def test_calc_same_diff_likelihood_ratio():
np.random.seed(1234)
n_k = 100
K = 7
dim = 10
data_dictionary = generate_data(n_k, K, dim)
X_train = data_dictionary['data'][:500]
Y = data_dictionary['labels'][:500]
model = plda.Model(X_train, Y)
X_infer_category_1 = data_dictionary['data'][500:600]
X_infer_category_1 = model.transform(X_infer_category_1, 'D', 'U_model')
X_infer_category_2 = data_dictionary['data'][600:]
X_infer_category_2 = model.transform(X_infer_category_2, 'D', 'U_model')
similarity_1v2 = model.calc_same_diff_likelihood_ratio(X_infer_category_1, X_infer_category_2)
similarity_2v2 = model.calc_same_diff_likelihood_ratio(
X_infer_category_2[:50],
X_infer_category_2[50:]
)
assert_almost_equal(similarity_1v2, -46868.44557534719)
assert_almost_equal(similarity_2v2, 29.917954937414834)
def data_dictionary():
np.random.seed(1234)
n_k = 1000
K = 5
dim = 10
return generate_data(n_k, K, dim)
def test_calc_logp_mariginal_likelihood():
np.random.seed(1234)
n_k = 100
K = 5
dim = 10
data_dictionary = generate_data(n_k, K, dim)
X = data_dictionary['data']
Y = data_dictionary['labels']
model = plda.Model(X, Y)
prior_mean = model.prior_params['mean']
prior_cov_diag = model.prior_params['cov_diag']
logpdf = gaussian(prior_mean, np.diag(prior_cov_diag + 1)).logpdf
data = np.random.random((n_k, prior_mean.shape[-1]))
expected_logps = logpdf(data)
actual_logps = model.calc_logp_marginal_likelihood(data[:, None])
assert_allclose(actual_logps, expected_logps)
def data_dict():
np.random.seed(1234)
return generate_data(n_k=1000, K=10, dimensionality=50)
def truth_dict():
np.random.seed(1234)
return generate_data(n_k=500, K=2000, dimensionality=5)