def classifier_multiclasslinearmachine_modular (fm_train_real=traindat,fm_test_real=testdat,label_train_multiclass=label_traindat,label_test_multiclass=label_testdat,lawidth=2.1,C=1,epsilon=1e-5):
from shogun.Features import RealFeatures, MulticlassLabels
from shogun.Classifier import LibLinear, L2R_L2LOSS_SVC, LinearMulticlassMachine
from shogun.Classifier import ECOCStrategy, ECOCDiscriminantEncoder, ECOCHDDecoder
feats_train = RealFeatures(fm_train_real)
feats_test = RealFeatures(fm_test_real)
labels = MulticlassLabels(label_train_multiclass)
classifier = LibLinear(L2R_L2LOSS_SVC)
classifier.set_epsilon(epsilon)
classifier.set_bias_enabled(True)
encoder = ECOCDiscriminantEncoder()
encoder.set_features(feats_train)
encoder.set_labels(labels)
encoder.set_sffs_iterations(50)
strategy = ECOCStrategy(encoder, ECOCHDDecoder())
classifier = LinearMulticlassMachine(strategy, feats_train, classifier, labels)
classifier.train()
label_pred = classifier.apply(feats_test)
out = label_pred.get_labels()
if label_test_multiclass is not None:
from shogun.Evaluation import MulticlassAccuracy
labels_test = MulticlassLabels(label_test_multiclass)
evaluator = MulticlassAccuracy()
acc = evaluator.evaluate(label_pred, labels_test)
print('Accuracy = %.4f' % acc)
return out
def liblinear (): print 'LibLinear' from shogun.Features import RealFeatures, SparseRealFeatures, Labels from shogun.Classifier import LibLinear 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=LibLinear(C, feats_train, labels) svm.set_epsilon(epsilon) svm.parallel.set_num_threads(num_threads) svm.set_bias_enabled(True) svm.train() svm.set_features(feats_test) print svm.classify().get_labels()
def classifier_multiclasslinearmachine_modular(
fm_train_real=traindat, fm_test_real=testdat, label_train_multiclass=label_traindat, width=2.1, C=1, epsilon=1e-5
):
from shogun.Features import RealFeatures, Labels
from shogun.Classifier import LibLinear, L2R_L2LOSS_SVC, LinearMulticlassMachine
from shogun.Classifier import ECOCStrategy, ECOCRandomSparseEncoder, ECOCRandomDenseEncoder, ECOCHDDecoder
feats_train = RealFeatures(fm_train_real)
feats_test = RealFeatures(fm_test_real)
labels = Labels(label_train_multiclass)
classifier = LibLinear(L2R_L2LOSS_SVC)
classifier.set_epsilon(epsilon)
classifier.set_bias_enabled(True)
rnd_dense_strategy = ECOCStrategy(ECOCRandomDenseEncoder(), ECOCHDDecoder())
rnd_sparse_strategy = ECOCStrategy(ECOCRandomSparseEncoder(), ECOCHDDecoder())
dense_classifier = LinearMulticlassMachine(rnd_dense_strategy, feats_train, classifier, labels)
dense_classifier.train()
out_dense = dense_classifier.apply(feats_test).get_labels()
sparse_classifier = LinearMulticlassMachine(rnd_sparse_strategy, feats_train, classifier, labels)
sparse_classifier.train()
out_sparse = sparse_classifier.apply(feats_test).get_labels()
return out_sparse, out_dense
def classifier_multiclasslinearmachine_modular(
fm_train_real=traindat,
fm_test_real=testdat,
label_train_multiclass=label_traindat,
label_test_multiclass=label_testdat,
width=2.1,
C=1,
epsilon=1e-5):
from shogun.Features import RealFeatures, MulticlassLabels
from shogun.Classifier import LibLinear, L2R_L2LOSS_SVC, LinearMulticlassMachine, MulticlassOneVsOneStrategy, MulticlassOneVsRestStrategy
feats_train = RealFeatures(fm_train_real)
feats_test = RealFeatures(fm_test_real)
labels = MulticlassLabels(label_train_multiclass)
classifier = LibLinear(L2R_L2LOSS_SVC)
classifier.set_epsilon(epsilon)
classifier.set_bias_enabled(True)
mc_classifier = LinearMulticlassMachine(MulticlassOneVsOneStrategy(),
feats_train, classifier, labels)
mc_classifier.train()
label_pred = mc_classifier.apply()
out = label_pred.get_labels()
if label_test_multiclass is not None:
from shogun.Evaluation import MulticlassAccuracy
labels_test = MulticlassLabels(label_test_multiclass)
evaluator = MulticlassAccuracy()
acc = evaluator.evaluate(label_pred, labels_test)
print('Accuracy = %.4f' % acc)
return out
