wRI: Weighted Rand Index (wRI)
In haowulab/Wind: Wind: weighted indexes for clustering evaluation

Description Usage Arguments Details Value Author(s) See Also Examples

View source: R/wRI.R

This function computes the weighted Rand index (wRI), which computes the agreement of two partitions (often a gold standard reference and a clustering result) based on a modified Rand index definition to account for cell type hierarchy.

1	wRI(trueclass, cluster, w0 = NULL, w1 = NULL)

`trueclass`	A vector for the true classes of cells. Often from an outside experiement.
`cluster`	A vector for the clustering results.
`w0`	An optional square matrix of dimension JxJ, where J is the number of classes provided by 'trueclass'. The (i,j)-th entry is the score of separating two cells of types i and j in different clusters.
`w1`	An optional square matrix of dimension JxJ, where J is the number of classes provided by 'trueclass'. The(i,j)-th entry is the score for putting two cells of different types in the same cluster.

The w0 and w1 matrics can be specified by user based on based on prior biological knowledge. If not given, they will be estimated using 'createWeights' function.

A vector of numerics for values related to the Weighted Rand Index (wRI), including:

`wRI`	The wRI value.
`NI1`	The index with the positive prediction value interpretation: given two subjects are put in the same cluster, the probability that they truely belong to the same type.
`NI2`	The index with the negative prediction value interpretation: given two subjects are separated in different clusters, the probability they belong to different types.
`p1`	The proportaion of "in-cluster" relationships in the reference, among all pair-wise relationships.
`p0`	The proportaion of "seprated in different cluster" relationships in the reference, among all pair-wise relationships.

Zhijin Wu <zhijin_wu@brown.edu>, Hao Wu <hao.wu@emory.edu>

createWeights, wNMI

data(Zhengmix8eq)
weights = createWeights(Y, trueclass)
methods = names(clusterRes)
allRI = matrix(0, nrow=length(methods), ncol=6)
rownames(allRI) = methods
colnames(allRI) = c("RI", "NI1","NI2","wRI","wNI1","wNI2")
for(i in 1:length(clusterRes)) {
    allRI[i,1:3] = wRI(trueclass, clusterRes[[i]]) [1:3]
    allRI[i,4:6] = wRI(trueclass, clusterRes[[i]], weights$W0, weights$W1)[1:3]
}
barplot(t(allRI[,c(1,4)]), beside=TRUE, ylim=c(0.7,1.05), legend.text=TRUE, xpd=FALSE)