def test_model_arrays(savefile, filename, P, T, **kwargs):
with open(savefile, 'r') as FILE:
master_com = pickle.load(FILE)
print("Committee size: {0}".format(len(master_com)))
output_file = 'test_{0}_{1}.cvs'.format(os.path.splitext(os.path.basename(savefile))[0], \
os.path.splitext(os.path.basename(filename))[0])
#Need double brackets for dimensions to be right for numpy
outputs = numpy.array([[master_com.risk_eval(inputs)] for inputs in P])
if T is None or len(T) == 0:
with open(output_file, 'w') as F:
#print('Targets\tOutputs\tEvents:')
F.write("Outputs\n")
for o in outputs:
#print("{0}\t{1}\t{2}".format(t[0], o[0], t[1]))
F.write("{0}\n".format(o[0]))
return outputs
c_index = get_C_index(T, outputs)
print("C-Index: {0}".format(c_index))
#if len(sys.argv) > 2:
# thresholds = [float(t) for t in sys.argv[2:]]
#else:
thresholds = None
#Calculate suitable size for the figure for use in LaTEX
fig_width_pt = 396.0 # Get this from LaTeX using \showthe\columnwidth
inches_per_pt = 1.0 / 72.27 # Convert pt to inch
golden_mean = (sqrt(5) - 1.0) / 2.0 # Aesthetic ratio
fig_width = fig_width_pt * inches_per_pt # width in inches
fig_height = fig_width * golden_mean # height in inches
fig_size = [fig_width, fig_height]
#Update settings
plt.rcParams['figure.figsize'] = fig_size
th = kaplanmeier(time_array=T[:, 0],
event_array=T[:, 1],
output_array=outputs,
threshold=thresholds,
show_plot=False,
bestcut=False,
**kwargs)
#print("Threshold dividing the set in two equal pieces: " + str(th))
if plt:
plt.savefig('kaplanmeier_{0}_{1}.eps'.format(os.path.splitext(os.path.basename(savefile))[0], \
os.path.splitext(os.path.basename(filename))[0]))
with open(output_file, 'w') as F:
#print('Targets\tOutputs\tEvents:')
F.write("Targets,Outputs,Events\n")
for t, o in zip(T, outputs):
#print("{0}\t{1}\t{2}".format(t[0], o[0], t[1]))
F.write("{0},{1},{2}\n".format(t[0], o[0], t[1]))
return output_file
def experiment(net, P, T, vP, vT, filename, epochs, learning_rate):
logger.info("Running experiment for: " + filename + ' ' + str(epochs) + ", rate: " + str(learning_rate))
print("Number of patients with events: " + str(T[:, 1].sum()))
print("Number of censored patients: " + str((1 - T[:, 1]).sum()))
timeslots = generate_timeslots(T)
try:
net = traingd(net, (P, T), (vP, vT), epochs, learning_rate, block_size = 100, 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)
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
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)
def plotKM(targets, outputs, cut):
kaplanmeier(time_array=targets[:,0], event_array=targets[:, 1],
output_array=outputs, threshold=cut, show_plot=False)
def test_model_arrays(savefile, filename, P, T, **kwargs):
with open(savefile, "r") as FILE:
master_com = pickle.load(FILE)
print("Committee size: {0}".format(len(master_com)))
output_file = "test_{0}_{1}.cvs".format(
os.path.splitext(os.path.basename(savefile))[0], os.path.splitext(os.path.basename(filename))[0]
)
# Need double brackets for dimensions to be right for numpy
outputs = numpy.array([[master_com.risk_eval(inputs)] for inputs in P])
if T is None or len(T) == 0:
with open(output_file, "w") as F:
# print('Targets\tOutputs\tEvents:')
F.write("Outputs\n")
for o in outputs:
# print("{0}\t{1}\t{2}".format(t[0], o[0], t[1]))
F.write("{0}\n".format(o[0]))
return outputs
c_index = get_C_index(T, outputs)
print("C-Index: {0}".format(c_index))
# if len(sys.argv) > 2:
# thresholds = [float(t) for t in sys.argv[2:]]
# else:
thresholds = None
# Calculate suitable size for the figure for use in LaTEX
fig_width_pt = 396.0 # Get this from LaTeX using \showthe\columnwidth
inches_per_pt = 1.0 / 72.27 # Convert pt to inch
golden_mean = (sqrt(5) - 1.0) / 2.0 # Aesthetic ratio
fig_width = fig_width_pt * inches_per_pt # width in inches
fig_height = fig_width * golden_mean # height in inches
fig_size = [fig_width, fig_height]
# Update settings
plt.rcParams["figure.figsize"] = fig_size
th = kaplanmeier(
time_array=T[:, 0],
