diff --git a/DESCRIPTION b/DESCRIPTION
index f080051c..c44161f3 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -1,6 +1,6 @@
Package: AMR
-Version: 0.7.1.9069
-Date: 2019-09-01
+Version: 0.7.1.9070
+Date: 2019-09-02
Title: Antimicrobial Resistance Analysis
Authors@R: c(
person(role = c("aut", "cre"),
diff --git a/NEWS.md b/NEWS.md
index 94d56390..375f3054 100755
--- a/NEWS.md
+++ b/NEWS.md
@@ -1,5 +1,5 @@
-# AMR 0.7.1.9069
-Last updated: 01-Sep-2019
+# AMR 0.7.1.9070
+Last updated: 02-Sep-2019
### Breaking
* Determination of first isolates now **excludes** all 'unknown' microorganisms at default, i.e. microbial code `"UNKNOWN"`. They can be included with the new parameter `include_unknown`:
@@ -97,6 +97,7 @@
* Speed improvement for `guess_ab_col()` which is now 30 times faster for antibiotic abbreviations
* Improved `filter_ab_class()` to be more reliable and to support 5th generation cephalosporins
* Function `availability()` now uses `portion_R()` instead of `portion_IR()`, to comply with EUCAST insights
+* Functions `age()` and `age_groups()` now have a `na.rm` parameter to remove empty values
#### Other
* Added Prof Dr Casper Albers as doctoral advisor and Dr Bart Meijer, Dr Dennis Souverein and Annick Lenglet as contributors
diff --git a/R/age.R b/R/age.R
index b11ea31d..4a7f35d4 100755
--- a/R/age.R
+++ b/R/age.R
@@ -25,8 +25,9 @@
#' @param x date(s), will be coerced with \code{\link{as.POSIXlt}}
#' @param reference reference date(s) (defaults to today), will be coerced with \code{\link{as.POSIXlt}} and cannot be lower than \code{x}
#' @param exact a logical to indicate whether age calculation should be exact, i.e. with decimals. It divides the number of days of \href{https://en.wikipedia.org/wiki/Year-to-date}{year-to-date} (YTD) of \code{x} by the number of days in a year of \code{reference} (either 365 or 366).
+#' @param na.rm a logical to indicate whether missing values should be removed
#' @return An integer (no decimals) if \code{exact = FALSE}, a double (with decimals) otherwise
-#' @seealso \code{\link{age_groups}} to split age into age groups
+#' @seealso To split ages into groups, use the \code{\link{age_groups}} function.
#' @importFrom dplyr if_else
#' @inheritSection AMR Read more on our website!
#' @export
@@ -39,7 +40,7 @@
#' df$age_exact <- age(df$birth_date, exact = TRUE)
#'
#' df
-age <- function(x, reference = Sys.Date(), exact = FALSE) {
+age <- function(x, reference = Sys.Date(), exact = FALSE, na.rm = FALSE) {
if (length(x) != length(reference)) {
if (length(reference) == 1) {
reference <- rep(reference, length(x))
@@ -79,6 +80,10 @@ age <- function(x, reference = Sys.Date(), exact = FALSE) {
if (any(ages > 120, na.rm = TRUE)) {
warning("Some ages are above 120.")
}
+
+ if (isTRUE(na.rm)) {
+ ages <- ages[!is.na(ages)]
+ }
ages
}
@@ -88,6 +93,7 @@ age <- function(x, reference = Sys.Date(), exact = FALSE) {
#' Split ages into age groups defined by the \code{split} parameter. This allows for easier demographic (antimicrobial resistance) analysis.
#' @param x age, e.g. calculated with \code{\link{age}}
#' @param split_at values to split \code{x} at, defaults to age groups 0-11, 12-24, 25-54, 55-74 and 75+. See Details.
+#' @param na.rm a logical to indicate whether missing values should be removed
#' @details To split ages, the input can be:
#' \itemize{
#' \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+.
@@ -102,7 +108,7 @@ age <- function(x, reference = Sys.Date(), exact = FALSE) {
#' }
#' @keywords age_group age
#' @return Ordered \code{\link{factor}}
-#' @seealso \code{\link{age}} to determine ages based on one or more reference dates
+#' @seealso To determine ages, based on one or more reference dates, use the \code{\link{age}} function.
#' @export
#' @inheritSection AMR Read more on our website!
#' @examples
@@ -135,7 +141,7 @@ age <- function(x, reference = Sys.Date(), exact = FALSE) {
#' group_by(age_group = age_groups(age)) %>%
#' select(age_group, CIP) %>%
#' ggplot_rsi(x = "age_group")
-age_groups <- function(x, split_at = c(12, 25, 55, 75)) {
+age_groups <- function(x, split_at = c(12, 25, 55, 75), na.rm = FALSE) {
if (!is.numeric(x)) {
stop("`x` and must be numeric, not a ", paste0(class(x), collapse = "/"), ".")
}
@@ -174,5 +180,11 @@ age_groups <- function(x, split_at = c(12, 25, 55, 75)) {
# last category
labs[length(labs)] <- paste0(split_at[length(split_at)], "+")
- factor(labs[y], levels = labs, ordered = TRUE)
+ agegroups <- factor(labs[y], levels = labs, ordered = TRUE)
+
+ if (isTRUE(na.rm)) {
+ agegroups <- agegroups[!is.na(agegroups)]
+ }
+
+ agegroups
}
diff --git a/docs/LICENSE-text.html b/docs/LICENSE-text.html
index eef454d1..e9ad1f32 100644
--- a/docs/LICENSE-text.html
+++ b/docs/LICENSE-text.html
@@ -78,7 +78,7 @@
AMR (for R)
- 0.7.1.9069
+ 0.7.1.9070
diff --git a/docs/articles/benchmarks.html b/docs/articles/benchmarks.html
index f8b66330..d845543e 100644
--- a/docs/articles/benchmarks.html
+++ b/docs/articles/benchmarks.html
@@ -40,7 +40,7 @@
AMR (for R)
- 0.7.1.9069
+ 0.7.1.9070
@@ -185,7 +185,7 @@
In the table above, all measurements are shown in milliseconds (thousands of seconds). A value of 5 milliseconds means it can determine 200 input values per second. It case of 100 milliseconds, this is only 10 input values per second. The second input is the only one that has to be looked up thoroughly. All the others are known codes (the first one is a WHONET code) or common laboratory codes, or common full organism names like the last one. Full organism names are always preferred.
To achieve this speed, the as.mo function also takes into account the prevalence of human pathogenic microorganisms. The downside is of course that less prevalent microorganisms will be determined less fast. See this example for the ID of Thermus islandicus (B_THERMS_ISL), a bug probably never found before in humans:
That takes 1.1 times as much time on average. A value of 100 milliseconds means it can only determine ~10 different input values per second. We can conclude that looking up arbitrary codes of less prevalent microorganisms is the worst way to go, in terms of calculation performance. Full names (like Thermus islandicus) are almost fast - these are the most probable input from most data sets.
That takes 1.2 times as much time on average. A value of 100 milliseconds means it can only determine ~10 different input values per second. We can conclude that looking up arbitrary codes of less prevalent microorganisms is the worst way to go, in terms of calculation performance. Full names (like Thermus islandicus) are almost fast - these are the most probable input from most data sets.
In the figure below, we compare Escherichia coli (which is very common) with Prevotella brevis (which is moderately common) and with Thermus islandicus (which is uncommon):
Uncommon microorganisms take a lot more time than common microorganisms. To relieve this pitfall and further improve performance, two important calculations take almost no time at all: repetitive results and already precalculated results.
