heatmap_fit: summary plot of globally and pairwise informative variables

In PARSE: Model-Based Clustering with Regularization Methods for High-Dimensional Data

Description

Heatmaps of the data with estimated informative variables and the indicator for pairwise informativeness of each globally informative variables.

Usage

heatmap_fit(output, y, plot_type = 'info.data', eps.diff = 1e-5,
margins = c(5,5), cexRow = 0.5, cexCol = 0.4, lhei = c(0.8,5),
lwid=c(0.8,5), adjCol = c(0.8,0.4), sepwidth=c(0.05,0.05))

Arguments

output	results from parse, apfp, apL1 or nopenalty functions. For the ‘nopenalty’ function, the ‘short.output’ should be FALSE.
y	data.
plot_type	takes two values, 'info.data' or 'info.pair'. 'info.data' is the heatmap of the data with informative variables; 'info.pair' indicates which globally informative variable is pairwise informative for each pair of clusters.
eps.diff	The lower bound of pairwise difference of two mean values. Any value lower than it is treated as 0. The default value is 1e-5.
margins	parameter in 'heatmap.2' function, 2-dimensional numeric vector containing the margins for column and row names, respectively.
cexRow	parameter in 'heatmap.2' function, positive numbers for the row axis labeling.
cexCol	parameter in 'heatmap.2' function, positive numbers for the column axis labeling.
lhei	parameters in 'heatmap.2' function, visual layout of column height.
lwid	parameters in 'heatmap.2' function, visual layout of column weight.
adjCol	parameters in 'heatmap.2' function, justification of column labels (variables names).
sepwidth	parameters in 'heatmap.2' function, 2-dimensional vector giving the width and height of the separator box

Value

heatmap of the data with informative variables or heatmap of whether the globally informative variables are pairwise informative for each pair of clusters or not.

References

Gregory R. Warnes, Ben Bolker, Lodewijk Bonebakker, Robert Gentleman, Wolfgang Huber Andy Liaw, Thomas Lumley, Martin Maechler, Arni Magnusson, Steffen Moeller, Marc Schwartz and Bill Venables (2015). gplots: Various R Programming Tools for Plotting Data. R package version 2.17.0. https://CRAN.R-project.org/package=gplots

See Also

heatmap.2

Examples

y <- rbind(matrix(rnorm(120,0,1),ncol=4),
matrix(rnorm(120,4,1), ncol=4), matrix(rnorm(120,0,1),ncol=4))
output <- parse(K = 3, lambda = 1, y=y)
output$mu.hat.best
heatmap_fit(output, y, cexRow=1)

PARSE documentation built on May 2, 2019, 9:57 a.m.