AMR/R/age.R

157 lines
6.3 KiB
R
Raw Normal View History

2018-12-15 22:40:07 +01:00
# ==================================================================== #
# TITLE #
# Antimicrobial Resistance (AMR) Analysis #
# #
2019-01-02 23:24:07 +01:00
# SOURCE #
# https://gitlab.com/msberends/AMR #
2018-12-15 22:40:07 +01:00
# #
# LICENCE #
2019-01-02 23:24:07 +01:00
# (c) 2019 Berends MS (m.s.berends@umcg.nl), Luz CF (c.f.luz@umcg.nl) #
2018-12-15 22:40:07 +01:00
# #
2019-01-02 23:24:07 +01:00
# This R package is free software; you can freely use and distribute #
# it for both personal and commercial purposes under the terms of the #
# GNU General Public License version 2.0 (GNU GPL-2), as published by #
# the Free Software Foundation. #
# #
# This R package was created for academic research and was publicly #
# released in the hope that it will be useful, but it comes WITHOUT #
# ANY WARRANTY OR LIABILITY. #
# Visit our website for more info: https://msberends.gitab.io/AMR. #
2018-12-15 22:40:07 +01:00
# ==================================================================== #
#' Age in years of individuals
#'
2019-01-12 11:06:58 +01:00
#' Calculates age in years based on a reference date, which is the sytem date at default.
2018-12-22 22:39:34 +01:00
#' @param x date(s), will be coerced with \code{\link{as.POSIXlt}}
2019-01-12 11:06:58 +01:00
#' @param reference reference date(s) (defaults to today), will be coerced with \code{\link{as.POSIXlt}} and cannot be lower than \code{x}
2018-12-15 22:40:07 +01:00
#' @return Integer (no decimals)
2019-01-12 11:06:58 +01:00
#' @seealso \code{\link{age_groups}} to split age into age groups
2018-12-15 22:40:07 +01:00
#' @importFrom dplyr if_else
2019-01-02 23:24:07 +01:00
#' @inheritSection AMR Read more on our website!
2018-12-15 22:40:07 +01:00
#' @export
2019-01-25 13:18:41 +01:00
#' @examples
#' df <- data.frame(birth_date = Sys.Date() - runif(100) * 25000)
#' df$age <- age(df$birth_date)
2018-12-22 22:39:34 +01:00
age <- function(x, reference = Sys.Date()) {
if (length(x) != length(reference)) {
if (length(reference) == 1) {
reference <- rep(reference, length(x))
2018-12-15 22:40:07 +01:00
} else {
2018-12-22 22:39:34 +01:00
stop("`x` and `reference` must be of same length, or `reference` must be of length 1.")
2018-12-15 22:40:07 +01:00
}
}
x <- base::as.POSIXlt(x)
2018-12-22 22:39:34 +01:00
reference <- base::as.POSIXlt(reference)
2019-01-25 13:18:41 +01:00
2018-12-15 22:40:07 +01:00
# from https://stackoverflow.com/a/25450756/4575331
2019-01-25 13:18:41 +01:00
years_gap <- reference$year - x$year
2018-12-22 22:39:34 +01:00
ages <- if_else(reference$mon < x$mon | (reference$mon == x$mon & reference$mday < x$mday),
2019-01-12 11:06:58 +01:00
as.integer(years_gap - 1),
as.integer(years_gap))
2019-01-25 13:18:41 +01:00
if (any(ages < 0, na.rm = TRUE)) {
warning("NAs introduced for ages below 0.")
ages[ages < 0] <- NA_integer_
}
if (any(ages > 120, na.rm = TRUE)) {
2019-01-11 20:37:23 +01:00
warning("Some ages are > 120.")
2018-12-15 22:40:07 +01:00
}
2019-01-25 13:18:41 +01:00
2018-12-15 22:40:07 +01:00
ages
}
#' Split ages into age groups
2018-12-15 22:40:07 +01:00
#'
2018-12-22 22:39:34 +01:00
#' Split ages into age groups defined by the \code{split} parameter. This allows for easier demographic (antimicrobial resistance) analysis.
2018-12-15 22:40:07 +01:00
#' @param x age, e.g. calculated with \code{\link{age}}
2018-12-22 22:39:34 +01:00
#' @param split_at values to split \code{x} at, defaults to age groups 0-11, 12-24, 26-54, 55-74 and 75+. See Details.
2018-12-15 22:40:07 +01:00
#' @details To split ages, the input can be:
#' \itemize{
2019-01-12 11:06:58 +01:00
#' \item{A numeric vector. A vector of e.g. \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+.
2018-12-15 22:40:07 +01:00
#' 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.}
2018-12-15 22:40:07 +01:00
#' }
#' }
#' @keywords age_group age
2018-12-15 22:40:07 +01:00
#' @return Ordered \code{\link{factor}}
2018-12-22 22:39:34 +01:00
#' @seealso \code{\link{age}} to determine ages based on one or more reference dates
2018-12-15 22:40:07 +01:00
#' @export
2019-01-02 23:24:07 +01:00
#' @inheritSection AMR Read more on our website!
2018-12-15 22:40:07 +01:00
#' @examples
#' ages <- c(3, 8, 16, 54, 31, 76, 101, 43, 21)
#'
#' # split into 0-49 and 50+
2018-12-15 22:40:07 +01:00
#' age_groups(ages, 50)
#'
#' # split into 0-19, 20-49 and 50+
#' age_groups(ages, c(20, 50))
2018-12-15 22:40:07 +01:00
#'
#' # split into groups of ten years
2018-12-15 22:40:07 +01:00
#' age_groups(ages, 1:10 * 10)
#' age_groups(ages, split_at = "tens")
2018-12-15 22:40:07 +01:00
#'
#' # split into groups of five years
2018-12-15 22:40:07 +01:00
#' age_groups(ages, 1:20 * 5)
#' age_groups(ages, split_at = "fives")
2018-12-15 22:40:07 +01:00
#'
#' # split specifically for children
2018-12-15 22:40:07 +01:00
#' age_groups(ages, "children")
#' # same:
#' age_groups(ages, c(1, 2, 4, 6, 13, 17))
2018-12-15 22:40:07 +01:00
#'
#' # resistance of ciprofloxacine per age group
2018-12-16 09:50:14 +01:00
#' library(dplyr)
2018-12-15 22:40:07 +01:00
#' 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)) {
split_at <- split_at[1L]
2018-12-15 22:40:07 +01:00
if (split_at %like% "^child") {
split_at <- c(0, 1, 2, 4, 6, 13, 18)
} else if (split_at %like% "^(elder|senior)") {
2018-12-15 22:40:07 +01:00
split_at <- c(65, 75, 85, 95)
} else if (split_at %like% "^five") {
2018-12-15 22:40:07 +01:00
split_at <- 1:20 * 5
} else if (split_at %like% "^ten") {
2018-12-15 22:40:07 +01:00
split_at <- 1:10 * 10
}
}
split_at <- as.integer(split_at)
2018-12-15 22:40:07 +01:00
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
labs <- split_at
2018-12-15 22:40:07 +01:00
for (i in 1:length(split_at)) {
y[x >= split_at[i]] <- i
# create labels
2019-01-12 11:06:58 +01:00
labs[i - 1] <- paste0(unique(c(split_at[i - 1], split_at[i] - 1)), collapse = "-")
2018-12-15 22:40:07 +01:00
}
# last category
labs[length(labs)] <- paste0(split_at[length(split_at)], "+")
factor(labs[y], levels = labs, ordered = TRUE)
}