topicsModel {topics}R Documentation

Topic modelling

Description

The function to create and train and an LDA model.

Usage

topicsModel(
  dtm,
  num_topics = 20,
  num_top_words = 10,
  num_iterations = 1000,
  seed = 42,
  save_dir,
  load_dir = NULL
)

Arguments

dtm

(R_obj) The document term matrix

num_topics

(integer) The number of topics to be created

num_top_words

(integer) The number of top words to be displayed

num_iterations

(integer) The number of iterations to run the model

seed

(integer) The seed to set for reproducibility

save_dir

(string) The directory to save the model, if NULL, the model will not be saved

load_dir

(string) The directory to load the model from, if NULL, the model will not be loaded

Value

A list of the model, the top terms, the labels, the coherence, and the prevalence

Examples


# Create LDA Topic Model 
save_dir_temp <- tempfile()
dtm <- topicsDtm(
data = dep_wor_data$Depphrase, 
save_dir = save_dir_temp)

model <- topicsModel(
dtm = dtm, # output of topicsDtm()
num_topics = 20,
num_top_words = 10,
num_iterations = 1000,
seed = 42,
save_dir = save_dir_temp)
                   
# Load precomputed LDA Topic Model
model <- topicsModel(
load_dir = save_dir_temp,
seed = 42,
save_dir = save_dir_temp)


[Package topics version 0.21.0 Index]