Plots per-component standard deviations (or approximate singular values if running PCAFast), percent variance explained per principal component, or cumulative percent variance explained, to help pick an elbow in the graph. This elbow often corresponds well with significant dimensions and is much faster to run than Jackstraw.
ElbowPlot(
object,
ndims = 20,
reduction = "pca",
plot_type = c("stdev", "variance", "cumulative_variance")
)Arguments
- object
Seurat object
- ndims
Number of dimensions to plot (positive integer; capped by stored components)
- reduction
Reduction technique to plot (default is 'pca')
- plot_type
One of
"stdev"(default),"variance"(per-PC % variance), or"cumulative_variance"(running sum of those percentages; equals 100% at the last stored PC whenndimsspans all of them)
Value
A ggplot object
Examples
data("pbmc_small")
ElbowPlot(object = pbmc_small)
#> Warning: The object only has information for 19 dimensions
ElbowPlot(object = pbmc_small, plot_type = "variance")
#> Warning: The object only has information for 19 dimensions
ElbowPlot(object = pbmc_small, plot_type = "cumulative_variance")
#> Warning: The object only has information for 19 dimensions
