Speed-up tests of pipeline combinations using subsample
with random_state
#538
Labels
enhancement
Feature improvement or request
priority
Needs to be fixed rapidly
test-suite
Issue related to testing
Those currently take a while because they use the full sample, and (very rarely) randomly fail because of
DirectionalBias
: could use anotherfit_func
than the sum of sinusoids to avoid this.The text was updated successfully, but these errors were encountered: