26.40 10</span></a>
<a class="sourceLine" id="cb2-18" title="18"><span class="co">#&gt; as.mo("Staphylococcus aureus") 7.35 7.45 7.53 7.51 7.56 7.97 10</span></a></code></pre></div>
<p>In the table above, all measurements are shown in milliseconds (thousands of seconds). A value of 5 milliseconds means it can determine 200 input values per second. It case of 100 milliseconds, this is only 10 input values per second. The second input is the only one that has to be looked up thoroughly. All the others are known codes (the first one is a WHONET code) or common laboratory codes, or common full organism names like the last one. Full organism names are always preferred.</p>
<p>To achieve this speed, the <code>as.mo</code> function also takes into account the prevalence of human pathogenic microorganisms. The downside is of course that less prevalent microorganisms will be determined less fast. See this example for the ID of <em>Thermus islandicus</em> (<code>B_THERMS_ISL</code>), a bug probably never found before in humans:</p>
<div class="sourceCode" id="cb3"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb3-1" title="1">T.islandicus &lt;-<span class="st"> </span><span class="kw"><a href="https://www.rdocumentation.org/packages/microbenchmark/topics/microbenchmark">microbenchmark</a></span>(<span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"theisl"</span>),</a>
@ -236,11 +236,11 @@
<a class="sourceLine" id="cb3-7" title="7"><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/print">print</a></span>(T.islandicus, <span class="dt">unit =</span> <span class="st">"ms"</span>, <span class="dt">signif =</span> <span class="dv">3</span>)</a>
<a class="sourceLine" id="cb3-8" title="8"><span class="co">#&gt; Unit: milliseconds</span></a>
<a class="sourceLine" id="cb3-9" title="9"><span class="co">#&gt; expr min lq mean median uq max neval</span></a>
<a class="sourceLine" id="cb3-10" title="10"><span class="co">#&gt; as.mo("theisl") 262.0 264.0 297.0 306 310 376 10</span></a>
<a class="sourceLine" id="cb3-11" title="11"><span class="co">#&gt; as.mo("THEISL") 262.0 265.0 292.0 290 308 355 10</span></a>
<a class="sourceLine" id="cb3-12" title="12"><span class="co">#&gt; as.mo("T. islandicus") 142.0 142.0 161.0 148 185 186 10</span></a>
<a class="sourceLine" id="cb3-13" title="13"><span class="co">#&gt; as.mo("T. islandicus") 141.0 142.0 184.0 174 188 340 10</span></a>
<a class="sourceLine" id="cb3-14" title="14"><span class="co">#&gt; as.mo("Thermus islandicus") 68.4 68.8 96.3 110 115 125 10</span></a></code></pre></div>
<a class="sourceLine" id="cb3-10" title="10"><span class="co">#&gt; as.mo("theisl") 265.0 268.0 294.0 307.0 312 321 10</span></a>
<a class="sourceLine" id="cb3-11" title="11"><span class="co">#&gt; as.mo("THEISL") 264.0 264.0 312.0 307.0 316 464 10</span></a>
<a class="sourceLine" id="cb3-12" title="12"><span class="co">#&gt; as.mo("T. islandicus") 142.0 142.0 159.0 143.0 187 216 10</span></a>
<a class="sourceLine" id="cb3-13" title="13"><span class="co">#&gt; as.mo("T. islandicus") 142.0 143.0 173.0 185.0 187 190 10</span></a>
<a class="sourceLine" id="cb3-14" title="14"><span class="co">#&gt; as.mo("Thermus islandicus") 68.1 68.4 81.9 68.6 111 115 10</span></a></code></pre></div>
<p>That takes 8 times as much time on average. A value of 100 milliseconds means it can only determine ~10 different input values per second. We can conclude that looking up arbitrary codes of less prevalent microorganisms is the worst way to go, in terms of calculation performance. Full names (like <em>Thermus islandicus</em>) are almost fast - these are the most probable input from most data sets.</p>
<p>In the figure below, we compare <em>Escherichia coli</em> (which is very common) with <em>Prevotella brevis</em> (which is moderately common) and with <em>Thermus islandicus</em> (which is very uncommon):</p>
<div class="sourceCode" id="cb4"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb4-1" title="1"><span class="kw"><a href="https://www.rdocumentation.org/packages/graphics/topics/par">par</a></span>(<span class="dt">mar =</span> <span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/c">c</a></span>(<span class="dv">5</span>, <span class="dv">16</span>, <span class="dv">4</span>, <span class="dv">2</span>)) <span class="co"># set more space for left margin text (16)</span></a>
@ -287,8 +287,8 @@
<a class="sourceLine" id="cb5-24" title="24"><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/print">print</a></span>(run_it, <span class="dt">unit =</span> <span class="st">"ms"</span>, <span class="dt">signif =</span> <span class="dv">3</span>)</a>
<a class="sourceLine" id="cb5-25" title="25"><span class="co">#&gt; Unit: milliseconds</span></a>
<a class="sourceLine" id="cb5-26" title="26"><span class="co">#&gt; expr min lq mean median uq max neval</span></a>
<a class="sourceLine" id="cb5-27" title="27"><span class="co">#&gt; mo_fullname(x) 723 731 797 785 807 1010 10</span></a></code></pre></div>
<p>So transforming 500,000 values (!!) of 50 unique values only takes 0.78 seconds (784 ms). You only lose time on your unique input values.</p>
<a class="sourceLine" id="cb5-27" title="27"><span class="co">#&gt; mo_fullname(x) 732 772 823 819 858 1020 10</span></a></code></pre></div>
<p>So transforming 500,000 values (!!) of 50 unique values only takes 0.82 seconds (819 ms). You only lose time on your unique input values.</p>
</div>
<div id="precalculated-results" class="section level3">
<h3 class="hasAnchor">
@ -300,10 +300,10 @@
<a class="sourceLine" id="cb6-4" title="4"> <span class="dt">times =</span> <span class="dv">10</span>)</a>
<a class="sourceLine" id="cb6-5" title="5"><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/print">print</a></span>(run_it, <span class="dt">unit =</span> <span class="st">"ms"</span>, <span class="dt">signif =</span> <span class="dv">3</span>)</a>
<a class="sourceLine" id="cb6-6" title="6"><span class="co">#&gt; Unit: milliseconds</span></a>
<a class="sourceLine" id="cb6-7" title="7"><span class="co">#&gt; expr min lq mean median uq max neval</span></a>
<a class="sourceLine" id="cb6-8" title="8"><span class="co">#&gt; A 11.20 11.300 12.100 11.800 12.200 15.500 10</span></a>
<a class="sourceLine" id="cb6-9" title="9"><span class="co">#&gt; B 22.20 22.700 26.900 23.900 24.200 57.600 10</span></a>
<a class="sourceLine" id="cb6-10" title="10"><span class="co">#&gt; C 0.53 0.552 0.652 0.591 0.781 0.803 10</span></a></code></pre></div>
<a class="sourceLine" id="cb6-7" title="7"><span class="co">#&gt; expr min lq mean median uq max neval</span></a>
<a class="sourceLine" id="cb6-8" title="8"><span class="co">#&gt; A 11.100 11.400 16.700 11.700 14.400 43.200 10</span></a>
<a class="sourceLine" id="cb6-9" title="9"><span class="co">#&gt; B 22.300 22.400 22.800 22.700 22.900 24.100 10</span></a>
<a class="sourceLine" id="cb6-10" title="10"><span class="co">#&gt; C 0.324 0.439 0.532 0.577 0.582 0.677 10</span></a></code></pre></div>
<p>So going from <code><a href="../reference/mo_property.html">mo_fullname("Staphylococcus aureus")</a></code> to <code>"Staphylococcus aureus"</code> takes 0.0006 seconds - it doesnt even start calculating <em>if the result would be the same as the expected resulting value</em>. That goes for all helper functions:</p>
<div class="sourceCode" id="cb7"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb7-1" title="1">run_it &lt;-<span class="st"> </span><span class="kw"><a href="https://www.rdocumentation.org/packages/microbenchmark/topics/microbenchmark">microbenchmark</a></span>(<span class="dt">A =</span> <span class="kw"><a href="../reference/mo_property.html">mo_species</a></span>(<span class="st">"aureus"</span>),</a>
<a class="sourceLine" id="cb7-2" title="2"> <span class="dt">B =</span> <span class="kw"><a href="../reference/mo_property.html">mo_genus</a></span>(<span class="st">"Staphylococcus"</span>),</a>
@ -317,14 +317,14 @@
<a class="sourceLine" id="cb7-10" title="10"><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/print">print</a></span>(run_it, <span class="dt">unit =</span> <span class="st">"ms"</span>, <span class="dt">signif =</span> <span class="dv">3</span>)</a>
<a class="sourceLine" id="cb7-11" title="11"><span class="co">#&gt; Unit: milliseconds</span></a>
<a class="sourceLine" id="cb7-12" title="12"><span class="co">#&gt; expr min lq mean median uq max neval</span></a>
<a class="sourceLine" id="cb7-13" title="13"><span class="co">#&gt; A 0.318 0.329 0.414 0.431 0.464 0.532 10</span></a>
<a class="sourceLine" id="cb7-14" title="14"><span class="co">#&gt; B 0.346 0.355 0.414 0.405 0.456 0.528 10</span></a>
<a class="sourceLine" id="cb7-15" title="15"><span class="co">#&gt; C 0.347 0.357 0.507 0.489 0.608 0.778 10</span></a>
<a class="sourceLine" id="cb7-16" title="16"><span class="co">#&gt; D 0.280 0.306 0.348 0.343 0.378 0.453 10</span></a>
<a class="sourceLine" id="cb7-17" title="17"><span class="co">#&gt; E 0.241 0.298 0.333 0.329 0.401 0.408 10</span></a>
<a class="sourceLine" id="cb7-18" title="18"><span class="co">#&gt; F 0.253 0.295 0.320 0.308 0.330 0.415 10</span></a>
<a class="sourceLine" id="cb7-19" title="19"><span class="co">#&gt; G 0.271 0.279 0.309 0.284 0.363 0.379 10</span></a>
<a class="sourceLine" id="cb7-20" title="20"><span class="co">#&gt; H 0.218 0.260 0.328 0.341 0.366 0.426 10</span></a></code></pre></div>
<a class="sourceLine" id="cb7-13" title="13"><span class="co">#&gt; A 0.322 0.338 0.397 0.384 0.415 0.569 10</span></a>
<a class="sourceLine" id="cb7-14" title="14"><span class="co">#&gt; B 0.316 0.370 0.442 0.442 0.508 0.601 10</span></a>
<a class="sourceLine" id="cb7-15" title="15"><span class="co">#&gt; C 0.335 0.385 0.502 0.504 0.566 0.724 10</span></a>
<a class="sourceLine" id="cb7-16" title="16"><span class="co">#&gt; D 0.283 0.324 0.362 0.366 0.389 0.437 10</span></a>
<a class="sourceLine" id="cb7-17" title="17"><span class="co">#&gt; E 0.252 0.274 0.317 0.323 0.355 0.383 10</span></a>
<a class="sourceLine" id="cb7-18" title="18"><span class="co">#&gt; F 0.255 0.275 0.325 0.332 0.348 0.411 10</span></a>
<a class="sourceLine" id="cb7-19" title="19"><span class="co">#&gt; G 0.259 0.272 0.307 0.299 0.318 0.412 10</span></a>
<a class="sourceLine" id="cb7-20" title="20"><span class="co">#&gt; H 0.271 0.319 0.338 0.334 0.362 0.418 10</span></a></code></pre></div>
<p>Of course, when running <code><a href="../reference/mo_property.html">mo_phylum("Firmicutes")</a></code> the function has zero knowledge about the actual microorganism, namely <em>S. aureus</em>. But since the result would be <code>"Firmicutes"</code> too, there is no point in calculating the result. And because this package knows all phyla of all known bacteria (according to the Catalogue of Life), it can just return the initial value immediately.</p>
</div>
<div id="results-in-other-languages" class="section level3">
@ -351,13 +351,13 @@
<a class="sourceLine" id="cb8-18" title="18"><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/print">print</a></span>(run_it, <span class="dt">unit =</span> <span class="st">"ms"</span>, <span class="dt">signif =</span> <span class="dv">4</span>)</a>
<a class="sourceLine" id="cb8-19" title="19"><span class="co">#&gt; Unit: milliseconds</span></a>
<a class="sourceLine" id="cb8-20" title="20"><span class="co">#&gt; expr min lq mean median uq max neval</span></a>
<a class="sourceLine" id="cb8-21" title="21"><span class="co">#&gt; en 15.12 15.39 19.60 15.47 15.63 57.02 10</span></a>
<a class="sourceLine" id="cb8-22" title="22"><span class="co">#&gt; de 23.37 23.62 24.02 24.01 24.09 25.10 10</span></a>
<a class="sourceLine" id="cb8-23" title="23"><span class="co">#&gt; nl 23.44 23.94 24.05 24.02 24.14 25.02 10</span></a>
<a class="sourceLine" id="cb8-24" title="24"><span class="co">#&gt; es 23.71 24.03 28.36 24.08 24.29 65.92 10</span></a>
<a class="sourceLine" id="cb8-25" title="25"><span class="co">#&gt; it 23.65 23.94 24.08 24.03 24.07 25.12 10</span></a>
<a class="sourceLine" id="cb8-26" title="26"><span class="co">#&gt; fr 23.94 23.99 32.58 24.17 25.14 66.00 10</span></a>
<a class="sourceLine" id="cb8-27" title="27"><span class="co">#&gt; pt 23.30 23.63 28.51 24.06 24.78 68.87 10</span></a></code></pre></div>
<a class="sourceLine" id="cb8-21" title="21"><span class="co">#&gt; en 14.92 15.11 15.44 15.31 15.83 16.30 10</span></a>
<a class="sourceLine" id="cb8-22" title="22"><span class="co">#&gt; de 27.88 27.89 32.32 28.03 28.37 69.82 10</span></a>
<a class="sourceLine" id="cb8-23" title="23"><span class="co">#&gt; nl 27.39 28.01 40.70 28.48 69.20 70.26 10</span></a>
<a class="sourceLine" id="cb8-24" title="24"><span class="co">#&gt; es 27.69 27.93 38.06 28.12 29.21 84.95 10</span></a>
<a class="sourceLine" id="cb8-25" title="25"><span class="co">#&gt; it 27.73 27.95 28.16 28.00 28.15 29.40 10</span></a>
<a class="sourceLine" id="cb8-26" title="26"><span class="co">#&gt; fr 27.13 27.65 32.76 28.41 29.50 69.48 10</span></a>
<a class="sourceLine" id="cb8-27" title="27"><span class="co">#&gt; pt 27.08 27.34 27.89 27.99 28.05 29.40 10</span></a></code></pre></div>
<p>Currently supported are German, Dutch, Spanish, Italian, French and Portuguese.</p>
</div>
</div>

Binary file not shown.

Before

Width:  |  Height:  |  Size: 28 KiB

After

Width:  |  Height:  |  Size: 28 KiB

View File

@ -192,7 +192,7 @@
<h1>How to create frequency tables</h1>
<h4 class="author">Matthijs S. Berends</h4>
<h4 class="date">01 March 2019</h4>
<h4 class="date">02 March 2019</h4>
<div class="hidden name"><code>freq.Rmd</code></div>

View File

@ -192,7 +192,7 @@
<h1>How to get properties of a microorganism</h1>
<h4 class="author">Matthijs S. Berends</h4>
<h4 class="date">01 March 2019</h4>
<h4 class="date">02 March 2019</h4>
<div class="hidden name"><code>mo_property.Rmd</code></div>

View File

@ -192,7 +192,7 @@
<h1>How to predict antimicrobial resistance</h1>
<h4 class="author">Matthijs S. Berends</h4>
<h4 class="date">01 March 2019</h4>
<h4 class="date">02 March 2019</h4>
<div class="hidden name"><code>resistance_predict.Rmd</code></div>

View File

@ -328,12 +328,19 @@ These functions use <code><a href="../reference/as.atc.html">as.atc()</a></code>
<li>Functions <code><a href="../reference/AMR-deprecated.html">atc_ddd()</a></code> and <code><a href="../reference/AMR-deprecated.html">atc_groups()</a></code> have been renamed <code><a href="../reference/atc_online.html">atc_online_ddd()</a></code> and <code><a href="../reference/atc_online.html">atc_online_groups()</a></code>. The old functions are deprecated and will be removed in a future version.</li>
<li>Function <code><a href="../reference/AMR-deprecated.html">guess_mo()</a></code> is now deprecated in favour of <code><a href="../reference/as.mo.html">as.mo()</a></code> and will be removed in future versions</li>
<li>Function <code><a href="../reference/AMR-deprecated.html">guess_atc()</a></code> is now deprecated in favour of <code><a href="../reference/as.atc.html">as.atc()</a></code> and will be removed in future versions</li>
<li>Improvements for <code><a href="../reference/as.mo.html">as.mo()</a></code>:
<li>Improvements for <code><a href="../reference/as.mo.html">as.mo()</a></code>:\
<ul>
<li>Incoercible results will now be considered unknown, MO code <code>UNKNOWN</code>. Properties of these will be translated on foreign systems in all language already previously supported: German, Dutch, French, Italian, Spanish and Portuguese:</li>
</ul>
<div class="sourceCode" id="cb5"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb5-1" title="1"><span class="kw"><a href="../reference/mo_property.html">mo_genus</a></span>(<span class="st">"qwerty"</span>, <span class="dt">language =</span> <span class="st">"es"</span>)</a>
<a class="sourceLine" id="cb5-2" title="2"><span class="co"># Warning: </span></a>
<a class="sourceLine" id="cb5-3" title="3"><span class="co"># one unique value (^= 100.0%) could not be coerced and is considered 'unknown': "qwerty". Use mo_failures() to review it.</span></a>
<a class="sourceLine" id="cb5-4" title="4"><span class="co">#&gt; [1] "(género desconocido)"</span></a></code></pre></div>
<ul>
<li>Fix for vector containing only empty values</li>
<li>Finds better results when input is in other languages</li>
<li>Better handling for subspecies</li>
<li>Better handling for <em>Salmonellae</em>
<li>Better handling for <em>Salmonellae</em>, especially the city like serovars like <em>Salmonella London</em>
</li>
<li>Understanding of highly virulent <em>E. coli</em> strains like EIEC, EPEC and STEC</li>
<li>There will be looked for uncertain results at default - these results will be returned with an informative warning</li>
@ -363,24 +370,30 @@ These functions use <code><a href="../reference/as.atc.html">as.atc()</a></code>
</li>
<li>Small text updates to summaries of class <code>rsi</code> and <code>mic</code>
</li>
<li>Function <code><a href="../reference/as.rsi.html">as.rsi()</a></code> now gives a warning when inputting MIC values</li>
<li>Function <code><a href="../reference/as.rsi.html">as.rsi()</a></code>:
<ul>
<li>Now gives a warning when inputting MIC values</li>
<li>Now accepts high and low resistance: <code>"HIGH S"</code> will return <code>S</code>
</li>
</ul>
</li>
<li>Frequency tables (<code><a href="../reference/freq.html">freq()</a></code> function):
<ul>
<li>
<p>Support for tidyverse quasiquotation! Now you can create frequency tables of function outcomes:</p>
<div class="sourceCode" id="cb5"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb5-1" title="1"><span class="co"># Determine genus of microorganisms (mo) in `septic_patients` data set:</span></a>
<a class="sourceLine" id="cb5-2" title="2"><span class="co"># OLD WAY</span></a>
<a class="sourceLine" id="cb5-3" title="3">septic_patients <span class="op">%&gt;%</span></a>
<a class="sourceLine" id="cb5-4" title="4"><span class="st"> </span><span class="kw">mutate</span>(<span class="dt">genus =</span> <span class="kw"><a href="../reference/mo_property.html">mo_genus</a></span>(mo)) <span class="op">%&gt;%</span></a>
<a class="sourceLine" id="cb5-5" title="5"><span class="st"> </span><span class="kw"><a href="../reference/freq.html">freq</a></span>(genus)</a>
<a class="sourceLine" id="cb5-6" title="6"><span class="co"># NEW WAY</span></a>
<a class="sourceLine" id="cb5-7" title="7">septic_patients <span class="op">%&gt;%</span><span class="st"> </span></a>
<a class="sourceLine" id="cb5-8" title="8"><span class="st"> </span><span class="kw"><a href="../reference/freq.html">freq</a></span>(<span class="kw"><a href="../reference/mo_property.html">mo_genus</a></span>(mo))</a>
<a class="sourceLine" id="cb5-9" title="9"></a>
<a class="sourceLine" id="cb5-10" title="10"><span class="co"># Even supports grouping variables:</span></a>
<a class="sourceLine" id="cb5-11" title="11">septic_patients <span class="op">%&gt;%</span></a>
<a class="sourceLine" id="cb5-12" title="12"><span class="st"> </span><span class="kw">group_by</span>(gender) <span class="op">%&gt;%</span><span class="st"> </span></a>
<a class="sourceLine" id="cb5-13" title="13"><span class="st"> </span><span class="kw"><a href="../reference/freq.html">freq</a></span>(<span class="kw"><a href="../reference/mo_property.html">mo_genus</a></span>(mo))</a></code></pre></div>
<div class="sourceCode" id="cb6"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb6-1" title="1"><span class="co"># Determine genus of microorganisms (mo) in `septic_patients` data set:</span></a>
<a class="sourceLine" id="cb6-2" title="2"><span class="co"># OLD WAY</span></a>
<a class="sourceLine" id="cb6-3" title="3">septic_patients <span class="op">%&gt;%</span></a>
<a class="sourceLine" id="cb6-4" title="4"><span class="st"> </span><span class="kw">mutate</span>(<span class="dt">genus =</span> <span class="kw"><a href="../reference/mo_property.html">mo_genus</a></span>(mo)) <span class="op">%&gt;%</span></a>
<a class="sourceLine" id="cb6-5" title="5"><span class="st"> </span><span class="kw"><a href="../reference/freq.html">freq</a></span>(genus)</a>
<a class="sourceLine" id="cb6-6" title="6"><span class="co"># NEW WAY</span></a>
<a class="sourceLine" id="cb6-7" title="7">septic_patients <span class="op">%&gt;%</span><span class="st"> </span></a>
<a class="sourceLine" id="cb6-8" title="8"><span class="st"> </span><span class="kw"><a href="../reference/freq.html">freq</a></span>(<span class="kw"><a href="../reference/mo_property.html">mo_genus</a></span>(mo))</a>
<a class="sourceLine" id="cb6-9" title="9"></a>
<a class="sourceLine" id="cb6-10" title="10"><span class="co"># Even supports grouping variables:</span></a>
<a class="sourceLine" id="cb6-11" title="11">septic_patients <span class="op">%&gt;%</span></a>
<a class="sourceLine" id="cb6-12" title="12"><span class="st"> </span><span class="kw">group_by</span>(gender) <span class="op">%&gt;%</span><span class="st"> </span></a>