event_array=T[:, 1],
output_array=outputs,
threshold=thresholds,
show_plot=False,
bestcut=False,
**kwargs
)
# print("Threshold dividing the set in two equal pieces: " + str(th))
if plt:
plt.savefig(
"kaplanmeier_{0}_{1}.eps".format(
os.path.splitext(os.path.basename(savefile))[0], os.path.splitext(os.path.basename(filename))[0]
)
)
with open(output_file, "w") as F:
# print('Targets\tOutputs\tEvents:')
F.write("Targets,Outputs,Events\n")
for t, o in zip(T, outputs):
# print("{0}\t{1}\t{2}".format(t[0], o[0], t[1]))
F.write("{0},{1},{2}\n".format(t[0], o[0], t[1]))
return output_file
def plotKM(targets, outputs, cut):
kaplanmeier(time_array=targets[:, 0],
event_array=targets[:, 1],
output_array=outputs,
threshold=cut,
show_plot=False)
def train_single():
try:
netsize = input('Number of hidden nodes? [1]: ')
except SyntaxError as e:
netsize = 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
SB22 = "/home/gibson/jonask/Dropbox/Ann-Survival-Phd/Two_thirds_of_SA_1889_dataset_SB22.txt"
Benmargskohorten = "/home/gibson/jonask/Dropbox/Ann-Survival-Phd/Two_thirds_of_SA_1889_dataset_Benmargskohorten.txt"
SB91b = "/home/gibson/jonask/Dropbox/Ann-Survival-Phd/Two_thirds_of_SA_1889_dataset_SB91b.txt"
all_studies = "/home/gibson/jonask/Dropbox/Ann-Survival-Phd/Two_thirds_of_SA_1889_dataset.txt"
#Real data
print("Studies to choose from:")
print("1: SB22")
print("2: Benmargskohorten")
print("3: SB91b")
print("0: All combined (default)")
try:
study = input("Which study to train on? [0]: ")
except SyntaxError as e:
study = 0
if study == 1:
filename = SB22
elif study == 2:
filename = Benmargskohorten
elif study == 3:
filename = SB91b
else:
filename = all_studies
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 = [2, -4, -3, -2, -1], ignorerows = [0], normalize = True)
P, T = parse_file(filename, targetcols = [4, 5], inputcols = columns, ignorerows = [0], normalize = True)
#Used for output comparison
studies = {}
studies[SB22] = parse_file(SB22, targetcols = [4, 5], inputcols = columns, ignorerows = [0], normalize = True)
studies[Benmargskohorten] = parse_file(Benmargskohorten, targetcols = [4, 5], inputcols = columns, ignorerows = [0], normalize = True)
studies[SB91b] = parse_file(SB91b, targetcols = [4, 5], inputcols = columns, ignorerows = [0], normalize = True)
studies[all_studies] = parse_file(all_studies, 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:
pieces = input('Size of validation set? Input denominator (1 for no validation set). Default is 1/[1] parts: ')
except:
pieces = 1
TandV = get_cross_validation_sets(P, T, pieces , binary_column = 1)
#Network part
p = len(P[0]) #number of input covariates
net = build_feedforward(p, netsize, 1, output_function = 'linear')
#net = build_feedforward_multilayered(p, [7, 10], 1, output_function = 'linear')
#Initial state
#outputs = net.sim(tP)
#orderscatter(outputs, tT, filename, 's')
try:
epochs = input("Number of generations (1): ")
except SyntaxError as e:
epochs = 1
for ((tP, tT), (vP, vT)) in TandV:
#train
net = test(net, tP, tT, vP, vT, filename, epochs, population_size = pop_size, mutation_rate = mutation_rate)
if plt:
outputs = net.sim(tP)
threshold = kaplanmeier(time_array = tT[:, 0], event_array = tT[:, 1], output_array = outputs[:, 0])
if len(vP) > 0:
outputs = net.sim(vP)
kaplanmeier(time_array = vT[:, 0], event_array = vT[:, 1], output_array = outputs[:, 0], threshold = threshold)
print("\nThreshold dividing the training set in two equal pieces: " + str(threshold))
raw_input("\nPress enter to show plots...")
plt.show()
try:
answer = input("Do you wish to print network output? Enter filename, or 'no' / 'n'. ['n']: ")
except (SyntaxError, NameError):
answer = 'n'
if os.path.exists(answer):
print("File exists. Will add random number to front")
answer = str(random.randint(0, 123456)) + answer
if answer != 'n' and answer != 'no':
print_output(answer, net, filename, targetcols = [4, 5], inputcols = columns, ignorerows = [0], normalize = True)
