1
0
mirror of https://github.com/msberends/AMR.git synced 2024-12-26 18:46:13 +01:00
AMR/R/count.R

200 lines
8.1 KiB
R
Raw Normal View History

2018-08-22 00:02:26 +02:00
# ==================================================================== #
# TITLE #
2020-10-08 11:16:03 +02:00
# Antimicrobial Resistance (AMR) Analysis for R #
2018-08-22 00:02:26 +02:00
# #
2019-01-02 23:24:07 +01:00
# SOURCE #
2020-07-08 14:48:06 +02:00
# https://github.com/msberends/AMR #
2018-08-22 00:02:26 +02:00
# #
# LICENCE #
# (c) 2018-2020 Berends MS, Luz CF et al. #
2020-10-08 11:16:03 +02:00
# Developed at the University of Groningen, the Netherlands, in #
# collaboration with non-profit organisations Certe Medical #
# Diagnostics & Advice, and University Medical Center Groningen. #
2018-08-22 00:02:26 +02:00
# #
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. #
# We created this package for both routine data analysis and academic #
# research and it was publicly released in the hope that it will be #
# useful, but it comes WITHOUT ANY WARRANTY OR LIABILITY. #
2020-10-08 11:16:03 +02:00
# #
# Visit our website for the full manual and a complete tutorial about #
# how to conduct AMR analysis: https://msberends.github.io/AMR/ #
2018-08-22 00:02:26 +02:00
# ==================================================================== #
#' Count available isolates
2018-08-22 00:02:26 +02:00
#'
2020-05-16 20:08:21 +02:00
#' @description These functions can be used to count resistant/susceptible microbial isolates. All functions support quasiquotation with pipes, can be used in `summarise()` from the `dplyr` package and also support grouped variables, please see *Examples*.
2018-08-22 00:02:26 +02:00
#'
#' [count_resistant()] should be used to count resistant isolates, [count_susceptible()] should be used to count susceptible isolates.
#' @inheritSection lifecycle Stable lifecycle
#' @param ... one or more vectors (or columns) with antibiotic interpretations. They will be transformed internally with [as.rsi()] if needed.
#' @inheritParams proportion
2019-11-29 19:43:23 +01:00
#' @inheritSection as.rsi Interpretation of R and S/I
#' @details These functions are meant to count isolates. Use the [resistance()]/[susceptibility()] functions to calculate microbial resistance/susceptibility.
#'
#' The function [count_resistant()] is equal to the function [count_R()]. The function [count_susceptible()] is equal to the function [count_SI()].
2018-08-22 00:02:26 +02:00
#'
2020-05-16 20:08:21 +02:00
#' The function [n_rsi()] is an alias of [count_all()]. They can be used to count all available isolates, i.e. where all input antibiotics have an available result (S, I or R). Their use is equal to `n_distinct()`. Their function is equal to `count_susceptible(...) + count_resistant(...)`.
2018-08-22 00:02:26 +02:00
#'
2020-05-16 13:05:47 +02:00
#' The function [count_df()] takes any variable from `data` that has an [`rsi`] class (created with [as.rsi()]) and counts the number of S's, I's and R's. It also supports grouped variables. The function [rsi_df()] works exactly like [count_df()], but adds the percentage of S, I and R.
#' @inheritSection proportion Combination therapy
#' @seealso [`proportion_*`][proportion] to calculate microbial resistance and susceptibility.
#' @return An [integer]
2018-08-22 00:02:26 +02:00
#' @rdname count
#' @name count
#' @export
2019-01-02 23:24:07 +01:00
#' @inheritSection AMR Read more on our website!
2018-08-22 00:02:26 +02:00
#' @examples
#' # example_isolates is a data set available in the AMR package.
#' ?example_isolates
#'
#' count_resistant(example_isolates$AMX) # counts "R"
#' count_susceptible(example_isolates$AMX) # counts "S" and "I"
#' count_all(example_isolates$AMX) # counts "S", "I" and "R"
2018-08-22 00:02:26 +02:00
#'
#' # be more specific
#' count_S(example_isolates$AMX)
#' count_SI(example_isolates$AMX)
#' count_I(example_isolates$AMX)
#' count_IR(example_isolates$AMX)
#' count_R(example_isolates$AMX)
2018-08-22 00:02:26 +02:00
#'
2018-10-12 16:35:18 +02:00
#' # Count all available isolates
#' count_all(example_isolates$AMX)
#' n_rsi(example_isolates$AMX)
2018-10-12 16:35:18 +02:00
#'
#' # n_rsi() is an alias of count_all().
#' # Since it counts all available isolates, you can
#' # calculate back to count e.g. susceptible isolates.