<a class="sourceLine" id="cb6-13" title="13"><span class="st"> </span><span class="kw"><a href="../reference/freq.html">freq</a></span>(<span class="kw"><a href="../reference/mo_property.html">mo_genus</a></span>(mo))</a></code></pre></div>
</li>
<li>Header info is now available as a list, with the <code>header</code> function</li>
<li>The parameter <code>header</code> is now set to <code>TRUE</code> at default, even for markdown</li>
@ -454,10 +467,10 @@ These functions use <code><a href="../reference/as.atc.html">as.atc()</a></code>
<li>Fewer than 3 characters as input for <code>as.mo</code> will return NA</li>
<li>
<p>Function <code>as.mo</code> (and all <code>mo_*</code> wrappers) now supports genus abbreviations with “species” attached</p>
<div class="sourceCode" id="cb6"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb6-1" title="1"><span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"E. species"</span>) <span class="co"># B_ESCHR</span></a>
<a class="sourceLine" id="cb6-2" title="2"><span class="kw"><a href="../reference/mo_property.html">mo_fullname</a></span>(<span class="st">"E. spp."</span>) <span class="co"># "Escherichia species"</span></a>
<a class="sourceLine" id="cb6-3" title="3"><span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"S. spp"</span>) <span class="co"># B_STPHY</span></a>
<a class="sourceLine" id="cb6-4" title="4"><span class="kw"><a href="../reference/mo_property.html">mo_fullname</a></span>(<span class="st">"S. species"</span>) <span class="co"># "Staphylococcus species"</span></a></code></pre></div>
<div class="sourceCode" id="cb7"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb7-1" title="1"><span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"E. species"</span>) <span class="co"># B_ESCHR</span></a>
<a class="sourceLine" id="cb7-2" title="2"><span class="kw"><a href="../reference/mo_property.html">mo_fullname</a></span>(<span class="st">"E. spp."</span>) <span class="co"># "Escherichia species"</span></a>
<a class="sourceLine" id="cb7-3" title="3"><span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"S. spp"</span>) <span class="co"># B_STPHY</span></a>
<a class="sourceLine" id="cb7-4" title="4"><span class="kw"><a href="../reference/mo_property.html">mo_fullname</a></span>(<span class="st">"S. species"</span>) <span class="co"># "Staphylococcus species"</span></a></code></pre></div>
</li>
<li>Added parameter <code>combine_IR</code> (TRUE/FALSE) to functions <code>portion_df</code> and <code>count_df</code>, to indicate that all values of I and R must be merged into one, so the output only consists of S vs. IR (susceptible vs. non-susceptible)</li>
<li>Fix for <code>portion_*(..., as_percent = TRUE)</code> when minimal number of isolates would not be met</li>
@ -470,15 +483,15 @@ These functions use <code><a href="../reference/as.atc.html">as.atc()</a></code>
<ul>
<li>
<p>Support for grouping variables, test with:</p>
<div class="sourceCode" id="cb7"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb7-1" title="1">septic_patients <span class="op">%&gt;%</span><span class="st"> </span></a>
<a class="sourceLine" id="cb7-2" title="2"><span class="st"> </span><span class="kw">group_by</span>(hospital_id) <span class="op">%&gt;%</span><span class="st"> </span></a>
<a class="sourceLine" id="cb7-3" title="3"><span class="st"> </span><span class="kw"><a href="../reference/freq.html">freq</a></span>(gender)</a></code></pre></div>
<div class="sourceCode" id="cb8"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb8-1" title="1">septic_patients <span class="op">%&gt;%</span><span class="st"> </span></a>
<a class="sourceLine" id="cb8-2" title="2"><span class="st"> </span><span class="kw">group_by</span>(hospital_id) <span class="op">%&gt;%</span><span class="st"> </span></a>
<a class="sourceLine" id="cb8-3" title="3"><span class="st"> </span><span class="kw"><a href="../reference/freq.html">freq</a></span>(gender)</a></code></pre></div>
</li>
<li>
<p>Support for (un)selecting columns:</p>
<div class="sourceCode" id="cb8"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb8-1" title="1">septic_patients <span class="op">%&gt;%</span><span class="st"> </span></a>
<a class="sourceLine" id="cb8-2" title="2"><span class="st"> </span><span class="kw"><a href="../reference/freq.html">freq</a></span>(hospital_id) <span class="op">%&gt;%</span><span class="st"> </span></a>
<a class="sourceLine" id="cb8-3" title="3"><span class="st"> </span><span class="kw">select</span>(<span class="op">-</span>count, <span class="op">-</span>cum_count) <span class="co"># only get item, percent, cum_percent</span></a></code></pre></div>
<div class="sourceCode" id="cb9"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb9-1" title="1">septic_patients <span class="op">%&gt;%</span><span class="st"> </span></a>
<a class="sourceLine" id="cb9-2" title="2"><span class="st"> </span><span class="kw"><a href="../reference/freq.html">freq</a></span>(hospital_id) <span class="op">%&gt;%</span><span class="st"> </span></a>
<a class="sourceLine" id="cb9-3" title="3"><span class="st"> </span><span class="kw">select</span>(<span class="op">-</span>count, <span class="op">-</span>cum_count) <span class="co"># only get item, percent, cum_percent</span></a></code></pre></div>
</li>
<li>Check for <code><a href="https://www.rdocumentation.org/packages/hms/topics/hms">hms::is.hms</a></code>
</li>
@ -558,18 +571,18 @@ These functions use <code><a href="../reference/as.atc.html">as.atc()</a></code>
</li>
</ul>
<p>They also come with support for German, Dutch, French, Italian, Spanish and Portuguese:</p>
<div class="sourceCode" id="cb9"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb9-1" title="1"><span class="kw"><a href="../reference/mo_property.html">mo_gramstain</a></span>(<span class="st">"E. coli"</span>)</a>
<a class="sourceLine" id="cb9-2" title="2"><span class="co"># [1] "Gram negative"</span></a>
<a class="sourceLine" id="cb9-3" title="3"><span class="kw"><a href="../reference/mo_property.html">mo_gramstain</a></span>(<span class="st">"E. coli"</span>, <span class="dt">language =</span> <span class="st">"de"</span>) <span class="co"># German</span></a>
<a class="sourceLine" id="cb9-4" title="4"><span class="co"># [1] "Gramnegativ"</span></a>
<a class="sourceLine" id="cb9-5" title="5"><span class="kw"><a href="../reference/mo_property.html">mo_gramstain</a></span>(<span class="st">"E. coli"</span>, <span class="dt">language =</span> <span class="st">"es"</span>) <span class="co"># Spanish</span></a>
<a class="sourceLine" id="cb9-6" title="6"><span class="co"># [1] "Gram negativo"</span></a>
<a class="sourceLine" id="cb9-7" title="7"><span class="kw"><a href="../reference/mo_property.html">mo_fullname</a></span>(<span class="st">"S. group A"</span>, <span class="dt">language =</span> <span class="st">"pt"</span>) <span class="co"># Portuguese</span></a>
<a class="sourceLine" id="cb9-8" title="8"><span class="co"># [1] "Streptococcus grupo A"</span></a></code></pre></div>
<div class="sourceCode" id="cb10"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb10-1" title="1"><span class="kw"><a href="../reference/mo_property.html">mo_gramstain</a></span>(<span class="st">"E. coli"</span>)</a>
<a class="sourceLine" id="cb10-2" title="2"><span class="co"># [1] "Gram negative"</span></a>
<a class="sourceLine" id="cb10-3" title="3"><span class="kw"><a href="../reference/mo_property.html">mo_gramstain</a></span>(<span class="st">"E. coli"</span>, <span class="dt">language =</span> <span class="st">"de"</span>) <span class="co"># German</span></a>
<a class="sourceLine" id="cb10-4" title="4"><span class="co"># [1] "Gramnegativ"</span></a>
