success_ratio: Evaluate External Valifity os a Binary Partition

In PPCI: Projection Pursuit for Cluster Identification

Description

Computes the success ratio of a binary partition by comparing the solution with true class labels.

Usage

success_ratio(assigned, labels)

Arguments

assigned	a vector of cluster assignments made by a clustering algorithm.
labels	a vector of true class labels to be compared with assigned.

Value

the success ratio of the cluster assignment solution.

References

Hofmeyr, D. (2016) Clustering by Minimum Cut Hyperplanes. IEEE Transactions on Pattern Analysis and Machine Intelligence.

Examples

## load optidigits dataset
data(optidigits)

## generate a binary partition using minimum normalised cut hyperplane
sol <- ncuth(optidigits$x)

## evaluate using success ratio
success_ratio(sol$cluster, optidigits$c)

PPCI documentation built on March 13, 2020, 3:27 a.m.