Robust Aggregative Feature Selection

---

Documentation for package ‘RAFS’ version 0.2.5

• DESCRIPTION file.
• Package NEWS.

Help Pages

builtin_dist_funs	All built-in feature dissimilarity functions
compute_fs_results	Compute preliminary feature selection results for RAFS
cor_dist	Feature dissimilarity based on Pearson's Correlation (cor)
create_seeded_folds	Create seeded folds
default_dist_funs	Default feature dissimilarity functions
default_fs_fun	Default (example) feature selection function for RAFS
default_hclust_methods	Default hclust methods
get_rafs_all_reps_from_popcnts	Get all representatives from their popcnts
get_rafs_occurrence_matrix	Get co-occurrence matrix from RAFS results
get_rafs_reps_popcnts	Get representatives' popularity counts (popcnts) from RAFS results
get_rafs_rep_tuples_matrix	Get representatives' tuples' co-representation matrix from RAFS results
get_rafs_rep_tuples_popcnts	Get representatives' tuples' popularity counts (popcnts) from RAFS results
get_rafs_tops_popcnts	Get top popularity counts (popcnts) from FS results
get_rafs_top_reps_from_popcnts	Get top (i.e., most common) representatives from their popcnts
get_rafs_top_rep_tuples_from_popcnts	Get top (i.e., most common) representatives's tuples from their popcnts
get_run_id	Generate CV run identifiers
run_rafs	Robust Aggregative Feature Selection (RAFS)
run_rafs_with_fs_results	Robust Aggregative Feature Selection (RAFS) from feature selection results
stig_dist	Symmetric Target Information Gain (STIG) computed directly
stig_from_ig_dist	Symmetric Target Information Gain (STIG) computed from single Information Gains (IGs)
stig_stable_dist	Symmetric Target Information Gain (STIG) computed directly but with pre-computed 1D conditional entropy (aka stable)
vi_dist	Variation of Information (VI)