P281424/AMR
1
0
Fork 0
mirror of https://github.com/msberends/AMR.git synced 2024-12-25 19:26:13 +01:00
Code Releases Activity

parameter combine_IR

Browse Source
This commit is contained in:
dr. M.S. (Matthijs) Berends 2018-10-16 09:59:31 +02:00
parent 5b5b95a47b
commit d5a41de711
10 changed files with 110 additions and 48 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
DESCRIPTION
View File

@ -1,6 +1,6 @@
Package: AMR
Version: 0.4.0.9002
Date: 2018-10-12
Version: 0.4.0.9003
Date: 2018-10-16
Title: Antimicrobial Resistance Analysis
Authors@R: c(
person(

2
NEWS.md
View File

@ -4,6 +4,7 @@
* Function `count_all` to get all available isolates (that like all `portion_*` and `count_*` functions also supports `summarise` and `group_by`), the old `n_rsi` is now an alias of `count_all`
#### Changed
* Added parameter `combine_IR` (TRUE/FALSE) to functions `portion_df` and `count_df`, 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)
* Fix for `portion_*(..., as_percent = TRUE)` when minimal amount of isolates would not be met
* Using `portion_*` functions now throws a warning when total available isolate is below parameter `minimum`
* `as.mo` will not set package name as attribute anymore
@ -18,6 +19,7 @@
* `"MSSA"` -> *Staphylococcus aureus*
* `"MSSE"` -> *Staphylococcus epidermidis*
* Fix for `join` functions
* In `g.test`, when `sum(x)` is below 1000, suggest Fisher's Exact Test
#### Other
* Updated vignettes to comply with README

45
R/count.R
View File

@ -163,7 +163,8 @@ n_rsi <- function(...) {
#' @importFrom dplyr %>% select_if bind_rows summarise_if mutate group_vars select everything
#' @export
count_df <- function(data,
translate_ab = getOption("get_antibiotic_names", "official")) {
translate_ab = getOption("get_antibiotic_names", "official"),
combine_IR = FALSE) {
if (!"data.frame" %in% class(data)) {
stop("`count_df` must be called on a data.frame")
@ -184,23 +185,37 @@ count_df <- function(data,
mutate(Interpretation = "S") %>%
select(Interpretation, everything())
resI <- summarise_if(.tbl = data,
.predicate = is.rsi,
.funs = count_I) %>%
mutate(Interpretation = "I") %>%
select(Interpretation, everything())
if (combine_IR == FALSE) {
resI <- summarise_if(.tbl = data,
.predicate = is.rsi,
.funs = count_I) %>%
mutate(Interpretation = "I") %>%
select(Interpretation, everything())
resR <- summarise_if(.tbl = data,
.predicate = is.rsi,
.funs = count_R) %>%
mutate(Interpretation = "R") %>%
select(Interpretation, everything())
resR <- summarise_if(.tbl = data,
.predicate = is.rsi,
.funs = count_R) %>%
mutate(Interpretation = "R") %>%
select(Interpretation, everything())
data.groups <- group_vars(data)
data.groups <- group_vars(data)
res <- bind_rows(resS, resI, resR) %>%
mutate(Interpretation = factor(Interpretation, levels = c("R", "I", "S"), ordered = TRUE)) %>%
tidyr::gather(Antibiotic, Value, -Interpretation, -data.groups)
res <- bind_rows(resS, resI, resR) %>%
mutate(Interpretation = factor(Interpretation, levels = c("R", "I", "S"), ordered = TRUE)) %>%
tidyr::gather(Antibiotic, Value, -Interpretation, -data.groups)
} else {
resIR <- summarise_if(.tbl = data,
.predicate = is.rsi,
.funs = count_IR) %>%
mutate(Interpretation = "IR") %>%
select(Interpretation, everything())
data.groups <- group_vars(data)
res <- bind_rows(resS, resIR) %>%
mutate(Interpretation = factor(Interpretation, levels = c("IR", "S"), ordered = TRUE)) %>%
tidyr::gather(Antibiotic, Value, -Interpretation, -data.groups)
}
if (!translate_ab == FALSE) {
if (!tolower(translate_ab) %in% tolower(colnames(AMR::antibiotics))) {

