johrpan/geposan
1
0
Fork 0
mirror of https://github.com/johrpan/geposan.git synced 2025-10-26 10:47:25 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions

adjacency: Use median as estimate

Browse source
This commit is contained in:
Elias Projahn 2022-01-09 21:27:30 +01:00
parent 32776469bf
commit 23bb499d3a
4 changed files with 4 additions and 50 deletions
Download patch file Download diff file Expand all files Collapse all files

1
NAMESPACE
View file

@ -12,7 +12,6 @@ export(analyze)
export(clustering) export(clustering)
export(compare) export(compare)
export(correlation) export(correlation)
export(densest)
export(method) export(method)
export(neural) export(neural)
export(optimal_weights) export(optimal_weights)

28
R/adjacency.R
View file

@ -1,31 +1,7 @@
#' Find the densest value in the data.
#'
#' This function assumes that data represents a continuous variable and finds
#' a single value with the highest estimated density. This can be used to
#' estimate the mode of the data. If there is only one value that value is
#' returned. If multiple density maxima with the same density exist, their mean
#' is returned.
#'
#' @param data The input data.
#'
#' @return The densest value of data.
#'
#' @export
densest <- function(data) {
as.numeric(if (length(data) <= 0) {
NULL
} else if (length(data) == 1) {
data
} else {
density <- stats::density(data)
mean(density$x[density$y == max(density$y)])
})
}
#' Score genes based on their proximity to the reference genes. #' Score genes based on their proximity to the reference genes.
#' #'
#' @param estimate A function that will be used to summarize the distance #' @param estimate A function that will be used to summarize the distance
#' values for each gene. See [densest()] for the default implementation. #' values for each gene. By default, [median()] is used.
#' @param combination A function that will be used to combine the different #' @param combination A function that will be used to combine the different
#' distances to the reference genes. By default [min()] is used. That means #' distances to the reference genes. By default [min()] is used. That means
#' the distance to the nearest reference gene will be scored. #' the distance to the nearest reference gene will be scored.
@ -33,7 +9,7 @@ densest <- function(data) {
#' @return An object of class `geposan_method`. #' @return An object of class `geposan_method`.
#' #'
#' @export #' @export
adjacency <- function(estimate = densest, combination = min) { adjacency <- function(estimate = stats::median, combination = min) {
method( method(
id = "adjacency", id = "adjacency",
name = "Adjacency", name = "Adjacency",

4
man/adjacency.Rd
View file

@ -4,11 +4,11 @@
\alias{adjacency} \alias{adjacency}
\title{Score genes based on their proximity to the reference genes.} \title{Score genes based on their proximity to the reference genes.}
\usage{ \usage{
adjacency(estimate = densest, combination = min) adjacency(estimate = stats::median, combination = min)
} }
\arguments{ \arguments{
\item{estimate}{A function that will be used to summarize the distance \item{estimate}{A function that will be used to summarize the distance
values for each gene. See \code{\link[=densest]{densest()}} for the default implementation.} values for each gene. By default, \code{\link[=median]{median()}} is used.}
\item{combination}{A function that will be used to combine the different \item{combination}{A function that will be used to combine the different
distances to the reference genes. By default \code{\link[=min]{min()}} is used. That means distances to the reference genes. By default \code{\link[=min]{min()}} is used. That means

21
man/densest.Rd
View file

@ -1,21 +0,0 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/adjacency.R
\name{densest}
\alias{densest}
\title{Find the densest value in the data.}
\usage{
densest(data)
}
\arguments{
\item{data}{The input data.}
}
\value{
The densest value of data.
}
\description{
This function assumes that data represents a continuous variable and finds
a single value with the highest estimated density. This can be used to
estimate the mode of the data. If there is only one value that value is
returned. If multiple density maxima with the same density exist, their mean
is returned.
}