def classifier_svmocas_modular(train_fname=traindat,
test_fname=testdat,
label_fname=label_traindat,
C=0.9,
epsilon=1e-5,
num_threads=1):
from modshogun import RealFeatures, BinaryLabels
from modshogun import CSVFile
try:
from modshogun import SVMOcas
except ImportError:
print("SVMOcas not available")
return
feats_train = RealFeatures(CSVFile(train_fname))
feats_test = RealFeatures(CSVFile(test_fname))
labels = BinaryLabels(CSVFile(label_fname))
svm = SVMOcas(C, feats_train, labels)
svm.set_epsilon(epsilon)
svm.parallel.set_num_threads(num_threads)
svm.set_bias_enabled(False)
svm.train()
bias = svm.get_bias()
w = svm.get_w()
predictions = svm.apply(feats_test)
return predictions, svm, predictions.get_labels()
if __name__ == '__main__':
from modshogun import SparseRealFeatures, RandomFourierDotFeatures, GAUSSIAN
from modshogun import LibSVMFile, BinaryLabels, SVMOcas
from modshogun import Time
from numpy import array
args = parse_arguments()
print 'Loading training data...'
sparse_data = load_sparse_data(args.dataset, args.dimension)
kernel_params = array([args.width], dtype=float)
rf_feats = RandomFourierDotFeatures(sparse_data['data'], args.D, GAUSSIAN,
kernel_params)
svm = SVMOcas(args.C, rf_feats, sparse_data['labels'])
svm.set_epsilon(args.epsilon)
print 'Starting training.'
timer = Time()
svm.train()
timer.stop()
print 'Training completed, took {0:.2f}s.'.format(timer.time_diff_sec())
predicted_labels = svm.apply()
evaluate(predicted_labels, sparse_data['labels'], 'Training results')
if args.testset != None:
random_coef = rf_feats.get_random_coefficients()
# removing current dataset from memory in order to load the test dataset,
# to avoid running out of memory
rf_feats = None