11
R/g.test.R
View File

@ -217,8 +217,15 @@ g.test <- function(x,
}
names(STATISTIC) <- "X-squared"
names(PARAMETER) <- "df"
if (any(E < 5) && is.finite(PARAMETER))
warning("G-statistic approximation may be incorrect")
# if (any(E < 5) && is.finite(PARAMETER))
# warning("G-statistic approximation may be incorrect")
# suggest fisher.test when total is < 1000 (John McDonald, Handbook of Biological Statistics, 2014)
if (sum(x, na.rm = TRUE) < 1000 && is.finite(PARAMETER)) {
warning("G-statistic approximation may be incorrect, consider Fisher's Exact test")
} else if (any(E < 5) && is.finite(PARAMETER)) {
warning("G-statistic approximation may be incorrect, consider Fisher's Exact test")
}
structure(list(statistic = STATISTIC, parameter = PARAMETER,
p.value = PVAL, method = METHOD, data.name = DNAME,
observed = x, expected = E, residuals = (x - E)/sqrt(E),

60
R/portion.R
View File

@ -22,10 +22,11 @@
#'
#' \code{portion_R} and \code{portion_IR} can be used to calculate resistance, \code{portion_S} and \code{portion_SI} can be used to calculate susceptibility.\cr
#' @param ... one or more vectors (or columns) with antibiotic interpretations. They will be transformed internally with \code{\link{as.rsi}} if needed. Use multiple columns to calculate (the lack of) co-resistance: the probability where one of two drugs have a resistant or susceptible result. See Examples.
#' @param minimum minimal amount of available isolates. Any number lower than \code{minimum} will return \code{NA} with a warning. The default number of \code{30} isolates is advised by the Clinical and Laboratory Standards Institute (CLSI) as best practice, see Source.
#' @param as_percent logical to indicate whether the output must be returned as a hundred fold with \% sign (a character). A value of \code{0.123456} will then be returned as \code{"12.3\%"}.
#' @param minimum the minimal amount of available isolates. Any number lower than \code{minimum} will return \code{NA} with a warning. The default number of \code{30} isolates is advised by the Clinical and Laboratory Standards Institute (CLSI) as best practice, see Source.
#' @param as_percent a logical to indicate whether the output must be returned as a hundred fold with \% sign (a character). A value of \code{0.123456} will then be returned as \code{"12.3\%"}.
#' @param data a \code{data.frame} containing columns with class \code{rsi} (see \code{\link{as.rsi}})
#' @param translate_ab a column name of the \code{\link{antibiotics}} data set to translate the antibiotic abbreviations to, using \code{\link{abname}}. This can be set with \code{\link{getOption}("get_antibiotic_names")}.
#' @param combine_IR a logical to indicate whether all values of I and R must be merged into one, so the output only consists of S vs. IR (susceptible vs. non-susceptible)