def classifier_multiclasslinearmachine_modular (fm_train_real=traindat,fm_test_real=testdat,label_train_multiclass=label_traindat,width=2.1,C=1,epsilon=1e-5):
from shogun.Features import RealFeatures, Labels
from shogun.Classifier import LibLinear, L2R_L2LOSS_SVC, LinearMulticlassMachine
from shogun.Classifier import ECOCStrategy, ECOCOVREncoder, ECOCHDDecoder, MulticlassOneVsRestStrategy
feats_train = RealFeatures(fm_train_real)
feats_test = RealFeatures(fm_test_real)
labels = Labels(label_train_multiclass)
classifier = LibLinear(L2R_L2LOSS_SVC)
classifier.set_epsilon(epsilon)
classifier.set_bias_enabled(True)
mc_classifier = LinearMulticlassMachine(MulticlassOneVsRestStrategy(), feats_train, classifier, labels)
mc_classifier.train()
out_mc = mc_classifier.apply(feats_test).get_labels()
ecoc_strategy = ECOCStrategy(ECOCOVREncoder(), ECOCHDDecoder())
ecoc_classifier = LinearMulticlassMachine(ecoc_strategy, feats_train, classifier, labels)
ecoc_classifier.train()
out_ecoc = ecoc_classifier.apply(feats_test).get_labels()
n_diff = (out_mc != out_ecoc).sum()
if n_diff == 0:
print("Same results for OvR and ECOCOvR")
else:
print("Different results for OvR and ECOCOvR (%d out of %d are different)" % (n_diff, len(out_mc)))
return out_ecoc, out_mc
def classifier_multiclasslinearmachine_modular (fm_train_real=traindat,fm_test_real=testdat,label_train_multiclass=label_traindat,label_test_multiclass=label_testdat,width=2.1,C=1,epsilon=1e-5):
from shogun.Features import RealFeatures, MulticlassLabels
from shogun.Classifier import LibLinear, L2R_L2LOSS_SVC, LinearMulticlassMachine, MulticlassOneVsOneStrategy, MulticlassOneVsRestStrategy
feats_train = RealFeatures(fm_train_real)
feats_test = RealFeatures(fm_test_real)
labels = MulticlassLabels(label_train_multiclass)
classifier = LibLinear(L2R_L2LOSS_SVC)
classifier.set_epsilon(epsilon)
classifier.set_bias_enabled(True)
mc_classifier = LinearMulticlassMachine(MulticlassOneVsOneStrategy(), feats_train, classifier, labels)
mc_classifier.train()
label_pred = mc_classifier.apply()
out = label_pred.get_labels()
if label_test_multiclass is not None:
from shogun.Evaluation import MulticlassAccuracy
labels_test = MulticlassLabels(label_test_multiclass)
evaluator = MulticlassAccuracy()
acc = evaluator.evaluate(label_pred, labels_test)
print('Accuracy = %.4f' % acc)
return out
def train_svm(feats_train, labels, C=1):
from shogun.Classifier import LibLinear, L2R_L2LOSS_SVC, L2R_L2LOSS_SVC_DUAL
epsilon = 1e-3
svm = LibLinear(C, feats_train, labels)
svm.set_liblinear_solver_type(L2R_L2LOSS_SVC)
svm.set_epsilon(epsilon)
svm.set_bias_enabled(False)
svm.train()
return svm
def train_svm(feats_train, labels, C=1): from shogun.Classifier import LibLinear, L2R_L2LOSS_SVC, L2R_L2LOSS_SVC_DUAL epsilon = 1e-3 svm = LibLinear(C, feats_train, labels) svm.set_liblinear_solver_type(L2R_L2LOSS_SVC) svm.set_epsilon(epsilon) svm.set_bias_enabled(False) svm.train() return svm
def classifier_multiclass_ecoc_ovr(fm_train_real=traindat,
fm_test_real=testdat,
label_train_multiclass=label_traindat,
label_test_multiclass=label_testdat,
lawidth=2.1,
C=1,
epsilon=1e-5):
from shogun.Features import RealFeatures, MulticlassLabels
from shogun.Classifier import LibLinear, L2R_L2LOSS_SVC, LinearMulticlassMachine
from shogun.Classifier import ECOCStrategy, ECOCOVREncoder, ECOCLLBDecoder, MulticlassOneVsRestStrategy
feats_train = RealFeatures(fm_train_real)
feats_test = RealFeatures(fm_test_real)
labels = MulticlassLabels(label_train_multiclass)
classifier = LibLinear(L2R_L2LOSS_SVC)
classifier.set_epsilon(epsilon)
classifier.set_bias_enabled(True)
mc_classifier = LinearMulticlassMachine(MulticlassOneVsRestStrategy(),
feats_train, classifier, labels)
mc_classifier.train()
label_mc = mc_classifier.apply(feats_test)
out_mc = label_mc.get_labels()
ecoc_strategy = ECOCStrategy(ECOCOVREncoder(), ECOCLLBDecoder())
ecoc_classifier = LinearMulticlassMachine(ecoc_strategy, feats_train,
classifier, labels)
ecoc_classifier.train()
label_ecoc = ecoc_classifier.apply(feats_test)
