def test_probabilistic_pca_1():
"""test that probabilistic PCA yields a readonable score
"""
n, p = 1000, 3
X = randn(n, p)*.1 + np.array([3, 4, 5])
ppca = ProbabilisticPCA(n_comp=2)
ppca.fit(X)
ll1 = ppca.score(X)
h = 0.5 * np.log(2 * np.pi * np.exp(1) / 0.1**2) * p
np.testing.assert_almost_equal(ll1.mean()/h, 1, 0)
def test_probabilistic_pca_2():
"""test that probabilistic PCA correctly separated different datasets
"""
n, p = 100, 3
X = randn(n, p)*.1 + np.array([3, 4, 5])
ppca = ProbabilisticPCA(n_comp=2)
ppca.fit(X)
ll1 = ppca.score(X)
ll2 = ppca.score(randn(n, p)*.2 + np.array([3, 4, 5]))
assert_true(ll1.mean() > ll2.mean())
def test_probabilistic_pca_4():
"""Check that ppca select the right model
"""
n, p = 200, 3
Xl = randn(n, p) + randn(n, 1)*np.array([3, 4, 5]) + np.array([1, 0, 7])
Xt = randn(n, p) + randn(n, 1)*np.array([3, 4, 5]) + np.array([1, 0, 7])
ll = np.zeros(p)
for k in range(p):
ppca = ProbabilisticPCA(n_comp=k)
ppca.fit(Xl)
ll[k] = ppca.score(Xt).mean()
assert_true(ll.argmax() == 1)
def test_probabilistic_pca_3():
"""The homoscedastic model should work slightly worth
than the heteroscedastic one in over-fitting condition
"""
n, p = 100, 3
X = randn(n, p)*.1 + np.array([3, 4, 5])
ppca = ProbabilisticPCA(n_comp=2)
ppca.fit(X)
ll1 = ppca.score(X)
ppca.fit(X, False)
ll2 = ppca.score(X)
assert_true(ll1.mean() < ll2.mean())
