relations (version 0.3-3)

choice: Relation-Based Choices

Description

Choose objects based on an ensemble of relations between these.

Usage

relation_choice(x, method = "symdiff", control = list(), ...)

Arguments

x

an ensemble of endorelations.

method

a character string specifying one of the built-in methods, or a function to be taken as a user-defined method. See Details for available built-in methods.

control

a list of control parameters. See Details.

...

a list of control parameters (overruling those specified in control).

Value

• A set with the chosen objects, or a list of such sets.

Details

A social choice function is a rule for choosing from a set $D$ of objects, i.e., selecting suitable subsets of $D$. Voting rules used in elections are the most prominent example of such functions, which typically aggregate individual preferences (e.g., of voters).

Choice method "symdiff" (currently the only one available) chooses a given number $k$ of objects (winners) by determining a relation $R$ which minimizes $\sum_b d(R_b, R)$ over all relations for which winners are always strictly preferred to losers, without any further constraints on the relations between pairs of winners or pairs of losers, where $d$ is symmetric difference dissimilarity and the $R_b$ are crisp endorelations. (Note that this is different from computing consensus preference relations.)

Available control options include: [object Object],[object Object]

Examples

data("SVM_Benchmarking_Classification")
## Determine the three best classification learners in the above sense.
relation_choice(SVM_Benchmarking_Classification, k = 3)