out_ecoc = label_ecoc.get_labels()
n_diff = (out_mc != out_ecoc).sum()
if n_diff == 0:
print("Same results for OvR and ECOCOvR")
else:
print(
"Different results for OvR and ECOCOvR (%d out of %d are different)"
% (n_diff, len(out_mc)))
if label_test_multiclass is not None:
from shogun.Evaluation import MulticlassAccuracy
labels_test = MulticlassLabels(label_test_multiclass)
evaluator = MulticlassAccuracy()
acc_mc = evaluator.evaluate(label_mc, labels_test)
acc_ecoc = evaluator.evaluate(label_ecoc, labels_test)
print('Normal OVR Accuracy = %.4f' % acc_mc)
print('ECOC OVR Accuracy = %.4f' % acc_ecoc)
return out_ecoc, out_mc
def classifier_multiclass_ecoc_random(fm_train_real=traindat,
fm_test_real=testdat,
label_train_multiclass=label_traindat,
label_test_multiclass=label_testdat,
lawidth=2.1,
C=1,
epsilon=1e-5):
from shogun.Features import RealFeatures, MulticlassLabels
from shogun.Classifier import LibLinear, L2R_L2LOSS_SVC, LinearMulticlassMachine
from shogun.Classifier import ECOCStrategy, ECOCRandomSparseEncoder, ECOCRandomDenseEncoder, ECOCHDDecoder
feats_train = RealFeatures(fm_train_real)
feats_test = RealFeatures(fm_test_real)
labels = MulticlassLabels(label_train_multiclass)
classifier = LibLinear(L2R_L2LOSS_SVC)
classifier.set_epsilon(epsilon)
classifier.set_bias_enabled(True)
rnd_dense_strategy = ECOCStrategy(ECOCRandomDenseEncoder(),
ECOCHDDecoder())
rnd_sparse_strategy = ECOCStrategy(ECOCRandomSparseEncoder(),
ECOCHDDecoder())
dense_classifier = LinearMulticlassMachine(rnd_dense_strategy, feats_train,
classifier, labels)
dense_classifier.train()
label_dense = dense_classifier.apply(feats_test)
out_dense = label_dense.get_labels()
sparse_classifier = LinearMulticlassMachine(rnd_sparse_strategy,
feats_train, classifier,
labels)
sparse_classifier.train()
label_sparse = sparse_classifier.apply(feats_test)
out_sparse = label_sparse.get_labels()
if label_test_multiclass is not None:
from shogun.Evaluation import MulticlassAccuracy
labels_test = MulticlassLabels(label_test_multiclass)
evaluator = MulticlassAccuracy()
acc_dense = evaluator.evaluate(label_dense, labels_test)
acc_sparse = evaluator.evaluate(label_sparse, labels_test)
print('Random Dense Accuracy = %.4f' % acc_dense)
print('Random Sparse Accuracy = %.4f' % acc_sparse)
return out_sparse, out_dense
def classifier_multiclasslinearmachine_modular (fm_train_real=traindat,fm_test_real=testdat,label_train_multiclass=label_traindat,width=2.1,C=1,epsilon=1e-5): from shogun.Features import RealFeatures, Labels from shogun.Classifier import LibLinear, L2R_L2LOSS_SVC, LinearMulticlassMachine, ONE_VS_REST_STRATEGY, ONE_VS_ONE_STRATEGY feats_train = RealFeatures(fm_train_real) feats_test = RealFeatures(fm_test_real) labels = Labels(label_train_multiclass) classifier = LibLinear(L2R_L2LOSS_SVC) classifier.set_epsilon(epsilon) classifier.set_bias_enabled(True) mc_classifier = LinearMulticlassMachine(ONE_VS_ONE_STRATEGY, feats_train, classifier, labels) mc_classifier.train() out = mc_classifier.apply().get_labels() return out
def features_director_dot_modular (fm_train_real, fm_test_real, label_train_twoclass, C, epsilon): from shogun.Features import RealFeatures, SparseRealFeatures, BinaryLabels from shogun.Classifier import LibLinear, L2R_L2LOSS_SVC_DUAL from shogun.Mathematics import Math_init_random Math_init_random(17) feats_train=RealFeatures(fm_train_real) feats_test=RealFeatures(fm_test_real) labels=BinaryLabels(label_train_twoclass) dfeats_train=NumpyFeatures(fm_train_real) dfeats_test=NumpyFeatures(fm_test_real) dlabels=BinaryLabels(label_train_twoclass) print feats_train.get_computed_dot_feature_matrix() print dfeats_train.get_computed_dot_feature_matrix() svm=LibLinear(C, feats_train, labels) svm.set_liblinear_solver_type(L2R_L2LOSS_SVC_DUAL) svm.set_epsilon(epsilon) svm.set_bias_enabled(True) svm.train() svm.set_features(feats_test) svm.apply().get_labels() predictions = svm.apply() dfeats_train.__disown__() dfeats_train.parallel.set_num_threads(1) dsvm=LibLinear(C, dfeats_train, dlabels) dsvm.set_liblinear_solver_type(L2R_L2LOSS_SVC_DUAL) dsvm.set_epsilon(epsilon) dsvm.set_bias_enabled(True) dsvm.train() dfeats_test.__disown__() dfeats_test.parallel.set_num_threads(1) dsvm.set_features(dfeats_test) dsvm.apply().get_labels() dpredictions = dsvm.apply() return predictions, svm, predictions.get_labels()
