def test_eval_fitness_min():
"""Test eval_fitness method for a minimization problem"""
problem = OptProb(5, OneMax(), maximize=False)
x = np.array([0, 1, 2, 3, 4])
fitness = problem.eval_fitness(x)
assert fitness == -10
def test_set_state_min():
"""Test set_state method for a minimization problem"""
problem = OptProb(5, OneMax(), maximize=False)
x = np.array([0, 1, 2, 3, 4])
problem.set_state(x)
assert (np.array_equal(problem.get_state(), x)
and problem.get_fitness() == -10)
def test_eval_mate_probs_maximize_false():
"""Test eval_mate_probs method"""
problem = OptProb(5, OneMax(), maximize=False)
pop = np.array([[0, 0, 0, 0, 1],
[1, 0, 1, 0, 1],
[1, 1, 1, 1, 0],
[1, 0, 0, 0, 1],
[0, 0, 0, 0, 0],
[1, 1, 1, 1, 1]])
problem.set_population(pop)
problem.eval_mate_probs()
probs = np.array([0.26667, 0.13333, 0.06667, 0.2, 0.33333, 0])
assert np.allclose(problem.get_mate_probs(), probs, atol=0.00001)
def test_best_child_max():
"""Test best_child method for a maximization problem"""
problem = OptProb(5, OneMax(), maximize=True)
pop = np.array([[0, 0, 0, 0, 1],
[1, 0, 1, 0, 1],
[1, 1, 1, 1, 0],
[1, 0, 0, 0, 1],
[100, 0, 0, 0, 0],
[0, 0, 0, 0, 0],
[1, 1, 1, 1, 1],
[0, 0, 0, 0, -50]])
problem.set_population(pop)
x = problem.best_child()
assert np.array_equal(x, np.array([100, 0, 0, 0, 0]))
def test_eval_mate_probs_all_zero():
"""Test eval_mate_probs method when all states have zero fitness"""
problem = OptProb(5, OneMax(), maximize=True)
pop = np.array([[0, 0, 0, 0, 0],
[0, 0, 0, 0, 0],
[0, 0, 0, 0, 0],
[0, 0, 0, 0, 0],
[0, 0, 0, 0, 0],
[0, 0, 0, 0, 0]])
problem.set_population(pop)
problem.eval_mate_probs()
probs = np.array([0.16667, 0.16667, 0.16667, 0.16667,
0.16667, 0.16667])
assert np.allclose(problem.get_mate_probs(), probs, atol=0.00001)
def test_best_neighbor_min():
"""Test best_neighbor method for a minimization problem"""
problem = OptProb(5, OneMax(), maximize=False)
pop = np.array([[0, 0, 0, 0, 1],
[1, 0, 1, 0, 1],
[1, 1, 1, 1, 0],
[1, 0, 0, 0, 1],
[100, 0, 0, 0, 0],
[0, 0, 0, 0, 0],
[1, 1, 1, 1, 1],
[0, 0, 0, 0, -50]])
problem.neighbors = pop
x = problem.best_neighbor()
assert np.array_equal(x, np.array([0, 0, 0, 0, -50]))
def test_set_population_min():
"""Test set_population method for a minimization problem"""
problem = OptProb(5, OneMax(), maximize=False)
pop = np.array([[0, 0, 0, 0, 1],
[1, 0, 1, 0, 1],
[1, 1, 1, 1, 0],
[1, 0, 0, 0, 1],
[100, 0, 0, 0, 0],
[0, 0, 0, 0, 0],
[1, 1, 1, 1, 1],
[0, 0, 0, 0, -50]])
pop_fit = -1.0*np.array([1, 3, 4, 2, 100, 0, 5, -50])
problem.set_population(pop)
assert (np.array_equal(problem.get_population(), pop)
and np.array_equal(problem.get_pop_fitness(), pop_fit))