crossval: Cross-validate a fitted textmodel
In quanteda/quanteda.classifiers: Models for supervised text classification

crossval

R Documentation

Cross-validate a fitted textmodel

Description

Cross-validate a fitted textmodel using k-fold cross-validation.

Usage

crossval(x, k = 5, by_class = FALSE, verbose = FALSE)

Arguments

`x`	a fitted textmodel
`k`	number of folds
`by_class`	logical; if `TRUE`, estimate performance score separately for each class, otherwise average across classes
`verbose`	logical; if `TRUE`, output results to the console

Examples

library("quanteda")
library("quanteda.textmodels")
dfmat <- tokens(data_corpus_moviereviews) |>
  dfm()
tmod <- textmodel_nb(dfmat, y = data_corpus_moviereviews$sentiment)
crossval(tmod, k = 5, by_class = TRUE)
crossval(tmod, k = 5, by_class = FALSE)
crossval(tmod, k = 5, by_class = FALSE, verbose = TRUE)

quanteda/quanteda.classifiers documentation built on Oct. 20, 2023, 6:53 a.m.