lda_fgs_lppv_R: Log Posterior Predictive Value based on the Full Gibbs...

In clintpgeorge/ldamcmc: Markov chain Monte Carlo Algorithms for the Latent Dirichlet Allocation Model

Description

Computation is based on Zhe Chen (2015)'s method

Usage

lda_fgs_lppv_R(K, V, alpha, eta, did, wid, doc.N, max.iter = 5 * 10^3,
  burn.in = 10^3, spacing = 1)

Arguments

K	Number of topics in the corpus
V	Vocabulary size
alpha	Hyperparameter value for θ matrix
eta	Smoothing parameter for the β matrix
did	Document ids of every word instance in each corpus document (1 X total.N vector). We assume vocabulary id starts with 1
wid	Vocabulary ids of every word instance in each corpus document (1 X total.N vector). We assume vocabulary id starts with 1
doc.N	Documents' word counts
max.iter	Maximum number of Gibbs iterations to be performed
burn.in	Burn-in-period for the Gibbs sampler
spacing	Spacing between the stored samples (to reduce correlation)

Value

Log Posterior Predictive Value

See Also

Other posterior predictive check (PPC) options: lda_acgs_lppv_R, lda_fgs_lppv

clintpgeorge/ldamcmc documentation built on Feb. 22, 2020, 12:39 p.m.