def run_nn_fold(training_data, test_data):
test_features, ignore, featureMap, labels, labelMap = fs.mutualinfo(training_data)
input_len = len(test_features[0])
num_classes = len(labelMap.keys())
train_ds = ClassificationDataSet(input_len, 1,nb_classes=num_classes)
for i in range(len(test_features)):
train_ds.addSample(tuple(test_features[i]), (labels[i]))
train_ds._convertToOneOfMany()
net = buildNetwork(train_ds.indim, 2, train_ds.outdim, bias=True, hiddenclass=TanhLayer, outclass=SoftmaxLayer)
trainer = BackpropTrainer(net, train_ds, verbose=True)
print "training until convergence..."
trainer.trainUntilConvergence(maxEpochs=100)
print "done. testing..."
test_ds = ClassificationDataSet(input_len, 1,nb_classes=num_classes)
labels = []
for tweetinfo in test_data:
featuresFound = tweetinfo["Features"]
label = tweetinfo["Answer"]
labels.append(label)
features = [0]*len(featureMap.keys())
for feat in featuresFound:
if feat in featureMap:
features[ featureMap[feat] ] = 1
test_ds.addSample(tuple(features), (labelMap[label]))
test_ds._convertToOneOfMany()
tstresult = percentError( trainer.testOnClassData(
dataset=test_ds ), test_ds['class'] )
print tstresult
def train(training_data):
"""
Trains a model, using bernoulli features
"""
if ARGV.features == "bernoulli":
features, featureMap, labels, labelMap = fs.bernoulli(training_data)
else:
features, scores, featureMap, labels, labelMap = fs.mutualinfo(training_data)
learner = models[ ARGV.model ]()
if ARGV.one_vs:
labels[ labels != labelMap[ ARGV.one_vs ] ] = 0
labels[ labels == labelMap[ ARGV.one_vs ] ] = 1
model = learner.train(features, labels)
if ARGV.features == "bernoulli":
return (model, featureMap, labelMap)
else:
return ((model,scores), featureMap, labelMap)
def train(training_data):
"""
Trains a model, using bernoulli features
"""
if ARGV.features == "bernoulli":
features, featureMap, labels, labelMap = fs.bernoulli(training_data)
else:
features, scores, featureMap, labels, labelMap = fs.mutualinfo(
training_data)
learner = models[ARGV.model]()
if ARGV.one_vs:
labels[labels != labelMap[ARGV.one_vs]] = 0
labels[labels == labelMap[ARGV.one_vs]] = 1
model = learner.train(features, labels)
if ARGV.features == "bernoulli":
return (model, featureMap, labelMap)
else:
return ((model, scores), featureMap, labelMap)
def run_nn_fold(training_data, test_data):
test_features, ignore, featureMap, labels, labelMap = fs.mutualinfo(
training_data)
input_len = len(test_features[0])
num_classes = len(labelMap.keys())
train_ds = ClassificationDataSet(input_len, 1, nb_classes=num_classes)
for i in range(len(test_features)):
train_ds.addSample(tuple(test_features[i]), (labels[i]))
train_ds._convertToOneOfMany()
net = buildNetwork(train_ds.indim,
2,
train_ds.outdim,
bias=True,
hiddenclass=TanhLayer,
outclass=SoftmaxLayer)
trainer = BackpropTrainer(net, train_ds, verbose=True)
print "training until convergence..."
trainer.trainUntilConvergence(maxEpochs=100)
print "done. testing..."
test_ds = ClassificationDataSet(input_len, 1, nb_classes=num_classes)
labels = []
for tweetinfo in test_data:
featuresFound = tweetinfo["Features"]
label = tweetinfo["Answer"]
labels.append(label)
features = [0] * len(featureMap.keys())
for feat in featuresFound:
if feat in featureMap:
features[featureMap[feat]] = 1
test_ds.addSample(tuple(features), (labelMap[label]))
test_ds._convertToOneOfMany()
tstresult = percentError(trainer.testOnClassData(dataset=test_ds),
test_ds['class'])
print tstresult