<a class="sourceLine" id="cb10-5" title="5"><span class="kw"><a href="../reference/mo_property.html">mo_gramstain</a></span>(<span class="st">"E. coli"</span>, <span class="dt">language =</span> <span class="st">"es"</span>) <span class="co"># Spanish</span></a>
<a class="sourceLine" id="cb10-6" title="6"><span class="co"># [1] "Gram negativo"</span></a>
<a class="sourceLine" id="cb10-7" title="7"><span class="kw"><a href="../reference/mo_property.html">mo_fullname</a></span>(<span class="st">"S. group A"</span>, <span class="dt">language =</span> <span class="st">"pt"</span>) <span class="co"># Portuguese</span></a>
<a class="sourceLine" id="cb10-8" title="8"><span class="co"># [1] "Streptococcus grupo A"</span></a></code></pre></div>
<p>Furthermore, former taxonomic names will give a note about the current taxonomic name:</p>
<div class="sourceCode" id="cb10"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb10-1" title="1"><span class="kw"><a href="../reference/mo_property.html">mo_gramstain</a></span>(<span class="st">"Esc blattae"</span>)</a>
<a class="sourceLine" id="cb10-2" title="2"><span class="co"># Note: 'Escherichia blattae' (Burgess et al., 1973) was renamed 'Shimwellia blattae' (Priest and Barker, 2010)</span></a>
<a class="sourceLine" id="cb10-3" title="3"><span class="co"># [1] "Gram negative"</span></a></code></pre></div>
<div class="sourceCode" id="cb11"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb11-1" title="1"><span class="kw"><a href="../reference/mo_property.html">mo_gramstain</a></span>(<span class="st">"Esc blattae"</span>)</a>
<a class="sourceLine" id="cb11-2" title="2"><span class="co"># Note: 'Escherichia blattae' (Burgess et al., 1973) was renamed 'Shimwellia blattae' (Priest and Barker, 2010)</span></a>
<a class="sourceLine" id="cb11-3" title="3"><span class="co"># [1] "Gram negative"</span></a></code></pre></div>
</li>
<li>Functions <code>count_R</code>, <code>count_IR</code>, <code>count_I</code>, <code>count_SI</code> and <code>count_S</code> to selectively count resistant or susceptible isolates
<ul>
@ -580,18 +593,18 @@ These functions use <code><a href="../reference/as.atc.html">as.atc()</a></code>
</li>
<li>
<p>Functions <code>as.mo</code> and <code>is.mo</code> as replacements for <code>as.bactid</code> and <code>is.bactid</code> (since the <code>microoganisms</code> data set not only contains bacteria). These last two functions are deprecated and will be removed in a future release. The <code>as.mo</code> function determines microbial IDs using Artificial Intelligence (AI):</p>
<div class="sourceCode" id="cb11"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb11-1" title="1"><span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"E. coli"</span>)</a>
<a class="sourceLine" id="cb11-2" title="2"><span class="co"># [1] B_ESCHR_COL</span></a>
<a class="sourceLine" id="cb11-3" title="3"><span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"MRSA"</span>)</a>
<a class="sourceLine" id="cb11-4" title="4"><span class="co"># [1] B_STPHY_AUR</span></a>
<a class="sourceLine" id="cb11-5" title="5"><span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"S group A"</span>)</a>
<a class="sourceLine" id="cb11-6" title="6"><span class="co"># [1] B_STRPTC_GRA</span></a></code></pre></div>
<div class="sourceCode" id="cb12"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb12-1" title="1"><span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"E. coli"</span>)</a>
<a class="sourceLine" id="cb12-2" title="2"><span class="co"># [1] B_ESCHR_COL</span></a>
<a class="sourceLine" id="cb12-3" title="3"><span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"MRSA"</span>)</a>
<a class="sourceLine" id="cb12-4" title="4"><span class="co"># [1] B_STPHY_AUR</span></a>
<a class="sourceLine" id="cb12-5" title="5"><span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"S group A"</span>)</a>
<a class="sourceLine" id="cb12-6" title="6"><span class="co"># [1] B_STRPTC_GRA</span></a></code></pre></div>
<p>And with great speed too - on a quite regular Linux server from 2007 it takes us less than 0.02 seconds to transform 25,000 items:</p>
<div class="sourceCode" id="cb12"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb12-1" title="1">thousands_of_E_colis &lt;-<span class="st"> </span><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/rep">rep</a></span>(<span class="st">"E. coli"</span>, <span class="dv">25000</span>)</a>
<a class="sourceLine" id="cb12-2" title="2">microbenchmark<span class="op">::</span><span class="kw"><a href="https://www.rdocumentation.org/packages/microbenchmark/topics/microbenchmark">microbenchmark</a></span>(<span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(thousands_of_E_colis), <span class="dt">unit =</span> <span class="st">"s"</span>)</a>
<a class="sourceLine" id="cb12-3" title="3"><span class="co"># Unit: seconds</span></a>
<a class="sourceLine" id="cb12-4" title="4"><span class="co"># min median max neval</span></a>
<a class="sourceLine" id="cb12-5" title="5"><span class="co"># 0.01817717 0.01843957 0.03878077 100</span></a></code></pre></div>
<div class="sourceCode" id="cb13"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb13-1" title="1">thousands_of_E_colis &lt;-<span class="st"> </span><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/rep">rep</a></span>(<span class="st">"E. coli"</span>, <span class="dv">25000</span>)</a>
<a class="sourceLine" id="cb13-2" title="2">microbenchmark<span class="op">::</span><span class="kw"><a href="https://www.rdocumentation.org/packages/microbenchmark/topics/microbenchmark">microbenchmark</a></span>(<span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(thousands_of_E_colis), <span class="dt">unit =</span> <span class="st">"s"</span>)</a>
<a class="sourceLine" id="cb13-3" title="3"><span class="co"># Unit: seconds</span></a>
<a class="sourceLine" id="cb13-4" title="4"><span class="co"># min median max neval</span></a>
<a class="sourceLine" id="cb13-5" title="5"><span class="co"># 0.01817717 0.01843957 0.03878077 100</span></a></code></pre></div>
</li>
<li>Added parameter <code>reference_df</code> for <code>as.mo</code>, so users can supply their own microbial IDs, name or codes as a reference table</li>
<li>Renamed all previous references to <code>bactid</code> to <code>mo</code>, like:
@ -619,12 +632,12 @@ These functions use <code><a href="../reference/as.atc.html">as.atc()</a></code>
<li>Added three antimicrobial agents to the <code>antibiotics</code> data set: Terbinafine (D01BA02), Rifaximin (A07AA11) and Isoconazole (D01AC05)</li>
<li>
<p>Added 163 trade names to the <code>antibiotics</code> data set, it now contains 298 different trade names in total, e.g.:</p>
<div class="sourceCode" id="cb13"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb13-1" title="1"><span class="kw"><a href="../reference/AMR-deprecated.html">ab_official</a></span>(<span class="st">"Bactroban"</span>)</a>
<a class="sourceLine" id="cb13-2" title="2"><span class="co"># [1] "Mupirocin"</span></a>
<a class="sourceLine" id="cb13-3" title="3"><span class="kw"><a href="../reference/AMR-deprecated.html">ab_name</a></span>(<span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/c">c</a></span>(<span class="st">"Bactroban"</span>, <span class="st">"Amoxil"</span>, <span class="st">"Zithromax"</span>, <span class="st">"Floxapen"</span>))</a>
<a class="sourceLine" id="cb13-4" title="4"><span class="co"># [1] "Mupirocin" "Amoxicillin" "Azithromycin" "Flucloxacillin"</span></a>
<a class="sourceLine" id="cb13-5" title="5"><span class="kw"><a href="../reference/AMR-deprecated.html">ab_atc</a></span>(<span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/c">c</a></span>(<span class="st">"Bactroban"</span>, <span class="st">"Amoxil"</span>, <span class="st">"Zithromax"</span>, <span class="st">"Floxapen"</span>))</a>
