1
0
mirror of https://github.com/msberends/AMR.git synced 2024-12-26 06:46:11 +01:00

age and age_groups

This commit is contained in:
dr. M.S. (Matthijs) Berends 2018-12-15 22:40:07 +01:00
parent ecebc60bfd
commit 2018d5b477
9 changed files with 293 additions and 3 deletions

View File

@ -1,6 +1,6 @@
Package: AMR Package: AMR
Version: 0.5.0.9004 Version: 0.5.0.9005
Date: 2018-12-14 Date: 2018-12-15
Title: Antimicrobial Resistance Analysis Title: Antimicrobial Resistance Analysis
Authors@R: c( Authors@R: c(
person( person(

View File

@ -46,6 +46,8 @@ export(ab_tradenames)
export(ab_trivial_nl) export(ab_trivial_nl)
export(ab_umcg) export(ab_umcg)
export(abname) export(abname)
export(age)
export(age_groups)
export(anti_join_microorganisms) export(anti_join_microorganisms)
export(as.atc) export(as.atc)
export(as.bactid) export(as.bactid)

View File

@ -3,6 +3,8 @@
#### New #### New
* Function `mo_failures` to review values that could not be coerced to a valid MO code, using `as.mo`. This latter function will now only show a maximum of 25 uncoerced values. * Function `mo_failures` to review values that could not be coerced to a valid MO code, using `as.mo`. This latter function will now only show a maximum of 25 uncoerced values.
* Function `mo_renamed` to get a list of all returned values from `as.mo` that have had taxonomic renaming * Function `mo_renamed` to get a list of all returned values from `as.mo` that have had taxonomic renaming
* Function `age` to calculate the (patients) age in years
* Function `age_groups` to split ages into custom or predefined groups (like children or elderly). This allows for easier antimicrobial resistance per age group.
#### Changed #### Changed
* Improvements for `as.mo`: * Improvements for `as.mo`:
@ -16,7 +18,7 @@
* Function `first_isolate`: * Function `first_isolate`:
* Will now use a column named like "patid" for the patient ID (parameter `col_patientid`), when this parameter was left blank * Will now use a column named like "patid" for the patient ID (parameter `col_patientid`), when this parameter was left blank
* Will now use a column named like "key(...)ab" or "key(...)antibiotics" for the key antibiotics (parameter `col_keyantibiotics`), when this parameter was left blank * Will now use a column named like "key(...)ab" or "key(...)antibiotics" for the key antibiotics (parameter `col_keyantibiotics`), when this parameter was left blank
* A note to the manual pages of the `portion` functions, that low counts can infuence the outcome and that the `portion` functions may camouflage this, since they only return the portion (albeit being dependent on the `minimum` parameter) * A note to the manual pages of the `portion` functions, that low counts can influence the outcome and that the `portion` functions may camouflage this, since they only return the portion (albeit being dependent on the `minimum` parameter)
* Function `mo_taxonomy` now contains the kingdom too * Function `mo_taxonomy` now contains the kingdom too
* Function `first_isolate` will now use a column named like "patid" for the patient ID, when this parameter was left blank * Function `first_isolate` will now use a column named like "patid" for the patient ID, when this parameter was left blank
* Reduce false positives for `is.rsi.eligible` * Reduce false positives for `is.rsi.eligible`

