Convert the output of a topicmodels Latent Dirichlet Allocation model to JSON for use with LDAvis

topicmodels_json_ldavis.R

#' Convert the output of a topicmodels Latent Dirichlet Allocation to JSON
#' for use with LDAvis
#'
#' @param fitted Output from a topicmodels \code{LDA} model.
#' @param corpus Corpus object used to create the document term
#' matrix for the \code{LDA} model. This should have been create with
#' the tm package's \code{Corpus} function.
#' @param doc_term The document term matrix used in the \code{LDA}
#' model. This should have been created with the tm package's 
#' \code{DocumentTermMatrix} function.
#'
#' @seealso \link{LDAvis}.
#' @export

topicmodels_json_ldavis <- function(fitted, corpus, doc_term){
    # Required packages
    library(topicmodels)
    library(dplyr)
    library(stringi)
    library(tm)
    library(LDAvis)

    # Find required quantities
    phi <- posterior(fitted)$terms %>% as.matrix
    theta <- posterior(fitted)$topics %>% as.matrix
    vocab <- colnames(phi)
    doc_length <- vector()
    for (i in 1:length(corpus)) {
        temp <- paste(corpus[[i]]$content, collapse = ' ')
        doc_length <- c(doc_length, stri_count(temp, regex = '\\S+'))
    }
    temp_frequency <- as.data.frame(as.matrix(doc_term)) # elegant, silenced solution adapted from http://stackoverflow.com/a/18749888/5514568
    freq_matrix <- data.frame(ST = colnames(temp_frequency),
                              Freq = colSums(temp_frequency))
    rm(temp_frequency)

    # Convert to json
    json_lda <- LDAvis::createJSON(phi = phi, theta = theta,
                            vocab = vocab,
                            doc.length = doc_length,
                            term.frequency = freq_matrix$Freq)

    return(json_lda)
}