plotGridSearchPerplexityDiff: Visualize perplexity differences of a list of celda models

In celda: CEllular Latent Dirichlet Allocation

Description

Visualize perplexity differences of every model in a celdaList, by unique K/L combinations. Line represents centered moving average with windows of length n.

Usage

plotGridSearchPerplexityDiff(x, ...)

## S4 method for signature 'SingleCellExperiment'
plotGridSearchPerplexityDiff(x, altExpName = "featureSubset", sep = 1, n = 10)

## S4 method for signature 'celdaList'
plotGridSearchPerplexityDiff(x, sep = 1, n = 10)

Arguments

x	Can be one of A SingleCellExperiment object returned from celdaGridSearch, recursiveSplitModule, or recursiveSplitCell. Must contain a list named "celda_grid_search" in metadata(x). celdaList object.
...	Ignored. Placeholder to prevent check warning.
altExpName	The name for the altExp slot to use. Default "featureSubset".
sep	Numeric. Breaks in the x axis of the resulting plot.
n	Integer. Width of the rolling window. Default 10.

Value

A ggplot plot object showing perplexity diferences as a function of clustering parameters.

Examples

data(sceCeldaCGGridSearch)
sce <- resamplePerplexity(sceCeldaCGGridSearch)
plotGridSearchPerplexityDiff(sce)
data(celdaCGSim, celdaCGGridSearchRes)
## Run various combinations of parameters with 'celdaGridSearch'
celdaCGGridSearchRes <- resamplePerplexity(
  celdaCGSim$counts,
  celdaCGGridSearchRes)
plotGridSearchPerplexityDiff(celdaCGGridSearchRes)

celda documentation built on Nov. 8, 2020, 8:24 p.m.