def test_possible_segfaults_genetic():
# Setting an incorrect value should not be allowed
from ann import geneticnetwork
net = geneticnetwork(2, 0, 1)
X = np.array([[0, 0], [0, 1], [1, 0], [1, 1]], dtype=float)
Y = np.array([[0], [1], [1], [0]], dtype=float)
failed = False
try:
net.learn(0, Y)
except ValueError:
failed = True
assert failed
failed = False
try:
net.learn(X, 0)
except ValueError:
failed = True
assert failed
failed = False
try:
net.learn(0, 0)
except ValueError:
failed = True
assert failed
def get_net(rows, incols, func=ann.geneticnetwork.FITNESS_SURV_KAPLAN_MIN, mingroup=None,
hidden_count=3, popsize=100, generations=200, mutchance=0.15, conchance=0,
crossover=ann.geneticnetwork.CROSSOVER_UNIFORM,
selection=ann.geneticnetwork.SELECTION_TOURNAMENT):
outcount = 2
l = incols + hidden_count + outcount + 1
net = ann.geneticnetwork(incols, hidden_count, outcount)
net.fitness_function = func
if mingroup is None:
mingroup = int(0.25 * rows)
# Be explicit here even though I changed the defaults
net.connection_mutation_chance = conchance
net.activation_mutation_chance = 0
# Some other values
net.crossover_method = crossover
net.selection_method = selection
net.population_size = popsize
net.generations = generations
net.weight_mutation_chance = mutchance
ann.utils.connect_feedforward(net, hidden_act=net.TANH, out_act=net.SOFTMAX)
c = net.connections.reshape((l, l))
c[-outcount:, :(incols + hidden_count)] = 1
net.connections = c.ravel()
return net
def test_possible_segfaults_genetic():
# Setting an incorrect value should not be allowed
from ann import geneticnetwork
net = geneticnetwork(2, 0, 1)
X = np.array([[0, 0], [0, 1], [1, 0], [1, 1]], dtype=float)
Y = np.array([[0], [1], [1], [0]], dtype=float)
failed = False
try:
net.learn(0, Y)
except ValueError:
failed = True
assert failed
failed = False
try:
net.learn(X, 0)
except ValueError:
failed = True
assert failed
failed = False
try:
net.learn(0, 0)
except ValueError:
failed = True
assert failed
def time_learn(rows, cols):
'''Return time elapsed to learn 10000 iterations on data'''
x, y = get_test_data(rows, cols)
net = geneticnetwork(x.shape[1], 8, 1)
connect_feedforward(net)
net.generations=10
# Time it
start = time.time()
net.learn(x, y)
# Final time
elapsed = time.time() - start
return elapsed
def time_learn(rows, cols):
'''Return time elapsed to learn 10000 iterations on data'''
x, y = get_test_data(rows, cols)
net = geneticnetwork(x.shape[1], 8, 1)
connect_feedforward(net)
net.generations = 10
# Time it
start = time.time()
net.learn(x, y)
# Final time
elapsed = time.time() - start
return elapsed
def test_gennetwork():
from ann import geneticnetwork
net = geneticnetwork(2, 4, 1)
xor_in, xor_out = getXOR()
net.generations = 1000
net.crossover_chance = 0.8
net.connection_mutation_chance = 0.2
net.activation_mutation_chance = 0.2
net.crossover_method = net.CROSSOVER_UNIFORM
net.fitness_function = net.FITNESS_MSE
net.selection_method = net.SELECTION_TOURNAMENT
net.learn(xor_in, xor_out)
for val in xor_in:
#print("In:", val, " out:", net.output(val))
if sum(val) != 1:
assert net.output(val) < 0.1, "xor solution doesnt work"
else:
assert net.output(val) > 0.9, "xor solution doesnt work"
def test_gennetwork():
from ann import geneticnetwork
net = geneticnetwork(2, 4, 1)
xor_in, xor_out = getXOR()
net.generations = 1000
net.crossover_chance = 0.8
net.connection_mutation_chance = 0.2
net.activation_mutation_chance = 0.2
net.crossover_method = net.CROSSOVER_UNIFORM
net.fitness_function = net.FITNESS_MSE
net.selection_method = net.SELECTION_TOURNAMENT
net.learn(xor_in, xor_out)
for val in xor_in:
#print("In:", val, " out:", net.output(val))
if sum(val) != 1:
assert net.output(val) < 0.1, "xor solution doesnt work"
else:
assert net.output(val) > 0.9, "xor solution doesnt work"
