prepare_data: Preparing Data

In RankAggSIgFUR: Polynomially Bounded Rank Aggregation under Kemeny's Axiomatic Approach

Preparing Data

Description

Prepares the given data for rank aggregation functions. The function returns a matrix of input rankings and a vector indicating weights of the ranking for each judge. Useful when scores need to be converted to rankings. Also helpful in reducing the size of the problem for large p, especially when p > n!.

Usage

prepare_data(df, HighertheBetter = 0)

Arguments

df	a n by p matrix or dataframe of scores of n objects given by p judges. Each column corresponds to a different judge.
HighertheBetter	an integer with 1 indicating that the higher values in the input correspond to the better rank. An optional parameter. Default value is 0, i.e., the lower the score the better the rank (e.g., score of 1 is the topmost rank).

Value

A list containing a matrix of input rankings (named input_rkgs) and a weight vector corresponding to weights for each judge (named wt). These two objects are used as inputs to subit_convergence, rap_greedy_alg, fur, and sigfur.

See Also

subit_convergence, rap_greedy_alg, fur, sigfur

Examples

## Five input rankings with five objects 
input_rkgs <- matrix(c(3, 2, 5, 4, 1, 2, 3, 1, 5, 4, 2, 3, 1, 5, 4, 5, 1, 3, 4, 2, 1, 
                       2, 4, 5, 3),byrow = FALSE, ncol = 5)
out = prepare_data(input_rkgs) 
input_rkgs = out$input_rkgs
wt = out$wt

## Five input rankings with five objects
## testing the higher the better 
input_rkgs <- matrix(c(3, 2, 5, 4, 1, 2, 3, 1, 5, 4, 2, 3, 1, 5, 4, 5, 1, 3, 4, 2, 1, 
                       2, 4, 5, 3),byrow = FALSE, ncol = 5)
input_rkgs = input_rkgs*2+input_rkgs #artificially create a score matrix
# Testing the higher the better rank
out = prepare_data(input_rkgs, HighertheBetter = 1) 
input_rkgs = out$input_rkgs
wt = out$wt

RankAggSIgFUR documentation built on July 9, 2023, 7:26 p.m.