Test: quanteda::textmodel-ca

To test the performance of calculation applying on dense dfm matrix versus on sparse dfm matrix (with truncated svd).

require(quanteda, quietly = TRUE, warn.conflicts = FALSE)
## quanteda version 0.9.9.46
## Using 7 of 8 cores for parallel computing
ie2010dfm <- dfm(data_corpus_irishbudget2010, verbose = FALSE)

ie2010dfm_dense <- as.matrix(ie2010dfm)

microbenchmark::microbenchmark(
    ca = ca::ca(ie2010dfm_dense), 
    ca_textmodel = textmodel_ca(ie2010dfm),
    times=10, unit = 'relative')
## Unit: relative
##          expr      min       lq     mean   median       uq      max neval
##            ca 1.842227 1.675758 1.354429 1.758322 1.731018 1.100471    10
##  ca_textmodel 1.000000 1.000000 1.000000 1.000000 1.000000 1.000000    10
data(SOTUCorpus, package = "quantedaData")
SOTUdfm <- dfm(SOTUCorpus)
SOTUdfm_dense <- as.matrix(SOTUdfm)
microbenchmark::microbenchmark(
    ca = ca::ca(SOTUdfm_dense), 
    ca_textmodel = textmodel_ca(SOTUdfm),
    times=10, unit = 'relative')
## Unit: relative
##          expr      min       lq   mean   median       uq      max neval
##            ca 1.902012 1.805813 1.7407 1.742105 1.702073 1.576118    10
##  ca_textmodel 1.000000 1.000000 1.0000 1.000000 1.000000 1.000000    10