def test_signal_rank_warning():
# Throws warning signal rank is larger than possible rank, sets to max-1
ajive = AJIVE(init_signal_ranks=[2, 2], joint_rank=2)
a = np.vstack([[1, 1], [1, 1]])
with pytest.warns(RuntimeWarning):
ajive.fit([a, a])
assert ajive.init_signal_ranks_ == [1, 1]
def test_random_state(data):
# Tests reproducible simulations
dat = data["same_views"]
ajive1 = AJIVE(init_signal_ranks=[2, 2], random_state=0)
ajive1 = ajive1.fit(Xs=dat)
ajive2 = AJIVE(init_signal_ranks=[2, 2], random_state=0)
ajive2 = ajive2.fit(Xs=dat)
assert_allclose(ajive1.wedin_samples_, ajive2.wedin_samples_)
assert_allclose(ajive1.random_sv_samples_, ajive2.random_sv_samples_)
def test_same_indiv(data, init_signal_ranks, individual_ranks, joint_rank):
# Test same indiv input result across varying inputs
dat = data["same_views"]
ajive = AJIVE(
init_signal_ranks=init_signal_ranks,
joint_rank=joint_rank,
individual_ranks=individual_ranks,
)
ajive = ajive.fit(Xs=dat)
Is = ajive.individual_mats_
assert_allclose(Is[0], Is[1])
def test_fit_elbows():
n = 10
elbows = 3
np.random.seed(1)
x = np.random.binomial(1, 0.6, (n**2)).reshape(n, n)
xorth = orth(x)
d = np.zeros(xorth.shape[0])
for i in range(0, len(d), int(len(d) / (elbows + 1))):
d[:i] += 10
X = xorth.T.dot(np.diag(d)).dot(xorth)
Xs = [X, X]
ajive = AJIVE(n_elbows=2)
ajive = ajive.fit(Xs)
assert_equal(ajive.init_signal_ranks_[0], 4)
def test_joint_rank(data):
dat = data["same_views"]
ajive = AJIVE(init_signal_ranks=[2, 2], joint_rank=2)
ajive = ajive.fit(Xs=dat)
assert_equal(ajive.joint_rank, 2)
def test_indiv_rank(data):
dat = data["same_views"]
ajive = AJIVE(init_signal_ranks=[2, 2], individual_ranks=[2, 1])
ajive = ajive.fit(Xs=dat)
assert_equal(ajive.individual_ranks_[0], 2)