def features_director_dot_modular(fm_train_real, fm_test_real,
label_train_twoclass, C, epsilon):
from shogun.Features import RealFeatures, SparseRealFeatures, BinaryLabels
from shogun.Classifier import LibLinear, L2R_L2LOSS_SVC_DUAL
from shogun.Mathematics import Math_init_random
Math_init_random(17)
feats_train = RealFeatures(fm_train_real)
feats_test = RealFeatures(fm_test_real)
labels = BinaryLabels(label_train_twoclass)
dfeats_train = NumpyFeatures(fm_train_real)
dfeats_test = NumpyFeatures(fm_test_real)
dlabels = BinaryLabels(label_train_twoclass)
print feats_train.get_computed_dot_feature_matrix()
print dfeats_train.get_computed_dot_feature_matrix()
svm = LibLinear(C, feats_train, labels)
svm.set_liblinear_solver_type(L2R_L2LOSS_SVC_DUAL)
svm.set_epsilon(epsilon)
svm.set_bias_enabled(True)
svm.train()
svm.set_features(feats_test)
svm.apply().get_labels()
predictions = svm.apply()
dfeats_train.__disown__()
dfeats_train.parallel.set_num_threads(1)
dsvm = LibLinear(C, dfeats_train, dlabels)
dsvm.set_liblinear_solver_type(L2R_L2LOSS_SVC_DUAL)
dsvm.set_epsilon(epsilon)
dsvm.set_bias_enabled(True)
dsvm.train()
dfeats_test.__disown__()
dfeats_test.parallel.set_num_threads(1)
dsvm.set_features(dfeats_test)
dsvm.apply().get_labels()
dpredictions = dsvm.apply()
return predictions, svm, predictions.get_labels()
def classifier_multiclasslinearmachine_modular(
fm_train_real=traindat,
fm_test_real=testdat,
label_train_multiclass=label_traindat,
label_test_multiclass=label_testdat,
lawidth=2.1,
C=1,
epsilon=1e-5):
from shogun.Features import RealFeatures, MulticlassLabels
from shogun.Classifier import LibLinear, L2R_L2LOSS_SVC, LinearMulticlassMachine
from shogun.Classifier import ECOCStrategy, ECOCDiscriminantEncoder, ECOCHDDecoder
feats_train = RealFeatures(fm_train_real)
feats_test = RealFeatures(fm_test_real)
labels = MulticlassLabels(label_train_multiclass)
classifier = LibLinear(L2R_L2LOSS_SVC)
classifier.set_epsilon(epsilon)
classifier.set_bias_enabled(True)
encoder = ECOCDiscriminantEncoder()
encoder.set_features(feats_train)
encoder.set_labels(labels)
encoder.set_sffs_iterations(50)
strategy = ECOCStrategy(encoder, ECOCHDDecoder())
classifier = LinearMulticlassMachine(strategy, feats_train, classifier,
labels)
classifier.train()
label_pred = classifier.apply(feats_test)
out = label_pred.get_labels()
if label_test_multiclass is not None:
from shogun.Evaluation import MulticlassAccuracy
labels_test = MulticlassLabels(label_test_multiclass)
evaluator = MulticlassAccuracy()
acc = evaluator.evaluate(label_pred, labels_test)
print('Accuracy = %.4f' % acc)
return out
def classifier_multiclass_ecoc_ovr (fm_train_real=traindat,fm_test_real=testdat,label_train_multiclass=label_traindat,label_test_multiclass=label_testdat,lawidth=2.1,C=1,epsilon=1e-5):
from shogun.Features import RealFeatures, MulticlassLabels
from shogun.Classifier import LibLinear, L2R_L2LOSS_SVC, LinearMulticlassMachine
from shogun.Classifier import ECOCStrategy, ECOCOVREncoder, ECOCLLBDecoder, MulticlassOneVsRestStrategy
feats_train = RealFeatures(fm_train_real)
feats_test = RealFeatures(fm_test_real)
labels = MulticlassLabels(label_train_multiclass)
classifier = LibLinear(L2R_L2LOSS_SVC)
classifier.set_epsilon(epsilon)
classifier.set_bias_enabled(True)
mc_classifier = LinearMulticlassMachine(MulticlassOneVsRestStrategy(), feats_train, classifier, labels)
mc_classifier.train()
label_mc = mc_classifier.apply(feats_test)
out_mc = label_mc.get_labels()
ecoc_strategy = ECOCStrategy(ECOCOVREncoder(), ECOCLLBDecoder())
ecoc_classifier = LinearMulticlassMachine(ecoc_strategy, feats_train, classifier, labels)