147
R/age.R Normal file
View File

@ -0,0 +1,147 @@
# ==================================================================== #
# TITLE #
# Antimicrobial Resistance (AMR) Analysis #
# #
# AUTHORS #
# Berends MS (m.s.berends@umcg.nl), Luz CF (c.f.luz@umcg.nl) #
# #
# LICENCE #
# This program is free software; you can redistribute it and/or modify #
# it under the terms of the GNU General Public License version 2.0, #
# as published by the Free Software Foundation. #
# #
# This program is distributed in the hope that it will be useful, #
# but WITHOUT ANY WARRANTY; without even the implied warranty of #
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the #
# GNU General Public License for more details. #
# ==================================================================== #
#' Age in years of individuals
#'
#' Calculates age in years based on a reference date, which is the sytem time at default.
#' @param x date(s) - will be coerced with \code{\link{as.POSIXlt}}
#' @param y reference date(s) - defaults to \code{\link{Sys.Date}} - will be coerced with \code{\link{as.POSIXlt}}
#' @return Integer (no decimals)
#' @seealso age_groups
#' @importFrom dplyr if_else
#' @export
age <- function(x, y = Sys.Date()) {
if (length(x) != length(y)) {
if (length(y) == 1) {
y <- rep(y, length(x))
} else {
stop("`x` and `y` must be of same length, or `y` must be of length 1.")
}
}
x <- base::as.POSIXlt(x)
y <- base::as.POSIXlt(y)
if (any(y < x)) {
stop("`y` cannot be lower (older) than `x`.")
}
years_gap <- y$year - x$year
# from https://stackoverflow.com/a/25450756/4575331
ages <- if_else(y$mon < x$mon | (y$mon == x$mon & y$mday < x$mday),
as.integer(years_gap - 1),
as.integer(years_gap))
if (any(ages > 120)) {
warning("Some ages are >120.")
}
ages
}
#' Split ages in age groups
#'
#' Splits ages into groups defined by the \code{split} parameter.
#' @param x age, e.g. calculated with \code{\link{age}}
#' @param split_at values to split \code{x}, defaults to 0-11, 12-24, 26-54, 55-74 and 75+. See Details.
#' @details To split ages, the input can be:
#' \itemize{
#' \item{A numeric vector. A vector of \code{c(10, 20)} will split on 0-9, 10-19 and 20+. A value of only \code{50} will split on 0-49 and 50+.
#' The default is to split on young children (0-11), youth (12-24), young adults (26-54), middle-aged adults (55-74) and elderly (75+).}
#' \item{A character:}
#' \itemize{
#' \item{\code{"children"}, equivalent of: \code{c(0, 1, 2, 4, 6, 13, 18)}. This will split on 0, 1, 2-3, 4-5, 6-12, 13-17 and 18+.}
#' \item{\code{"elderly"} or \code{"seniors"}, equivalent: of \code{c(65, 75, 85, 95)}. This will split on 0-64, 65-74, 75-84, 85-94 and 95+.}
#' \item{\code{"fives"}, equivalent: of \code{1:20 * 5}. This will split on 0-4, 5-9, 10-14, 15-19 and so forth.}
#' \item{\code{"tens"}, equivalent: of \code{1:10 * 10}. This will split on 0-9, 10-19, 20-29 and so forth.}
#' }
#' }
#' @return Ordered \code{\link{factor}}
#' @seealso age
#' @export
#' @examples
#' ages <- c(3, 8, 16, 54, 31, 76, 101, 43, 21)
#'
#' # split on 0-49 and 50+
#' age_groups(ages, 50)
#'
#' # split on 0-20, 21-49 and 50+
#' age_groups(ages, c(21, 50))
#'
#' # split on every ten years
#' age_groups(ages, 1:10 * 10)
#' age_groups(ages, "tens")
#'
#' # split on every five years
#' age_groups(ages, 1:20 * 5)
#' age_groups(ages, "fives")
#'
#' # split on children
#' age_groups(ages, "children")
#'
#' # resistance of ciprofloxacine per age group
#' septic_patients %>%
#' mutate(first_isolate = first_isolate(.)) %>%
#' filter(first_isolate == TRUE,
#' mo == as.mo("E. coli")) %>%
#' group_by(age_group = age_groups(age)) %>%
#' select(age_group,
#' cipr) %>%
#' ggplot_rsi(x = "age_group")
age_groups <- function(x, split_at = c(12, 25, 55, 75)) {
if (is.character(split_at)) {
if (split_at %like% "^child") {
split_at <- c(0, 1, 2, 4, 6, 13, 18)
}
if (split_at %like% "^elder" | split_at %like% "^senior") {
split_at <- c(65, 75, 85, 95)
}
if (split_at %like% "fives") {
split_at <- 1:20 * 5
}
if (split_at %like% "^tens") {
split_at <- 1:10 * 10
}
}
if (!is.numeric(x) | !is.numeric(split_at)) {
stop("`x` and `split_at` must both be numeric.")
}
split_at <- sort(unique(split_at))
if (!split_at[1] == 0) {
split_at <- c(0, split_at)
}
if (length(split_at) == 1) {
# only 0 available
stop("invalid value for `split_at`.")
}
# turn input values to 'split_at' indices
y <- x
for (i in 1:length(split_at)) {
y[x >= split_at[i]] <- i
}
# create labels
labs <- split_at
for (i in 2:length(labs)) {
if (split_at[i - 1] == split_at[i] - 1) {
labs[i - 1] <- split_at[i - 1]
} else {
labs[i - 1] <- paste0(split_at[i - 1], "-", split_at[i] - 1)
}
}
# last category
labs[length(labs)] <- paste0(split_at[length(split_at)], "+")
factor(labs[y], levels = labs, ordered = TRUE)
}

View File

@ -86,6 +86,17 @@
#' size = 1, #' size = 1,
#' linetype = 2, #' linetype = 2,
#' alpha = 0.25) #' alpha = 0.25)
#'
#' # resistance of ciprofloxacine per age group
#' septic_patients %>%
#' mutate(first_isolate = first_isolate(.)) %>%
#' filter(first_isolate == TRUE,
#' mo == as.mo("E. coli")) %>%
#' # `age_group` is also a function of this package:
#' group_by(age_group = age_groups(age)) %>%
#' select(age_group,
#' cipr) %>%
#' ggplot_rsi(x = "age_group")
#' \donttest{ #' \donttest{
#' #'
#' # for colourblind mode, use divergent colours from the viridis package: #' # for colourblind mode, use divergent colours from the viridis package:

