def test_pca_score2(self):
# Test that probabilistic PCA correctly separated different datasets
n, p = 100, 3
rng = np.random.RandomState(0)
X = mt.tensor(rng.randn(n, p) * .1) + mt.array([3, 4, 5])
for solver in self.solver_list:
pca = PCA(n_components=2, svd_solver=solver)
pca.fit(X)
ll1 = pca.score(X)
ll2 = pca.score(mt.tensor(rng.randn(n, p) * .2) + mt.array([3, 4, 5]))
self.assertGreater(ll1.fetch(), ll2.fetch())
# Test that it gives different scores if whiten=True
pca = PCA(n_components=2, whiten=True, svd_solver=solver)
pca.fit(X)
ll2 = pca.score(X)
assert ll1.fetch() > ll2.fetch()
def test_pca_score(self):
# Test that probabilistic PCA scoring yields a reasonable score
n, p = 1000, 3
rng = np.random.RandomState(0)
X = mt.tensor(rng.randn(n, p) * .1) + mt.array([3, 4, 5])
for solver in self.solver_list:
pca = PCA(n_components=2, svd_solver=solver)
pca.fit(X)
ll1 = pca.score(X)
h = -0.5 * mt.log(2 * mt.pi * mt.exp(1) * 0.1**2) * p
np.testing.assert_almost_equal((ll1 / h).execute(), 1, 0)
def test_pca_score3(self):
# Check that probabilistic PCA selects the right model
n, p = 200, 3
rng = np.random.RandomState(0)
Xl = mt.tensor(rng.randn(n, p) + rng.randn(n, 1) * np.array([3, 4, 5]) +
np.array([1, 0, 7]))
Xt = mt.tensor(rng.randn(n, p) + rng.randn(n, 1) * np.array([3, 4, 5]) +
np.array([1, 0, 7]))
ll = mt.zeros(p)
for k in range(p):
pca = PCA(n_components=k, svd_solver='full')
pca.fit(Xl)
ll[k] = pca.score(Xt)
assert ll.argmax().execute() == 1