def test_server_conditional_gof(N, V, C, M):
set_random_seed(make_seed(N, V, C, M, 1))
model = generate_fake_model(N, V, C, M)
config = TINY_CONFIG.copy()
config['model_num_clusters'] = M
model['config'] = config
server = TreeCatServer(model)
validate_gof(N, V, C, M, server, conditional=True)
def test_ensemble_latent_perplexity(N, V, C, M):
set_random_seed(make_seed(N, V, C, M))
ensemble = generate_fake_ensemble(N, V, C, M)
server = EnsembleServer(ensemble)
perplexity = server.latent_perplexity()
print(perplexity)
assert perplexity.shape == (V, )
assert np.all(1 <= perplexity)
assert np.all(perplexity <= M)
def test_ensemble_latent_correlation(N, V, C, M):
set_random_seed(make_seed(N, V, C, M))
ensemble = generate_fake_ensemble(N, V, C, M)
server = EnsembleServer(ensemble)
correlation = server.latent_correlation()
print(correlation)
assert np.all(0 <= correlation)
assert np.all(correlation <= 1)
assert np.allclose(correlation, correlation.T)
for v in range(V):
assert correlation[v, :].argmax() == v
assert correlation[:, v].argmax() == v
def test_latent_perplexity(N, V, C, M):
set_random_seed(make_seed(N, V, C, M))
model = generate_fake_model(N, V, C, M)
config = TINY_CONFIG.copy()
config['model_num_clusters'] = M
model['config'] = config
server = TreeCatServer(model)
perplexity = server.latent_perplexity()
print(perplexity)
assert perplexity.shape == (V, )
assert np.all(1 <= perplexity)
assert np.all(perplexity <= M)
def test_latent_correlation(N, V, C, M):
set_random_seed(make_seed(N, V, C, M))
model = generate_fake_model(N, V, C, M)
config = TINY_CONFIG.copy()
config['model_num_clusters'] = M
model['config'] = config
server = TreeCatServer(model)
correlation = server.latent_correlation()
print(correlation)
assert np.all(0 <= correlation)
assert np.all(correlation <= 1)
assert np.allclose(correlation, correlation.T)
for v in range(V):
assert correlation[v, :].argmax() == v
assert correlation[:, v].argmax() == v
def test_observed_perplexity(N, V, C, M):
set_random_seed(make_seed(N, V, C, M))
model = generate_fake_model(N, V, C, M)
config = TINY_CONFIG.copy()
config['model_num_clusters'] = M
model['config'] = config
server = TreeCatServer(model)
for count in [1, 2, 3]:
if count > 1 and C > 2:
continue # NotImplementedError.
counts = 1
perplexity = server.observed_perplexity(counts)
print(perplexity)
assert perplexity.shape == (V, )
assert np.all(1 <= perplexity)
assert np.all(perplexity <= count * C)
def test_quantize_from_probs2(size, resolution):
set_random_seed(make_seed(size, resolution))
probs = np.exp(np.random.random(size)).astype(np.float32)
probs2 = probs.reshape((1, size))
quantized = quantize_from_probs2(probs2, resolution)
assert quantized.shape == probs2.shape
assert quantized.dtype == np.int8
assert np.all(quantized.sum(axis=1) == resolution)
# Check that quantized result is closer to target than any other value.
quantized = quantized.reshape((size, ))
target = resolution * probs / probs.sum()
distance = np.abs(quantized - target).sum()
for combo in itertools.combinations(range(size), resolution):
other = np.zeros(size, np.int8)
for i in combo:
other[i] += 1
assert other.sum() == resolution
other_distance = np.abs(other - target).sum()
assert distance <= other_distance