22
man/age.Rd Normal file
View File

@ -0,0 +1,22 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/age.R
\name{age}
\alias{age}
\title{Age in years of individuals}
\usage{
age(x, y = Sys.Date())
}
\arguments{
\item{x}{date(s) - will be coerced with \code{\link{as.POSIXlt}}}
\item{y}{reference date(s) - defaults to \code{\link{Sys.Date}} - will be coerced with \code{\link{as.POSIXlt}}}
}
\value{
Integer (no decimals)
}
\description{
Calculates age in years based on a reference date, which is the sytem time at default.
}
\seealso{
age_groups
}

66
man/age_groups.Rd Normal file
View File

@ -0,0 +1,66 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/age.R
\name{age_groups}
\alias{age_groups}
\title{Split ages in age groups}
\usage{
age_groups(x, split_at = c(12, 25, 55, 75))
}
\arguments{
\item{x}{age, e.g. calculated with \code{\link{age}}}
\item{split_at}{values to split \code{x}, defaults to 0-11, 12-24, 26-54, 55-74 and 75+. See Details.}
}
\value{
Ordered \code{\link{factor}}
}
\description{
Splits ages into groups defined by the \code{split} parameter.
}
\details{
To split ages, the input can be:
\itemize{
\item{A numeric vector. A vector of \code{c(10, 20)} will split on 0-9, 10-19 and 20+. A value of only \code{50} will split on 0-49 and 50+.
The default is to split on young children (0-11), youth (12-24), young adults (26-54), middle-aged adults (55-74) and elderly (75+).}
\item{A character:}
\itemize{
\item{\code{"children"}, equivalent of: \code{c(0, 1, 2, 4, 6, 13, 18)}. This will split on 0, 1, 2-3, 4-5, 6-12, 13-17 and 18+.}
\item{\code{"elderly"} or \code{"seniors"}, equivalent: of \code{c(65, 75, 85, 95)}. This will split on 0-64, 65-74, 75-84, 85-94 and 95+.}
\item{\code{"fives"}, equivalent: of \code{1:20 * 5}. This will split on 0-4, 5-9, 10-14, 15-19 and so forth.}
\item{\code{"tens"}, equivalent: of \code{1:10 * 10}. This will split on 0-9, 10-19, 20-29 and so forth.}
}
}
}
\examples{
ages <- c(3, 8, 16, 54, 31, 76, 101, 43, 21)
# split on 0-49 and 50+
age_groups(ages, 50)
# split on 0-20, 21-49 and 50+
age_groups(ages, c(21, 50))
# split on every ten years
age_groups(ages, 1:10 * 10)
age_groups(ages, "tens")
# split on every five years
age_groups(ages, 1:20 * 5)
age_groups(ages, "fives")
# split on children
age_groups(ages, "children")
# resistance of ciprofloxacine per age group
septic_patients \%>\%
mutate(first_isolate = first_isolate(.)) \%>\%
filter(first_isolate == TRUE,
mo == as.mo("E. coli")) \%>\%
group_by(age_group = age_groups(age)) \%>\%
select(age_group,
cipr) \%>\%
ggplot_rsi(x = "age_group")
}
\seealso{
age
}

View File

@ -114,6 +114,17 @@ septic_patients \%>\%
size = 1, size = 1,
linetype = 2, linetype = 2,
alpha = 0.25) alpha = 0.25)
# resistance of ciprofloxacine per age group
septic_patients \%>\%
mutate(first_isolate = first_isolate(.)) \%>\%
filter(first_isolate == TRUE,
mo == as.mo("E. coli")) \%>\%
# `age_group` is also a function of this package:
group_by(age_group = age_groups(age)) \%>\%
select(age_group,
cipr) \%>\%
ggplot_rsi(x = "age_group")
\donttest{ \donttest{
# for colourblind mode, use divergent colours from the viridis package: # for colourblind mode, use divergent colours from the viridis package:

29
tests/testthat/test-age.R Normal file
View File

@ -0,0 +1,29 @@
context("g.test.R")
test_that("age works", {
expect_equal(age(x = c("1980-01-01", "1985-01-01", "1990-01-01"),
y = "2019-01-01"),
c(39, 34, 29))
expect_error(age(x = c("1980-01-01", "1985-01-01", "1990-01-01"),
y = c("2019-01-01", "2019-01-01")))
expect_error(age(x = c("1980-01-01", "1985-01-01", "1990-01-01"),
y = "1975-01-01"))
expect_warning(age(x = c("1800-01-01", "1805-01-01", "1810-01-01"),
y = "2019-01-01"))
})
test_that("age_groups works", {
ages <- c(3, 8, 16, 54, 31, 76, 101, 43, 21)
expect_equal(length(unique(age_groups(ages, 50))),
2)
expect_equal(length(unique(age_groups(ages, c(50, 60)))),
3)
expect_identical(class(age_groups(ages)),
c("ordered", "factor"))
})