#' @details \strong{Remember that you should filter your table to let it contain only first isolates!} Use \code{\link{first_isolate}} to determine them in your data set.
#'
#' These functions are not meant to count isolates, but to calculate the portion of resistance/susceptibility. If a column has been transformed with \code{\link{as.rsi}}, just use e.g. \code{isolates[isolates == "R"]} to get the resistant ones. You could then calculate the \code{\link{length}} of it.
@ -200,7 +201,8 @@ portion_S <- function(...,
portion_df <- function(data,
translate_ab = getOption("get_antibiotic_names", "official"),
minimum = 30,
as_percent = FALSE) {
as_percent = FALSE,
combine_IR = FALSE) {
if (!"data.frame" %in% class(data)) {
stop("`portion_df` must be called on a data.frame")
@ -223,27 +225,43 @@ portion_df <- function(data,
mutate(Interpretation = "S") %>%
select(Interpretation, everything())
resI <- summarise_if(.tbl = data,
.predicate = is.rsi,
.funs = portion_I,
minimum = minimum,
as_percent = as_percent) %>%
mutate(Interpretation = "I") %>%
select(Interpretation, everything())
if (combine_IR == FALSE) {
resI <- summarise_if(.tbl = data,
.predicate = is.rsi,
.funs = portion_I,
minimum = minimum,
as_percent = as_percent) %>%
mutate(Interpretation = "I") %>%
select(Interpretation, everything())
resR <- summarise_if(.tbl = data,
.predicate = is.rsi,
.funs = portion_R,
minimum = minimum,
as_percent = as_percent) %>%
mutate(Interpretation = "R") %>%
select(Interpretation, everything())
resR <- summarise_if(.tbl = data,
.predicate = is.rsi,
.funs = portion_R,
minimum = minimum,
as_percent = as_percent) %>%
mutate(Interpretation = "R") %>%
select(Interpretation, everything())
data.groups <- group_vars(data)
data.groups <- group_vars(data)
res <- bind_rows(resS, resI, resR) %>%
mutate(Interpretation = factor(Interpretation, levels = c("R", "I", "S"), ordered = TRUE)) %>%
tidyr::gather(Antibiotic, Value, -Interpretation, -data.groups)
res <- bind_rows(resS, resI, resR) %>%
mutate(Interpretation = factor(Interpretation, levels = c("R", "I", "S"), ordered = TRUE)) %>%
tidyr::gather(Antibiotic, Value, -Interpretation, -data.groups)
} else {
resIR <- summarise_if(.tbl = data,
.predicate = is.rsi,
.funs = portion_IR,
minimum = minimum,
as_percent = as_percent) %>%
mutate(Interpretation = "IR") %>%
select(Interpretation, everything())
data.groups <- group_vars(data)
res <- bind_rows(resS, resIR) %>%
mutate(Interpretation = factor(Interpretation, levels = c("IR", "S"), ordered = TRUE)) %>%
tidyr::gather(Antibiotic, Value, -Interpretation, -data.groups)
}
if (!translate_ab == FALSE) {
if (!tolower(translate_ab) %in% tolower(colnames(AMR::antibiotics))) {

