def test_spearmanr2(self):
# Test that _spearnmanr2 returns the same result that stats.spearmanr
# would
n, m = tuple(np.random.randint(2, 5, size=2))
mean = np.random.uniform(-1, 1, size=m)
cov = np.random.uniform(0, 1.0 / m, size=(m, m))
cov = (cov + cov.T) / 2
cov.flat[::m + 1] = 1.0
X1 = np.random.multivariate_normal(mean, cov, size=n)
X2 = np.random.multivariate_normal(mean, cov, size=n)
expected = scipy.stats.spearmanr(X1, X2, axis=1)[0][:n, n:]
np.testing.assert_almost_equal(_spearmanr2(X1, X2, axis=1),
expected,
decimal=9)
expected = scipy.stats.spearmanr(X1, X2, axis=0)[0][:m, m:]
np.testing.assert_almost_equal(_spearmanr2(X1, X2, axis=0),
expected,
decimal=9)
def test_spearmanr2(self):
# Test that _spearnmanr2 returns the same result that stats.spearmanr
# would
n, m = tuple(np.random.randint(2, 5, size=2))
mean = np.random.uniform(-1, 1, size=m)
cov = np.random.uniform(0, 1./m, size=(m, m))
cov = (cov + cov.T) / 2
cov.flat[::m + 1] = 1.0
X1 = np.random.multivariate_normal(mean, cov, size=n)
X2 = np.random.multivariate_normal(mean, cov, size=n)
expected = scipy.stats.spearmanr(X1, X2, axis=1)[0][:n, n:]
np.testing.assert_almost_equal(
_spearmanr2(X1, X2, axis=1),
expected,
decimal=9
)
expected = scipy.stats.spearmanr(X1, X2, axis=0)[0][:m, m:]
np.testing.assert_almost_equal(
_spearmanr2(X1, X2, axis=0),
expected,
decimal=9,
)