ecoc_classifier.train()
label_ecoc = ecoc_classifier.apply(feats_test)
out_ecoc = label_ecoc.get_labels()
n_diff = (out_mc != out_ecoc).sum()
if n_diff == 0:
print("Same results for OvR and ECOCOvR")
else:
print("Different results for OvR and ECOCOvR (%d out of %d are different)" % (n_diff, len(out_mc)))
if label_test_multiclass is not None:
from shogun.Evaluation import MulticlassAccuracy
labels_test = MulticlassLabels(label_test_multiclass)
evaluator = MulticlassAccuracy()
acc_mc = evaluator.evaluate(label_mc, labels_test)
acc_ecoc = evaluator.evaluate(label_ecoc, labels_test)
print('Normal OVR Accuracy = %.4f' % acc_mc)
print('ECOC OVR Accuracy = %.4f' % acc_ecoc)
return out_ecoc, out_mc
def classifier_liblinear_modular(fm_train_real, fm_test_real, label_train_twoclass, C, epsilon):
from shogun.Features import RealFeatures, SparseRealFeatures, Labels
from shogun.Classifier import LibLinear, L2R_L2LOSS_SVC_DUAL
from shogun.Mathematics import Math_init_random
Math_init_random(17)
feats_train = RealFeatures(fm_train_real)
feats_test = RealFeatures(fm_test_real)
labels = Labels(label_train_twoclass)
svm = LibLinear(C, feats_train, labels)
svm.set_liblinear_solver_type(L2R_L2LOSS_SVC_DUAL)
svm.set_epsilon(epsilon)
svm.set_bias_enabled(True)
svm.train()
svm.set_features(feats_test)
svm.apply().get_labels()
predictions = svm.apply()
return predictions, svm, predictions.get_labels()
def classifier_liblinear_modular(fm_train_real, fm_test_real,
label_train_twoclass, C, epsilon):
from shogun.Features import RealFeatures, SparseRealFeatures, Labels
from shogun.Classifier import LibLinear, L2R_L2LOSS_SVC_DUAL
from shogun.Mathematics import Math_init_random
Math_init_random(17)
feats_train = RealFeatures(fm_train_real)
feats_test = RealFeatures(fm_test_real)
labels = Labels(label_train_twoclass)
svm = LibLinear(C, feats_train, labels)
svm.set_liblinear_solver_type(L2R_L2LOSS_SVC_DUAL)
svm.set_epsilon(epsilon)
svm.set_bias_enabled(True)
svm.train()
svm.set_features(feats_test)
svm.apply().get_labels()
predictions = svm.apply()
return predictions, svm, predictions.get_labels()
def classifier_multiclasslinearmachine_modular(
fm_train_real=traindat,
fm_test_real=testdat,
label_train_multiclass=label_traindat,
width=2.1,
C=1,
epsilon=1e-5):
from shogun.Features import RealFeatures, Labels
from shogun.Classifier import LibLinear, L2R_L2LOSS_SVC, LinearMulticlassMachine
from shogun.Classifier import ECOCStrategy, ECOCRandomSparseEncoder, ECOCRandomDenseEncoder, ECOCHDDecoder
feats_train = RealFeatures(fm_train_real)
feats_test = RealFeatures(fm_test_real)
labels = Labels(label_train_multiclass)
classifier = LibLinear(L2R_L2LOSS_SVC)
classifier.set_epsilon(epsilon)
classifier.set_bias_enabled(True)
rnd_dense_strategy = ECOCStrategy(ECOCRandomDenseEncoder(),
ECOCHDDecoder())
rnd_sparse_strategy = ECOCStrategy(ECOCRandomSparseEncoder(),
ECOCHDDecoder())
dense_classifier = LinearMulticlassMachine(rnd_dense_strategy, feats_train,
classifier, labels)
dense_classifier.train()
out_dense = dense_classifier.apply(feats_test).get_labels()
sparse_classifier = LinearMulticlassMachine(rnd_sparse_strategy,
feats_train, classifier,
labels)
sparse_classifier.train()
out_sparse = sparse_classifier.apply(feats_test).get_labels()
return out_sparse, out_dense
def classifier_multiclasslinearmachine_modular (fm_train_real=traindat,fm_test_real=testdat,label_train_multiclass=label_traindat,label_test_multiclass=label_testdat,lawidth=2.1,C=1,epsilon=1e-5):
from shogun.Features import RealFeatures, MulticlassLabels
from shogun.Classifier import LibLinear, L2R_L2LOSS_SVC, LinearMulticlassMachine
from shogun.Classifier import ECOCStrategy, ECOCRandomSparseEncoder, ECOCRandomDenseEncoder, ECOCHDDecoder
feats_train = RealFeatures(fm_train_real)
feats_test = RealFeatures(fm_test_real)
labels = MulticlassLabels(label_train_multiclass)
classifier = LibLinear(L2R_L2LOSS_SVC)
classifier.set_epsilon(epsilon)
classifier.set_bias_enabled(True)
