def test_absorbing_regressors(cat, cont, interact, weights):
areg = AbsorbingRegressor(cat=cat,
cont=cont,
interactions=interact,
weights=weights)
rank = areg.approx_rank
expected_rank = 0
expected = []
for i, col in enumerate(cat):
expected_rank += pd.Series(cat[col].cat.codes).nunique() - (i > 0)
expected.append(dummy_matrix(cat, precondition=False)[0])
expected_rank += cont.shape[1]
expected.append(csc_matrix(cont))
if interact is not None:
for inter in interact:
interact_mat = inter.sparse
expected_rank += interact_mat.shape[1]
expected.append(interact_mat)
expected = sp.hstack(expected, format="csc")
if weights is not None:
expected = (sp.diags(np.sqrt(weights)).dot(expected)).asformat("csc")
actual = areg.regressors
assert expected.shape == actual.shape
assert_array_equal(expected.indptr, actual.indptr)
assert_array_equal(expected.indices, actual.indices)
assert_allclose(expected.A, actual.A)
assert expected_rank == rank
def test_absorbing_regressors_hash(cat, cont, interact, weights):
areg = AbsorbingRegressor(
cat=cat, cont=cont, interactions=interact, weights=weights
)
# Build hash
hashes = []
for col in cat:
hashes.append((hasher.single(cat[col].cat.codes.to_numpy().data),))
for col in cont:
hashes.append((hasher.single(cont[col].to_numpy().data),))
hashes = sorted(hashes)
if interact is not None:
for inter in interact:
hashes.extend(inter.hash)
if weights is not None:
hashes.append((hasher.single(weights.data),))
hashes = tuple(sorted(hashes))
assert hashes == areg.hash
def test_empty_absorbing_regressor():
areg = AbsorbingRegressor()
assert areg.regressors.shape == (0, 0)
assert areg.hash == tuple()