def __init__(self, data, targets, cv_data, cv_targets, extra, layers, epochs=1, smoothing=1, new=True, filename_in=False):
if len(cv_data) != len(cv_targets): raise Exception("Number of CV data and CV targets must be equal")
if len(data) != len(targets): raise Exception("Number of data and targets must be equal")
if new:
class_tr_targets = [str(int(t[0]) - 1) for t in targets] # for pybrain's classification datset
print "...training the DNNRegressor"
if len(layers) > 2: # TODO testing only
net = DNNRegressor(data, extra, class_tr_targets, layers, hidden_layer="TanhLayer", final_layer="SoftmaxLayer", compression_epochs=epochs, bias=True, autoencoding_only=False)
print "...running net.fit()"
net = net.fit()
elif len(layers) == 2:
net = buildNetwork(layers[0], layers[-1], outclass=SoftmaxLayer, bias=True)
ds = ClassificationDataSet(len(data[0]), 1, nb_classes=9)
bag = 1
noisy, _ = self.dropout(data, noise=0.0, bag=bag, debug=True)
bagged_targets = []
for t in class_tr_targets:
for b in range(bag):
bagged_targets.append(t)
for i,d in enumerate(noisy):
t = bagged_targets[i]
ds.addSample(d, t)
ds._convertToOneOfMany()
print "...smoothing for epochs: ", smoothing
self.model = net
preds = [self.predict(d) for d in cv_data]
cv = score(preds, cv_targets, debug=False)
preds = [self.predict(d) for d in data]
tr = score(preds, targets, debug=False)
trainer = BackpropTrainer(net, ds, verbose=True, learningrate=0.0008, momentum=0.04, weightdecay=0.05) # best score 0.398 after 50 compression epochs and 200 epochs with lr=0.0008, weightdecay=0.05, momentum=0.04. Used dropout of 0.2 in compression, 0.5 in softmax pretraining, and no dropout in smoothing.
print "Train score before training: ", tr
print "CV score before training: ", cv
for i in range(smoothing):
trainer.train()
self.model = net
preds = [self.predict(d) for d in cv_data]
cv = score(preds, cv_targets, debug=False)
preds = [self.predict(d) for d in data]
tr = score(preds, targets, debug=False)
print "Train/CV score at epoch ", (i+1), ': ', tr, '/', cv
#if i == 1:
#print "...saving the model"
#save("data/1000_ex_4_hidden/net_epoch_1.txt", net)
#elif i == 3:
#print "...saving the model"
#save("data/1000_ex_4_hidden/net_epoch_3.txt", net)
#elif i == 5:
#print "...saving the model"
#save("data/1000_ex_4_hidden/net_epoch_5.txt", net)
print "...saving the model"
#save("data/1000_ex_4_hidden/net_epoch_10.txt", net)
else:
model = load(filename_in)
self.model = model
def do_import(ast, module):
if module in importedFiles:
return True
importedFiles.append(module)
subprocess.call([sys.argv[0], "-c", module])
name_p = module.replace(".kh", ".kp")
obj = my_pickle.load(open(name_p, "rb"))
ast.ref.body += obj[0].body
for it in obj[0].types.maps:
ast.ref.types.update(it)
symtab.update(obj[1])
def autoencode(self, data, targets, cv, epochs=1, new=True):
if new:
end = 1000
autoencoder = AutoEncoder(
data[:end],
targets[:end],
[1875, 900, 9],
hidden_layer="SigmoidLayer",
final_layer="SigmoidLayer",
compression_epochs=epochs,
bias=True,
autoencoding_only=True,
)
autoencoder = autoencoder.fit()
save(filename, autoencoder)
else:
autoencoder = load(filename)
data = [autoencoder.activate(d) for d in data]
cv = [autoencoder.activate(c) for c in cv]
print data[0][:10]
return data, cv