rnd_dense_strategy = ECOCStrategy(ECOCRandomDenseEncoder(), ECOCHDDecoder())
rnd_sparse_strategy = ECOCStrategy(ECOCRandomSparseEncoder(), ECOCHDDecoder())
dense_classifier = LinearMulticlassMachine(rnd_dense_strategy, feats_train, classifier, labels)
dense_classifier.train()
label_dense = dense_classifier.apply(feats_test)
out_dense = label_dense.get_labels()
sparse_classifier = LinearMulticlassMachine(rnd_sparse_strategy, feats_train, classifier, labels)
sparse_classifier.train()
label_sparse = sparse_classifier.apply(feats_test)
out_sparse = label_sparse.get_labels()
if label_test_multiclass is not None:
from shogun.Evaluation import MulticlassAccuracy
labels_test = MulticlassLabels(label_test_multiclass)
evaluator = MulticlassAccuracy()
acc_dense = evaluator.evaluate(label_dense, labels_test)
acc_sparse = evaluator.evaluate(label_sparse, labels_test)
print('Random Dense Accuracy = %.4f' % acc_dense)
print('Random Sparse Accuracy = %.4f' % acc_sparse)
return out_sparse, out_dense
def classifier_multiclasslinearmachine_modular(
fm_train_real=traindat,
fm_test_real=testdat,
label_train_multiclass=label_traindat,
width=2.1,
C=1,
epsilon=1e-5):
from shogun.Features import RealFeatures, MulticlassLabels
from shogun.Classifier import LibLinear, L2R_L2LOSS_SVC, LinearMulticlassMachine, MulticlassOneVsOneStrategy, MulticlassOneVsRestStrategy
feats_train = RealFeatures(fm_train_real)
feats_test = RealFeatures(fm_test_real)
labels = MulticlassLabels(label_train_multiclass)
classifier = LibLinear(L2R_L2LOSS_SVC)
classifier.set_epsilon(epsilon)
classifier.set_bias_enabled(True)
mc_classifier = LinearMulticlassMachine(MulticlassOneVsOneStrategy(),
feats_train, classifier, labels)
mc_classifier.train()
out = mc_classifier.apply().get_labels()
return out
def classifier_non_separable_svm(n=100, m=10, distance=5, seed=None):
'''
n is the number of examples per class and m is the number of examples per class that gets its
label swapped to force non-linear separability
'''
from shogun.Features import RealFeatures, BinaryLabels
from shogun.Classifier import LibLinear, L2R_L2LOSS_SVC
# 2D data
_DIM = 2
# To get the nice message that the perceptron has converged
dummy = BinaryLabels()
np.random.seed(seed)
# Produce some (probably) linearly separable training data by hand
# Two Gaussians at a far enough distance
X = np.array(np.random.randn(_DIM, n)) + distance
Y = np.array(np.random.randn(_DIM, n))
# The last five points of each class are swapped to force non-linear separable data
label_train_twoclass = np.hstack(
(np.ones(n - m), -np.ones(m), -np.ones(n - m), np.ones(m)))
fm_train_real = np.hstack((X, Y))
feats_train = RealFeatures(fm_train_real)
labels = BinaryLabels(label_train_twoclass)
# Train linear SVM
C = 1
epsilon = 1e-3
svm = LibLinear(C, feats_train, labels)
svm.set_liblinear_solver_type(L2R_L2LOSS_SVC)
svm.set_epsilon(epsilon)
svm.set_bias_enabled(True)
svm.train()
# Get hyperplane parameters
b = svm.get_bias()
w = svm.get_w()
# Find limits for visualization
x_min = min(np.min(X[0, :]), np.min(Y[0, :]))
x_max = max(np.max(X[0, :]), np.max(Y[0, :]))
y_min = min(np.min(X[1, :]), np.min(Y[1, :]))
y_max = max(np.max(X[1, :]), np.max(Y[1, :]))
hx = np.linspace(x_min - 1, x_max + 1)
hy = -w[1] / w[0] * hx
plt.plot(hx, -1 / w[1] * (w[0] * hx + b), 'k', linewidth=2.0)
# Plot the two-class data
pos_idxs = label_train_twoclass == +1
plt.scatter(fm_train_real[0, pos_idxs],
fm_train_real[1, pos_idxs],
s=40,
marker='o',
facecolors='none',
edgecolors='b')
neg_idxs = label_train_twoclass == -1
plt.scatter(fm_train_real[0, neg_idxs],
fm_train_real[1, neg_idxs],
s=40,
marker='s',
facecolors='none',
edgecolors='r')
# Customize the plot
plt.axis([x_min - 1, x_max + 1, y_min - 1, y_max + 1])
plt.title('SVM with non-linearly separable data')
plt.xlabel('x')
plt.ylabel('y')
plt.show()
return svm
def classifier_perceptron_graphical(n=100, distance=5, learn_rate=1., max_iter=1000, num_threads=1, seed=None, nperceptrons=5):
