def test_derivate_large(self):
classes = ['a', 'b', 'c']
y = 'b'
x = random.randn(8, 3, 10) * 5 + 3
state_machine = DefaultStateMachine(classes)
parameters = Hacrf._initialize_parameters(state_machine, x.shape[2])
parameters = random.randn(*parameters.shape) * 10 - 2
test_model = _Model(state_machine, x, y)
print(test_model._lattice)
expected_dll = np.zeros(parameters.shape)
# Finite difference gradient approximation
delta = 10.0**-7
S, D = expected_dll.shape
for s in range(S):
for d in range(D):
dg = np.zeros(parameters.shape)
dg[s, d] = delta
y0, _ = test_model.forward_backward(parameters)
y1, _ = test_model.forward_backward(parameters + dg)
print(s, d, y0, y1)
expected_dll[s, d] = (y1 - y0) / delta
actual_ll, actual_dll = test_model.forward_backward(parameters)
print(expected_dll)
print(actual_dll)
self.assertEqual((np.isnan(actual_dll)).any(), False)
assert_array_almost_equal(actual_dll, expected_dll, decimal=TEST_PRECISION)
def test_derivate_large():
classes = ['a', 'b', 'c']
y = 'b'
x = random.randn(20, 3, 10) * 5 + 3
state_machine, states_to_classes = Hacrf._default_state_machine(classes)
parameters = Hacrf._initialize_parameters(state_machine, x.shape[2])
parameters = random.randn(*parameters.shape) * 10 - 2
test_model = _Model(state_machine, states_to_classes, x, y)
expected_dll = np.zeros(parameters.shape)
# Finite difference gradient approximation
delta = 10.0**-7
S, D = expected_dll.shape
for s in xrange(S):
for d in xrange(D):
dg = np.zeros(parameters.shape)
dg[s, d] = delta
y0, _ = test_model.forward_backward(parameters)
y1, _ = test_model.forward_backward(parameters + dg)
expected_dll[s, d] = (y1 - y0) / delta
actual_ll, actual_dll = test_model.forward_backward(parameters)
print(abs(actual_dll) - abs(expected_dll)).sum()
assert_array_almost_equal(actual_dll, expected_dll, decimal=4)
def test_derivate_large():
classes = ['a', 'b', 'c']
y = 'b'
x = random.randn(20, 3, 10) * 5 + 3
state_machine, states_to_classes = Hacrf._default_state_machine(classes)
parameters = Hacrf._initialize_parameters(state_machine, x.shape[2])
parameters = random.randn(*parameters.shape) * 10 - 2
test_model = _Model(state_machine, states_to_classes, x, y)
expected_dll = np.zeros(parameters.shape)
# Finite difference gradient approximation
delta = 10.0**-7
S, D = expected_dll.shape
for s in xrange(S):
for d in xrange(D):
dg = np.zeros(parameters.shape)
dg[s, d] = delta
y0, _ = test_model.forward_backward(parameters)
y1, _ = test_model.forward_backward(parameters + dg)
expected_dll[s, d] = (y1 - y0) / delta
actual_ll, actual_dll = test_model.forward_backward(parameters)
print (abs(actual_dll) - abs(expected_dll)).sum()
assert_array_almost_equal(actual_dll, expected_dll, decimal=4)
def test_derivate_large(self):
classes = ['a', 'b', 'c']
y = 'b'
x = random.randn(8, 3, 10) * 5 + 3
state_machine = DefaultStateMachine(classes)
parameters = Hacrf._initialize_parameters(state_machine, x.shape[2])
parameters = random.randn(*parameters.shape) * 10 - 2
test_model = _AdjacentModel(state_machine, x, y)
expected_dll = np.zeros(parameters.shape)
# Finite difference gradient approximation
delta = 10.0**-7
S, D = expected_dll.shape
for s in range(S):
for d in range(D):
dg = np.zeros(parameters.shape)
dg[s, d] = delta
y0, _ = test_model.forward_backward(parameters)
y1, _ = test_model.forward_backward(parameters + dg)
print(s, d, y0, y1)
expected_dll[s, d] = (y1 - y0) / delta
actual_ll, actual_dll = test_model.forward_backward(parameters)
print(expected_dll)
print(actual_dll)
self.assertEqual((np.isnan(actual_dll)).any(), False)
assert_array_almost_equal(actual_dll,
expected_dll,
decimal=TEST_PRECISION)
def test_initialize_parameters(self):
start_states = [0]
transitions = [(0, 0, (1, 1)),
(0, 1, (0, 1)),
(0, 0, (1, 0))]
states_to_classes = {0: 'a'}
state_machine = GeneralStateMachine(start_states=start_states,
transitions=transitions,
states_to_classes=states_to_classes)
n_features = 3
actual_parameters = Hacrf._initialize_parameters(state_machine, n_features)
expected_parameter_shape = (5, 3)
self.assertEqual(actual_parameters.shape, expected_parameter_shape)
def test_initialize_parameters(self):
start_states = [0]
transitions = [(0, 0, (1, 1)), (0, 1, (0, 1)), (0, 0, (1, 0))]
states_to_classes = {0: 'a'}
state_machine = GeneralStateMachine(
start_states=start_states,
transitions=transitions,
states_to_classes=states_to_classes)
n_features = 3
actual_parameters = Hacrf._initialize_parameters(
state_machine, n_features)
expected_parameter_shape = (5, 3)
self.assertEqual(actual_parameters.shape, expected_parameter_shape)
