score_models: Score Models Using Scores from 'ldatuning' Package

Description Usage Arguments Value

View source: R/ldatuning2.R

Description

Replaces FindTopicsNumber from ldatuning package. Takes topicmodels LDA output models and topic count and returns several scores of the clustering fit.

Usage

1
2
score_models(models, dtm, topics = seq(10, 40, by = 10),
  metrics = c("CaoJuan2009", "Arun2010", "Deveaud2014"), verbose = FALSE)

Arguments

dtm

An object of class "DocumentTermMatrix" with term-frequency weighting or an object coercible to a "simple_triplet_matrix" with integer entries.

topics

Vvector with number of topics to compare different models.

metrics

String or vector of possible metrics: "Griffiths2004", "CaoJuan2009", "Arun2010", "Deveaud2014".

verbose

Logical; Print status updates.

mc.cores

Integer; The number of CPU cores to processes models simultaneously.

Value

Data-frame with one or more metrics. numbers of topics and corresponding values of metric. Can be directly used by FindTopicsNumber_plot to draw a plot.


nateaff/legolda documentation built on Sept. 24, 2017, 4:38 a.m.