Let *clustering* be a label from data of \(N\) observations and suppose
we are given \(M\) such labels. Co-occurrent matrix counts the number of events
where two observations \(X_i\) and \(X_j\) belong to the same category/class.
*PCM* serves as a measure of uncertainty embedded in any algorithms with non-deterministic components.

pcm(partitions)

partitions | partitions can be provided in either (1) an \((M\times N)\) matrix where each row is a clustering for \(N\) objects, or (2) a length-\(M\) list of length-\(N\) clustering labels. |
---|

an \((N\times N)\) matrix, whose elements \((i,j)\) are counts for how many times observations \(i\) and \(j\) belong to the same cluster, ranging from \(0\) to \(M\).

# ------------------------------------------------------------- # PSM with 'iris' dataset + k-means++ # ------------------------------------------------------------- ## PREPARE WITH SUBSET OF DATA data(iris) X = as.matrix(iris[,1:4]) lab = as.integer(as.factor(iris[,5])) ## EMBEDDING WITH PCA X2d = Rdimtools::do.pca(X, ndim=2)$Y ## RUN K-MEANS++ 100 TIMES partitions = list() for (i in 1:100){ partitions[[i]] = kmeanspp(X)$cluster } ## COMPUTE PCM iris.pcm = pcm(partitions) ## VISUALIZATION opar <- par(no.readonly=TRUE) par(mfrow=c(1,2), pty="s") plot(X2d, col=lab, pch=19, main="true label") image(iris.pcm[,150:1], axes=FALSE, main="PCM")