ConsensusStatsAndPlots: The ConsensusStatsAndPlots function

In mpru/ConsensusClustering: An R Package for Consensus Clustering

Description

Calculates cluster consensus and item consensus (with their plots), and intra and inter cluster consensus summary.

Usage

ConsensusStatsAndPlots(results, plots = TRUE, plotSave = c("no", "pdf",
  "bmp", "png", "ps"), pathOutput = "")

Arguments

results	output from consensusClustering function.
plots	logical indicating whether the plots should be produced. Plots are produced if the results have been produced for more than a single value of K (length(K) > 1).
plotSave	character string indicating the format the plot to be saved in a file. Default is "no", the plot is not saved, but printed to the screen.
pathOutput	directory for saving plots if plotSave == TRUE, defaults to current working directory.

Details

The Cluster Consensus Plot highlights the mean pairwise consensus values between a cluster's members for each k. The color scheme follows all previous graphs and sample are stacked bars grouped by K value on the horizontal x-axis. High values show that the clusters hold high stability and likewise low values highlights a clusters instability. In the Item Consensus Plots, each stacked bar is a sample. Item-consensus values are indicated by the heights of the colored portion of the bars (using the tracking color scheme). This plot provides a view of item-consensus across all other clusters at a given k. As Wilkerman (2010) explains, with this plot it is possible to see if a sample is a very "pure" member of a cluster or if it shares high consensus to multiple clusters (large rectangles in a column of multiple colors), suggesting that it is an unstable member.

Value

A list with the following elements:

• clusterConsensus: average consensus index between all pairs of items belonging to the same cluster, for each K.

• itemConsensus: average consensus index between item i and all the (other) items in cluster cl, for all i and cl, for each K.

• intraInterCons: matrix with intra consensus statistic (the mean of all cluster consensus for each K) and inter consensus statistic (mean of all item consensus between an item and all clusters to which the item does not belong, for each K).

Examples

mat <- matrix(rnorm(10*6), 10, 6)
result <- consensusClustering(mat, nIters = 5, consensusStatsPlots = FALSE)
ConsensusStatsAndPlots(result)

mpru/ConsensusClustering documentation built on May 9, 2019, 5:54 a.m.