def test_all_scalar_output_fuzzy():
"""
Test output for fuzzy factors, i.e. means in [0,1]
"""
L = 3
for model in aux.canonical_loms():
for randiter in range(3):
z = np.random.rand(L)
u = np.random.rand(L)
numba_fct = lupd.get_scalar_output_function_2d(model, fuzzy=True)
numba_out = numba_fct(z, u)
python_out = scalar_output_python_fuzzy(model, z, u)
try:
assert abs(numba_out - python_out) < 1e-12
except:
import pdb
pdb.set_trace()
raise ValueError(
'Fuzzy scalar output function for ' +
model + ' failed.')
def test_all_3D_LOMs():
operators = ['AND', 'NAND', 'OR', 'NOR', 'XOR', 'NXOR']
# operators = ['OR', 'AND']
machines = [
x[0] + '-' + x[1] for x in list(itertools.product(operators, repeat=2))
]
for machine in aux.canonical_loms(): # machines:
N = 50
D = 10
L = 3
Z = np.array(np.random.rand(N, L) > .5, dtype=np.int8)
U = np.array(np.random.rand(D, L) > .5, dtype=np.int8)
V = np.array(np.random.rand(D, L) > .5, dtype=np.int8)
# generate_data_fast is not available for all machines
X = aux.lom_generate_data([2 * Z - 1, 2 * U - 1, 2 * V - 1],
model=machine)
orm = lom.Machine()
data = orm.add_matrix(X, fixed=True)
layer = orm.add_layer(latent_size=L, child=data, model=machine)
layer.z.val = (1 - 2 * layer.invert_factors) * (2 * Z - 1)
layer.u.val = (1 - 2 * layer.invert_factors) * (2 * U - 1)
layer.v.val = (1 - 2 * layer.invert_factors) * (2 * V - 1)
# we initialise with ground truth, hence set lbda large to avoid effectively
# random initialisation
layer.lbda.val = 3.0
orm.infer(burn_in_min=10, fix_lbda_iters=2)
try:
assert np.mean((2 * (layer.output(technique='factor_map') > .5) -
1) == data()) > .98
assert np.mean((2 * (layer.output(technique='factor_mean') > .5) -
1) == data()) > .98
except:
acc = np.mean((2 * (layer.output(technique='factor_mean') > .5) -
1) == data())
print(machine + ' failed with reconstruction accuracy of ' +
str(acc))
# import pdb; pdb.set_trace()
raise ValueError()
def test_all_scalar_output():
"""
Test numba implementations against the simple python implementation
"""
# generate random data
L = 3
for model in aux.canonical_loms():
for randiter in range(10):
z = 2 * np.array(np.random.rand(L) > .5, dtype=np.int8) - 1
u = 2 * np.array(np.random.rand(L) > .5, dtype=np.int8) - 1
numba_fct = lupd.get_scalar_output_function_2d(model, fuzzy=False)
try:
assert numba_fct(z, u) == scalar_output_python(model, z, u)
except:
raise ValueError(
'Scalar output function for ' +
model + ' failed.')
def test_densities():
machines = aux.canonical_loms(level='clans', mode='implemented')
for machine in machines:
d = aux.expected_density(machine, L=3, K=2, f=.5)
N = 200
D = 200
L = 3
Z = np.array(np.random.rand(N, L) > .5, dtype=np.int8)
U = np.array(np.random.rand(D, L) > .5, dtype=np.int8)
X = aux.lom_generate_data_fast([2 * Z - 1, 2 * U - 1], model=machine)
X_train, train_mask = experiments.split_train_test(X, split=.1)
try:
assert (np.abs(np.mean(X == 1) - d)) < 5e-2
except:
print(np.abs(np.mean(X == 1)))
print(d)
print(machine)