4
man/count.Rd
View File

@ -30,7 +30,7 @@ count_all(...)
n_rsi(...)
count_df(data, translate_ab = getOption("get_antibiotic_names",
"official"))
"official"), combine_IR = FALSE)
}
\arguments{
\item{...}{one or more vectors (or columns) with antibiotic interpretations. They will be transformed internally with \code{\link{as.rsi}} if needed.}
@ -38,6 +38,8 @@ count_df(data, translate_ab = getOption("get_antibiotic_names",
\item{data}{a \code{data.frame} containing columns with class \code{rsi} (see \code{\link{as.rsi}})}
\item{translate_ab}{a column name of the \code{\link{antibiotics}} data set to translate the antibiotic abbreviations to, using \code{\link{abname}}. This can be set with \code{\link{getOption}("get_antibiotic_names")}.}
\item{combine_IR}{a logical to indicate whether all values of I and R must be merged into one, so the output only consists of S vs. IR (susceptible vs. non-susceptible)}
}
\value{
Integer

8
man/portion.Rd
View File

@ -26,18 +26,20 @@ portion_SI(..., minimum = 30, as_percent = FALSE)
portion_S(..., minimum = 30, as_percent = FALSE)
portion_df(data, translate_ab = getOption("get_antibiotic_names",
"official"), minimum = 30, as_percent = FALSE)
"official"), minimum = 30, as_percent = FALSE, combine_IR = FALSE)
}
\arguments{
\item{...}{one or more vectors (or columns) with antibiotic interpretations. They will be transformed internally with \code{\link{as.rsi}} if needed. Use multiple columns to calculate (the lack of) co-resistance: the probability where one of two drugs have a resistant or susceptible result. See Examples.}
\item{minimum}{minimal amount of available isolates. Any number lower than \code{minimum} will return \code{NA} with a warning. The default number of \code{30} isolates is advised by the Clinical and Laboratory Standards Institute (CLSI) as best practice, see Source.}
\item{minimum}{the minimal amount of available isolates. Any number lower than \code{minimum} will return \code{NA} with a warning. The default number of \code{30} isolates is advised by the Clinical and Laboratory Standards Institute (CLSI) as best practice, see Source.}
\item{as_percent}{logical to indicate whether the output must be returned as a hundred fold with \% sign (a character). A value of \code{0.123456} will then be returned as \code{"12.3\%"}.}
\item{as_percent}{a logical to indicate whether the output must be returned as a hundred fold with \% sign (a character). A value of \code{0.123456} will then be returned as \code{"12.3\%"}.}
\item{data}{a \code{data.frame} containing columns with class \code{rsi} (see \code{\link{as.rsi}})}
\item{translate_ab}{a column name of the \code{\link{antibiotics}} data set to translate the antibiotic abbreviations to, using \code{\link{abname}}. This can be set with \code{\link{getOption}("get_antibiotic_names")}.}
\item{combine_IR}{a logical to indicate whether all values of I and R must be merged into one, so the output only consists of S vs. IR (susceptible vs. non-susceptible)}
}
\value{
Double or, when \code{as_percent = TRUE}, a character.

4
man/rsi.Rd
View File

@ -12,9 +12,9 @@ rsi(ab1, ab2 = NULL, interpretation = "IR", minimum = 30,
\item{interpretation}{antimicrobial interpretation to check for}
\item{minimum}{minimal amount of available isolates. Any number lower than \code{minimum} will return \code{NA} with a warning. The default number of \code{30} isolates is advised by the Clinical and Laboratory Standards Institute (CLSI) as best practice, see Source.}
\item{minimum}{the minimal amount of available isolates. Any number lower than \code{minimum} will return \code{NA} with a warning. The default number of \code{30} isolates is advised by the Clinical and Laboratory Standards Institute (CLSI) as best practice, see Source.}
\item{as_percent}{logical to indicate whether the output must be returned as a hundred fold with \% sign (a character). A value of \code{0.123456} will then be returned as \code{"12.3\%"}.}
\item{as_percent}{a logical to indicate whether the output must be returned as a hundred fold with \% sign (a character). A value of \code{0.123456} will then be returned as \code{"12.3\%"}.}
\item{...}{deprecated parameters to support usage on older versions}
}

14
tests/testthat/test-count.R
View File

@ -27,8 +27,18 @@ test_that("counts work", {
pull(combination),
c(192, 446, 184, 474))
expect_equal(septic_patients %>% select(amox, cipr) %>% count_df(translate_ab = "official") %>% nrow(),
6)
# count_df
expect_equal(
septic_patients %>% select(amox) %>% count_df() %>% pull(Value),
c(septic_patients$amox %>% count_S(),
septic_patients$amox %>% count_I(),
septic_patients$amox %>% count_R())
)
expect_equal(
septic_patients %>% select(amox) %>% count_df(combine_IR = TRUE) %>% pull(Value),
c(septic_patients$amox %>% count_S(),
septic_patients$amox %>% count_IR())
)
# warning for speed loss
expect_warning(count_R(as.character(septic_patients$amcl)))

6
tests/testthat/test-portion.R
View File

@ -117,6 +117,12 @@ test_that("old rsi works", {
septic_patients$amox %>% portion_I(),
septic_patients$amox %>% portion_R())
)
expect_equal(
septic_patients %>% select(amox) %>% portion_df(combine_IR = TRUE) %>% pull(Value),
c(septic_patients$amox %>% portion_S(),
septic_patients$amox %>% portion_IR())
)
})