def test_inverse_transform(orig_label, ord_label, expected_reverted,
bad_ord_label, use_fit_transform, client):
n_workers = len(client.has_what())
orig_label = dask_cudf.from_cudf(orig_label, npartitions=n_workers)
ord_label = dask_cudf.from_cudf(ord_label, npartitions=n_workers)
expected_reverted = dask_cudf.from_cudf(expected_reverted,
npartitions=n_workers)
bad_ord_label = dask_cudf.from_cudf(bad_ord_label, npartitions=n_workers)
# prepare LabelEncoder
le = LabelEncoder()
if use_fit_transform:
le.fit_transform(orig_label)
else:
le.fit(orig_label)
assert (le._fitted is True)
# test if inverse_transform is correct
reverted = le.inverse_transform(ord_label)
reverted = reverted.compute().reset_index(drop=True)
expected_reverted = expected_reverted.compute()
assert (len(reverted) == len(expected_reverted))
assert (len(reverted) == len(reverted[reverted == expected_reverted]))
# test if correctly raies ValueError
with pytest.raises(ValueError, match='y contains previously unseen label'):
le.inverse_transform(bad_ord_label).compute()
def test_empty_input(empty, ord_label, client):
# prepare LabelEncoder
n_workers = len(client.has_what())
empty = dask_cudf.from_cudf(empty, npartitions=n_workers)
ord_label = dask_cudf.from_cudf(ord_label, npartitions=n_workers)
le = LabelEncoder()
le.fit(empty)
assert (le._fitted is True)
# test if correctly raies ValueError
with pytest.raises(ValueError, match='y contains previously unseen label'):
le.inverse_transform(ord_label).compute()
# check fit_transform()
le = LabelEncoder()
transformed = le.fit_transform(empty).compute()
assert (le._fitted is True)
assert (len(transformed) == 0)