johrpan/geposanui
1
0
Fork 0
mirror of https://github.com/johrpan/geposanui.git synced 2025-10-26 11:17:24 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions

clusteriness: Don't penalize missing values yet

Browse source
This commit is contained in:
Elias Projahn 2021-10-11 09:48:48 +02:00
parent b122f2e240
commit cd63486f0a
1 changed files with 7 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

14
clustering.R
View file

@ -5,12 +5,13 @@ library(data.table)
#' This function will cluster the data using `hclust` and `cutree` (with the #' This function will cluster the data using `hclust` and `cutree` (with the
#' specified height). Every cluster with at least two members qualifies for #' specified height). Every cluster with at least two members qualifies for
#' further analysis. Clusters are then ranked based on their size in relation #' further analysis. Clusters are then ranked based on their size in relation
#' to the total number of possible values (`n`). The return value is a final #' to the number of values. The return value is a final score between zero and
#' score between zero and one. Lower ranking clusters contribute less to this #' one. Lower ranking clusters contribute less to this score.
#' score. clusteriness <- function(data, height = 1000000) {
clusteriness <- function(data, n, height = 1000000) { n <- length(data)
# Return a score of 0.0 if there is just one or no value at all. # Return a score of 0.0 if there is just one or no value at all.
if (length(data) < 2) { if (n < 2) {
return(0.0) return(0.0)
} }
@ -48,7 +49,6 @@ clusteriness <- function(data, n, height = 1000000) {
#' @param gene_ids Genes to include in the computation. #' @param gene_ids Genes to include in the computation.
process_clustering <- function(distances, species_ids, gene_ids) { process_clustering <- function(distances, species_ids, gene_ids) {
results <- data.table(gene = gene_ids) results <- data.table(gene = gene_ids)
species_count <- length(species)
# Prefilter the input data by species. # Prefilter the input data by species.
distances <- distances[species %chin% species_ids] distances <- distances[species %chin% species_ids]
@ -58,7 +58,7 @@ process_clustering <- function(distances, species_ids, gene_ids) {
#' Perform the cluster analysis for one gene. #' Perform the cluster analysis for one gene.
compute <- function(gene_id) { compute <- function(gene_id) {
clusteriness(distances[gene_id, distance], species_count) clusteriness(distances[gene_id, distance])
} }
results[, clusteriness := compute(gene), by = 1:nrow(results)] results[, clusteriness := compute(gene), by = 1:nrow(results)]