def test_score_matching_matches_sym():
sigma = 1.
lmbda = 1.
Z = np.random.randn(100, 2)
a_sym = develop_gaussian.fit_sym(Z, sigma, lmbda)
a = gaussian.fit(Z, Z, sigma, lmbda)
assert_allclose(a, a_sym)
def test_score_matching_matches_sym():
sigma = 1.
lmbda = 1.
Z = np.random.randn(100, 2)
a_sym = develop_gaussian.fit_sym(Z, sigma, lmbda)
a = gaussian.fit(Z, Z, sigma, lmbda)
assert_allclose(a, a_sym)
def test_score_matching_objective_matches_sym():
sigma = 1.
lmbda = 1.
Z = np.random.randn(100, 2)
K = gaussian_kernel(Z, sigma=sigma)
J_sym = develop_gaussian.fit_sym(Z, sigma, lmbda, K)
J = gaussian.fit(Z, Z, sigma, lmbda, K)
assert_allclose(J, J_sym)
def test_score_matching_sym_execute_only():
sigma = 1.
lmbda = 1.
Z = np.random.randn(100, 2)
# only run here
a = develop_gaussian.fit_sym(Z, sigma, lmbda)
assert type(a) == np.ndarray
assert len(a.shape) == 1
assert len(a) == len(Z)
def test_fit_sym_matches_full():
sigma = 1.
lmbda = 1.
Z = np.random.randn(100, 2)
a = develop_gaussian.fit_sym(Z, sigma, lmbda)
R = incomplete_cholesky_gaussian(Z, sigma, eta=0.1)["R"]
a_cholesky_cg = develop_gaussian_low_rank.fit_sym(Z, sigma, lmbda, L=R.T)
assert_allclose(a, a_cholesky_cg, atol=3)
def test_fit_sym_matches_full():
sigma = 1.
lmbda = 1.
Z = np.random.randn(100, 2)
a = develop_gaussian.fit_sym(Z, sigma, lmbda)
R = incomplete_cholesky_gaussian(Z, sigma, eta=0.1)["R"]
a_cholesky_cg = develop_gaussian_low_rank.fit_sym(Z, sigma, lmbda, L=R.T)
assert_allclose(a, a_cholesky_cg, atol=3)
def test_score_matching_objective_matches_sym():
sigma = 1.
lmbda = 1.
Z = np.random.randn(100, 2)
K = gaussian_kernel(Z, sigma=sigma)
J_sym = develop_gaussian.fit_sym(Z, sigma, lmbda, K)
J = gaussian.fit(Z, Z, sigma, lmbda, K)
assert_allclose(J, J_sym)
def test_score_matching_sym_execute_only():
sigma = 1.
lmbda = 1.
Z = np.random.randn(100, 2)
# only run here
a = develop_gaussian.fit_sym(Z, sigma, lmbda)
assert type(a) == np.ndarray
assert len(a.shape) == 1
assert len(a) == len(Z)
def test_objective_sym_same_as_from_estimation():
sigma = 1.
lmbda = 1.
Z = np.random.randn(100, 2)
K = gaussian_kernel(Z, sigma=sigma)
a = develop_gaussian.fit_sym(Z, sigma, lmbda, K)
C = develop_gaussian.compute_C_sym(Z, K, sigma)
b = develop_gaussian.compute_b_sym(Z, K, sigma)
J = develop_gaussian.objective_sym(Z, sigma, lmbda, a, K, b, C)
J2 = develop_gaussian.objective_sym(Z, sigma, lmbda, a, K)
assert_almost_equal(J, J2)
def test_objective_sym_optimum():
sigma = 1.
lmbda = 1.
Z = np.random.randn(100, 2)
K = gaussian_kernel(Z, sigma=sigma)
a = develop_gaussian.fit_sym(Z, sigma, lmbda, K)
J_opt = develop_gaussian.objective_sym(Z, sigma, lmbda, a, K)
for _ in range(10):
a_random = np.random.randn(len(Z))
J = develop_gaussian.objective_sym(Z, sigma, lmbda, a_random, K)
assert J >= J_opt
def test_objective_sym_same_as_from_estimation():
sigma = 1.
lmbda = 1.
Z = np.random.randn(100, 2)
K = gaussian_kernel(Z, sigma=sigma)
a = develop_gaussian.fit_sym(Z, sigma, lmbda, K)
C = develop_gaussian.compute_C_sym(Z, K, sigma)
b = develop_gaussian.compute_b_sym(Z, K, sigma)
J = develop_gaussian.objective_sym(Z, sigma, lmbda, a, K, b, C)
J2 = develop_gaussian.objective_sym(Z, sigma, lmbda, a, K)
assert_almost_equal(J, J2)
def test_objective_sym_optimum():
sigma = 1.
lmbda = 1.
Z = np.random.randn(100, 2)
K = gaussian_kernel(Z, sigma=sigma)
a = develop_gaussian.fit_sym(Z, sigma, lmbda, K)
J_opt = develop_gaussian.objective_sym(Z, sigma, lmbda, a, K)
for _ in range(10):
a_random = np.random.randn(len(Z))
J = develop_gaussian.objective_sym(Z, sigma, lmbda, a_random, K)
assert J >= J_opt
def test_objective_sym_matches_full():
sigma = 1.
lmbda = 1.
Z = np.random.randn(100, 2)
K = gaussian_kernel(Z, sigma=sigma)
a_opt = develop_gaussian.fit_sym(Z, sigma, lmbda, K)
J_opt = develop_gaussian.objective_sym(Z, sigma, lmbda, a_opt, K)
L = incomplete_cholesky_gaussian(Z, sigma, eta=0.01)["R"].T
a_opt_chol = develop_gaussian_low_rank.fit_sym(Z, sigma, lmbda, L)
J_opt_chol = develop_gaussian_low_rank.objective_sym(Z, sigma, lmbda, a_opt_chol, L)
assert_almost_equal(J_opt, J_opt_chol, delta=2.)
def test_objective_sym_matches_full():
sigma = 1.
lmbda = 1.
Z = np.random.randn(100, 2)
K = gaussian_kernel(Z, sigma=sigma)
a_opt = develop_gaussian.fit_sym(Z, sigma, lmbda, K)
J_opt = develop_gaussian.objective_sym(Z, sigma, lmbda, a_opt, K)
L = incomplete_cholesky_gaussian(Z, sigma, eta=0.01)["R"].T
a_opt_chol = develop_gaussian_low_rank.fit_sym(Z, sigma, lmbda, L)
J_opt_chol = develop_gaussian_low_rank.objective_sym(
Z, sigma, lmbda, a_opt_chol, L)
assert_almost_equal(J_opt, J_opt_chol, delta=2.)