from shogun.Features import RealFeatures, BinaryLabels
from shogun.Classifier import Perceptron, LibLinear, L2R_L2LOSS_SVC
from modshogun import MSG_INFO
# 2D data
_DIM = 2
# To get the nice message that the perceptron has converged
dummy = BinaryLabels()
# dummy.io.set_loglevel(MSG_INFO)
np.random.seed(seed)
# Produce some (probably) linearly separable training data by hand
# Two Gaussians at a far enough distance
X = np.array(np.random.randn(_DIM,n))+distance
Y = np.array(np.random.randn(_DIM,n))
label_train_twoclass = np.hstack((np.ones(n), -np.ones(n)))
fm_train_real = np.hstack((X,Y))
feats_train = RealFeatures(fm_train_real)
labels = BinaryLabels(label_train_twoclass)
perceptron = Perceptron(feats_train, labels)
perceptron.set_learn_rate(learn_rate)
perceptron.set_max_iter(max_iter)
perceptron.set_initialize_hyperplane(False)
# Find limits for visualization
x_min = min(np.min(X[0,:]), np.min(Y[0,:]))
x_max = max(np.max(X[0,:]), np.max(Y[0,:]))
y_min = min(np.min(X[1,:]), np.min(Y[1,:]))
y_max = max(np.max(X[1,:]), np.max(Y[1,:]))
fig1, axes1 = plt.subplots(1,1)
fig2, axes2 = plt.subplots(1,1)
for i in xrange(nperceptrons):
# Initialize randomly weight vector and bias
perceptron.set_w(np.random.random(2))
perceptron.set_bias(np.random.random())
# Run the perceptron algorithm
perceptron.train()
# Construct the hyperplane for visualization
# Equation of the decision boundary is w^T x + b = 0
b = perceptron.get_bias()
w = perceptron.get_w()
hx = np.linspace(x_min-1,x_max+1)
hy = -w[1]/w[0] * hx
axes1.plot(hx, -1/w[1]*(w[0]*hx+b))
axes2.plot(hx, -1/w[1]*(w[0]*hx+b), alpha=0.5)
print('minimum distance with perceptron is %f' % min_distance(w, b, feats_train))
C = 1
epsilon = 1e-3
svm = LibLinear(C, feats_train, labels)
svm.set_liblinear_solver_type(L2R_L2LOSS_SVC)
svm.set_epsilon(epsilon)
svm.set_bias_enabled(True)
svm.train()
b = svm.get_bias()
w = svm.get_w()
print('minimum distance with svm is %f' % min_distance(w, b, feats_train))
hx = np.linspace(x_min-1,x_max+1)
hy = -w[1]/w[0] * hx
axes2.plot(hx, -1/w[1]*(w[0]*hx+b), 'k', linewidth=2.0)
# Plot the two-class data
axes1.scatter(X[0,:], X[1,:], s=40, marker='o', facecolors='none', edgecolors='b')
axes1.scatter(Y[0,:], Y[1,:], s=40, marker='s', facecolors='none', edgecolors='r')
axes2.scatter(X[0,:], X[1,:], s=40, marker='o', facecolors='none', edgecolors='b')
axes2.scatter(Y[0,:], Y[1,:], s=40, marker='s', facecolors='none', edgecolors='r')
# Customize the plot
axes1.axis([x_min-1, x_max+1, y_min-1, y_max+1])
axes1.set_title('Rosenblatt\'s Perceptron Algorithm')
axes1.set_xlabel('x')
axes1.set_ylabel('y')
axes2.axis([x_min-1, x_max+1, y_min-1, y_max+1])
axes2.set_title('Support Vector Machine')
axes2.set_xlabel('x')
axes2.set_ylabel('y')
plt.show()
return perceptron
def features_director_dot_modular (fm_train_real, fm_test_real, label_train_twoclass, C, epsilon): try: from shogun.Features import DirectorDotFeatures from shogun.Library import RealVector except ImportError: print "recompile shogun with --enable-swig-directors" return class NumpyFeatures(DirectorDotFeatures): # variables data=numpy.empty((1,1)) # constructor def __init__(self, d): DirectorDotFeatures.__init__(self) self.data = d # overloaded methods def add_to_dense_sgvec(self, alpha, vec_idx1, vec2, abs): if abs: vec2+=alpha*numpy.abs(self.data[:,vec_idx1]) else: vec2+=alpha*self.data[:,vec_idx1] def dot(self, vec_idx1, df, vec_idx2): return numpy.dot(self.data[:,vec_idx1], df.get_computed_dot_feature_vector(vec_idx2)) def dense_dot_sgvec(self, vec_idx1, vec2): return numpy.dot(self.data[:,vec_idx1], vec2[0:vec2.vlen]) def get_num_vectors(self): return self.data.shape[1] def get_dim_feature_space(self): return self.data.shape[0] # operators # def __add__(self, other): # return NumpyFeatures(self.data+other.data) # def __sub__(self, other): # return NumpyFeatures(self.data-other.data) # def __iadd__(self, other): # return NumpyFeatures(self.data+other.data) # def __isub__(self, other): # return