SnapATAC (version 1.0.0)

runViz: Dimentionality Reduction for Visualization

Description

Wrapper for the implementation of Barnes-Hut t-Distributed Stochastic Neighbor Embedding and FFT-accelerated Interpolation-based t-SNE (FIt-SNE) t-SNE, and UMAP

Usage

runViz(obj, dims, eigs.dims, method, fast_tsne_path, Y.init, seed.use,
  num.cores, tmp.folder, ...)

Arguments

obj

A snap object.

dims

integer; Output dimensionality (default: 2)

eigs.dims

integer vector; principal components used for running tsne or umap

method

character; A character variable indicates what t-sne method to use ("Rtsne", "fast_tsne", "umap").

fast_tsne_path

character; A character variable indicates the path of the excutable FIt-sen located. Required only when method="fast_tsne"

Y.init

matrix; Initial locations of the objs. If NULL, random initialization will be used (default: NULL). Note that when using this, the initial stage with exaggerated perplexity values and a larger momentum term will be skipped.

seed.use

number; Random seeds to use.

num.cores

number; Number of CPU used for computing.

tmp.folder

Directory to store temporary files.

...

Arguments passed to Rtsne, umap or FIt-tsne

Value

Returns a snap obj with the visulization

Examples

# NOT RUN {
data(demo.sp);
demo.sp = runViz(obj=demo.sp, tmp.folder=tempdir(), eigs.dims=1:5, method="Rtsne");

# }