my_searchK: Find the appropriate number of topics for stm

In pachterlab/museumst: Museum of Spatial Transcriptomics

Find the appropriate number of topics for stm

Description

This function is just like stm's searchK, but it uses tidyverse and allows a formula for prevalence. Adapted from Julia Silge's blog.

Usage

my_searchK(documents, K, prevalence = ~1, seed1 = 19, ...)

Arguments

documents	Quanteda dfm object.
K	Numeric vector of numbers of topics to try.
prevalence	Formula of topic prevalence.
seed1	Random seed to use.
...	Other arguments to pass to stm::stm.

Value

A tibble with the metrics output by searchK, plus a column for the fitted model for each value of K tried.

pachterlab/museumst documentation built on March 10, 2024, 4:21 p.m.