get_rafs_occurrence_matrix: Get co-occurrence matrix from RAFS results

In RAFS: Robust Aggregative Feature Selection

Get co-occurrence matrix from RAFS results

Description

This function obtains a matrix describing a graph of co-occurrence at each count of clusters (from n_clusters_range) computed over all runs of RAFS.

Usage

get_rafs_occurrence_matrix(
  rafs_results,
  interesting_reps,
  n_clusters_range = 2:15
)

Arguments

rafs_results	RAFS results as obtained from run_rafs
interesting_reps	the interesting representatives to build matrices for (in principle, these need not be representatives but it is more common)
n_clusters_range	range of clusters number to obtain matrices for

Details

If a single result over a cluster number range is desired, the selected matrices can be summed.

Value

A nested list with matrices. The first level is per the RAFS variant (combination of feature dissimilarity function and hclust method). The second level is per the number of clusters. The third (and last) level is the co-occurrence matrix.

Examples

library(MDFS)
mdfs_omp_set_num_threads(1)  # only to pass CRAN checks
data(madelon)
rafs_results <- run_rafs(madelon$data, madelon$decision, 2, c(12345))
rafs_reps_popcnts <- get_rafs_reps_popcnts(rafs_results, 5)
rafs_top_reps <- get_rafs_top_reps_from_popcnts(rafs_reps_popcnts$stig_single, 5)
get_rafs_occurrence_matrix(rafs_results, rafs_top_reps, 5)

RAFS documentation built on April 3, 2025, 5:27 p.m.