<a class="sourceLine" id="cb13-6" title="6"><span class="co"># [1] "R01AX06" "J01CA04" "J01FA10" "J01CF05"</span></a></code></pre></div>
<div class="sourceCode" id="cb14"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb14-1" title="1"><span class="kw"><a href="../reference/AMR-deprecated.html">ab_official</a></span>(<span class="st">"Bactroban"</span>)</a>
<a class="sourceLine" id="cb14-2" title="2"><span class="co"># [1] "Mupirocin"</span></a>
<a class="sourceLine" id="cb14-3" title="3"><span class="kw"><a href="../reference/AMR-deprecated.html">ab_name</a></span>(<span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/c">c</a></span>(<span class="st">"Bactroban"</span>, <span class="st">"Amoxil"</span>, <span class="st">"Zithromax"</span>, <span class="st">"Floxapen"</span>))</a>
<a class="sourceLine" id="cb14-4" title="4"><span class="co"># [1] "Mupirocin" "Amoxicillin" "Azithromycin" "Flucloxacillin"</span></a>
<a class="sourceLine" id="cb14-5" title="5"><span class="kw"><a href="../reference/AMR-deprecated.html">ab_atc</a></span>(<span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/c">c</a></span>(<span class="st">"Bactroban"</span>, <span class="st">"Amoxil"</span>, <span class="st">"Zithromax"</span>, <span class="st">"Floxapen"</span>))</a>
<a class="sourceLine" id="cb14-6" title="6"><span class="co"># [1] "R01AX06" "J01CA04" "J01FA10" "J01CF05"</span></a></code></pre></div>
</li>
<li>For <code>first_isolate</code>, rows will be ignored when theres no species available</li>
<li>Function <code>ratio</code> is now deprecated and will be removed in a future release, as it is not really the scope of this package</li>
@ -635,13 +648,13 @@ These functions use <code><a href="../reference/as.atc.html">as.atc()</a></code>
</li>
<li>
<p>Support for quasiquotation in the functions series <code>count_*</code> and <code>portions_*</code>, and <code>n_rsi</code>. This allows to check for more than 2 vectors or columns.</p>
<div class="sourceCode" id="cb14"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb14-1" title="1">septic_patients <span class="op">%&gt;%</span><span class="st"> </span><span class="kw">select</span>(amox, cipr) <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="../reference/count.html">count_IR</a></span>()</a>
<a class="sourceLine" id="cb14-2" title="2"><span class="co"># which is the same as:</span></a>
<a class="sourceLine" id="cb14-3" title="3">septic_patients <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="../reference/count.html">count_IR</a></span>(amox, cipr)</a>
<a class="sourceLine" id="cb14-4" title="4"></a>
<a class="sourceLine" id="cb14-5" title="5">septic_patients <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="../reference/portion.html">portion_S</a></span>(amcl)</a>
<a class="sourceLine" id="cb14-6" title="6">septic_patients <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="../reference/portion.html">portion_S</a></span>(amcl, gent)</a>
<a class="sourceLine" id="cb14-7" title="7">septic_patients <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="../reference/portion.html">portion_S</a></span>(amcl, gent, pita)</a></code></pre></div>
<div class="sourceCode" id="cb15"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb15-1" title="1">septic_patients <span class="op">%&gt;%</span><span class="st"> </span><span class="kw">select</span>(amox, cipr) <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="../reference/count.html">count_IR</a></span>()</a>
<a class="sourceLine" id="cb15-2" title="2"><span class="co"># which is the same as:</span></a>
<a class="sourceLine" id="cb15-3" title="3">septic_patients <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="../reference/count.html">count_IR</a></span>(amox, cipr)</a>
<a class="sourceLine" id="cb15-4" title="4"></a>
<a class="sourceLine" id="cb15-5" title="5">septic_patients <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="../reference/portion.html">portion_S</a></span>(amcl)</a>
<a class="sourceLine" id="cb15-6" title="6">septic_patients <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="../reference/portion.html">portion_S</a></span>(amcl, gent)</a>
<a class="sourceLine" id="cb15-7" title="7">septic_patients <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="../reference/portion.html">portion_S</a></span>(amcl, gent, pita)</a></code></pre></div>
</li>
<li>Edited <code>ggplot_rsi</code> and <code>geom_rsi</code> so they can cope with <code>count_df</code>. The new <code>fun</code> parameter has value <code>portion_df</code> at default, but can be set to <code>count_df</code>.</li>
<li>Fix for <code>ggplot_rsi</code> when the <code>ggplot2</code> package was not loaded</li>
@ -655,12 +668,12 @@ These functions use <code><a href="../reference/as.atc.html">as.atc()</a></code>
</li>
<li>
<p>Support for types (classes) list and matrix for <code>freq</code></p>
<div class="sourceCode" id="cb15"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb15-1" title="1">my_matrix =<span class="st"> </span><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/with">with</a></span>(septic_patients, <span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/matrix">matrix</a></span>(<span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/c">c</a></span>(age, gender), <span class="dt">ncol =</span> <span class="dv">2</span>))</a>
<a class="sourceLine" id="cb15-2" title="2"><span class="kw"><a href="../reference/freq.html">freq</a></span>(my_matrix)</a></code></pre></div>
<div class="sourceCode" id="cb16"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb16-1" title="1">my_matrix =<span class="st"> </span><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/with">with</a></span>(septic_patients, <span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/matrix">matrix</a></span>(<span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/c">c</a></span>(age, gender), <span class="dt">ncol =</span> <span class="dv">2</span>))</a>
<a class="sourceLine" id="cb16-2" title="2"><span class="kw"><a href="../reference/freq.html">freq</a></span>(my_matrix)</a></code></pre></div>
<p>For lists, subsetting is possible:</p>
<div class="sourceCode" id="cb16"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb16-1" title="1">my_list =<span class="st"> </span><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/list">list</a></span>(<span class="dt">age =</span> septic_patients<span class="op">$</span>age, <span class="dt">gender =</span> septic_patients<span class="op">$</span>gender)</a>
<a class="sourceLine" id="cb16-2" title="2">my_list <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="../reference/freq.html">freq</a></span>(age)</a>
<a class="sourceLine" id="cb16-3" title="3">my_list <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="../reference/freq.html">freq</a></span>(gender)</a></code></pre></div>
<div class="sourceCode" id="cb17"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb17-1" title="1">my_list =<span class="st"> </span><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/list">list</a></span>(<span class="dt">age =</span> septic_patients<span class="op">$</span>age, <span class="dt">gender =</span> septic_patients<span class="op">$</span>gender)</a>
<a class="sourceLine" id="cb17-2" title="2">my_list <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="../reference/freq.html">freq</a></span>(age)</a>
<a class="sourceLine" id="cb17-3" title="3">my_list <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="../reference/freq.html">freq</a></span>(gender)</a></code></pre></div>
</li>
</ul>
</div>

View File

@ -299,7 +299,8 @@
----&gt; taxonomic kingdom: A (Archaea), AN (Animalia), B (Bacteria), C (Chromista),
F (Fungi), P (Protozoa), PL (Plantae) or V (Viruses)
</pre>
<p>Use the <code><a href='mo_property.html'>mo_property</a></code> functions to get properties based on the returned code, see Examples.</p>
<p>Values that cannot be coered will be considered 'unknown' and have an MO code <code>UNKNOWN</code>.</p>
<p>Use the <code><a href='mo_property.html'>mo_property</a></code> functions to get properties based on the returned code, see Examples.</p>
<p><strong>Artificial Intelligence</strong> <br />
This function uses Artificial Intelligence (AI) to help getting fast and logical results. It tries to find matches in this order:</p><ul>
<li><p>Taxonomic kingdom: it first searches in Bacteria, then Fungi, then Protozoa</p></li>

View File

@ -245,7 +245,7 @@
<h2 class="hasAnchor" id="format"><a class="anchor" href="#format"></a>Format</h2>
<p>A <code><a href='https://www.rdocumentation.org/packages/base/topics/data.frame'>data.frame</a></code> with 57,158 observations and 14 variables:</p><dl class='dl-horizontal'>
<p>A <code><a href='https://www.rdocumentation.org/packages/base/topics/data.frame'>data.frame</a></code> with 59,985 observations and 15 variables:</p><dl class='dl-horizontal'>
<dt><code>mo</code></dt><dd><p>ID of microorganism as used by this package</p></dd>
<dt><code>col_id</code></dt><dd><p>Catalogue of Life ID</p></dd>
<dt><code>fullname</code></dt><dd><p>Full name, like <code>"Echerichia coli"</code></p></dd>
@ -260,6 +260,7 @@
<dt><code>rank</code></dt><dd><p>Taxonomic rank of the microorganism, like <code>"species"</code> or <code>"genus"</code></p></dd>
<dt><code>ref</code></dt><dd><p>Author(s) and year of concerning scientific publication</p></dd>
<dt><code>species_id</code></dt><dd><p>ID of the species as used by the Catalogue of Life</p></dd>
<dt><code>prevalence</code></dt><dd><p>Prevalence of the microorganism, see <code><a href='as.mo.html'>?as.mo</a></code></p></dd>
</dl>
<h2 class="hasAnchor" id="source"><a class="anchor" href="#source"></a>Source</h2>