#' # These results are the same:
#' count_susceptible(example_isolates$AMX)
#' susceptibility(example_isolates$AMX) * n_rsi(example_isolates$AMX)
2018-08-22 00:02:26 +02:00
#'
2020-05-16 20:08:21 +02:00
#'
2020-05-16 21:40:50 +02:00
#' if (require("dplyr")) {
2020-05-16 20:08:21 +02:00
#' example_isolates %>%
#' group_by(hospital_id) %>%
#' summarise(R = count_R(CIP),
#' I = count_I(CIP),
#' S = count_S(CIP),
#' n1 = count_all(CIP), # the actual total; sum of all three
#' n2 = n_rsi(CIP), # same - analogous to n_distinct
#' total = n()) # NOT the number of tested isolates!
#'
#' # Count co-resistance between amoxicillin/clav acid and gentamicin,
#' # so we can see that combination therapy does a lot more than mono therapy.
#' # Please mind that `susceptibility()` calculates percentages right away instead.
#' example_isolates %>% count_susceptible(AMC) # 1433
#' example_isolates %>% count_all(AMC) # 1879
#'
#' example_isolates %>% count_susceptible(GEN) # 1399
#' example_isolates %>% count_all(GEN) # 1855
#'
#' example_isolates %>% count_susceptible(AMC, GEN) # 1764
#' example_isolates %>% count_all(AMC, GEN) # 1936
#'
#' # Get number of S+I vs. R immediately of selected columns
#' example_isolates %>%
#' select(AMX, CIP) %>%
#' count_df(translate = FALSE)
#'
#' # It also supports grouping variables
#' example_isolates %>%
#' select(hospital_id, AMX, CIP) %>%
#' group_by(hospital_id) %>%
#' count_df(translate = FALSE)
#' }
count_resistant <- function(..., only_all_tested = FALSE) {
rsi_calc(...,
ab_result = "R",
only_all_tested = only_all_tested,
only_count = TRUE)
}
#' @rdname count
#' @export
count_susceptible <- function(..., only_all_tested = FALSE) {
rsi_calc(...,
ab_result = c("S", "I"),
only_all_tested = only_all_tested,
only_count = TRUE)
}
#' @rdname count
#' @export
count_R <- function(..., only_all_tested = FALSE) {
2018-08-23 00:40:36 +02:00
rsi_calc(...,
ab_result = "R",
only_all_tested = only_all_tested,
2018-08-22 00:02:26 +02:00
only_count = TRUE)
}
#' @rdname count
#' @export
count_IR <- function(..., only_all_tested = FALSE) {
2020-11-10 16:35:56 +01:00
warning_("Using 'count_IR' is discouraged; use 'count_resistant()' instead to not consider \"I\" being resistant.", call = FALSE)
2018-08-23 00:40:36 +02:00
rsi_calc(...,
ab_result = c("I", "R"),
only_all_tested = only_all_tested,
2018-08-22 00:02:26 +02:00
only_count = TRUE)
}
#' @rdname count
#' @export
count_I <- function(..., only_all_tested = FALSE) {
2018-08-23 00:40:36 +02:00
rsi_calc(...,
ab_result = "I",
only_all_tested = only_all_tested,
2018-08-22 00:02:26 +02:00
only_count = TRUE)
}
#' @rdname count
#' @export
count_SI <- function(..., only_all_tested = FALSE) {
2018-08-23 00:40:36 +02:00
rsi_calc(...,
ab_result = c("S", "I"),
only_all_tested = only_all_tested,
2018-08-22 00:02:26 +02:00
only_count = TRUE)
}
#' @rdname count
#' @export
count_S <- function(..., only_all_tested = FALSE) {
2020-11-10 16:35:56 +01:00
warning_("Using 'count_S' is discouraged; use 'count_susceptible()' instead to also consider \"I\" being susceptible.", call = FALSE)
2018-08-23 00:40:36 +02:00
rsi_calc(...,
ab_result = "S",
only_all_tested = only_all_tested,
2018-08-22 00:02:26 +02:00
only_count = TRUE)
}
2018-10-12 16:35:18 +02:00
#' @rdname count
#' @export
count_all <- function(..., only_all_tested = FALSE) {
rsi_calc(...,
ab_result = c("S", "I", "R"),
only_all_tested = only_all_tested,
only_count = TRUE)
2018-10-12 16:35:18 +02:00
}
#' @rdname count
#' @export
2019-10-11 17:21:02 +02:00
n_rsi <- count_all
2018-10-12 16:35:18 +02:00
2018-08-22 00:02:26 +02:00
#' @rdname count
#' @export
count_df <- function(data,
2019-05-10 16:44:59 +02:00
translate_ab = "name",
language = get_locale(),
2019-05-13 10:10:16 +02:00
combine_SI = TRUE,
2018-10-16 09:59:31 +02:00
combine_IR = FALSE) {
2019-05-13 10:10:16 +02:00
rsi_calc_df(type = "count",
data = data,
translate_ab = translate_ab,
language = language,
combine_SI = combine_SI,
combine_IR = combine_IR,
combine_SI_missing = missing(combine_SI))
2018-08-22 00:02:26 +02:00
}