P281424/AMR
1
0
Fork 0
mirror of https://github.com/msberends/AMR.git synced 2025-07-21 00:13:21 +02:00
Code Releases Activity

(v2.1.1.9126) implemented WISCA! Also added top_n_microorganisms() and fixed Python wrapper

Browse Source
This commit is contained in:
dr. M.S. (Matthijs) Berends
2025-01-26 23:01:17 +01:00
parent 92c4fc0f94
commit 66833b4f5a
46 changed files with 1786 additions and 1842 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
man/top_n_microorganisms.Rd Normal file
View File

@ -0,0 +1,44 @@
% 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 = "fullname", 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: "mo", "fullname", "status", "kingdom", "phylum", "class", "order", "family", "genus", "species", "subspecies", "rank", "ref", "oxygen_tolerance", "source", "lpsn", "lpsn_parent", "lpsn_renamed_to", "mycobank", "mycobank_parent", "mycobank_renamed_to", "gbif", "gbif_parent", "gbif_renamed_to", "prevalence", or "snomed". If \code{NULL}, the raw values from \code{col_mo} will be used without transformation.}
\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[=antibiograms]{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()}}
}