So going from mo_name("Staphylococcus aureus") to "Staphylococcus aureus" takes 0.0008 seconds - it doesn’t even start calculating if the result would be the same as the expected resulting value. That goes for all helper functions:
So going from mo_name("Staphylococcus aureus") to "Staphylococcus aureus" takes 0.001 seconds - it doesn’t even start calculating if the result would be the same as the expected resulting value. That goes for all helper functions:
Of course, when running mo_phylum("Firmicutes") the function has zero knowledge about the actual microorganism, namely S. aureus. But since the result would be "Firmicutes" too, there is no point in calculating the result. And because this package ‘knows’ all phyla of all known bacteria (according to the Catalogue of Life), it can just return the initial value immediately.
a logical to indicate whether age calculation should be exact, i.e. with decimals. It divides the number of days of year-to-date (YTD) of x by the number of days in a year of reference (either 365 or 366).
+
+
na.rm
+
a logical to indicate whether missing values should be removed
diff --git a/man/age.Rd b/man/age.Rd
index 4c969c82..e68e56f3 100644
--- a/man/age.Rd
+++ b/man/age.Rd
@@ -4,7 +4,7 @@
\alias{age}
\title{Age in years of individuals}
\usage{
-age(x, reference = Sys.Date(), exact = FALSE)
+age(x, reference = Sys.Date(), exact = FALSE, na.rm = FALSE)
}
\arguments{
\item{x}{date(s), will be coerced with \code{\link{as.POSIXlt}}}
@@ -12,6 +12,8 @@ age(x, reference = Sys.Date(), exact = FALSE)
\item{reference}{reference date(s) (defaults to today), will be coerced with \code{\link{as.POSIXlt}} and cannot be lower than \code{x}}
\item{exact}{a logical to indicate whether age calculation should be exact, i.e. with decimals. It divides the number of days of \href{https://en.wikipedia.org/wiki/Year-to-date}{year-to-date} (YTD) of \code{x} by the number of days in a year of \code{reference} (either 365 or 366).}
+
+\item{na.rm}{a logical to indicate whether missing values should be removed}
}
\value{
An integer (no decimals) if \code{exact = FALSE}, a double (with decimals) otherwise
@@ -35,5 +37,5 @@ df$age_exact <- age(df$birth_date, exact = TRUE)
df
}
\seealso{
-\code{\link{age_groups}} to split age into age groups
+To split ages into groups, use the \code{\link{age_groups}} function.
}
diff --git a/man/age_groups.Rd b/man/age_groups.Rd
index d02d5893..e3b6bad2 100644
--- a/man/age_groups.Rd
+++ b/man/age_groups.Rd
@@ -4,12 +4,14 @@
\alias{age_groups}
\title{Split ages into age groups}
\usage{
-age_groups(x, split_at = c(12, 25, 55, 75))
+age_groups(x, split_at = c(12, 25, 55, 75), na.rm = FALSE)
}
\arguments{
\item{x}{age, e.g. calculated with \code{\link{age}}}
\item{split_at}{values to split \code{x} at, defaults to age groups 0-11, 12-24, 25-54, 55-74 and 75+. See Details.}
+
+\item{na.rm}{a logical to indicate whether missing values should be removed}
}
\value{
Ordered \code{\link{factor}}
@@ -68,7 +70,7 @@ example_isolates \%>\%
ggplot_rsi(x = "age_group")
}
\seealso{
-\code{\link{age}} to determine ages based on one or more reference dates
+To determine ages, based on one or more reference dates, use the \code{\link{age}} function.
}
\keyword{age}
\keyword{age_group}
diff --git a/tests/testthat/test-age.R b/tests/testthat/test-age.R
index 7165759c..106b8d3c 100644
--- a/tests/testthat/test-age.R
+++ b/tests/testthat/test-age.R
@@ -40,6 +40,10 @@ test_that("age works", {
expect_warning(age(x = c("1800-01-01", "1805-01-01", "1810-01-01"),
reference = "2019-01-01"))
+
+ expect_equal(length(age(x = c("2019-01-01", NA), na.rm = TRUE)),
+ 1)
+
})
test_that("age_groups works", {
@@ -60,5 +64,8 @@ test_that("age_groups works", {
expect_identical(class(age_groups(ages, "fives")),
c("ordered", "factor"))
+
+ expect_equal(length(age_groups(c(10, 20, 30, NA), na.rm = TRUE)),
+ 3)
})
