#Limit to incourage overtraining!
#rows = sample(range(len(T)), 100)
#P = P[rows]
#T = T[rows]
p = len(P[0]) #number of input covariates
#net = load_network('/home/gibson/jonask/Projects/aNeuralN/ANNs/4x10x10x1.ann')
net = build_feedforward(p, 30, 1, output_function = 'linear')
#Initial state
outputs = net.sim(P)
orderscatter(outputs, T, filename, 's')
for var in xrange(len(P[0, :])):
plot_input(P[:, var])
glogger.show()
epochs = 20000
rate = 1
block_size = 0
for times in range(100):
net = test(net, P, T, filename, epochs, rate, block_size)
outputs = net.sim(P)
orderscatter(outputs, T, filename, 'o')
raw_input("Press enter to show plots...")
glogger.show()
def train_single():
try:
netsize = input('Number of hidden nodes? [3]: ')
except SyntaxError as e:
netsize = 3
try:
pop_size = input('Population size? [50]: ')
except SyntaxError as e:
pop_size = 50
try:
mutation_rate = input('Please input a mutation rate (0.25): ')
except SyntaxError as e:
mutation_rate = 0.25
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
#P, T = copy_without_tailcensored(P, T)
#Divide into validation sets
#((tP, tT), (vP, vT)) = get_validation_set(P, T, validation_size = 0.25, binary_column = 1)
TandV = get_cross_validation_sets(P, T, 2 , 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')
try:
epochs = input("Number of generations (200): ")
except SyntaxError as e:
epochs = 200
for times, ((tP, tT), (vP, vT)) in zip(xrange(2), TandV):
#train
net = test(net, tP, tT, vP, vT, filename, epochs, population_size = pop_size, mutation_rate = mutation_rate)
raw_input("Press enter to show plots...")
glogger.show()
