def train_svm():
svm = SVMUnit()
ds = ClassificationDataSet(len(input_args),1,nb_classes=2)
ds = generate_data(ds , hour_to_use_app = 10)
trainer = SVMTrainer( svm , ds )
trainer.train()
test = ClassificationDataSet(4,1)
test.addSample((12,6,10,6),[0])
test.addSample((12,1,7,22),[1])
test.addSample((12,3,20,1),[1])
svm.activateOnDataset(test)
return svm,trainer,ds,test
def bench_pybrain(X, y, T, valid):
#
# .. PyBrain ..
#
# local import, they require libsvm < 2.81
from pybrain.supervised.trainers.svmtrainer import SVMTrainer
from pybrain.structure.modules.svmunit import SVMUnit
from pybrain.datasets import SupervisedDataSet
tstart = datetime.now()
ds = SupervisedDataSet(X.shape[1], 1)
for i in range(X.shape[0]):
ds.addSample(X[i], y[i])
clf = SVMTrainer(SVMUnit(), ds)
clf.train()
pred = np.empty(T.shape[0], dtype=np.int32)
for i in range(T.shape[0]):
pred[i] = clf.svm.model.predict(T[i])
score = np.mean(pred == valid)
return score, datetime.now() - tstart
def bench_pybrain(X, y, T, valid):
#
# .. PyBrain ..
#
# local import, they require libsvm < 2.81
from pybrain.supervised.trainers.svmtrainer import SVMTrainer
from pybrain.structure.modules.svmunit import SVMUnit
from pybrain.datasets import SupervisedDataSet
tstart = datetime.now()
ds = SupervisedDataSet(X.shape[1], 1)
for i in range(X.shape[0]):
ds.addSample(X[i], y[i])
clf = SVMTrainer(SVMUnit(), ds)
clf.train()
pred = np.empty(T.shape[0], dtype=np.int32)
for i in range(T.shape[0]):
pred[i] = clf.svm.model.predict(T[i])
score = np.mean(pred == valid)
return score, datetime.now() - tstart
filename=join('.', 'testrun.log'),
format='%(asctime)s %(levelname)s %(message)s')
logging.getLogger('').addHandler(logging.StreamHandler())
# load the training and test data sets
trndata = generateClassificationData(20, nClasses=2)
tstdata = generateClassificationData(100, nClasses=2)
# initialize the SVM module and a corresponding trainer
svm = SVMUnit()
trainer = SVMTrainer(svm, trndata)
# train the with fixed meta-parameters
log2C = 0. # degree of slack
log2g = 1.1 # width of RBF kernels
trainer.train(log2C=log2C, log2g=log2g)
# alternatively, could train the SVM using design-of-experiments grid search
##trainer.train( search="GridSearchDOE" )
# pass data sets through the SVM to get performance
trnresult = percentError(svm.activateOnDataset(trndata), trndata['target'])
tstresult = percentError(svm.activateOnDataset(tstdata), tstdata['target'])
print "sigma: %7g, C: %7g, train error: %5.2f%%, test error: %5.2f%%" % (
2.0**log2g, 2.0**log2C, trnresult, tstresult)
# generate a grid dataset
griddat, X, Y = generateGridData(x=[-4, 8, 0.1], y=[-2, 3, 0.1])
# pass the grid through the SVM, but this time get the raw distance
# from the boundary, not the class
Z = svm.activateOnDataset(griddat, values=True)
dataset = SupervisedDataSet(2, 1)
dataset.addSample((0, 0), (0,))
dataset.addSample((0, 1), (1,))
dataset.addSample((1, 0), (1,))
dataset.addSample((1, 1), (0,))
# Criando a SVM unit
svm = SVMUnit()
# Trainando a SVM
trainer = SVMTrainer(svm, dataset)
# Treinando a rede
err = 1.0
while err > 0.0001:
err = trainer.train()
# print err
# Imprimindo ativação da rede para todo o conjunto
print network.activateOnDataset(dataset)
# Imprimindo pesos da rede
for mod in network.modules:
for conn in network.connections[mod]:
print conn
for cc in range(len(conn.params)):
print conn.whichBuffers(cc), conn.params[cc]
# Ativando entradas individualmente
# print network.activate([0,0])
# print network.activate([0,1])
#Crear los dataset supervisados
trainDS = ClassificationDataSet(numColsTrain-1, nb_classes=2, class_labels=['Not_Cancer', 'Cancer'])
for i in range(numPatTrain):
trainDS.appendLinked(patternTrainInput[i], patternTrain[i, 0])
validDS = ClassificationDataSet(numColsTrain-1, nb_classes=2, class_labels=['Not_Cancer', 'Cancer'])
for i in range(numPatValid):
validDS.appendLinked(patternValidInput[i], patternValid[i, 0])
testDS = ClassificationDataSet(numColsTrain-1, nb_classes=2, class_labels=['Not_Cancer', 'Cancer'])
for i in range(numPatTest):
testDS.appendLinked(patternTestInput[i], patternTest[i, 0])
#Crear la SVM y el trainer
svm = SVMUnit()
trainer = SVMTrainer(svm, trainDS)
#Parámetros de la SVM
myLog2C=0.
myLog2g=1.1
#Entrenar la red
trainer.train(log2g=myLog2g, log2C=myLog2C)
#
trnresult = percentError( svm.activateOnDataset(trndata), trndata['target'] )
tstresult = percentError( svm.activateOnDataset(tstdata), tstdata['target'] )
print("sigma: %7g, C: %7g, train error: %5.2f%%, test error: %5.2f%%" % (2.0**myLog2g, 2.0**myLog2C, trnresult, tstresult))
# load the training and test data sets
trndata = generateClassificationData(20, nClasses=2)
tstdata = generateClassificationData(100, nClasses=2)
for inpt, target in trndata:
print inpt, target
# initialize the SVM module and a corresponding trainer
svm = SVMUnit()
trainer = SVMTrainer(svm, trndata)
# train the with fixed meta-parameters
log2C = 0.0 # degree of slack
log2g = 1.1 # width of RBF kernels
trainer.train(log2C=log2C, log2g=log2g)
# alternatively, could train the SVM using design-of-experiments grid search
##trainer.train( search="GridSearchDOE" )
# pass data sets through the SVM to get performance
trnresult = percentError(svm.activateOnDataset(trndata), trndata["target"])
tstresult = percentError(svm.activateOnDataset(tstdata), tstdata["target"])
print "sigma: %7g, C: %7g, train error: %5.2f%%, test error: %5.2f%%" % (
2.0 ** log2g,
2.0 ** log2C,
trnresult,
tstresult,
)
# generate a grid dataset
griddat, X, Y = generateGridData(x=[-4, 8, 0.1], y=[-2, 3, 0.1])