def test_gradient_descent():
"""Test gradient_descent function"""
X = np.array([[0, 1, 0, 1], [0, 0, 0, 0], [1, 1, 1, 1], [1, 1, 1, 1],
[0, 0, 1, 1], [1, 0, 0, 0]])
y = np.reshape(np.array([1, 1, 0, 0, 1, 1]), [6, 1])
nodes = [4, 2, 1]
fitness = NetworkWeights(X,
y,
nodes,
activation=identity,
bias=False,
is_classifier=False,
learning_rate=0.1)
problem = ContinuousOpt(10,
fitness,
maximize=False,
min_val=-1,
max_val=1,
step=0.1)
test_weights = np.array([1, 1, 1, 1, 1, 1, 1, 1, 1, 1])
test_fitness = -1 * problem.eval_fitness(test_weights)
best_state, best_fitness, _ = gradient_descent(problem)
assert (len(best_state) == 10 and min(best_state) >= -1
and max(best_state) <= 1 and best_fitness < test_fitness)
def _run_with_gd(self, init_weights, num_nodes, problem):
if init_weights is None:
init_weights = np.random.uniform(-1, 1, num_nodes)
fitted_weights, loss, fitness_curve = gradient_descent(
problem,
max_attempts=self.max_attempts
if self.early_stopping else self.max_iters,
max_iters=self.max_iters,
curve=self.curve,
init_state=init_weights)
return ([] if fitness_curve is None else
fitness_curve), fitted_weights, loss
def test_gradient_descent_iter1():
"""Test gradient_descent function gets the correct answer after a
single iteration"""
X = np.array([[0, 1, 0, 1], [0, 0, 0, 0], [1, 1, 1, 1], [1, 1, 1, 1],
[0, 0, 1, 1], [1, 0, 0, 0]])
y = np.reshape(np.array([1, 1, 0, 0, 1, 1]), [6, 1])
nodes = [4, 2, 1]
fitness = NetworkWeights(X,
y,
nodes,
activation=identity,
bias=False,
is_classifier=False,
learning_rate=0.1)
problem = ContinuousOpt(10,
fitness,
maximize=False,
min_val=-1,
max_val=1,
step=0.1)
init_weights = np.array([1, 1, 1, 1, 1, 1, 1, 1, 1, 1])
best_state, best_fitness, _ = gradient_descent(problem,
max_iters=1,
init_state=init_weights)
x = np.array([-0.7, -0.7, -0.9, -0.9, -0.9, -0.9, -1, -1, -1, -1])
assert (np.allclose(best_state, x, atol=0.001)
and round(best_fitness, 2) == 19.14)