ebpmf_wbg2_subject: Empirical Bayes Poisson Matrix Factorization (Background...

In stephenslab/ebpmf.alpha:

Description

Empirical Bayes Poisson Matrix Factorization (Background Model with weights, using subject information)

Usage

ebpmf_wbg2_subject(
  X,
  u,
  K,
  pm_func = list(f = ebpm::ebpm_gamma_mixture, l = ebpm::ebpm_gamma, m =
    ebpm::ebpm_gamma),
  init = NULL,
  pm_control = NULL,
  fix_option = list(m = FALSE, gl = FALSE, ql = FALSE, gf = FALSE, qf = FALSE),
  maxiter = 100,
  tol = 1e-08,
  verbose = FALSE,
  seed = 123
)

Arguments

X	count matrix (dim(X) = c(n, p)).
u	vector encoding subject (length(u) = n; elements need to be from 1,..., length(unique(u))).
pm_func	functions for solving the ebpm subproblem for L and F; It is a list list(l, f, m);
init	Either NULL or list(qg, m, w)
pm_control	control parameters for pm_func function
fix_option	list(m, gl, ql, gf, qf) where each is either TRUE or FALSE
maxiter	maximum number of iterations
tol	stopping tolerance for ELBO
seed	used when init is NULL
k	number of topics

Value

A list containing elements:

m

list of "mean" and "mean_log", "g", "kl"; "mean" and "mean_log" are each a p by D background frequency matrix

qg

list(ql, gl,qf, gf)

ELBO

ELBO objective for this VEB algorithm

Examples

To add

stephenslab/ebpmf.alpha documentation built on Nov. 20, 2021, 11:57 a.m.