def survival_stat(filename, thresholds = None):
data = np.array(read_data_file(filename, ","))
D, t = parse_data(data, inputcols = (2, 3, 4, 5, 6, 7, 8, 9, 10), ignorerows = [0], normalize = False)
T = D[:, (2, 3)]
outputs = D[:, (-1, 3)]
C = get_C_index(T, outputs)
print("C-index: " + str(C))
print("Genetic error: " + str(1 / C))
th = kaplanmeier(D, 2, 3, -1, threshold = thresholds)
print("Threshold dividing the set in two equal pieces: " + str(th))
if plt:
plt.show()
def committee_test():
try:
netsize = input('Number of hidden nodes? [1]: ')
except SyntaxError as e:
netsize = 1
try:
comsize = input('Committee size? [1]: ')
except SyntaxError as e:
comsize = 1
try:
pop_size = input('Population size? [100]: ')
except SyntaxError as e:
pop_size = 100
try:
mutation_rate = input('Please input a mutation rate (0.05): ')
except SyntaxError as e:
mutation_rate = 0.05
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)
P, T = parse_file(filename, targetcols = [4, 5], inputcols = columns, ignorerows = [0], normalize = True)
#remove tail censored
try:
cutoff = input('Cutoff for censored data? [9999 years]: ')
except SyntaxError as e:
cutoff = 9999
P, T = copy_without_censored(P, T, cutoff)
#Divide into validation sets
try:
test_size = float(input('Size of test set (not used in training)? Input in fractions. Default is [0.0]: '))
except:
test_size = 0.0
((TP, TT), (VP, VT)) = get_validation_set(P, T, validation_size = test_size, binary_column = 1)
print("Length of training set: " + str(len(TP)))
print("Length of test set: " + str(len(VP)))
try:
epochs = input("\nNumber of generations (1): ")
except SyntaxError as e:
epochs = 1
com = build_feedforward_committee(comsize, len(P[0]), netsize, 1, output_function = 'linear')
#1 is the column in the target array which holds the binary censoring information
test_errors, vald_errors, data_sets = train_committee(com, train_evolutionary, P, T, 1, epochs, error_function = c_index_error, population_size = pop_size, mutation_chance = mutation_rate)
com.set_training_sets([set[0][0] for set in data_sets]) #first 0 gives training sets, second 0 gives inputs.
print('\nTest C_indices, Validation C_indices:')
for terr, verr in zip(test_errors.values(), vald_errors.values()):
print(str(1 / terr) + ", " + str(1 / verr))
if plt:
outputs = numpy.array([[com.risk_eval(inputs)] for inputs in TP]) #Need double brackets for dimensions to be right for numpy
kaplanmeier(time_array = TT[:, 0], event_array = TT[:, 1], output_array = outputs[:, 0], threshold = 0.5)
train_c_index = get_C_index(TT, outputs)
print("\nC-index on the training set: " + str(train_c_index))
if len(VP) > 0:
outputs = numpy.array([[com.risk_eval(inputs)] for inputs in VP]) #Need double brackets for dimensions to be right for numpy
test_c_index = get_C_index(VT, outputs)
kaplanmeier(time_array = VT[:, 0], event_array = VT[:, 1], output_array = outputs[:, 0], threshold = 0.5)
print("C-index on the test set: " + str(test_c_index))
#raw_input("\nPress enter to show plots...")
plt.show()
try:
answer = input("\nDo you wish to print committee risk output? ['n']: ")
except (SyntaxError, NameError):
answer = 'n'
if answer != 'n' and answer != 'no':
inputs = read_data_file(filename)
P, T = parse_file(filename, targetcols = [4, 5], inputcols = columns, ignorerows = [0], normalize = True)
outputs = [[com.risk_eval(patient)] for patient in P]
while len(inputs) > len(outputs):
outputs.insert(0, ["net_output"])
print("\n")
for rawline in zip(inputs, outputs):
line = ''
for col in rawline[0]:
line += str(col)
line += ','
for col in rawline[1]:
line += str(col)
print(line)