Last active
July 27, 2016 10:05
-
-
Save ypanagis/3ca0a7b92ba4f28561b4dbcef33ae60d to your computer and use it in GitHub Desktop.
Prepare the output of an LDA model for use in LDAVis where corpus is created with the quanteda package
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#' 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 corp Corpus object used to create the document term. | |
#' The corpus should be created with the \tm{quanteda} package | |
#' matrix for the \code{LDA} model. This should have been created 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 quanteda package's | |
#' \code{convert} function, e.g. \code{convert(twdfm, to="topicmodels")}. | |
#' where \code{twdfm} is the document-feature matrix created by quanteda's | |
#' function \code{dfm}. | |
#' The code is adapted from https://gist.github.com/christophergandrud/00e7451c16439421b24a | |
#' | |
#' @seealso \link{LDAvis}. | |
#' @export | |
topicmodels_json_ldavis <- function(fitted, corp, 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(corp$documents$texts)) { | |
temp <- paste(corp$documents$texts[i], collapse = ' ') | |
doc_length <- c(doc_length, stri_count(temp, regex = '\\S+')) | |
} | |
temp_frequency <- inspect(doc_term) | |
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) | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment