def cross_validation_test():
glogger.setLoggingLevel(glogger.nothing)
filename = "/home/gibson/jonask/Dropbox/Ann-Survival-Phd/Two_thirds_of_SA_1889_dataset.txt"
#try:
# columns = input("Which columns to include? (Do NOT forget trailing comma if only one column is used, e.g. '3,'\nAvailable columns are: 2, -4, -3, -2, -1. Just press ENTER for all columns.\n")
#except SyntaxError:
columns = (2, -4, -3, -2, -1)
print('\nIncluding columns: ' + str(columns))
P, T = parse_file(filename, targetcols = [4, 5], inputcols = columns, ignorerows = [0], normalize = True)
#remove tail censored
P, T = copy_without_tailcensored(P, T)
#try:
# comsize = input("Number of networks to cross-validate [10]: ")
#except SyntaxError:
comsize = 10
print('Number of networks to cross-validate: ' + str(comsize))
#try:
# netsize = input('Number of hidden nodes [3]: ')
#except SyntaxError as e:
if len(sys.argv) < 2:
netsize = 3
else:
netsize = sys.argv[1]
print("Number of hidden nodes: " + str(netsize))
#try:
# pop_size = input('Population size [50]: ')
#except SyntaxError as e:
pop_size = 50
print("Population size: " + str(pop_size))
#try:
# mutation_rate = input('Please input a mutation rate (0.25): ')
#except SyntaxError as e:
mutation_rate = 0.25
print("Mutation rate: " + str(mutation_rate))
#try:
# epochs = input("Number of generations (200): ")
#except SyntaxError as e:
epochs = 200
print("Epochs: " + str(epochs))
com = build_feedforward_committee(comsize, len(P[0]), netsize, 1, output_function = 'linear')
#1 is the column in the target array which holds teh binary censoring information
test_errors, vald_errors = train_committee(com, train_evolutionary, P, T, 1, epochs, error_function = c_index_error, population_size = pop_size, mutation_chance = mutation_rate)
print('\nTest Errors, Validation Errors:')
for terr, verr in zip(test_errors.values(), vald_errors.values()):
print(str(terr) + ", " + str(verr))
print('\nTest average, Validation average:')
print(str(sum(test_errors.values()) / len(test_errors.values())) + ', ' + str(sum(vald_errors.values()) / len(vald_errors.values())))
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
if __name__ == "__main__":
logging.basicConfig(level = logging.INFO)
glogger.setLoggingLevel(glogger.info)
p = 4 #number of input covariates
#net = load_network('/home/gibson/jonask/Projects/aNeuralN/ANNs/PERCEPTRON.ann')
net = build_feedforward(p, 10, 1, output_function = "linear")
lineartarget_nn = '/home/gibson/jonask/Dropbox/Ann-Survival-Phd/fake_data_set/lineartarget_no_noise.txt'
nonlineartarget_nn = '/home/gibson/jonask/Dropbox/Ann-Survival-Phd/fake_data_set/nonlineartarget_no_noise.txt'
lineartarget_wn = '/home/gibson/jonask/Dropbox/Ann-Survival-Phd/fake_data_set/lineartarget_with_noise.txt'
nonlineartarget_wn = '/home/gibson/jonask/Dropbox/Ann-Survival-Phd/fake_data_set/nonlineartarget_with_noise.txt'
while True:
experiment(net, nonlineartarget_wn, 500)
plt.show()
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
if __name__ == "__main__":
logging.basicConfig(level = logging.INFO)
glogger.setLoggingLevel(glogger.debug)
filename = "/home/gibson/jonask/Dropbox/Ann-Survival-Phd/Two_thirds_of_SA_1889_dataset.txt"
P, T = parse_file(filename, targetcols = [4, 5], inputcols = [2, -4, -3, -2, -1], ignorerows = [0], normalize = True)
#P, T = parse_file(filename, targetcols = [4, 5], inputcols = [2, -3], ignorerows = [0], normalize = True)
#Remove tail censored
P, T = copy_without_tailcensored(P, T)
#Limit to incourage overtraining!
#rows = sample(range(len(T)), 100)
#P = P[rows]
#T = T[rows]
p = len(P[0]) #number of input covariates
outputs = net.sim(P)
c_index = get_C_index(T, outputs)
logger.info("C index = " + str(c_index))
#plot_network_weights(net)
kaplanmeier(time_array = T[:, 0], event_array = T[:, 1], output_array = outputs[:, 0])
if vP is not None and len(vP) > 0:
outputs = net.sim(vP)
kaplanmeier(time_array = vT[:, 0], event_array = vT[:, 1], output_array = outputs[:, 0])
return net
if __name__ == "__main__":
logging.basicConfig(level = logging.INFO)
glogger.setLoggingLevel(glogger.nothing)
filename = "/home/gibson/jonask/Dropbox/Ann-Survival-Phd/Two_thirds_of_SA_1889_dataset.txt"
#try:
# columns = input("Which columns to include? (Do NOT forget trailing comma if only one column is used, e.g. '3,'\nAvailable columns are: 2, -4, -3, -2, -1. Just press ENTER for all columns.\n")
#except SyntaxError:
columns = (2, -4, -3, -2, -1)
print('\nIncluding columns: ' + str(columns))
P, T = parse_file(filename, targetcols = [4, 5], inputcols = columns, ignorerows = [0], normalize = True)
#remove tail censored
#print('\nRemoving tail censored...')
#P, T = copy_without_tailcensored(P, T)
try: