def test(net, P, T, vP, vT, filename, epochs, mutation_rate = 0.05, population_size = 50):
logger.info("Running genetic test for: " + filename + ' ' + str(epochs))
print("Number of patients with events: " + str(T[:, 1].sum()))
print("Number of censored patients: " + str((1 - T[:, 1]).sum()))
outputs = net.sim(P)
c_index = get_C_index(T, outputs)
logger.info("C index = " + str(c_index))
try:
net = train_evolutionary(net, (P, T), (vP, vT), epochs, error_function = c_index_error, population_size = population_size, mutation_chance = mutation_rate)
outputs = net.sim(P)
c_index = get_C_index(T, outputs)
logger.info("C index = " + str(c_index))
#net = traingd(net, (P, T), (None, None), epochs * 2, learning_rate = 1, block_size = 0, error_module = cox_error)
except FloatingPointError:
print('Aaawww....')
outputs = net.sim(P)
c_index = get_C_index(T, outputs)
logger.info("C index test = " + str(c_index))
outputs = net.sim(vP)
c_index = get_C_index(vT, outputs)
logger.info("C index vald = " + str(c_index))
if plt:
plot_network_weights(net)
return net
def test(net, P, T, filename, epochs, learning_rate, block_size):
logger.info("Running test for: " + filename + ' ' + str(epochs) + ", rate: " + str(learning_rate) + ", block_size: " + str(block_size))
print("Number of patients with events: " + str(T[:, 1].sum()))
print("Number of censored patients: " + str((1 - T[:, 1]).sum()))
outputs = net.sim(P)
c_index = get_C_index(T, outputs)
logger.info("C index = " + str(c_index))
try:
#net = train_cox(net, (P, T), (None, None), timeslots, epochs, learning_rate = learning_rate)
net = traingd(net, (P, T), (None, None), epochs, learning_rate, block_size, error_module = cox_error)
except FloatingPointError:
print('Aaawww....')
outputs = net.sim(P)
c_index = get_C_index(T, outputs)
logger.info("C index = " + str(c_index))
plot_network_weights(net)
return net
def experiment(net, filename, epochs):
P, T = parse_file(filename, targetcols = [4], inputcols = [0, 1, 2, 3], ignorecols = [], ignorerows = [], normalize = False)
#P = P[:100,:]
#T = T[:100, :]
try:
#net = train_cox(net, (P, T), (None, None), timeslots, epochs = 500, learning_rate = 5)
net = traingd(net, (P, T), (None, None), epochs = epochs, learning_rate = 0.01, block_size = 0)
#net = train_evolutionary(net, (P, T), (None, None), epochs = epochs)
except FloatingPointError:
print('Aaawww....')
outputs = net.sim(P)
plot_network_weights(net)
plt.figure()
plt.title('Scatter plot sum square error\n' + filename)
plt.xlabel('Survival time years')
plt.ylabel('Network output')
try:
plt.scatter(T.flatten(), outputs.flatten(), c = 'g', marker = 's')
plt.plot(T.flatten(), T.flatten(), 'r-')
except:
pass
