def classify(true_labels):
num_feats = 2
num_vec = true_labels.get_num_labels()
data_train = numpy.concatenate(
(numpy.random.randn(num_feats, num_vec / 2) - 1,
numpy.random.randn(num_feats, num_vec / 2) + 1),
axis=1)
realfeat = RealFeatures(data_train)
feats_train = SparseRealFeatures()
feats_train.obtain_from_simple(realfeat)
C = 3.
svm = SVMOcas(C, feats_train, true_labels)
svm.train()
data_test = numpy.concatenate(
(numpy.random.randn(num_feats, num_vec / 2) - 1,
numpy.random.randn(num_feats, num_vec / 2) + 1),
axis=1)
realfeat = RealFeatures(data_test)
feats_test = SparseRealFeatures()
feats_test.obtain_from_simple(realfeat)
svm.set_features(feats_test)
return numpy.array(svm.classify().get_labels())
def classify (true_labels): num_feats=2 num_vec=true_labels.get_num_labels() data_train=numpy.concatenate( (numpy.random.randn(num_feats, num_vec/2)-1, numpy.random.randn(num_feats, num_vec/2)+1), axis=1) realfeat=RealFeatures(data_train) feats_train=SparseRealFeatures() feats_train.obtain_from_simple(realfeat) C=3. svm=SVMOcas(C, feats_train, true_labels) svm.train() data_test=numpy.concatenate( (numpy.random.randn(num_feats, num_vec/2)-1, numpy.random.randn(num_feats, num_vec/2)+1), axis=1) realfeat=RealFeatures(data_test) feats_test=SparseRealFeatures() feats_test.obtain_from_simple(realfeat) svm.set_features(feats_test) return numpy.array(svm.classify().get_labels())
def classifier_svmocas_modular(fm_train_real=traindat,
fm_test_real=testdat,
label_train_twoclass=label_traindat,
C=0.9,
epsilon=1e-5,
num_threads=1):
from shogun.Features import RealFeatures, SparseRealFeatures, BinaryLabels
from shogun.Classifier import SVMOcas
realfeat = RealFeatures(fm_train_real)
feats_train = SparseRealFeatures()
feats_train.obtain_from_simple(realfeat)
realfeat = RealFeatures(fm_test_real)
feats_test = SparseRealFeatures()
feats_test.obtain_from_simple(realfeat)
labels = BinaryLabels(label_train_twoclass)
svm = SVMOcas(C, feats_train, labels)
svm.set_epsilon(epsilon)
svm.parallel.set_num_threads(num_threads)
svm.set_bias_enabled(False)
svm.train()
svm.set_features(feats_test)
svm.apply().get_labels()
predictions = svm.apply()
return predictions, svm, predictions.get_labels()
def classifier_svmocas_modular (fm_train_real=traindat,fm_test_real=testdat,label_train_twoclass=label_traindat,C=0.9,epsilon=1e-5,num_threads=1): from shogun.Features import RealFeatures, SparseRealFeatures, Labels from shogun.Classifier import SVMOcas realfeat=RealFeatures(fm_train_real) feats_train=SparseRealFeatures() feats_train.obtain_from_simple(realfeat) realfeat=RealFeatures(fm_test_real) feats_test=SparseRealFeatures() feats_test.obtain_from_simple(realfeat) labels=Labels(label_train_twoclass) svm=SVMOcas(C, feats_train, labels) svm.set_epsilon(epsilon) svm.parallel.set_num_threads(num_threads) svm.set_bias_enabled(False) svm.train() svm.set_features(feats_test) svm.classify().get_labels() predictions = svm.classify() return predictions, svm, predictions.get_labels()
def svmocas():
print "SVMOcas"
from shogun.Features import RealFeatures, SparseRealFeatures, Labels
from shogun.Classifier import SVMOcas
realfeat = RealFeatures(fm_train_real)
feats_train = SparseRealFeatures()
feats_train.obtain_from_simple(realfeat)
realfeat = RealFeatures(fm_test_real)
feats_test = SparseRealFeatures()
feats_test.obtain_from_simple(realfeat)
C = 0.9
epsilon = 1e-5
num_threads = 1
labels = Labels(label_train_twoclass)
svm = SVMOcas(C, feats_train, labels)
svm.set_epsilon(epsilon)
svm.parallel.set_num_threads(num_threads)
svm.set_bias_enabled(False)
svm.train()
svm.set_features(feats_test)
svm.classify().get_labels()
