mirror of
https://github.com/msberends/AMR.git
synced 2026-04-02 22:15:54 +02:00
48 lines
2.9 KiB
R
48 lines
2.9 KiB
R
% Generated by roxygen2: do not edit by hand
|
|
% Please edit documentation in R/top_n_microorganisms.R
|
|
\name{top_n_microorganisms}
|
|
\alias{top_n_microorganisms}
|
|
\title{Filter Top \emph{n} Microorganisms}
|
|
\usage{
|
|
top_n_microorganisms(x, n, property = "species", n_for_each = NULL,
|
|
col_mo = NULL, ...)
|
|
}
|
|
\arguments{
|
|
\item{x}{A data frame containing microbial data.}
|
|
|
|
\item{n}{An integer specifying the maximum number of unique values of the \code{property} to include in the output.}
|
|
|
|
\item{property}{A character string indicating the microorganism property to use for filtering. Must be one of the column names of the \link{microorganisms} data set: {.val mo}, {.val fullname}, {.val status}, {.val kingdom}, {.val phylum}, {.val class}, {.val order}, {.val family}, {.val genus}, {.val species}, {.val subspecies}, {.val rank}, {.val ref}, {.val oxygen_tolerance}, {.val source}, {.val lpsn}, {.val lpsn_parent}, {.val lpsn_renamed_to}, {.val mycobank}, {.val mycobank_parent}, {.val mycobank_renamed_to}, {.val gbif}, {.val gbif_parent}, {.val gbif_renamed_to}, {.val prevalence}, or {.val snomed}. If \code{NULL}, the raw values from \code{col_mo} will be used without transformation. When using \code{"species"} (default) or \code{"subpecies"}, the genus will be added to make sure each (sub)species still belongs to the right genus.}
|
|
|
|
\item{n_for_each}{An optional integer specifying the maximum number of rows to retain for each value of the selected property. If \code{NULL}, all rows within the top \emph{n} groups will be included.}
|
|
|
|
\item{col_mo}{A character string indicating the column in \code{x} that contains microorganism names or codes. Defaults to the first column of class \code{\link{mo}}. Values will be coerced using \code{\link[=as.mo]{as.mo()}}.}
|
|
|
|
\item{...}{Additional arguments passed on to \code{\link[=mo_property]{mo_property()}} when \code{property} is not \code{NULL}.}
|
|
}
|
|
\description{
|
|
This function filters a data set to include only the top \emph{n} microorganisms based on a specified property, such as taxonomic family or genus. For example, it can filter a data set to the top 3 species, or to any species in the top 5 genera, or to the top 3 species in each of the top 5 genera.
|
|
}
|
|
\details{
|
|
This function is useful for preprocessing data before creating \link[=antibiogram]{antibiograms} or other analyses that require focused subsets of microbial data. For example, it can filter a data set to only include isolates from the top 10 species.
|
|
}
|
|
\examples{
|
|
# filter to the top 3 species:
|
|
top_n_microorganisms(example_isolates,
|
|
n = 3
|
|
)
|
|
|
|
# filter to any species in the top 5 genera:
|
|
top_n_microorganisms(example_isolates,
|
|
n = 5, property = "genus"
|
|
)
|
|
|
|
# filter to the top 3 species in each of the top 5 genera:
|
|
top_n_microorganisms(example_isolates,
|
|
n = 5, property = "genus", n_for_each = 3
|
|
)
|
|
}
|
|
\seealso{
|
|
\code{\link[=mo_property]{mo_property()}}, \code{\link[=as.mo]{as.mo()}}, \code{\link[=antibiogram]{antibiogram()}}
|
|
}
|