AMR/R/availability.R

96 lines
3.9 KiB
R
Raw Normal View History

2019-02-04 12:24:07 +01:00
# ==================================================================== #
# TITLE #
# Antimicrobial Resistance (AMR) Analysis #
# #
# SOURCE #
2020-07-08 14:48:06 +02:00
# https://github.com/msberends/AMR #
2019-02-04 12:24:07 +01:00
# #
# LICENCE #
# (c) 2018-2020 Berends MS, Luz CF et al. #
2019-02-04 12:24:07 +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. #
2020-07-08 14:48:06 +02:00
# Visit our website for more info: https://msberends.github.io/AMR. #
2019-02-04 12:24:07 +01:00
# ==================================================================== #
#' Check availability of columns
#'
#' Easy check for data availability of all columns in a data set. This makes it easy to get an idea of which antimicrobial combinations can be used for calculation with e.g. [susceptibility()] and [resistance()].
#' @inheritSection lifecycle Stable lifecycle
#' @param tbl a [`data.frame`] or [`list`]
2019-03-26 15:34:04 +01:00
#' @param width number of characters to present the visual availability, defaults to filling the width of the console
#' @details The function returns a [`data.frame`] with columns `"resistant"` and `"visual_resistance"`. The values in that columns are calculated with [resistance()].
#' @return [`data.frame`] with column names of `tbl` as row names
2019-02-21 18:55:52 +01:00
#' @inheritSection AMR Read more on our website!
2019-02-04 12:24:07 +01:00
#' @export
#' @examples
#' availability(example_isolates)
2019-02-04 12:24:07 +01:00
#'
2020-05-16 21:40:50 +02:00
#' \dontrun{
2019-02-04 12:24:07 +01:00
#' library(dplyr)
#' example_isolates %>% availability()
2019-02-04 12:24:07 +01:00
#'
#' example_isolates %>%
2019-02-04 12:24:07 +01:00
#' select_if(is.rsi) %>%
#' availability()
#'
#' example_isolates %>%
2019-02-04 12:24:07 +01:00
#' filter(mo == as.mo("E. coli")) %>%
#' select_if(is.rsi) %>%
#' availability()
2020-05-16 21:40:50 +02:00
#' }
2019-03-26 15:34:04 +01:00
availability <- function(tbl, width = NULL) {
stop_ifnot(is.data.frame(tbl), "`tbl` must be a data.frame")
2019-10-11 17:21:02 +02:00
x <- base::sapply(tbl, function(x) {
1 - base::sum(base::is.na(x)) / base::length(x)
})
2019-02-04 12:24:07 +01:00
n <- base::sapply(tbl, function(x) base::length(x[!base::is.na(x)]))
R <- base::sapply(tbl, function(x) base::ifelse(is.rsi(x), resistance(x, minimum = 0), NA))
2019-08-25 22:53:22 +02:00
R_print <- character(length(R))
R_print[!is.na(R)] <- percentage(R[!is.na(R)])
2019-08-25 22:53:22 +02:00
R_print[is.na(R)] <- ""
2020-07-13 09:17:24 +02:00
2019-03-26 15:34:04 +01:00
if (is.null(width)) {
width <- options()$width -
(max(nchar(colnames(tbl))) +
# count col
8 +
# available % column
10 +
# resistant % column
10 +
# extra margin
5)
width <- width / 2
}
2020-07-13 09:17:24 +02:00
2019-08-25 22:53:22 +02:00
if (length(R[is.na(R)]) == ncol(tbl)) {
2019-03-26 15:34:04 +01:00
width <- width * 2 + 10
}
2020-07-13 09:17:24 +02:00
2019-08-25 22:53:22 +02:00
x_chars_R <- strrep("#", round(width * R, digits = 2))
x_chars_SI <- strrep("-", width - nchar(x_chars_R))
vis_resistance <- paste0("|", x_chars_R, x_chars_SI, "|")
vis_resistance[is.na(R)] <- ""
2020-07-13 09:17:24 +02:00
2019-03-26 15:34:04 +01:00
x_chars <- strrep("#", round(x, digits = 2) / (1 / width))
x_chars_empty <- strrep("-", width - nchar(x_chars))
2020-07-13 09:17:24 +02:00
2019-03-26 15:34:04 +01:00
df <- data.frame(count = n,
available = percentage(x),
2019-03-26 15:34:04 +01:00
visual_availabilty = paste0("|", x_chars, x_chars_empty, "|"),
2019-08-25 22:53:22 +02:00
resistant = R_print,
2019-03-26 15:34:04 +01:00
visual_resistance = vis_resistance)
2019-08-25 22:53:22 +02:00
if (length(R[is.na(R)]) == ncol(tbl)) {
2019-10-11 17:21:02 +02:00
df[, 1:3]
2019-03-26 15:34:04 +01:00
} else {
df
}
2019-02-04 12:24:07 +01:00
}