View File

@ -245,7 +245,7 @@
<h2 class="hasAnchor" id="format"><a class="anchor" href="#format"></a>Format</h2>
<p>A <code><a href='https://www.rdocumentation.org/packages/base/topics/data.frame'>data.frame</a></code> with 14,487 observations and 4 variables:</p><dl class='dl-horizontal'>
<p>A <code><a href='https://www.rdocumentation.org/packages/base/topics/data.frame'>data.frame</a></code> with 17,069 observations and 4 variables:</p><dl class='dl-horizontal'>
<dt><code>col_id</code></dt><dd><p>Catalogue of Life ID</p></dd>
<dt><code>tsn_new</code></dt><dd><p>New Catalogue of Life ID</p></dd>
<dt><code>fullname</code></dt><dd><p>Old taxonomic name of the microorganism</p></dd>

View File

@ -58,6 +58,8 @@ A microbial ID from this package (class: \code{mo}) typically looks like these e
F (Fungi), P (Protozoa), PL (Plantae) or V (Viruses)
}
Values that cannot be coered will be considered 'unknown' and have an MO code \code{UNKNOWN}.
Use the \code{\link{mo_property}} functions to get properties based on the returned code, see Examples.
\strong{Artificial Intelligence} \cr

View File

@ -4,7 +4,7 @@
\name{microorganisms}
\alias{microorganisms}
\title{Data set with ~60,000 microorganisms}
\format{A \code{\link{data.frame}} with 57,158 observations and 14 variables:
\format{A \code{\link{data.frame}} with 59,985 observations and 15 variables:
\describe{
\item{\code{mo}}{ID of microorganism as used by this package}
\item{\code{col_id}}{Catalogue of Life ID}
@ -20,6 +20,7 @@
\item{\code{rank}}{Taxonomic rank of the microorganism, like \code{"species"} or \code{"genus"}}
\item{\code{ref}}{Author(s) and year of concerning scientific publication}
\item{\code{species_id}}{ID of the species as used by the Catalogue of Life}
\item{\code{prevalence}}{Prevalence of the microorganism, see \code{?as.mo}}
}}
\source{
Catalogue of Life: Annual Checklist (public online database), \url{www.catalogueoflife.org}.

View File

@ -4,7 +4,7 @@
\name{microorganisms.old}
\alias{microorganisms.old}
\title{Data set with previously accepted taxonomic names}
\format{A \code{\link{data.frame}} with 14,487 observations and 4 variables:
\format{A \code{\link{data.frame}} with 17,069 observations and 4 variables:
\describe{
\item{\code{col_id}}{Catalogue of Life ID}
\item{\code{tsn_new}}{New Catalogue of Life ID}

View File

@ -86,6 +86,9 @@ MOs <- taxon %>%
ref = gsub("^, ", "", ref)
)
# remove the HUGE file
rm(taxon)
# remove non-ASCII characters (not allowed by CRAN)
MOs <- MOs %>%
lapply(iconv, from = "UTF-8", to = "ASCII//TRANSLIT") %>%
@ -180,6 +183,52 @@ MOs <- MOs %>%
# add non-taxonomic entries
MOs <- MOs %>%
bind_rows(
# Unknowns
MOs %>%
.[1,] %>%
mutate(mo = "UNKNOWN",
col_id = NA_integer_,
fullname = "(unknown name)",
kingdom = "(unknown kingdom)",
phylum = "(unknown phylum)",
class = "(unknown class)",
order = "(unknown order)",
family = "(unknown family)",
genus = "(unknown genus)",
species = "(unknown species)",
subspecies = "(unknown subspecies)",
rank = "(unknown rank)",
ref = NA_character_,
# kingdom Bacteria:
species_id = "36bea735613185bbd9ce135fb0d9382c"),
data.frame(mo = "B_GRAMN",
col_id = NA_integer_,
fullname = "(unknown Gram negatives)",
kingdom = "Bacteria",
phylum = "(unknown phylum)",
class = "(unknown class)",
order = "(unknown order)",
family = "(unknown family)",
genus = "(unknown Gram negatives)",
species = "(unknown species)",
subspecies = "(unknown subspecies)",
rank = "species",
ref = NA_character_,
stringsAsFactors = FALSE),
data.frame(mo = "B_GRAMP",
col_id = NA_integer_,
fullname = "(unknown Gram positives)",
kingdom = "Bacteria",
phylum = "(unknown phylum)",
class = "(unknown class)",
order = "(unknown order)",
family = "(unknown family)",
genus = "(unknown Gram positives)",
species = "(unknown species)",
subspecies = "(unknown subspecies)",
rank = "species",
ref = NA_character_,
stringsAsFactors = FALSE),
# CoNS
MOs %>%
filter(genus == "Staphylococcus", species == "epidermidis") %>% .[1,] %>%
@ -258,41 +307,13 @@ MOs <- MOs %>%
col_id = NA_integer_,
species = "beta-haemolytic" ,
fullname = "Beta-haemolytic Streptococcus",
ref = NA_character_),
# unknowns
data.frame(mo = "B_GRAMN",
col_id = NA_integer_,
fullname = "(unknown Gram negatives)",
kingdom = "Bacteria",
phylum = NA_character_,
class = NA_character_,
order = NA_character_,
family = NA_character_,
genus = "(unknown Gram negatives)",
species = NA_character_,
subspecies = NA_character_,
rank = "species",
ref = NA_character_,
stringsAsFactors = FALSE),
data.frame(mo = "B_GRAMP",
col_id = NA_integer_,
fullname = "(unknown Gram positives)",
kingdom = "Bacteria",
phylum = NA_character_,
class = NA_character_,
order = NA_character_,
family = NA_character_,
genus = "(unknown Gram positives)",
species = NA_character_,
subspecies = NA_character_,
rank = "species",
ref = NA_character_,
stringsAsFactors = FALSE)
ref = NA_character_)
)
# everything distinct?
sum(duplicated(MOs$mo))
colnames(MOs)
# save it
MOs <- as.data.frame(MOs %>% arrange(mo), stringsAsFactors = FALSE)

View File

@ -103,7 +103,7 @@ test_that("as.mo works", {
expect_warning(as.mo("ab"))
expect_equal(suppressWarnings(as.character(as.mo(c("Qq species", "", "CRS", "K. pneu rhino", "esco")))),
c(NA_character_, NA_character_, "B_STNTR_MAL", "B_KLBSL_PNE_RHI", "B_ESCHR_COL"))
c("UNKNOWN", NA_character_, "B_STNTR_MAL", "B_KLBSL_PNE_RHI", "B_ESCHR_COL"))
# check for Becker classification
expect_identical(as.character(as.mo("S. epidermidis", Becker = FALSE)), "B_STPHY_EPI")
@ -196,7 +196,7 @@ test_that("as.mo works", {
print(mo_renamed())
# check uncertain names
expect_equal(suppressWarnings(as.character(as.mo("esco extra_text", allow_uncertain = FALSE))), NA_character_)
expect_equal(suppressWarnings(as.character(as.mo("esco extra_text", allow_uncertain = FALSE))), "UNKNOWN")
expect_equal(suppressWarnings(as.character(as.mo("esco extra_text", allow_uncertain = TRUE))), "B_ESCHR_COL")
expect_warning(as.mo("esco extra_text", allow_uncertain = TRUE))