NumpyFeatures(self.data-other.data) from shogun.Features import RealFeatures, SparseRealFeatures, BinaryLabels from shogun.Classifier import LibLinear, L2R_L2LOSS_SVC_DUAL from shogun.Mathematics import Math_init_random Math_init_random(17) feats_train=RealFeatures(fm_train_real) feats_test=RealFeatures(fm_test_real) labels=BinaryLabels(label_train_twoclass) dfeats_train=NumpyFeatures(fm_train_real) dfeats_test=NumpyFeatures(fm_test_real) dlabels=BinaryLabels(label_train_twoclass) print feats_train.get_computed_dot_feature_matrix() print dfeats_train.get_computed_dot_feature_matrix() svm=LibLinear(C, feats_train, labels) svm.set_liblinear_solver_type(L2R_L2LOSS_SVC_DUAL) svm.set_epsilon(epsilon) svm.set_bias_enabled(True) svm.train() svm.set_features(feats_test) svm.apply().get_labels() predictions = svm.apply() dfeats_train.__disown__() dfeats_train.parallel.set_num_threads(1) dsvm=LibLinear(C, dfeats_train, dlabels) dsvm.set_liblinear_solver_type(L2R_L2LOSS_SVC_DUAL) dsvm.set_epsilon(epsilon) dsvm.set_bias_enabled(True) dsvm.train() dfeats_test.__disown__() dfeats_test.parallel.set_num_threads(1) dsvm.set_features(dfeats_test) dsvm.apply().get_labels() dpredictions = dsvm.apply() return predictions, svm, predictions.get_labels()
def SVMLinear(traindata, trainlabs, testdata, C=1.0, eps=1e-5, threads=1, getw=False, useLibLinear=False, useL1R=False):
"""
Does efficient linear SVM using the OCAS subgradient solver (as interfaced
by shogun). Handles multiclass problems using a one-versus-all approach.
NOTE: the training and testing data should both be scaled such that each
dimension ranges from 0 to 1
traindata = n by d training data array
trainlabs = n-length training data label vector (should be normalized
so labels range from 0 to c-1, where c is the number of classes)
testdata = m by d array of data to test
C = SVM regularization constant
eps = precision parameter used by OCAS
threads = number of threads to use
getw = whether or not to return the learned weight vector from the SVM (note:
only works for 2-class problems)
returns:
m-length vector containing the predicted labels of the instances
in testdata
if problem is 2-class and getw == True, then a d-length weight vector is also returned
"""
numc = trainlabs.max() + 1
#
# when using an L1 solver, we need the data transposed
#
# trainfeats = wrapFeatures(traindata, sparse=True)
# testfeats = wrapFeatures(testdata, sparse=True)
if not useL1R:
### traindata directly here for LR2_L2LOSS_SVC
trainfeats = wrapFeatures(traindata, sparse=False)
else:
### traindata.T here for L1R_LR
trainfeats = wrapFeatures(traindata.T, sparse=False)
testfeats = wrapFeatures(testdata, sparse=False)
if numc > 2:
preds = np.zeros(testdata.shape[0], dtype=np.int32)
predprobs = np.zeros(testdata.shape[0])
predprobs[:] = -np.inf
for i in xrange(numc):
# set up svm
tlabs = np.int32(trainlabs == i)
tlabs[tlabs == 0] = -1
# print tlabs
# print i, ' ', np.sum(tlabs==-1), ' ', np.sum(tlabs==1)
labels = BinaryLabels(np.float64(tlabs))
if useLibLinear:
# Use LibLinear and set the solver type
svm = LibLinear(C, trainfeats, labels)
if useL1R:
# this is L1 regularization on logistic loss
svm.set_liblinear_solver_type(L1R_LR)
else:
# most of my results were computed with this (ucf50)
svm.set_liblinear_solver_type(L2R_L2LOSS_SVC)
else:
# Or Use SVMOcas
svm = SVMOcas(C, trainfeats, labels)
svm.set_epsilon(eps)
svm.parallel.set_num_threads(threads)
svm.set_bias_enabled(True)
# train
svm.train()
# test
res = svm.apply(testfeats).get_labels()
thisclass = res > predprobs
preds[thisclass] = i
predprobs[thisclass] = res[thisclass]
return preds
else:
tlabs = trainlabs.copy()
tlabs[tlabs == 0] = -1
labels = Labels(np.float64(tlabs))
svm = SVMOcas(C, trainfeats, labels)
svm.set_epsilon(eps)
svm.parallel.set_num_threads(threads)
svm.set_bias_enabled(True)
# train
svm.train()
# test
res = svm.classify(testfeats).get_labels()
res[res > 0] = 1
res[res <= 0] = 0
if getw == True:
return res, svm.get_w()
else:
return res
