rankMatrix: Create rank matrix

In RobustRankAggreg: Methods for robust rank aggregation

Description

Convert a set of ranked lists into a rank matrix

Usage

  rankMatrix(glist, N = NA, full = FALSE)

Arguments

glist	list of preference lists
N	number of all rankable elements
full	logical showing if the given rankings are complete

Details

The lists are converted to a format that is used by aggregateRanks. If partial rankings are given to the function, all the missing values are subtituted by the maximum rank N, which can be specified manually. This parameter has a very strong influence on the performance of RRA algorithm, therfore it should be reasonably accurate. If the N is different for the gene lists, it can be also given as a vector.

Parameter full is used, when full rankings are given, but the sets of ranked elements do not match perfectly. Then the structurally missing values are substituted with NA-s.

Value

A matrix, with as many columns as input rankings and rows as unique elements in all the rankings combined.

Author(s)

Raivo Kolde [email protected]

Examples

# Make sample input data
glist <- list(sample(letters, 4), sample(letters, 10), sample(letters, 12))

r = rankMatrix(glist)
r = rankMatrix(glist, full = TRUE)

# Use real data
data(cellCycleKO)
r = rankMatrix(cellCycleKO$gl, N = cellCycleKO$N)

Example output

RobustRankAggreg documentation built on May 29, 2017, 3:49 p.m.